"), set the escape flag to false.
-
- In any case, emit the input character as a character token. Stay
- in the data state.
-
- EOF
- Emit an end-of-file token.
-
- Anything else
- Emit the input character as a character token. Stay in the data
- state.
-
- 8.2.4.2 Character reference data state
-
- (This cannot happen if the content model flag is set to the CDATA
- state.)
-
- Attempt to consume a character reference, with no additional allowed
- character.
-
- If nothing is returned, emit a U+0026 AMPERSAND character token.
-
- Otherwise, emit the character token that was returned.
-
- Finally, switch to the data state.
-
- 8.2.4.3 Tag open state
-
- The behavior of this state depends on the content model flag.
-
- If the content model flag is set to the RCDATA or CDATA states
- Consume the next input character. If it is a U+002F SOLIDUS (/)
- character, switch to the close tag open state. Otherwise, emit a
- U+003C LESS-THAN SIGN character token and reconsume the current
- input character in the data state.
-
- If the content model flag is set to the PCDATA state
- Consume the next input character:
-
- U+0021 EXCLAMATION MARK (!)
- Switch to the markup declaration open state.
-
- U+002F SOLIDUS (/)
- Switch to the close tag open state.
-
- U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL
- LETTER Z
- Create a new start tag token, set its tag name to the
- lowercase version of the input character (add 0x0020 to
- the character's code point), then switch to the tag name
- state. (Don't emit the token yet; further details will be
- filled in before it is emitted.)
-
- U+0061 LATIN SMALL LETTER A through to U+007A LATIN SMALL LETTER Z
- Create a new start tag token, set its tag name to the
- input character, then switch to the tag name state. (Don't
- emit the token yet; further details will be filled in
- before it is emitted.)
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Emit a U+003C LESS-THAN SIGN character token
- and a U+003E GREATER-THAN SIGN character token. Switch to
- the data state.
-
- U+003F QUESTION MARK (?)
- Parse error. Switch to the bogus comment state.
-
- Anything else
- Parse error. Emit a U+003C LESS-THAN SIGN character token
- and reconsume the current input character in the data
- state.
-
- 8.2.4.4 Close tag open state
-
- If the content model flag is set to the RCDATA or CDATA states but no
- start tag token has ever been emitted by this instance of the tokeniser
- (fragment case), or, if the content model flag is set to the RCDATA or
- CDATA states and the next few characters do not match the tag name of
- the last start tag token emitted (compared in an ASCII case-insensitive
- manner), or if they do but they are not immediately followed by one of
- the following characters:
- * U+0009 CHARACTER TABULATION
- * U+000A LINE FEED (LF)
- * U+000C FORM FEED (FF)
- * U+0020 SPACE
- * U+003E GREATER-THAN SIGN (>)
- * U+002F SOLIDUS (/)
- * EOF
-
- ...then emit a U+003C LESS-THAN SIGN character token, a U+002F SOLIDUS
- character token, and switch to the data state to process the next input
- character.
-
- Otherwise, if the content model flag is set to the PCDATA state, or if
- the next few characters do match that tag name, consume the next input
- character:
-
- U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z
- Create a new end tag token, set its tag name to the lowercase
- version of the input character (add 0x0020 to the character's
- code point), then switch to the tag name state. (Don't emit the
- token yet; further details will be filled in before it is
- emitted.)
-
- U+0061 LATIN SMALL LETTER A through to U+007A LATIN SMALL LETTER Z
- Create a new end tag token, set its tag name to the input
- character, then switch to the tag name state. (Don't emit the
- token yet; further details will be filled in before it is
- emitted.)
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Switch to the data state.
-
- EOF
- Parse error. Emit a U+003C LESS-THAN SIGN character token and a
- U+002F SOLIDUS character token. Reconsume the EOF character in
- the data state.
-
- Anything else
- Parse error. Switch to the bogus comment state.
-
- 8.2.4.5 Tag name state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Switch to the before attribute name state.
-
- U+002F SOLIDUS (/)
- Switch to the self-closing start tag state.
-
- U+003E GREATER-THAN SIGN (>)
- Emit the current tag token. Switch to the data state.
-
- U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z
- Append the lowercase version of the current input character (add
- 0x0020 to the character's code point) to the current tag token's
- tag name. Stay in the tag name state.
-
- EOF
- Parse error. Emit the current tag token. Reconsume the EOF
- character in the data state.
-
- Anything else
- Append the current input character to the current tag token's
- tag name. Stay in the tag name state.
-
- 8.2.4.6 Before attribute name state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Stay in the before attribute name state.
-
- U+002F SOLIDUS (/)
- Switch to the self-closing start tag state.
-
- U+003E GREATER-THAN SIGN (>)
- Emit the current tag token. Switch to the data state.
-
- U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z
- Start a new attribute in the current tag token. Set that
- attribute's name to the lowercase version of the current input
- character (add 0x0020 to the character's code point), and its
- value to the empty string. Switch to the attribute name state.
-
- U+0022 QUOTATION MARK (")
- U+0027 APOSTROPHE (')
- U+003D EQUALS SIGN (=)
- Parse error. Treat it as per the "anything else" entry below.
-
- EOF
- Parse error. Emit the current tag token. Reconsume the EOF
- character in the data state.
-
- Anything else
- Start a new attribute in the current tag token. Set that
- attribute's name to the current input character, and its value
- to the empty string. Switch to the attribute name state.
-
- 8.2.4.7 Attribute name state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Switch to the after attribute name state.
-
- U+002F SOLIDUS (/)
- Switch to the self-closing start tag state.
-
- U+003D EQUALS SIGN (=)
- Switch to the before attribute value state.
-
- U+003E GREATER-THAN SIGN (>)
- Emit the current tag token. Switch to the data state.
-
- U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z
- Append the lowercase version of the current input character (add
- 0x0020 to the character's code point) to the current attribute's
- name. Stay in the attribute name state.
-
- U+0022 QUOTATION MARK (")
- U+0027 APOSTROPHE (')
- Parse error. Treat it as per the "anything else" entry below.
-
- EOF
- Parse error. Emit the current tag token. Reconsume the EOF
- character in the data state.
-
- Anything else
- Append the current input character to the current attribute's
- name. Stay in the attribute name state.
-
- When the user agent leaves the attribute name state (and before
- emitting the tag token, if appropriate), the complete attribute's name
- must be compared to the other attributes on the same token; if there is
- already an attribute on the token with the exact same name, then this
- is a parse error and the new attribute must be dropped, along with the
- value that gets associated with it (if any).
-
- 8.2.4.8 After attribute name state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Stay in the after attribute name state.
-
- U+002F SOLIDUS (/)
- Switch to the self-closing start tag state.
-
- U+003D EQUALS SIGN (=)
- Switch to the before attribute value state.
-
- U+003E GREATER-THAN SIGN (>)
- Emit the current tag token. Switch to the data state.
-
- U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z
- Start a new attribute in the current tag token. Set that
- attribute's name to the lowercase version of the current input
- character (add 0x0020 to the character's code point), and its
- value to the empty string. Switch to the attribute name state.
-
- U+0022 QUOTATION MARK (")
- U+0027 APOSTROPHE (')
- Parse error. Treat it as per the "anything else" entry below.
-
- EOF
- Parse error. Emit the current tag token. Reconsume the EOF
- character in the data state.
-
- Anything else
- Start a new attribute in the current tag token. Set that
- attribute's name to the current input character, and its value
- to the empty string. Switch to the attribute name state.
-
- 8.2.4.9 Before attribute value state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Stay in the before attribute value state.
-
- U+0022 QUOTATION MARK (")
- Switch to the attribute value (double-quoted) state.
-
- U+0026 AMPERSAND (&)
- Switch to the attribute value (unquoted) state and reconsume
- this input character.
-
- U+0027 APOSTROPHE (')
- Switch to the attribute value (single-quoted) state.
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Emit the current tag token. Switch to the data
- state.
-
- U+003D EQUALS SIGN (=)
- Parse error. Treat it as per the "anything else" entry below.
-
- EOF
- Parse error. Emit the current tag token. Reconsume the character
- in the data state.
-
- Anything else
- Append the current input character to the current attribute's
- value. Switch to the attribute value (unquoted) state.
-
- 8.2.4.10 Attribute value (double-quoted) state
-
- Consume the next input character:
-
- U+0022 QUOTATION MARK (")
- Switch to the after attribute value (quoted) state.
-
- U+0026 AMPERSAND (&)
- Switch to the character reference in attribute value state, with
- the additional allowed character being U+0022 QUOTATION MARK
- (").
-
- EOF
- Parse error. Emit the current tag token. Reconsume the character
- in the data state.
-
- Anything else
- Append the current input character to the current attribute's
- value. Stay in the attribute value (double-quoted) state.
-
- 8.2.4.11 Attribute value (single-quoted) state
-
- Consume the next input character:
-
- U+0027 APOSTROPHE (')
- Switch to the after attribute value (quoted) state.
-
- U+0026 AMPERSAND (&)
- Switch to the character reference in attribute value state, with
- the additional allowed character being U+0027 APOSTROPHE (').
-
- EOF
- Parse error. Emit the current tag token. Reconsume the character
- in the data state.
-
- Anything else
- Append the current input character to the current attribute's
- value. Stay in the attribute value (single-quoted) state.
-
- 8.2.4.12 Attribute value (unquoted) state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Switch to the before attribute name state.
-
- U+0026 AMPERSAND (&)
- Switch to the character reference in attribute value state, with
- no additional allowed character.
-
- U+003E GREATER-THAN SIGN (>)
- Emit the current tag token. Switch to the data state.
-
- U+0022 QUOTATION MARK (")
- U+0027 APOSTROPHE (')
- U+003D EQUALS SIGN (=)
- Parse error. Treat it as per the "anything else" entry below.
-
- EOF
- Parse error. Emit the current tag token. Reconsume the character
- in the data state.
-
- Anything else
- Append the current input character to the current attribute's
- value. Stay in the attribute value (unquoted) state.
-
- 8.2.4.13 Character reference in attribute value state
-
- Attempt to consume a character reference.
-
- If nothing is returned, append a U+0026 AMPERSAND character to the
- current attribute's value.
-
- Otherwise, append the returned character token to the current
- attribute's value.
-
- Finally, switch back to the attribute value state that you were in when
- were switched into this state.
-
- 8.2.4.14 After attribute value (quoted) state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Switch to the before attribute name state.
-
- U+002F SOLIDUS (/)
- Switch to the self-closing start tag state.
-
- U+003E GREATER-THAN SIGN (>)
- Emit the current tag token. Switch to the data state.
-
- EOF
- Parse error. Emit the current tag token. Reconsume the EOF
- character in the data state.
-
- Anything else
- Parse error. Reconsume the character in the before attribute
- name state.
-
- 8.2.4.15 Self-closing start tag state
-
- Consume the next input character:
-
- U+003E GREATER-THAN SIGN (>)
- Set the self-closing flag of the current tag token. Emit the
- current tag token. Switch to the data state.
-
- EOF
- Parse error. Emit the current tag token. Reconsume the EOF
- character in the data state.
-
- Anything else
- Parse error. Reconsume the character in the before attribute
- name state.
-
- 8.2.4.16 Bogus comment state
-
- (This can only happen if the content model flag is set to the PCDATA
- state.)
-
- Consume every character up to and including the first U+003E
- GREATER-THAN SIGN character (>) or the end of the file (EOF), whichever
- comes first. Emit a comment token whose data is the concatenation of
- all the characters starting from and including the character that
- caused the state machine to switch into the bogus comment state, up to
- and including the character immediately before the last consumed
- character (i.e. up to the character just before the U+003E or EOF
- character). (If the comment was started by the end of the file (EOF),
- the token is empty.)
-
- Switch to the data state.
-
- If the end of the file was reached, reconsume the EOF character.
-
- 8.2.4.17 Markup declaration open state
-
- (This can only happen if the content model flag is set to the PCDATA
- state.)
-
- If the next two characters are both U+002D HYPHEN-MINUS (-) characters,
- consume those two characters, create a comment token whose data is the
- empty string, and switch to the comment start state.
-
- Otherwise, if the next seven characters are an ASCII case-insensitive
- match for the word "DOCTYPE", then consume those characters and switch
- to the DOCTYPE state.
-
- Otherwise, if the insertion mode is "in foreign content" and the
- current node is not an element in the HTML namespace and the next seven
- characters are an ASCII case-sensitive match for the string "[CDATA["
- (the five uppercase letters "CDATA" with a U+005B LEFT SQUARE BRACKET
- character before and after), then consume those characters and switch
- to the CDATA section state (which is unrelated to the content model
- flag's CDATA state).
-
- Otherwise, this is a parse error. Switch to the bogus comment state.
- The next character that is consumed, if any, is the first character
- that will be in the comment.
-
- 8.2.4.18 Comment start state
-
- Consume the next input character:
-
- U+002D HYPHEN-MINUS (-)
- Switch to the comment start dash state.
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Emit the comment token. Switch to the data state.
-
- EOF
- Parse error. Emit the comment token. Reconsume the EOF character
- in the data state.
-
- Anything else
- Append the input character to the comment token's data. Switch
- to the comment state.
-
- 8.2.4.19 Comment start dash state
-
- Consume the next input character:
-
- U+002D HYPHEN-MINUS (-)
- Switch to the comment end state
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Emit the comment token. Switch to the data state.
-
- EOF
- Parse error. Emit the comment token. Reconsume the EOF character
- in the data state.
-
- Anything else
- Append a U+002D HYPHEN-MINUS (-) character and the input
- character to the comment token's data. Switch to the comment
- state.
-
- 8.2.4.20 Comment state
-
- Consume the next input character:
-
- U+002D HYPHEN-MINUS (-)
- Switch to the comment end dash state
-
- EOF
- Parse error. Emit the comment token. Reconsume the EOF character
- in the data state.
-
- Anything else
- Append the input character to the comment token's data. Stay in
- the comment state.
-
- 8.2.4.21 Comment end dash state
-
- Consume the next input character:
-
- U+002D HYPHEN-MINUS (-)
- Switch to the comment end state
-
- EOF
- Parse error. Emit the comment token. Reconsume the EOF character
- in the data state.
-
- Anything else
- Append a U+002D HYPHEN-MINUS (-) character and the input
- character to the comment token's data. Switch to the comment
- state.
-
- 8.2.4.22 Comment end state
-
- Consume the next input character:
-
- U+003E GREATER-THAN SIGN (>)
- Emit the comment token. Switch to the data state.
-
- U+002D HYPHEN-MINUS (-)
- Parse error. Append a U+002D HYPHEN-MINUS (-) character to the
- comment token's data. Stay in the comment end state.
-
- EOF
- Parse error. Emit the comment token. Reconsume the EOF character
- in the data state.
-
- Anything else
- Parse error. Append two U+002D HYPHEN-MINUS (-) characters and
- the input character to the comment token's data. Switch to the
- comment state.
-
- 8.2.4.23 DOCTYPE state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Switch to the before DOCTYPE name state.
-
- Anything else
- Parse error. Reconsume the current character in the before
- DOCTYPE name state.
-
- 8.2.4.24 Before DOCTYPE name state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Stay in the before DOCTYPE name state.
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Create a new DOCTYPE token. Set its force-quirks
- flag to on. Emit the token. Switch to the data state.
-
- U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z
- Create a new DOCTYPE token. Set the token's name to the
- lowercase version of the input character (add 0x0020 to the
- character's code point). Switch to the DOCTYPE name state.
-
- EOF
- Parse error. Create a new DOCTYPE token. Set its force-quirks
- flag to on. Emit the token. Reconsume the EOF character in the
- data state.
-
- Anything else
- Create a new DOCTYPE token. Set the token's name to the current
- input character. Switch to the DOCTYPE name state.
-
- 8.2.4.25 DOCTYPE name state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Switch to the after DOCTYPE name state.
-
- U+003E GREATER-THAN SIGN (>)
- Emit the current DOCTYPE token. Switch to the data state.
-
- U+0041 LATIN CAPITAL LETTER A through to U+005A LATIN CAPITAL LETTER Z
- Append the lowercase version of the input character (add 0x0020
- to the character's code point) to the current DOCTYPE token's
- name. Stay in the DOCTYPE name state.
-
- EOF
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- Append the current input character to the current DOCTYPE
- token's name. Stay in the DOCTYPE name state.
-
- 8.2.4.26 After DOCTYPE name state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Stay in the after DOCTYPE name state.
-
- U+003E GREATER-THAN SIGN (>)
- Emit the current DOCTYPE token. Switch to the data state.
-
- EOF
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- If the six characters starting from the current input character
- are an ASCII case-insensitive match for the word "PUBLIC", then
- consume those characters and switch to the before DOCTYPE public
- identifier state.
-
- Otherwise, if the six characters starting from the current input
- character are an ASCII case-insensitive match for the word
- "SYSTEM", then consume those characters and switch to the before
- DOCTYPE system identifier state.
-
- Otherwise, this is the parse error. Set the DOCTYPE token's
- force-quirks flag to on. Switch to the bogus DOCTYPE state.
-
- 8.2.4.27 Before DOCTYPE public identifier state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Stay in the before DOCTYPE public identifier state.
-
- U+0022 QUOTATION MARK (")
- Set the DOCTYPE token's public identifier to the empty string
- (not missing), then switch to the DOCTYPE public identifier
- (double-quoted) state.
-
- U+0027 APOSTROPHE (')
- Set the DOCTYPE token's public identifier to the empty string
- (not missing), then switch to the DOCTYPE public identifier
- (single-quoted) state.
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Switch to the data state.
-
- EOF
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Switch to the bogus DOCTYPE state.
-
- 8.2.4.28 DOCTYPE public identifier (double-quoted) state
-
- Consume the next input character:
-
- U+0022 QUOTATION MARK (")
- Switch to the after DOCTYPE public identifier state.
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Switch to the data state.
-
- EOF
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- Append the current input character to the current DOCTYPE
- token's public identifier. Stay in the DOCTYPE public identifier
- (double-quoted) state.
-
- 8.2.4.29 DOCTYPE public identifier (single-quoted) state
-
- Consume the next input character:
-
- U+0027 APOSTROPHE (')
- Switch to the after DOCTYPE public identifier state.
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Switch to the data state.
-
- EOF
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- Append the current input character to the current DOCTYPE
- token's public identifier. Stay in the DOCTYPE public identifier
- (single-quoted) state.
-
- 8.2.4.30 After DOCTYPE public identifier state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Stay in the after DOCTYPE public identifier state.
-
- U+0022 QUOTATION MARK (")
- Set the DOCTYPE token's system identifier to the empty string
- (not missing), then switch to the DOCTYPE system identifier
- (double-quoted) state.
-
- U+0027 APOSTROPHE (')
- Set the DOCTYPE token's system identifier to the empty string
- (not missing), then switch to the DOCTYPE system identifier
- (single-quoted) state.
-
- U+003E GREATER-THAN SIGN (>)
- Emit the current DOCTYPE token. Switch to the data state.
-
- EOF
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Switch to the bogus DOCTYPE state.
-
- 8.2.4.31 Before DOCTYPE system identifier state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Stay in the before DOCTYPE system identifier state.
-
- U+0022 QUOTATION MARK (")
- Set the DOCTYPE token's system identifier to the empty string
- (not missing), then switch to the DOCTYPE system identifier
- (double-quoted) state.
-
- U+0027 APOSTROPHE (')
- Set the DOCTYPE token's system identifier to the empty string
- (not missing), then switch to the DOCTYPE system identifier
- (single-quoted) state.
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Switch to the data state.
-
- EOF
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Switch to the bogus DOCTYPE state.
-
- 8.2.4.32 DOCTYPE system identifier (double-quoted) state
-
- Consume the next input character:
-
- U+0022 QUOTATION MARK (")
- Switch to the after DOCTYPE system identifier state.
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Switch to the data state.
-
- EOF
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- Append the current input character to the current DOCTYPE
- token's system identifier. Stay in the DOCTYPE system identifier
- (double-quoted) state.
-
- 8.2.4.33 DOCTYPE system identifier (single-quoted) state
-
- Consume the next input character:
-
- U+0027 APOSTROPHE (')
- Switch to the after DOCTYPE system identifier state.
-
- U+003E GREATER-THAN SIGN (>)
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Switch to the data state.
-
- EOF
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- Append the current input character to the current DOCTYPE
- token's system identifier. Stay in the DOCTYPE system identifier
- (single-quoted) state.
-
- 8.2.4.34 After DOCTYPE system identifier state
-
- Consume the next input character:
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- Stay in the after DOCTYPE system identifier state.
-
- U+003E GREATER-THAN SIGN (>)
- Emit the current DOCTYPE token. Switch to the data state.
-
- EOF
- Parse error. Set the DOCTYPE token's force-quirks flag to on.
- Emit that DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- Parse error. Switch to the bogus DOCTYPE state. (This does not
- set the DOCTYPE token's force-quirks flag to on.)
-
- 8.2.4.35 Bogus DOCTYPE state
-
- Consume the next input character:
-
- U+003E GREATER-THAN SIGN (>)
- Emit the DOCTYPE token. Switch to the data state.
-
- EOF
- Emit the DOCTYPE token. Reconsume the EOF character in the data
- state.
-
- Anything else
- Stay in the bogus DOCTYPE state.
-
- 8.2.4.36 CDATA section state
-
- (This can only happen if the content model flag is set to the PCDATA
- state, and is unrelated to the content model flag's CDATA state.)
-
- Consume every character up to the next occurrence of the three
- character sequence U+005D RIGHT SQUARE BRACKET U+005D RIGHT SQUARE
- BRACKET U+003E GREATER-THAN SIGN (]]>), or the end of the file (EOF),
- whichever comes first. Emit a series of character tokens consisting of
- all the characters consumed except the matching three character
- sequence at the end (if one was found before the end of the file).
-
- Switch to the data state.
-
- If the end of the file was reached, reconsume the EOF character.
-
- 8.2.4.37 Tokenizing character references
-
- This section defines how to consume a character reference. This
- definition is used when parsing character references in text and in
- attributes.
-
- The behavior depends on the identity of the next character (the one
- immediately after the U+0026 AMPERSAND character):
-
- U+0009 CHARACTER TABULATION
- U+000A LINE FEED (LF)
- U+000C FORM FEED (FF)
- U+0020 SPACE
- U+003C LESS-THAN SIGN
- U+0026 AMPERSAND
- EOF
- The additional allowed character, if there is one
- Not a character reference. No characters are consumed, and
- nothing is returned. (This is not an error, either.)
-
- U+0023 NUMBER SIGN (#)
- Consume the U+0023 NUMBER SIGN.
-
- The behavior further depends on the character after the U+0023
- NUMBER SIGN:
-
- U+0078 LATIN SMALL LETTER X
- U+0058 LATIN CAPITAL LETTER X
- Consume the X.
-
- Follow the steps below, but using the range of characters
- U+0030 DIGIT ZERO through to U+0039 DIGIT NINE, U+0061
- LATIN SMALL LETTER A through to U+0066 LATIN SMALL LETTER
- F, and U+0041 LATIN CAPITAL LETTER A, through to U+0046
- LATIN CAPITAL LETTER F (in other words, 0-9, A-F, a-f).
-
- When it comes to interpreting the number, interpret it as
- a hexadecimal number.
-
- Anything else
- Follow the steps below, but using the range of characters
- U+0030 DIGIT ZERO through to U+0039 DIGIT NINE (i.e. just
- 0-9).
-
- When it comes to interpreting the number, interpret it as
- a decimal number.
-
- Consume as many characters as match the range of characters
- given above.
-
- If no characters match the range, then don't consume any
- characters (and unconsume the U+0023 NUMBER SIGN character and,
- if appropriate, the X character). This is a parse error; nothing
- is returned.
-
- Otherwise, if the next character is a U+003B SEMICOLON, consume
- that too. If it isn't, there is a parse error.
-
- If one or more characters match the range, then take them all
- and interpret the string of characters as a number (either
- hexadecimal or decimal as appropriate).
-
- If that number is one of the numbers in the first column of the
- following table, then this is a parse error. Find the row with
- that number in the first column, and return a character token
- for the Unicode character given in the second column of that
- row.
-
- Number Unicode character
- 0x0D U+000A LINE FEED (LF)
- 0x80 U+20AC EURO SIGN ('€')
- 0x81 U+FFFD REPLACEMENT CHARACTER
- 0x82 U+201A SINGLE LOW-9 QUOTATION MARK ('‚')
- 0x83 U+0192 LATIN SMALL LETTER F WITH HOOK ('ƒ')
- 0x84 U+201E DOUBLE LOW-9 QUOTATION MARK ('„')
- 0x85 U+2026 HORIZONTAL ELLIPSIS ('…')
- 0x86 U+2020 DAGGER ('†')
- 0x87 U+2021 DOUBLE DAGGER ('‡')
- 0x88 U+02C6 MODIFIER LETTER CIRCUMFLEX ACCENT ('ˆ')
- 0x89 U+2030 PER MILLE SIGN ('‰')
- 0x8A U+0160 LATIN CAPITAL LETTER S WITH CARON ('Š')
- 0x8B U+2039 SINGLE LEFT-POINTING ANGLE QUOTATION MARK ('‹')
- 0x8C U+0152 LATIN CAPITAL LIGATURE OE ('Œ')
- 0x8D U+FFFD REPLACEMENT CHARACTER
- 0x8E U+017D LATIN CAPITAL LETTER Z WITH CARON ('Ž')
- 0x8F U+FFFD REPLACEMENT CHARACTER
- 0x90 U+FFFD REPLACEMENT CHARACTER
- 0x91 U+2018 LEFT SINGLE QUOTATION MARK ('‘')
- 0x92 U+2019 RIGHT SINGLE QUOTATION MARK ('’')
- 0x93 U+201C LEFT DOUBLE QUOTATION MARK ('“')
- 0x94 U+201D RIGHT DOUBLE QUOTATION MARK ('”')
- 0x95 U+2022 BULLET ('•')
- 0x96 U+2013 EN DASH ('–')
- 0x97 U+2014 EM DASH ('—')
- 0x98 U+02DC SMALL TILDE ('˜')
- 0x99 U+2122 TRADE MARK SIGN ('™')
- 0x9A U+0161 LATIN SMALL LETTER S WITH CARON ('š')
- 0x9B U+203A SINGLE RIGHT-POINTING ANGLE QUOTATION MARK ('›')
- 0x9C U+0153 LATIN SMALL LIGATURE OE ('œ')
- 0x9D U+FFFD REPLACEMENT CHARACTER
- 0x9E U+017E LATIN SMALL LETTER Z WITH CARON ('ž')
- 0x9F U+0178 LATIN CAPITAL LETTER Y WITH DIAERESIS ('Ÿ')
-
- Otherwise, if the number is in the range 0x0000 to 0x0008,
- 0x000E to 0x001F, 0x007F to 0x009F, 0xD800 to 0xDFFF, 0xFDD0 to
- 0xFDEF, or is one of 0x000B, 0xFFFE, 0xFFFF, 0x1FFFE, 0x1FFFF,
- 0x2FFFE, 0x2FFFF, 0x3FFFE, 0x3FFFF, 0x4FFFE, 0x4FFFF, 0x5FFFE,
- 0x5FFFF, 0x6FFFE, 0x6FFFF, 0x7FFFE, 0x7FFFF, 0x8FFFE, 0x8FFFF,
- 0x9FFFE, 0x9FFFF, 0xAFFFE, 0xAFFFF, 0xBFFFE, 0xBFFFF, 0xCFFFE,
- 0xCFFFF, 0xDFFFE, 0xDFFFF, 0xEFFFE, 0xEFFFF, 0xFFFFE, 0xFFFFF,
- 0x10FFFE, or 0x10FFFF, or is higher than 0x10FFFF, then this is
- a parse error; return a character token for the U+FFFD
- REPLACEMENT CHARACTER character instead.
-
- Otherwise, return a character token for the Unicode character
- whose code point is that number.
-
- Anything else
- Consume the maximum number of characters possible, with the
- consumed characters matching one of the identifiers in the first
- column of the named character references table (in a
- case-sensitive manner).
-
- If no match can be made, then this is a parse error. No
- characters are consumed, and nothing is returned.
-
- If the last character matched is not a U+003B SEMICOLON (;),
- there is a parse error.
-
- If the character reference is being consumed as part of an
- attribute, and the last character matched is not a U+003B
- SEMICOLON (;), and the next character is in the range U+0030
- DIGIT ZERO to U+0039 DIGIT NINE, U+0041 LATIN CAPITAL LETTER A
- to U+005A LATIN CAPITAL LETTER Z, or U+0061 LATIN SMALL LETTER A
- to U+007A LATIN SMALL LETTER Z, then, for historical reasons,
- all the characters that were matched after the U+0026 AMPERSAND
- (&) must be unconsumed, and nothing is returned.
-
- Otherwise, return a character token for the character
- corresponding to the character reference name (as given by the
- second column of the named character references table).
-
- If the markup contains I'm ¬it; I tell you, the character
- reference is parsed as "not", as in, I'm ¬it; I tell you. But if
- the markup was I'm ∉ I tell you, the character reference
- would be parsed as "notin;", resulting in I'm ∉ I tell you.
diff --git a/doc/tree-construction.txt b/doc/tree-construction.txt
deleted file mode 100644
index 0febf147..00000000
--- a/doc/tree-construction.txt
+++ /dev/null
@@ -1,2201 +0,0 @@
- #8.2.4 Tokenization Table of contents 8.4 Serializing HTML fragments
-
- WHATWG
-
-HTML 5
-
-Draft Recommendation — 13 January 2009
-
- ← 8.2.4 Tokenization – Table of contents – 8.4 Serializing HTML
- fragments →
-
- 8.2.5 Tree construction
-
- The input to the tree construction stage is a sequence of tokens from
- the tokenization stage. The tree construction stage is associated with
- a DOM Document object when a parser is created. The "output" of this
- stage consists of dynamically modifying or extending that document's
- DOM tree.
-
- This specification does not define when an interactive user agent has
- to render the Document so that it is available to the user, or when it
- has to begin accepting user input.
-
- As each token is emitted from the tokeniser, the user agent must
- process the token according to the rules given in the section
- corresponding to the current insertion mode.
-
- When the steps below require the UA to insert a character into a node,
- if that node has a child immediately before where the character is to
- be inserted, and that child is a Text node, and that Text node was the
- last node that the parser inserted into the document, then the
- character must be appended to that Text node; otherwise, a new Text
- node whose data is just that character must be inserted in the
- appropriate place.
-
- DOM mutation events must not fire for changes caused by the UA parsing
- the document. (Conceptually, the parser is not mutating the DOM, it is
- constructing it.) This includes the parsing of any content inserted
- using document.write() and document.writeln() calls. [DOM3EVENTS]
-
- Not all of the tag names mentioned below are conformant tag names in
- this specification; many are included to handle legacy content. They
- still form part of the algorithm that implementations are required to
- implement to claim conformance.
-
- The algorithm described below places no limit on the depth of the DOM
- tree generated, or on the length of tag names, attribute names,
- attribute values, text nodes, etc. While implementors are encouraged to
- avoid arbitrary limits, it is recognized that practical concerns will
- likely force user agents to impose nesting depths.
-
- 8.2.5.1 Creating and inserting elements
-
- When the steps below require the UA to create an element for a token in
- a particular namespace, the UA must create a node implementing the
- interface appropriate for the element type corresponding to the tag
- name of the token in the given namespace (as given in the specification
- that defines that element, e.g. for an a element in the HTML namespace,
- this specification defines it to be the HTMLAnchorElement interface),
- with the tag name being the name of that element, with the node being
- in the given namespace, and with the attributes on the node being those
- given in the given token.
-
- The interface appropriate for an element in the HTML namespace that is
- not defined in this specification is HTMLElement. The interface
- appropriate for an element in another namespace that is not defined by
- that namespace's specification is Element.
-
- When a resettable element is created in this manner, its reset
- algorithm must be invoked once the attributes are set. (This
- initializes the element's value and checkedness based on the element's
- attributes.)
- __________________________________________________________________
-
- When the steps below require the UA to insert an HTML element for a
- token, the UA must first create an element for the token in the HTML
- namespace, and then append this node to the current node, and push it
- onto the stack of open elements so that it is the new current node.
-
- The steps below may also require that the UA insert an HTML element in
- a particular place, in which case the UA must follow the same steps
- except that it must insert or append the new node in the location
- specified instead of appending it to the current node. (This happens in
- particular during the parsing of tables with invalid content.)
-
- If an element created by the insert an HTML element algorithm is a
- form-associated element, and the form element pointer is not null, and
- the newly created element doesn't have a form attribute, the user agent
- must associate the newly created element with the form element pointed
- to by the form element pointer before inserting it wherever it is to be
- inserted.
- __________________________________________________________________
-
- When the steps below require the UA to insert a foreign element for a
- token, the UA must first create an element for the token in the given
- namespace, and then append this node to the current node, and push it
- onto the stack of open elements so that it is the new current node. If
- the newly created element has an xmlns attribute in the XMLNS namespace
- whose value is not exactly the same as the element's namespace, that is
- a parse error.
-
- When the steps below require the user agent to adjust MathML attributes
- for a token, then, if the token has an attribute named definitionurl,
- change its name to definitionURL (note the case difference).
-
- When the steps below require the user agent to adjust foreign
- attributes for a token, then, if any of the attributes on the token
- match the strings given in the first column of the following table, let
- the attribute be a namespaced attribute, with the prefix being the
- string given in the corresponding cell in the second column, the local
- name being the string given in the corresponding cell in the third
- column, and the namespace being the namespace given in the
- corresponding cell in the fourth column. (This fixes the use of
- namespaced attributes, in particular xml:lang.)
-
- Attribute name Prefix Local name Namespace
- xlink:actuate xlink actuate XLink namespace
- xlink:arcrole xlink arcrole XLink namespace
- xlink:href xlink href XLink namespace
- xlink:role xlink role XLink namespace
- xlink:show xlink show XLink namespace
- xlink:title xlink title XLink namespace
- xlink:type xlink type XLink namespace
- xml:base xml base XML namespace
- xml:lang xml lang XML namespace
- xml:space xml space XML namespace
- xmlns (none) xmlns XMLNS namespace
- xmlns:xlink xmlns xlink XMLNS namespace
- __________________________________________________________________
-
- The generic CDATA element parsing algorithm and the generic RCDATA
- element parsing algorithm consist of the following steps. These
- algorithms are always invoked in response to a start tag token.
- 1. Insert an HTML element for the token.
- 2. If the algorithm that was invoked is the generic CDATA element
- parsing algorithm, switch the tokeniser's content model flag to the
- CDATA state; otherwise the algorithm invoked was the generic RCDATA
- element parsing algorithm, switch the tokeniser's content model
- flag to the RCDATA state.
- 3. Let the original insertion mode be the current insertion mode.
- 4. Then, switch the insertion mode to "in CDATA/RCDATA".
-
- 8.2.5.2 Closing elements that have implied end tags
-
- When the steps below require the UA to generate implied end tags, then,
- while the current node is a dd element, a dt element, an li element, an
- option element, an optgroup element, a p element, an rp element, or an
- rt element, the UA must pop the current node off the stack of open
- elements.
-
- If a step requires the UA to generate implied end tags but lists an
- element to exclude from the process, then the UA must perform the above
- steps as if that element was not in the above list.
-
- 8.2.5.3 Foster parenting
-
- Foster parenting happens when content is misnested in tables.
-
- When a node node is to be foster parented, the node node must be
- inserted into the foster parent element, and the current table must be
- marked as tainted. (Once the current table has been tainted, whitespace
- characters are inserted into the foster parent element instead of the
- current node.)
-
- The foster parent element is the parent element of the last table
- element in the stack of open elements, if there is a table element and
- it has such a parent element. If there is no table element in the stack
- of open elements (fragment case), then the foster parent element is the
- first element in the stack of open elements (the html element).
- Otherwise, if there is a table element in the stack of open elements,
- but the last table element in the stack of open elements has no parent,
- or its parent node is not an element, then the foster parent element is
- the element before the last table element in the stack of open
- elements.
-
- If the foster parent element is the parent element of the last table
- element in the stack of open elements, then node must be inserted
- immediately before the last table element in the stack of open elements
- in the foster parent element; otherwise, node must be appended to the
- foster parent element.
-
- 8.2.5.4 The "initial" insertion mode
-
- When the insertion mode is "initial", tokens must be handled as
- follows:
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
- Ignore the token.
-
- A comment token
- Append a Comment node to the Document object with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- If the DOCTYPE token's name is not a case-sensitive match for
- the string "html", or if the token's public identifier is
- neither missing nor a case-sensitive match for the string
- "XSLT-compat", or if the token's system identifier is not
- missing, then there is a parse error (this is the DOCTYPE parse
- error). Conformance checkers may, instead of reporting this
- error, switch to a conformance checking mode for another
- language (e.g. based on the DOCTYPE token a conformance checker
- could recognize that the document is an HTML4-era document, and
- defer to an HTML4 conformance checker.)
-
- Append a DocumentType node to the Document node, with the name
- attribute set to the name given in the DOCTYPE token; the
- publicId attribute set to the public identifier given in the
- DOCTYPE token, or the empty string if the public identifier was
- missing; the systemId attribute set to the system identifier
- given in the DOCTYPE token, or the empty string if the system
- identifier was missing; and the other attributes specific to
- DocumentType objects set to null and empty lists as appropriate.
- Associate the DocumentType node with the Document object so that
- it is returned as the value of the doctype attribute of the
- Document object.
-
- Then, if the DOCTYPE token matches one of the conditions in the
- following list, then set the document to quirks mode:
-
- + The force-quirks flag is set to on.
- + The name is set to anything other than "HTML".
- + The public identifier starts with: "+//Silmaril//dtd html Pro
- v0r11 19970101//"
- + The public identifier starts with: "-//AdvaSoft Ltd//DTD HTML
- 3.0 asWedit + extensions//"
- + The public identifier starts with: "-//AS//DTD HTML 3.0
- asWedit + extensions//"
- + The public identifier starts with: "-//IETF//DTD HTML 2.0
- Level 1//"
- + The public identifier starts with: "-//IETF//DTD HTML 2.0
- Level 2//"
- + The public identifier starts with: "-//IETF//DTD HTML 2.0
- Strict Level 1//"
- + The public identifier starts with: "-//IETF//DTD HTML 2.0
- Strict Level 2//"
- + The public identifier starts with: "-//IETF//DTD HTML 2.0
- Strict//"
- + The public identifier starts with: "-//IETF//DTD HTML 2.0//"
- + The public identifier starts with: "-//IETF//DTD HTML 2.1E//"
- + The public identifier starts with: "-//IETF//DTD HTML 3.0//"
- + The public identifier starts with: "-//IETF//DTD HTML 3.2
- Final//"
- + The public identifier starts with: "-//IETF//DTD HTML 3.2//"
- + The public identifier starts with: "-//IETF//DTD HTML 3//"
- + The public identifier starts with: "-//IETF//DTD HTML Level
- 0//"
- + The public identifier starts with: "-//IETF//DTD HTML Level
- 1//"
- + The public identifier starts with: "-//IETF//DTD HTML Level
- 2//"
- + The public identifier starts with: "-//IETF//DTD HTML Level
- 3//"
- + The public identifier starts with: "-//IETF//DTD HTML Strict
- Level 0//"
- + The public identifier starts with: "-//IETF//DTD HTML Strict
- Level 1//"
- + The public identifier starts with: "-//IETF//DTD HTML Strict
- Level 2//"
- + The public identifier starts with: "-//IETF//DTD HTML Strict
- Level 3//"
- + The public identifier starts with: "-//IETF//DTD HTML
- Strict//"
- + The public identifier starts with: "-//IETF//DTD HTML//"
- + The public identifier starts with: "-//Metrius//DTD Metrius
- Presentational//"
- + The public identifier starts with: "-//Microsoft//DTD Internet
- Explorer 2.0 HTML Strict//"
- + The public identifier starts with: "-//Microsoft//DTD Internet
- Explorer 2.0 HTML//"
- + The public identifier starts with: "-//Microsoft//DTD Internet
- Explorer 2.0 Tables//"
- + The public identifier starts with: "-//Microsoft//DTD Internet
- Explorer 3.0 HTML Strict//"
- + The public identifier starts with: "-//Microsoft//DTD Internet
- Explorer 3.0 HTML//"
- + The public identifier starts with: "-//Microsoft//DTD Internet
- Explorer 3.0 Tables//"
- + The public identifier starts with: "-//Netscape Comm.
- Corp.//DTD HTML//"
- + The public identifier starts with: "-//Netscape Comm.
- Corp.//DTD Strict HTML//"
- + The public identifier starts with: "-//O'Reilly and
- Associates//DTD HTML 2.0//"
- + The public identifier starts with: "-//O'Reilly and
- Associates//DTD HTML Extended 1.0//"
- + The public identifier starts with: "-//O'Reilly and
- Associates//DTD HTML Extended Relaxed 1.0//"
- + The public identifier starts with: "-//SoftQuad Software//DTD
- HoTMetaL PRO 6.0::19990601::extensions to HTML 4.0//"
- + The public identifier starts with: "-//SoftQuad//DTD HoTMetaL
- PRO 4.0::19971010::extensions to HTML 4.0//"
- + The public identifier starts with: "-//Spyglass//DTD HTML 2.0
- Extended//"
- + The public identifier starts with: "-//SQ//DTD HTML 2.0
- HoTMetaL + extensions//"
- + The public identifier starts with: "-//Sun Microsystems
- Corp.//DTD HotJava HTML//"
- + The public identifier starts with: "-//Sun Microsystems
- Corp.//DTD HotJava Strict HTML//"
- + The public identifier starts with: "-//W3C//DTD HTML 3
- 1995-03-24//"
- + The public identifier starts with: "-//W3C//DTD HTML 3.2
- Draft//"
- + The public identifier starts with: "-//W3C//DTD HTML 3.2
- Final//"
- + The public identifier starts with: "-//W3C//DTD HTML 3.2//"
- + The public identifier starts with: "-//W3C//DTD HTML 3.2S
- Draft//"
- + The public identifier starts with: "-//W3C//DTD HTML 4.0
- Frameset//"
- + The public identifier starts with: "-//W3C//DTD HTML 4.0
- Transitional//"
- + The public identifier starts with: "-//W3C//DTD HTML
- Experimental 19960712//"
- + The public identifier starts with: "-//W3C//DTD HTML
- Experimental 970421//"
- + The public identifier starts with: "-//W3C//DTD W3 HTML//"
- + The public identifier starts with: "-//W3O//DTD W3 HTML 3.0//"
- + The public identifier is set to: "-//W3O//DTD W3 HTML Strict
- 3.0//EN//"
- + The public identifier starts with: "-//WebTechs//DTD Mozilla
- HTML 2.0//"
- + The public identifier starts with: "-//WebTechs//DTD Mozilla
- HTML//"
- + The public identifier is set to: "-/W3C/DTD HTML 4.0
- Transitional/EN"
- + The public identifier is set to: "HTML"
- + The system identifier is set to:
- "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd"
- + The system identifier is missing and the public identifier
- starts with: "-//W3C//DTD HTML 4.01 Frameset//"
- + The system identifier is missing and the public identifier
- starts with: "-//W3C//DTD HTML 4.01 Transitional//"
-
- Otherwise, if the DOCTYPE token matches one of the conditions in
- the following list, then set the document to limited quirks
- mode:
-
- + The public identifier starts with: "-//W3C//DTD XHTML 1.0
- Frameset//"
- + The public identifier starts with: "-//W3C//DTD XHTML 1.0
- Transitional//"
- + The system identifier is not missing and the public identifier
- starts with: "-//W3C//DTD HTML 4.01 Frameset//"
- + The system identifier is not missing and the public identifier
- starts with: "-//W3C//DTD HTML 4.01 Transitional//"
-
- The name, system identifier, and public identifier strings must
- be compared to the values given in the lists above in an ASCII
- case-insensitive manner. A system identifier whose value is the
- empty string is not considered missing for the purposes of the
- conditions above.
-
- Then, switch the insertion mode to "before html".
-
- Anything else
- Parse error.
-
- Set the document to quirks mode.
-
- Switch the insertion mode to "before html", then reprocess the
- current token.
-
- 8.2.5.5 The "before html" insertion mode
-
- When the insertion mode is "before html", tokens must be handled as
- follows:
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A comment token
- Append a Comment node to the Document object with the data
- attribute set to the data given in the comment token.
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
- Ignore the token.
-
- A start tag whose tag name is "html"
- Create an element for the token in the HTML namespace. Append it
- to the Document object. Put this element in the stack of open
- elements.
-
- If the token has an attribute "manifest", then resolve the value
- of that attribute to an absolute URL, and if that is successful,
- run the application cache selection algorithm with the resulting
- absolute URL. Otherwise, if there is no such attribute or
- resolving it fails, run the application cache selection
- algorithm with no manifest. The algorithm must be passed the
- Document object.
-
- Switch the insertion mode to "before head".
-
- Anything else
- Create an HTMLElement node with the tag name html, in the HTML
- namespace. Append it to the Document object. Put this element in
- the stack of open elements.
-
- Run the application cache selection algorithm with no manifest,
- passing it the Document object.
-
- Switch the insertion mode to "before head", then reprocess the
- current token.
-
- Should probably make end tags be ignored, so that "" puts the comment before the root node (or should we?)
-
- The root element can end up being removed from the Document object,
- e.g. by scripts; nothing in particular happens in such cases, content
- continues being appended to the nodes as described in the next section.
-
- 8.2.5.6 The "before head" insertion mode
-
- When the insertion mode is "before head", tokens must be handled as
- follows:
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
- Ignore the token.
-
- A comment token
- Append a Comment node to the current node with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- A start tag whose tag name is "head"
- Insert an HTML element for the token.
-
- Set the head element pointer to the newly created head element.
-
- Switch the insertion mode to "in head".
-
- An end tag whose tag name is one of: "head", "br"
- Act as if a start tag token with the tag name "head" and no
- attributes had been seen, then reprocess the current token.
-
- Any other end tag
- Parse error. Ignore the token.
-
- Anything else
- Act as if a start tag token with the tag name "head" and no
- attributes had been seen, then reprocess the current token.
-
- This will result in an empty head element being generated, with
- the current token being reprocessed in the "after head"
- insertion mode.
-
- 8.2.5.7 The "in head" insertion mode
-
- When the insertion mode is "in head", tokens must be handled as
- follows:
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
- Insert the character into the current node.
-
- A comment token
- Append a Comment node to the current node with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- A start tag whose tag name is one of: "base", "command", "eventsource",
- "link"
- Insert an HTML element for the token. Immediately pop the
- current node off the stack of open elements.
-
- Acknowledge the token's self-closing flag, if it is set.
-
- A start tag whose tag name is "meta"
- Insert an HTML element for the token. Immediately pop the
- current node off the stack of open elements.
-
- Acknowledge the token's self-closing flag, if it is set.
-
- If the element has a charset attribute, and its value is a
- supported encoding, and the confidence is currently tentative,
- then change the encoding to the encoding given by the value of
- the charset attribute.
-
- Otherwise, if the element has a content attribute, and applying
- the algorithm for extracting an encoding from a Content-Type to
- its value returns a supported encoding encoding, and the
- confidence is currently tentative, then change the encoding to
- the encoding encoding.
-
- A start tag whose tag name is "title"
- Follow the generic RCDATA element parsing algorithm.
-
- A start tag whose tag name is "noscript", if the scripting flag is
- enabled
-
- A start tag whose tag name is one of: "noframes", "style"
- Follow the generic CDATA element parsing algorithm.
-
- A start tag whose tag name is "noscript", if the scripting flag is
- disabled
- Insert an HTML element for the token.
-
- Switch the insertion mode to "in head noscript".
-
- A start tag whose tag name is "script"
-
- 1. Create an element for the token in the HTML namespace.
- 2. Mark the element as being "parser-inserted".
- This ensures that, if the script is external, any
- document.write() calls in the script will execute in-line,
- instead of blowing the document away, as would happen in most
- other cases. It also prevents the script from executing until
- the end tag is seen.
- 3. If the parser was originally created for the HTML fragment
- parsing algorithm, then mark the script element as "already
- executed". (fragment case)
- 4. Append the new element to the current node.
- 5. Switch the tokeniser's content model flag to the CDATA state.
- 6. Let the original insertion mode be the current insertion mode.
- 7. Switch the insertion mode to "in CDATA/RCDATA".
-
- An end tag whose tag name is "head"
- Pop the current node (which will be the head element) off the
- stack of open elements.
-
- Switch the insertion mode to "after head".
-
- An end tag whose tag name is "br"
- Act as described in the "anything else" entry below.
-
- A start tag whose tag name is "head"
- Any other end tag
- Parse error. Ignore the token.
-
- Anything else
- Act as if an end tag token with the tag name "head" had been
- seen, and reprocess the current token.
-
- In certain UAs, some elements don't trigger the "in body" mode
- straight away, but instead get put into the head. Do we want to
- copy that?
-
- 8.2.5.8 The "in head noscript" insertion mode
-
- When the insertion mode is "in head noscript", tokens must be handled
- as follows:
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- An end tag whose tag name is "noscript"
- Pop the current node (which will be a noscript element) from the
- stack of open elements; the new current node will be a head
- element.
-
- Switch the insertion mode to "in head".
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
-
- A comment token
- A start tag whose tag name is one of: "link", "meta", "noframes",
- "style"
- Process the token using the rules for the "in head" insertion
- mode.
-
- An end tag whose tag name is "br"
- Act as described in the "anything else" entry below.
-
- A start tag whose tag name is one of: "head", "noscript"
- Any other end tag
- Parse error. Ignore the token.
-
- Anything else
- Parse error. Act as if an end tag with the tag name "noscript"
- had been seen and reprocess the current token.
-
- 8.2.5.9 The "after head" insertion mode
-
- When the insertion mode is "after head", tokens must be handled as
- follows:
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
- Insert the character into the current node.
-
- A comment token
- Append a Comment node to the current node with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- A start tag whose tag name is "body"
- Insert an HTML element for the token.
-
- Switch the insertion mode to "in body".
-
- A start tag whose tag name is "frameset"
- Insert an HTML element for the token.
-
- Switch the insertion mode to "in frameset".
-
- A start tag token whose tag name is one of: "base", "link", "meta",
- "noframes", "script", "style", "title"
- Parse error.
-
- Push the node pointed to by the head element pointer onto the
- stack of open elements.
-
- Process the token using the rules for the "in head" insertion
- mode.
-
- Remove the node pointed to by the head element pointer from the
- stack of open elements.
-
- An end tag whose tag name is "br"
- Act as described in the "anything else" entry below.
-
- A start tag whose tag name is "head"
- Any other end tag
- Parse error. Ignore the token.
-
- Anything else
- Act as if a start tag token with the tag name "body" and no
- attributes had been seen, and then reprocess the current token.
-
- 8.2.5.10 The "in body" insertion mode
-
- When the insertion mode is "in body", tokens must be handled as
- follows:
-
- A character token
- Reconstruct the active formatting elements, if any.
-
- Insert the token's character into the current node.
-
- A comment token
- Append a Comment node to the current node with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "html"
- Parse error. For each attribute on the token, check to see if
- the attribute is already present on the top element of the stack
- of open elements. If it is not, add the attribute and its
- corresponding value to that element.
-
- A start tag token whose tag name is one of: "base", "command",
- "eventsource", "link", "meta", "noframes", "script", "style",
- "title"
- Process the token using the rules for the "in head" insertion
- mode.
-
- A start tag whose tag name is "body"
- Parse error.
-
- If the second element on the stack of open elements is not a
- body element, or, if the stack of open elements has only one
- node on it, then ignore the token. (fragment case)
-
- Otherwise, for each attribute on the token, check to see if the
- attribute is already present on the body element (the second
- element) on the stack of open elements. If it is not, add the
- attribute and its corresponding value to that element.
-
- An end-of-file token
- If there is a node in the stack of open elements that is not
- either a dd element, a dt element, an li element, a p element, a
- tbody element, a td element, a tfoot element, a th element, a
- thead element, a tr element, the body element, or the html
- element, then this is a parse error.
-
- Stop parsing.
-
- An end tag whose tag name is "body"
- If the stack of open elements does not have a body element in
- scope, this is a parse error; ignore the token.
-
- Otherwise, if there is a node in the stack of open elements that
- is not either a dd element, a dt element, an li element, a p
- element, a tbody element, a td element, a tfoot element, a th
- element, a thead element, a tr element, the body element, or the
- html element, then this is a parse error.
-
- Switch the insertion mode to "after body".
-
- An end tag whose tag name is "html"
- Act as if an end tag with tag name "body" had been seen, then,
- if that token wasn't ignored, reprocess the current token.
-
- The fake end tag token here can only be ignored in the fragment
- case.
-
- A start tag whose tag name is one of: "address", "article", "aside",
- "blockquote", "center", "datagrid", "details", "dialog", "dir",
- "div", "dl", "fieldset", "figure", "footer", "header", "menu",
- "nav", "ol", "p", "section", "ul"
- If the stack of open elements has a p element in scope, then act
- as if an end tag with the tag name "p" had been seen.
-
- Insert an HTML element for the token.
-
- A start tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5",
- "h6"
- If the stack of open elements has a p element in scope, then act
- as if an end tag with the tag name "p" had been seen.
-
- If the current node is an element whose tag name is one of "h1",
- "h2", "h3", "h4", "h5", or "h6", then this is a parse error; pop
- the current node off the stack of open elements.
-
- Insert an HTML element for the token.
-
- A start tag whose tag name is one of: "pre", "listing"
- If the stack of open elements has a p element in scope, then act
- as if an end tag with the tag name "p" had been seen.
-
- Insert an HTML element for the token.
-
- If the next token is a U+000A LINE FEED (LF) character token,
- then ignore that token and move on to the next one. (Newlines at
- the start of pre blocks are ignored as an authoring
- convenience.)
-
- A start tag whose tag name is "form"
- If the form element pointer is not null, then this is a parse
- error; ignore the token.
-
- Otherwise:
-
- If the stack of open elements has a p element in scope, then act
- as if an end tag with the tag name "p" had been seen.
-
- Insert an HTML element for the token, and set the form element
- pointer to point to the element created.
-
- A start tag whose tag name is "li"
- Run the following algorithm:
-
- 1. Initialize node to be the current node (the bottommost node of
- the stack).
- 2. If node is an li element, then act as if an end tag with the
- tag name "li" had been seen, then jump to the last step.
- 3. If node is not in the formatting category, and is not in the
- phrasing category, and is not an address, div, or p element,
- then jump to the last step.
- 4. Otherwise, set node to the previous entry in the stack of open
- elements and return to step 2.
- 5. This is the last step.
- If the stack of open elements has a p element in scope, then
- act as if an end tag with the tag name "p" had been seen.
- Finally, insert an HTML element for the token.
-
- A start tag whose tag name is one of: "dd", "dt"
- Run the following algorithm:
-
- 1. Initialize node to be the current node (the bottommost node of
- the stack).
- 2. If node is a dd or dt element, then act as if an end tag with
- the same tag name as node had been seen, then jump to the last
- step.
- 3. If node is not in the formatting category, and is not in the
- phrasing category, and is not an address, div, or p element,
- then jump to the last step.
- 4. Otherwise, set node to the previous entry in the stack of open
- elements and return to step 2.
- 5. This is the last step.
- If the stack of open elements has a p element in scope, then
- act as if an end tag with the tag name "p" had been seen.
- Finally, insert an HTML element for the token.
-
- A start tag whose tag name is "plaintext"
- If the stack of open elements has a p element in scope, then act
- as if an end tag with the tag name "p" had been seen.
-
- Insert an HTML element for the token.
-
- Switch the content model flag to the PLAINTEXT state.
-
- Once a start tag with the tag name "plaintext" has been seen,
- that will be the last token ever seen other than character
- tokens (and the end-of-file token), because there is no way to
- switch the content model flag out of the PLAINTEXT state.
-
- An end tag whose tag name is one of: "address", "article", "aside",
- "blockquote", "center", "datagrid", "details", "dialog", "dir",
- "div", "dl", "fieldset", "figure", "footer", "header",
- "listing", "menu", "nav", "ol", "pre", "section", "ul"
- If the stack of open elements does not have an element in scope
- with the same tag name as that of the token, then this is a
- parse error; ignore the token.
-
- Otherwise, run these steps:
-
- 1. Generate implied end tags.
- 2. If the current node is not an element with the same tag name
- as that of the token, then this is a parse error.
- 3. Pop elements from the stack of open elements until an element
- with the same tag name as the token has been popped from the
- stack.
-
- An end tag whose tag name is "form"
- Let node be the element that the form element pointer is set to.
-
- Set the form element pointer to null.
-
- If node is null or the stack of open elements does not have node
- in scope, then this is a parse error; ignore the token.
-
- Otherwise, run these steps:
-
- 1. Generate implied end tags.
- 2. If the current node is not node, then this is a parse error.
- 3. Remove node from the stack of open elements.
-
- An end tag whose tag name is "p"
- If the stack of open elements does not have an element in scope
- with the same tag name as that of the token, then this is a
- parse error; act as if a start tag with the tag name p had been
- seen, then reprocess the current token.
-
- Otherwise, run these steps:
-
- 1. Generate implied end tags, except for elements with the same
- tag name as the token.
- 2. If the current node is not an element with the same tag name
- as that of the token, then this is a parse error.
- 3. Pop elements from the stack of open elements until an element
- with the same tag name as the token has been popped from the
- stack.
-
- An end tag whose tag name is one of: "dd", "dt", "li"
- If the stack of open elements does not have an element in scope
- with the same tag name as that of the token, then this is a
- parse error; ignore the token.
-
- Otherwise, run these steps:
-
- 1. Generate implied end tags, except for elements with the same
- tag name as the token.
- 2. If the current node is not an element with the same tag name
- as that of the token, then this is a parse error.
- 3. Pop elements from the stack of open elements until an element
- with the same tag name as the token has been popped from the
- stack.
-
- An end tag whose tag name is one of: "h1", "h2", "h3", "h4", "h5", "h6"
- If the stack of open elements does not have an element in scope
- whose tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6",
- then this is a parse error; ignore the token.
-
- Otherwise, run these steps:
-
- 1. Generate implied end tags.
- 2. If the current node is not an element with the same tag name
- as that of the token, then this is a parse error.
- 3. Pop elements from the stack of open elements until an element
- whose tag name is one of "h1", "h2", "h3", "h4", "h5", or "h6"
- has been popped from the stack.
-
- An end tag whose tag name is "sarcasm"
- Take a deep breath, then act as described in the "any other end
- tag" entry below.
-
- A start tag whose tag name is "a"
- If the list of active formatting elements contains an element
- whose tag name is "a" between the end of the list and the last
- marker on the list (or the start of the list if there is no
- marker on the list), then this is a parse error; act as if an
- end tag with the tag name "a" had been seen, then remove that
- element from the list of active formatting elements and the
- stack of open elements if the end tag didn't already remove it
- (it might not have if the element is not in table scope).
-
- In the non-conforming stream
- a
x, the first a element
- would be closed upon seeing the second one, and the "x"
- character would be inside a link to "b", not to "a". This is
- despite the fact that the outer a element is not in table scope
- (meaning that a regular end tag at the start of the table
- wouldn't close the outer a element).
-
- Reconstruct the active formatting elements, if any.
-
- Insert an HTML element for the token. Add that element to the
- list of active formatting elements.
-
- A start tag whose tag name is one of: "b", "big", "em", "font", "i",
- "s", "small", "strike", "strong", "tt", "u"
- Reconstruct the active formatting elements, if any.
-
- Insert an HTML element for the token. Add that element to the
- list of active formatting elements.
-
- A start tag whose tag name is "nobr"
- Reconstruct the active formatting elements, if any.
-
- If the stack of open elements has a nobr element in scope, then
- this is a parse error; act as if an end tag with the tag name
- "nobr" had been seen, then once again reconstruct the active
- formatting elements, if any.
-
- Insert an HTML element for the token. Add that element to the
- list of active formatting elements.
-
- An end tag whose tag name is one of: "a", "b", "big", "em", "font",
- "i", "nobr", "s", "small", "strike", "strong", "tt", "u"
- Follow these steps:
-
- 1. Let the formatting element be the last element in the list of
- active formatting elements that:
- o is between the end of the list and the last scope marker
- in the list, if any, or the start of the list otherwise,
- and
- o has the same tag name as the token.
- If there is no such node, or, if that node is also in the
- stack of open elements but the element is not in scope, then
- this is a parse error; ignore the token, and abort these
- steps.
- Otherwise, if there is such a node, but that node is not in
- the stack of open elements, then this is a parse error; remove
- the element from the list, and abort these steps.
- Otherwise, there is a formatting element and that element is
- in the stack and is in scope. If the element is not the
- current node, this is a parse error. In any case, proceed with
- the algorithm as written in the following steps.
- 2. Let the furthest block be the topmost node in the stack of
- open elements that is lower in the stack than the formatting
- element, and is not an element in the phrasing or formatting
- categories. There might not be one.
- 3. If there is no furthest block, then the UA must skip the
- subsequent steps and instead just pop all the nodes from the
- bottom of the stack of open elements, from the current node up
- to and including the formatting element, and remove the
- formatting element from the list of active formatting
- elements.
- 4. Let the common ancestor be the element immediately above the
- formatting element in the stack of open elements.
- 5. If the furthest block has a parent node, then remove the
- furthest block from its parent node.
- 6. Let a bookmark note the position of the formatting element in
- the list of active formatting elements relative to the
- elements on either side of it in the list.
- 7. Let node and last node be the furthest block. Follow these
- steps:
- 1. Let node be the element immediately above node in the
- stack of open elements.
- 2. If node is not in the list of active formatting elements,
- then remove node from the stack of open elements and then
- go back to step 1.
- 3. Otherwise, if node is the formatting element, then go to
- the next step in the overall algorithm.
- 4. Otherwise, if last node is the furthest block, then move
- the aforementioned bookmark to be immediately after the
- node in the list of active formatting elements.
- 5. If node has any children, perform a shallow clone of
- node, replace the entry for node in the list of active
- formatting elements with an entry for the clone, replace
- the entry for node in the stack of open elements with an
- entry for the clone, and let node be the clone.
- 6. Insert last node into node, first removing it from its
- previous parent node if any.
- 7. Let last node be node.
- 8. Return to step 1 of this inner set of steps.
- 8. If the common ancestor node is a table, tbody, tfoot, thead,
- or tr element, then, foster parent whatever last node ended up
- being in the previous step.
- Otherwise, append whatever last node ended up being in the
- previous step to the common ancestor node, first removing it
- from its previous parent node if any.
- 9. Perform a shallow clone of the formatting element.
- 10. Take all of the child nodes of the furthest block and append
- them to the clone created in the last step.
- 11. Append that clone to the furthest block.
- 12. Remove the formatting element from the list of active
- formatting elements, and insert the clone into the list of
- active formatting elements at the position of the
- aforementioned bookmark.
- 13. Remove the formatting element from the stack of open elements,
- and insert the clone into the stack of open elements
- immediately below the position of the furthest block in that
- stack.
- 14. Jump back to step 1 in this series of steps.
-
- The way these steps are defined, only elements in the formatting
- category ever get cloned by this algorithm.
-
- Because of the way this algorithm causes elements to change
- parents, it has been dubbed the "adoption agency algorithm" (in
- contrast with other possibly algorithms for dealing with
- misnested content, which included the "incest algorithm", the
- "secret affair algorithm", and the "Heisenberg algorithm").
-
- A start tag whose tag name is "button"
- If the stack of open elements has a button element in scope,
- then this is a parse error; act as if an end tag with the tag
- name "button" had been seen, then reprocess the token.
-
- Otherwise:
-
- Reconstruct the active formatting elements, if any.
-
- Insert an HTML element for the token.
-
- Insert a marker at the end of the list of active formatting
- elements.
-
- A start tag token whose tag name is one of: "applet", "marquee",
- "object"
- Reconstruct the active formatting elements, if any.
-
- Insert an HTML element for the token.
-
- Insert a marker at the end of the list of active formatting
- elements.
-
- An end tag token whose tag name is one of: "applet", "button",
- "marquee", "object"
- If the stack of open elements does not have an element in scope
- with the same tag name as that of the token, then this is a
- parse error; ignore the token.
-
- Otherwise, run these steps:
-
- 1. Generate implied end tags.
- 2. If the current node is not an element with the same tag name
- as that of the token, then this is a parse error.
- 3. Pop elements from the stack of open elements until an element
- with the same tag name as the token has been popped from the
- stack.
- 4. Clear the list of active formatting elements up to the last
- marker.
-
- A start tag whose tag name is "xmp"
- Reconstruct the active formatting elements, if any.
-
- Follow the generic CDATA element parsing algorithm.
-
- A start tag whose tag name is "table"
- If the stack of open elements has a p element in scope, then act
- as if an end tag with the tag name "p" had been seen.
-
- Insert an HTML element for the token.
-
- Switch the insertion mode to "in table".
-
- A start tag whose tag name is one of: "area", "basefont", "bgsound",
- "br", "embed", "img", "input", "spacer", "wbr"
- Reconstruct the active formatting elements, if any.
-
- Insert an HTML element for the token. Immediately pop the
- current node off the stack of open elements.
-
- Acknowledge the token's self-closing flag, if it is set.
-
- A start tag whose tag name is one of: "param", "source"
- Insert an HTML element for the token. Immediately pop the
- current node off the stack of open elements.
-
- Acknowledge the token's self-closing flag, if it is set.
-
- A start tag whose tag name is "hr"
- If the stack of open elements has a p element in scope, then act
- as if an end tag with the tag name "p" had been seen.
-
- Insert an HTML element for the token. Immediately pop the
- current node off the stack of open elements.
-
- Acknowledge the token's self-closing flag, if it is set.
-
- A start tag whose tag name is "image"
- Parse error. Change the token's tag name to "img" and reprocess
- it. (Don't ask.)
-
- A start tag whose tag name is "isindex"
- Parse error.
-
- If the form element pointer is not null, then ignore the token.
-
- Otherwise:
-
- Acknowledge the token's self-closing flag, if it is set.
-
- Act as if a start tag token with the tag name "form" had been
- seen.
-
- If the token has an attribute called "action", set the action
- attribute on the resulting form element to the value of the
- "action" attribute of the token.
-
- Act as if a start tag token with the tag name "hr" had been
- seen.
-
- Act as if a start tag token with the tag name "p" had been seen.
-
- Act as if a start tag token with the tag name "label" had been
- seen.
-
- Act as if a stream of character tokens had been seen (see below
- for what they should say).
-
- Act as if a start tag token with the tag name "input" had been
- seen, with all the attributes from the "isindex" token except
- "name", "action", and "prompt". Set the name attribute of the
- resulting input element to the value "isindex".
-
- Act as if a stream of character tokens had been seen (see below
- for what they should say).
-
- Act as if an end tag token with the tag name "label" had been
- seen.
-
- Act as if an end tag token with the tag name "p" had been seen.
-
- Act as if a start tag token with the tag name "hr" had been
- seen.
-
- Act as if an end tag token with the tag name "form" had been
- seen.
-
- If the token has an attribute with the name "prompt", then the
- first stream of characters must be the same string as given in
- that attribute, and the second stream of characters must be
- empty. Otherwise, the two streams of character tokens together
- should, together with the input element, express the equivalent
- of "This is a searchable index. Insert your search keywords
- here: (input field)" in the user's preferred language.
-
- A start tag whose tag name is "textarea"
-
- 1. Insert an HTML element for the token.
- 2. If the next token is a U+000A LINE FEED (LF) character token,
- then ignore that token and move on to the next one. (Newlines
- at the start of textarea elements are ignored as an authoring
- convenience.)
- 3. Switch the tokeniser's content model flag to the RCDATA state.
- 4. Let the original insertion mode be the current insertion mode.
- 5. Switch the insertion mode to "in CDATA/RCDATA".
-
- A start tag whose tag name is one of: "iframe", "noembed"
- A start tag whose tag name is "noscript", if the scripting flag is
- enabled
- Follow the generic CDATA element parsing algorithm.
-
- A start tag whose tag name is "select"
- Reconstruct the active formatting elements, if any.
-
- Insert an HTML element for the token.
-
- If the insertion mode is one of in table", "in caption", "in
- column group", "in table body", "in row", or "in cell", then
- switch the insertion mode to "in select in table". Otherwise,
- switch the insertion mode to "in select".
-
- A start tag whose tag name is one of: "optgroup", "option"
- If the stack of open elements has an option element in scope,
- then act as if an end tag with the tag name "option" had been
- seen.
-
- Reconstruct the active formatting elements, if any.
-
- Insert an HTML element for the token.
-
- A start tag whose tag name is one of: "rp", "rt"
- If the stack of open elements has a ruby element in scope, then
- generate implied end tags. If the current node is not then a
- ruby element, this is a parse error; pop all the nodes from the
- current node up to the node immediately before the bottommost
- ruby element on the stack of open elements.
-
- Insert an HTML element for the token.
-
- An end tag whose tag name is "br"
- Parse error. Act as if a start tag token with the tag name "br"
- had been seen. Ignore the end tag token.
-
- A start tag whose tag name is "math"
- Reconstruct the active formatting elements, if any.
-
- Adjust MathML attributes for the token. (This fixes the case of
- MathML attributes that are not all lowercase.)
-
- Adjust foreign attributes for the token. (This fixes the use of
- namespaced attributes, in particular XLink.)
-
- Insert a foreign element for the token, in the MathML namespace.
-
- If the token has its self-closing flag set, pop the current node
- off the stack of open elements and acknowledge the token's
- self-closing flag.
-
- Otherwise, let the secondary insertion mode be the current
- insertion mode, and then switch the insertion mode to "in
- foreign content".
-
- A start tag whose tag name is one of: "caption", "col", "colgroup",
- "frame", "frameset", "head", "tbody", "td", "tfoot", "th",
- "thead", "tr"
- Parse error. Ignore the token.
-
- Any other start tag
- Reconstruct the active formatting elements, if any.
-
- Insert an HTML element for the token.
-
- This element will be a phrasing element.
-
- Any other end tag
- Run the following steps:
-
- 1. Initialize node to be the current node (the bottommost node of
- the stack).
- 2. If node has the same tag name as the end tag token, then:
- 1. Generate implied end tags.
- 2. If the tag name of the end tag token does not match the
- tag name of the current node, this is a parse error.
- 3. Pop all the nodes from the current node up to node,
- including node, then stop these steps.
- 3. Otherwise, if node is in neither the formatting category nor
- the phrasing category, then this is a parse error; ignore the
- token, and abort these steps.
- 4. Set node to the previous entry in the stack of open elements.
- 5. Return to step 2.
-
- 8.2.5.11 The "in CDATA/RCDATA" insertion mode
-
- When the insertion mode is "in CDATA/RCDATA", tokens must be handled as
- follows:
-
- A character token
- Insert the token's character into the current node.
-
- An end-of-file token
- Parse error.
-
- If the current node is a script element, mark the script element
- as "already executed".
-
- Pop the current node off the stack of open elements.
-
- Switch the insertion mode to the original insertion mode and
- reprocess the current token.
-
- An end tag whose tag name is "script"
- Let script be the current node (which will be a script element).
-
- Pop the current node off the stack of open elements.
-
- Switch the insertion mode to the original insertion mode.
-
- Let the old insertion point have the same value as the current
- insertion point. Let the insertion point be just before the next
- input character.
-
- Increment the parser's script nesting level by one.
-
- Run the script. This might cause some script to execute, which
- might cause new characters to be inserted into the tokeniser,
- and might cause the tokeniser to output more tokens, resulting
- in a reentrant invocation of the parser.
-
- Decrement the parser's script nesting level by one. If the
- parser's script nesting level is zero, then set the parser pause
- flag to false.
-
- Let the insertion point have the value of the old insertion
- point. (In other words, restore the insertion point to the value
- it had before the previous paragraph. This value might be the
- "undefined" value.)
-
- At this stage, if there is a pending external script, then:
-
- If the tree construction stage is being called reentrantly, say
- from a call to document.write():
- Set the parser pause flag to true, and abort the
- processing of any nested invocations of the tokeniser,
- yielding control back to the caller. (Tokenization will
- resume when the caller returns to the "outer" tree
- construction stage.)
-
- Otherwise:
- Follow these steps:
-
- 1. Let the script be the pending external script. There is
- no longer a pending external script.
- 2. Pause until the script has completed loading.
- 3. Let the insertion point be just before the next input
- character.
- 4. Execute the script.
- 5. Let the insertion point be undefined again.
- 6. If there is once again a pending external script, then
- repeat these steps from step 1.
-
- Any other end tag
- Pop the current node off the stack of open elements.
-
- Switch the insertion mode to the original insertion mode.
-
- 8.2.5.12 The "in table" insertion mode
-
- When the insertion mode is "in table", tokens must be handled as
- follows:
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
- If the current table is tainted, then act as described in the
- "anything else" entry below.
-
- Otherwise, insert the character into the current node.
-
- A comment token
- Append a Comment node to the current node with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "caption"
- Clear the stack back to a table context. (See below.)
-
- Insert a marker at the end of the list of active formatting
- elements.
-
- Insert an HTML element for the token, then switch the insertion
- mode to "in caption".
-
- A start tag whose tag name is "colgroup"
- Clear the stack back to a table context. (See below.)
-
- Insert an HTML element for the token, then switch the insertion
- mode to "in column group".
-
- A start tag whose tag name is "col"
- Act as if a start tag token with the tag name "colgroup" had
- been seen, then reprocess the current token.
-
- A start tag whose tag name is one of: "tbody", "tfoot", "thead"
- Clear the stack back to a table context. (See below.)
-
- Insert an HTML element for the token, then switch the insertion
- mode to "in table body".
-
- A start tag whose tag name is one of: "td", "th", "tr"
- Act as if a start tag token with the tag name "tbody" had been
- seen, then reprocess the current token.
-
- A start tag whose tag name is "table"
- Parse error. Act as if an end tag token with the tag name
- "table" had been seen, then, if that token wasn't ignored,
- reprocess the current token.
-
- The fake end tag token here can only be ignored in the fragment
- case.
-
- An end tag whose tag name is "table"
- If the stack of open elements does not have an element in table
- scope with the same tag name as the token, this is a parse
- error. Ignore the token. (fragment case)
-
- Otherwise:
-
- Pop elements from this stack until a table element has been
- popped from the stack.
-
- Reset the insertion mode appropriately.
-
- An end tag whose tag name is one of: "body", "caption", "col",
- "colgroup", "html", "tbody", "td", "tfoot", "th", "thead", "tr"
- Parse error. Ignore the token.
-
- A start tag whose tag name is one of: "style", "script"
- If the current table is tainted then act as described in the
- "anything else" entry below.
-
- Otherwise, process the token using the rules for the "in head"
- insertion mode.
-
- A start tag whose tag name is "input"
- If the token does not have an attribute with the name "type", or
- if it does, but that attribute's value is not an ASCII
- case-insensitive match for the string "hidden", or, if the
- current table is tainted, then: act as described in the
- "anything else" entry below.
-
- Otherwise:
-
- Parse error.
-
- Insert an HTML element for the token.
-
- Pop that input element off the stack of open elements.
-
- An end-of-file token
- If the current node is not the root html element, then this is a
- parse error.
-
- It can only be the current node in the fragment case.
-
- Stop parsing.
-
- Anything else
- Parse error. Process the token using the rules for the "in body"
- insertion mode, except that if the current node is a table,
- tbody, tfoot, thead, or tr element, then, whenever a node would
- be inserted into the current node, it must instead be foster
- parented.
-
- When the steps above require the UA to clear the stack back to a table
- context, it means that the UA must, while the current node is not a
- table element or an html element, pop elements from the stack of open
- elements.
-
- The current node being an html element after this process is a fragment
- case.
-
- 8.2.5.13 The "in caption" insertion mode
-
- When the insertion mode is "in caption", tokens must be handled as
- follows:
-
- An end tag whose tag name is "caption"
- If the stack of open elements does not have an element in table
- scope with the same tag name as the token, this is a parse
- error. Ignore the token. (fragment case)
-
- Otherwise:
-
- Generate implied end tags.
-
- Now, if the current node is not a caption element, then this is
- a parse error.
-
- Pop elements from this stack until a caption element has been
- popped from the stack.
-
- Clear the list of active formatting elements up to the last
- marker.
-
- Switch the insertion mode to "in table".
-
- A start tag whose tag name is one of: "caption", "col", "colgroup",
- "tbody", "td", "tfoot", "th", "thead", "tr"
-
- An end tag whose tag name is "table"
- Parse error. Act as if an end tag with the tag name "caption"
- had been seen, then, if that token wasn't ignored, reprocess the
- current token.
-
- The fake end tag token here can only be ignored in the fragment
- case.
-
- An end tag whose tag name is one of: "body", "col", "colgroup", "html",
- "tbody", "td", "tfoot", "th", "thead", "tr"
- Parse error. Ignore the token.
-
- Anything else
- Process the token using the rules for the "in body" insertion
- mode.
-
- 8.2.5.14 The "in column group" insertion mode
-
- When the insertion mode is "in column group", tokens must be handled as
- follows:
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
- Insert the character into the current node.
-
- A comment token
- Append a Comment node to the current node with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- A start tag whose tag name is "col"
- Insert an HTML element for the token. Immediately pop the
- current node off the stack of open elements.
-
- Acknowledge the token's self-closing flag, if it is set.
-
- An end tag whose tag name is "colgroup"
- If the current node is the root html element, then this is a
- parse error; ignore the token. (fragment case)
-
- Otherwise, pop the current node (which will be a colgroup
- element) from the stack of open elements. Switch the insertion
- mode to "in table".
-
- An end tag whose tag name is "col"
- Parse error. Ignore the token.
-
- An end-of-file token
- If the current node is the root html element, then stop parsing.
- (fragment case)
-
- Otherwise, act as described in the "anything else" entry below.
-
- Anything else
- Act as if an end tag with the tag name "colgroup" had been seen,
- and then, if that token wasn't ignored, reprocess the current
- token.
-
- The fake end tag token here can only be ignored in the fragment
- case.
-
- 8.2.5.15 The "in table body" insertion mode
-
- When the insertion mode is "in table body", tokens must be handled as
- follows:
-
- A start tag whose tag name is "tr"
- Clear the stack back to a table body context. (See below.)
-
- Insert an HTML element for the token, then switch the insertion
- mode to "in row".
-
- A start tag whose tag name is one of: "th", "td"
- Parse error. Act as if a start tag with the tag name "tr" had
- been seen, then reprocess the current token.
-
- An end tag whose tag name is one of: "tbody", "tfoot", "thead"
- If the stack of open elements does not have an element in table
- scope with the same tag name as the token, this is a parse
- error. Ignore the token.
-
- Otherwise:
-
- Clear the stack back to a table body context. (See below.)
-
- Pop the current node from the stack of open elements. Switch the
- insertion mode to "in table".
-
- A start tag whose tag name is one of: "caption", "col", "colgroup",
- "tbody", "tfoot", "thead"
-
- An end tag whose tag name is "table"
- If the stack of open elements does not have a tbody, thead, or
- tfoot element in table scope, this is a parse error. Ignore the
- token. (fragment case)
-
- Otherwise:
-
- Clear the stack back to a table body context. (See below.)
-
- Act as if an end tag with the same tag name as the current node
- ("tbody", "tfoot", or "thead") had been seen, then reprocess the
- current token.
-
- An end tag whose tag name is one of: "body", "caption", "col",
- "colgroup", "html", "td", "th", "tr"
- Parse error. Ignore the token.
-
- Anything else
- Process the token using the rules for the "in table" insertion
- mode.
-
- When the steps above require the UA to clear the stack back to a table
- body context, it means that the UA must, while the current node is not
- a tbody, tfoot, thead, or html element, pop elements from the stack of
- open elements.
-
- The current node being an html element after this process is a fragment
- case.
-
- 8.2.5.16 The "in row" insertion mode
-
- When the insertion mode is "in row", tokens must be handled as follows:
-
- A start tag whose tag name is one of: "th", "td"
- Clear the stack back to a table row context. (See below.)
-
- Insert an HTML element for the token, then switch the insertion
- mode to "in cell".
-
- Insert a marker at the end of the list of active formatting
- elements.
-
- An end tag whose tag name is "tr"
- If the stack of open elements does not have an element in table
- scope with the same tag name as the token, this is a parse
- error. Ignore the token. (fragment case)
-
- Otherwise:
-
- Clear the stack back to a table row context. (See below.)
-
- Pop the current node (which will be a tr element) from the stack
- of open elements. Switch the insertion mode to "in table body".
-
- A start tag whose tag name is one of: "caption", "col", "colgroup",
- "tbody", "tfoot", "thead", "tr"
-
- An end tag whose tag name is "table"
- Act as if an end tag with the tag name "tr" had been seen, then,
- if that token wasn't ignored, reprocess the current token.
-
- The fake end tag token here can only be ignored in the fragment
- case.
-
- An end tag whose tag name is one of: "tbody", "tfoot", "thead"
- If the stack of open elements does not have an element in table
- scope with the same tag name as the token, this is a parse
- error. Ignore the token.
-
- Otherwise, act as if an end tag with the tag name "tr" had been
- seen, then reprocess the current token.
-
- An end tag whose tag name is one of: "body", "caption", "col",
- "colgroup", "html", "td", "th"
- Parse error. Ignore the token.
-
- Anything else
- Process the token using the rules for the "in table" insertion
- mode.
-
- When the steps above require the UA to clear the stack back to a table
- row context, it means that the UA must, while the current node is not a
- tr element or an html element, pop elements from the stack of open
- elements.
-
- The current node being an html element after this process is a fragment
- case.
-
- 8.2.5.17 The "in cell" insertion mode
-
- When the insertion mode is "in cell", tokens must be handled as
- follows:
-
- An end tag whose tag name is one of: "td", "th"
- If the stack of open elements does not have an element in table
- scope with the same tag name as that of the token, then this is
- a parse error and the token must be ignored.
-
- Otherwise:
-
- Generate implied end tags.
-
- Now, if the current node is not an element with the same tag
- name as the token, then this is a parse error.
-
- Pop elements from this stack until an element with the same tag
- name as the token has been popped from the stack.
-
- Clear the list of active formatting elements up to the last
- marker.
-
- Switch the insertion mode to "in row". (The current node will be
- a tr element at this point.)
-
- A start tag whose tag name is one of: "caption", "col", "colgroup",
- "tbody", "td", "tfoot", "th", "thead", "tr"
- If the stack of open elements does not have a td or th element
- in table scope, then this is a parse error; ignore the token.
- (fragment case)
-
- Otherwise, close the cell (see below) and reprocess the current
- token.
-
- An end tag whose tag name is one of: "body", "caption", "col",
- "colgroup", "html"
- Parse error. Ignore the token.
-
- An end tag whose tag name is one of: "table", "tbody", "tfoot",
- "thead", "tr"
- If the stack of open elements does not have an element in table
- scope with the same tag name as that of the token (which can
- only happen for "tbody", "tfoot" and "thead", or, in the
- fragment case), then this is a parse error and the token must be
- ignored.
-
- Otherwise, close the cell (see below) and reprocess the current
- token.
-
- Anything else
- Process the token using the rules for the "in body" insertion
- mode.
-
- Where the steps above say to close the cell, they mean to run the
- following algorithm:
- 1. If the stack of open elements has a td element in table scope, then
- act as if an end tag token with the tag name "td" had been seen.
- 2. Otherwise, the stack of open elements will have a th element in
- table scope; act as if an end tag token with the tag name "th" had
- been seen.
-
- The stack of open elements cannot have both a td and a th element in
- table scope at the same time, nor can it have neither when the
- insertion mode is "in cell".
-
- 8.2.5.18 The "in select" insertion mode
-
- When the insertion mode is "in select", tokens must be handled as
- follows:
-
- A character token
- Insert the token's character into the current node.
-
- A comment token
- Append a Comment node to the current node with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- A start tag whose tag name is "option"
- If the current node is an option element, act as if an end tag
- with the tag name "option" had been seen.
-
- Insert an HTML element for the token.
-
- A start tag whose tag name is "optgroup"
- If the current node is an option element, act as if an end tag
- with the tag name "option" had been seen.
-
- If the current node is an optgroup element, act as if an end tag
- with the tag name "optgroup" had been seen.
-
- Insert an HTML element for the token.
-
- An end tag whose tag name is "optgroup"
- First, if the current node is an option element, and the node
- immediately before it in the stack of open elements is an
- optgroup element, then act as if an end tag with the tag name
- "option" had been seen.
-
- If the current node is an optgroup element, then pop that node
- from the stack of open elements. Otherwise, this is a parse
- error; ignore the token.
-
- An end tag whose tag name is "option"
- If the current node is an option element, then pop that node
- from the stack of open elements. Otherwise, this is a parse
- error; ignore the token.
-
- An end tag whose tag name is "select"
- If the stack of open elements does not have an element in table
- scope with the same tag name as the token, this is a parse
- error. Ignore the token. (fragment case)
-
- Otherwise:
-
- Pop elements from the stack of open elements until a select
- element has been popped from the stack.
-
- Reset the insertion mode appropriately.
-
- A start tag whose tag name is "select"
- Parse error. Act as if the token had been an end tag with the
- tag name "select" instead.
-
- A start tag whose tag name is one of: "input", "textarea"
- Parse error. Act as if an end tag with the tag name "select" had
- been seen, and reprocess the token.
-
- A start tag token whose tag name is "script"
- Process the token using the rules for the "in head" insertion
- mode.
-
- An end-of-file token
- If the current node is not the root html element, then this is a
- parse error.
-
- It can only be the current node in the fragment case.
-
- Stop parsing.
-
- Anything else
- Parse error. Ignore the token.
-
- 8.2.5.19 The "in select in table" insertion mode
-
- When the insertion mode is "in select in table", tokens must be handled
- as follows:
-
- A start tag whose tag name is one of: "caption", "table", "tbody",
- "tfoot", "thead", "tr", "td", "th"
- Parse error. Act as if an end tag with the tag name "select" had
- been seen, and reprocess the token.
-
- An end tag whose tag name is one of: "caption", "table", "tbody",
- "tfoot", "thead", "tr", "td", "th"
- Parse error.
-
- If the stack of open elements has an element in table scope with
- the same tag name as that of the token, then act as if an end
- tag with the tag name "select" had been seen, and reprocess the
- token. Otherwise, ignore the token.
-
- Anything else
- Process the token using the rules for the "in select" insertion
- mode.
-
- 8.2.5.20 The "in foreign content" insertion mode
-
- When the insertion mode is "in foreign content", tokens must be handled
- as follows:
-
- A character token
- Insert the token's character into the current node.
-
- A comment token
- Append a Comment node to the current node with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is neither "mglyph" nor "malignmark", if the
- current node is an mi element in the MathML namespace.
-
- A start tag whose tag name is neither "mglyph" nor "malignmark", if the
- current node is an mo element in the MathML namespace.
-
- A start tag whose tag name is neither "mglyph" nor "malignmark", if the
- current node is an mn element in the MathML namespace.
-
- A start tag whose tag name is neither "mglyph" nor "malignmark", if the
- current node is an ms element in the MathML namespace.
-
- A start tag whose tag name is neither "mglyph" nor "malignmark", if the
- current node is an mtext element in the MathML namespace.
-
- A start tag, if the current node is an element in the HTML namespace.
- An end tag
- Process the token using the rules for the secondary insertion
- mode.
-
- If, after doing so, the insertion mode is still "in foreign
- content", but there is no element in scope that has a namespace
- other than the HTML namespace, switch the insertion mode to the
- secondary insertion mode.
-
- A start tag whose tag name is one of: "b", "big", "blockquote", "body",
- "br", "center", "code", "dd", "div", "dl", "dt", "em", "embed",
- "h1", "h2", "h3", "h4", "h5", "h6", "head", "hr", "i", "img",
- "li", "listing", "menu", "meta", "nobr", "ol", "p", "pre",
- "ruby", "s", "small", "span", "strong", "strike", "sub", "sup",
- "table", "tt", "u", "ul", "var"
-
- A start tag whose tag name is "font", if the token has any attributes
- named "color", "face", or "size"
-
- An end-of-file token
- Parse error.
-
- Pop elements from the stack of open elements until the current
- node is in the HTML namespace.
-
- Switch the insertion mode to the secondary insertion mode, and
- reprocess the token.
-
- Any other start tag
- If the current node is an element in the MathML namespace,
- adjust MathML attributes for the token. (This fixes the case of
- MathML attributes that are not all lowercase.)
-
- Adjust foreign attributes for the token. (This fixes the use of
- namespaced attributes, in particular XLink in SVG.)
-
- Insert a foreign element for the token, in the same namespace as
- the current node.
-
- If the token has its self-closing flag set, pop the current node
- off the stack of open elements and acknowledge the token's
- self-closing flag.
-
- 8.2.5.21 The "after body" insertion mode
-
- When the insertion mode is "after body", tokens must be handled as
- follows:
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
- Process the token using the rules for the "in body" insertion
- mode.
-
- A comment token
- Append a Comment node to the first element in the stack of open
- elements (the html element), with the data attribute set to the
- data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- An end tag whose tag name is "html"
- If the parser was originally created as part of the HTML
- fragment parsing algorithm, this is a parse error; ignore the
- token. (fragment case)
-
- Otherwise, switch the insertion mode to "after after body".
-
- An end-of-file token
- Stop parsing.
-
- Anything else
- Parse error. Switch the insertion mode to "in body" and
- reprocess the token.
-
- 8.2.5.22 The "in frameset" insertion mode
-
- When the insertion mode is "in frameset", tokens must be handled as
- follows:
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
- Insert the character into the current node.
-
- A comment token
- Append a Comment node to the current node with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- A start tag whose tag name is "frameset"
- Insert an HTML element for the token.
-
- An end tag whose tag name is "frameset"
- If the current node is the root html element, then this is a
- parse error; ignore the token. (fragment case)
-
- Otherwise, pop the current node from the stack of open elements.
-
- If the parser was not originally created as part of the HTML
- fragment parsing algorithm (fragment case), and the current node
- is no longer a frameset element, then switch the insertion mode
- to "after frameset".
-
- A start tag whose tag name is "frame"
- Insert an HTML element for the token. Immediately pop the
- current node off the stack of open elements.
-
- Acknowledge the token's self-closing flag, if it is set.
-
- A start tag whose tag name is "noframes"
- Process the token using the rules for the "in head" insertion
- mode.
-
- An end-of-file token
- If the current node is not the root html element, then this is a
- parse error.
-
- It can only be the current node in the fragment case.
-
- Stop parsing.
-
- Anything else
- Parse error. Ignore the token.
-
- 8.2.5.23 The "after frameset" insertion mode
-
- When the insertion mode is "after frameset", tokens must be handled as
- follows:
-
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
- Insert the character into the current node.
-
- A comment token
- Append a Comment node to the current node with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- Parse error. Ignore the token.
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- An end tag whose tag name is "html"
- Switch the insertion mode to "after after frameset".
-
- A start tag whose tag name is "noframes"
- Process the token using the rules for the "in head" insertion
- mode.
-
- An end-of-file token
- Stop parsing.
-
- Anything else
- Parse error. Ignore the token.
-
- This doesn't handle UAs that don't support frames, or that do support
- frames but want to show the NOFRAMES content. Supporting the former is
- easy; supporting the latter is harder.
-
- 8.2.5.24 The "after after body" insertion mode
-
- When the insertion mode is "after after body", tokens must be handled
- as follows:
-
- A comment token
- Append a Comment node to the Document object with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- An end-of-file token
- Stop parsing.
-
- Anything else
- Parse error. Switch the insertion mode to "in body" and
- reprocess the token.
-
- 8.2.5.25 The "after after frameset" insertion mode
-
- When the insertion mode is "after after frameset", tokens must be
- handled as follows:
-
- A comment token
- Append a Comment node to the Document object with the data
- attribute set to the data given in the comment token.
-
- A DOCTYPE token
- A character token that is one of one of U+0009 CHARACTER TABULATION,
- U+000A LINE FEED (LF), U+000C FORM FEED (FF), or U+0020 SPACE
-
- A start tag whose tag name is "html"
- Process the token using the rules for the "in body" insertion
- mode.
-
- An end-of-file token
- Stop parsing.
-
- A start tag whose tag name is "noframes"
- Process the token using the rules for the "in head" insertion
- mode.
-
- Anything else
- Parse error. Ignore the token.
-
- 8.2.6 The end
-
- Once the user agent stops parsing the document, the user agent must
- follow the steps in this section.
-
- First, the current document readiness must be set to "interactive".
-
- Then, the rules for when a script completes loading start applying
- (script execution is no longer managed by the parser).
-
- If any of the scripts in the list of scripts that will execute as soon
- as possible have completed loading, or if the list of scripts that will
- execute asynchronously is not empty and the first script in that list
- has completed loading, then the user agent must act as if those scripts
- just completed loading, following the rules given for that in the
- script element definition.
-
- Then, if the list of scripts that will execute when the document has
- finished parsing is not empty, and the first item in this list has
- already completed loading, then the user agent must act as if that
- script just finished loading.
-
- By this point, there will be no scripts that have loaded but have not
- yet been executed.
-
- The user agent must then fire a simple event called DOMContentLoaded at
- the Document.
-
- Once everything that delays the load event has completed, the user
- agent must set the current document readiness to "complete", and then
- fire a load event at the body element.
-
- delaying the load event for things like image loads allows for intranet
- port scans (even without javascript!). Should we really encode that
- into the spec?
-
- 8.2.7 Coercing an HTML DOM into an infoset
-
- When an application uses an HTML parser in conjunction with an XML
- pipeline, it is possible that the constructed DOM is not compatible
- with the XML tool chain in certain subtle ways. For example, an XML
- toolchain might not be able to represent attributes with the name
- xmlns, since they conflict with the Namespaces in XML syntax. There is
- also some data that the HTML parser generates that isn't included in
- the DOM itself. This section specifies some rules for handling these
- issues.
-
- If the XML API being used doesn't support DOCTYPEs, the tool may drop
- DOCTYPEs altogether.
-
- If the XML API doesn't support attributes in no namespace that are
- named "xmlns", attributes whose names start with "xmlns:", or
- attributes in the XMLNS namespace, then the tool may drop such
- attributes.
-
- The tool may annotate the output with any namespace declarations
- required for proper operation.
-
- If the XML API being used restricts the allowable characters in the
- local names of elements and attributes, then the tool may map all
- element and attribute local names that the API wouldn't support to a
- set of names that are allowed, by replacing any character that isn't
- supported with the uppercase letter U and the five digits of the
- character's Unicode codepoint when expressed in hexadecimal, using
- digits 0-9 and capital letters A-F as the symbols, in increasing
- numeric order.
-
- For example, the element name foo start tag will be closed
- by a end tag, and never by a end tag, even if
- the user agent is using the rules above to then generate an actual
- element in the DOM with the name aU0003AU0003A for that start tag.
-
- 8.3 Namespaces
-
- The HTML namespace is: http://www.w3.org/1999/xhtml
-
- The MathML namespace is: http://www.w3.org/1998/Math/MathML
-
- The SVG namespace is: http://www.w3.org/2000/svg
-
- The XLink namespace is: http://www.w3.org/1999/xlink
-
- The XML namespace is: http://www.w3.org/XML/1998/namespace
-
- The XMLNS namespace is: http://www.w3.org/2000/xmlns/
diff --git a/gwt-src/nu/validator/htmlparser/HtmlParser.gwt.xml b/gwt-src/nu/validator/htmlparser/HtmlParser.gwt.xml
deleted file mode 100644
index 1eab09c2..00000000
--- a/gwt-src/nu/validator/htmlparser/HtmlParser.gwt.xml
+++ /dev/null
@@ -1,12 +0,0 @@
-
-
-
-
-
-
-
-
-
-
-
-
diff --git a/gwt-src/nu/validator/htmlparser/gwt/BrowserTreeBuilder.java b/gwt-src/nu/validator/htmlparser/gwt/BrowserTreeBuilder.java
deleted file mode 100644
index 2eaa6764..00000000
--- a/gwt-src/nu/validator/htmlparser/gwt/BrowserTreeBuilder.java
+++ /dev/null
@@ -1,477 +0,0 @@
-/*
- * Copyright (c) 2007 Henri Sivonen
- * Copyright (c) 2008-2017 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.gwt;
-
-import java.util.LinkedList;
-
-import nu.validator.htmlparser.common.DocumentMode;
-import nu.validator.htmlparser.impl.CoalescingTreeBuilder;
-import nu.validator.htmlparser.impl.HtmlAttributes;
-
-import org.xml.sax.SAXException;
-
-import com.google.gwt.core.client.JavaScriptException;
-import com.google.gwt.core.client.JavaScriptObject;
-
-class BrowserTreeBuilder extends CoalescingTreeBuilder {
-
- private JavaScriptObject document;
-
- private JavaScriptObject script;
-
- private JavaScriptObject placeholder;
-
- private boolean readyToRun;
-
- private final LinkedList scriptStack = new LinkedList();
-
- private class ScriptHolder {
- private final JavaScriptObject script;
-
- private final JavaScriptObject placeholder;
-
- /**
- * @param script
- * @param placeholder
- */
- public ScriptHolder(JavaScriptObject script,
- JavaScriptObject placeholder) {
- this.script = script;
- this.placeholder = placeholder;
- }
-
- /**
- * Returns the script.
- *
- * @return the script
- */
- public JavaScriptObject getScript() {
- return script;
- }
-
- /**
- * Returns the placeholder.
- *
- * @return the placeholder
- */
- public JavaScriptObject getPlaceholder() {
- return placeholder;
- }
- }
-
- protected BrowserTreeBuilder(JavaScriptObject document) {
- super();
- this.document = document;
- installExplorerCreateElementNS(document);
- }
-
- private static native boolean installExplorerCreateElementNS(
- JavaScriptObject doc) /*-{
- if (!doc.createElementNS) {
- doc.createElementNS = function (uri, local) {
- if ("http://www.w3.org/1999/xhtml" == uri) {
- return doc.createElement(local);
- } else if ("http://www.w3.org/1998/Math/MathML" == uri) {
- if (!doc.mathplayerinitialized) {
- var obj = document.createElement("object");
- obj.setAttribute("id", "mathplayer");
- obj.setAttribute("classid", "clsid:32F66A20-7614-11D4-BD11-00104BD3F987");
- document.getElementsByTagName("head")[0].appendChild(obj);
- document.namespaces.add("m", "http://www.w3.org/1998/Math/MathML", "#mathplayer");
- doc.mathplayerinitialized = true;
- }
- return doc.createElement("m:" + local);
- } else if ("http://www.w3.org/2000/svg" == uri) {
- if (!doc.renesisinitialized) {
- var obj = document.createElement("object");
- obj.setAttribute("id", "renesis");
- obj.setAttribute("classid", "clsid:AC159093-1683-4BA2-9DCF-0C350141D7F2");
- document.getElementsByTagName("head")[0].appendChild(obj);
- document.namespaces.add("s", "http://www.w3.org/2000/svg", "#renesis");
- doc.renesisinitialized = true;
- }
- return doc.createElement("s:" + local);
- } else {
- // throw
- }
- }
- }
- }-*/;
-
- private static native boolean hasAttributeNS(JavaScriptObject element,
- String uri, String localName) /*-{
- return element.hasAttributeNS(uri, localName);
- }-*/;
-
- private static native void setAttributeNS(JavaScriptObject element,
- String uri, String localName, String value) /*-{
- element.setAttributeNS(uri, localName, value);
- }-*/;
-
- @Override protected void addAttributesToElement(JavaScriptObject element,
- HtmlAttributes attributes) throws SAXException {
- try {
- for (int i = 0; i < attributes.getLength(); i++) {
- String localName = attributes.getLocalNameNoBoundsCheck(i);
- String uri = attributes.getURINoBoundsCheck(i);
- if (!hasAttributeNS(element, uri, localName)) {
- setAttributeNS(element, uri, localName,
- attributes.getValueNoBoundsCheck(i));
- }
- }
- } catch (JavaScriptException e) {
- fatal(e);
- }
- }
-
- private static native void appendChild(JavaScriptObject parent,
- JavaScriptObject child) /*-{
- parent.appendChild(child);
- }-*/;
-
- private static native JavaScriptObject createTextNode(JavaScriptObject doc,
- String text) /*-{
- return doc.createTextNode(text);
- }-*/;
-
- private static native JavaScriptObject getLastChild(JavaScriptObject node) /*-{
- return node.lastChild;
- }-*/;
-
- private static native void extendTextNode(JavaScriptObject node, String text) /*-{
- node.data += text;
- }-*/;
-
- @Override protected void appendCharacters(JavaScriptObject parent,
- String text) throws SAXException {
- try {
- if (parent == placeholder) {
- appendChild(script, createTextNode(document, text));
-
- }
- JavaScriptObject lastChild = getLastChild(parent);
- if (lastChild != null && getNodeType(lastChild) == 3) {
- extendTextNode(lastChild, text);
- return;
- }
- appendChild(parent, createTextNode(document, text));
- } catch (JavaScriptException e) {
- fatal(e);
- }
- }
-
- private static native boolean hasChildNodes(JavaScriptObject element) /*-{
- return element.hasChildNodes();
- }-*/;
-
- private static native JavaScriptObject getFirstChild(
- JavaScriptObject element) /*-{
- return element.firstChild;
- }-*/;
-
- @Override protected void appendChildrenToNewParent(
- JavaScriptObject oldParent, JavaScriptObject newParent)
- throws SAXException {
- try {
- while (hasChildNodes(oldParent)) {
- appendChild(newParent, getFirstChild(oldParent));
- }
- } catch (JavaScriptException e) {
- fatal(e);
- }
- }
-
- private static native JavaScriptObject createComment(JavaScriptObject doc,
- String text) /*-{
- return doc.createComment(text);
- }-*/;
-
- @Override protected void appendComment(JavaScriptObject parent,
- String comment) throws SAXException {
- try {
- if (parent == placeholder) {
- appendChild(script, createComment(document, comment));
- }
- appendChild(parent, createComment(document, comment));
- } catch (JavaScriptException e) {
- fatal(e);
- }
- }
-
- @Override protected void appendCommentToDocument(String comment)
- throws SAXException {
- try {
- appendChild(document, createComment(document, comment));
- } catch (JavaScriptException e) {
- fatal(e);
- }
- }
-
- private static native JavaScriptObject createElementNS(
- JavaScriptObject doc, String ns, String local) /*-{
- return doc.createElementNS(ns, local);
- }-*/;
-
- @Override protected JavaScriptObject createElement(String ns, String name,
- HtmlAttributes attributes) throws SAXException {
- try {
- JavaScriptObject rv = createElementNS(document, ns, name);
- for (int i = 0; i < attributes.getLength(); i++) {
- setAttributeNS(rv, attributes.getURINoBoundsCheck(i),
- attributes.getLocalNameNoBoundsCheck(i),
- attributes.getValueNoBoundsCheck(i));
- }
-
- if ("script" == name) {
- if (placeholder != null) {
- scriptStack.addLast(new ScriptHolder(script, placeholder));
- }
- script = rv;
- placeholder = createElementNS(document,
- "http://n.validator.nu/placeholder/", "script");
- rv = placeholder;
- for (int i = 0; i < attributes.getLength(); i++) {
- setAttributeNS(rv, attributes.getURINoBoundsCheck(i),
- attributes.getLocalNameNoBoundsCheck(i),
- attributes.getValueNoBoundsCheck(i));
- }
- }
-
- return rv;
- } catch (JavaScriptException e) {
- fatal(e);
- throw new RuntimeException("Unreachable");
- }
- }
-
- @Override protected JavaScriptObject createHtmlElementSetAsRoot(
- HtmlAttributes attributes) throws SAXException {
- try {
- JavaScriptObject rv = createElementNS(document,
- "http://www.w3.org/1999/xhtml", "html");
- for (int i = 0; i < attributes.getLength(); i++) {
- setAttributeNS(rv, attributes.getURINoBoundsCheck(i),
- attributes.getLocalNameNoBoundsCheck(i),
- attributes.getValueNoBoundsCheck(i));
- }
- appendChild(document, rv);
- return rv;
- } catch (JavaScriptException e) {
- fatal(e);
- throw new RuntimeException("Unreachable");
- }
- }
-
- private static native JavaScriptObject getParentNode(
- JavaScriptObject element) /*-{
- return element.parentNode;
- }-*/;
-
- @Override protected void appendElement(JavaScriptObject child,
- JavaScriptObject newParent) throws SAXException {
- try {
- if (newParent == placeholder) {
- appendChild(script, cloneNodeDeep(child));
- }
- appendChild(newParent, child);
- } catch (JavaScriptException e) {
- fatal(e);
- }
- }
-
- @Override protected boolean hasChildren(JavaScriptObject element)
- throws SAXException {
- try {
- return hasChildNodes(element);
- } catch (JavaScriptException e) {
- fatal(e);
- throw new RuntimeException("Unreachable");
- }
- }
-
- private static native void insertBeforeNative(JavaScriptObject parent,
- JavaScriptObject child, JavaScriptObject sibling) /*-{
- parent.insertBefore(child, sibling);
- }-*/;
-
- private static native int getNodeType(JavaScriptObject node) /*-{
- return node.nodeType;
- }-*/;
-
- private static native JavaScriptObject cloneNodeDeep(JavaScriptObject node) /*-{
- return node.cloneNode(true);
- }-*/;
-
- /**
- * Returns the document.
- *
- * @return the document
- */
- JavaScriptObject getDocument() {
- JavaScriptObject rv = document;
- document = null;
- return rv;
- }
-
- private static native JavaScriptObject createDocumentFragment(
- JavaScriptObject doc) /*-{
- return doc.createDocumentFragment();
- }-*/;
-
- JavaScriptObject getDocumentFragment() {
- JavaScriptObject rv = createDocumentFragment(document);
- JavaScriptObject rootElt = getFirstChild(document);
- while (hasChildNodes(rootElt)) {
- appendChild(rv, getFirstChild(rootElt));
- }
- document = null;
- return rv;
- }
-
- /**
- * @see nu.validator.htmlparser.impl.TreeBuilder#createJavaScriptObject(String,
- * java.lang.String, org.xml.sax.Attributes, java.lang.Object)
- */
- @Override protected JavaScriptObject createElement(String ns, String name,
- HtmlAttributes attributes, JavaScriptObject form)
- throws SAXException {
- try {
- JavaScriptObject rv = createElement(ns, name, attributes);
- // rv.setUserData("nu.validator.form-pointer", form, null);
- return rv;
- } catch (JavaScriptException e) {
- fatal(e);
- return null;
- }
- }
-
- /**
- * @see nu.validator.htmlparser.impl.TreeBuilder#start()
- */
- @Override protected void start(boolean fragment) throws SAXException {
- script = null;
- placeholder = null;
- readyToRun = false;
- }
-
- protected void documentMode(DocumentMode mode, String publicIdentifier,
- String systemIdentifier)
- throws SAXException {
- // document.setUserData("nu.validator.document-mode", mode, null);
- }
-
- /**
- * @see nu.validator.htmlparser.impl.TreeBuilder#elementPopped(java.lang.String,
- * java.lang.String, java.lang.Object)
- */
- @Override protected void elementPopped(String ns, String name,
- JavaScriptObject node) throws SAXException {
- if (node == placeholder) {
- readyToRun = true;
- requestSuspension();
- }
- }
-
- private static native void replace(JavaScriptObject oldNode,
- JavaScriptObject newNode) /*-{
- oldNode.parentNode.replaceChild(newNode, oldNode);
- }-*/;
-
- private static native JavaScriptObject getPreviousSibling(JavaScriptObject node) /*-{
- return node.previousSibling;
- }-*/;
-
- void maybeRunScript() {
- if (readyToRun) {
- readyToRun = false;
- replace(placeholder, script);
- if (scriptStack.isEmpty()) {
- script = null;
- placeholder = null;
- } else {
- ScriptHolder scriptHolder = scriptStack.removeLast();
- script = scriptHolder.getScript();
- placeholder = scriptHolder.getPlaceholder();
- }
- }
- }
-
- @Override protected void insertFosterParentedCharacters(String text,
- JavaScriptObject table, JavaScriptObject stackParent)
- throws SAXException {
- try {
- JavaScriptObject parent = getParentNode(table);
- if (parent != null) { // always an element if not null
- JavaScriptObject previousSibling = getPreviousSibling(table);
- if (previousSibling != null
- && getNodeType(previousSibling) == 3) {
- extendTextNode(previousSibling, text);
- return;
- }
- insertBeforeNative(parent, createTextNode(document, text), table);
- return;
- }
- JavaScriptObject lastChild = getLastChild(stackParent);
- if (lastChild != null && getNodeType(lastChild) == 3) {
- extendTextNode(lastChild, text);
- return;
- }
- appendChild(stackParent, createTextNode(document, text));
- } catch (JavaScriptException e) {
- fatal(e);
- }
- }
-
- @Override protected void insertFosterParentedChild(JavaScriptObject child,
- JavaScriptObject table, JavaScriptObject stackParent)
- throws SAXException {
- JavaScriptObject parent = getParentNode(table);
- try {
- if (parent != null && getNodeType(parent) == 1) {
- insertBeforeNative(parent, child, table);
- } else {
- appendChild(stackParent, child);
- }
- } catch (JavaScriptException e) {
- fatal(e);
- }
- }
-
- private static native void removeChild(JavaScriptObject parent,
- JavaScriptObject child) /*-{
- parent.removeChild(child);
- }-*/;
-
- @Override protected void detachFromParent(JavaScriptObject element)
- throws SAXException {
- try {
- JavaScriptObject parent = getParentNode(element);
- if (parent != null) {
- removeChild(parent, element);
- }
- } catch (JavaScriptException e) {
- fatal(e);
- }
- }
-}
diff --git a/gwt-src/nu/validator/htmlparser/gwt/HtmlParser.java b/gwt-src/nu/validator/htmlparser/gwt/HtmlParser.java
deleted file mode 100644
index 1d71cdfd..00000000
--- a/gwt-src/nu/validator/htmlparser/gwt/HtmlParser.java
+++ /dev/null
@@ -1,265 +0,0 @@
-/*
- * Copyright (c) 2007 Henri Sivonen
- * Copyright (c) 2007-2008 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.gwt;
-
-import java.util.LinkedList;
-
-import nu.validator.htmlparser.common.XmlViolationPolicy;
-import nu.validator.htmlparser.impl.ErrorReportingTokenizer;
-import nu.validator.htmlparser.impl.Tokenizer;
-import nu.validator.htmlparser.impl.UTF16Buffer;
-
-import org.xml.sax.ErrorHandler;
-import org.xml.sax.SAXException;
-import org.xml.sax.SAXParseException;
-
-import com.google.gwt.core.client.JavaScriptObject;
-import com.google.gwt.user.client.Timer;
-
-/**
- * This class implements an HTML5 parser that exposes data through the DOM
- * interface.
- *
- *
By default, when using the constructor without arguments, the
- * this parser treats XML 1.0-incompatible infosets as fatal errors.
- * This corresponds to
- * FATAL as the general XML violation policy. To make the parser
- * support non-conforming HTML fully per the HTML 5 spec while on the other
- * hand potentially violating the DOM API contract, set the general XML
- * violation policy to ALLOW. This does not work with a standard
- * DOM implementation. Handling all input without fatal errors and without
- * violating the DOM API contract is possible by setting
- * the general XML violation policy to ALTER_INFOSET. This
- * makes the parser non-conforming but is probably the most useful
- * setting for most applications.
- *
- *
The doctype is not represented in the tree.
- *
- *
The document mode is represented as user data DocumentMode
- * object with the key nu.validator.document-mode on the document
- * node.
- *
- *
The form pointer is also stored as user data with the key
- * nu.validator.form-pointer.
- *
- * @version $Id: HtmlDocumentBuilder.java 255 2008-05-29 08:57:38Z hsivonen $
- * @author hsivonen
- */
-public class HtmlParser {
-
- private static final int CHUNK_SIZE = 512;
-
- private final Tokenizer tokenizer;
-
- private final BrowserTreeBuilder domTreeBuilder;
-
- private final StringBuilder documentWriteBuffer = new StringBuilder();
-
- private ErrorHandler errorHandler;
-
- private UTF16Buffer stream;
-
- private int streamLength;
-
- private boolean lastWasCR;
-
- private boolean ending;
-
- private ParseEndListener parseEndListener;
-
- private final LinkedList bufferStack = new LinkedList();
-
- /**
- * Instantiates the parser
- *
- * @param implementation
- * the DOM implementation
- * @param xmlPolicy the policy
- */
- public HtmlParser(JavaScriptObject document) {
- this.domTreeBuilder = new BrowserTreeBuilder(document);
- this.tokenizer = new ErrorReportingTokenizer(domTreeBuilder);
- this.domTreeBuilder.setNamePolicy(XmlViolationPolicy.ALTER_INFOSET);
- this.tokenizer.setCommentPolicy(XmlViolationPolicy.ALTER_INFOSET);
- this.tokenizer.setContentNonXmlCharPolicy(XmlViolationPolicy.ALTER_INFOSET);
- this.tokenizer.setContentSpacePolicy(XmlViolationPolicy.ALTER_INFOSET);
- this.tokenizer.setNamePolicy(XmlViolationPolicy.ALTER_INFOSET);
- this.tokenizer.setXmlnsPolicy(XmlViolationPolicy.ALTER_INFOSET);
- }
-
- /**
- * Parses a document from a SAX InputSource.
- * @param is the source
- * @return the doc
- * @see javax.xml.parsers.DocumentBuilder#parse(org.xml.sax.InputSource)
- */
- public void parse(String source, ParseEndListener callback) throws SAXException {
- parseEndListener = callback;
- domTreeBuilder.setFragmentContext(null);
- tokenize(source, null);
- }
-
- /**
- * @param is
- * @throws SAXException
- * @throws IOException
- * @throws MalformedURLException
- */
- private void tokenize(String source, String context) throws SAXException {
- lastWasCR = false;
- ending = false;
- documentWriteBuffer.setLength(0);
- streamLength = source.length();
- stream = new UTF16Buffer(source.toCharArray(), 0,
- (streamLength < CHUNK_SIZE ? streamLength : CHUNK_SIZE));
- bufferStack.clear();
- push(stream);
- domTreeBuilder.setFragmentContext(context == null ? null : context.intern());
- tokenizer.start();
- pump();
- }
-
- private void pump() throws SAXException {
- if (ending) {
- tokenizer.end();
- domTreeBuilder.getDocument(); // drops the internal reference
- parseEndListener.parseComplete();
- // Don't schedule timeout
- return;
- }
-
- int docWriteLen = documentWriteBuffer.length();
- if (docWriteLen > 0) {
- char[] newBuf = new char[docWriteLen];
- documentWriteBuffer.getChars(0, docWriteLen, newBuf, 0);
- push(new UTF16Buffer(newBuf, 0, docWriteLen));
- documentWriteBuffer.setLength(0);
- }
-
- for (;;) {
- UTF16Buffer buffer = peek();
- if (!buffer.hasMore()) {
- if (buffer == stream) {
- if (buffer.getEnd() == streamLength) {
- // Stop parsing
- tokenizer.eof();
- ending = true;
- break;
- } else {
- int newEnd = buffer.getStart() + CHUNK_SIZE;
- buffer.setEnd(newEnd < streamLength ? newEnd
- : streamLength);
- continue;
- }
- } else {
- pop();
- continue;
- }
- }
- // now we have a non-empty buffer
- buffer.adjust(lastWasCR);
- lastWasCR = false;
- if (buffer.hasMore()) {
- lastWasCR = tokenizer.tokenizeBuffer(buffer);
- domTreeBuilder.maybeRunScript();
- break;
- } else {
- continue;
- }
- }
-
- // schedule
- Timer timer = new Timer() {
-
- @Override public void run() {
- try {
- pump();
- } catch (SAXException e) {
- ending = true;
- if (errorHandler != null) {
- try {
- errorHandler.fatalError(new SAXParseException(
- e.getMessage(), null, null, -1, -1, e));
- } catch (SAXException e1) {
- }
- }
- }
- }
-
- };
- timer.schedule(1);
- }
-
- private void push(UTF16Buffer buffer) {
- bufferStack.addLast(buffer);
- }
-
- private UTF16Buffer peek() {
- return bufferStack.getLast();
- }
-
- private void pop() {
- bufferStack.removeLast();
- }
-
- public void documentWrite(String text) throws SAXException {
- UTF16Buffer buffer = new UTF16Buffer(text.toCharArray(), 0, text.length());
- while (buffer.hasMore()) {
- buffer.adjust(lastWasCR);
- lastWasCR = false;
- if (buffer.hasMore()) {
- lastWasCR = tokenizer.tokenizeBuffer(buffer);
- domTreeBuilder.maybeRunScript();
- }
- }
- }
-
- /**
- * @see javax.xml.parsers.DocumentBuilder#setErrorHandler(org.xml.sax.ErrorHandler)
- */
- public void setErrorHandler(ErrorHandler errorHandler) {
- this.errorHandler = errorHandler;
- domTreeBuilder.setErrorHandler(errorHandler);
- tokenizer.setErrorHandler(errorHandler);
- }
-
- /**
- * Sets whether comment nodes appear in the tree.
- * @param ignoreComments true to ignore comments
- * @see nu.validator.htmlparser.impl.TreeBuilder#setIgnoringComments(boolean)
- */
- public void setIgnoringComments(boolean ignoreComments) {
- domTreeBuilder.setIgnoringComments(ignoreComments);
- }
-
- /**
- * Sets whether the parser considers scripting to be enabled for noscript treatment.
- * @param scriptingEnabled true to enable
- * @see nu.validator.htmlparser.impl.TreeBuilder#setScriptingEnabled(boolean)
- */
- public void setScriptingEnabled(boolean scriptingEnabled) {
- domTreeBuilder.setScriptingEnabled(scriptingEnabled);
- }
-
-}
diff --git a/gwt-src/nu/validator/htmlparser/gwt/HtmlParserModule.java b/gwt-src/nu/validator/htmlparser/gwt/HtmlParserModule.java
deleted file mode 100644
index 255a02d1..00000000
--- a/gwt-src/nu/validator/htmlparser/gwt/HtmlParserModule.java
+++ /dev/null
@@ -1,87 +0,0 @@
-/*
- * Copyright (c) 2008 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.gwt;
-
-import org.xml.sax.SAXException;
-
-import com.google.gwt.core.client.EntryPoint;
-import com.google.gwt.core.client.JavaScriptObject;
-
-public class HtmlParserModule implements EntryPoint {
-
- private static native void zapChildren(JavaScriptObject node) /*-{
- while (node.hasChildNodes()) {
- node.removeChild(node.lastChild);
- }
- }-*/;
-
- private static native void installDocWrite(JavaScriptObject doc, HtmlParser parser) /*-{
- doc.write = function() {
- if (arguments.length == 0) {
- return;
- }
- var text = arguments[0];
- for (var i = 1; i < arguments.length; i++) {
- text += arguments[i];
- }
- parser.@nu.validator.htmlparser.gwt.HtmlParser::documentWrite(Ljava/lang/String;)(text);
- }
- doc.writeln = function() {
- if (arguments.length == 0) {
- parser.@nu.validator.htmlparser.gwt.HtmlParser::documentWrite(Ljava/lang/String;)("\n");
- return;
- }
- var text = arguments[0];
- for (var i = 1; i < arguments.length; i++) {
- text += arguments[i];
- }
- text += "\n";
- parser.@nu.validator.htmlparser.gwt.HtmlParser::documentWrite(Ljava/lang/String;)(text);
- }
- }-*/;
-
- @SuppressWarnings("unused")
- private static void parseHtmlDocument(String source, JavaScriptObject document, JavaScriptObject readyCallback, JavaScriptObject errorHandler) throws SAXException {
- if (readyCallback == null) {
- readyCallback = JavaScriptObject.createFunction();
- }
- zapChildren(document);
- HtmlParser parser = new HtmlParser(document);
- parser.setScriptingEnabled(true);
- // XXX error handler
-
- installDocWrite(document, parser);
-
- parser.parse(source, new ParseEndListener(readyCallback));
- }
-
- private static native void exportEntryPoints() /*-{
- $wnd.parseHtmlDocument = @nu.validator.htmlparser.gwt.HtmlParserModule::parseHtmlDocument(Ljava/lang/String;Lcom/google/gwt/core/client/JavaScriptObject;Lcom/google/gwt/core/client/JavaScriptObject;Lcom/google/gwt/core/client/JavaScriptObject;);
- }-*/;
-
-
- public void onModuleLoad() {
- exportEntryPoints();
- }
-
-}
diff --git a/gwt-src/nu/validator/htmlparser/public/HtmlParser.html b/gwt-src/nu/validator/htmlparser/public/HtmlParser.html
deleted file mode 100644
index 4d9cde81..00000000
--- a/gwt-src/nu/validator/htmlparser/public/HtmlParser.html
+++ /dev/null
@@ -1,225 +0,0 @@
-
-
-
- Live DOM Viewer
-
-
-
-
-
-
-
This script puts a function w(s) into the
- global scope of the test page, where s is a string to
- output to the log. Also, five files are accessible in the current
- directory for test purposes: image (a GIF image),
- flash (a Flash file), script (a JS file),
- style (a CSS file), and document (an HTML
- file).
-
-
\ No newline at end of file
diff --git a/gwt-src/nu/validator/htmlparser/public/LICENSE.Live-DOM-viewer.txt b/gwt-src/nu/validator/htmlparser/public/LICENSE.Live-DOM-viewer.txt
deleted file mode 100644
index bd2f4fcf..00000000
--- a/gwt-src/nu/validator/htmlparser/public/LICENSE.Live-DOM-viewer.txt
+++ /dev/null
@@ -1,25 +0,0 @@
-From:
-http://software.hixie.ch/utilities/js/live-dom-viewer/LICENSE
-regarding the upstream of HtmlParser.html:
-
-The MIT License
-
-Copyright (c) 2000, 2006, 2008 Ian Hickson and various contributors
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in
-all copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
-THE SOFTWARE.
diff --git a/gwt-src/nu/validator/htmlparser/public/blank.html b/gwt-src/nu/validator/htmlparser/public/blank.html
deleted file mode 100644
index a8756c9f..00000000
--- a/gwt-src/nu/validator/htmlparser/public/blank.html
+++ /dev/null
@@ -1,2 +0,0 @@
-
-
\ No newline at end of file
diff --git a/htmlparser/pom.xml b/htmlparser/pom.xml
new file mode 100644
index 00000000..3922ae75
--- /dev/null
+++ b/htmlparser/pom.xml
@@ -0,0 +1,134 @@
+
+
+ 4.0.0
+
+
+ nu.validator.htmlparser
+ parent
+ 2.0
+
+
+ htmlparser
+
+ htmlparser
+
+
+
+ nu.validator.htmlparser
+ saxtree
+
+
+ com.sdicons.jsontools
+ jsontools-core
+ 1.7
+ test
+
+
+
+
+
+
+ maven-resources-plugin
+
+
+ backup-tokenizer
+ process-sources
+
+ copy-resources
+
+
+ true
+ ${project.build.directory}/hotspot-backup
+
+
+ src/main/java/nu/validator/htmlparser/impl
+
+
+
+
+
+
+
+
+
+
+ org.codehaus.mojo
+ exec-maven-plugin
+
+
+ tokenizer-hotspot-workaround-javac
+ process-sources
+
+ exec
+
+
+ javac
+
+ ${project.basedir}/src/hotspot/java/nu/validator/htmlparser/generator/ApplyHotSpotWorkaround.java
+ -d
+ ${project.build.directory}/hotspot-classes
+
+
+
+
+ tokenizer-hotspot-workaround-java
+ process-sources
+
+ exec
+
+
+ java
+
+ -cp
+ ${project.build.directory}/hotspot-classes
+ nu.validator.htmlparser.generator.ApplyHotSpotWorkaround
+ ${project.build.sourceDirectory}/nu/validator/htmlparser/impl/Tokenizer.java
+ ${project.basedir}/src/hotspot/resources/HotSpotWorkaround.txt
+
+
+
+
+
+
+
+
diff --git a/translator-src/nu/validator/htmlparser/generator/ApplyHotSpotWorkaround.java b/htmlparser/src/hotspot/java/nu/validator/htmlparser/generator/ApplyHotSpotWorkaround.java
similarity index 100%
rename from translator-src/nu/validator/htmlparser/generator/ApplyHotSpotWorkaround.java
rename to htmlparser/src/hotspot/java/nu/validator/htmlparser/generator/ApplyHotSpotWorkaround.java
diff --git a/src/nu/validator/htmlparser/impl/HotSpotWorkaround.txt b/htmlparser/src/hotspot/resources/HotSpotWorkaround.txt
similarity index 100%
rename from src/nu/validator/htmlparser/impl/HotSpotWorkaround.txt
rename to htmlparser/src/hotspot/resources/HotSpotWorkaround.txt
diff --git a/htmlparser/src/main/java/module-info.java b/htmlparser/src/main/java/module-info.java
new file mode 100644
index 00000000..a9e5f2ef
--- /dev/null
+++ b/htmlparser/src/main/java/module-info.java
@@ -0,0 +1,40 @@
+/*
+ * Copyright (c) 2020 Anthony Vanelverdinghe
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/**
+ * Provides an implementation of the HTML5 parsing algorithm in Java for applications.
+ * The parser is designed to work as a drop-in replacement for the XML parser in applications
+ * that already support XHTML 1.x content with an XML parser and use SAX or DOM to interface with the parser.
+ */
+module nu.validator.htmlparser {
+ requires transitive java.xml;
+ requires nu.validator.saxtree;
+
+ exports nu.validator.htmlparser.annotation;
+ exports nu.validator.htmlparser.common;
+ exports nu.validator.htmlparser.dom;
+ exports nu.validator.htmlparser.extra;
+ exports nu.validator.htmlparser.impl;
+ exports nu.validator.htmlparser.io;
+ exports nu.validator.htmlparser.rewindable;
+ exports nu.validator.htmlparser.sax;
+}
diff --git a/src/nu/validator/htmlparser/annotation/Auto.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/Auto.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/Auto.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/Auto.java
diff --git a/src/nu/validator/htmlparser/annotation/CharacterName.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/CharacterName.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/CharacterName.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/CharacterName.java
diff --git a/src/nu/validator/htmlparser/annotation/Const.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/Const.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/Const.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/Const.java
diff --git a/src/nu/validator/htmlparser/annotation/Creator.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/Creator.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/Creator.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/Creator.java
diff --git a/src/nu/validator/htmlparser/annotation/HtmlCreator.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/HtmlCreator.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/HtmlCreator.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/HtmlCreator.java
diff --git a/src/nu/validator/htmlparser/annotation/IdType.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/IdType.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/IdType.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/IdType.java
diff --git a/src/nu/validator/htmlparser/annotation/Inline.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/Inline.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/Inline.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/Inline.java
diff --git a/src/nu/validator/htmlparser/annotation/Literal.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/Literal.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/Literal.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/Literal.java
diff --git a/src/nu/validator/htmlparser/annotation/Local.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/Local.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/Local.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/Local.java
diff --git a/src/nu/validator/htmlparser/annotation/NoLength.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/NoLength.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/NoLength.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/NoLength.java
diff --git a/src/nu/validator/htmlparser/annotation/NsUri.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/NsUri.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/NsUri.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/NsUri.java
diff --git a/src/nu/validator/htmlparser/annotation/Prefix.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/Prefix.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/Prefix.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/Prefix.java
diff --git a/src/nu/validator/htmlparser/annotation/QName.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/QName.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/QName.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/QName.java
diff --git a/src/nu/validator/htmlparser/annotation/SvgCreator.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/SvgCreator.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/SvgCreator.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/SvgCreator.java
diff --git a/src/nu/validator/htmlparser/annotation/Unsigned.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/Unsigned.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/Unsigned.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/Unsigned.java
diff --git a/src/nu/validator/htmlparser/annotation/Virtual.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/Virtual.java
similarity index 100%
rename from src/nu/validator/htmlparser/annotation/Virtual.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/annotation/Virtual.java
diff --git a/htmlparser/src/main/java/nu/validator/htmlparser/annotation/package-info.java b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/package-info.java
new file mode 100644
index 00000000..ca70c00b
--- /dev/null
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/annotation/package-info.java
@@ -0,0 +1,27 @@
+/*
+ Copyright (c) 2008 Mozilla Foundation
+
+ Permission is hereby granted, free of charge, to any person obtaining a
+ copy of this software and associated documentation files (the "Software"),
+ to deal in the Software without restriction, including without limitation
+ the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ and/or sell copies of the Software, and to permit persons to whom the
+ Software is furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ DEALINGS IN THE SOFTWARE.
+ */
+
+/**
+ * This package provides annotations for facilitating automated translation
+ * of the source code into other programming languages.
+ */
+package nu.validator.htmlparser.annotation;
diff --git a/src/nu/validator/htmlparser/common/ByteReadable.java b/htmlparser/src/main/java/nu/validator/htmlparser/common/ByteReadable.java
old mode 100755
new mode 100644
similarity index 100%
rename from src/nu/validator/htmlparser/common/ByteReadable.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/ByteReadable.java
diff --git a/src/nu/validator/htmlparser/common/CharacterHandler.java b/htmlparser/src/main/java/nu/validator/htmlparser/common/CharacterHandler.java
similarity index 100%
rename from src/nu/validator/htmlparser/common/CharacterHandler.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/CharacterHandler.java
diff --git a/src/nu/validator/htmlparser/common/DocumentMode.java b/htmlparser/src/main/java/nu/validator/htmlparser/common/DocumentMode.java
similarity index 100%
rename from src/nu/validator/htmlparser/common/DocumentMode.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/DocumentMode.java
diff --git a/src/nu/validator/htmlparser/common/DocumentModeHandler.java b/htmlparser/src/main/java/nu/validator/htmlparser/common/DocumentModeHandler.java
similarity index 100%
rename from src/nu/validator/htmlparser/common/DocumentModeHandler.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/DocumentModeHandler.java
diff --git a/src/nu/validator/htmlparser/common/EncodingDeclarationHandler.java b/htmlparser/src/main/java/nu/validator/htmlparser/common/EncodingDeclarationHandler.java
similarity index 100%
rename from src/nu/validator/htmlparser/common/EncodingDeclarationHandler.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/EncodingDeclarationHandler.java
diff --git a/src/nu/validator/htmlparser/common/Heuristics.java b/htmlparser/src/main/java/nu/validator/htmlparser/common/Heuristics.java
similarity index 100%
rename from src/nu/validator/htmlparser/common/Heuristics.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/Heuristics.java
diff --git a/src/nu/validator/htmlparser/common/Interner.java b/htmlparser/src/main/java/nu/validator/htmlparser/common/Interner.java
similarity index 100%
rename from src/nu/validator/htmlparser/common/Interner.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/Interner.java
diff --git a/src/nu/validator/htmlparser/common/TokenHandler.java b/htmlparser/src/main/java/nu/validator/htmlparser/common/TokenHandler.java
old mode 100755
new mode 100644
similarity index 100%
rename from src/nu/validator/htmlparser/common/TokenHandler.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/TokenHandler.java
diff --git a/src/nu/validator/htmlparser/common/TransitionHandler.java b/htmlparser/src/main/java/nu/validator/htmlparser/common/TransitionHandler.java
similarity index 100%
rename from src/nu/validator/htmlparser/common/TransitionHandler.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/TransitionHandler.java
diff --git a/src/nu/validator/htmlparser/common/XmlViolationPolicy.java b/htmlparser/src/main/java/nu/validator/htmlparser/common/XmlViolationPolicy.java
similarity index 100%
rename from src/nu/validator/htmlparser/common/XmlViolationPolicy.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/XmlViolationPolicy.java
diff --git a/test-src/nu/validator/htmlparser/tools/package.html b/htmlparser/src/main/java/nu/validator/htmlparser/common/package-info.java
similarity index 86%
rename from test-src/nu/validator/htmlparser/tools/package.html
rename to htmlparser/src/main/java/nu/validator/htmlparser/common/package-info.java
index a04bf3cd..0d04ee70 100644
--- a/test-src/nu/validator/htmlparser/tools/package.html
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/common/package-info.java
@@ -1,7 +1,4 @@
-
-
-Package Overview
-
-
-
-
Demo apps.
-
-
\ No newline at end of file
+ */
+
+/**
+ * This package provides common interfaces and enumerations.
+ */
+package nu.validator.htmlparser.common;
diff --git a/src/nu/validator/htmlparser/dom/DOMTreeBuilder.java b/htmlparser/src/main/java/nu/validator/htmlparser/dom/DOMTreeBuilder.java
similarity index 100%
rename from src/nu/validator/htmlparser/dom/DOMTreeBuilder.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/dom/DOMTreeBuilder.java
diff --git a/src/nu/validator/htmlparser/dom/Dom2Sax.java b/htmlparser/src/main/java/nu/validator/htmlparser/dom/Dom2Sax.java
similarity index 100%
rename from src/nu/validator/htmlparser/dom/Dom2Sax.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/dom/Dom2Sax.java
diff --git a/src/nu/validator/htmlparser/dom/HtmlDocumentBuilder.java b/htmlparser/src/main/java/nu/validator/htmlparser/dom/HtmlDocumentBuilder.java
similarity index 98%
rename from src/nu/validator/htmlparser/dom/HtmlDocumentBuilder.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/dom/HtmlDocumentBuilder.java
index 1674aa72..cbeccb51 100644
--- a/src/nu/validator/htmlparser/dom/HtmlDocumentBuilder.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/dom/HtmlDocumentBuilder.java
@@ -375,7 +375,7 @@ public void setTransitionHander(TransitionHandler handler) {
/**
* Indicates whether NFC normalization of source is being checked.
* @return true if NFC normalization of source is being checked.
- * @see nu.validator.htmlparser.impl.Tokenizer#isCheckingNormalization()
+ * @see nu.validator.htmlparser.io.Driver#isCheckingNormalization()
*/
public boolean isCheckingNormalization() {
return checkingNormalization;
@@ -384,7 +384,7 @@ public boolean isCheckingNormalization() {
/**
* Toggles the checking of the NFC normalization of source.
* @param enable true to check normalization
- * @see nu.validator.htmlparser.impl.Tokenizer#setCheckingNormalization(boolean)
+ * @see nu.validator.htmlparser.io.Driver#setCheckingNormalization(boolean)
*/
public void setCheckingNormalization(boolean enable) {
this.checkingNormalization = enable;
@@ -609,7 +609,7 @@ public void setNamePolicy(XmlViolationPolicy namePolicy) {
* Sets the encoding sniffing heuristics.
*
* @param heuristics the heuristics to set
- * @see nu.validator.htmlparser.impl.Tokenizer#setHeuristics(nu.validator.htmlparser.common.Heuristics)
+ * @see nu.validator.htmlparser.io.Driver#setHeuristics(nu.validator.htmlparser.common.Heuristics)
*/
public void setHeuristics(Heuristics heuristics) {
this.heuristics = heuristics;
@@ -650,6 +650,7 @@ public XmlViolationPolicy getNamePolicy() {
* Does nothing.
* @deprecated
*/
+ @Deprecated
public void setBogusXmlnsPolicy(
XmlViolationPolicy bogusXmlnsPolicy) {
}
@@ -659,6 +660,7 @@ public void setBogusXmlnsPolicy(
* @deprecated
* @return XmlViolationPolicy.ALTER_INFOSET
*/
+ @Deprecated
public XmlViolationPolicy getBogusXmlnsPolicy() {
return XmlViolationPolicy.ALTER_INFOSET;
}
diff --git a/test-src/nu/validator/htmlparser/test/package.html b/htmlparser/src/main/java/nu/validator/htmlparser/dom/package-info.java
similarity index 85%
rename from test-src/nu/validator/htmlparser/test/package.html
rename to htmlparser/src/main/java/nu/validator/htmlparser/dom/package-info.java
index 57809b84..8d874fd0 100644
--- a/test-src/nu/validator/htmlparser/test/package.html
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/dom/package-info.java
@@ -1,7 +1,4 @@
-
-
-Package Overview
-
-
-
-
Test drivers.
-
-
\ No newline at end of file
+ */
+
+/**
+ * This package provides an HTML5 parser that exposes the document using the DOM API.
+ */
+package nu.validator.htmlparser.dom;
diff --git a/htmlparser/src/main/java/nu/validator/htmlparser/extra/NormalizationChecker.java b/htmlparser/src/main/java/nu/validator/htmlparser/extra/NormalizationChecker.java
new file mode 100644
index 00000000..44016348
--- /dev/null
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/extra/NormalizationChecker.java
@@ -0,0 +1,342 @@
+/*
+ * Copyright (c) 2006, 2007 Henri Sivonen
+ * Copyright (c) 2007 Mozilla Foundation
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+package nu.validator.htmlparser.extra;
+
+import nu.validator.htmlparser.common.CharacterHandler;
+
+import java.text.Normalizer;
+import java.util.Arrays;
+import java.util.HashSet;
+import java.util.Set;
+
+import org.xml.sax.ErrorHandler;
+import org.xml.sax.Locator;
+import org.xml.sax.SAXException;
+import org.xml.sax.SAXParseException;
+
+/**
+ * @version $Id$
+ * @author hsivonen
+ */
+public final class NormalizationChecker implements CharacterHandler {
+
+ private ErrorHandler errorHandler;
+
+ private Locator locator;
+
+ /**
+ * A set of composing characters as per Charmod Norm.
+ *
+ * Generated with ICU4J 67.1 using: new UnicodeSet("[[:nfc_qc=maybe:][:^ccc=0:]]").freeze()
+ */
+ private static final Set COMPOSING_CHARACTERS = new HashSet(Arrays.asList(
+ 768, 769, 770, 771, 772, 773, 774, 775, 776, 777, 778, 779, 780, 781, 782, 783, 784, 785,
+ 786, 787, 788, 789, 790, 791, 792, 793, 794, 795, 796, 797, 798, 799, 800, 801, 802, 803,
+ 804, 805, 806, 807, 808, 809, 810, 811, 812, 813, 814, 815, 816, 817, 818, 819, 820, 821,
+ 822, 823, 824, 825, 826, 827, 828, 829, 830, 831, 832, 833, 834, 835, 836, 837, 838, 839,
+ 840, 841, 842, 843, 844, 845, 846, 848, 849, 850, 851, 852, 853, 854, 855, 856, 857, 858,
+ 859, 860, 861, 862, 863, 864, 865, 866, 867, 868, 869, 870, 871, 872, 873, 874, 875, 876,
+ 877, 878, 879, 1155, 1156, 1157, 1158, 1159, 1425, 1426, 1427, 1428, 1429, 1430, 1431, 1432,
+ 1433, 1434, 1435, 1436, 1437, 1438, 1439, 1440, 1441, 1442, 1443, 1444, 1445, 1446, 1447,
+ 1448, 1449, 1450, 1451, 1452, 1453, 1454, 1455, 1456, 1457, 1458, 1459, 1460, 1461, 1462,
+ 1463, 1464, 1465, 1466, 1467, 1468, 1469, 1471, 1473, 1474, 1476, 1477, 1479, 1552, 1553,
+ 1554, 1555, 1556, 1557, 1558, 1559, 1560, 1561, 1562, 1611, 1612, 1613, 1614, 1615, 1616,
+ 1617, 1618, 1619, 1620, 1621, 1622, 1623, 1624, 1625, 1626, 1627, 1628, 1629, 1630, 1631,
+ 1648, 1750, 1751, 1752, 1753, 1754, 1755, 1756, 1759, 1760, 1761, 1762, 1763, 1764, 1767,
+ 1768, 1770, 1771, 1772, 1773, 1809, 1840, 1841, 1842, 1843, 1844, 1845, 1846, 1847, 1848,
+ 1849, 1850, 1851, 1852, 1853, 1854, 1855, 1856, 1857, 1858, 1859, 1860, 1861, 1862, 1863,
+ 1864, 1865, 1866, 2027, 2028, 2029, 2030, 2031, 2032, 2033, 2034, 2035, 2045, 2070, 2071,
+ 2072, 2073, 2075, 2076, 2077, 2078, 2079, 2080, 2081, 2082, 2083, 2085, 2086, 2087, 2089,
+ 2090, 2091, 2092, 2093, 2137, 2138, 2139, 2259, 2260, 2261, 2262, 2263, 2264, 2265, 2266,
+ 2267, 2268, 2269, 2270, 2271, 2272, 2273, 2275, 2276, 2277, 2278, 2279, 2280, 2281, 2282,
+ 2283, 2284, 2285, 2286, 2287, 2288, 2289, 2290, 2291, 2292, 2293, 2294, 2295, 2296, 2297,
+ 2298, 2299, 2300, 2301, 2302, 2303, 2364, 2381, 2385, 2386, 2387, 2388, 2492, 2494, 2509,
+ 2519, 2558, 2620, 2637, 2748, 2765, 2876, 2878, 2893, 2902, 2903, 3006, 3021, 3031, 3149,
+ 3157, 3158, 3260, 3266, 3277, 3285, 3286, 3387, 3388, 3390, 3405, 3415, 3530, 3535, 3551,
+ 3640, 3641, 3642, 3656, 3657, 3658, 3659, 3768, 3769, 3770, 3784, 3785, 3786, 3787, 3864,
+ 3865, 3893, 3895, 3897, 3953, 3954, 3956, 3962, 3963, 3964, 3965, 3968, 3970, 3971, 3972,
+ 3974, 3975, 4038, 4142, 4151, 4153, 4154, 4237, 4449, 4450, 4451, 4452, 4453, 4454, 4455,
+ 4456, 4457, 4458, 4459, 4460, 4461, 4462, 4463, 4464, 4465, 4466, 4467, 4468, 4469, 4520,
+ 4521, 4522, 4523, 4524, 4525, 4526, 4527, 4528, 4529, 4530, 4531, 4532, 4533, 4534, 4535,
+ 4536, 4537, 4538, 4539, 4540, 4541, 4542, 4543, 4544, 4545, 4546, 4957, 4958, 4959, 5908,
+ 5940, 6098, 6109, 6313, 6457, 6458, 6459, 6679, 6680, 6752, 6773, 6774, 6775, 6776, 6777,
+ 6778, 6779, 6780, 6783, 6832, 6833, 6834, 6835, 6836, 6837, 6838, 6839, 6840, 6841, 6842,
+ 6843, 6844, 6845, 6847, 6848, 6964, 6965, 6980, 7019, 7020, 7021, 7022, 7023, 7024, 7025,
+ 7026, 7027, 7082, 7083, 7142, 7154, 7155, 7223, 7376, 7377, 7378, 7380, 7381, 7382, 7383,
+ 7384, 7385, 7386, 7387, 7388, 7389, 7390, 7391, 7392, 7394, 7395, 7396, 7397, 7398, 7399,
+ 7400, 7405, 7412, 7416, 7417, 7616, 7617, 7618, 7619, 7620, 7621, 7622, 7623, 7624, 7625,
+ 7626, 7627, 7628, 7629, 7630, 7631, 7632, 7633, 7634, 7635, 7636, 7637, 7638, 7639, 7640,
+ 7641, 7642, 7643, 7644, 7645, 7646, 7647, 7648, 7649, 7650, 7651, 7652, 7653, 7654, 7655,
+ 7656, 7657, 7658, 7659, 7660, 7661, 7662, 7663, 7664, 7665, 7666, 7667, 7668, 7669, 7670,
+ 7671, 7672, 7673, 7675, 7676, 7677, 7678, 7679, 8400, 8401, 8402, 8403, 8404, 8405, 8406,
+ 8407, 8408, 8409, 8410, 8411, 8412, 8417, 8421, 8422, 8423, 8424, 8425, 8426, 8427, 8428,
+ 8429, 8430, 8431, 8432, 11503, 11504, 11505, 11647, 11744, 11745, 11746, 11747, 11748, 11749,
+ 11750, 11751, 11752, 11753, 11754, 11755, 11756, 11757, 11758, 11759, 11760, 11761, 11762,
+ 11763, 11764, 11765, 11766, 11767, 11768, 11769, 11770, 11771, 11772, 11773, 11774, 11775,
+ 12330, 12331, 12332, 12333, 12334, 12335, 12441, 12442, 42607, 42612, 42613, 42614, 42615,
+ 42616, 42617, 42618, 42619, 42620, 42621, 42654, 42655, 42736, 42737, 43014, 43052, 43204,
+ 43232, 43233, 43234, 43235, 43236, 43237, 43238, 43239, 43240, 43241, 43242, 43243, 43244,
+ 43245, 43246, 43247, 43248, 43249, 43307, 43308, 43309, 43347, 43443, 43456, 43696, 43698,
+ 43699, 43700, 43703, 43704, 43710, 43711, 43713, 43766, 44013, 64286, 65056, 65057, 65058,
+ 65059, 65060, 65061, 65062, 65063, 65064, 65065, 65066, 65067, 65068, 65069, 65070, 65071,
+ 66045, 66272, 66422, 66423, 66424, 66425, 66426, 68109, 68111, 68152, 68153, 68154, 68159,
+ 68325, 68326, 68900, 68901, 68902, 68903, 69291, 69292, 69446, 69447, 69448, 69449, 69450,
+ 69451, 69452, 69453, 69454, 69455, 69456, 69702, 69759, 69817, 69818, 69888, 69889, 69890,
+ 69927, 69939, 69940, 70003, 70080, 70090, 70197, 70198, 70377, 70378, 70459, 70460, 70462,
+ 70477, 70487, 70502, 70503, 70504, 70505, 70506, 70507, 70508, 70512, 70513, 70514, 70515,
+ 70516, 70722, 70726, 70750, 70832, 70842, 70845, 70850, 70851, 71087, 71103, 71104, 71231,
+ 71350, 71351, 71467, 71737, 71738, 71984, 71997, 71998, 72003, 72160, 72244, 72263, 72345,
+ 72767, 73026, 73028, 73029, 73111, 92912, 92913, 92914, 92915, 92916, 92976, 92977, 92978,
+ 92979, 92980, 92981, 92982, 94192, 94193, 113822, 119141, 119142, 119143, 119144, 119145,
+ 119149, 119150, 119151, 119152, 119153, 119154, 119163, 119164, 119165, 119166, 119167,
+ 119168, 119169, 119170, 119173, 119174, 119175, 119176, 119177, 119178, 119179, 119210,
+ 119211, 119212, 119213, 119362, 119363, 119364, 122880, 122881, 122882, 122883, 122884,
+ 122885, 122886, 122888, 122889, 122890, 122891, 122892, 122893, 122894, 122895, 122896,
+ 122897, 122898, 122899, 122900, 122901, 122902, 122903, 122904, 122907, 122908, 122909,
+ 122910, 122911, 122912, 122913, 122915, 122916, 122918, 122919, 122920, 122921, 122922,
+ 123184, 123185, 123186, 123187, 123188, 123189, 123190, 123628, 123629, 123630, 123631,
+ 125136, 125137, 125138, 125139, 125140, 125141, 125142, 125252, 125253, 125254, 125255,
+ 125256, 125257, 125258
+ ));
+
+ // see http://sourceforge.net/mailarchive/message.php?msg_id=37279908
+
+ /**
+ * A buffer for holding sequences overlap the SAX buffer boundary.
+ */
+ private char[] buf = new char[128];
+
+ /**
+ * A holder for the original buffer (for the memory leak prevention
+ * mechanism).
+ */
+ private char[] bufHolder = null;
+
+ /**
+ * The current used length of the buffer, i.e. the index of the first slot
+ * that does not hold current data.
+ */
+ private int pos;
+
+ /**
+ * Indicates whether the checker the next call to characters()
+ * is the first call in a run.
+ */
+ private boolean atStartOfRun;
+
+ /**
+ * Indicates whether the current run has already caused an error.
+ */
+ private boolean alreadyComplainedAboutThisRun;
+
+ /**
+ * Emit an error. The locator is used.
+ *
+ * @param message the error message
+ * @throws SAXException if something goes wrong
+ */
+ public void err(String message) throws SAXException {
+ if (errorHandler != null) {
+ SAXParseException spe = new SAXParseException(message, locator);
+ errorHandler.error(spe);
+ }
+ }
+
+ /**
+ * Returns true if the argument is a composing BMP character
+ * or a surrogate and false otherwise.
+ *
+ * @param c a UTF-16 code unit
+ * @return true if the argument is a composing BMP character
+ * or a surrogate and false otherwise
+ */
+ private static boolean isComposingCharOrSurrogate(char c) {
+ if (Character.isHighSurrogate(c) || Character.isLowSurrogate(c)) {
+ return true;
+ }
+ return isComposingChar(c);
+ }
+
+ /**
+ * Returns true if the argument is a composing character
+ * and false otherwise.
+ *
+ * @param c a Unicode code point
+ * @return true if the argument is a composing character
+ * false otherwise
+ */
+ private static boolean isComposingChar(int c) {
+ return COMPOSING_CHARACTERS.contains(c);
+ }
+
+ /**
+ * Constructor with locator.
+ *
+ * @param locator
+ */
+ public NormalizationChecker(Locator locator) {
+ super();
+ start();
+ }
+
+ /**
+ * @see nu.validator.htmlparser.common.CharacterHandler#start()
+ */
+ public void start() {
+ atStartOfRun = true;
+ alreadyComplainedAboutThisRun = false;
+ pos = 0;
+ }
+
+ /**
+ * @see nu.validator.htmlparser.common.CharacterHandler#characters(char[], int, int)
+ */
+ public void characters(char[] ch, int start, int length)
+ throws SAXException {
+ if (alreadyComplainedAboutThisRun) {
+ return;
+ }
+ if (atStartOfRun) {
+ char c = ch[start];
+ if (pos == 1) {
+ // there's a single high surrogate in buf
+ if (isComposingChar(getCodePoint(buf[0], c))) {
+ err("Text run starts with a composing character.");
+ }
+ atStartOfRun = false;
+ } else {
+ if (length == 1 && Character.isHighSurrogate(c)) {
+ buf[0] = c;
+ pos = 1;
+ return;
+ } else {
+ if (Character.isHighSurrogate(c)) {
+ if (isComposingChar(getCodePoint(c, ch[start + 1]))) {
+ err("Text run starts with a composing character.");
+ }
+ } else {
+ if (isComposingCharOrSurrogate(c)) {
+ err("Text run starts with a composing character.");
+ }
+ }
+ atStartOfRun = false;
+ }
+ }
+ }
+ int i = start;
+ int stop = start + length;
+ if (pos > 0) {
+ // there's stuff in buf
+ while (i < stop && isComposingCharOrSurrogate(ch[i])) {
+ i++;
+ }
+ appendToBuf(ch, start, i);
+ if (i == stop) {
+ return;
+ } else {
+ if (!Normalizer.isNormalized(new String(buf, 0, pos), Normalizer.Form.NFC)) {
+ errAboutTextRun();
+ }
+ pos = 0;
+ }
+ }
+ if (i < stop) {
+ start = i;
+ i = stop - 1;
+ while (i > start && isComposingCharOrSurrogate(ch[i])) {
+ i--;
+ }
+ if (i > start) {
+ if (!Normalizer.isNormalized(new String(ch, start, i), Normalizer.Form.NFC)) {
+ errAboutTextRun();
+ }
+ }
+ appendToBuf(ch, i, stop);
+ }
+ }
+
+ private static int getCodePoint(char lead, char trail) {
+ if (Character.isSurrogatePair(lead, trail)) {
+ return Character.toCodePoint(lead, trail);
+ }
+ throw new IllegalArgumentException("Illegal surrogate characters");
+ }
+
+ /**
+ * Emits an error stating that the current text run or the source
+ * text is not in NFC.
+ *
+ * @throws SAXException if the ErrorHandler throws
+ */
+ private void errAboutTextRun() throws SAXException {
+ err("Source text is not in Unicode Normalization Form C.");
+ alreadyComplainedAboutThisRun = true;
+ }
+
+ /**
+ * Appends a slice of an UTF-16 code unit array to the internal
+ * buffer.
+ *
+ * @param ch the array from which to copy
+ * @param start the index of the first element that is copied
+ * @param end the index of the first element that is not copied
+ */
+ private void appendToBuf(char[] ch, int start, int end) {
+ if (start == end) {
+ return;
+ }
+ int neededBufLen = pos + (end - start);
+ if (neededBufLen > buf.length) {
+ char[] newBuf = new char[neededBufLen];
+ System.arraycopy(buf, 0, newBuf, 0, pos);
+ if (bufHolder == null) {
+ bufHolder = buf; // keep the original around
+ }
+ buf = newBuf;
+ }
+ System.arraycopy(ch, start, buf, pos, end - start);
+ pos += (end - start);
+ }
+
+ /**
+ * @see nu.validator.htmlparser.common.CharacterHandler#end()
+ */
+ public void end() throws SAXException {
+ if (!alreadyComplainedAboutThisRun
+ && !Normalizer.isNormalized(new String(buf, 0, pos), Normalizer.Form.NFC)) {
+ errAboutTextRun();
+ }
+ if (bufHolder != null) {
+ // restore the original small buffer to avoid leaking
+ // memory if this checker is recycled
+ buf = bufHolder;
+ bufHolder = null;
+ }
+ }
+
+ public void setErrorHandler(ErrorHandler errorHandler) {
+ this.errorHandler = errorHandler;
+ }
+
+}
diff --git a/src/nu/validator/htmlparser/impl/AttributeName.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/AttributeName.java
similarity index 99%
rename from src/nu/validator/htmlparser/impl/AttributeName.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/AttributeName.java
index ca748713..1f8ce5e4 100644
--- a/src/nu/validator/htmlparser/impl/AttributeName.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/impl/AttributeName.java
@@ -22,11 +22,6 @@
package nu.validator.htmlparser.impl;
-import java.util.Arrays;
-import java.util.Collections;
-import java.util.LinkedList;
-import java.util.List;
-
import nu.validator.htmlparser.annotation.Inline;
import nu.validator.htmlparser.annotation.Local;
import nu.validator.htmlparser.annotation.NoLength;
diff --git a/src/nu/validator/htmlparser/impl/CoalescingTreeBuilder.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/CoalescingTreeBuilder.java
similarity index 100%
rename from src/nu/validator/htmlparser/impl/CoalescingTreeBuilder.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/CoalescingTreeBuilder.java
diff --git a/src/nu/validator/htmlparser/impl/ElementName.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/ElementName.java
similarity index 100%
rename from src/nu/validator/htmlparser/impl/ElementName.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/ElementName.java
diff --git a/src/nu/validator/htmlparser/impl/ErrorReportingTokenizer.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/ErrorReportingTokenizer.java
similarity index 99%
rename from src/nu/validator/htmlparser/impl/ErrorReportingTokenizer.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/ErrorReportingTokenizer.java
index 19fbe7a6..4c41e33a 100644
--- a/src/nu/validator/htmlparser/impl/ErrorReportingTokenizer.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/impl/ErrorReportingTokenizer.java
@@ -128,7 +128,7 @@ public void setContentNonXmlCharPolicy(
/**
* Sets the errorProfile.
*
- * @param errorProfile
+ * @param errorProfileMap
*/
public void setErrorProfile(HashMap errorProfileMap) {
this.errorProfileMap = errorProfileMap;
@@ -225,6 +225,7 @@ public boolean isNextCharOnNewLine() {
cstart = 0x7fffffff;
}
+ @SuppressWarnings("fallthrough")
@Override protected char checkChar(@NoLength char[] buf, int pos)
throws SAXException {
linePrev = line;
@@ -564,6 +565,7 @@ private boolean isAstralPrivateUse(int c) {
}
}
+ @SuppressWarnings("fallthrough")
@Override protected char errNcrNonCharacter(char ch) throws SAXException {
switch (contentNonXmlCharPolicy) {
case FATAL:
@@ -592,6 +594,7 @@ private boolean isAstralPrivateUse(int c) {
err("Character reference expands to a surrogate.");
}
+ @SuppressWarnings("fallthrough")
@Override protected char errNcrControlChar(char ch) throws SAXException {
switch (contentNonXmlCharPolicy) {
case FATAL:
diff --git a/src/nu/validator/htmlparser/impl/HtmlAttributes.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/HtmlAttributes.java
similarity index 99%
rename from src/nu/validator/htmlparser/impl/HtmlAttributes.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/HtmlAttributes.java
index 7f747c3a..5401f233 100644
--- a/src/nu/validator/htmlparser/impl/HtmlAttributes.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/impl/HtmlAttributes.java
@@ -31,7 +31,6 @@
import nu.validator.htmlparser.annotation.NsUri;
import nu.validator.htmlparser.annotation.Prefix;
import nu.validator.htmlparser.annotation.QName;
-import nu.validator.htmlparser.common.Interner;
import nu.validator.htmlparser.common.XmlViolationPolicy;
/**
@@ -482,6 +481,7 @@ public boolean equalsAnother(HtmlAttributes other) {
return true;
}
+ @SuppressWarnings("fallthrough")
void processNonNcNames(TreeBuilder treeBuilder, XmlViolationPolicy namePolicy) throws SAXException {
for (int i = 0; i < length; i++) {
AttributeName attName = names[i];
diff --git a/src/nu/validator/htmlparser/impl/LocatorImpl.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/LocatorImpl.java
similarity index 97%
rename from src/nu/validator/htmlparser/impl/LocatorImpl.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/LocatorImpl.java
index b334aa6a..29bb8c72 100644
--- a/src/nu/validator/htmlparser/impl/LocatorImpl.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/impl/LocatorImpl.java
@@ -26,7 +26,7 @@
import org.xml.sax.Locator;
import org.xml.sax.ext.Locator2;
-public class LocatorImpl implements Locator, Locator2 {
+public class LocatorImpl implements Locator2 {
private final String systemId;
diff --git a/src/nu/validator/htmlparser/impl/MetaScanner.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/MetaScanner.java
old mode 100755
new mode 100644
similarity index 99%
rename from src/nu/validator/htmlparser/impl/MetaScanner.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/MetaScanner.java
index a1c8eb80..10c24e40
--- a/src/nu/validator/htmlparser/impl/MetaScanner.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/impl/MetaScanner.java
@@ -208,6 +208,7 @@ protected int read() throws IOException {
/**
* The runs the meta scanning algorithm.
*/
+ @SuppressWarnings("fallthrough")
protected final void stateLoop(int state)
throws SAXException, IOException {
int c = -1;
diff --git a/src/nu/validator/htmlparser/impl/NCName.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/NCName.java
similarity index 100%
rename from src/nu/validator/htmlparser/impl/NCName.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/NCName.java
diff --git a/src/nu/validator/htmlparser/impl/NamedCharacters.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/NamedCharacters.java
old mode 100755
new mode 100644
similarity index 100%
rename from src/nu/validator/htmlparser/impl/NamedCharacters.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/NamedCharacters.java
diff --git a/src/nu/validator/htmlparser/impl/NamedCharactersAccel.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/NamedCharactersAccel.java
similarity index 100%
rename from src/nu/validator/htmlparser/impl/NamedCharactersAccel.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/NamedCharactersAccel.java
diff --git a/src/nu/validator/htmlparser/impl/Portability.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/Portability.java
similarity index 100%
rename from src/nu/validator/htmlparser/impl/Portability.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/Portability.java
diff --git a/src/nu/validator/htmlparser/impl/PushedLocation.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/PushedLocation.java
similarity index 100%
rename from src/nu/validator/htmlparser/impl/PushedLocation.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/PushedLocation.java
diff --git a/src/nu/validator/htmlparser/impl/StackNode.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/StackNode.java
similarity index 100%
rename from src/nu/validator/htmlparser/impl/StackNode.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/StackNode.java
diff --git a/src/nu/validator/htmlparser/impl/StateSnapshot.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/StateSnapshot.java
similarity index 99%
rename from src/nu/validator/htmlparser/impl/StateSnapshot.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/StateSnapshot.java
index cba711f7..f6c3359a 100644
--- a/src/nu/validator/htmlparser/impl/StateSnapshot.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/impl/StateSnapshot.java
@@ -25,6 +25,7 @@
import nu.validator.htmlparser.annotation.Auto;
+@SuppressWarnings("exports")
public class StateSnapshot implements TreeBuilderState {
private final @Auto StackNode[] stack;
diff --git a/src/nu/validator/htmlparser/impl/TaintableLocatorImpl.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/TaintableLocatorImpl.java
similarity index 100%
rename from src/nu/validator/htmlparser/impl/TaintableLocatorImpl.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/TaintableLocatorImpl.java
diff --git a/src/nu/validator/htmlparser/impl/Tokenizer.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/Tokenizer.java
old mode 100755
new mode 100644
similarity index 99%
rename from src/nu/validator/htmlparser/impl/Tokenizer.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/Tokenizer.java
index 13fd56b1..db6257e1
--- a/src/nu/validator/htmlparser/impl/Tokenizer.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/impl/Tokenizer.java
@@ -36,7 +36,6 @@
package nu.validator.htmlparser.impl;
import org.xml.sax.ErrorHandler;
-import org.xml.sax.Locator;
import org.xml.sax.ext.Locator2;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
@@ -67,7 +66,8 @@
* @version $Id$
* @author hsivonen
*/
-public class Tokenizer implements Locator, Locator2 {
+@SuppressWarnings("fallthrough")
+public class Tokenizer implements Locator2 {
private static final int DATA_AND_RCDATA_MASK = ~1;
diff --git a/src/nu/validator/htmlparser/impl/TreeBuilder.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/TreeBuilder.java
similarity index 99%
rename from src/nu/validator/htmlparser/impl/TreeBuilder.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/TreeBuilder.java
index 7b78b1b7..784ab921 100644
--- a/src/nu/validator/htmlparser/impl/TreeBuilder.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/impl/TreeBuilder.java
@@ -35,7 +35,6 @@
package nu.validator.htmlparser.impl;
-import java.util.Arrays;
import java.util.HashMap;
import java.util.Map;
@@ -54,10 +53,10 @@
import nu.validator.htmlparser.annotation.NsUri;
import nu.validator.htmlparser.common.DocumentMode;
import nu.validator.htmlparser.common.DocumentModeHandler;
-import nu.validator.htmlparser.common.Interner;
import nu.validator.htmlparser.common.TokenHandler;
import nu.validator.htmlparser.common.XmlViolationPolicy;
+@SuppressWarnings("exports")
public abstract class TreeBuilder implements TokenHandler,
TreeBuilderState {
@@ -577,7 +576,7 @@ final void warn(String message, Locator locator) throws SAXException {
// ]NOCPP]
- @SuppressWarnings("unchecked") public final void startTokenization(Tokenizer self) throws SAXException {
+ @SuppressWarnings({"rawtypes", "unchecked"}) public final void startTokenization(Tokenizer self) throws SAXException {
tokenizer = self;
stackNodes = new StackNode[64];
stack = new StackNode[64];
@@ -844,6 +843,7 @@ public final void comment(@NoLength char[] buf, int start, int length)
* @see nu.validator.htmlparser.common.TokenHandler#characters(char[], int,
* int)
*/
+ @SuppressWarnings("fallthrough")
public final void characters(@Const @NoLength char[] buf, int start, int length)
throws SAXException {
// Note: Can't attach error messages to EOF in C++ yet
@@ -1241,6 +1241,7 @@ public void zeroOriginatingReplacementCharacter() throws SAXException {
}
}
+ @SuppressWarnings("fallthrough")
public final void eof() throws SAXException {
flushCharacters();
// Note: Can't attach error messages to EOF in C++ yet
@@ -1448,6 +1449,7 @@ public final void endTokenization() throws SAXException {
end();
}
+ @SuppressWarnings("fallthrough")
public final void startTag(ElementName elementName,
HtmlAttributes attributes, boolean selfClosing) throws SAXException {
flushCharacters();
@@ -2898,8 +2900,6 @@ private boolean isSpecialParentInForeign(StackNode stackNode) {
* C++ memory note: The return value must be released.
*
* @return
- * @throws SAXException
- * @throws StopSniffingException
*/
public static String extractCharsetFromContent(String attributeValue
// CPPONLY: , TreeBuilder tb
@@ -3095,6 +3095,7 @@ private void checkMetaCharset(HtmlAttributes attributes)
}
}
+ @SuppressWarnings("fallthrough")
public final void endTag(ElementName elementName) throws SAXException {
flushCharacters();
needToDropLF = false;
@@ -4292,7 +4293,7 @@ private void pushTemplateMode(int mode) {
templateModeStack[templateModePtr] = mode;
}
- @SuppressWarnings("unchecked") private void push(StackNode node) throws SAXException {
+ @SuppressWarnings({"rawtypes", "unchecked"}) private void push(StackNode node) throws SAXException {
currentPtr++;
if (currentPtr == stack.length) {
StackNode[] newStack = new StackNode[stack.length + 64];
@@ -4303,7 +4304,7 @@ private void pushTemplateMode(int mode) {
elementPushed(node.ns, node.popName, node.node);
}
- @SuppressWarnings("unchecked") private void silentPush(StackNode node) throws SAXException {
+ @SuppressWarnings({"rawtypes", "unchecked"}) private void silentPush(StackNode node) throws SAXException {
currentPtr++;
if (currentPtr == stack.length) {
StackNode[] newStack = new StackNode[stack.length + 64];
@@ -4313,7 +4314,7 @@ private void pushTemplateMode(int mode) {
stack[currentPtr] = node;
}
- @SuppressWarnings("unchecked") private void append(StackNode node) {
+ @SuppressWarnings({"rawtypes", "unchecked"}) private void append(StackNode node) {
listPtr++;
if (listPtr == listOfActiveFormattingElements.length) {
StackNode[] newList = new StackNode[listOfActiveFormattingElements.length + 64];
@@ -4787,7 +4788,7 @@ void notifyUnusedStackNode(int idxInStackNodes) {
}
}
- @SuppressWarnings("unchecked") private StackNode getUnusedStackNode() {
+ @SuppressWarnings({"rawtypes", "unchecked"}) private StackNode getUnusedStackNode() {
// Search for an unused stack node.
while (stackNodesIdx < numStackNodes) {
if (stackNodes[stackNodesIdx].isUnused()) {
@@ -5871,7 +5872,7 @@ private boolean charBufferContainsNonWhitespace() {
* @return a snapshot.
* @throws SAXException
*/
- @SuppressWarnings("unchecked") public TreeBuilderState newSnapshot()
+ @SuppressWarnings({"rawtypes", "unchecked"}) public TreeBuilderState newSnapshot()
throws SAXException {
StackNode[] listCopy = new StackNode[listPtr + 1];
for (int i = 0; i < listCopy.length; i++) {
@@ -5965,7 +5966,7 @@ public boolean snapshotMatches(TreeBuilderState snapshot) {
return true;
}
- @SuppressWarnings("unchecked") public void loadState(
+ @SuppressWarnings({"rawtypes", "unchecked"}) public void loadState(
TreeBuilderState snapshot)
throws SAXException {
// CPPONLY: mCurrentHtmlScriptIsAsyncOrDefer = false;
diff --git a/src/nu/validator/htmlparser/impl/TreeBuilderState.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/TreeBuilderState.java
similarity index 99%
rename from src/nu/validator/htmlparser/impl/TreeBuilderState.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/TreeBuilderState.java
index 5b7a9dcf..42c019fc 100644
--- a/src/nu/validator/htmlparser/impl/TreeBuilderState.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/impl/TreeBuilderState.java
@@ -29,6 +29,7 @@
* @version $Id$
* @author hsivonen
*/
+@SuppressWarnings("exports")
public interface TreeBuilderState {
/**
diff --git a/src/nu/validator/htmlparser/impl/UTF16Buffer.java b/htmlparser/src/main/java/nu/validator/htmlparser/impl/UTF16Buffer.java
similarity index 100%
rename from src/nu/validator/htmlparser/impl/UTF16Buffer.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/UTF16Buffer.java
diff --git a/src/nu/validator/htmlparser/common/package.html b/htmlparser/src/main/java/nu/validator/htmlparser/impl/package-info.java
similarity index 83%
rename from src/nu/validator/htmlparser/common/package.html
rename to htmlparser/src/main/java/nu/validator/htmlparser/impl/package-info.java
index 43f141cd..dfa43eec 100644
--- a/src/nu/validator/htmlparser/common/package.html
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/impl/package-info.java
@@ -1,7 +1,4 @@
-
-
-Package Overview
-
-
-
-
This package provides common interfaces and enumerations.
-
-
\ No newline at end of file
+ */
+
+/**
+ * This package contains the bulk of parser internals.
+ * Only implementors of additional tree builders or token handlers should look here.
+ */
+package nu.validator.htmlparser.impl;
diff --git a/src/nu/validator/htmlparser/io/BomSniffer.java b/htmlparser/src/main/java/nu/validator/htmlparser/io/BomSniffer.java
old mode 100755
new mode 100644
similarity index 100%
rename from src/nu/validator/htmlparser/io/BomSniffer.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/io/BomSniffer.java
diff --git a/src/nu/validator/htmlparser/io/Confidence.java b/htmlparser/src/main/java/nu/validator/htmlparser/io/Confidence.java
similarity index 100%
rename from src/nu/validator/htmlparser/io/Confidence.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/io/Confidence.java
diff --git a/src/nu/validator/htmlparser/io/Driver.java b/htmlparser/src/main/java/nu/validator/htmlparser/io/Driver.java
similarity index 99%
rename from src/nu/validator/htmlparser/io/Driver.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/io/Driver.java
index aa2354c9..0c971eef 100644
--- a/src/nu/validator/htmlparser/io/Driver.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/io/Driver.java
@@ -497,6 +497,7 @@ protected Encoding whineAboutEncodingAndReturnActual(String encoding,
}
}
+ @SuppressWarnings("serial")
private class ReparseException extends SAXException {
}
diff --git a/src/nu/validator/htmlparser/io/Encoding.java b/htmlparser/src/main/java/nu/validator/htmlparser/io/Encoding.java
similarity index 100%
rename from src/nu/validator/htmlparser/io/Encoding.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/io/Encoding.java
diff --git a/src/nu/validator/htmlparser/io/HtmlInputStreamReader.java b/htmlparser/src/main/java/nu/validator/htmlparser/io/HtmlInputStreamReader.java
old mode 100755
new mode 100644
similarity index 96%
rename from src/nu/validator/htmlparser/io/HtmlInputStreamReader.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/io/HtmlInputStreamReader.java
index 3de1af2a..b7d7e14b
--- a/src/nu/validator/htmlparser/io/HtmlInputStreamReader.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/io/HtmlInputStreamReader.java
@@ -35,19 +35,15 @@
import nu.validator.htmlparser.common.ByteReadable;
import nu.validator.htmlparser.common.Heuristics;
-import nu.validator.htmlparser.common.XmlViolationPolicy;
-import nu.validator.htmlparser.extra.ChardetSniffer;
-import nu.validator.htmlparser.extra.IcuDetectorSniffer;
import nu.validator.htmlparser.impl.Tokenizer;
import org.xml.sax.ErrorHandler;
-import org.xml.sax.Locator;
import org.xml.sax.ext.Locator2;
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
/**
- * Be very careful with this class. It is not a general-purpose subclass of of
+ * Be very careful with this class. It is not a general-purpose subclass of
* Reader. Instead, it is the minimal implementation that does
* what Tokenizer needs while being an instance of
* Reader.
@@ -58,8 +54,7 @@
* @version $Id$
* @author hsivonen
*/
-public final class HtmlInputStreamReader extends Reader implements
- ByteReadable, Locator, Locator2 {
+public final class HtmlInputStreamReader extends Reader implements ByteReadable, Locator2 {
private static final int SNIFFING_LIMIT = 1024;
@@ -112,7 +107,9 @@ public final class HtmlInputStreamReader extends Reader implements
/**
* @param inputStream
* @param errorHandler
- * @param locator
+ * @param tokenizer
+ * @param driver
+ * @param heuristics
* @throws IOException
* @throws SAXException
*/
@@ -136,15 +133,6 @@ public HtmlInputStreamReader(InputStream inputStream,
+ encoding.getCanonName()
+ "\u201D used. Documents must use UTF-8.");
}
- if (encoding == null
- && (heuristics == Heuristics.CHARDET || heuristics == Heuristics.ALL)) {
- encoding = (new ChardetSniffer(byteArray, limit)).sniff();
- }
- if (encoding == null
- && (heuristics == Heuristics.ICU || heuristics == Heuristics.ALL)) {
- position = 0;
- encoding = (new IcuDetectorSniffer(this)).sniff();
- }
sniffing = false;
if (encoding == null) {
encoding = Encoding.WINDOWS1252;
diff --git a/src/nu/validator/htmlparser/io/MetaSniffer.java b/htmlparser/src/main/java/nu/validator/htmlparser/io/MetaSniffer.java
old mode 100755
new mode 100644
similarity index 98%
rename from src/nu/validator/htmlparser/io/MetaSniffer.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/io/MetaSniffer.java
index 9deaef7a..dd4dee9f
--- a/src/nu/validator/htmlparser/io/MetaSniffer.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/io/MetaSniffer.java
@@ -34,7 +34,7 @@
import org.xml.sax.SAXException;
import org.xml.sax.SAXParseException;
-public class MetaSniffer extends MetaScanner implements Locator, Locator2 {
+public class MetaSniffer extends MetaScanner implements Locator2 {
private Encoding characterEncoding = null;
@@ -91,7 +91,6 @@ protected int read() throws IOException {
*
* @throws SAXException
* @throws IOException
- * @throws
*/
public Encoding sniff(ByteReadable readable) throws SAXException, IOException {
this.readable = readable;
diff --git a/src/nu/validator/htmlparser/rewindable/Rewindable.java b/htmlparser/src/main/java/nu/validator/htmlparser/rewindable/Rewindable.java
old mode 100755
new mode 100644
similarity index 100%
rename from src/nu/validator/htmlparser/rewindable/Rewindable.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/rewindable/Rewindable.java
diff --git a/src/nu/validator/htmlparser/rewindable/RewindableInputStream.java b/htmlparser/src/main/java/nu/validator/htmlparser/rewindable/RewindableInputStream.java
old mode 100755
new mode 100644
similarity index 100%
rename from src/nu/validator/htmlparser/rewindable/RewindableInputStream.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/rewindable/RewindableInputStream.java
diff --git a/src/nu/validator/htmlparser/sax/HtmlParser.java b/htmlparser/src/main/java/nu/validator/htmlparser/sax/HtmlParser.java
similarity index 98%
rename from src/nu/validator/htmlparser/sax/HtmlParser.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/sax/HtmlParser.java
index ad17e892..c7751761 100644
--- a/src/nu/validator/htmlparser/sax/HtmlParser.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/sax/HtmlParser.java
@@ -552,6 +552,7 @@ public void setTransitionHandler(TransitionHandler handler) {
* @see org.xml.sax.XMLReader#setErrorHandler(org.xml.sax.ErrorHandler)
* @deprecated For Validator.nu internal use
*/
+ @Deprecated
public void setTreeBuilderErrorHandlerOverride(ErrorHandler handler) {
treeBuilderErrorHandler = handler;
if (driver != null) {
@@ -714,7 +715,7 @@ public void setProperty(String name, Object value)
/**
* Indicates whether NFC normalization of source is being checked.
* @return true if NFC normalization of source is being checked.
- * @see nu.validator.htmlparser.impl.Tokenizer#isCheckingNormalization()
+ * @see nu.validator.htmlparser.io.Driver#isCheckingNormalization()
*/
public boolean isCheckingNormalization() {
return checkingNormalization;
@@ -723,7 +724,7 @@ public boolean isCheckingNormalization() {
/**
* Toggles the checking of the NFC normalization of source.
* @param enable true to check normalization
- * @see nu.validator.htmlparser.impl.Tokenizer#setCheckingNormalization(boolean)
+ * @see nu.validator.htmlparser.io.Driver#setCheckingNormalization(boolean)
*/
public void setCheckingNormalization(boolean enable) {
this.checkingNormalization = enable;
@@ -941,8 +942,8 @@ public boolean isReportingDoctype() {
}
/**
- * @param errorProfile
- * @see nu.validator.htmlparser.impl.errorReportingTokenizer#setErrorProfile(set)
+ * @param errorProfileMap
+ * @see nu.validator.htmlparser.impl.ErrorReportingTokenizer#setErrorProfile(HashMap)
*/
public void setErrorProfile(HashMap errorProfileMap) {
this.errorProfileMap = errorProfileMap;
@@ -965,7 +966,7 @@ public void setNamePolicy(XmlViolationPolicy namePolicy) {
* Sets the encoding sniffing heuristics.
*
* @param heuristics the heuristics to set
- * @see nu.validator.htmlparser.impl.Tokenizer#setHeuristics(nu.validator.htmlparser.common.Heuristics)
+ * @see nu.validator.htmlparser.io.Driver#setHeuristics(nu.validator.htmlparser.common.Heuristics)
*/
public void setHeuristics(Heuristics heuristics) {
this.heuristics = heuristics;
@@ -1006,6 +1007,7 @@ public XmlViolationPolicy getNamePolicy() {
* Does nothing.
* @deprecated
*/
+ @Deprecated
public void setBogusXmlnsPolicy(
XmlViolationPolicy bogusXmlnsPolicy) {
}
@@ -1015,6 +1017,7 @@ public void setBogusXmlnsPolicy(
* @deprecated
* @return XmlViolationPolicy.ALTER_INFOSET
*/
+ @Deprecated
public XmlViolationPolicy getBogusXmlnsPolicy() {
return XmlViolationPolicy.ALTER_INFOSET;
}
diff --git a/src/nu/validator/htmlparser/sax/HtmlSerializer.java b/htmlparser/src/main/java/nu/validator/htmlparser/sax/HtmlSerializer.java
similarity index 100%
rename from src/nu/validator/htmlparser/sax/HtmlSerializer.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/sax/HtmlSerializer.java
diff --git a/src/nu/validator/htmlparser/sax/InfosetCoercingHtmlParser.java b/htmlparser/src/main/java/nu/validator/htmlparser/sax/InfosetCoercingHtmlParser.java
similarity index 100%
rename from src/nu/validator/htmlparser/sax/InfosetCoercingHtmlParser.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/sax/InfosetCoercingHtmlParser.java
diff --git a/src/nu/validator/htmlparser/sax/NameCheckingXmlSerializer.java b/htmlparser/src/main/java/nu/validator/htmlparser/sax/NameCheckingXmlSerializer.java
similarity index 99%
rename from src/nu/validator/htmlparser/sax/NameCheckingXmlSerializer.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/sax/NameCheckingXmlSerializer.java
index b6cb2f87..bacbbfce 100644
--- a/src/nu/validator/htmlparser/sax/NameCheckingXmlSerializer.java
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/sax/NameCheckingXmlSerializer.java
@@ -40,7 +40,7 @@ public NameCheckingXmlSerializer(Writer out) {
}
/**
- * @see nu.validator.htmlparser.sax.XmlSerializer#checkNCName()
+ * @see nu.validator.htmlparser.sax.XmlSerializer#checkNCName(String)
*/
@Override protected void checkNCName(String name) throws SAXException {
if (!NCName.isNCName(name)) {
diff --git a/src/nu/validator/htmlparser/sax/SAXStreamer.java b/htmlparser/src/main/java/nu/validator/htmlparser/sax/SAXStreamer.java
similarity index 100%
rename from src/nu/validator/htmlparser/sax/SAXStreamer.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/sax/SAXStreamer.java
diff --git a/src/nu/validator/htmlparser/sax/SAXTreeBuilder.java b/htmlparser/src/main/java/nu/validator/htmlparser/sax/SAXTreeBuilder.java
similarity index 100%
rename from src/nu/validator/htmlparser/sax/SAXTreeBuilder.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/sax/SAXTreeBuilder.java
diff --git a/src/nu/validator/htmlparser/sax/XmlSerializer.java b/htmlparser/src/main/java/nu/validator/htmlparser/sax/XmlSerializer.java
similarity index 100%
rename from src/nu/validator/htmlparser/sax/XmlSerializer.java
rename to htmlparser/src/main/java/nu/validator/htmlparser/sax/XmlSerializer.java
diff --git a/test-src/nu/validator/saxtree/test/package.html b/htmlparser/src/main/java/nu/validator/htmlparser/sax/package-info.java
similarity index 85%
rename from test-src/nu/validator/saxtree/test/package.html
rename to htmlparser/src/main/java/nu/validator/htmlparser/sax/package-info.java
index 57809b84..7ade27d9 100644
--- a/test-src/nu/validator/saxtree/test/package.html
+++ b/htmlparser/src/main/java/nu/validator/htmlparser/sax/package-info.java
@@ -1,7 +1,4 @@
-
-
-Package Overview
-
-
-
-
Test drivers.
-
-
\ No newline at end of file
+ */
+
+/**
+ * This package provides an HTML5 parser that exposes the document through the SAX API.
+ */
+package nu.validator.htmlparser.sax;
diff --git a/test-src/nu/validator/htmlparser/test/DecoderLoopTester.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/DecoderLoopTester.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/DecoderLoopTester.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/DecoderLoopTester.java
diff --git a/test-src/nu/validator/htmlparser/test/DomIdTester.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/DomIdTester.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/DomIdTester.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/DomIdTester.java
diff --git a/test-src/nu/validator/htmlparser/test/DomTest.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/DomTest.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/DomTest.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/DomTest.java
diff --git a/test-src/nu/validator/htmlparser/test/EncodingTester.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/EncodingTester.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/EncodingTester.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/EncodingTester.java
diff --git a/test-src/nu/validator/htmlparser/test/JSONArrayTokenHandler.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/JSONArrayTokenHandler.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/JSONArrayTokenHandler.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/JSONArrayTokenHandler.java
diff --git a/test-src/nu/validator/htmlparser/test/ListErrorHandler.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/ListErrorHandler.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/ListErrorHandler.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/ListErrorHandler.java
diff --git a/test-src/nu/validator/htmlparser/test/SystemErrErrorHandler.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/SystemErrErrorHandler.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/SystemErrErrorHandler.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/SystemErrErrorHandler.java
diff --git a/test-src/nu/validator/htmlparser/test/TokenPrinter.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/TokenPrinter.java
old mode 100755
new mode 100644
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/TokenPrinter.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/TokenPrinter.java
diff --git a/test-src/nu/validator/htmlparser/test/TokenizerTester.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/TokenizerTester.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/TokenizerTester.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/TokenizerTester.java
diff --git a/test-src/nu/validator/htmlparser/test/TreeDumpContentHandler.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/TreeDumpContentHandler.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/TreeDumpContentHandler.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/TreeDumpContentHandler.java
diff --git a/test-src/nu/validator/htmlparser/test/TreePrinter.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/TreePrinter.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/TreePrinter.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/TreePrinter.java
diff --git a/test-src/nu/validator/htmlparser/test/TreeTester.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/TreeTester.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/TreeTester.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/TreeTester.java
diff --git a/test-src/nu/validator/htmlparser/test/UntilHashInputStream.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/UntilHashInputStream.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/UntilHashInputStream.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/UntilHashInputStream.java
diff --git a/test-src/nu/validator/htmlparser/test/XmlSerializerTester.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/XmlSerializerTester.java
similarity index 100%
rename from test-src/nu/validator/htmlparser/test/XmlSerializerTester.java
rename to htmlparser/src/test/java/nu/validator/htmlparser/test/XmlSerializerTester.java
diff --git a/htmlparser/src/test/java/nu/validator/htmlparser/test/package-info.java b/htmlparser/src/test/java/nu/validator/htmlparser/test/package-info.java
new file mode 100644
index 00000000..82d43a7d
--- /dev/null
+++ b/htmlparser/src/test/java/nu/validator/htmlparser/test/package-info.java
@@ -0,0 +1,26 @@
+/*
+ Copyright (c) 2007 Henri Sivonen
+
+ Permission is hereby granted, free of charge, to any person obtaining a
+ copy of this software and associated documentation files (the "Software"),
+ to deal in the Software without restriction, including without limitation
+ the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ and/or sell copies of the Software, and to permit persons to whom the
+ Software is furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ DEALINGS IN THE SOFTWARE.
+ */
+
+/**
+ * Test drivers.
+ */
+package nu.validator.htmlparser.test;
diff --git a/test-src/nu/validator/saxtree/test/PassThruPrinter.java b/htmlparser/src/test/java/nu/validator/saxtree/test/PassThruPrinter.java
similarity index 100%
rename from test-src/nu/validator/saxtree/test/PassThruPrinter.java
rename to htmlparser/src/test/java/nu/validator/saxtree/test/PassThruPrinter.java
diff --git a/htmlparser/src/test/java/nu/validator/saxtree/test/package-info.java b/htmlparser/src/test/java/nu/validator/saxtree/test/package-info.java
new file mode 100644
index 00000000..ad8ce418
--- /dev/null
+++ b/htmlparser/src/test/java/nu/validator/saxtree/test/package-info.java
@@ -0,0 +1,26 @@
+/*
+ Copyright (c) 2007 Henri Sivonen
+
+ Permission is hereby granted, free of charge, to any person obtaining a
+ copy of this software and associated documentation files (the "Software"),
+ to deal in the Software without restriction, including without limitation
+ the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ and/or sell copies of the Software, and to permit persons to whom the
+ Software is furnished to do so, subject to the following conditions:
+
+ The above copyright notice and this permission notice shall be included in
+ all copies or substantial portions of the Software.
+
+ THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ DEALINGS IN THE SOFTWARE.
+ */
+
+/**
+ * Test drivers.
+ */
+package nu.validator.saxtree.test;
diff --git a/mozilla-export-scripts/README.txt b/mozilla-export-scripts/README.txt
deleted file mode 100644
index 3567b846..00000000
--- a/mozilla-export-scripts/README.txt
+++ /dev/null
@@ -1,25 +0,0 @@
-These scripts export the Java-to-C++ translator and the java source files that
-implement the HTML5 parser. The exported translator may be used (with no
-external dependencies) to translate the exported java source files into Gecko-
-compatible C++.
-
-Hacking the translator itself still requires a working copy of the Java HTML5
-parser repository, but hacking the parser (modifying the Java source files and
-performing the translation) should now be possible using only files committed
-to the mozilla source tree.
-
-Run any of these scripts without arguments to receive usage instructions.
-
- make-translator-jar.sh: compiles the Java-to-C++ translator into a .jar file
- export-java-srcs.sh: exports minimal java source files implementing the
- HTML5 parser
- export-translator.sh: exports the compiled translator and javaparser.jar
- export-all.sh: runs the previous two scripts
- util.sh: provides various shell utility functions to the
- scripts listed above (does nothing if run directly)
-
-All path arguments may be either absolute or relative. This includes the path
-to the script itself ($0), so the directory from which you run these scripts
-doesn't matter.
-
-Ben Newman (7 July 2009)
diff --git a/mozilla-export-scripts/export-all.sh b/mozilla-export-scripts/export-all.sh
deleted file mode 100644
index 9ae07d33..00000000
--- a/mozilla-export-scripts/export-all.sh
+++ /dev/null
@@ -1,24 +0,0 @@
-#!/usr/bin/env sh
-
-SCRIPT_DIR=`dirname $0`
-source $SCRIPT_DIR/util.sh
-SCRIPT_DIR=`abs $SCRIPT_DIR`
-
-if [ $# -eq 1 ]
-then
- MOZ_PARSER_PATH=`abs $1`
-else
- echo
- echo "Usage: sh `basename $0` /path/to/mozilla-central/parser/html"
- echo "Note that relative paths will work just fine."
- echo
- exit 1
-fi
-
-$SCRIPT_DIR/export-translator.sh $MOZ_PARSER_PATH
-$SCRIPT_DIR/export-java-srcs.sh $MOZ_PARSER_PATH
-
-echo
-echo "Now go to $MOZ_PARSER_PATH and run"
-echo " java -jar javalib/translator.jar javasrc . nsHtml5AtomList.h"
-echo
diff --git a/mozilla-export-scripts/export-java-srcs.sh b/mozilla-export-scripts/export-java-srcs.sh
deleted file mode 100644
index 6d32b07d..00000000
--- a/mozilla-export-scripts/export-java-srcs.sh
+++ /dev/null
@@ -1,25 +0,0 @@
-#!/usr/bin/env sh
-
-SCRIPT_DIR=`dirname $0`
-source $SCRIPT_DIR/util.sh
-SCRIPT_DIR=`abs $SCRIPT_DIR`
-
-SRCDIR=`abs $SCRIPT_DIR/../src/nu/validator/htmlparser/impl`
-
-if [ $# -eq 1 ]
-then
- MOZ_PARSER_PATH=`abs $1`
-else
- echo
- echo "Usage: sh `basename $0` /path/to/mozilla-central/parser/html"
- echo "Note that relative paths will work just fine."
- echo
- exit 1
-fi
-
-SRCTARGET=$MOZ_PARSER_PATH/javasrc
-
-rm -rf $SRCTARGET
-mkdir $SRCTARGET
-# Avoid copying the .svn directory:
-cp -rv $SRCDIR/*.java $SRCTARGET
diff --git a/mozilla-export-scripts/export-translator.sh b/mozilla-export-scripts/export-translator.sh
deleted file mode 100644
index d1f4f1c3..00000000
--- a/mozilla-export-scripts/export-translator.sh
+++ /dev/null
@@ -1,24 +0,0 @@
-#!/usr/bin/env sh
-
-SCRIPT_DIR=`dirname $0`
-source $SCRIPT_DIR/util.sh
-SCRIPT_DIR=`abs $SCRIPT_DIR`
-
-LIBDIR=`abs $SCRIPT_DIR/../translator-lib`
-
-if [ $# -eq 1 ]
-then
- MOZ_PARSER_PATH=`abs $1`
-else
- echo
- echo "Usage: sh `basename $0` /path/to/mozilla-central/parser/html"
- echo "Note that relative paths will work just fine."
- echo "Be sure that you have run `dirname $0`/make-translator-jar.sh before running this script."
- echo
- exit 1
-fi
-
-LIBTARGET=$MOZ_PARSER_PATH/javalib
-
-rm -rf $LIBTARGET
-cp -rv $LIBDIR $LIBTARGET
diff --git a/mozilla-export-scripts/make-translator-jar.sh b/mozilla-export-scripts/make-translator-jar.sh
deleted file mode 100644
index 4f21ae66..00000000
--- a/mozilla-export-scripts/make-translator-jar.sh
+++ /dev/null
@@ -1,63 +0,0 @@
-#!/usr/bin/env sh
-
-SCRIPT_DIR=`dirname $0`
-source $SCRIPT_DIR/util.sh
-SCRIPT_DIR=`abs $SCRIPT_DIR`
-
-SRCDIR=`abs $SCRIPT_DIR/../translator-src`
-BINDIR=`abs $SCRIPT_DIR/../translator-bin`
-LIBDIR=`abs $SCRIPT_DIR/../translator-lib`
-
-if [ $# -eq 1 ]
-then
- JAVAPARSER_JAR_PATH=`abs $1`
-else
- echo
- echo "Usage: sh `basename $0` /path/to/javaparser-1.0.7.jar"
- echo "Note that relative paths will work just fine."
- echo "Obtain javaparser-1.0.7.jar from http://code.google.com/p/javaparser"
- echo
- exit 1
-fi
-
-set_up() {
- rm -rf $BINDIR; mkdir $BINDIR
- rm -rf $LIBDIR; mkdir $LIBDIR
- cp $JAVAPARSER_JAR_PATH $LIBDIR/javaparser.jar
-}
-
-write_manifest() {
- rm -f $LIBDIR/manifest
- echo "Main-Class: nu.validator.htmlparser.cpptranslate.Main" > $LIBDIR/manifest
- echo "Class-Path: javaparser.jar" >> $LIBDIR/manifest
-}
-
-compile_translator() {
- find $SRCDIR -name "*.java" | \
- xargs javac -cp $LIBDIR/javaparser.jar -g -d $BINDIR
-}
-
-generate_jar() {
- jar cvfm $LIBDIR/translator.jar $LIBDIR/manifest -C $BINDIR .
-}
-
-clean_up() {
- rm -f $LIBDIR/manifest
-}
-
-success_message() {
- echo
- echo "Successfully generated directory \"$LIBDIR\" with contents:"
- echo
- ls -al $LIBDIR
- echo
- echo "Now run `dirname $0`/export-all.sh with no arguments and follow the usage instructions."
- echo
-}
-
-set_up && \
- compile_translator && \
- write_manifest && \
- generate_jar && \
- clean_up && \
- success_message
diff --git a/mozilla-export-scripts/util.sh b/mozilla-export-scripts/util.sh
deleted file mode 100644
index 348ca14f..00000000
--- a/mozilla-export-scripts/util.sh
+++ /dev/null
@@ -1,23 +0,0 @@
-#!/usr/bin/env sh
-
-abs() {
- local rel
- local p
- if [ $# -ne 1 ]
- then
- rel=.
- else
- rel=$1
- fi
- if [ -d $rel ]
- then
- pushd $rel > /dev/null
- p=`pwd`
- popd > /dev/null
- else
- pushd `dirname $rel` > /dev/null
- p=`pwd`/`basename $rel`
- popd > /dev/null
- fi
- echo $p
-}
diff --git a/pom.xml b/pom.xml
index 41f46725..8720018f 100644
--- a/pom.xml
+++ b/pom.xml
@@ -20,221 +20,140 @@
* DEALINGS IN THE SOFTWARE.
-->
+ xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 https://maven.apache.org/xsd/maven-4.0.0.xsd">
4.0.0
- nu.validator.htmlparser
- htmlparser
- bundle
- 1.4
- htmlparser
- http://about.validator.nu/htmlparser/
- The Validator.nu HTML Parser is an implementation of the HTML5 parsing algorithm in Java for applications. The parser is designed to work as a drop-in replacement for the XML parser in applications that already support XHTML 1.x content with an XML parser and use SAX, DOM or XOM to interface with the parser.
-
-
- hsivonen
- Henri Sivonen
- hsivonen@iki.fi
- http://hsivonen.iki.fi/
-
-
+
+ nu.validator.htmlparser
+ parent
+ 2.0
+ pom
+
+ parent
+ The Validator.nu HTML Parser is an implementation of the HTML5 parsing algorithm in Java for applications. The parser is designed to work as a drop-in replacement for the XML parser in applications that already support XHTML 1.x content with an XML parser and use SAX, DOM or XOM to interface with the parser.
+ https://about.validator.nu/htmlparser/The MIT License
- http://www.opensource.org/licenses/mit-license.php
+ https://opensource.org/licenses/mit-license.phprepoThe (New) BSD License
- http://www.opensource.org/licenses/bsd-license.php
+ https://opensource.org/licenses/bsd-license.phprepo
+
+
+
+ hsivonen
+ Henri Sivonen
+ hsivonen@iki.fi
+ https://hsivonen.fi/
+
+
+
+
+ htmlparser
+ saxtree
+ xom
+
+
- scm:hg:http://hg.mozilla.org/projects/htmlparser/
- http://hg.mozilla.org/projects/htmlparser/
+ scm:git:https://github.com/validator/htmlparser.git
+ https://github.com/validator/htmlparser
-
- ${project.build.directory}/src
- ${basedir}/test-src
-
-
- org.apache.maven.plugins
- maven-compiler-plugin
-
- 1.5
- 1.5
-
-
-
- maven-antrun-plugin
- 1.7
-
-
- com.sun
- tools
- 1.5.0
- system
- ${java.home}/../lib/tools.jar
-
-
-
-
- intitialize-sources
- initialize
-
- run
-
-
-
-
-
-
-
-
-
-
-
-
- tokenizer-hotspot-workaround
- process-sources
-
- run
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
- org.apache.maven.plugins
- maven-surefire-plugin
-
- true
-
-
-
- org.apache.felix
- maven-bundle-plugin
- 2.3.7
- true
-
-
- false
-
-
- ${project.name}
- nu.validator.htmlparser
- ${project.version}
- J2SE-1.5
- <_removeheaders>Built-By,Bnd-LastModified
-
-
-
-
- org.codehaus.mojo
- rpm-maven-plugin
-
- 1
- The MIT License
- Development/Java
- /var/tmp/${project.build.finalName}
-
- _javadir ${rpm.java.dir}
- _javadocdir ${rpm.javadoc.dir}
-
-
-
- ${rpm.java.dir}
- 644
- root
- root
-
-
- ${project.build.directory}/${project.build.finalName}.jar
-
-
-
-
- ${rpm.javadoc.dir}/${project.build.finalName}
- 644
- root
- root
-
-
- ${project.build.directory}/apidocs
-
-
-
-
- %__ln_s ${project.build.finalName}.jar %{buildroot}%{_javadir}/${project.name}.jar
-
-
-
-
-
-
- com.ibm.icu
- icu4j
- 4.0.1
- compile
- true
-
-
- xom
- xom
- 1.1
- compile
- true
-
-
- net.sourceforge.jchardet
- jchardet
- 1.0
- compile
- true
-
-
- com.sdicons.jsontools
- jsontools-core
- 1.4
- test
-
-
+
- /usr/share/java
- /usr/share/javadoc
+ 11
+ trueUTF-8
+
+
+
+
+ nu.validator.htmlparser
+ htmlparser
+ 2.0
+
+
+ nu.validator.htmlparser
+ saxtree
+ 2.0
+
+
+ nu.validator.htmlparser
+ xom
+ 2.0
+
+
+
+
+
+
+
+
+ maven-clean-plugin
+ 3.1.0
+
+
+ maven-compiler-plugin
+ 3.8.1
+
+
+ base-compile
+
+ compile
+
+
+ 8
+
+ module-info.java
+
+
+
+
+
+
+ maven-javadoc-plugin
+ 3.2.0
+
+
+ maven-resources-plugin
+ 3.2.0
+
+
+ maven-source-plugin
+ 3.2.1
+
+
+ maven-surefire-plugin
+ 2.22.2
+
+
+ org.codehaus.mojo
+ exec-maven-plugin
+ 3.0.0
+
+
+
+
diff --git a/ruby-gcj/DomUtils.java b/ruby-gcj/DomUtils.java
deleted file mode 100644
index dc43da83..00000000
--- a/ruby-gcj/DomUtils.java
+++ /dev/null
@@ -1,36 +0,0 @@
-import java.util.HashSet;
-import org.w3c.dom.Document;
-import org.w3c.dom.Node;
-import org.w3c.dom.Element;
-
-public class DomUtils {
-
- private static HashSet pinned_list = new HashSet();
-
- public static synchronized void pin(Document d) {
- pinned_list.add(d);
- }
-
- public static synchronized void unpin(Document d) {
- pinned_list.remove(d);
- }
-
- // return all the text content contained by a single element
- public static void getElementContent(Element e, StringBuffer b) {
- for (Node n = e.getFirstChild(); n!=null; n=n.getNextSibling()) {
- if (n.getNodeType() == n.TEXT_NODE) {
- b.append(n.getNodeValue());
- } else if (n.getNodeType() == n.ELEMENT_NODE) {
- getElementContent((Element) e, b);
- }
- }
- }
-
- // replace all child nodes of a given element with a single text element
- public static void setElementContent(Element e, String s) {
- while (e.hasChildNodes()) {
- e.removeChild(e.getFirstChild());
- }
- e.appendChild(e.getOwnerDocument().createTextNode(s));
- }
-}
diff --git a/ruby-gcj/README b/ruby-gcj/README
deleted file mode 100644
index b368437f..00000000
--- a/ruby-gcj/README
+++ /dev/null
@@ -1,65 +0,0 @@
-Disclaimer:
-
- This code is experimental.
-
- When some people say experimental, they mean "it may not do what it is
- intended to do; in fact, it might even wipe out your hard drive". I mean
- that too. But I mean something more than that.
-
- In this case, experimental means that I don't even know what it is intended
- to do. I just have a vague vision, and I am trying out various things in
- the hopes that one of them will work out.
-
-Vision:
-
- My vague vision is that I would like to see HTML 5 be a success. For me to
- consider it to be a success, it needs to be a standard, be interoperable,
- and be ubiquitous.
-
- I believe that the Validator.nu parser can be used to bootstrap that
- process. It is written in Java. Has been compiled into JavaScript. Has
- been translated into C++ based on the Mozilla libraries with the intent of
- being included in Firefox. It very closely tracks to the standard.
-
- For the moment, the effort is on extending that to another language (Ruby)
- on a single environment (i.e., Linux). Once that is complete, intent is to
- evaluate the results, decide what needs to be changed, and what needs to be
- done to support other languages and environments.
-
- The bar I'm setting for myself isn't just another SWIG generated low level
- interface to a DOM, but rather a best of breed interface; which for Ruby
- seems to be the one pioneered by Hpricot and adopted by Nokogiri. Success
- will mean passing all of the tests from one of those two parsers as well as
- all of the HTML5 tests.
-
-Build instructions:
-
- You'll need icu4j and chardet jars. If you checked out and ran dldeps you
- are already all set:
-
- svn co http://svn.versiondude.net/whattf/build/trunk/ build
- python build/build.py checkout dldeps
-
- Fedora 11:
-
- yum install ruby-devel rubygem-rake java-1.5.0-gcj-devel gcc-c++
-
- Ubuntu 9.04:
-
- apt-get install ruby ruby1.8-dev rake gcj g++
-
- Also at this time, you need to install a jdk (e.g. sun-java6-jdk), simply
- because the javac that comes with gcj doesn't support -sourcepath, and
- I haven't spent the time to find a replacement.
-
- Finally, make sure that libjaxp1.3-java is *not* installed.
-
- http://gcc.gnu.org/ml/java/2009-06/msg00055.html
-
- If this is done, you should be all set.
-
- cd htmlparser/ruby-gcj
- rake test
-
- If things are successful, the last lines of the output will list the
- font attributes and values found in the test/google.html file.
diff --git a/ruby-gcj/Rakefile b/ruby-gcj/Rakefile
deleted file mode 100644
index 7b518025..00000000
--- a/ruby-gcj/Rakefile
+++ /dev/null
@@ -1,77 +0,0 @@
-deps = ENV['deps'] || '../../dependencies'
-icu4j = "#{deps}/icu4j-4_0.jar"
-chardet = "#{deps}/mozilla/intl/chardet/java/dist/lib/chardet.jar"
-libgcj = Dir['/usr/share/java/libgcj*.jar'].grep(/gcj[-\d.]*jar$/).sort.last
-
-task :default => %w(headers libs Makefile validator.so)
-
-# headers
-
-hdb = 'nu/validator/htmlparser/dom/HtmlDocumentBuilder'
-task :headers => %W(headers/DomUtils.h headers/#{hdb}.h)
-
-file 'headers/DomUtils.h' => 'DomUtils.java' do |t|
- mkdir_p %w(classes headers), :verbose => false
- sh "javac -d classes #{t.prerequisites.first}"
- sh "gcjh -force -o #{t.name} -cp #{libgcj}:classes DomUtils"
-end
-
-file "headers/#{hdb}.h" => "../src/#{hdb}.java" do |t|
- mkdir_p %w(classes headers), :verbose => false
- sh "javac -cp #{icu4j}:#{chardet} -d classes -sourcepath ../src " +
- t.prerequisites.first
- sh "gcjh -force -cp classes -o #{t.name} -cp #{libgcj}:classes " +
- hdb.gsub('/','.')
-end
-
-# libs
-
-task :libs => %w(htmlparser chardet icu).map {|name| "lib/libnu-#{name}.so"}
-
-htmlparser = Dir['../src/**/*.java'].reject {|name| name.include? '/xom/'}
-file 'lib/libnu-htmlparser.so' => htmlparser + ['DomUtils.java'] do |t|
- mkdir_p 'lib', :verbose => false
- sh "gcj -shared --classpath=#{icu4j}:#{chardet} -fPIC " +
- "-o #{t.name} #{t.prerequisites.join(' ')}"
-end
-
-file 'lib/libnu-chardet.so' => chardet do |t|
- mkdir_p 'lib', :verbose => false
- sh "gcj -shared -fPIC -o #{t.name} #{t.prerequisites.join(' ')}"
-end
-
-file 'lib/libnu-icu.so' => icu4j do |t|
- mkdir_p 'lib', :verbose => false
- sh "gcj -shared -fPIC -o #{t.name} #{t.prerequisites.join(' ')}"
-end
-
-# module
-
-file 'Makefile' do
- sh "ruby extconf.rb --with-gcj=#{libgcj}"
-end
-
-file 'validator.so' => %w(Makefile validator.cpp headers/DomUtils.h) do
- system 'make'
-end
-
-file 'nu/validator.so' do
- mkdir_p 'nu', :verbose => false
- system 'ln -s -t nu ../validator.so'
-end
-
-# tasks
-
-task :test => [:default, 'nu/validator.so'] do
- ENV['LD_LIBRARY_PATH']='lib'
- sh 'ruby test/fonts.rb test/google.html'
-end
-
-task :clean do
- rm_rf %W(classes lib nu mkmf.log headers/DomUtils.h headers/#{hdb}.h) +
- Dir['*.o'] + Dir['*.so']
-end
-
-task :clobber => :clean do
- rm_rf %w(headers Makefile)
-end
diff --git a/ruby-gcj/extconf.rb b/ruby-gcj/extconf.rb
deleted file mode 100644
index 415cf430..00000000
--- a/ruby-gcj/extconf.rb
+++ /dev/null
@@ -1,45 +0,0 @@
-require 'mkmf'
-
-# system dependencies
-gcj = with_config('gcj', '/usr/share/java/libgcj.jar')
-
-# headers for JAXP
-CONFIG['CC'] = 'g++'
-with_cppflags('-xc++') do
-
- unless find_header('org/w3c/dom/Document.h', 'headers')
-
- `jar tf #{gcj}`.split.each do |file|
- next unless file =~ /\.class$/
- next unless file =~ /^(javax|org)\/(w3c|xml)/
- next if file.include? '$'
-
- dest = 'headers/' + file.sub(/\.class$/,'.h')
- name = file.sub(/\.class$/,'').gsub('/','.')
-
- next if File.exist? dest
-
- cmd = "gcjh -cp #{gcj} -o #{dest} #{name}"
- puts cmd
- break unless system cmd
- system "ruby -pi -e '$_.sub!(/namespace namespace$/," +
- "\"namespace namespace$\")' #{dest}"
- system "ruby -pi -e '$_.sub!(/::namespace::/," +
- "\"::namespace$::\")' #{dest}"
- end
-
- exit unless find_header('org/w3c/dom/Document.h', 'headers')
- end
-
- find_header 'nu/validator/htmlparser/dom/HtmlDocumentBuilder.h', 'headers'
-end
-
-# Java libraries
-Config::CONFIG['CC'] = 'g++ -shared'
-dir_config('nu-htmlparser', nil, 'lib')
-have_library 'nu-htmlparser'
-have_library 'nu-icu'
-have_library 'nu-chardet'
-
-# Ruby library
-create_makefile 'nu/validator'
diff --git a/ruby-gcj/test/domencoding.rb b/ruby-gcj/test/domencoding.rb
deleted file mode 100644
index 1beb94c1..00000000
--- a/ruby-gcj/test/domencoding.rb
+++ /dev/null
@@ -1,5 +0,0 @@
-require 'nu/validator'
-
-ARGV.each do |arg|
- puts Nu::Validator::parse(open(arg)).root.name
-end
diff --git a/ruby-gcj/test/fonts.rb b/ruby-gcj/test/fonts.rb
deleted file mode 100644
index 595e3ae0..00000000
--- a/ruby-gcj/test/fonts.rb
+++ /dev/null
@@ -1,11 +0,0 @@
-require 'nu/validator'
-require 'open-uri'
-
-ARGV.each do |arg|
- doc = Nu::Validator::parse(open(arg))
- doc.xpath("//*[local-name()='font']").each do |font|
- font.attributes.each do |name, attr|
- puts "#{name} => #{attr.value}"
- end
- end
-end
diff --git a/ruby-gcj/test/google.html b/ruby-gcj/test/google.html
deleted file mode 100644
index 8d2183b2..00000000
--- a/ruby-gcj/test/google.html
+++ /dev/null
@@ -1,10 +0,0 @@
-Google
\ No newline at end of file
diff --git a/ruby-gcj/test/greek.xml b/ruby-gcj/test/greek.xml
deleted file mode 100644
index a14d23eb..00000000
--- a/ruby-gcj/test/greek.xml
+++ /dev/null
@@ -1,2 +0,0 @@
-
-
diff --git a/ruby-gcj/validator.cpp b/ruby-gcj/validator.cpp
deleted file mode 100644
index aadd24ab..00000000
--- a/ruby-gcj/validator.cpp
+++ /dev/null
@@ -1,210 +0,0 @@
-#include
-
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-#include
-
-#include "nu/validator/htmlparser/dom/HtmlDocumentBuilder.h"
-
-#include "DomUtils.h"
-
-#include "ruby.h"
-
-using namespace java::io;
-using namespace java::lang;
-using namespace java::util;
-using namespace javax::xml::parsers;
-using namespace javax::xml::xpath;
-using namespace nu::validator::htmlparser::dom;
-using namespace org::w3c::dom;
-using namespace org::xml::sax;
-
-static VALUE jaxp_Document;
-static VALUE jaxp_Attr;
-static VALUE jaxp_Element;
-static ID ID_read;
-static ID ID_doc;
-static ID ID_element;
-
-// convert a Java string into a Ruby string
-static VALUE j2r(String *string) {
- if (string == NULL) return Qnil;
- jint len = JvGetStringUTFLength(string);
- char buf[len];
- JvGetStringUTFRegion(string, 0, len, buf);
- return rb_str_new(buf, len);
-}
-
-// convert a Ruby string into a Java string
-static String *r2j(VALUE string) {
- return JvNewStringUTF(RSTRING(string)->ptr);
-}
-
-// release the Java Document associated with this Ruby Document
-static void vnu_document_free(Document *doc) {
- DomUtils::unpin(doc);
-}
-
-// Nu::Validator::parse( string|file )
-static VALUE vnu_parse(VALUE self, VALUE input) {
- HtmlDocumentBuilder *parser = new HtmlDocumentBuilder();
-
- // read file-like objects into memory. TODO: buffer such objects
- if (rb_respond_to(input, ID_read))
- input = rb_funcall(input, ID_read, 0);
-
- // convert input in to a ByteArrayInputStream
- jbyteArray bytes = JvNewByteArray(RSTRING(input)->len);
- memcpy(elements(bytes), RSTRING(input)->ptr, RSTRING(input)->len);
- InputSource *source = new InputSource(new ByteArrayInputStream(bytes));
-
- // parse, pin, and wrap
- Document *doc = parser->parse(source);
- DomUtils::pin(doc);
- return Data_Wrap_Struct(jaxp_Document, NULL, vnu_document_free, doc);
-}
-
-// Jaxp::parse( string|file )
-static VALUE jaxp_parse(VALUE self, VALUE input) {
- DocumentBuilderFactory *factory = DocumentBuilderFactory::newInstance();
- DocumentBuilder *parser = factory->newDocumentBuilder();
-
- // read file-like objects into memory. TODO: buffer such objects
- if (rb_respond_to(input, ID_read))
- input = rb_funcall(input, ID_read, 0);
-
- try {
- jbyteArray bytes = JvNewByteArray(RSTRING(input)->len);
- memcpy(elements(bytes), RSTRING(input)->ptr, RSTRING(input)->len);
- Document *doc = parser->parse(new ByteArrayInputStream(bytes));
- DomUtils::pin(doc);
- return Data_Wrap_Struct(jaxp_Document, NULL, vnu_document_free, doc);
- } catch (java::lang::Throwable *ex) {
- ex->printStackTrace();
- return Qnil;
- }
-}
-
-
-// Nu::Validator::Document#encoding
-static VALUE jaxp_document_encoding(VALUE rdoc) {
- Document *jdoc;
- Data_Get_Struct(rdoc, Document, jdoc);
- return j2r(jdoc->getXmlEncoding());
-}
-
-// Nu::Validator::Document#root
-static VALUE jaxp_document_root(VALUE rdoc) {
- Document *jdoc;
- Data_Get_Struct(rdoc, Document, jdoc);
-
- Element *jelement = jdoc->getDocumentElement();
- if (jelement==NULL) return Qnil;
-
- VALUE relement = Data_Wrap_Struct(jaxp_Element, NULL, NULL, jelement);
- rb_ivar_set(relement, ID_doc, rdoc);
- return relement;
-}
-
-// Nu::Validator::Document#xpath
-static VALUE jaxp_document_xpath(VALUE rdoc, VALUE path) {
- Document *jdoc;
- Data_Get_Struct(rdoc, Document, jdoc);
-
- Element *jelement = jdoc->getDocumentElement();
- if (jelement==NULL) return Qnil;
-
- XPath *xpath = XPathFactory::newInstance()->newXPath();
- XPathExpression *expr = xpath->compile(r2j(path));
- NodeList *list = (NodeList*) expr->evaluate(jdoc, XPathConstants::NODESET);
-
- VALUE result = rb_ary_new();
- for (int i=0; igetLength(); i++) {
- VALUE relement = Data_Wrap_Struct(jaxp_Element, NULL, NULL, list->item(i));
- rb_ivar_set(relement, ID_doc, rdoc);
- rb_ary_push(result, relement);
- }
- return result;
-}
-
-// Nu::Validator::Element#name
-static VALUE jaxp_element_name(VALUE relement) {
- Element *jelement;
- Data_Get_Struct(relement, Element, jelement);
- return j2r(jelement->getNodeName());
-}
-
-// Nu::Validator::Element#attributes
-static VALUE jaxp_element_attributes(VALUE relement) {
- Element *jelement;
- Data_Get_Struct(relement, Element, jelement);
- VALUE result = rb_hash_new();
- NamedNodeMap *map = jelement->getAttributes();
- for (int i=0; igetLength(); i++) {
- Attr *jattr = (Attr *) map->item(i);
- VALUE rattr = Data_Wrap_Struct(jaxp_Attr, NULL, NULL, jattr);
- rb_ivar_set(rattr, ID_element, relement);
- rb_hash_aset(result, j2r(jattr->getName()), rattr);
- }
- return result;
-}
-
-// Nu::Validator::Attribute#value
-static VALUE jaxp_attribute_value(VALUE rattribute) {
- Attr *jattribute;
- Data_Get_Struct(rattribute, Attr, jattribute);
- return j2r(jattribute->getValue());
-}
-
-typedef VALUE (ruby_method)(...);
-
-// Nu::Validator module initialization
-extern "C" void Init_validator() {
- JvCreateJavaVM(NULL);
- JvAttachCurrentThread(NULL, NULL);
- JvInitClass(&DomUtils::class$);
- JvInitClass(&XPathFactory::class$);
- JvInitClass(&XPathConstants::class$);
-
- VALUE jaxp = rb_define_module("Jaxp");
- rb_define_singleton_method(jaxp, "parse", (ruby_method*)&jaxp_parse, 1);
-
- VALUE nu = rb_define_module("Nu");
- VALUE validator = rb_define_module_under(nu, "Validator");
- rb_define_singleton_method(validator, "parse", (ruby_method*)&vnu_parse, 1);
-
- jaxp_Document = rb_define_class_under(jaxp, "Document", rb_cObject);
- rb_define_method(jaxp_Document, "encoding",
- (ruby_method*)&jaxp_document_encoding, 0);
- rb_define_method(jaxp_Document, "root",
- (ruby_method*)&jaxp_document_root, 0);
- rb_define_method(jaxp_Document, "xpath",
- (ruby_method*)&jaxp_document_xpath, 1);
-
- jaxp_Element = rb_define_class_under(jaxp, "Element", rb_cObject);
- rb_define_method(jaxp_Element, "name",
- (ruby_method*)&jaxp_element_name, 0);
- rb_define_method(jaxp_Element, "attributes",
- (ruby_method*)&jaxp_element_attributes, 0);
-
- jaxp_Attr = rb_define_class_under(jaxp, "Attr", rb_cObject);
- rb_define_method(jaxp_Attr, "value",
- (ruby_method*)&jaxp_attribute_value, 0);
-
- ID_read = rb_intern("read");
- ID_doc = rb_intern("@doc");
- ID_element = rb_intern("@element");
-}
diff --git a/super/nu/validator/htmlparser/translatable/java/io/IOException.java b/saxtree/pom.xml
similarity index 68%
rename from super/nu/validator/htmlparser/translatable/java/io/IOException.java
rename to saxtree/pom.xml
index f323f1e3..fe31a185 100644
--- a/super/nu/validator/htmlparser/translatable/java/io/IOException.java
+++ b/saxtree/pom.xml
@@ -1,5 +1,5 @@
-/*
- * Copyright (c) 2009 Mozilla Foundation
+
+
+ 4.0.0
-package java.io;
+
+ nu.validator.htmlparser
+ parent
+ 2.0
+
-public class IOException extends Exception {
+ saxtree
- public IOException() {
- }
-
- public IOException(String arg0) {
- super(arg0);
- }
-
- public IOException(Throwable arg0) {
- super(arg0);
- }
-
- public IOException(String arg0, Throwable arg1) {
- super(arg0, arg1);
- }
-
-}
+ saxtree
+
diff --git a/gwt-src/nu/validator/htmlparser/gwt/ParseEndListener.java b/saxtree/src/main/java/module-info.java
similarity index 58%
rename from gwt-src/nu/validator/htmlparser/gwt/ParseEndListener.java
rename to saxtree/src/main/java/module-info.java
index 43235c5b..077e6379 100644
--- a/gwt-src/nu/validator/htmlparser/gwt/ParseEndListener.java
+++ b/saxtree/src/main/java/module-info.java
@@ -1,46 +1,30 @@
-/*
- * Copyright (c) 2008 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.gwt;
-
-import com.google.gwt.core.client.JavaScriptObject;
-
-public class ParseEndListener {
-
- private final JavaScriptObject callback;
-
- /**
- * @param callback
- */
- public ParseEndListener(JavaScriptObject callback) {
- this.callback = callback;
- }
-
- public void parseComplete() {
- call(callback);
- }
-
- private static native void call(JavaScriptObject callback) /*-{
- callback();
- }-*/;
-
-}
+/*
+ * Copyright (c) 2020 Anthony Vanelverdinghe
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the "Software"),
+ * to deal in the Software without restriction, including without limitation
+ * the rights to use, copy, modify, merge, publish, distribute, sublicense,
+ * and/or sell copies of the Software, and to permit persons to whom the
+ * Software is furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in
+ * all copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
+ * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
+ * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
+ * DEALINGS IN THE SOFTWARE.
+ */
+
+/**
+ * Provides SAX Tree: a tree model optimized for creation from SAX events and replay as SAX events.
+ */
+module nu.validator.saxtree {
+ requires transitive java.xml;
+
+ exports nu.validator.saxtree;
+}
diff --git a/src/nu/validator/saxtree/CDATA.java b/saxtree/src/main/java/nu/validator/saxtree/CDATA.java
similarity index 100%
rename from src/nu/validator/saxtree/CDATA.java
rename to saxtree/src/main/java/nu/validator/saxtree/CDATA.java
diff --git a/src/nu/validator/saxtree/CharBufferNode.java b/saxtree/src/main/java/nu/validator/saxtree/CharBufferNode.java
similarity index 100%
rename from src/nu/validator/saxtree/CharBufferNode.java
rename to saxtree/src/main/java/nu/validator/saxtree/CharBufferNode.java
diff --git a/src/nu/validator/saxtree/Characters.java b/saxtree/src/main/java/nu/validator/saxtree/Characters.java
similarity index 100%
rename from src/nu/validator/saxtree/Characters.java
rename to saxtree/src/main/java/nu/validator/saxtree/Characters.java
diff --git a/src/nu/validator/saxtree/Comment.java b/saxtree/src/main/java/nu/validator/saxtree/Comment.java
similarity index 100%
rename from src/nu/validator/saxtree/Comment.java
rename to saxtree/src/main/java/nu/validator/saxtree/Comment.java
diff --git a/src/nu/validator/saxtree/DTD.java b/saxtree/src/main/java/nu/validator/saxtree/DTD.java
similarity index 100%
rename from src/nu/validator/saxtree/DTD.java
rename to saxtree/src/main/java/nu/validator/saxtree/DTD.java
diff --git a/src/nu/validator/saxtree/Document.java b/saxtree/src/main/java/nu/validator/saxtree/Document.java
similarity index 100%
rename from src/nu/validator/saxtree/Document.java
rename to saxtree/src/main/java/nu/validator/saxtree/Document.java
diff --git a/src/nu/validator/saxtree/DocumentFragment.java b/saxtree/src/main/java/nu/validator/saxtree/DocumentFragment.java
similarity index 95%
rename from src/nu/validator/saxtree/DocumentFragment.java
rename to saxtree/src/main/java/nu/validator/saxtree/DocumentFragment.java
index a9e2db84..9f496bf3 100644
--- a/src/nu/validator/saxtree/DocumentFragment.java
+++ b/saxtree/src/main/java/nu/validator/saxtree/DocumentFragment.java
@@ -23,7 +23,7 @@
package nu.validator.saxtree;
-import nu.validator.htmlparser.impl.LocatorImpl;
+import org.xml.sax.ext.Locator2Impl;
/**
* A document fragment.
@@ -37,7 +37,7 @@ public final class DocumentFragment extends ParentNode {
* The constructor.
*/
public DocumentFragment() {
- super(new LocatorImpl());
+ super(new Locator2Impl());
}
/**
diff --git a/src/nu/validator/saxtree/Element.java b/saxtree/src/main/java/nu/validator/saxtree/Element.java
similarity index 100%
rename from src/nu/validator/saxtree/Element.java
rename to saxtree/src/main/java/nu/validator/saxtree/Element.java
diff --git a/src/nu/validator/saxtree/Entity.java b/saxtree/src/main/java/nu/validator/saxtree/Entity.java
similarity index 100%
rename from src/nu/validator/saxtree/Entity.java
rename to saxtree/src/main/java/nu/validator/saxtree/Entity.java
diff --git a/src/nu/validator/saxtree/IgnorableWhitespace.java b/saxtree/src/main/java/nu/validator/saxtree/IgnorableWhitespace.java
similarity index 100%
rename from src/nu/validator/saxtree/IgnorableWhitespace.java
rename to saxtree/src/main/java/nu/validator/saxtree/IgnorableWhitespace.java
diff --git a/src/nu/validator/saxtree/LocatorImpl.java b/saxtree/src/main/java/nu/validator/saxtree/LocatorImpl.java
similarity index 98%
rename from src/nu/validator/saxtree/LocatorImpl.java
rename to saxtree/src/main/java/nu/validator/saxtree/LocatorImpl.java
index b6416f1a..6a1f81ba 100644
--- a/src/nu/validator/saxtree/LocatorImpl.java
+++ b/saxtree/src/main/java/nu/validator/saxtree/LocatorImpl.java
@@ -31,7 +31,7 @@
* @version $Id$
* @author hsivonen
*/
-public final class LocatorImpl implements Locator, Locator2 {
+public final class LocatorImpl implements Locator2 {
/**
* The system id.
diff --git a/src/nu/validator/saxtree/Node.java b/saxtree/src/main/java/nu/validator/saxtree/Node.java
similarity index 99%
rename from src/nu/validator/saxtree/Node.java
rename to saxtree/src/main/java/nu/validator/saxtree/Node.java
index c9292dd2..1ead08b4 100644
--- a/src/nu/validator/saxtree/Node.java
+++ b/saxtree/src/main/java/nu/validator/saxtree/Node.java
@@ -35,7 +35,7 @@
* @version $Id$
* @author hsivonen
*/
-public abstract class Node implements Locator, Locator2 {
+public abstract class Node implements Locator2 {
/**
* The system id.
diff --git a/src/nu/validator/saxtree/NodeType.java b/saxtree/src/main/java/nu/validator/saxtree/NodeType.java
similarity index 100%
rename from src/nu/validator/saxtree/NodeType.java
rename to saxtree/src/main/java/nu/validator/saxtree/NodeType.java
diff --git a/src/nu/validator/saxtree/NullLexicalHandler.java b/saxtree/src/main/java/nu/validator/saxtree/NullLexicalHandler.java
similarity index 100%
rename from src/nu/validator/saxtree/NullLexicalHandler.java
rename to saxtree/src/main/java/nu/validator/saxtree/NullLexicalHandler.java
diff --git a/src/nu/validator/saxtree/ParentNode.java b/saxtree/src/main/java/nu/validator/saxtree/ParentNode.java
similarity index 100%
rename from src/nu/validator/saxtree/ParentNode.java
rename to saxtree/src/main/java/nu/validator/saxtree/ParentNode.java
diff --git a/src/nu/validator/saxtree/PrefixMapping.java b/saxtree/src/main/java/nu/validator/saxtree/PrefixMapping.java
similarity index 100%
rename from src/nu/validator/saxtree/PrefixMapping.java
rename to saxtree/src/main/java/nu/validator/saxtree/PrefixMapping.java
diff --git a/src/nu/validator/saxtree/ProcessingInstruction.java b/saxtree/src/main/java/nu/validator/saxtree/ProcessingInstruction.java
similarity index 100%
rename from src/nu/validator/saxtree/ProcessingInstruction.java
rename to saxtree/src/main/java/nu/validator/saxtree/ProcessingInstruction.java
diff --git a/src/nu/validator/saxtree/SkippedEntity.java b/saxtree/src/main/java/nu/validator/saxtree/SkippedEntity.java
similarity index 100%
rename from src/nu/validator/saxtree/SkippedEntity.java
rename to saxtree/src/main/java/nu/validator/saxtree/SkippedEntity.java
diff --git a/src/nu/validator/saxtree/TreeBuilder.java b/saxtree/src/main/java/nu/validator/saxtree/TreeBuilder.java
similarity index 100%
rename from src/nu/validator/saxtree/TreeBuilder.java
rename to saxtree/src/main/java/nu/validator/saxtree/TreeBuilder.java
diff --git a/src/nu/validator/saxtree/TreeParser.java b/saxtree/src/main/java/nu/validator/saxtree/TreeParser.java
similarity index 99%
rename from src/nu/validator/saxtree/TreeParser.java
rename to saxtree/src/main/java/nu/validator/saxtree/TreeParser.java
index 6f86f7f0..29792f84 100644
--- a/src/nu/validator/saxtree/TreeParser.java
+++ b/saxtree/src/main/java/nu/validator/saxtree/TreeParser.java
@@ -35,7 +35,7 @@
* @version $Id$
* @author hsivonen
*/
-public final class TreeParser implements Locator, Locator2 {
+public final class TreeParser implements Locator2 {
/**
* The content handler.
diff --git a/src/nu/validator/htmlparser/impl/package.html b/saxtree/src/main/java/nu/validator/saxtree/package-info.java
similarity index 52%
rename from src/nu/validator/htmlparser/impl/package.html
rename to saxtree/src/main/java/nu/validator/saxtree/package-info.java
index 6d029a13..54af5a4c 100644
--- a/src/nu/validator/htmlparser/impl/package.html
+++ b/saxtree/src/main/java/nu/validator/saxtree/package-info.java
@@ -1,7 +1,4 @@
-
-
-Package Overview
-
-
-
-
This package contains the bulk of parser internals. Only implementors of
-additional tree builders or token handlers should look here.
-
-
\ No newline at end of file
+ */
+
+/**
+ * This package provides SAX Tree: a tree model optimized for creation from SAX events and replay as SAX events.
+ *
+ *
Design Principles
+ *
+ *
Preserve information exposed through ContentHandler,
+ * LexicalHandlerandLocator.
+ *
Creation from SAX events or as part of the parse of a conforming
+ * HTML5 document should be fast.
+ *
Emitting SAX events based on the tree should be fast.
+ *
Mutations should be possible but should not make the above "fast" cases slower.
+ *
Concurrent reads should work without locking when there are no concurrent mutations.
+ *
The user of the API has the responsibility of using the API properly:
+ * for the sake of performance, the model does not check if it is being used properly.
+ * Improper use may, therefore, put the model in and inconsistent state.
+ *
This package provides annotations for facilitating automated translation
-of the source code into other programming languages.
-
-
\ No newline at end of file
diff --git a/src/nu/validator/htmlparser/dom/package.html b/src/nu/validator/htmlparser/dom/package.html
deleted file mode 100644
index d793bcf8..00000000
--- a/src/nu/validator/htmlparser/dom/package.html
+++ /dev/null
@@ -1,29 +0,0 @@
-
-
-Package Overview
-
-
-
-
This package provides an HTML5 parser that exposes the document using the DOM API.
-
-
\ No newline at end of file
diff --git a/src/nu/validator/htmlparser/extra/ChardetSniffer.java b/src/nu/validator/htmlparser/extra/ChardetSniffer.java
deleted file mode 100644
index a7575039..00000000
--- a/src/nu/validator/htmlparser/extra/ChardetSniffer.java
+++ /dev/null
@@ -1,84 +0,0 @@
-/*
- * Copyright (c) 2008 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.extra;
-
-import java.io.IOException;
-import java.nio.charset.UnsupportedCharsetException;
-
-import nu.validator.htmlparser.io.Encoding;
-
-import org.mozilla.intl.chardet.nsDetector;
-import org.mozilla.intl.chardet.nsICharsetDetectionObserver;
-import org.mozilla.intl.chardet.nsPSMDetector;
-
-import com.ibm.icu.text.CharsetDetector;
-
-public class ChardetSniffer implements nsICharsetDetectionObserver {
-
- private final byte[] source;
-
- private final int length;
-
- private Encoding returnValue = null;
-
- /**
- * @param source
- */
- public ChardetSniffer(final byte[] source, final int length) {
- this.source = source;
- this.length = length;
- }
-
- public Encoding sniff() throws IOException {
- nsDetector detector = new nsDetector(nsPSMDetector.ALL);
- detector.Init(this);
- detector.DoIt(source, length, false);
- detector.DataEnd();
- if (returnValue != null && returnValue != Encoding.WINDOWS1252 && returnValue.isAsciiSuperset()) {
- return returnValue;
- } else {
- return null;
- }
- }
-
- public static void main(String[] args) {
- String[] detectable = CharsetDetector.getAllDetectableCharsets();
- for (int i = 0; i < detectable.length; i++) {
- String charset = detectable[i];
- System.out.println(charset);
- }
- }
-
- public void Notify(String charsetName) {
- try {
- Encoding enc = Encoding.forName(charsetName);
- Encoding actual = enc.getActualHtmlEncoding();
- if (actual != null) {
- enc = actual;
- }
- returnValue = enc;
- } catch (UnsupportedCharsetException e) {
- returnValue = null;
- }
- }
-}
diff --git a/src/nu/validator/htmlparser/extra/IcuDetectorSniffer.java b/src/nu/validator/htmlparser/extra/IcuDetectorSniffer.java
deleted file mode 100644
index f3caab5c..00000000
--- a/src/nu/validator/htmlparser/extra/IcuDetectorSniffer.java
+++ /dev/null
@@ -1,77 +0,0 @@
-/*
- * Copyright (c) 2008 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.extra;
-
-import java.io.IOException;
-import java.io.InputStream;
-
-import nu.validator.htmlparser.common.ByteReadable;
-import nu.validator.htmlparser.io.Encoding;
-
-import com.ibm.icu.text.CharsetDetector;
-import com.ibm.icu.text.CharsetMatch;
-
-public class IcuDetectorSniffer extends InputStream {
-
- private final ByteReadable source;
-
- /**
- * @param source
- */
- public IcuDetectorSniffer(final ByteReadable source) {
- this.source = source;
- }
-
- @Override
- public int read() throws IOException {
- return source.readByte();
- }
-
- public Encoding sniff() throws IOException {
- try {
- CharsetDetector detector = new CharsetDetector();
- detector.setText(this);
- CharsetMatch match = detector.detect();
- Encoding enc = Encoding.forName(match.getName());
- Encoding actual = enc.getActualHtmlEncoding();
- if (actual != null) {
- enc = actual;
- }
- if (enc != Encoding.WINDOWS1252 && enc.isAsciiSuperset()) {
- return enc;
- } else {
- return null;
- }
- } catch (Exception e) {
- return null;
- }
- }
-
- public static void main(String[] args) {
- String[] detectable = CharsetDetector.getAllDetectableCharsets();
- for (int i = 0; i < detectable.length; i++) {
- String charset = detectable[i];
- System.out.println(charset);
- }
- }
-}
diff --git a/src/nu/validator/htmlparser/extra/NormalizationChecker.java b/src/nu/validator/htmlparser/extra/NormalizationChecker.java
deleted file mode 100644
index 45df62fb..00000000
--- a/src/nu/validator/htmlparser/extra/NormalizationChecker.java
+++ /dev/null
@@ -1,268 +0,0 @@
-/*
- * Copyright (c) 2006, 2007 Henri Sivonen
- * Copyright (c) 2007 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.extra;
-
-import nu.validator.htmlparser.common.CharacterHandler;
-
-import org.xml.sax.ErrorHandler;
-import org.xml.sax.Locator;
-import org.xml.sax.SAXException;
-import org.xml.sax.SAXParseException;
-
-import com.ibm.icu.lang.UCharacter;
-import com.ibm.icu.text.Normalizer;
-import com.ibm.icu.text.UnicodeSet;
-
-/**
- * @version $Id$
- * @author hsivonen
- */
-public final class NormalizationChecker implements CharacterHandler {
-
- private ErrorHandler errorHandler;
-
- private Locator locator;
-
- /**
- * A thread-safe set of composing characters as per Charmod Norm.
- */
- @SuppressWarnings("deprecation")
- private static final UnicodeSet COMPOSING_CHARACTERS = (UnicodeSet) new UnicodeSet(
- "[[:nfc_qc=maybe:][:^ccc=0:]]").freeze();
-
- // see http://sourceforge.net/mailarchive/message.php?msg_id=37279908
-
- /**
- * A buffer for holding sequences overlap the SAX buffer boundary.
- */
- private char[] buf = new char[128];
-
- /**
- * A holder for the original buffer (for the memory leak prevention
- * mechanism).
- */
- private char[] bufHolder = null;
-
- /**
- * The current used length of the buffer, i.e. the index of the first slot
- * that does not hold current data.
- */
- private int pos;
-
- /**
- * Indicates whether the checker the next call to characters()
- * is the first call in a run.
- */
- private boolean atStartOfRun;
-
- /**
- * Indicates whether the current run has already caused an error.
- */
- private boolean alreadyComplainedAboutThisRun;
-
- /**
- * Emit an error. The locator is used.
- *
- * @param message the error message
- * @throws SAXException if something goes wrong
- */
- public void err(String message) throws SAXException {
- if (errorHandler != null) {
- SAXParseException spe = new SAXParseException(message, locator);
- errorHandler.error(spe);
- }
- }
-
- /**
- * Returns true if the argument is a composing BMP character
- * or a surrogate and false otherwise.
- *
- * @param c a UTF-16 code unit
- * @return true if the argument is a composing BMP character
- * or a surrogate and false otherwise
- */
- private static boolean isComposingCharOrSurrogate(char c) {
- if (UCharacter.isHighSurrogate(c) || UCharacter.isLowSurrogate(c)) {
- return true;
- }
- return isComposingChar(c);
- }
-
- /**
- * Returns true if the argument is a composing character
- * and false otherwise.
- *
- * @param c a Unicode code point
- * @return true if the argument is a composing character
- * false otherwise
- */
- private static boolean isComposingChar(int c) {
- return COMPOSING_CHARACTERS.contains(c);
- }
-
- /**
- * Constructor with mode selection.
- *
- * @param sourceTextMode whether the source text-related messages
- * should be enabled.
- */
- public NormalizationChecker(Locator locator) {
- super();
- start();
- }
-
- /**
- * @see nu.validator.htmlparser.common.CharacterHandler#start()
- */
- public void start() {
- atStartOfRun = true;
- alreadyComplainedAboutThisRun = false;
- pos = 0;
- }
-
- /**
- * @see nu.validator.htmlparser.common.CharacterHandler#characters(char[], int, int)
- */
- public void characters(char[] ch, int start, int length)
- throws SAXException {
- if (alreadyComplainedAboutThisRun) {
- return;
- }
- if (atStartOfRun) {
- char c = ch[start];
- if (pos == 1) {
- // there's a single high surrogate in buf
- if (isComposingChar(UCharacter.getCodePoint(buf[0], c))) {
- err("Text run starts with a composing character.");
- }
- atStartOfRun = false;
- } else {
- if (length == 1 && UCharacter.isHighSurrogate(c)) {
- buf[0] = c;
- pos = 1;
- return;
- } else {
- if (UCharacter.isHighSurrogate(c)) {
- if (isComposingChar(UCharacter.getCodePoint(c,
- ch[start + 1]))) {
- err("Text run starts with a composing character.");
- }
- } else {
- if (isComposingCharOrSurrogate(c)) {
- err("Text run starts with a composing character.");
- }
- }
- atStartOfRun = false;
- }
- }
- }
- int i = start;
- int stop = start + length;
- if (pos > 0) {
- // there's stuff in buf
- while (i < stop && isComposingCharOrSurrogate(ch[i])) {
- i++;
- }
- appendToBuf(ch, start, i);
- if (i == stop) {
- return;
- } else {
- if (!Normalizer.isNormalized(buf, 0, pos, Normalizer.NFC, 0)) {
- errAboutTextRun();
- }
- pos = 0;
- }
- }
- if (i < stop) {
- start = i;
- i = stop - 1;
- while (i > start && isComposingCharOrSurrogate(ch[i])) {
- i--;
- }
- if (i > start) {
- if (!Normalizer.isNormalized(ch, start, i, Normalizer.NFC, 0)) {
- errAboutTextRun();
- }
- }
- appendToBuf(ch, i, stop);
- }
- }
-
- /**
- * Emits an error stating that the current text run or the source
- * text is not in NFC.
- *
- * @throws SAXException if the ErrorHandler throws
- */
- private void errAboutTextRun() throws SAXException {
- err("Source text is not in Unicode Normalization Form C.");
- alreadyComplainedAboutThisRun = true;
- }
-
- /**
- * Appends a slice of an UTF-16 code unit array to the internal
- * buffer.
- *
- * @param ch the array from which to copy
- * @param start the index of the first element that is copied
- * @param end the index of the first element that is not copied
- */
- private void appendToBuf(char[] ch, int start, int end) {
- if (start == end) {
- return;
- }
- int neededBufLen = pos + (end - start);
- if (neededBufLen > buf.length) {
- char[] newBuf = new char[neededBufLen];
- System.arraycopy(buf, 0, newBuf, 0, pos);
- if (bufHolder == null) {
- bufHolder = buf; // keep the original around
- }
- buf = newBuf;
- }
- System.arraycopy(ch, start, buf, pos, end - start);
- pos += (end - start);
- }
-
- /**
- * @see nu.validator.htmlparser.common.CharacterHandler#end()
- */
- public void end() throws SAXException {
- if (!alreadyComplainedAboutThisRun
- && !Normalizer.isNormalized(buf, 0, pos, Normalizer.NFC, 0)) {
- errAboutTextRun();
- }
- if (bufHolder != null) {
- // restore the original small buffer to avoid leaking
- // memory if this checker is recycled
- buf = bufHolder;
- bufHolder = null;
- }
- }
-
- public void setErrorHandler(ErrorHandler errorHandler) {
- this.errorHandler = errorHandler;
- }
-
-}
diff --git a/src/nu/validator/htmlparser/sax/package.html b/src/nu/validator/htmlparser/sax/package.html
deleted file mode 100644
index 60532962..00000000
--- a/src/nu/validator/htmlparser/sax/package.html
+++ /dev/null
@@ -1,29 +0,0 @@
-
-
-Package Overview
-
-
-
-
This package provides an HTML5 parser that exposes the document through the SAX API.
-
-
\ No newline at end of file
diff --git a/src/nu/validator/htmlparser/xom/package.html b/src/nu/validator/htmlparser/xom/package.html
deleted file mode 100644
index a936d5e3..00000000
--- a/src/nu/validator/htmlparser/xom/package.html
+++ /dev/null
@@ -1,29 +0,0 @@
-
-
-Package Overview
-
-
-
-
This package provides an HTML5 parser that exposes the document through the XOM API.
-
-
\ No newline at end of file
diff --git a/src/nu/validator/saxtree/package.html b/src/nu/validator/saxtree/package.html
deleted file mode 100644
index 0c34dad8..00000000
--- a/src/nu/validator/saxtree/package.html
+++ /dev/null
@@ -1,46 +0,0 @@
-
-
-Package Overview
-
-
-
-
This package provides SAX Tree: a tree model optimized for creation from SAX
-events and replay as SAX events.
-
Design Principles
-
-
Preserve information exposed through ContentHandler,
-LexicalHandlerandLocator.
-
Creation from SAX events or as part of the parse of a conforming
-HTML5 document should be fast.
-
Emitting SAX events based on the tree should be fast.
-
Mutations should be possible but should not make the above
-"fast" cases slower.
-
Concurrent reads should work without locking when there are no
-concurrent mutations.
-
The user of the API has the responsibility of using the API properly:
-for the sake of performance, the model does not check if it is being
-used properly. Improper use may, therefore, put the model in and
-inconsistent state.
-
-
-
\ No newline at end of file
diff --git a/super/nu/validator/htmlparser/translatable/org/xml/sax/Attributes.java b/super/nu/validator/htmlparser/translatable/org/xml/sax/Attributes.java
deleted file mode 100644
index b25432d4..00000000
--- a/super/nu/validator/htmlparser/translatable/org/xml/sax/Attributes.java
+++ /dev/null
@@ -1,257 +0,0 @@
-// Attributes.java - attribute list with Namespace support
-// http://www.saxproject.org
-// Written by David Megginson
-// NO WARRANTY! This class is in the public domain.
-// $Id: Attributes.java,v 1.13 2004/03/18 12:28:05 dmegginson Exp $
-
-package org.xml.sax;
-
-
-/**
- * Interface for a list of XML attributes.
- *
- *
- * This module, both source code and documentation, is in the
- * Public Domain, and comes with NO WARRANTY.
- * See http://www.saxproject.org
- * for further information.
- *
- *
- *
This interface allows access to a list of attributes in
- * three different ways:
- *
- *
- *
by attribute index;
- *
by Namespace-qualified name; or
- *
by qualified (prefixed) name.
- *
- *
- *
The list will not contain attributes that were declared
- * #IMPLIED but not specified in the start tag. It will also not
- * contain attributes used as Namespace declarations (xmlns*) unless
- * the http://xml.org/sax/features/namespace-prefixes
- * feature is set to true (it is false by
- * default).
- * Because SAX2 conforms to the original "Namespaces in XML"
- * recommendation, it normally does not
- * give namespace declaration attributes a namespace URI.
- *
- *
- *
Some SAX2 parsers may support using an optional feature flag
- * (http://xml.org/sax/features/xmlns-uris) to request
- * that those attributes be given URIs, conforming to a later
- * backwards-incompatible revision of that recommendation. (The
- * attribute's "local name" will be the prefix, or "xmlns" when
- * defining a default element namespace.) For portability, handler
- * code should always resolve that conflict, rather than requiring
- * parsers that can change the setting of that feature flag.
- *
- *
If the namespace-prefixes feature (see above) is
- * false, access by qualified name may not be available; if
- * the http://xml.org/sax/features/namespaces feature is
- * false, access by Namespace-qualified names may not be
- * available.
- *
- *
This interface replaces the now-deprecated SAX1 {@link
- * org.xml.sax.AttributeList AttributeList} interface, which does not
- * contain Namespace support. In addition to Namespace support, it
- * adds the getIndex methods (below).
- *
- *
The order of attributes in the list is unspecified, and will
- * vary from implementation to implementation.
- *
- * @since SAX 2.0
- * @author David Megginson
- * @version 2.0.1 (sax2r2)
- * @see org.xml.sax.helpers.AttributesImpl
- * @see org.xml.sax.ext.DeclHandler#attributeDecl
- */
-public interface Attributes
-{
-
-
- ////////////////////////////////////////////////////////////////////
- // Indexed access.
- ////////////////////////////////////////////////////////////////////
-
-
- /**
- * Return the number of attributes in the list.
- *
- *
Once you know the number of attributes, you can iterate
- * through the list.
- *
- * @return The number of attributes in the list.
- * @see #getURI(int)
- * @see #getLocalName(int)
- * @see #getQName(int)
- * @see #getType(int)
- * @see #getValue(int)
- */
- public abstract int getLength ();
-
-
- /**
- * Look up an attribute's Namespace URI by index.
- *
- * @param index The attribute index (zero-based).
- * @return The Namespace URI, or the empty string if none
- * is available, or null if the index is out of
- * range.
- * @see #getLength
- */
- public abstract String getURI (int index);
-
-
- /**
- * Look up an attribute's local name by index.
- *
- * @param index The attribute index (zero-based).
- * @return The local name, or the empty string if Namespace
- * processing is not being performed, or null
- * if the index is out of range.
- * @see #getLength
- */
- public abstract String getLocalName (int index);
-
-
- /**
- * Look up an attribute's XML qualified (prefixed) name by index.
- *
- * @param index The attribute index (zero-based).
- * @return The XML qualified name, or the empty string
- * if none is available, or null if the index
- * is out of range.
- * @see #getLength
- */
- public abstract String getQName (int index);
-
-
- /**
- * Look up an attribute's type by index.
- *
- *
The attribute type is one of the strings "CDATA", "ID",
- * "IDREF", "IDREFS", "NMTOKEN", "NMTOKENS", "ENTITY", "ENTITIES",
- * or "NOTATION" (always in upper case).
- *
- *
If the parser has not read a declaration for the attribute,
- * or if the parser does not report attribute types, then it must
- * return the value "CDATA" as stated in the XML 1.0 Recommendation
- * (clause 3.3.3, "Attribute-Value Normalization").
- *
- *
For an enumerated attribute that is not a notation, the
- * parser will report the type as "NMTOKEN".
- *
- * @param index The attribute index (zero-based).
- * @return The attribute's type as a string, or null if the
- * index is out of range.
- * @see #getLength
- */
- public abstract String getType (int index);
-
-
- /**
- * Look up an attribute's value by index.
- *
- *
If the attribute value is a list of tokens (IDREFS,
- * ENTITIES, or NMTOKENS), the tokens will be concatenated
- * into a single string with each token separated by a
- * single space.
- *
- * @param index The attribute index (zero-based).
- * @return The attribute's value as a string, or null if the
- * index is out of range.
- * @see #getLength
- */
- public abstract String getValue (int index);
-
-
-
- ////////////////////////////////////////////////////////////////////
- // Name-based query.
- ////////////////////////////////////////////////////////////////////
-
-
- /**
- * Look up the index of an attribute by Namespace name.
- *
- * @param uri The Namespace URI, or the empty string if
- * the name has no Namespace URI.
- * @param localName The attribute's local name.
- * @return The index of the attribute, or -1 if it does not
- * appear in the list.
- */
- public int getIndex (String uri, String localName);
-
-
- /**
- * Look up the index of an attribute by XML qualified (prefixed) name.
- *
- * @param qName The qualified (prefixed) name.
- * @return The index of the attribute, or -1 if it does not
- * appear in the list.
- */
- public int getIndex (String qName);
-
-
- /**
- * Look up an attribute's type by Namespace name.
- *
- *
See {@link #getType(int) getType(int)} for a description
- * of the possible types.
- *
- * @param uri The Namespace URI, or the empty String if the
- * name has no Namespace URI.
- * @param localName The local name of the attribute.
- * @return The attribute type as a string, or null if the
- * attribute is not in the list or if Namespace
- * processing is not being performed.
- */
- public abstract String getType (String uri, String localName);
-
-
- /**
- * Look up an attribute's type by XML qualified (prefixed) name.
- *
- *
See {@link #getType(int) getType(int)} for a description
- * of the possible types.
- *
- * @param qName The XML qualified name.
- * @return The attribute type as a string, or null if the
- * attribute is not in the list or if qualified names
- * are not available.
- */
- public abstract String getType (String qName);
-
-
- /**
- * Look up an attribute's value by Namespace name.
- *
- *
See {@link #getValue(int) getValue(int)} for a description
- * of the possible values.
- *
- * @param uri The Namespace URI, or the empty String if the
- * name has no Namespace URI.
- * @param localName The local name of the attribute.
- * @return The attribute value as a string, or null if the
- * attribute is not in the list.
- */
- public abstract String getValue (String uri, String localName);
-
-
- /**
- * Look up an attribute's value by XML qualified (prefixed) name.
- *
- *
See {@link #getValue(int) getValue(int)} for a description
- * of the possible values.
- *
- * @param qName The XML qualified name.
- * @return The attribute value as a string, or null if the
- * attribute is not in the list or if qualified names
- * are not available.
- */
- public abstract String getValue (String qName);
-
-}
-
-// end of Attributes.java
diff --git a/super/nu/validator/htmlparser/translatable/org/xml/sax/ErrorHandler.java b/super/nu/validator/htmlparser/translatable/org/xml/sax/ErrorHandler.java
deleted file mode 100644
index 37d25014..00000000
--- a/super/nu/validator/htmlparser/translatable/org/xml/sax/ErrorHandler.java
+++ /dev/null
@@ -1,139 +0,0 @@
-// SAX error handler.
-// http://www.saxproject.org
-// No warranty; no copyright -- use this as you will.
-// $Id: ErrorHandler.java,v 1.10 2004/03/08 13:01:00 dmegginson Exp $
-
-package org.xml.sax;
-
-
-/**
- * Basic interface for SAX error handlers.
- *
- *
- * This module, both source code and documentation, is in the
- * Public Domain, and comes with NO WARRANTY.
- * See http://www.saxproject.org
- * for further information.
- *
- *
- *
If a SAX application needs to implement customized error
- * handling, it must implement this interface and then register an
- * instance with the XML reader using the
- * {@link org.xml.sax.XMLReader#setErrorHandler setErrorHandler}
- * method. The parser will then report all errors and warnings
- * through this interface.
- *
- *
WARNING: If an application does not
- * register an ErrorHandler, XML parsing errors will go unreported,
- * except that SAXParseExceptions will be thrown for fatal errors.
- * In order to detect validity errors, an ErrorHandler that does something
- * with {@link #error error()} calls must be registered.
- *
- *
For XML processing errors, a SAX driver must use this interface
- * in preference to throwing an exception: it is up to the application
- * to decide whether to throw an exception for different types of
- * errors and warnings. Note, however, that there is no requirement that
- * the parser continue to report additional errors after a call to
- * {@link #fatalError fatalError}. In other words, a SAX driver class
- * may throw an exception after reporting any fatalError.
- * Also parsers may throw appropriate exceptions for non-XML errors.
- * For example, {@link XMLReader#parse XMLReader.parse()} would throw
- * an IOException for errors accessing entities or the document.
SAX parsers will use this method to report conditions that
- * are not errors or fatal errors as defined by the XML
- * recommendation. The default behaviour is to take no
- * action.
- *
- *
The SAX parser must continue to provide normal parsing events
- * after invoking this method: it should still be possible for the
- * application to process the document through to the end.
- *
- *
Filters may use this method to report other, non-XML warnings
- * as well.
- *
- * @param exception The warning information encapsulated in a
- * SAX parse exception.
- * @exception org.xml.sax.SAXException Any SAX exception, possibly
- * wrapping another exception.
- * @see org.xml.sax.SAXParseException
- */
- public abstract void warning (SAXParseException exception)
- throws SAXException;
-
-
- /**
- * Receive notification of a recoverable error.
- *
- *
This corresponds to the definition of "error" in section 1.2
- * of the W3C XML 1.0 Recommendation. For example, a validating
- * parser would use this callback to report the violation of a
- * validity constraint. The default behaviour is to take no
- * action.
- *
- *
The SAX parser must continue to provide normal parsing
- * events after invoking this method: it should still be possible
- * for the application to process the document through to the end.
- * If the application cannot do so, then the parser should report
- * a fatal error even if the XML recommendation does not require
- * it to do so.
- *
- *
Filters may use this method to report other, non-XML errors
- * as well.
- *
- * @param exception The error information encapsulated in a
- * SAX parse exception.
- * @exception org.xml.sax.SAXException Any SAX exception, possibly
- * wrapping another exception.
- * @see org.xml.sax.SAXParseException
- */
- public abstract void error (SAXParseException exception)
- throws SAXException;
-
-
- /**
- * Receive notification of a non-recoverable error.
- *
- *
There is an apparent contradiction between the
- * documentation for this method and the documentation for {@link
- * org.xml.sax.ContentHandler#endDocument}. Until this ambiguity
- * is resolved in a future major release, clients should make no
- * assumptions about whether endDocument() will or will not be
- * invoked when the parser has reported a fatalError() or thrown
- * an exception.
- *
- *
This corresponds to the definition of "fatal error" in
- * section 1.2 of the W3C XML 1.0 Recommendation. For example, a
- * parser would use this callback to report the violation of a
- * well-formedness constraint.
- *
- *
The application must assume that the document is unusable
- * after the parser has invoked this method, and should continue
- * (if at all) only for the sake of collecting additional error
- * messages: in fact, SAX parsers are free to stop reporting any
- * other events once this method has been invoked.
- *
- * @param exception The error information encapsulated in a
- * SAX parse exception.
- * @exception org.xml.sax.SAXException Any SAX exception, possibly
- * wrapping another exception.
- * @see org.xml.sax.SAXParseException
- */
- public abstract void fatalError (SAXParseException exception)
- throws SAXException;
-
-}
-
-// end of ErrorHandler.java
diff --git a/super/nu/validator/htmlparser/translatable/org/xml/sax/Locator.java b/super/nu/validator/htmlparser/translatable/org/xml/sax/Locator.java
deleted file mode 100644
index f8f3484c..00000000
--- a/super/nu/validator/htmlparser/translatable/org/xml/sax/Locator.java
+++ /dev/null
@@ -1,136 +0,0 @@
-// SAX locator interface for document events.
-// http://www.saxproject.org
-// No warranty; no copyright -- use this as you will.
-// $Id: Locator.java,v 1.8 2002/01/30 21:13:47 dbrownell Exp $
-
-package org.xml.sax;
-
-
-/**
- * Interface for associating a SAX event with a document location.
- *
- *
- * This module, both source code and documentation, is in the
- * Public Domain, and comes with NO WARRANTY.
- * See http://www.saxproject.org
- * for further information.
- *
- *
- *
If a SAX parser provides location information to the SAX
- * application, it does so by implementing this interface and then
- * passing an instance to the application using the content
- * handler's {@link org.xml.sax.ContentHandler#setDocumentLocator
- * setDocumentLocator} method. The application can use the
- * object to obtain the location of any other SAX event
- * in the XML source document.
- *
- *
Note that the results returned by the object will be valid only
- * during the scope of each callback method: the application
- * will receive unpredictable results if it attempts to use the
- * locator at any other time, or after parsing completes.
- *
- *
SAX parsers are not required to supply a locator, but they are
- * very strongly encouraged to do so. If the parser supplies a
- * locator, it must do so before reporting any other document events.
- * If no locator has been set by the time the application receives
- * the {@link org.xml.sax.ContentHandler#startDocument startDocument}
- * event, the application should assume that a locator is not
- * available.
- *
- * @since SAX 1.0
- * @author David Megginson
- * @version 2.0.1 (sax2r2)
- * @see org.xml.sax.ContentHandler#setDocumentLocator
- */
-public interface Locator {
-
-
- /**
- * Return the public identifier for the current document event.
- *
- *
The return value is the public identifier of the document
- * entity or of the external parsed entity in which the markup
- * triggering the event appears.
- *
- * @return A string containing the public identifier, or
- * null if none is available.
- * @see #getSystemId
- */
- public abstract String getPublicId ();
-
-
- /**
- * Return the system identifier for the current document event.
- *
- *
The return value is the system identifier of the document
- * entity or of the external parsed entity in which the markup
- * triggering the event appears.
- *
- *
If the system identifier is a URL, the parser must resolve it
- * fully before passing it to the application. For example, a file
- * name must always be provided as a file:... URL, and other
- * kinds of relative URI are also resolved against their bases.
- *
- * @return A string containing the system identifier, or null
- * if none is available.
- * @see #getPublicId
- */
- public abstract String getSystemId ();
-
-
- /**
- * Return the line number where the current document event ends.
- * Lines are delimited by line ends, which are defined in
- * the XML specification.
- *
- *
Warning: The return value from the method
- * is intended only as an approximation for the sake of diagnostics;
- * it is not intended to provide sufficient information
- * to edit the character content of the original XML document.
- * In some cases, these "line" numbers match what would be displayed
- * as columns, and in others they may not match the source text
- * due to internal entity expansion.
- *
- *
The return value is an approximation of the line number
- * in the document entity or external parsed entity where the
- * markup triggering the event appears.
- *
- *
If possible, the SAX driver should provide the line position
- * of the first character after the text associated with the document
- * event. The first line is line 1.
- *
- * @return The line number, or -1 if none is available.
- * @see #getColumnNumber
- */
- public abstract int getLineNumber ();
-
-
- /**
- * Return the column number where the current document event ends.
- * This is one-based number of Java char values since
- * the last line end.
- *
- *
Warning: The return value from the method
- * is intended only as an approximation for the sake of diagnostics;
- * it is not intended to provide sufficient information
- * to edit the character content of the original XML document.
- * For example, when lines contain combining character sequences, wide
- * characters, surrogate pairs, or bi-directional text, the value may
- * not correspond to the column in a text editor's display.
- *
- *
The return value is an approximation of the column number
- * in the document entity or external parsed entity where the
- * markup triggering the event appears.
- *
- *
If possible, the SAX driver should provide the line position
- * of the first character after the text associated with the document
- * event. The first column in each line is column 1.
- *
- * @return The column number, or -1 if none is available.
- * @see #getLineNumber
- */
- public abstract int getColumnNumber ();
-
-}
-
-// end of Locator.java
diff --git a/super/nu/validator/htmlparser/translatable/org/xml/sax/SAXException.java b/super/nu/validator/htmlparser/translatable/org/xml/sax/SAXException.java
deleted file mode 100644
index 256719ce..00000000
--- a/super/nu/validator/htmlparser/translatable/org/xml/sax/SAXException.java
+++ /dev/null
@@ -1,153 +0,0 @@
-// SAX exception class.
-// http://www.saxproject.org
-// No warranty; no copyright -- use this as you will.
-// $Id: SAXException.java,v 1.7 2002/01/30 21:13:48 dbrownell Exp $
-
-package org.xml.sax;
-
-/**
- * Encapsulate a general SAX error or warning.
- *
- *
- * This module, both source code and documentation, is in the
- * Public Domain, and comes with NO WARRANTY.
- * See http://www.saxproject.org
- * for further information.
- *
- *
- *
This class can contain basic error or warning information from
- * either the XML parser or the application: a parser writer or
- * application writer can subclass it to provide additional
- * functionality. SAX handlers may throw this exception or
- * any exception subclassed from it.
- *
- *
If the application needs to pass through other types of
- * exceptions, it must wrap those exceptions in a SAXException
- * or an exception derived from a SAXException.
- *
- *
If the parser or application needs to include information about a
- * specific location in an XML document, it should use the
- * {@link org.xml.sax.SAXParseException SAXParseException} subclass.
- *
- * @since SAX 1.0
- * @author David Megginson
- * @version 2.0.1 (sax2r2)
- * @see org.xml.sax.SAXParseException
- */
-public class SAXException extends Exception {
-
-
- /**
- * Create a new SAXException.
- */
- public SAXException ()
- {
- super();
- this.exception = null;
- }
-
-
- /**
- * Create a new SAXException.
- *
- * @param message The error or warning message.
- */
- public SAXException (String message) {
- super(message);
- this.exception = null;
- }
-
-
- /**
- * Create a new SAXException wrapping an existing exception.
- *
- *
The existing exception will be embedded in the new
- * one, and its message will become the default message for
- * the SAXException.
- *
- * @param e The exception to be wrapped in a SAXException.
- */
- public SAXException (Exception e)
- {
- super();
- this.exception = e;
- }
-
-
- /**
- * Create a new SAXException from an existing exception.
- *
- *
The existing exception will be embedded in the new
- * one, but the new exception will have its own message.
- *
- * @param message The detail message.
- * @param e The exception to be wrapped in a SAXException.
- */
- public SAXException (String message, Exception e)
- {
- super(message);
- this.exception = e;
- }
-
-
- /**
- * Return a detail message for this exception.
- *
- *
If there is an embedded exception, and if the SAXException
- * has no detail message of its own, this method will return
- * the detail message from the embedded exception.
- *
- * @return The error or warning message.
- */
- public String getMessage ()
- {
- String message = super.getMessage();
-
- if (message == null && exception != null) {
- return exception.getMessage();
- } else {
- return message;
- }
- }
-
-
- /**
- * Return the embedded exception, if any.
- *
- * @return The embedded exception, or null if there is none.
- */
- public Exception getException ()
- {
- return exception;
- }
-
-
- /**
- * Override toString to pick up any embedded exception.
- *
- * @return A string representation of this exception.
- */
- public String toString ()
- {
- if (exception != null) {
- return exception.toString();
- } else {
- return super.toString();
- }
- }
-
-
-
- //////////////////////////////////////////////////////////////////////
- // Internal state.
- //////////////////////////////////////////////////////////////////////
-
-
- /**
- * @serial The embedded exception if tunnelling, or null.
- */
- private Exception exception;
-
-}
-
-// end of SAXException.java
diff --git a/super/nu/validator/htmlparser/translatable/org/xml/sax/SAXParseException.java b/super/nu/validator/htmlparser/translatable/org/xml/sax/SAXParseException.java
deleted file mode 100644
index 1df5e142..00000000
--- a/super/nu/validator/htmlparser/translatable/org/xml/sax/SAXParseException.java
+++ /dev/null
@@ -1,269 +0,0 @@
-// SAX exception class.
-// http://www.saxproject.org
-// No warranty; no copyright -- use this as you will.
-// $Id: SAXParseException.java,v 1.11 2004/04/21 13:05:02 dmegginson Exp $
-
-package org.xml.sax;
-
-/**
- * Encapsulate an XML parse error or warning.
- *
- *
- * This module, both source code and documentation, is in the
- * Public Domain, and comes with NO WARRANTY.
- * See http://www.saxproject.org
- * for further information.
- *
- *
- *
This exception may include information for locating the error
- * in the original XML document, as if it came from a {@link Locator}
- * object. Note that although the application
- * will receive a SAXParseException as the argument to the handlers
- * in the {@link org.xml.sax.ErrorHandler ErrorHandler} interface,
- * the application is not actually required to throw the exception;
- * instead, it can simply read the information in it and take a
- * different action.
- *
- *
Since this exception is a subclass of {@link org.xml.sax.SAXException
- * SAXException}, it inherits the ability to wrap another exception.
- *
- * @since SAX 1.0
- * @author David Megginson
- * @version 2.0.1 (sax2r2)
- * @see org.xml.sax.SAXException
- * @see org.xml.sax.Locator
- * @see org.xml.sax.ErrorHandler
- */
-public class SAXParseException extends SAXException {
-
-
- //////////////////////////////////////////////////////////////////////
- // Constructors.
- //////////////////////////////////////////////////////////////////////
-
-
- /**
- * Create a new SAXParseException from a message and a Locator.
- *
- *
This constructor is especially useful when an application is
- * creating its own exception from within a {@link org.xml.sax.ContentHandler
- * ContentHandler} callback.
- *
- * @param message The error or warning message.
- * @param locator The locator object for the error or warning (may be
- * null).
- * @see org.xml.sax.Locator
- */
- public SAXParseException (String message, Locator locator) {
- super(message);
- if (locator != null) {
- init(locator.getPublicId(), locator.getSystemId(),
- locator.getLineNumber(), locator.getColumnNumber());
- } else {
- init(null, null, -1, -1);
- }
- }
-
-
- /**
- * Wrap an existing exception in a SAXParseException.
- *
- *
This constructor is especially useful when an application is
- * creating its own exception from within a {@link org.xml.sax.ContentHandler
- * ContentHandler} callback, and needs to wrap an existing exception that is not a
- * subclass of {@link org.xml.sax.SAXException SAXException}.
- *
- * @param message The error or warning message, or null to
- * use the message from the embedded exception.
- * @param locator The locator object for the error or warning (may be
- * null).
- * @param e Any exception.
- * @see org.xml.sax.Locator
- */
- public SAXParseException (String message, Locator locator,
- Exception e) {
- super(message, e);
- if (locator != null) {
- init(locator.getPublicId(), locator.getSystemId(),
- locator.getLineNumber(), locator.getColumnNumber());
- } else {
- init(null, null, -1, -1);
- }
- }
-
-
- /**
- * Create a new SAXParseException.
- *
- *
This constructor is most useful for parser writers.
- *
- *
All parameters except the message are as if
- * they were provided by a {@link Locator}. For example, if the
- * system identifier is a URL (including relative filename), the
- * caller must resolve it fully before creating the exception.
- *
- *
- * @param message The error or warning message.
- * @param publicId The public identifier of the entity that generated
- * the error or warning.
- * @param systemId The system identifier of the entity that generated
- * the error or warning.
- * @param lineNumber The line number of the end of the text that
- * caused the error or warning.
- * @param columnNumber The column number of the end of the text that
- * cause the error or warning.
- */
- public SAXParseException (String message, String publicId, String systemId,
- int lineNumber, int columnNumber)
- {
- super(message);
- init(publicId, systemId, lineNumber, columnNumber);
- }
-
-
- /**
- * Create a new SAXParseException with an embedded exception.
- *
- *
This constructor is most useful for parser writers who
- * need to wrap an exception that is not a subclass of
- * {@link org.xml.sax.SAXException SAXException}.
- *
- *
All parameters except the message and exception are as if
- * they were provided by a {@link Locator}. For example, if the
- * system identifier is a URL (including relative filename), the
- * caller must resolve it fully before creating the exception.
- *
- * @param message The error or warning message, or null to use
- * the message from the embedded exception.
- * @param publicId The public identifier of the entity that generated
- * the error or warning.
- * @param systemId The system identifier of the entity that generated
- * the error or warning.
- * @param lineNumber The line number of the end of the text that
- * caused the error or warning.
- * @param columnNumber The column number of the end of the text that
- * cause the error or warning.
- * @param e Another exception to embed in this one.
- */
- public SAXParseException (String message, String publicId, String systemId,
- int lineNumber, int columnNumber, Exception e)
- {
- super(message, e);
- init(publicId, systemId, lineNumber, columnNumber);
- }
-
-
- /**
- * Internal initialization method.
- *
- * @param publicId The public identifier of the entity which generated the exception,
- * or null.
- * @param systemId The system identifier of the entity which generated the exception,
- * or null.
- * @param lineNumber The line number of the error, or -1.
- * @param columnNumber The column number of the error, or -1.
- */
- private void init (String publicId, String systemId,
- int lineNumber, int columnNumber)
- {
- this.publicId = publicId;
- this.systemId = systemId;
- this.lineNumber = lineNumber;
- this.columnNumber = columnNumber;
- }
-
-
- /**
- * Get the public identifier of the entity where the exception occurred.
- *
- * @return A string containing the public identifier, or null
- * if none is available.
- * @see org.xml.sax.Locator#getPublicId
- */
- public String getPublicId ()
- {
- return this.publicId;
- }
-
-
- /**
- * Get the system identifier of the entity where the exception occurred.
- *
- *
If the system identifier is a URL, it will have been resolved
- * fully.
- *
- * @return A string containing the system identifier, or null
- * if none is available.
- * @see org.xml.sax.Locator#getSystemId
- */
- public String getSystemId ()
- {
- return this.systemId;
- }
-
-
- /**
- * The line number of the end of the text where the exception occurred.
- *
- *
The first line is line 1.
- *
- * @return An integer representing the line number, or -1
- * if none is available.
- * @see org.xml.sax.Locator#getLineNumber
- */
- public int getLineNumber ()
- {
- return this.lineNumber;
- }
-
-
- /**
- * The column number of the end of the text where the exception occurred.
- *
- *
The first column in a line is position 1.
- *
- * @return An integer representing the column number, or -1
- * if none is available.
- * @see org.xml.sax.Locator#getColumnNumber
- */
- public int getColumnNumber ()
- {
- return this.columnNumber;
- }
-
-
- //////////////////////////////////////////////////////////////////////
- // Internal state.
- //////////////////////////////////////////////////////////////////////
-
-
- /**
- * @serial The public identifier, or null.
- * @see #getPublicId
- */
- private String publicId;
-
-
- /**
- * @serial The system identifier, or null.
- * @see #getSystemId
- */
- private String systemId;
-
-
- /**
- * @serial The line number, or -1.
- * @see #getLineNumber
- */
- private int lineNumber;
-
-
- /**
- * @serial The column number, or -1.
- * @see #getColumnNumber
- */
- private int columnNumber;
-
-}
-
-// end of SAXParseException.java
diff --git a/super/nu/validator/htmlparser/translatable/org/xml/sax/package.html b/super/nu/validator/htmlparser/translatable/org/xml/sax/package.html
deleted file mode 100644
index dd7030e2..00000000
--- a/super/nu/validator/htmlparser/translatable/org/xml/sax/package.html
+++ /dev/null
@@ -1,297 +0,0 @@
-
-
-
-
-
This package provides the core SAX APIs.
-Some SAX1 APIs are deprecated to encourage integration of
-namespace-awareness into designs of new applications
-and into maintenance of existing infrastructure.
One of the essential characteristics of SAX2 is that it added
-feature flags which can be used to examine and perhaps modify
-parser modes, in particular modes such as validation.
-Since features are identified by (absolute) URIs, anyone
-can define such features.
-Currently defined standard feature URIs have the prefix
-http://xml.org/sax/features/ before an identifier such as
-validation. Turn features on or off using
-setFeature. Those standard identifiers are:
-
-
-
-
-
Feature ID
-
Access
-
Default
-
Description
-
-
-
-
external-general-entities
-
read/write
-
unspecified
-
Reports whether this parser processes external
- general entities; always true if validating.
-
-
-
-
-
external-parameter-entities
-
read/write
-
unspecified
-
Reports whether this parser processes external
- parameter entities; always true if validating.
-
-
-
-
-
is-standalone
-
(parsing) read-only, (not parsing) none
-
not applicable
-
May be examined only during a parse, after the
- startDocument() callback has been completed; read-only.
- The value is true if the document specified standalone="yes" in
- its XML declaration, and otherwise is false.
-
-
-
-
-
lexical-handler/parameter-entities
-
read/write
-
unspecified
-
A value of "true" indicates that the LexicalHandler will report
- the beginning and end of parameter entities.
-
-
-
-
-
namespaces
-
read/write
-
true
-
A value of "true" indicates namespace URIs and unprefixed local names
- for element and attribute names will be available.
-
-
-
-
-
namespace-prefixes
-
read/write
-
false
-
A value of "true" indicates that XML qualified names (with prefixes) and
- attributes (including xmlns* attributes) will be available.
-
-
-
-
-
resolve-dtd-uris
-
read/write
-
true
-
A value of "true" indicates that system IDs in declarations will
- be absolutized (relative to their base URIs) before reporting.
- (That is the default behavior for all SAX2 XML parsers.)
- A value of "false" indicates those IDs will not be absolutized;
- parsers will provide the base URI from
- Locator.getSystemId().
- This applies to system IDs passed in
-
DTDHandler.notationDecl(),
-
DTDHandler.unparsedEntityDecl(), and
-
DeclHandler.externalEntityDecl().
-
- It does not apply to EntityResolver.resolveEntity(),
- which is not used to report declarations, or to
- LexicalHandler.startDTD(), which already provides
- the non-absolutized URI.
-
-
-
-
-
string-interning
-
read/write
-
unspecified
-
Has a value of "true" if all XML names (for elements, prefixes,
- attributes, entities, notations, and local names),
- as well as Namespace URIs, will have been interned
- using java.lang.String.intern. This supports fast
- testing of equality/inequality against string constants,
- rather than forcing slower calls to String.equals().
-
-
-
-
-
unicode-normalization-checking
-
read/write
-
false
-
Controls whether the parser reports Unicode normalization
- errors as described in section 2.13 and Appendix B of the
- XML 1.1 Recommendation. If true, Unicode normalization
- errors are reported using the ErrorHandler.error() callback.
- Such errors are not fatal in themselves (though, obviously,
- other Unicode-related encoding errors may be).
-
-
-
-
-
use-attributes2
-
read-only
-
not applicable
-
Returns "true" if the Attributes objects passed by
- this parser in ContentHandler.startElement()
- implement the org.xml.sax.ext.Attributes2 interface.
- That interface exposes additional DTD-related information,
- such as whether the attribute was specified in the
- source text rather than defaulted.
-
-
-
-
-
use-locator2
-
read-only
-
not applicable
-
Returns "true" if the Locator objects passed by
- this parser in ContentHandler.setDocumentLocator()
- implement the org.xml.sax.ext.Locator2 interface.
- That interface exposes additional entity information,
- such as the character encoding and XML version used.
-
-
-
-
-
use-entity-resolver2
-
read/write
-
true
-
Returns "true" if, when setEntityResolver is given
- an object implementing the org.xml.sax.ext.EntityResolver2 interface,
- those new methods will be used.
- Returns "false" to indicate that those methods will not be used.
-
-
-
-
-
validation
-
read/write
-
unspecified
-
Controls whether the parser is reporting all validity
- errors; if true, all external entities will be read.
-
-
-
-
-
xmlns-uris
-
read/write
-
false
-
Controls whether, when the namespace-prefixes feature
- is set, the parser treats namespace declaration attributes as
- being in the http://www.w3.org/2000/xmlns/ namespace.
- By default, SAX2 conforms to the original "Namespaces in XML"
- Recommendation, which explicitly states that such attributes are
- not in any namespace.
- Setting this optional flag to "true" makes the SAX2 events conform to
- a later backwards-incompatible revision of that recommendation,
- placing those attributes in a namespace.
-
-
-
-
-
xml-1.1
-
read-only
-
not applicable
-
Returns "true" if the parser supports both XML 1.1 and XML 1.0.
- Returns "false" if the parser supports only XML 1.0.
-
-
-
-
-
-
Support for the default values of the
-namespaces and namespace-prefixes
-properties is required.
-Support for any other feature flags is entirely optional.
-
-
-
For default values not specified by SAX2,
-each XMLReader implementation specifies its default,
-or may choose not to expose the feature flag.
-Unless otherwise specified here,
-implementations may support changing current values
-of these standard feature flags, but not while parsing.
-
-
-
SAX2 Standard Handler and Property IDs
-
-
For parser interface characteristics that are described
-as objects, a separate namespace is defined. The
-objects in this namespace are again identified by URI, and
-the standard property URIs have the prefix
-http://xml.org/sax/properties/ before an identifier such as
-lexical-handler or
-dom-node. Manage those properties using
-setProperty(). Those identifiers are:
-
-
-
-
Property ID
-
Description
-
-
-
-
declaration-handler
-
Used to see most DTD declarations except those treated
- as lexical ("document element name is ...") or which are
- mandatory for all SAX parsers (DTDHandler).
- The Object must implement org.xml.sax.ext.DeclHandler.
-
-
-
-
-
document-xml-version
-
May be examined only during a parse, after the startDocument()
- callback has been completed; read-only. This property is a
- literal string describing the actual XML version of the document,
- such as "1.0" or "1.1".
-
-
-
-
-
dom-node
-
For "DOM Walker" style parsers, which ignore their
- parser.parse() parameters, this is used to
- specify the DOM (sub)tree being walked by the parser.
- The Object must implement the
- org.w3c.dom.Node interface.
-
-
-
-
-
lexical-handler
-
Used to see some syntax events that are essential in some
- applications: comments, CDATA delimiters, selected general
- entity inclusions, and the start and end of the DTD
- (and declaration of document element name).
- The Object must implement org.xml.sax.ext.LexicalHandler.
-
-
-
-
-
xml-string
-
Readable only during a parser callback, this exposes a TBS
- chunk of characters responsible for the current event.
-
-
-
-
-
All of these standard properties are optional;
-XMLReader implementations need not support them.
-
-
-
\ No newline at end of file
diff --git a/test-src/nu/validator/htmlparser/tools/HTML2HTML.java b/test-src/nu/validator/htmlparser/tools/HTML2HTML.java
deleted file mode 100644
index 5e2cf1f5..00000000
--- a/test-src/nu/validator/htmlparser/tools/HTML2HTML.java
+++ /dev/null
@@ -1,87 +0,0 @@
-/*
- * Copyright (c) 2008 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.tools;
-
-import java.io.FileInputStream;
-import java.io.FileOutputStream;
-import java.io.IOException;
-import java.io.InputStream;
-import java.io.OutputStream;
-import java.net.MalformedURLException;
-
-import javax.xml.parsers.ParserConfigurationException;
-import javax.xml.transform.TransformerException;
-
-import nu.validator.htmlparser.common.XmlViolationPolicy;
-import nu.validator.htmlparser.sax.HtmlParser;
-import nu.validator.htmlparser.sax.HtmlSerializer;
-import nu.validator.htmlparser.sax.XmlSerializer;
-import nu.validator.htmlparser.test.SystemErrErrorHandler;
-
-import org.xml.sax.ContentHandler;
-import org.xml.sax.InputSource;
-import org.xml.sax.SAXException;
-
-public class HTML2HTML {
-
- /**
- * @param args
- */
- public static void main(String[] args) throws SAXException,
- ParserConfigurationException, MalformedURLException, IOException,
- TransformerException {
- InputStream in;
- OutputStream out;
-
- switch (args.length) {
- case 0:
- in = System.in;
- out = System.out;
- break;
- case 1:
- in = new FileInputStream(args[0]);
- out = System.out;
- break;
- case 2:
- in = new FileInputStream(args[0]);
- out = new FileOutputStream(args[1]);
- break;
- default:
- System.err.println("Too many arguments. No arguments to use stdin/stdout. One argument to reading from file and write to stdout. Two arguments to read from first file and write to second.");
- System.exit(1);
- return;
- }
-
- ContentHandler serializer = new HtmlSerializer(out);
-
- HtmlParser parser = new HtmlParser(XmlViolationPolicy.ALLOW);
-
- parser.setErrorHandler(new SystemErrErrorHandler());
- parser.setContentHandler(serializer);
- parser.setProperty("http://xml.org/sax/properties/lexical-handler",
- serializer);
- parser.parse(new InputSource(in));
- out.flush();
- out.close();
- }
-}
diff --git a/test-src/nu/validator/htmlparser/tools/HTML2XML.java b/test-src/nu/validator/htmlparser/tools/HTML2XML.java
deleted file mode 100644
index 57666f93..00000000
--- a/test-src/nu/validator/htmlparser/tools/HTML2XML.java
+++ /dev/null
@@ -1,86 +0,0 @@
-/*
- * Copyright (c) 2008 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.tools;
-
-import java.io.FileInputStream;
-import java.io.FileOutputStream;
-import java.io.IOException;
-import java.io.InputStream;
-import java.io.OutputStream;
-import java.net.MalformedURLException;
-
-import javax.xml.parsers.ParserConfigurationException;
-import javax.xml.transform.TransformerException;
-
-import nu.validator.htmlparser.common.XmlViolationPolicy;
-import nu.validator.htmlparser.sax.HtmlParser;
-import nu.validator.htmlparser.sax.XmlSerializer;
-import nu.validator.htmlparser.test.SystemErrErrorHandler;
-
-import org.xml.sax.ContentHandler;
-import org.xml.sax.InputSource;
-import org.xml.sax.SAXException;
-
-public class HTML2XML {
-
- /**
- * @param args
- */
- public static void main(String[] args) throws SAXException,
- ParserConfigurationException, MalformedURLException, IOException,
- TransformerException {
- InputStream in;
- OutputStream out;
-
- switch (args.length) {
- case 0:
- in = System.in;
- out = System.out;
- break;
- case 1:
- in = new FileInputStream(args[0]);
- out = System.out;
- break;
- case 2:
- in = new FileInputStream(args[0]);
- out = new FileOutputStream(args[1]);
- break;
- default:
- System.err.println("Too many arguments. No arguments to use stdin/stdout. One argument to reading from file and write to stdout. Two arguments to read from first file and write to second.");
- System.exit(1);
- return;
- }
-
- ContentHandler serializer = new XmlSerializer(out);
-
- HtmlParser parser = new HtmlParser(XmlViolationPolicy.ALTER_INFOSET);
-
- parser.setErrorHandler(new SystemErrErrorHandler());
- parser.setContentHandler(serializer);
- parser.setProperty("http://xml.org/sax/properties/lexical-handler",
- serializer);
- parser.parse(new InputSource(in));
- out.flush();
- out.close();
- }
-}
diff --git a/test-src/nu/validator/htmlparser/tools/XML2HTML.java b/test-src/nu/validator/htmlparser/tools/XML2HTML.java
deleted file mode 100644
index dad89a5b..00000000
--- a/test-src/nu/validator/htmlparser/tools/XML2HTML.java
+++ /dev/null
@@ -1,89 +0,0 @@
-/*
- * Copyright (c) 2008 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.tools;
-
-import java.io.FileInputStream;
-import java.io.FileOutputStream;
-import java.io.IOException;
-import java.io.InputStream;
-import java.io.OutputStream;
-import java.net.MalformedURLException;
-
-import javax.xml.parsers.ParserConfigurationException;
-import javax.xml.parsers.SAXParserFactory;
-import javax.xml.transform.TransformerException;
-
-import nu.validator.htmlparser.sax.HtmlSerializer;
-import nu.validator.htmlparser.sax.XmlSerializer;
-import nu.validator.htmlparser.test.SystemErrErrorHandler;
-
-import org.xml.sax.ContentHandler;
-import org.xml.sax.InputSource;
-import org.xml.sax.SAXException;
-import org.xml.sax.XMLReader;
-
-public class XML2HTML {
-
- /**
- * @param args
- */
- public static void main(String[] args) throws SAXException,
- ParserConfigurationException, MalformedURLException, IOException,
- TransformerException {
- InputStream in;
- OutputStream out;
-
- switch (args.length) {
- case 0:
- in = System.in;
- out = System.out;
- break;
- case 1:
- in = new FileInputStream(args[0]);
- out = System.out;
- break;
- case 2:
- in = new FileInputStream(args[0]);
- out = new FileOutputStream(args[1]);
- break;
- default:
- System.err.println("Too many arguments. No arguments to use stdin/stdout. One argument to reading from file and write to stdout. Two arguments to read from first file and write to second.");
- System.exit(1);
- return;
- }
-
- ContentHandler serializer = new HtmlSerializer(out);
-
- SAXParserFactory factory = SAXParserFactory.newInstance();
- factory.setNamespaceAware(true);
- factory.setValidating(false);
- XMLReader parser = factory.newSAXParser().getXMLReader();
- parser.setErrorHandler(new SystemErrErrorHandler());
- parser.setContentHandler(serializer);
- parser.setProperty("http://xml.org/sax/properties/lexical-handler",
- serializer);
- parser.parse(new InputSource(in));
- out.flush();
- out.close();
- }
-}
diff --git a/test-src/nu/validator/htmlparser/tools/XML2XML.java b/test-src/nu/validator/htmlparser/tools/XML2XML.java
deleted file mode 100644
index 2f6aa24d..00000000
--- a/test-src/nu/validator/htmlparser/tools/XML2XML.java
+++ /dev/null
@@ -1,89 +0,0 @@
-/*
- * Copyright (c) 2008 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.tools;
-
-import java.io.FileInputStream;
-import java.io.FileOutputStream;
-import java.io.IOException;
-import java.io.InputStream;
-import java.io.OutputStream;
-import java.net.MalformedURLException;
-
-import javax.xml.parsers.ParserConfigurationException;
-import javax.xml.parsers.SAXParserFactory;
-import javax.xml.transform.TransformerException;
-
-import nu.validator.htmlparser.sax.NameCheckingXmlSerializer;
-import nu.validator.htmlparser.sax.XmlSerializer;
-import nu.validator.htmlparser.test.SystemErrErrorHandler;
-
-import org.xml.sax.ContentHandler;
-import org.xml.sax.InputSource;
-import org.xml.sax.SAXException;
-import org.xml.sax.XMLReader;
-
-public class XML2XML {
-
- /**
- * @param args
- */
- public static void main(String[] args) throws SAXException,
- ParserConfigurationException, MalformedURLException, IOException,
- TransformerException {
- InputStream in;
- OutputStream out;
-
- switch (args.length) {
- case 0:
- in = System.in;
- out = System.out;
- break;
- case 1:
- in = new FileInputStream(args[0]);
- out = System.out;
- break;
- case 2:
- in = new FileInputStream(args[0]);
- out = new FileOutputStream(args[1]);
- break;
- default:
- System.err.println("Too many arguments. No arguments to use stdin/stdout. One argument to reading from file and write to stdout. Two arguments to read from first file and write to second.");
- System.exit(1);
- return;
- }
-
- ContentHandler serializer = new NameCheckingXmlSerializer(out);
-
- SAXParserFactory factory = SAXParserFactory.newInstance();
- factory.setNamespaceAware(true);
- factory.setValidating(false);
- XMLReader parser = factory.newSAXParser().getXMLReader();
- parser.setErrorHandler(new SystemErrErrorHandler());
- parser.setContentHandler(serializer);
- parser.setProperty("http://xml.org/sax/properties/lexical-handler",
- serializer);
- parser.parse(new InputSource(in));
- out.flush();
- out.close();
- }
-}
diff --git a/test-src/nu/validator/htmlparser/tools/XSLT4HTML5.java b/test-src/nu/validator/htmlparser/tools/XSLT4HTML5.java
deleted file mode 100644
index 05d8193c..00000000
--- a/test-src/nu/validator/htmlparser/tools/XSLT4HTML5.java
+++ /dev/null
@@ -1,237 +0,0 @@
-/*
- * Copyright (c) 2007 Henri Sivonen
- * Copyright (c) 2007 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.tools;
-
-import java.io.File;
-import java.io.FileOutputStream;
-import java.io.IOException;
-import java.net.MalformedURLException;
-
-import javax.xml.parsers.DocumentBuilder;
-import javax.xml.parsers.DocumentBuilderFactory;
-import javax.xml.parsers.ParserConfigurationException;
-import javax.xml.parsers.SAXParserFactory;
-import javax.xml.transform.Templates;
-import javax.xml.transform.Transformer;
-import javax.xml.transform.TransformerException;
-import javax.xml.transform.TransformerFactory;
-import javax.xml.transform.dom.DOMSource;
-import javax.xml.transform.sax.SAXResult;
-import javax.xml.transform.sax.SAXTransformerFactory;
-import javax.xml.transform.sax.TemplatesHandler;
-import javax.xml.transform.sax.TransformerHandler;
-
-import nu.validator.htmlparser.common.XmlViolationPolicy;
-import nu.validator.htmlparser.dom.HtmlDocumentBuilder;
-import nu.validator.htmlparser.sax.HtmlParser;
-import nu.validator.htmlparser.sax.HtmlSerializer;
-import nu.validator.htmlparser.sax.XmlSerializer;
-import nu.validator.htmlparser.test.SystemErrErrorHandler;
-
-import org.w3c.dom.Document;
-import org.xml.sax.ContentHandler;
-import org.xml.sax.SAXException;
-import org.xml.sax.XMLReader;
-import org.xml.sax.ext.LexicalHandler;
-
-public class XSLT4HTML5 {
-
- private enum Mode {
- STREAMING_SAX, BUFFERED_SAX, DOM,
- }
-
- private static final String TEMPLATE = "--template=";
-
- private static final String INPUT_HTML = "--input-html=";
-
- private static final String INPUT_XML = "--input-xml=";
-
- private static final String OUTPUT_HTML = "--output-html=";
-
- private static final String OUTPUT_XML = "--output-xml=";
-
- private static final String MODE = "--mode=";
-
- /**
- * @param args
- * @throws ParserConfigurationException
- * @throws SAXException
- * @throws IOException
- * @throws MalformedURLException
- * @throws TransformerException
- */
- public static void main(String[] args) throws SAXException,
- ParserConfigurationException, MalformedURLException, IOException, TransformerException {
- if (args.length == 0) {
- System.out.println("--template=file --input-[html|xml]=file --output-[html|xml]=file --mode=[sax-streaming|sax-buffered|dom]");
- System.exit(0);
- }
- String template = null;
- String input = null;
- boolean inputHtml = false;
- String output = null;
- boolean outputHtml = false;
- Mode mode = null;
- for (int i = 0; i < args.length; i++) {
- String arg = args[i];
- if (arg.startsWith(TEMPLATE)) {
- if (template == null) {
- template = arg.substring(TEMPLATE.length());
- } else {
- System.err.println("Tried to set template twice.");
- System.exit(1);
- }
- } else if (arg.startsWith(INPUT_HTML)) {
- if (input == null) {
- input = arg.substring(INPUT_HTML.length());
- inputHtml = true;
- } else {
- System.err.println("Tried to set input twice.");
- System.exit(2);
- }
- } else if (arg.startsWith(INPUT_XML)) {
- if (input == null) {
- input = arg.substring(INPUT_XML.length());
- inputHtml = false;
- } else {
- System.err.println("Tried to set input twice.");
- System.exit(2);
- }
- } else if (arg.startsWith(OUTPUT_HTML)) {
- if (output == null) {
- output = arg.substring(OUTPUT_HTML.length());
- outputHtml = true;
- } else {
- System.err.println("Tried to set output twice.");
- System.exit(3);
- }
- } else if (arg.startsWith(OUTPUT_XML)) {
- if (output == null) {
- output = arg.substring(OUTPUT_XML.length());
- outputHtml = false;
- } else {
- System.err.println("Tried to set output twice.");
- System.exit(3);
- }
- } else if (arg.startsWith(MODE)) {
- if (mode == null) {
- String modeStr = arg.substring(MODE.length());
- if ("dom".equals(modeStr)) {
- mode = Mode.DOM;
- } else if ("sax-buffered".equals(modeStr)) {
- mode = Mode.BUFFERED_SAX;
- } else if ("sax-streaming".equals(modeStr)) {
- mode = Mode.STREAMING_SAX;
- } else {
- System.err.println("Unrecognized mode.");
- System.exit(5);
- }
- } else {
- System.err.println("Tried to set mode twice.");
- System.exit(4);
- }
- }
- }
-
- if (template == null) {
- System.err.println("No template specified.");
- System.exit(6);
- }
- if (input == null) {
- System.err.println("No input specified.");
- System.exit(7);
- }
- if (output == null) {
- System.err.println("No output specified.");
- System.exit(8);
- }
- if (mode == null) {
- mode = Mode.BUFFERED_SAX;
- }
-
- SystemErrErrorHandler errorHandler = new SystemErrErrorHandler();
-
- SAXParserFactory factory = SAXParserFactory.newInstance();
- factory.setNamespaceAware(true);
- factory.setValidating(false);
- XMLReader reader = factory.newSAXParser().getXMLReader();
- reader.setErrorHandler(errorHandler);
-
- SAXTransformerFactory transformerFactory = (SAXTransformerFactory) TransformerFactory.newInstance();
- transformerFactory.setErrorListener(errorHandler);
- TemplatesHandler templatesHandler = transformerFactory.newTemplatesHandler();
- reader.setContentHandler(templatesHandler);
- reader.parse(new File(template).toURI().toASCIIString());
-
- Templates templates = templatesHandler.getTemplates();
-
- FileOutputStream outputStream = new FileOutputStream(output);
- ContentHandler serializer;
- if (outputHtml) {
- serializer = new HtmlSerializer(outputStream);
- } else {
- serializer = new XmlSerializer(outputStream);
- }
- SAXResult result = new SAXResult(new XmlnsDropper(serializer));
- result.setLexicalHandler((LexicalHandler) serializer);
-
- if (mode == Mode.DOM) {
- Document inputDoc;
- DocumentBuilder builder;
- if (inputHtml) {
- builder = new HtmlDocumentBuilder(XmlViolationPolicy.ALTER_INFOSET);
- } else {
- DocumentBuilderFactory builderFactory = DocumentBuilderFactory.newInstance();
- factory.setNamespaceAware(true);
- try {
- builder = builderFactory.newDocumentBuilder();
- } catch (ParserConfigurationException e) {
- throw new RuntimeException(e);
- }
- }
- inputDoc = builder.parse(new File(input));
- DOMSource inputSource = new DOMSource(inputDoc,
- new File(input).toURI().toASCIIString());
- Transformer transformer = templates.newTransformer();
- transformer.setErrorListener(errorHandler);
- transformer.transform(inputSource, result);
- } else {
- if (inputHtml) {
- reader = new HtmlParser(XmlViolationPolicy.ALTER_INFOSET);
- if (mode == Mode.STREAMING_SAX) {
- reader.setProperty("http://validator.nu/properties/streamability-violation-policy", XmlViolationPolicy.FATAL);
- }
- }
- TransformerHandler transformerHandler = transformerFactory.newTransformerHandler(templates);
- transformerHandler.setResult(result);
- reader.setErrorHandler(errorHandler);
- reader.setContentHandler(transformerHandler);
- reader.setProperty("http://xml.org/sax/properties/lexical-handler", transformerHandler);
- reader.parse(new File(input).toURI().toASCIIString());
- }
- outputStream.flush();
- outputStream.close();
- }
-
-}
diff --git a/test-src/nu/validator/htmlparser/tools/XSLT4HTML5XOM.java b/test-src/nu/validator/htmlparser/tools/XSLT4HTML5XOM.java
deleted file mode 100644
index b364cc52..00000000
--- a/test-src/nu/validator/htmlparser/tools/XSLT4HTML5XOM.java
+++ /dev/null
@@ -1,162 +0,0 @@
-/*
- * Copyright (c) 2007 Henri Sivonen
- * Copyright (c) 2007 Mozilla Foundation
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.tools;
-
-import java.io.File;
-import java.io.FileOutputStream;
-import java.io.IOException;
-
-import nu.validator.htmlparser.common.XmlViolationPolicy;
-import nu.validator.htmlparser.sax.HtmlSerializer;
-import nu.validator.htmlparser.xom.HtmlBuilder;
-import nu.xom.Builder;
-import nu.xom.Document;
-import nu.xom.Element;
-import nu.xom.Nodes;
-import nu.xom.ParsingException;
-import nu.xom.Serializer;
-import nu.xom.ValidityException;
-import nu.xom.converters.SAXConverter;
-import nu.xom.xslt.XSLException;
-import nu.xom.xslt.XSLTransform;
-
-import org.xml.sax.SAXException;
-
-public class XSLT4HTML5XOM {
-
- private static final String TEMPLATE = "--template=";
-
- private static final String INPUT_HTML = "--input-html=";
-
- private static final String INPUT_XML = "--input-xml=";
-
- private static final String OUTPUT_HTML = "--output-html=";
-
- private static final String OUTPUT_XML = "--output-xml=";
-
- /**
- * @param args
- * @throws IOException
- * @throws ParsingException
- * @throws ValidityException
- * @throws XSLException
- * @throws SAXException
- */
- public static void main(String[] args) throws ValidityException,
- ParsingException, IOException, XSLException, SAXException {
- if (args.length == 0) {
- System.out.println("--template=file --input-[html|xml]=file --output-[html|xml]=file --mode=[sax-streaming|sax-buffered|dom]");
- System.exit(0);
- }
- String template = null;
- String input = null;
- boolean inputHtml = false;
- String output = null;
- boolean outputHtml = false;
- for (int i = 0; i < args.length; i++) {
- String arg = args[i];
- if (arg.startsWith(TEMPLATE)) {
- if (template == null) {
- template = arg.substring(TEMPLATE.length());
- } else {
- System.err.println("Tried to set template twice.");
- System.exit(1);
- }
- } else if (arg.startsWith(INPUT_HTML)) {
- if (input == null) {
- input = arg.substring(INPUT_HTML.length());
- inputHtml = true;
- } else {
- System.err.println("Tried to set input twice.");
- System.exit(2);
- }
- } else if (arg.startsWith(INPUT_XML)) {
- if (input == null) {
- input = arg.substring(INPUT_XML.length());
- inputHtml = false;
- } else {
- System.err.println("Tried to set input twice.");
- System.exit(2);
- }
- } else if (arg.startsWith(OUTPUT_HTML)) {
- if (output == null) {
- output = arg.substring(OUTPUT_HTML.length());
- outputHtml = true;
- } else {
- System.err.println("Tried to set output twice.");
- System.exit(3);
- }
- } else if (arg.startsWith(OUTPUT_XML)) {
- if (output == null) {
- output = arg.substring(OUTPUT_XML.length());
- outputHtml = false;
- } else {
- System.err.println("Tried to set output twice.");
- System.exit(3);
- }
- }
- }
-
- if (template == null) {
- System.err.println("No template specified.");
- System.exit(6);
- }
- if (input == null) {
- System.err.println("No input specified.");
- System.exit(7);
- }
- if (output == null) {
- System.err.println("No output specified.");
- System.exit(8);
- }
-
- Builder builder = new Builder();
-
- Document transformationDoc = builder.build(new File(template));
-
- XSLTransform transform = new XSLTransform(transformationDoc);
-
- FileOutputStream outputStream = new FileOutputStream(output);
-
- Document inputDoc;
- if (inputHtml) {
- builder = new HtmlBuilder(XmlViolationPolicy.ALTER_INFOSET);
- }
- inputDoc = builder.build(new File(input));
- Nodes result = transform.transform(inputDoc);
- Document outputDoc = new Document((Element) result.get(0));
- if (outputHtml) {
- HtmlSerializer htmlSerializer = new HtmlSerializer(outputStream);
- SAXConverter converter = new SAXConverter(htmlSerializer);
- converter.setLexicalHandler(htmlSerializer);
- converter.convert(outputDoc);
- } else {
- Serializer serializer = new Serializer(outputStream);
- serializer.write(outputDoc);
- }
- outputStream.flush();
- outputStream.close();
- }
-
-}
diff --git a/test-src/nu/validator/htmlparser/tools/XmlnsDropper.java b/test-src/nu/validator/htmlparser/tools/XmlnsDropper.java
deleted file mode 100644
index 0e6d4b1c..00000000
--- a/test-src/nu/validator/htmlparser/tools/XmlnsDropper.java
+++ /dev/null
@@ -1,169 +0,0 @@
-/*
- * Copyright (c) 2007 Henri Sivonen
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice shall be included in
- * all copies or substantial portions of the Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS IN THE SOFTWARE.
- */
-
-package nu.validator.htmlparser.tools;
-
-import org.xml.sax.Attributes;
-import org.xml.sax.ContentHandler;
-import org.xml.sax.Locator;
-import org.xml.sax.SAXException;
-import org.xml.sax.helpers.AttributesImpl;
-
-/**
- * Quick and dirty hack to work around Xalan xmlns weirdness.
- *
- * @version $Id$
- * @author hsivonen
- */
-class XmlnsDropper implements ContentHandler {
-
- private final ContentHandler delegate;
-
- /**
- * @param delegate
- */
- public XmlnsDropper(final ContentHandler delegate) {
- this.delegate = delegate;
- }
-
- /**
- * @param ch
- * @param start
- * @param length
- * @throws SAXException
- * @see org.xml.sax.ContentHandler#characters(char[], int, int)
- */
- public void characters(char[] ch, int start, int length) throws SAXException {
- delegate.characters(ch, start, length);
- }
-
- /**
- * @throws SAXException
- * @see org.xml.sax.ContentHandler#endDocument()
- */
- public void endDocument() throws SAXException {
- delegate.endDocument();
- }
-
- /**
- * @param uri
- * @param localName
- * @param qName
- * @throws SAXException
- * @see org.xml.sax.ContentHandler#endElement(java.lang.String, java.lang.String, java.lang.String)
- */
- public void endElement(String uri, String localName, String qName) throws SAXException {
- delegate.endElement(uri, localName, qName);
- }
-
- /**
- * @param prefix
- * @throws SAXException
- * @see org.xml.sax.ContentHandler#endPrefixMapping(java.lang.String)
- */
- public void endPrefixMapping(String prefix) throws SAXException {
- delegate.endPrefixMapping(prefix);
- }
-
- /**
- * @param ch
- * @param start
- * @param length
- * @throws SAXException
- * @see org.xml.sax.ContentHandler#ignorableWhitespace(char[], int, int)
- */
- public void ignorableWhitespace(char[] ch, int start, int length) throws SAXException {
- delegate.ignorableWhitespace(ch, start, length);
- }
-
- /**
- * @param target
- * @param data
- * @throws SAXException
- * @see org.xml.sax.ContentHandler#processingInstruction(java.lang.String, java.lang.String)
- */
- public void processingInstruction(String target, String data) throws SAXException {
- delegate.processingInstruction(target, data);
- }
-
- /**
- * @param locator
- * @see org.xml.sax.ContentHandler#setDocumentLocator(org.xml.sax.Locator)
- */
- public void setDocumentLocator(Locator locator) {
- delegate.setDocumentLocator(locator);
- }
-
- /**
- * @param name
- * @throws SAXException
- * @see org.xml.sax.ContentHandler#skippedEntity(java.lang.String)
- */
- public void skippedEntity(String name) throws SAXException {
- delegate.skippedEntity(name);
- }
-
- /**
- * @throws SAXException
- * @see org.xml.sax.ContentHandler#startDocument()
- */
- public void startDocument() throws SAXException {
- delegate.startDocument();
- }
-
- /**
- * @param uri
- * @param localName
- * @param qName
- * @param atts
- * @throws SAXException
- * @see org.xml.sax.ContentHandler#startElement(java.lang.String, java.lang.String, java.lang.String, org.xml.sax.Attributes)
- */
- public void startElement(String uri, String localName, String qName, Attributes atts) throws SAXException {
- AttributesImpl ai = new AttributesImpl();
- for (int i = 0; i < atts.getLength(); i++) {
- String u = atts.getURI(i);
- String t = atts.getType(i);
- String v = atts.getValue(i);
- String n = atts.getLocalName(i);
- String q = atts.getQName(i);
- if (q != null) {
- if ("xmlns".equals(q) || q.startsWith("xmlns:")) {
- continue;
- }
- }
- ai.addAttribute(u, n, q, t, v);
- }
- delegate.startElement(uri, localName, qName, ai);
- }
-
- /**
- * @param prefix
- * @param uri
- * @throws SAXException
- * @see org.xml.sax.ContentHandler#startPrefixMapping(java.lang.String, java.lang.String)
- */
- public void startPrefixMapping(String prefix, String uri) throws SAXException {
- delegate.startPrefixMapping(prefix, uri);
- }
-
-}
diff --git a/translator-src/nu/validator/htmlparser/cpptranslate/AnnotationHelperVisitor.java b/translator-src/nu/validator/htmlparser/cpptranslate/AnnotationHelperVisitor.java
deleted file mode 100644
index 98a0226e..00000000
--- a/translator-src/nu/validator/htmlparser/cpptranslate/AnnotationHelperVisitor.java
+++ /dev/null
@@ -1,159 +0,0 @@
-/* ***** BEGIN LICENSE BLOCK *****
- * Version: MPL 1.1/GPL 2.0/LGPL 2.1
- *
- * The contents of this file are subject to the Mozilla Public License Version
- * 1.1 (the "License"); you may not use this file except in compliance with
- * the License. You may obtain a copy of the License at
- * http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS" basis,
- * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
- * for the specific language governing rights and limitations under the
- * License.
- *
- * The Original Code is HTML Parser C++ Translator code.
- *
- * The Initial Developer of the Original Code is
- * Mozilla Foundation.
- * Portions created by the Initial Developer are Copyright (C) 2009
- * the Initial Developer. All Rights Reserved.
- *
- * Contributor(s):
- * Henri Sivonen
- *
- * Alternatively, the contents of this file may be used under the terms of
- * either the GNU General Public License Version 2 or later (the "GPL"), or
- * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
- * in which case the provisions of the GPL or the LGPL are applicable instead
- * of those above. If you wish to allow use of your version of this file only
- * under the terms of either the GPL or the LGPL, and not to allow others to
- * use your version of this file under the terms of the MPL, indicate your
- * decision by deleting the provisions above and replace them with the notice
- * and other provisions required by the GPL or the LGPL. If you do not delete
- * the provisions above, a recipient may use your version of this file under
- * the terms of any one of the MPL, the GPL or the LGPL.
- *
- * ***** END LICENSE BLOCK ***** */
-
-package nu.validator.htmlparser.cpptranslate;
-
-import java.util.List;
-
-import japa.parser.ast.expr.AnnotationExpr;
-import japa.parser.ast.expr.MarkerAnnotationExpr;
-import japa.parser.ast.type.ReferenceType;
-import japa.parser.ast.visitor.VoidVisitorAdapter;
-
-public class AnnotationHelperVisitor extends VoidVisitorAdapter {
-
- protected List currentAnnotations;
-
- protected boolean nsUri() {
- return hasAnnotation("NsUri");
- }
-
- protected boolean prefix() {
- return hasAnnotation("Prefix");
- }
-
- protected boolean local() {
- return hasAnnotation("Local");
- }
-
- protected boolean literal() {
- return hasAnnotation("Literal");
- }
-
- protected boolean inline() {
- return hasAnnotation("Inline");
- }
-
- protected boolean noLength() {
- return hasAnnotation("NoLength");
- }
-
- protected boolean unsigned() {
- return hasAnnotation("Unsigned");
- }
-
- protected boolean auto() {
- return hasAnnotation("Auto");
- }
-
- protected boolean virtual() {
- return hasAnnotation("Virtual");
- }
-
- protected boolean override() {
- return hasAnnotation("Override");
- }
-
- protected boolean isConst() {
- return hasAnnotation("Const");
- }
-
- protected boolean characterName() {
- return hasAnnotation("CharacterName");
- }
-
- protected boolean creator() {
- return hasAnnotation("Creator");
- }
-
- protected boolean htmlCreator() {
- return hasAnnotation("HtmlCreator");
- }
-
- protected boolean svgCreator() {
- return hasAnnotation("SvgCreator");
- }
-
- private boolean hasAnnotation(String anno) {
- if (currentAnnotations == null) {
- return false;
- }
- for (AnnotationExpr ann : currentAnnotations) {
- if (ann instanceof MarkerAnnotationExpr) {
- MarkerAnnotationExpr marker = (MarkerAnnotationExpr) ann;
- if (marker.getName().getName().equals(anno)) {
- return true;
- }
- }
- }
- return false;
- }
-
- protected Type convertType(japa.parser.ast.type.Type type, int modifiers) {
- if (type instanceof ReferenceType) {
- ReferenceType referenceType = (ReferenceType) type;
- return new Type(convertTypeName(referenceType.getType().toString()), referenceType.getArrayCount(), noLength(), modifiers);
- } else {
- return new Type(convertTypeName(type.toString()), 0, false, modifiers);
- }
- }
-
- private String convertTypeName(String name) {
- if ("String".equals(name)) {
- if (local()) {
- return "@Local";
- }
- if (nsUri()) {
- return "@NsUri";
- }
- if (prefix()) {
- return "@Prefix";
- }
- if (literal()) {
- return "@Literal";
- }
- if (auto()) {
- return "@Auto";
- }
- if (characterName()) {
- return "@CharacterName";
- }
- }
- return name;
- }
-
-}
diff --git a/translator-src/nu/validator/htmlparser/cpptranslate/CppOnlyInputStream.java b/translator-src/nu/validator/htmlparser/cpptranslate/CppOnlyInputStream.java
deleted file mode 100644
index 587b8160..00000000
--- a/translator-src/nu/validator/htmlparser/cpptranslate/CppOnlyInputStream.java
+++ /dev/null
@@ -1,70 +0,0 @@
-/* ***** BEGIN LICENSE BLOCK *****
- * Version: MPL 1.1/GPL 2.0/LGPL 2.1
- *
- * The contents of this file are subject to the Mozilla Public License Version
- * 1.1 (the "License"); you may not use this file except in compliance with
- * the License. You may obtain a copy of the License at
- * http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS" basis,
- * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
- * for the specific language governing rights and limitations under the
- * License.
- *
- * The Original Code is HTML Parser C++ Translator code.
- *
- * The Initial Developer of the Original Code is
- * Mozilla Foundation.
- * Portions created by the Initial Developer are Copyright (C) 2010
- * the Initial Developer. All Rights Reserved.
- *
- * Contributor(s):
- * Henri Sivonen
- *
- * Alternatively, the contents of this file may be used under the terms of
- * either the GNU General Public License Version 2 or later (the "GPL"), or
- * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
- * in which case the provisions of the GPL or the LGPL are applicable instead
- * of those above. If you wish to allow use of your version of this file only
- * under the terms of either the GPL or the LGPL, and not to allow others to
- * use your version of this file under the terms of the MPL, indicate your
- * decision by deleting the provisions above and replace them with the notice
- * and other provisions required by the GPL or the LGPL. If you do not delete
- * the provisions above, a recipient may use your version of this file under
- * the terms of any one of the MPL, the GPL or the LGPL.
- *
- * ***** END LICENSE BLOCK ***** */
-
-package nu.validator.htmlparser.cpptranslate;
-
-import java.io.BufferedInputStream;
-import java.io.IOException;
-import java.io.InputStream;
-
-public class CppOnlyInputStream extends InputStream {
-
- private static final String DROP = "// CPPONLY:";
-
- private final InputStream delegate;
-
- public CppOnlyInputStream(InputStream delegate) {
- this.delegate = new BufferedInputStream(delegate);
- }
-
- @Override public int read() throws IOException {
- int c = delegate.read();
- if (c == DROP.charAt(0)) {
- delegate.mark(DROP.length());
- for (int i = 1; i < DROP.length(); ++i) {
- int d = delegate.read();
- if (d != DROP.charAt(i)) {
- delegate.reset();
- return c;
- }
- }
- return delegate.read();
- }
- return c;
- }
-
-}
diff --git a/translator-src/nu/validator/htmlparser/cpptranslate/CppTypes.java b/translator-src/nu/validator/htmlparser/cpptranslate/CppTypes.java
deleted file mode 100644
index d75f8fe0..00000000
--- a/translator-src/nu/validator/htmlparser/cpptranslate/CppTypes.java
+++ /dev/null
@@ -1,493 +0,0 @@
-/* ***** BEGIN LICENSE BLOCK *****
- * Version: MPL 1.1/GPL 2.0/LGPL 2.1
- *
- * The contents of this file are subject to the Mozilla Public License Version
- * 1.1 (the "License"); you may not use this file except in compliance with
- * the License. You may obtain a copy of the License at
- * http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS" basis,
- * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
- * for the specific language governing rights and limitations under the
- * License.
- *
- * The Original Code is HTML Parser C++ Translator code.
- *
- * The Initial Developer of the Original Code is
- * Mozilla Foundation.
- * Portions created by the Initial Developer are Copyright (C) 2008-2009
- * the Initial Developer. All Rights Reserved.
- *
- * Contributor(s):
- * Henri Sivonen
- *
- * Alternatively, the contents of this file may be used under the terms of
- * either the GNU General Public License Version 2 or later (the "GPL"), or
- * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
- * in which case the provisions of the GPL or the LGPL are applicable instead
- * of those above. If you wish to allow use of your version of this file only
- * under the terms of either the GPL or the LGPL, and not to allow others to
- * use your version of this file under the terms of the MPL, indicate your
- * decision by deleting the provisions above and replace them with the notice
- * and other provisions required by the GPL or the LGPL. If you do not delete
- * the provisions above, a recipient may use your version of this file under
- * the terms of any one of the MPL, the GPL or the LGPL.
- *
- * ***** END LICENSE BLOCK ***** */
-
-package nu.validator.htmlparser.cpptranslate;
-
-import java.io.BufferedReader;
-import java.io.File;
-import java.io.FileInputStream;
-import java.io.FileOutputStream;
-import java.io.IOException;
-import java.io.InputStreamReader;
-import java.io.OutputStreamWriter;
-import java.io.Writer;
-import java.util.Arrays;
-import java.util.HashMap;
-import java.util.HashSet;
-import java.util.Map;
-import java.util.Set;
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
-
-public class CppTypes {
-
- /* Please note we aren't looking for the following Atom definitions:
- PseudoElementAtom or NonInheritingAnonBoxAtom or InheritingAnonBoxAtom */
- private static final Pattern ATOM_DEF = Pattern.compile("^\\s*Atom\\(\"([^,]+)\",\\s*\"([^\"]*)\"\\).*$");
-
- private static Set reservedWords = new HashSet();
-
- static {
- reservedWords.add("small");
- reservedWords.add("for");
- reservedWords.add("false");
- reservedWords.add("true");
- reservedWords.add("default");
- reservedWords.add("class");
- reservedWords.add("switch");
- reservedWords.add("union");
- reservedWords.add("template");
- reservedWords.add("int");
- reservedWords.add("char");
- reservedWords.add("operator");
- reservedWords.add("or");
- reservedWords.add("and");
- reservedWords.add("not");
- reservedWords.add("xor");
- reservedWords.add("unicode");
- }
-
- private static final String[] TREE_BUILDER_INCLUDES = { "nsContentUtils", "nsAtom", "nsHtml5AtomTable",
- "nsHtml5String", "nsNameSpaceManager", "nsIContent", "nsTraceRefcnt", "jArray", "nsHtml5DocumentMode",
- "nsHtml5ArrayCopy", "nsHtml5Parser", "nsGkAtoms", "nsHtml5TreeOperation", "nsHtml5StateSnapshot",
- "nsHtml5StackNode", "nsHtml5TreeOpExecutor", "nsHtml5StreamParser", "nsAHtml5TreeBuilderState",
- "nsHtml5Highlighter", "nsHtml5PlainTextUtils", "nsHtml5ViewSourceUtils", "mozilla/ImportScanner",
- "mozilla/Likely", "nsIContentHandle", "nsHtml5OplessBuilder", };
-
- private static final String[] TOKENIZER_INCLUDES = { "nsAtom",
- "nsHtml5AtomTable", "nsHtml5String", "nsIContent", "nsTraceRefcnt",
- "jArray", "nsHtml5DocumentMode", "nsHtml5ArrayCopy",
- "nsHtml5NamedCharacters", "nsHtml5NamedCharactersAccel",
- "nsGkAtoms", "nsAHtml5TreeBuilderState", "nsHtml5Macros",
- "nsHtml5Highlighter", "nsHtml5TokenizerLoopPolicies" };
-
- private static final String[] INCLUDES = { "nsAtom", "nsHtml5AtomTable",
- "nsHtml5String", "nsNameSpaceManager", "nsIContent",
- "nsTraceRefcnt", "jArray", "nsHtml5ArrayCopy",
- "nsAHtml5TreeBuilderState", "nsGkAtoms", "nsHtml5ByteReadable",
- "nsHtml5Macros", "nsIContentHandle", "nsHtml5Portability",
- "nsHtml5ContentCreatorFunction"};
-
- private static final String[] OTHER_DECLATIONS = {};
-
- private static final String[] TREE_BUILDER_OTHER_DECLATIONS = {};
-
- private static final String[] NAMED_CHARACTERS_INCLUDES = { "jArray",
- "nscore", "nsDebug", "mozilla/Logging", "nsMemory" };
-
- private static final String[] FORWARD_DECLARATIONS = { "nsHtml5StreamParser" };
-
- private static final String[] CLASSES_THAT_NEED_SUPPLEMENT = {
- "MetaScanner", "Tokenizer", "TreeBuilder", "UTF16Buffer", };
-
- private static final String[] STATE_LOOP_POLICIES = {
- "nsHtml5ViewSourcePolicy", "nsHtml5SilentPolicy" };
-
- private final Map atomMap = new HashMap();
-
- private final Writer atomWriter;
-
- public CppTypes(File atomList, File generatedAtomFile) {
- if (atomList == null) {
- atomWriter = null;
- } else {
- try {
- ingestAtoms(atomList);
- atomWriter = new OutputStreamWriter(new FileOutputStream(
- generatedAtomFile), "utf-8");
- this.start();
- } catch (IOException e) {
- throw new RuntimeException(e);
- }
- }
- }
-
- private void ingestAtoms(File atomList) throws IOException {
- // This doesn't need to be efficient, so let's make it easy to write.
- BufferedReader atomReader = new BufferedReader(
- new InputStreamReader(new FileInputStream(atomList), "utf-8"));
- try {
- String line;
- boolean startedParsing = false;
- while ((line = atomReader.readLine()) != null) {
- // only start parsing lines after this comment
- if (line.trim().startsWith("# START ATOMS")) {
- startedParsing = true;
- } else if (!startedParsing) {
- continue;
- }
- // stop parsing lines after this comment
- if (line.trim().startsWith("# END ATOMS")) {
- return;
- }
- if (!line.trim().startsWith("Atom")) {
- continue;
- }
- Matcher m = ATOM_DEF.matcher(line);
- if (!m.matches()) {
- throw new RuntimeException("Malformed atom definition: " + line);
- }
- atomMap.put(m.group(2), m.group(1));
- }
- throw new RuntimeException(
- "Atom list did not have a marker for generated section.");
- } finally {
- atomReader.close();
- }
- }
-
- public void start() {
- try {
-
- if (atomWriter != null) {
- atomWriter.write("# THIS FILE IS GENERATED BY THE HTML PARSER TRANSLATOR AND WILL BE OVERWRITTEN!\n");
- atomWriter.write("from Atom import Atom\n\n");
- atomWriter.write("HTML_PARSER_ATOMS = [\n");
- }
- } catch (IOException e) {
- throw new RuntimeException(e);
- }
- }
-
- public void finished() {
- try {
- if (atomWriter != null) {
- atomWriter.write("]\n");
- atomWriter.flush();
- atomWriter.close();
- }
- } catch (IOException e) {
- throw new RuntimeException(e);
- }
- }
-
- public String classPrefix() {
- return "nsHtml5";
- }
-
- public String booleanType() {
- return "bool";
- }
-
- public String byteType() {
- return "int8_t";
- }
-
- public String charType() {
- return "char16_t";
- }
-
- /**
- * Only used for named characters.
- *
- * @return
- */
- public String unsignedShortType() {
- return "uint16_t";
- }
-
- public String intType() {
- return "int32_t";
- }
-
- public String unsignedIntType() {
- return "uint32_t";
- }
-
- public String stringType() {
- return "nsHtml5String";
- }
-
- public String weakLocalType() {
- return "nsAtom*";
- }
-
- public String localType() {
- return "RefPtr";
- }
-
- public String prefixType() {
- return "nsStaticAtom*";
- }
-
- public String nsUriType() {
- return "int32_t";
- }
-
- public String falseLiteral() {
- return "false";
- }
-
- public String trueLiteral() {
- return "true";
- }
-
- public String nullLiteral() {
- return "nullptr";
- }
-
- public String encodingDeclarationHandlerType() {
- return "nsHtml5StreamParser*";
- }
-
- public String nodeType() {
- return "nsIContentHandle*";
- }
-
- public String htmlCreatorType() {
- return "mozilla::dom::HTMLContentCreatorFunction";
- }
-
- public String svgCreatorType() {
- return "mozilla::dom::SVGContentCreatorFunction";
- }
-
- public String creatorType() {
- return "nsHtml5ContentCreatorFunction";
- }
-
- public String xhtmlNamespaceLiteral() {
- return "kNameSpaceID_XHTML";
- }
-
- public String svgNamespaceLiteral() {
- return "kNameSpaceID_SVG";
- }
-
- public String xmlnsNamespaceLiteral() {
- return "kNameSpaceID_XMLNS";
- }
-
- public String xmlNamespaceLiteral() {
- return "kNameSpaceID_XML";
- }
-
- public String noNamespaceLiteral() {
- return "kNameSpaceID_None";
- }
-
- public String xlinkNamespaceLiteral() {
- return "kNameSpaceID_XLink";
- }
-
- public String mathmlNamespaceLiteral() {
- return "kNameSpaceID_MathML";
- }
-
- public String arrayTemplate() {
- return "jArray";
- }
-
- public String autoArrayTemplate() {
- return "autoJArray";
- }
-
- public String localForLiteral(String literal) {
- String atom = atomMap.get(literal);
- if (atom == null) {
- atom = createAtomName(literal);
- atomMap.put(literal, atom);
- if (atomWriter != null) {
- try {
- atomWriter.write(" # ATOM GENERATED BY HTML PARSER TRANSLATOR (WILL BE AUTOMATICALLY OVERWRITTEN):\n Atom(\"" + atom + "\", \"" + literal
- + "\"),\n");
- } catch (IOException e) {
- throw new RuntimeException(e);
- }
- }
- }
- return "nsGkAtoms::" + atom;
- }
-
- private String createAtomName(String literal) {
- String candidate = literal.replaceAll("[^a-zA-Z0-9_]", "_");
- if ("".equals(candidate)) {
- candidate = "emptystring";
- }
- while (atomMap.values().contains(candidate)
- || reservedWords.contains(candidate)) {
- candidate = candidate + '_';
- }
- return candidate;
- }
-
- public String stringForLiteral(String literal) {
- return '"' + literal + '"';
- }
-
- public String staticArrayTemplate() {
- return "staticJArray";
- }
-
- public String newArrayCreator() {
- return "newJArray";
- }
-
- public String[] boilerplateIncludes(String javaClass) {
- if ("TreeBuilder".equals(javaClass)) {
- return TREE_BUILDER_INCLUDES;
- } else if ("Tokenizer".equals(javaClass)) {
- return TOKENIZER_INCLUDES;
- } else {
- return INCLUDES;
- }
- }
-
- public String[] boilerplateDeclarations(String javaClass) {
- if ("TreeBuilder".equals(javaClass)) {
- return TREE_BUILDER_OTHER_DECLATIONS;
- } else {
- return OTHER_DECLATIONS;
- }
- }
-
- public String[] namedCharactersIncludes() {
- return NAMED_CHARACTERS_INCLUDES;
- }
-
- public String[] boilerplateForwardDeclarations() {
- return FORWARD_DECLARATIONS;
- }
-
- public String documentModeHandlerType() {
- return "nsHtml5TreeBuilder*";
- }
-
- public String documentModeType() {
- return "nsHtml5DocumentMode";
- }
-
- public String arrayCopy() {
- return "nsHtml5ArrayCopy::arraycopy";
- }
-
- public String maxInteger() {
- return "INT32_MAX";
- }
-
- public String constructorBoilerplate(String className) {
- return "MOZ_COUNT_CTOR(" + className + ");";
- }
-
- public String destructorBoilerplate(String className) {
- return "MOZ_COUNT_DTOR(" + className + ");";
- }
-
- public String literalType() {
- return "const char*";
- }
-
- public boolean hasSupplement(String javaClass) {
- return Arrays.binarySearch(CLASSES_THAT_NEED_SUPPLEMENT, javaClass) > -1;
- }
-
- public String internerType() {
- return "nsHtml5AtomTable*";
- }
-
- public String treeBuilderStateInterface() {
- return "nsAHtml5TreeBuilderState";
- }
-
- public String treeBuilderStateType() {
- return "nsAHtml5TreeBuilderState*";
- }
-
- public String arrayLengthMacro() {
- return "MOZ_ARRAY_LENGTH";
- }
-
- public String staticAssert() {
- return "static_assert";
- }
-
- public String continueMacro() {
- return "NS_HTML5_CONTINUE";
- }
-
- public String breakMacro() {
- return "NS_HTML5_BREAK";
- }
-
- public String characterNameType() {
- return "nsHtml5CharacterName&";
- }
-
- public String characterNameTypeDeclaration() {
- return "nsHtml5CharacterName";
- }
-
- public String transition() {
- return "P::transition";
- }
-
- public String tokenizerErrorCondition() {
- return "P::reportErrors";
- }
-
- public String firstTransitionArg() {
- return "mViewSource.get()";
- }
-
- public String errorHandler() {
- return this.unlikely() + "(mViewSource)";
- }
-
- public String unlikely() {
- return "MOZ_UNLIKELY";
- }
-
- public String completedCharacterReference() {
- return "P::completedNamedCharacterReference(mViewSource.get())";
- }
-
- public String[] stateLoopPolicies() {
- return STATE_LOOP_POLICIES;
- }
-
- public String assertionMacro() {
- return "MOZ_ASSERT";
- }
-
- public String releaseAssertionMacro() {
- return "MOZ_RELEASE_ASSERT";
- }
-
- public String crashMacro() {
- return "MOZ_CRASH";
- }
-}
diff --git a/translator-src/nu/validator/htmlparser/cpptranslate/CppVisitor.java b/translator-src/nu/validator/htmlparser/cpptranslate/CppVisitor.java
deleted file mode 100755
index e832e3bb..00000000
--- a/translator-src/nu/validator/htmlparser/cpptranslate/CppVisitor.java
+++ /dev/null
@@ -1,2446 +0,0 @@
-/*
- * Copyright (C) 2007 Júlio Vilmar Gesser.
- * Copyright (C) 2008 Mozilla Foundation
- *
- * This file is part of HTML Parser C++ Translator. It was derived from DumpVisitor
- * which was part of Java 1.5 parser and Abstract Syntax Tree and came with the following notice:
- *
- * Java 1.5 parser and Abstract Syntax Tree is free software: you can redistribute it and/or modify
- * it under the terms of the GNU Lesser General Public License as published by
- * the Free Software Foundation, either version 3 of the License, or
- * (at your option) any later version.
- *
- * Java 1.5 parser and Abstract Syntax Tree is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
- * GNU Lesser General Public License for more details.
- *
- * You should have received a copy of the GNU Lesser General Public License
- * along with Java 1.5 parser and Abstract Syntax Tree. If not, see .
- */
-/*
- * Created on 05/10/2006
- */
-package nu.validator.htmlparser.cpptranslate;
-
-import java.util.Arrays;
-import java.util.HashSet;
-import java.util.Iterator;
-import java.util.LinkedList;
-import java.util.List;
-import java.util.Set;
-
-import japa.parser.ast.BlockComment;
-import japa.parser.ast.CompilationUnit;
-import japa.parser.ast.ImportDeclaration;
-import japa.parser.ast.LineComment;
-import japa.parser.ast.Node;
-import japa.parser.ast.PackageDeclaration;
-import japa.parser.ast.TypeParameter;
-import japa.parser.ast.body.AnnotationDeclaration;
-import japa.parser.ast.body.AnnotationMemberDeclaration;
-import japa.parser.ast.body.BodyDeclaration;
-import japa.parser.ast.body.ClassOrInterfaceDeclaration;
-import japa.parser.ast.body.ConstructorDeclaration;
-import japa.parser.ast.body.EmptyMemberDeclaration;
-import japa.parser.ast.body.EmptyTypeDeclaration;
-import japa.parser.ast.body.EnumConstantDeclaration;
-import japa.parser.ast.body.EnumDeclaration;
-import japa.parser.ast.body.FieldDeclaration;
-import japa.parser.ast.body.InitializerDeclaration;
-import japa.parser.ast.body.JavadocComment;
-import japa.parser.ast.body.MethodDeclaration;
-import japa.parser.ast.body.ModifierSet;
-import japa.parser.ast.body.Parameter;
-import japa.parser.ast.body.TypeDeclaration;
-import japa.parser.ast.body.VariableDeclarator;
-import japa.parser.ast.body.VariableDeclaratorId;
-import japa.parser.ast.expr.ArrayAccessExpr;
-import japa.parser.ast.expr.ArrayCreationExpr;
-import japa.parser.ast.expr.ArrayInitializerExpr;
-import japa.parser.ast.expr.AssignExpr;
-import japa.parser.ast.expr.BinaryExpr;
-import japa.parser.ast.expr.BooleanLiteralExpr;
-import japa.parser.ast.expr.CastExpr;
-import japa.parser.ast.expr.CharLiteralExpr;
-import japa.parser.ast.expr.ClassExpr;
-import japa.parser.ast.expr.ConditionalExpr;
-import japa.parser.ast.expr.DoubleLiteralExpr;
-import japa.parser.ast.expr.EnclosedExpr;
-import japa.parser.ast.expr.Expression;
-import japa.parser.ast.expr.FieldAccessExpr;
-import japa.parser.ast.expr.InstanceOfExpr;
-import japa.parser.ast.expr.IntegerLiteralExpr;
-import japa.parser.ast.expr.IntegerLiteralMinValueExpr;
-import japa.parser.ast.expr.LongLiteralExpr;
-import japa.parser.ast.expr.LongLiteralMinValueExpr;
-import japa.parser.ast.expr.MarkerAnnotationExpr;
-import japa.parser.ast.expr.MemberValuePair;
-import japa.parser.ast.expr.MethodCallExpr;
-import japa.parser.ast.expr.NameExpr;
-import japa.parser.ast.expr.NormalAnnotationExpr;
-import japa.parser.ast.expr.NullLiteralExpr;
-import japa.parser.ast.expr.ObjectCreationExpr;
-import japa.parser.ast.expr.QualifiedNameExpr;
-import japa.parser.ast.expr.SingleMemberAnnotationExpr;
-import japa.parser.ast.expr.StringLiteralExpr;
-import japa.parser.ast.expr.SuperExpr;
-import japa.parser.ast.expr.ThisExpr;
-import japa.parser.ast.expr.UnaryExpr;
-import japa.parser.ast.expr.VariableDeclarationExpr;
-import japa.parser.ast.stmt.AssertStmt;
-import japa.parser.ast.stmt.BlockStmt;
-import japa.parser.ast.stmt.BreakStmt;
-import japa.parser.ast.stmt.CatchClause;
-import japa.parser.ast.stmt.ContinueStmt;
-import japa.parser.ast.stmt.DoStmt;
-import japa.parser.ast.stmt.EmptyStmt;
-import japa.parser.ast.stmt.ExplicitConstructorInvocationStmt;
-import japa.parser.ast.stmt.ExpressionStmt;
-import japa.parser.ast.stmt.ForStmt;
-import japa.parser.ast.stmt.ForeachStmt;
-import japa.parser.ast.stmt.IfStmt;
-import japa.parser.ast.stmt.LabeledStmt;
-import japa.parser.ast.stmt.ReturnStmt;
-import japa.parser.ast.stmt.Statement;
-import japa.parser.ast.stmt.SwitchEntryStmt;
-import japa.parser.ast.stmt.SwitchStmt;
-import japa.parser.ast.stmt.SynchronizedStmt;
-import japa.parser.ast.stmt.ThrowStmt;
-import japa.parser.ast.stmt.TryStmt;
-import japa.parser.ast.stmt.TypeDeclarationStmt;
-import japa.parser.ast.stmt.WhileStmt;
-import japa.parser.ast.type.ClassOrInterfaceType;
-import japa.parser.ast.type.PrimitiveType;
-import japa.parser.ast.type.ReferenceType;
-import japa.parser.ast.type.Type;
-import japa.parser.ast.type.VoidType;
-import japa.parser.ast.type.WildcardType;
-
-/**
- * @author Julio Vilmar Gesser
- * @author Henri Sivonen
- */
-
-public class CppVisitor extends AnnotationHelperVisitor {
-
- private static final String[] CLASS_NAMES = { "AttributeName",
- "ElementName", "HtmlAttributes", "LocatorImpl", "MetaScanner",
- "NamedCharacters", "NamedCharactersAccel", "Portability",
- "StackNode", "Tokenizer", "TreeBuilder", "UTF16Buffer" };
-
- private static final String[] METHODS_WITH_UNLIKELY_CONDITIONS = {
- "appendStrBuf" };
-
- public class SourcePrinter {
-
- private int level = 0;
-
- private boolean indented = false;
-
- private final StringBuilder buf = new StringBuilder();
-
- public void indent() {
- level++;
- }
-
- public void unindent() {
- level--;
- }
-
- private void makeIndent() {
- for (int i = 0; i < level; i++) {
- buf.append(" ");
- }
- }
-
- public void printWithoutIndent(String arg) {
- indented = false;
- buf.append(arg);
- }
-
- public void print(String arg) {
- if (!indented) {
- makeIndent();
- indented = true;
- }
- buf.append(arg);
- }
-
- public void printLn(String arg) {
- print(arg);
- printLn();
- }
-
- public void printLn() {
- buf.append("\n");
- indented = false;
- }
-
- public String getSource() {
- return buf.toString();
- }
-
- @Override public String toString() {
- return getSource();
- }
- }
-
- private boolean supportErrorReporting = true;
-
- protected SourcePrinter printer = new SourcePrinter();
-
- private SourcePrinter staticInitializerPrinter = new SourcePrinter();
-
- private SourcePrinter tempPrinterHolder;
-
- protected final CppTypes cppTypes;
-
- protected String className = "";
-
- protected int currentArrayCount;
-
- protected Set forLoopsWithCondition = new HashSet();
-
- protected boolean inPrimitiveNoLengthFieldDeclarator = false;
-
- protected boolean inField = false;
-
- protected boolean inArray = false;
-
- protected final SymbolTable symbolTable;
-
- protected String definePrefix;
-
- protected String javaClassName;
-
- protected boolean suppressPointer = false;
-
- private final List staticReleases = new LinkedList();
-
- private boolean inConstructorBody = false;
-
- private String currentMethod = null;
-
- private Set labels = null;
-
- private boolean destructor;
-
- protected boolean inStatic = false;
-
- private boolean reportTransitions = false;
-
- private int stateLoopCallCount = 0;
-
- /**
- * @param cppTypes
- */
- public CppVisitor(CppTypes cppTypes, SymbolTable symbolTable) {
- this.cppTypes = cppTypes;
- this.symbolTable = symbolTable;
- staticInitializerPrinter.indent();
- }
-
- public String getSource() {
- return printer.getSource();
- }
-
- private String classNameFromExpression(Expression e) {
- if (e instanceof NameExpr) {
- NameExpr nameExpr = (NameExpr) e;
- String name = nameExpr.getName();
- if (Arrays.binarySearch(CLASS_NAMES, name) > -1) {
- return name;
- }
- }
- return null;
- }
-
- protected void printModifiers(int modifiers) {
- }
-
- private void printMembers(List members,
- LocalSymbolTable arg) {
- for (BodyDeclaration member : members) {
- if ("Tokenizer".equals(javaClassName)
- && member instanceof MethodDeclaration
- && "stateLoop".equals(((MethodDeclaration) member).getName())) {
- reportTransitions = true;
- }
- member.accept(this, arg);
- reportTransitions = false;
- }
- }
-
- private void printTypeArgs(List args, LocalSymbolTable arg) {
- // if (args != null) {
- // printer.print("<");
- // for (Iterator i = args.iterator(); i.hasNext();) {
- // Type t = i.next();
- // t.accept(this, arg);
- // if (i.hasNext()) {
- // printer.print(", ");
- // }
- // }
- // printer.print(">");
- // }
- }
-
- private void printTypeParameters(List args,
- LocalSymbolTable arg) {
- // if (args != null) {
- // printer.print("<");
- // for (Iterator i = args.iterator(); i.hasNext();) {
- // TypeParameter t = i.next();
- // t.accept(this, arg);
- // if (i.hasNext()) {
- // printer.print(", ");
- // }
- // }
- // printer.print(">");
- // }
- }
-
- public void visit(Node n, LocalSymbolTable arg) {
- throw new IllegalStateException(n.getClass().getName());
- }
-
- public void visit(CompilationUnit n, LocalSymbolTable arg) {
- if (n.getTypes() != null) {
- for (Iterator i = n.getTypes().iterator(); i.hasNext();) {
- i.next().accept(this, arg);
- printer.printLn();
- if (i.hasNext()) {
- printer.printLn();
- }
- }
- }
- }
-
- public void visit(PackageDeclaration n, LocalSymbolTable arg) {
- throw new IllegalStateException(n.getClass().getName());
- }
-
- public void visit(NameExpr n, LocalSymbolTable arg) {
- if ("mappingLangToXmlLang".equals(n.getName())) {
- printer.print("0");
- } else if ("LANG_NS".equals(n.getName())) {
- printer.print("ALL_NO_NS");
- } else if ("LANG_PREFIX".equals(n.getName())) {
- printer.print("ALL_NO_PREFIX");
- } else if ("HTML_LOCAL".equals(n.getName())) {
- printer.print(cppTypes.localForLiteral("html"));
- } else if ("documentModeHandler".equals(n.getName())) {
- printer.print("this");
- } else if ("errorHandler".equals(n.getName())) {
- printer.print(cppTypes.errorHandler());
- } else if ("MOZ_FALLTHROUGH".equals(n.getName())) {
- printer.print("[[fallthrough]]");
- } else {
- printer.print(n.getName());
- }
- }
-
- public void visit(QualifiedNameExpr n, LocalSymbolTable arg) {
- n.getQualifier().accept(this, arg);
- printer.print(".");
- printer.print(n.getName());
- }
-
- public void visit(ImportDeclaration n, LocalSymbolTable arg) {
- throw new IllegalStateException(n.getClass().getName());
- }
-
- public void visit(ClassOrInterfaceDeclaration n, LocalSymbolTable arg) {
- javaClassName = n.getName();
- className = cppTypes.classPrefix() + javaClassName;
- definePrefix = makeDefinePrefix(className);
-
- startClassDeclaration();
-
- if (n.getMembers() != null) {
- printMembers(n.getMembers(), arg);
- }
-
- endClassDeclaration();
- }
-
- private String makeDefinePrefix(String name) {
- StringBuilder sb = new StringBuilder();
- boolean prevWasLowerCase = true;
- for (int i = 0; i < name.length(); i++) {
- char c = name.charAt(i);
- if (c >= 'a' && c <= 'z') {
- sb.append((char) (c - 0x20));
- prevWasLowerCase = true;
- } else if (c >= 'A' && c <= 'Z') {
- if (prevWasLowerCase) {
- sb.append('_');
- }
- sb.append(c);
- prevWasLowerCase = false;
- } else if (c >= '0' && c <= '9') {
- sb.append(c);
- prevWasLowerCase = false;
- }
- }
- sb.append('_');
- return sb.toString();
- }
-
- protected void endClassDeclaration() {
- printer.printLn("void");
- printer.print(className);
- printer.printLn("::initializeStatics()");
- printer.printLn("{");
- printer.print(staticInitializerPrinter.getSource());
- printer.printLn("}");
- printer.printLn();
-
- printer.printLn("void");
- printer.print(className);
- printer.printLn("::releaseStatics()");
- printer.printLn("{");
- printer.indent();
- for (String del : staticReleases) {
- printer.print(del);
- printer.printLn(";");
- }
- printer.unindent();
- printer.printLn("}");
- printer.printLn();
-
- if (cppTypes.hasSupplement(javaClassName)) {
- printer.printLn();
- printer.print("#include \"");
- printer.print(className);
- printer.printLn("CppSupplement.h\"");
- }
- }
-
- protected void startClassDeclaration() {
- printer.print("#define ");
- printer.print(className);
- printer.printLn("_cpp__");
- printer.printLn();
-
- String[] incs = cppTypes.boilerplateIncludes(javaClassName);
- for (int i = 0; i < incs.length; i++) {
- String inc = incs[i];
- printer.print("#include \"");
- printer.print(inc);
- printer.printLn(".h\"");
- }
-
- printer.printLn();
-
- for (int i = 0; i < Main.H_LIST.length; i++) {
- String klazz = Main.H_LIST[i];
- if (!klazz.equals(javaClassName)) {
- printer.print("#include \"");
- printer.print(cppTypes.classPrefix());
- printer.print(klazz);
- printer.printLn(".h\"");
- }
- }
-
- printer.printLn();
- printer.print("#include \"");
- printer.print(className);
- printer.printLn(".h\"");
- printer.printLn();
- }
-
- public void visit(EmptyTypeDeclaration n, LocalSymbolTable arg) {
- if (n.getJavaDoc() != null) {
- n.getJavaDoc().accept(this, arg);
- }
- printer.print(";");
- }
-
- public void visit(JavadocComment n, LocalSymbolTable arg) {
- printer.print("/**");
- printer.print(n.getContent());
- printer.printLn("*/");
- }
-
- public void visit(ClassOrInterfaceType n, LocalSymbolTable arg) {
- if (n.getScope() != null) {
- n.getScope().accept(this, arg);
- printer.print(".");
- throw new IllegalStateException("Can't translate nested classes.");
- }
- String name = n.getName();
- if ("String".equals(name)) {
- if (local()) {
- name = inField || inArray ? cppTypes.localType() : cppTypes.weakLocalType();
- } else if (prefix()) {
- name = cppTypes.prefixType();
- } else if (nsUri()) {
- name = cppTypes.nsUriType();
- } else if (literal()) {
- name = cppTypes.literalType();
- } else if (characterName()) {
- name = cppTypes.characterNameType();
- } else {
- name = cppTypes.stringType();
- }
- } else if ("T".equals(name) || "Object".equals(name)) {
- if (htmlCreator()) {
- name = cppTypes.htmlCreatorType();
- } else if (svgCreator()) {
- name = cppTypes.svgCreatorType();
- } else if (creator()) {
- name = cppTypes.creatorType();
- } else {
- name = cppTypes.nodeType();
- }
- } else if ("TokenHandler".equals(name)) {
- name = cppTypes.classPrefix() + "TreeBuilder*";
- } else if ("EncodingDeclarationHandler".equals(name)) {
- name = cppTypes.encodingDeclarationHandlerType();
- } else if ("Interner".equals(name)) {
- name = cppTypes.internerType();
- } else if ("TreeBuilderState".equals(name)) {
- name = cppTypes.treeBuilderStateType();
- } else if ("DocumentModeHandler".equals(name)) {
- name = cppTypes.documentModeHandlerType();
- } else if ("DocumentMode".equals(name)) {
- name = cppTypes.documentModeType();
- } else {
- name = cppTypes.classPrefix() + name + (suppressPointer ? "" : "*");
- }
- printer.print(name);
- printTypeArgs(n.getTypeArgs(), arg);
- }
-
- protected boolean inHeader() {
- return false;
- }
-
- public void visit(TypeParameter n, LocalSymbolTable arg) {
- printer.print(n.getName());
- if (n.getTypeBound() != null) {
- printer.print(" extends ");
- for (Iterator i = n.getTypeBound().iterator(); i.hasNext();) {
- ClassOrInterfaceType c = i.next();
- c.accept(this, arg);
- if (i.hasNext()) {
- printer.print(" & ");
- }
- }
- }
- }
-
- public void visit(PrimitiveType n, LocalSymbolTable arg) {
- switch (n.getType()) {
- case Boolean:
- printer.print(cppTypes.booleanType());
- break;
- case Byte:
- printer.print(cppTypes.byteType());
- break;
- case Char:
- printer.print(cppTypes.charType());
- break;
- case Double:
- throw new IllegalStateException("Unsupported primitive.");
- case Float:
- throw new IllegalStateException("Unsupported primitive.");
- case Int:
- if (unsigned()) {
- printer.print(cppTypes.unsignedIntType());
- } else {
- printer.print(cppTypes.intType());
- }
- break;
- case Long:
- throw new IllegalStateException("Unsupported primitive.");
- case Short:
- throw new IllegalStateException("Unsupported primitive.");
- }
- }
-
- public void visit(ReferenceType n, LocalSymbolTable arg) {
- if (isConst()) {
- printer.print("const ");
- }
- boolean wasInArray = inArray;
- if (n.getArrayCount() > 0) {
- inArray = true;
- }
- if (noLength()) {
- n.getType().accept(this, arg);
- for (int i = 0; i < n.getArrayCount(); i++) {
- if (!inPrimitiveNoLengthFieldDeclarator) {
- printer.print("*");
- }
- }
- } else {
- for (int i = 0; i < n.getArrayCount(); i++) {
- if (inStatic) {
- printer.print(cppTypes.staticArrayTemplate());
- } else {
- if (auto()) {
- printer.print(cppTypes.autoArrayTemplate());
- } else {
- printer.print(cppTypes.arrayTemplate());
- }
- }
- printer.print("<");
- }
- n.getType().accept(this, arg);
- for (int i = 0; i < n.getArrayCount(); i++) {
- printer.print(", ");
- printer.print(cppTypes.intType());
- printer.print(">");
- }
- }
- if (n.getArrayCount() > 0) {
- inArray = wasInArray;
- }
- }
-
- public void visit(WildcardType n, LocalSymbolTable arg) {
- printer.print("?");
- if (n.getExtends() != null) {
- printer.print(" extends ");
- n.getExtends().accept(this, arg);
- }
- if (n.getSuper() != null) {
- printer.print(" super ");
- n.getSuper().accept(this, arg);
- }
- }
-
- public void visit(FieldDeclaration n, LocalSymbolTable arg) {
- currentAnnotations = n.getAnnotations();
- fieldDeclaration(n, arg);
- currentAnnotations = null;
- }
-
- protected boolean isNonToCharArrayMethodCall(Expression exp) {
- if (exp instanceof MethodCallExpr) {
- MethodCallExpr mce = (MethodCallExpr) exp;
- return !"toCharArray".equals(mce.getName());
- } else {
- return false;
- }
- }
-
- protected void fieldDeclaration(FieldDeclaration n, LocalSymbolTable arg) {
- inField = true;
- tempPrinterHolder = printer;
- printer = staticInitializerPrinter;
- int modifiers = n.getModifiers();
- List variables = n.getVariables();
- VariableDeclarator declarator = variables.get(0);
- if (ModifierSet.isStatic(modifiers) && ModifierSet.isFinal(modifiers)
- && !(n.getType() instanceof PrimitiveType)
- && declarator.getInit() != null) {
- if (n.getType() instanceof ReferenceType) {
- ReferenceType rt = (ReferenceType) n.getType();
- currentArrayCount = rt.getArrayCount();
- if (currentArrayCount > 0) {
- if (currentArrayCount != 1) {
- throw new IllegalStateException(
- "Multidimensional arrays not supported. " + n);
- }
- if (noLength()) {
- if (rt.getType() instanceof PrimitiveType) {
- inPrimitiveNoLengthFieldDeclarator = true;
- printer = tempPrinterHolder;
- n.getType().accept(this, arg);
- printer.print(" ");
- printer.print(className);
- printer.print("::");
- declarator.getId().accept(this, arg);
-
- printer.print(" = ");
-
- declarator.getInit().accept(this, arg);
-
- printer.printLn(";");
- printer = staticInitializerPrinter;
- } else {
- printer = tempPrinterHolder;
- n.getType().accept(this, arg);
- printer.print(" ");
- printer.print(className);
- printer.print("::");
- declarator.getId().accept(this, arg);
-
- printer.printLn(" = 0;");
- printer = staticInitializerPrinter;
-
- staticReleases.add("delete[] "
- + declarator.getId().getName());
-
- ArrayInitializerExpr aie = (ArrayInitializerExpr) declarator.getInit();
-
- declarator.getId().accept(this, arg);
- printer.print(" = new ");
- // suppressPointer = true;
- rt.getType().accept(this, arg);
- // suppressPointer = false;
- printer.print("[");
- printer.print("" + aie.getValues().size());
- printer.printLn("];");
-
- printArrayInit(declarator.getId(), aie.getValues(),
- arg);
- }
- } else if ((rt.getType() instanceof PrimitiveType) || "String".equals(rt.getType().toString())) {
- printer = tempPrinterHolder;
- printer.print("static ");
- rt.getType().accept(this, arg);
- printer.print(" const ");
- declarator.getId().accept(this, arg);
- printer.print("_DATA[] = ");
- declarator.getInit().accept(this, arg);
- printer.printLn(";");
- printer.print(cppTypes.staticArrayTemplate());
- printer.print("<");
- suppressPointer = true;
- rt.getType().accept(this, arg);
- suppressPointer = false;
- printer.print(", ");
- printer.print(cppTypes.intType());
- printer.print("> ");
- printer.print(className);
- printer.print("::");
- declarator.getId().accept(this, arg);
- printer.print(" = { ");
- declarator.getId().accept(this, arg);
- printer.print("_DATA, ");
- printer.print(cppTypes.arrayLengthMacro());
- printer.print("(");
- declarator.getId().accept(this, arg);
- printer.printLn("_DATA) };");
- printer = staticInitializerPrinter;
- } else if (isNonToCharArrayMethodCall(declarator.getInit())) {
- staticReleases.add(declarator.getId().getName()
- + ".release()");
- declarator.getId().accept(this, arg);
- printer.print(" = ");
- if (declarator.getInit() instanceof ArrayInitializerExpr) {
-
- ArrayInitializerExpr aie = (ArrayInitializerExpr) declarator.getInit();
- printer.print(cppTypes.arrayTemplate());
- printer.print("<");
- suppressPointer = true;
- rt.getType().accept(this, arg);
- suppressPointer = false;
- printer.print(", ");
- printer.print(cppTypes.intType());
- printer.print(">::");
- printer.print(cppTypes.newArrayCreator());
- printer.print("(");
- printer.print("" + aie.getValues().size());
- printer.printLn(");");
- printArrayInit(declarator.getId(), aie.getValues(),
- arg);
- } else {
- declarator.getInit().accept(this, arg);
- printer.printLn(";");
- }
- }
- } else {
- if (ModifierSet.isStatic(modifiers)) {
- printer = tempPrinterHolder;
- n.getType().accept(this, arg);
- printer.print(" ");
- printer.print(className);
- printer.print("::");
- String clazzName = n.getType().toString();
- String field = declarator.getId().toString();
- if (symbolTable.isAttributeOrElementName(clazzName, field)) {
- if ("AttributeName".equals(clazzName)) {
- printer.print("ATTR_");
- } else if ("ElementName".equals(clazzName)) {
- printer.print("ELT_");
- }
- }
- declarator.getId().accept(this, arg);
- printer.print(" = ");
- printer.print(cppTypes.nullLiteral());
- printer.printLn(";");
- printer = staticInitializerPrinter;
- }
-
- if ("AttributeName".equals(n.getType().toString())) {
- printer.print("ATTR_");
- staticReleases.add("delete ATTR_"
- + declarator.getId().getName());
- } else if ("ElementName".equals(n.getType().toString())) {
- printer.print("ELT_");
- staticReleases.add("delete ELT_"
- + declarator.getId().getName());
- } else {
- staticReleases.add("delete "
- + declarator.getId().getName());
- }
- declarator.accept(this, arg);
- printer.printLn(";");
- }
- } else {
- throw new IllegalStateException(
- "Non-reference, non-primitive fields not supported.");
- }
- }
- currentArrayCount = 0;
- printer = tempPrinterHolder;
- inPrimitiveNoLengthFieldDeclarator = false;
- inField = false;
- }
-
- private void printArrayInit(VariableDeclaratorId variableDeclaratorId,
- List values, LocalSymbolTable arg) {
- for (int i = 0; i < values.size(); i++) {
- Expression exp = values.get(i);
- variableDeclaratorId.accept(this, arg);
- printer.print("[");
- printer.print("" + i);
- printer.print("] = ");
- if (exp instanceof NameExpr) {
- if ("AttributeName".equals(javaClassName)) {
- printer.print("ATTR_");
- } else if ("ElementName".equals(javaClassName)) {
- printer.print("ELT_");
- }
- }
- exp.accept(this, arg);
- printer.printLn(";");
- }
- }
-
- public void visit(VariableDeclarator n, LocalSymbolTable arg) {
- n.getId().accept(this, arg);
-
- if (n.getInit() != null) {
- printer.print(" = ");
- n.getInit().accept(this, arg);
- }
- }
-
- public void visit(VariableDeclaratorId n, LocalSymbolTable arg) {
- printer.print(n.getName());
- if (noLength()) {
- for (int i = 0; i < currentArrayCount; i++) {
- if (inPrimitiveNoLengthFieldDeclarator) {
- printer.print("[]");
- }
- }
- }
- for (int i = 0; i < n.getArrayCount(); i++) {
- printer.print("[]");
- }
- }
-
- public void visit(ArrayInitializerExpr n, LocalSymbolTable arg) {
- printer.print("{");
- if (n.getValues() != null) {
- printer.print(" ");
- for (Iterator i = n.getValues().iterator(); i.hasNext();) {
- Expression expr = i.next();
- expr.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- printer.print(" ");
- }
- printer.print("}");
- }
-
- public void visit(VoidType n, LocalSymbolTable arg) {
- printer.print("void");
- }
-
- public void visit(ArrayAccessExpr n, LocalSymbolTable arg) {
- n.getName().accept(this, arg);
- printer.print("[");
- n.getIndex().accept(this, arg);
- printer.print("]");
- }
-
- public void visit(ArrayCreationExpr n, LocalSymbolTable arg) {
- // printer.print("new ");
- // n.getType().accept(this, arg);
- // printTypeArgs(n.getTypeArgs(), arg);
-
- inArray = true;
- if (n.getDimensions() != null) {
- if (noLength()) {
- for (Expression dim : n.getDimensions()) {
- printer.print("new ");
- n.getType().accept(this, arg);
- printer.print("[");
- dim.accept(this, arg);
- printer.print("]");
- }
- } else {
- for (Expression dim : n.getDimensions()) {
- printer.print(cppTypes.arrayTemplate());
- printer.print("<");
- n.getType().accept(this, arg);
- printer.print(", ");
- printer.print(cppTypes.intType());
- printer.print(">::");
- printer.print(cppTypes.newArrayCreator());
- printer.print("(");
- dim.accept(this, arg);
- printer.print(")");
- }
- }
- if (n.getArrayCount() > 0) {
- throw new IllegalStateException(
- "Nested array allocation not supported. "
- + n.toString());
- }
- } else {
- throw new IllegalStateException(
- "Array initializer as part of array creation not supported. "
- + n.toString());
- }
- inArray = false;
- }
-
- public void visit(AssignExpr n, LocalSymbolTable arg) {
- if (inConstructorBody) {
- n.getTarget().accept(this, arg);
- printer.print("(");
- n.getValue().accept(this, arg);
- printer.print(")");
- } else {
- n.getTarget().accept(this, arg);
- printer.print(" ");
- switch (n.getOperator()) {
- case assign:
- printer.print("=");
- break;
- case and:
- printer.print("&=");
- break;
- case or:
- printer.print("|=");
- break;
- case xor:
- printer.print("^=");
- break;
- case plus:
- printer.print("+=");
- break;
- case minus:
- printer.print("-=");
- break;
- case rem:
- printer.print("%=");
- break;
- case slash:
- printer.print("/=");
- break;
- case star:
- printer.print("*=");
- break;
- case lShift:
- printer.print("<<=");
- break;
- case rSignedShift:
- printer.print(">>=");
- break;
- case rUnsignedShift:
- printer.print(">>>=");
- break;
- }
- printer.print(" ");
- n.getValue().accept(this, arg);
- }
- }
-
- public void visit(BinaryExpr n, LocalSymbolTable arg) {
- Expression right = n.getRight();
- switch (n.getOperator()) {
- case notEquals:
- if (right instanceof NullLiteralExpr) {
- printer.print("!!");
- n.getLeft().accept(this, arg);
- return;
- } else if (right instanceof IntegerLiteralExpr) {
- IntegerLiteralExpr ile = (IntegerLiteralExpr) right;
- if ("0".equals(ile.getValue())) {
- n.getLeft().accept(this, arg);
- return;
- }
- }
- case equals:
- if (right instanceof NullLiteralExpr) {
- printer.print("!");
- n.getLeft().accept(this, arg);
- return;
- } else if (right instanceof IntegerLiteralExpr) {
- IntegerLiteralExpr ile = (IntegerLiteralExpr) right;
- if ("0".equals(ile.getValue())) {
- printer.print("!");
- n.getLeft().accept(this, arg);
- return;
- }
- }
- default:
- // fall thru
- }
-
- n.getLeft().accept(this, arg);
- printer.print(" ");
- switch (n.getOperator()) {
- case or:
- printer.print("||");
- break;
- case and:
- printer.print("&&");
- break;
- case binOr:
- printer.print("|");
- break;
- case binAnd:
- printer.print("&");
- break;
- case xor:
- printer.print("^");
- break;
- case equals:
- printer.print("==");
- break;
- case notEquals:
- printer.print("!=");
- break;
- case less:
- printer.print("<");
- break;
- case greater:
- printer.print(">");
- break;
- case lessEquals:
- printer.print("<=");
- break;
- case greaterEquals:
- printer.print(">=");
- break;
- case lShift:
- printer.print("<<");
- break;
- case rSignedShift:
- printer.print(">>");
- break;
- case rUnsignedShift:
- printer.print(">>>");
- break;
- case plus:
- printer.print("+");
- break;
- case minus:
- printer.print("-");
- break;
- case times:
- printer.print("*");
- break;
- case divide:
- printer.print("/");
- break;
- case remainder:
- printer.print("%");
- break;
- }
- printer.print(" ");
- n.getRight().accept(this, arg);
- }
-
- public void visit(CastExpr n, LocalSymbolTable arg) {
- printer.print("(");
- n.getType().accept(this, arg);
- printer.print(") ");
- n.getExpr().accept(this, arg);
- }
-
- public void visit(ClassExpr n, LocalSymbolTable arg) {
- n.getType().accept(this, arg);
- printer.print(".class");
- }
-
- public void visit(ConditionalExpr n, LocalSymbolTable arg) {
- n.getCondition().accept(this, arg);
- printer.print(" ? ");
- n.getThenExpr().accept(this, arg);
- printer.print(" : ");
- n.getElseExpr().accept(this, arg);
- }
-
- public void visit(EnclosedExpr n, LocalSymbolTable arg) {
- printer.print("(");
- n.getInner().accept(this, arg);
- printer.print(")");
- }
-
- public void visit(FieldAccessExpr n, LocalSymbolTable arg) {
- Expression scope = n.getScope();
- String field = n.getField();
- if (inConstructorBody && (scope instanceof ThisExpr)) {
- printer.print(field);
- } else if ("length".equals(field) && !(scope instanceof ThisExpr)) {
- scope.accept(this, arg);
- printer.print(".length");
- } else if ("MAX_VALUE".equals(field)
- && "Integer".equals(scope.toString())) {
- printer.print(cppTypes.maxInteger());
- } else {
- String clazzName = classNameFromExpression(scope);
- if (clazzName == null) {
- if ("DocumentMode".equals(scope.toString())) {
- // printer.print(cppTypes.documentModeType());
- // printer.print(".");
- } else if ("creator".equals(scope.toString()) || "this.creator".equals(scope.toString())) {
- scope.accept(this, arg);
- printer.print(".");
- } else {
- scope.accept(this, arg);
- printer.print("->");
- }
- } else {
- printer.print(cppTypes.classPrefix());
- printer.print(clazzName);
- printer.print("::");
- if (symbolTable.isAttributeOrElementName(clazzName, field)) {
- if ("AttributeName".equals(clazzName)) {
- printer.print("ATTR_");
- } else if ("ElementName".equals(clazzName)) {
- printer.print("ELT_");
- }
- }
- }
- printer.print(field);
- }
- }
-
- public void visit(InstanceOfExpr n, LocalSymbolTable arg) {
- n.getExpr().accept(this, arg);
- printer.print(" instanceof ");
- n.getType().accept(this, arg);
- }
-
- public void visit(CharLiteralExpr n, LocalSymbolTable arg) {
- printCharLiteral(n.getValue());
- }
-
- private void printCharLiteral(String val) {
- if (val.length() != 1) {
- printer.print("'");
- printer.print(val);
- printer.print("'");
- return;
- }
- char c = val.charAt(0);
- switch (c) {
- case 0:
- printer.print("'\\0'");
- break;
- case '\n':
- printer.print("'\\n'");
- break;
- case '\t':
- printer.print("'\\t'");
- break;
- case 0xB:
- printer.print("'\\v'");
- break;
- case '\b':
- printer.print("'\\b'");
- break;
- case '\r':
- printer.print("'\\r'");
- break;
- case 0xC:
- printer.print("'\\f'");
- break;
- case 0x7:
- printer.print("'\\a'");
- break;
- case '\\':
- printer.print("'\\\\'");
- break;
- case '?':
- printer.print("'\\?'");
- break;
- case '\'':
- printer.print("'\\''");
- break;
- case '"':
- printer.print("'\\\"'");
- break;
- default:
- if (c >= 0x20 && c <= 0x7F) {
- printer.print("'" + c);
- printer.print("'");
- } else {
- printer.print("0x");
- printer.print(Integer.toHexString(c));
- }
- break;
- }
- }
-
- public void visit(DoubleLiteralExpr n, LocalSymbolTable arg) {
- printer.print(n.getValue());
- }
-
- public void visit(IntegerLiteralExpr n, LocalSymbolTable arg) {
- printer.print(n.getValue());
- }
-
- public void visit(LongLiteralExpr n, LocalSymbolTable arg) {
- printer.print(n.getValue());
- }
-
- public void visit(IntegerLiteralMinValueExpr n, LocalSymbolTable arg) {
- printer.print(n.getValue());
- }
-
- public void visit(LongLiteralMinValueExpr n, LocalSymbolTable arg) {
- printer.print(n.getValue());
- }
-
- public void visit(StringLiteralExpr n, LocalSymbolTable arg) {
- String val = n.getValue();
- if ("http://www.w3.org/1999/xhtml".equals(val)) {
- printer.print(cppTypes.xhtmlNamespaceLiteral());
- } else if ("http://www.w3.org/2000/svg".equals(val)) {
- printer.print(cppTypes.svgNamespaceLiteral());
- } else if ("http://www.w3.org/2000/xmlns/".equals(val)) {
- printer.print(cppTypes.xmlnsNamespaceLiteral());
- } else if ("http://www.w3.org/XML/1998/namespace".equals(val)) {
- printer.print(cppTypes.xmlNamespaceLiteral());
- } else if ("http://www.w3.org/1999/xlink".equals(val)) {
- printer.print(cppTypes.xlinkNamespaceLiteral());
- } else if ("http://www.w3.org/1998/Math/MathML".equals(val)) {
- printer.print(cppTypes.mathmlNamespaceLiteral());
- } else if ("".equals(val) && "AttributeName".equals(javaClassName)) {
- printer.print(cppTypes.noNamespaceLiteral());
- } else if (val.startsWith("-/") || val.startsWith("+//")
- || val.startsWith("http://") || val.startsWith("XSLT")) {
- printer.print(cppTypes.stringForLiteral(val));
- } else if (("hidden".equals(val) || "isindex".equals(val)
- || "text/html".equals(val)
- || "application/xhtml+xml".equals(val) || "content-type".equals(val))
- && "TreeBuilder".equals(javaClassName)) {
- printer.print(cppTypes.stringForLiteral(val));
- } else if ("isQuirky".equals(currentMethod) && "html".equals(val)) {
- printer.print(cppTypes.stringForLiteral(val));
- } else {
- printer.print(cppTypes.localForLiteral(val));
- }
- }
-
- public void visit(BooleanLiteralExpr n, LocalSymbolTable arg) {
- if (n.getValue()) {
- printer.print(cppTypes.trueLiteral());
- } else {
- printer.print(cppTypes.falseLiteral());
- }
- }
-
- public void visit(NullLiteralExpr n, LocalSymbolTable arg) {
- printer.print(cppTypes.nullLiteral());
- }
-
- public void visit(ThisExpr n, LocalSymbolTable arg) {
- if (n.getClassExpr() != null) {
- n.getClassExpr().accept(this, arg);
- printer.print(".");
- }
- printer.print("this");
- }
-
- public void visit(SuperExpr n, LocalSymbolTable arg) {
- if (n.getClassExpr() != null) {
- n.getClassExpr().accept(this, arg);
- printer.print(".");
- }
- printer.print("super");
- }
-
- public void visit(MethodCallExpr n, LocalSymbolTable arg) {
- if ("releaseArray".equals(n.getName())
- && "Portability".equals(n.getScope().toString())) {
- n.getArgs().get(0).accept(this, arg);
- printer.print(".release()");
- } else if ("releaseString".equals(n.getName())
- && "Portability".equals(n.getScope().toString())) {
- n.getArgs().get(0).accept(this, arg);
- printer.print(".Release()");
- } else if ("deleteArray".equals(n.getName())
- && "Portability".equals(n.getScope().toString())) {
- printer.print("delete[] ");
- n.getArgs().get(0).accept(this, arg);
- } else if ("delete".equals(n.getName())
- && "Portability".equals(n.getScope().toString())) {
- printer.print("delete ");
- n.getArgs().get(0).accept(this, arg);
- } else if (("retainElement".equals(n.getName()) || "releaseElement".equals(n.getName()))
- && "Portability".equals(n.getScope().toString())) {
- // ignore for now
- } else if ("transition".equals(n.getName())
- && n.getScope() == null) {
- visitTransition(n, arg);
- } else if ("arraycopy".equals(n.getName())
- && "System".equals(n.getScope().toString())) {
- printer.print(cppTypes.arrayCopy());
- printer.print("(");
- if (n.getArgs().get(0).toString().equals(
- n.getArgs().get(2).toString())) {
- n.getArgs().get(0).accept(this, arg);
- printer.print(", ");
- n.getArgs().get(1).accept(this, arg);
- printer.print(", ");
- n.getArgs().get(3).accept(this, arg);
- printer.print(", ");
- n.getArgs().get(4).accept(this, arg);
- } else if (n.getArgs().get(1).toString().equals("0")
- && n.getArgs().get(3).toString().equals("0")) {
- n.getArgs().get(0).accept(this, arg);
- printer.print(", ");
- n.getArgs().get(2).accept(this, arg);
- printer.print(", ");
- n.getArgs().get(4).accept(this, arg);
- } else {
- for (Iterator i = n.getArgs().iterator(); i.hasNext();) {
- Expression e = i.next();
- e.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
- printer.print(")");
- } else if ("binarySearch".equals(n.getName())
- && "Arrays".equals(n.getScope().toString())) {
- n.getArgs().get(0).accept(this, arg);
- printer.print(".binarySearch(");
- n.getArgs().get(1).accept(this, arg);
- printer.print(")");
- } else {
- Expression scope = n.getScope();
- if (scope != null) {
- if (scope instanceof StringLiteralExpr) {
- StringLiteralExpr strLit = (StringLiteralExpr) scope;
- String str = strLit.getValue();
- if (!"toCharArray".equals(n.getName())) {
- throw new IllegalStateException(
- "Unsupported method call on string literal: "
- + n.getName());
- }
- printer.print("{ ");
- for (int i = 0; i < str.length(); i++) {
- char c = str.charAt(i);
- if (i != 0) {
- printer.print(", ");
- }
- printCharLiteral("" + c);
- }
- printer.print(" }");
- return;
- } else {
- String clazzName = classNameFromExpression(scope);
- if (clazzName == null) {
- scope.accept(this, arg);
- if ("length".equals(n.getName())
- || "charAt".equals(n.getName())
- || "creator".equals(scope.toString())) {
- printer.print(".");
- } else {
- printer.print("->");
- }
- } else {
- printer.print(cppTypes.classPrefix());
- printer.print(clazzName);
- printer.print("::");
- }
- }
- }
- printTypeArgs(n.getTypeArgs(), arg);
- printer.print(n.getName());
- if ("stateLoop".equals(n.getName())
- && "Tokenizer".equals(javaClassName)
- && cppTypes.stateLoopPolicies().length > 0) {
- printer.print("<");
- printer.print(cppTypes.stateLoopPolicies()[stateLoopCallCount]);
- printer.print(">");
- stateLoopCallCount++;
- }
- printer.print("(");
- if (n.getArgs() != null) {
- for (Iterator i = n.getArgs().iterator(); i.hasNext();) {
- Expression e = i.next();
- e.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
- printer.print(")");
- }
- }
-
- public void visit(ObjectCreationExpr n, LocalSymbolTable arg) {
- if (n.getScope() != null) {
- n.getScope().accept(this, arg);
- printer.print(".");
- }
-
- printer.print("new ");
-
- suppressPointer = true;
- printTypeArgs(n.getTypeArgs(), arg);
- n.getType().accept(this, arg);
- suppressPointer = false;
-
- if ("AttributeName".equals(n.getType().getName())) {
- List args = n.getArgs();
- while (args != null && args.size() > 3) {
- args.remove(3);
- }
- }
-
- printer.print("(");
- if (n.getArgs() != null) {
- for (Iterator i = n.getArgs().iterator(); i.hasNext();) {
- Expression e = i.next();
- e.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
- printer.print(")");
-
- if (n.getAnonymousClassBody() != null) {
- printer.printLn(" {");
- printer.indent();
- printMembers(n.getAnonymousClassBody(), arg);
- printer.unindent();
- printer.print("}");
- }
- }
-
- public void visit(UnaryExpr n, LocalSymbolTable arg) {
- switch (n.getOperator()) {
- case positive:
- printer.print("+");
- break;
- case negative:
- printer.print("-");
- break;
- case inverse:
- printer.print("~");
- break;
- case not:
- printer.print("!");
- break;
- case preIncrement:
- printer.print("++");
- break;
- case preDecrement:
- printer.print("--");
- break;
- }
-
- n.getExpr().accept(this, arg);
-
- switch (n.getOperator()) {
- case posIncrement:
- printer.print("++");
- break;
- case posDecrement:
- printer.print("--");
- break;
- }
- }
-
- public void visit(ConstructorDeclaration n, LocalSymbolTable arg) {
- if ("TreeBuilder".equals(javaClassName)) {
- return;
- }
-
- arg = new LocalSymbolTable(javaClassName, symbolTable);
-
- // if (n.getJavaDoc() != null) {
- // n.getJavaDoc().accept(this, arg);
- // }
- currentAnnotations = n.getAnnotations();
-
- printModifiers(n.getModifiers());
-
- printMethodNamespace();
- printConstructorExplicit(n.getParameters());
- printer.print(className);
- currentAnnotations = null;
-
- printer.print("(");
- if (n.getParameters() != null) {
- for (Iterator i = n.getParameters().iterator(); i.hasNext();) {
- Parameter p = i.next();
- p.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
- printer.print(")");
-
- printConstructorBody(n.getBlock(), arg);
- }
-
- protected void printConstructorExplicit(List params) {
- }
-
- protected void printConstructorBody(BlockStmt block, LocalSymbolTable arg) {
- inConstructorBody = true;
- List statements = block.getStmts();
- List nonAssigns = new LinkedList();
- int i = 0;
- boolean needOutdent = false;
- for (Statement statement : statements) {
- if (statement instanceof ExpressionStmt
- && ((ExpressionStmt) statement).getExpression() instanceof AssignExpr) {
- printer.printLn();
- if (i == 0) {
- // : firstMember(arg)
- printer.indent();
- printer.print(": ");
- needOutdent = true;
- } else {
- // , secondMember(arg)
- printer.print(", ");
- }
- statement.accept(this, arg);
- i++;
- } else {
- nonAssigns.add(statement);
- }
- }
- if (needOutdent) {
- printer.unindent();
- }
- inConstructorBody = false;
- printer.printLn();
- printer.printLn("{");
- printer.indent();
- String boilerplate = cppTypes.constructorBoilerplate(className);
- if (boilerplate != null) {
- printer.printLn(boilerplate);
- }
- for (Statement statement : nonAssigns) {
- statement.accept(this, arg);
- printer.printLn();
- }
- printer.unindent();
- printer.printLn("}");
- printer.printLn();
- }
-
- public void visit(MethodDeclaration n, LocalSymbolTable arg) {
- arg = new LocalSymbolTable(javaClassName, symbolTable);
- if (isPrintableMethod(n.getModifiers())
- && !(n.getName().equals("endCoalescing") || n.getName().equals(
- "startCoalescing"))) {
- printMethodDeclaration(n, arg);
- }
- }
-
- private boolean isPrintableMethod(int modifiers) {
- return !(ModifierSet.isAbstract(modifiers) || (ModifierSet.isProtected(modifiers) && !(ModifierSet.isFinal(modifiers) || "Tokenizer".equals(javaClassName))));
- }
-
- protected void printMethodDeclaration(MethodDeclaration n,
- LocalSymbolTable arg) {
- if (n.getName().startsWith("fatal") || n.getName().startsWith("err")
- || n.getName().startsWith("warn")
- || n.getName().startsWith("maybeErr")
- || n.getName().startsWith("maybeWarn")
- || n.getName().startsWith("note")
- || "releaseArray".equals(n.getName())
- || "releaseString".equals(n.getName())
- || "deleteArray".equals(n.getName())
- || "delete".equals(n.getName())) {
- return;
- }
-
- currentMethod = n.getName();
-
- destructor = "destructor".equals(currentMethod);
-
- // if (n.getJavaDoc() != null) {
- // n.getJavaDoc().accept(this, arg);
- // }
- currentAnnotations = n.getAnnotations();
- boolean isInline = inline();
- if (isInline && !inHeader()) {
- return;
- }
-
- if (destructor) {
- printModifiers(ModifierSet.PUBLIC);
- } else {
- printModifiers(n.getModifiers());
- }
-
- if ("stateLoop".equals(currentMethod)
- && "Tokenizer".equals(javaClassName)
- && cppTypes.stateLoopPolicies().length > 0) {
- printer.print("template");
- if (inHeader()) {
- printer.print(" ");
- } else {
- printer.printLn();
- }
- }
-
- printTypeParameters(n.getTypeParameters(), arg);
- if (n.getTypeParameters() != null) {
- printer.print(" ");
- }
- if (!destructor) {
- n.getType().accept(this, arg);
- printer.print(" ");
- }
- printMethodNamespace();
- if (destructor) {
- printer.print("~");
- printer.print(className);
- } else {
- printer.print(n.getName());
- }
-
- printer.print("(");
- if (n.getParameters() != null) {
- for (Iterator i = n.getParameters().iterator(); i.hasNext();) {
- Parameter p = i.next();
- p.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
- printer.print(")");
-
- for (int i = 0; i < n.getArrayCount(); i++) {
- printer.print("[]");
- }
-
- if (override() && inHeader()) {
- printer.print(" override");
- }
-
- currentAnnotations = null;
-
- if (inHeader() == isInline) {
- printMethodBody(n.getBody(), arg);
- } else {
- printer.printLn(";");
- }
- }
-
- private void printMethodBody(BlockStmt n, LocalSymbolTable arg) {
- if (n == null) {
- printer.print(";");
- } else {
- printer.printLn();
- printer.printLn("{");
- printer.indent();
- if (destructor) {
- String boilerplate = cppTypes.destructorBoilerplate(className);
- if (boilerplate != null) {
- printer.printLn(boilerplate);
- }
- }
- if (n.getStmts() != null) {
- for (Statement s : n.getStmts()) {
- s.accept(this, arg);
- printer.printLn();
- }
- }
- printer.unindent();
- printer.print("}");
- }
- printer.printLn();
- printer.printLn();
- }
-
- protected void printMethodNamespace() {
- printer.printLn();
- printer.print(className);
- printer.print("::");
- }
-
- public void visit(Parameter n, LocalSymbolTable arg) {
- currentAnnotations = n.getAnnotations();
-
- arg.putLocalType(n.getId().getName(), convertType(n.getType(),
- n.getModifiers()));
-
- n.getType().accept(this, arg);
- if (n.isVarArgs()) {
- printer.print("...");
- }
- printer.print(" ");
- n.getId().accept(this, arg);
- currentAnnotations = null;
- }
-
- public void visit(ExplicitConstructorInvocationStmt n, LocalSymbolTable arg) {
- if (n.isThis()) {
- printTypeArgs(n.getTypeArgs(), arg);
- printer.print("this");
- } else {
- if (n.getExpr() != null) {
- n.getExpr().accept(this, arg);
- printer.print(".");
- }
- printTypeArgs(n.getTypeArgs(), arg);
- printer.print("super");
- }
- printer.print("(");
- if (n.getArgs() != null) {
- for (Iterator i = n.getArgs().iterator(); i.hasNext();) {
- Expression e = i.next();
- e.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
- printer.print(");");
- }
-
- public void visit(VariableDeclarationExpr n, LocalSymbolTable arg) {
- currentAnnotations = n.getAnnotations();
-
- arg.putLocalType(n.getVars().get(0).toString(), convertType(
- n.getType(), n.getModifiers()));
-
- n.getType().accept(this, arg);
- printer.print(" ");
-
- for (Iterator i = n.getVars().iterator(); i.hasNext();) {
- VariableDeclarator v = i.next();
- v.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- currentAnnotations = null;
- }
-
- public void visit(TypeDeclarationStmt n, LocalSymbolTable arg) {
- n.getTypeDeclaration().accept(this, arg);
- }
-
- public void visit(AssertStmt n, LocalSymbolTable arg) {
- String message = null;
- Expression msg = n.getMessage();
- boolean hasCheck = true;
- if (msg != null) {
- if (msg instanceof StringLiteralExpr) {
- StringLiteralExpr sle = (StringLiteralExpr) msg;
- message = sle.getValue();
- } else {
- throw new RuntimeException("Bad assertion message.");
- }
- }
- String macro = cppTypes.assertionMacro();
- if (message != null && message.startsWith("RELEASE: ")) {
- message = message.substring("RELEASE: ".length());
- macro = cppTypes.releaseAssertionMacro();
- Expression check = n.getCheck();
- if (check instanceof BooleanLiteralExpr) {
- BooleanLiteralExpr expr = (BooleanLiteralExpr) check;
- if (!expr.getValue()) {
- hasCheck = false;
- macro = cppTypes.crashMacro();
- }
- }
- }
- if (macro != null) {
- printer.print(macro);
- printer.print("(");
- if (hasCheck) {
- n.getCheck().accept(this, arg);
- }
- if (message != null) {
- if (hasCheck) {
- printer.print(", ");
- }
- printer.print("\"");
- for (int i = 0; i < message.length(); i++) {
- char c = message.charAt(i);
- if (c == '"') {
- printer.print("\"");
- } else if (c >= ' ' && c <= '~') {
- printer.print("" + c);
- } else {
- throw new RuntimeException("Bad assertion message string.");
- }
- }
- printer.print("\"");
- }
- printer.print(");");
- }
- }
-
- public void visit(BlockStmt n, LocalSymbolTable arg) {
- printer.printLn("{");
- if (n.getStmts() != null) {
- printer.indent();
- for (Statement s : n.getStmts()) {
- s.accept(this, arg);
- printer.printLn();
- }
- printer.unindent();
- }
- printer.print("}");
-
- }
-
- public void visit(LabeledStmt n, LocalSymbolTable arg) {
- // Only conditionless for loops are needed and supported
- // Not implementing general Java continue semantics in order
- // to keep the generated C++ more readable.
- Statement stmt = n.getStmt();
- if (stmt instanceof ForStmt) {
- ForStmt forLoop = (ForStmt) stmt;
- if (!(forLoop.getInit() == null && forLoop.getCompare() == null && forLoop.getUpdate() == null)) {
- forLoopsWithCondition.add(n.getLabel());
- }
- } else {
- throw new IllegalStateException(
- "Only for loop supported as labeled statement. Line: "
- + n.getBeginLine());
- }
- String label = n.getLabel();
- if (labels.contains(label)) {
- printer.unindent();
- printer.print(label);
- printer.indent();
- printer.printLn(":");
- }
- stmt.accept(this, arg);
- printer.printLn();
- label += "_end";
- if (labels.contains(label)) {
- printer.unindent();
- printer.print(label);
- printer.indent();
- printer.print(":;");
- }
- }
-
- public void visit(EmptyStmt n, LocalSymbolTable arg) {
- printer.print(";");
- }
-
- public void visit(ExpressionStmt n, LocalSymbolTable arg) {
- Expression e = n.getExpression();
- if (isCompletedCharacterReference(e)) {
- printer.print(cppTypes.completedCharacterReference());
- printer.print(";");
- return;
- }
- boolean needsCondition = isTokenizerErrorReportingExpression(e);
- if (!needsCondition && isDroppedExpression(e)) {
- return;
- }
- if (needsCondition) {
- printer.print("if (");
- printer.print(cppTypes.tokenizerErrorCondition());
- printer.printLn(") {");
- printer.indent();
- }
- e.accept(this, arg);
- if (!inConstructorBody) {
- printer.print(";");
- }
- if (needsCondition) {
- printer.printLn();
- printer.unindent();
- printer.print("}");
- }
- }
-
- private void visitTransition(MethodCallExpr call, LocalSymbolTable arg) {
- List args = call.getArgs();
- if (reportTransitions) {
- printer.print(cppTypes.transition());
- printer.print("(");
- printer.print(cppTypes.firstTransitionArg());
- printer.print(", ");
- args.get(1).accept(this, arg);
- printer.print(", ");
- args.get(2).accept(this, arg);
- printer.print(", ");
- args.get(3).accept(this, arg);
- printer.print(")");
- } else {
- args.get(1).accept(this, arg);
- }
- }
-
- private boolean isTokenizerErrorReportingExpression(Expression e) {
- if (!reportTransitions) {
- return false;
- }
- if (e instanceof MethodCallExpr) {
- MethodCallExpr methodCallExpr = (MethodCallExpr) e;
- String name = methodCallExpr.getName();
- if (supportErrorReporting && !name.startsWith("errHtml4")
- && ("stateLoop".equals(currentMethod))
- && (name.startsWith("err") || name.startsWith("maybeErr"))) {
- return true;
- }
- }
- return false;
- }
-
- private boolean isCompletedCharacterReference(Expression e) {
- if (!reportTransitions) {
- return false;
- }
- if (e instanceof MethodCallExpr) {
- MethodCallExpr methodCallExpr = (MethodCallExpr) e;
- String name = methodCallExpr.getName();
- if (name.equals("completedNamedCharacterReference")) {
- return true;
- }
- }
- return false;
- }
-
- private boolean isDroppedExpression(Expression e) {
- if (e instanceof MethodCallExpr) {
- MethodCallExpr methodCallExpr = (MethodCallExpr) e;
- String name = methodCallExpr.getName();
- if (name.startsWith("fatal") || name.startsWith("note")
- || name.startsWith("errHtml4") || name.startsWith("warn")
- || name.startsWith("maybeWarn")) {
- return true;
- }
- if (supportErrorReporting
- && ("stateLoop".equals(currentMethod) && !reportTransitions)
- && (name.startsWith("err") || name.startsWith("maybeErr"))) {
- return true;
- }
- if (name.equals("completedNamedCharacterReference")
- && !reportTransitions) {
- return true;
- }
- }
- return false;
- }
-
- public void visit(SwitchStmt n, LocalSymbolTable arg) {
- printer.print("switch (");
- n.getSelector().accept(this, arg);
- printer.printLn(") {");
- if (n.getEntries() != null) {
- printer.indent();
- for (SwitchEntryStmt e : n.getEntries()) {
- e.accept(this, arg);
- }
- printer.unindent();
- }
- printer.print("}");
-
- }
-
- public void visit(SwitchEntryStmt n, LocalSymbolTable arg) {
- if (n.getLabel() != null) {
- boolean isMenuitem = n.getLabel().toString().equals("MENUITEM");
- if (isMenuitem) {
- printer.printWithoutIndent("#ifdef ENABLE_VOID_MENUITEM\n");
- }
- printer.print("case ");
- n.getLabel().accept(this, arg);
- printer.print(":");
- if (isMenuitem) {
- printer.printWithoutIndent("\n#endif");
- }
- } else {
- printer.print("default:");
- }
- if (isNoStatement(n.getStmts())) {
- printer.printLn();
- printer.indent();
- if (n.getLabel() == null) {
- printer.printLn("; // fall through");
- }
- printer.unindent();
- } else {
- printer.printLn(" {");
- printer.indent();
- for (Statement s : n.getStmts()) {
- s.accept(this, arg);
- printer.printLn();
- }
- printer.unindent();
- printer.printLn("}");
- }
- }
-
- private boolean isNoStatement(List stmts) {
- if (stmts == null) {
- return true;
- }
- for (Statement statement : stmts) {
- if (!isDroppableStatement(statement)) {
- return false;
- }
- }
- return true;
- }
-
- private boolean isDroppableStatement(Statement statement) {
- if (statement instanceof AssertStmt) {
- return true;
- } else if (statement instanceof ExpressionStmt) {
- ExpressionStmt es = (ExpressionStmt) statement;
- if (isDroppedExpression(es.getExpression())) {
- return true;
- }
- }
- return false;
- }
-
- public void visit(BreakStmt n, LocalSymbolTable arg) {
- if (n.getId() != null) {
- printer.print(cppTypes.breakMacro());
- printer.print("(");
- printer.print(n.getId());
- printer.print(")");
- } else {
- printer.print("break");
- }
- printer.print(";");
- }
-
- public void visit(ReturnStmt n, LocalSymbolTable arg) {
- printer.print("return");
- if (n.getExpr() != null) {
- printer.print(" ");
- n.getExpr().accept(this, arg);
- }
- printer.print(";");
- }
-
- public void visit(EnumDeclaration n, LocalSymbolTable arg) {
- if (n.getJavaDoc() != null) {
- n.getJavaDoc().accept(this, arg);
- }
- currentAnnotations = n.getAnnotations();
- // if (annotations != null) {
- // for (AnnotationExpr a : annotations) {
- // a.accept(this, arg);
- // printer.printLn();
- // }
- // }
- printModifiers(n.getModifiers());
-
- printer.print("enum ");
- printer.print(n.getName());
-
- currentAnnotations = null;
-
- if (n.getImplements() != null) {
- printer.print(" implements ");
- for (Iterator i = n.getImplements().iterator(); i.hasNext();) {
- ClassOrInterfaceType c = i.next();
- c.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
-
- printer.printLn(" {");
- printer.indent();
- if (n.getEntries() != null) {
- printer.printLn();
- for (Iterator i = n.getEntries().iterator(); i.hasNext();) {
- EnumConstantDeclaration e = i.next();
- e.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
- if (n.getMembers() != null) {
- printer.printLn(";");
- printMembers(n.getMembers(), arg);
- } else {
- if (n.getEntries() != null) {
- printer.printLn();
- }
- }
- printer.unindent();
- printer.print("}");
- }
-
- public void visit(EnumConstantDeclaration n, LocalSymbolTable arg) {
- if (n.getJavaDoc() != null) {
- n.getJavaDoc().accept(this, arg);
- }
- currentAnnotations = n.getAnnotations();
- // if (annotations != null) {
- // for (AnnotationExpr a : annotations) {
- // a.accept(this, arg);
- // printer.printLn();
- // }
- // }
- printer.print(n.getName());
-
- currentAnnotations = null;
-
- if (n.getArgs() != null) {
- printer.print("(");
- for (Iterator i = n.getArgs().iterator(); i.hasNext();) {
- Expression e = i.next();
- e.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- printer.print(")");
- }
-
- if (n.getClassBody() != null) {
- printer.printLn(" {");
- printer.indent();
- printMembers(n.getClassBody(), arg);
- printer.unindent();
- printer.printLn("}");
- }
- }
-
- public void visit(EmptyMemberDeclaration n, LocalSymbolTable arg) {
- if (n.getJavaDoc() != null) {
- n.getJavaDoc().accept(this, arg);
- }
- printer.print(";");
- }
-
- public void visit(InitializerDeclaration n, LocalSymbolTable arg) {
- if (n.getJavaDoc() != null) {
- n.getJavaDoc().accept(this, arg);
- }
- if (n.isStatic()) {
- printer.print("static ");
- }
- n.getBlock().accept(this, arg);
- }
-
- public void visit(IfStmt n, LocalSymbolTable arg) {
- if (TranslatorUtils.isDocumentModeHandlerNullCheck(n.getCondition())) {
- Statement then = n.getThenStmt();
- if (then instanceof BlockStmt) {
- BlockStmt block = (BlockStmt) then;
- List statements = block.getStmts();
- if (statements != null && statements.size() == 1) {
- statements.get(0).accept(this, arg);
- } else {
- then.accept(this, arg);
- }
- } else {
- then.accept(this, arg);
- }
- } else if (!TranslatorUtils.isErrorHandlerIf(n.getCondition(), supportErrorReporting)) {
- if (TranslatorUtils.isErrorOnlyBlock(n.getThenStmt(), supportErrorReporting)) {
- if (n.getElseStmt() != null
- && !TranslatorUtils.isErrorOnlyBlock(n.getElseStmt(), supportErrorReporting)) {
- printer.print("if (");
- if (n.getCondition() instanceof BinaryExpr) {
- BinaryExpr binExpr = (BinaryExpr) n.getCondition();
- switch (binExpr.getOperator()) {
- case equals:
- binExpr.getLeft().accept(this, arg);
- printer.print(" != ");
- binExpr.getRight().accept(this, arg);
- break;
- case notEquals:
- binExpr.getLeft().accept(this, arg);
- printer.print(" == ");
- binExpr.getRight().accept(this, arg);
- break;
- default:
- printer.print("!(");
- formatCondition(n.getCondition(), arg);
- printer.print(")");
- break;
- }
- } else {
- printer.print("!(");
- formatCondition(n.getCondition(), arg);
- printer.print(")");
- }
- printer.print(") ");
- n.getElseStmt().accept(this, arg);
- }
- } else {
- boolean unlikely = (currentMethod != null)
- && (Arrays.binarySearch(
- METHODS_WITH_UNLIKELY_CONDITIONS,
- currentMethod) >= 0);
- printer.print("if (");
- if (unlikely) {
- printer.print(cppTypes.unlikely());
- printer.print("(");
- }
- formatCondition(n.getCondition(), arg);
- if (unlikely) {
- printer.print(")");
- }
- printer.print(") ");
- n.getThenStmt().accept(this, arg);
- if (n.getElseStmt() != null
- && !TranslatorUtils.isErrorOnlyBlock(n.getElseStmt(), supportErrorReporting)) {
- printer.print(" else ");
- n.getElseStmt().accept(this, arg);
- }
- }
- }
- }
-
- private void formatCondition(Expression expr, LocalSymbolTable arg) {
- if (expr instanceof BinaryExpr) {
- BinaryExpr binExpr = (BinaryExpr) expr;
- switch (binExpr.getOperator()) {
- case notEquals:
- if (binExpr.getRight() instanceof NullLiteralExpr) {
- binExpr.getLeft().accept(this, arg);
- return;
- }
- break;
- default:
- break;
- }
- }
- expr.accept(this, arg);
- }
-
-
- public void visit(WhileStmt n, LocalSymbolTable arg) {
- printer.print("while (");
- n.getCondition().accept(this, arg);
- printer.print(") ");
- n.getBody().accept(this, arg);
- }
-
- public void visit(ContinueStmt n, LocalSymbolTable arg) {
- // Not supporting the general Java continue semantics.
- // Instead, making the generated code more readable for the
- // case at hand.
- if (n.getId() != null) {
- printer.print(cppTypes.continueMacro());
- printer.print("(");
- printer.print(n.getId());
- printer.print(")");
- if (forLoopsWithCondition.contains(n.getId())) {
- throw new IllegalStateException(
- "Continue attempted with a loop that has a condition. "
- + className + " " + n.getId());
- }
- } else {
- printer.print("continue");
- }
- printer.print(";");
- }
-
- public void visit(DoStmt n, LocalSymbolTable arg) {
- printer.print("do ");
- n.getBody().accept(this, arg);
- printer.print(" while (");
- n.getCondition().accept(this, arg);
- printer.print(");");
- }
-
- public void visit(ForeachStmt n, LocalSymbolTable arg) {
- printer.print("for (");
- n.getVariable().accept(this, arg);
- printer.print(" : ");
- n.getIterable().accept(this, arg);
- printer.print(") ");
- n.getBody().accept(this, arg);
- }
-
- public void visit(ForStmt n, LocalSymbolTable arg) {
- printer.print("for (");
- if (n.getInit() != null) {
- for (Iterator i = n.getInit().iterator(); i.hasNext();) {
- Expression e = i.next();
- e.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
- printer.print(";");
- if (n.getCompare() != null) {
- printer.print(" ");
- n.getCompare().accept(this, arg);
- }
- printer.print(";");
- if (n.getUpdate() != null) {
- printer.print(" ");
- for (Iterator i = n.getUpdate().iterator(); i.hasNext();) {
- Expression e = i.next();
- e.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
- printer.print(") ");
- n.getBody().accept(this, arg);
- }
-
- public void visit(ThrowStmt n, LocalSymbolTable arg) {
- printer.print("throw ");
- n.getExpr().accept(this, arg);
- printer.print(";");
- }
-
- public void visit(SynchronizedStmt n, LocalSymbolTable arg) {
- printer.print("synchronized (");
- n.getExpr().accept(this, arg);
- printer.print(") ");
- n.getBlock().accept(this, arg);
- }
-
- public void visit(TryStmt n, LocalSymbolTable arg) {
- printer.print("try ");
- n.getTryBlock().accept(this, arg);
- if (n.getCatchs() != null) {
- for (CatchClause c : n.getCatchs()) {
- c.accept(this, arg);
- }
- }
- if (n.getFinallyBlock() != null) {
- printer.print(" finally ");
- n.getFinallyBlock().accept(this, arg);
- }
- }
-
- public void visit(CatchClause n, LocalSymbolTable arg) {
- printer.print(" catch (");
- n.getExcept().accept(this, arg);
- printer.print(") ");
- n.getCatchBlock().accept(this, arg);
-
- }
-
- public void visit(AnnotationDeclaration n, LocalSymbolTable arg) {
- if (n.getJavaDoc() != null) {
- n.getJavaDoc().accept(this, arg);
- }
- currentAnnotations = n.getAnnotations();
- // if (annotations != null) {
- // for (AnnotationExpr a : annotations) {
- // a.accept(this, arg);
- // printer.printLn();
- // }
- // }
- printModifiers(n.getModifiers());
-
- printer.print("@interface ");
- printer.print(n.getName());
- currentAnnotations = null;
- printer.printLn(" {");
- printer.indent();
- if (n.getMembers() != null) {
- printMembers(n.getMembers(), arg);
- }
- printer.unindent();
- printer.print("}");
- }
-
- public void visit(AnnotationMemberDeclaration n, LocalSymbolTable arg) {
- if (n.getJavaDoc() != null) {
- n.getJavaDoc().accept(this, arg);
- }
- currentAnnotations = n.getAnnotations();
- // if (annotations != null) {
- // for (AnnotationExpr a : annotations) {
- // a.accept(this, arg);
- // printer.printLn();
- // }
- // }
- printModifiers(n.getModifiers());
-
- n.getType().accept(this, arg);
- printer.print(" ");
- printer.print(n.getName());
- currentAnnotations = null;
- printer.print("()");
- if (n.getDefaultValue() != null) {
- printer.print(" default ");
- n.getDefaultValue().accept(this, arg);
- }
- printer.print(";");
- }
-
- public void visit(MarkerAnnotationExpr n, LocalSymbolTable arg) {
- printer.print("@");
- n.getName().accept(this, arg);
- }
-
- public void visit(SingleMemberAnnotationExpr n, LocalSymbolTable arg) {
- printer.print("@");
- n.getName().accept(this, arg);
- printer.print("(");
- n.getMemberValue().accept(this, arg);
- printer.print(")");
- }
-
- public void visit(NormalAnnotationExpr n, LocalSymbolTable arg) {
- printer.print("@");
- n.getName().accept(this, arg);
- printer.print("(");
- if (n.getPairs() != null) {
- for (Iterator i = n.getPairs().iterator(); i.hasNext();) {
- MemberValuePair m = i.next();
- m.accept(this, arg);
- if (i.hasNext()) {
- printer.print(", ");
- }
- }
- }
- printer.print(")");
- }
-
- public void visit(MemberValuePair n, LocalSymbolTable arg) {
- printer.print(n.getName());
- printer.print(" = ");
- n.getValue().accept(this, arg);
- }
-
- public void visit(LineComment n, LocalSymbolTable arg) {
- printer.print("//");
- printer.printLn(n.getContent());
- }
-
- public void visit(BlockComment n, LocalSymbolTable arg) {
- printer.print("/*");
- printer.print(n.getContent());
- printer.printLn("*/");
- }
-
- public void setLabels(Set labels) {
- this.labels = labels;
- }
-
-}
diff --git a/translator-src/nu/validator/htmlparser/cpptranslate/GkAtomParser.java b/translator-src/nu/validator/htmlparser/cpptranslate/GkAtomParser.java
deleted file mode 100644
index 475a793b..00000000
--- a/translator-src/nu/validator/htmlparser/cpptranslate/GkAtomParser.java
+++ /dev/null
@@ -1,72 +0,0 @@
-/* ***** BEGIN LICENSE BLOCK *****
- * Version: MPL 1.1/GPL 2.0/LGPL 2.1
- *
- * The contents of this file are subject to the Mozilla Public License Version
- * 1.1 (the "License"); you may not use this file except in compliance with
- * the License. You may obtain a copy of the License at
- * http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS" basis,
- * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
- * for the specific language governing rights and limitations under the
- * License.
- *
- * The Original Code is HTML Parser C++ Translator code.
- *
- * The Initial Developer of the Original Code is
- * Mozilla Foundation.
- * Portions created by the Initial Developer are Copyright (C) 2008
- * the Initial Developer. All Rights Reserved.
- *
- * Contributor(s):
- * Henri Sivonen
- *
- * Alternatively, the contents of this file may be used under the terms of
- * either the GNU General Public License Version 2 or later (the "GPL"), or
- * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
- * in which case the provisions of the GPL or the LGPL are applicable instead
- * of those above. If you wish to allow use of your version of this file only
- * under the terms of either the GPL or the LGPL, and not to allow others to
- * use your version of this file under the terms of the MPL, indicate your
- * decision by deleting the provisions above and replace them with the notice
- * and other provisions required by the GPL or the LGPL. If you do not delete
- * the provisions above, a recipient may use your version of this file under
- * the terms of any one of the MPL, the GPL or the LGPL.
- *
- * ***** END LICENSE BLOCK ***** */
-
-package nu.validator.htmlparser.cpptranslate;
-
-import java.io.BufferedReader;
-import java.io.IOException;
-import java.io.Reader;
-import java.util.HashMap;
-import java.util.Map;
-import java.util.regex.Matcher;
-import java.util.regex.Pattern;
-
-public class GkAtomParser {
-
- /* Please note we aren't looking for the following Atom definitions:
- PseudoElementAtom or NonInheritingAnonBoxAtom or InheritingAnonBoxAtom */
- private static final Pattern ATOM = Pattern.compile("^Atom\\(\"([^,]+)\",\\s*\"([^\"]*)\"\\).*$");
-
- private final BufferedReader reader;
-
- public GkAtomParser(Reader reader) {
- this.reader = new BufferedReader(reader);
- }
-
- public Map parse() throws IOException {
- Map map = new HashMap();
- String line;
- while((line = reader.readLine()) != null) {
- Matcher m = ATOM.matcher(line.trim());
- if (m.matches()) {
- map.put(m.group(2), m.group(1));
- }
- }
- return map;
- }
-
-}
diff --git a/translator-src/nu/validator/htmlparser/cpptranslate/HVisitor.java b/translator-src/nu/validator/htmlparser/cpptranslate/HVisitor.java
deleted file mode 100644
index 6161746d..00000000
--- a/translator-src/nu/validator/htmlparser/cpptranslate/HVisitor.java
+++ /dev/null
@@ -1,291 +0,0 @@
-/* ***** BEGIN LICENSE BLOCK *****
- * Version: MPL 1.1/GPL 2.0/LGPL 2.1
- *
- * The contents of this file are subject to the Mozilla Public License Version
- * 1.1 (the "License"); you may not use this file except in compliance with
- * the License. You may obtain a copy of the License at
- * http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS" basis,
- * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
- * for the specific language governing rights and limitations under the
- * License.
- *
- * The Original Code is HTML Parser C++ Translator code.
- *
- * The Initial Developer of the Original Code is
- * Mozilla Foundation.
- * Portions created by the Initial Developer are Copyright (C) 2008
- * the Initial Developer. All Rights Reserved.
- *
- * Contributor(s):
- * Henri Sivonen
- *
- * Alternatively, the contents of this file may be used under the terms of
- * either the GNU General Public License Version 2 or later (the "GPL"), or
- * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
- * in which case the provisions of the GPL or the LGPL are applicable instead
- * of those above. If you wish to allow use of your version of this file only
- * under the terms of either the GPL or the LGPL, and not to allow others to
- * use your version of this file under the terms of the MPL, indicate your
- * decision by deleting the provisions above and replace them with the notice
- * and other provisions required by the GPL or the LGPL. If you do not delete
- * the provisions above, a recipient may use your version of this file under
- * the terms of any one of the MPL, the GPL or the LGPL.
- *
- * ***** END LICENSE BLOCK ***** */
-
-package nu.validator.htmlparser.cpptranslate;
-
-import java.util.List;
-
-import japa.parser.ast.body.FieldDeclaration;
-import japa.parser.ast.body.MethodDeclaration;
-import japa.parser.ast.body.ModifierSet;
-import japa.parser.ast.body.Parameter;
-import japa.parser.ast.body.VariableDeclarator;
-import japa.parser.ast.stmt.BlockStmt;
-import japa.parser.ast.type.PrimitiveType;
-import japa.parser.ast.type.ReferenceType;
-
-public class HVisitor extends CppVisitor {
-
- private enum Visibility {
- NONE, PRIVATE, PUBLIC, PROTECTED,
- }
-
- private Visibility previousVisibility = Visibility.NONE;
-
- /**
- * @see nu.validator.htmlparser.cpptranslate.CppVisitor#printMethodNamespace()
- */
- @Override protected void printMethodNamespace() {
- }
-
- public HVisitor(CppTypes cppTypes, SymbolTable symbolTable) {
- super(cppTypes, symbolTable);
- }
-
- /**
- * @see nu.validator.htmlparser.cpptranslate.CppVisitor#startClassDeclaration()
- */
- @Override protected void startClassDeclaration() {
- printer.print("#ifndef ");
- printer.print(className);
- printer.printLn("_h");
- printer.print("#define ");
- printer.print(className);
- printer.printLn("_h");
-
- printer.printLn();
-
- String[] incs = cppTypes.boilerplateIncludes(javaClassName);
- for (int i = 0; i < incs.length; i++) {
- String inc = incs[i];
- if (className.equals(inc)) {
- continue;
- }
- printer.print("#include \"");
- printer.print(inc);
- printer.printLn(".h\"");
- }
-
- printer.printLn();
-
- String[] forwDecls = cppTypes.boilerplateForwardDeclarations();
- for (int i = 0; i < forwDecls.length; i++) {
- String decl = forwDecls[i];
- printer.print("class ");
- printer.print(decl);
- printer.printLn(";");
- }
-
- printer.printLn();
-
- for (int i = 0; i < Main.H_LIST.length; i++) {
- String klazz = Main.H_LIST[i];
- if (!(klazz.equals(javaClassName) || klazz.equals("StackNode"))) {
- printer.print("class ");
- printer.print(cppTypes.classPrefix());
- printer.print(klazz);
- printer.printLn(";");
- }
- }
-
- printer.printLn();
-
- String[] otherDecls = cppTypes.boilerplateDeclarations(javaClassName);
- for (int i = 0; i < otherDecls.length; i++) {
- String decl = otherDecls[i];
- printer.printLn(decl);
- }
-
- printer.printLn();
-
- printer.print("class ");
- printer.print(className);
- if ("StateSnapshot".equals(javaClassName) || "TreeBuilder".equals(javaClassName)) {
- printer.print(" : public ");
- printer.print(cppTypes.treeBuilderStateInterface());
- }
- printer.printLn();
- printer.printLn("{");
- printer.indent();
- }
-
- /**
- * @see nu.validator.htmlparser.cpptranslate.CppVisitor#endClassDeclaration()
- */
- @Override protected void endClassDeclaration() {
- printModifiers(ModifierSet.PUBLIC | ModifierSet.STATIC);
- printer.printLn("void initializeStatics();");
- printModifiers(ModifierSet.PUBLIC | ModifierSet.STATIC);
- printer.printLn("void releaseStatics();");
-
- printer.unindent();
-
- if (cppTypes.hasSupplement(javaClassName)) {
- printer.printLn();
- printer.print("#include \"");
- printer.print(className);
- printer.printLn("HSupplement.h\"");
- }
-
- printer.printLn("};");
- printer.printLn();
- printer.print("#endif");
- }
-
- /**
- * @see nu.validator.htmlparser.cpptranslate.CppVisitor#printModifiers(int)
- */
- @Override protected void printModifiers(int modifiers) {
- if (ModifierSet.isPrivate(modifiers)) {
- if (previousVisibility != Visibility.PRIVATE) {
- printer.unindent();
- printer.printLn("private:");
- printer.indent();
- previousVisibility = Visibility.PRIVATE;
- }
- } else if (ModifierSet.isProtected(modifiers)) {
- if (previousVisibility != Visibility.PROTECTED) {
- printer.unindent();
- printer.printLn("protected:");
- printer.indent();
- previousVisibility = Visibility.PROTECTED;
- }
- } else {
- if (previousVisibility != Visibility.PUBLIC) {
- printer.unindent();
- printer.printLn("public:");
- printer.indent();
- previousVisibility = Visibility.PUBLIC;
- }
- }
- if (inline()) {
- printer.print("inline ");
- }
- if (virtual()) {
- printer.print("virtual ");
- }
- if (ModifierSet.isStatic(modifiers)) {
- printer.print("static ");
- }
- }
-
- /**
- * @see nu.validator.htmlparser.cpptranslate.CppVisitor#fieldDeclaration(japa.parser.ast.body.FieldDeclaration, java.lang.LocalSymbolTable)
- */
- @Override protected void fieldDeclaration(FieldDeclaration n, LocalSymbolTable arg) {
- inField = true;
- int modifiers = n.getModifiers();
- List variables = n.getVariables();
- VariableDeclarator declarator = variables.get(0);
- if (ModifierSet.isStatic(modifiers) && ModifierSet.isFinal(modifiers)
- && n.getType() instanceof PrimitiveType) {
- PrimitiveType type = (PrimitiveType) n.getType();
- if (type.getType() != PrimitiveType.Primitive.Int) {
- throw new IllegalStateException(
- "Only int constant #defines supported.");
- }
- if (variables.size() != 1) {
- throw new IllegalStateException(
- "More than one variable declared by one declarator.");
- }
- printModifiers(modifiers);
- printer.print("const ");
- n.getType().accept(this, arg);
- printer.print(" ");
- declarator.getId().accept(this, arg);
- printer.print(" = ");
- declarator.getInit().accept(this, arg);
- printer.printLn(";");
- printer.printLn();
- symbolTable.addPrimitiveConstant(javaClassName, declarator.getId().toString());
- } else {
- if (n.getType() instanceof ReferenceType) {
- ReferenceType rt = (ReferenceType) n.getType();
- currentArrayCount = rt.getArrayCount();
- if (currentArrayCount > 0
- && (rt.getType() instanceof PrimitiveType) && declarator.getInit() != null) {
- if (!ModifierSet.isStatic(modifiers)) {
- throw new IllegalStateException(
- "Non-static array case not supported here." + declarator);
- }
- if (noLength()) {
- inPrimitiveNoLengthFieldDeclarator = true;
- }
- }
- }
- printModifiers(modifiers);
- inStatic = ModifierSet.isStatic(modifiers);
- n.getType().accept(this, arg);
- printer.print(" ");
- if (ModifierSet.isStatic(modifiers)) {
- if ("AttributeName".equals(n.getType().toString())) {
- printer.print("ATTR_");
- } else if ("ElementName".equals(n.getType().toString())) {
- printer.print("ELT_");
- }
- }
- declarator.getId().accept(this, arg);
- printer.printLn(";");
- currentArrayCount = 0;
- inStatic = false;
- inPrimitiveNoLengthFieldDeclarator = false;
- }
- inField = false;
- }
-
- /**
- * @see nu.validator.htmlparser.cpptranslate.CppVisitor#printConstructorExplicit(java.util.List)
- */
- @Override protected void printConstructorExplicit(List params) {
- if (params != null && params.size() == 1) {
- printer.print("explicit ");
- }
- }
-
- /**
- * @see nu.validator.htmlparser.cpptranslate.CppVisitor#printConstructorBody(japa.parser.ast.stmt.BlockStmt, java.lang.LocalSymbolTable)
- */
- @Override protected void printConstructorBody(BlockStmt block, LocalSymbolTable arg) {
- printer.printLn(";");
- }
-
- /**
- * @see nu.validator.htmlparser.cpptranslate.CppVisitor#visit(japa.parser.ast.body.MethodDeclaration, java.lang.LocalSymbolTable)
- */
- @Override public void visit(MethodDeclaration n, LocalSymbolTable arg) {
- arg = new LocalSymbolTable(javaClassName, symbolTable);
- printMethodDeclaration(n, arg);
- }
-
- /**
- * @see nu.validator.htmlparser.cpptranslate.CppVisitor#inHeader()
- */
- @Override protected boolean inHeader() {
- return true;
- }
-
-}
diff --git a/translator-src/nu/validator/htmlparser/cpptranslate/LabelVisitor.java b/translator-src/nu/validator/htmlparser/cpptranslate/LabelVisitor.java
deleted file mode 100644
index f27d465a..00000000
--- a/translator-src/nu/validator/htmlparser/cpptranslate/LabelVisitor.java
+++ /dev/null
@@ -1,84 +0,0 @@
-/* ***** BEGIN LICENSE BLOCK *****
- * Version: MPL 1.1/GPL 2.0/LGPL 2.1
- *
- * The contents of this file are subject to the Mozilla Public License Version
- * 1.1 (the "License"); you may not use this file except in compliance with
- * the License. You may obtain a copy of the License at
- * http://www.mozilla.org/MPL/
- *
- * Software distributed under the License is distributed on an "AS IS" basis,
- * WITHOUT WARRANTY OF ANY KIND, either express or implied. See the License
- * for the specific language governing rights and limitations under the
- * License.
- *
- * The Original Code is HTML Parser C++ Translator code.
- *
- * The Initial Developer of the Original Code is
- * Mozilla Foundation.
- * Portions created by the Initial Developer are Copyright (C) 2008
- * the Initial Developer. All Rights Reserved.
- *
- * Contributor(s):
- * Henri Sivonen
- *
- * Alternatively, the contents of this file may be used under the terms of
- * either the GNU General Public License Version 2 or later (the "GPL"), or
- * the GNU Lesser General Public License Version 2.1 or later (the "LGPL"),
- * in which case the provisions of the GPL or the LGPL are applicable instead
- * of those above. If you wish to allow use of your version of this file only
- * under the terms of either the GPL or the LGPL, and not to allow others to
- * use your version of this file under the terms of the MPL, indicate your
- * decision by deleting the provisions above and replace them with the notice
- * and other provisions required by the GPL or the LGPL. If you do not delete
- * the provisions above, a recipient may use your version of this file under
- * the terms of any one of the MPL, the GPL or the LGPL.
- *
- * ***** END LICENSE BLOCK ***** */
-
-package nu.validator.htmlparser.cpptranslate;
-
-import japa.parser.ast.stmt.BreakStmt;
-import japa.parser.ast.stmt.ContinueStmt;
-import japa.parser.ast.visitor.VoidVisitorAdapter;
-
-import java.util.HashSet;
-import java.util.Set;
-
-public class LabelVisitor extends VoidVisitorAdapter
