Skip to content

Pass hash table directly in tokenizer #18650

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 25, 2025
Merged

Pass hash table directly in tokenizer #18650

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 9 additions & 7 deletions ext/tokenizer/tokenizer.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -280,7 +280,7 @@ static zend_string *make_str(unsigned char *text, size_t leng, HashTable *intern
}

static void add_token(
zval *return_value, int token_type, unsigned char *text, size_t leng, int lineno,
HashTable *return_value_ht, int token_type, unsigned char *text, size_t leng, int lineno,
zend_class_entry *token_class, HashTable *interned_strings) {
zval token;
if (token_class) {
Expand Down Expand Up @@ -315,7 +315,7 @@ static void add_token(
} else {
ZVAL_STR(&token, make_str(text, leng, interned_strings));
}
zend_hash_next_index_insert_new(Z_ARRVAL_P(return_value), &token);
zend_hash_next_index_insert_new(return_value_ht, &token);
}

static bool tokenize(zval *return_value, zend_string *source, zend_class_entry *token_class)
Expand All @@ -337,11 +337,13 @@ static bool tokenize(zval *return_value, zend_string *source, zend_class_entry *
zend_hash_init(&interned_strings, 0, NULL, NULL, 0);
array_init(return_value);

HashTable *return_value_ht = Z_ARRVAL_P(return_value);

while ((token_type = lex_scan(&token, NULL))) {
ZEND_ASSERT(token_type != T_ERROR);

add_token(
return_value, token_type, zendtext, zendleng, token_line,
return_value_ht, token_type, zendtext, zendleng, token_line,
token_class, &interned_strings);

if (Z_TYPE(token) != IS_UNDEF) {
Expand All @@ -358,7 +360,7 @@ static bool tokenize(zval *return_value, zend_string *source, zend_class_entry *
/* fetch the rest into a T_INLINE_HTML */
if (zendcursor < zendlimit) {
add_token(
return_value, T_INLINE_HTML, zendcursor, zendlimit - zendcursor,
return_value_ht, T_INLINE_HTML, zendcursor, zendlimit - zendcursor,
token_line, token_class, &interned_strings);
}
break;
Expand All @@ -383,7 +385,7 @@ static bool tokenize(zval *return_value, zend_string *source, zend_class_entry *
}

struct event_context {
zval *tokens;
HashTable *tokens;
zend_class_entry *token_class;
};

Expand Down Expand Up @@ -428,7 +430,7 @@ static void on_event(
ctx->tokens, token, (unsigned char *) text, length, line, ctx->token_class, NULL);
break;
case ON_FEEDBACK: {
HashTable *tokens_ht = Z_ARRVAL_P(ctx->tokens);
HashTable *tokens_ht = ctx->tokens;
zval *token_zv, *id_zv = NULL;
ZEND_HASH_REVERSE_FOREACH_VAL(tokens_ht, token_zv) {
id_zv = extract_token_id_to_replace(token_zv, text, length);
Expand Down Expand Up @@ -469,7 +471,7 @@ static bool tokenize_parse(
zend_prepare_string_for_scanning(&source_zval, ZSTR_EMPTY_ALLOC());
array_init(&token_stream);

ctx.tokens = &token_stream;
ctx.tokens = Z_ARRVAL(token_stream);
ctx.token_class = token_class;

CG(ast) = NULL;
Expand Down