Regenerate linkification data in MakeUnicodeFiles #1286
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
eggrobin marked this conversation as resolved.
Show resolved
Hide resolved
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
|
|
@@ -28,6 +28,7 @@ | |
| import org.unicode.props.BagFormatter; | ||
| import org.unicode.props.UcdProperty; | ||
| import org.unicode.props.UcdPropertyValues; | ||
| import org.unicode.text.utility.DiffingPrintWriter; | ||
| import org.unicode.utilities.LinkUtilities; | ||
| import org.unicode.utilities.LinkUtilities.LinkTermination; | ||
| import org.unicode.utilities.LinkUtilities.Part; | ||
|
|
@@ -45,7 +46,7 @@ | |
| * | ||
| * @throws IOException | ||
| */ | ||
| public class GenerateLinkData { | ||
|
|
||
| private static final Transliterator FIX_ODD = | ||
| Transliterator.createFromRules( | ||
|
|
@@ -75,9 +76,13 @@ class GenerateLinkData { | |
| ""); | ||
|
|
||
| public static void main(String[] args) throws IOException { | ||
| System.out.println("TLDs=\t" + Joiner.on(' ').join(LinkUtilities.TLDS)); | ||
|
Member
Author
There was a problem hiding this comment. I haven’t the faintest idea, this print statement was at the beginning of generatePropertyData and wasn’t part of the generation of any of the three files, so I lifted it here to preserve the behaviour of this tool. I guess it has something to do with top level domains ? |
||
| final String copyrightYear = dty.format(now); | ||
| generateLinkTerm(copyrightYear); | ||
| generateLinkEmail(copyrightYear); | ||
| generateLinkBracket(copyrightYear); | ||
| generateDetectionTestData(copyrightYear); | ||
| generateFormattingTestData(copyrightYear); | ||
| } | ||
|
|
||
| static final Instant now = Instant.now(); | ||
|
|
@@ -213,21 +218,24 @@ static void writePropHeader( | |
| SimpleFormatter simpleFormatter, | ||
| String filename, | ||
| String propertyName, | ||
| String missingValue, | ||
| String copyrightYear) { | ||
| out.println( | ||
| simpleFormatter.format( | ||
| filename, dt.format(now), copyrightYear, propertyName, missingValue)); | ||
| } | ||
|
|
||
| static void writeTestHeader( | ||
| PrintWriter out, | ||
| SimpleFormatter simpleFormatter, | ||
| String filename, | ||
| String testName, | ||
| String copyrightYear) { | ||
| out.println(simpleFormatter.format(filename, dt.format(now), copyrightYear, testName)); | ||
|
Member
There was a problem hiding this comment. curious / probably for later: are
Member
Author
There was a problem hiding this comment. dt.format(now) is for the Date: line; that one is actually the time of regeneration, but ignored for diffing. copyrightYear is not ignored for diffing, so when using MakeUnicodeFiles it is from MakeUnicodeFiles.txt so that we don’t break on the 1st of January. (Of course the emoji do break on the 1st of January, see #1273. I should fix that, timebombs in CI are annoying.) |
||
| } | ||
|
|
||
| /** Generate property data for the UTS */ | ||
| public static void generateLinkTerm(String copyrightYear) { | ||
| BagFormatter bf = new BagFormatter(LinkUtilities.IUP).setLineSeparator("\n"); | ||
| bf.setShowLiteral(FIX_ODD); | ||
|
|
||
|
|
@@ -236,62 +244,81 @@ static void generatePropertyData() { | |
| bf.setValueSource(LinkTermination.PROPERTY); | ||
| bf.setLabelSource(LinkUtilities.IUP.getProperty(UcdProperty.Age)); | ||
|
|
||
| try (final var out = new DiffingPrintWriter(LinkUtilities.DATA_DIR_DEV, "LinkTerm.txt"); ) { | ||
| writePropHeader( | ||
| out.tempPrintWriter, | ||
| HEADER_PROP_TERM, | ||
| "LinkTerm", | ||
| "Link_Term", | ||
| "Hard", | ||
| copyrightYear); | ||
| for (LinkTermination propValue : LinkTermination.NON_MISSING) { | ||
| bf.showSetNames(out.tempPrintWriter, propValue.base); | ||
|
Member
There was a problem hiding this comment. When do we use |
||
| out.println(""); | ||
| out.flush(); | ||
| System.out.println(propValue + "=\t" + propValue.base.toPattern(false)); | ||
| } | ||
| } | ||
| } | ||
|
|
||
| public static void generateLinkEmail(String copyrightYear) { | ||
| BagFormatter bf = new BagFormatter(LinkUtilities.IUP).setLineSeparator("\n"); | ||
| bf.setShowLiteral(FIX_ODD); | ||
| bf.setLabelSource(LinkUtilities.IUP.getProperty(UcdProperty.Age)); | ||
| // LinkEmail.txt | ||
| bf.setValueSource(UnicodeLabel.NULL); | ||
| try (final var out = | ||
| new DiffingPrintWriter(LinkUtilities.DATA_DIR_DEV, "LinkEmail.txt"); ) { | ||
| writePropHeader( | ||
| out.tempPrintWriter, | ||
| HEADER_PROP_BINARY, | ||
| "LinkEmail", | ||
| "Link_Email", | ||
| UcdPropertyValues.Binary.No.toString(), | ||
| copyrightYear); | ||
| UnicodeSet linkEmailSet = LinkUtilities.LinkEmail.getSet(UcdPropertyValues.Binary.Yes); | ||
| bf.showSetNames(out.tempPrintWriter, linkEmailSet); | ||
| System.out.println("LinkEmail=\t" + linkEmailSet.toPattern(false)); | ||
| } | ||
| } | ||
|
|
||
| public static void generateLinkBracket(String copyrightYear) { | ||
| BagFormatter bf = new BagFormatter(LinkUtilities.IUP).setLineSeparator("\n"); | ||
| bf.setShowLiteral(FIX_ODD); | ||
| bf.setLabelSource(LinkUtilities.IUP.getProperty(UcdProperty.Age)); | ||
| // LinkBracket.txt | ||
| bf.setValueSource(LinkUtilities.getLinkBracket()); | ||
| bf.setHexValue(true); | ||
| bf.setShowDehexedValue(true); | ||
| try (final var out = | ||
| new DiffingPrintWriter(LinkUtilities.DATA_DIR_DEV, "LinkBracket.txt"); ) { | ||
| writePropHeader( | ||
| out.tempPrintWriter, | ||
| HEADER_PROP_STRING, | ||
| "LinkBracket", | ||
| "Link_Bracket", | ||
| "<none>", | ||
| copyrightYear); | ||
| bf.showSetNames(out.tempPrintWriter, LinkTermination.Close.base); | ||
| } | ||
| } | ||
|
|
||
| /** | ||
| * The format of the test file sources are: source<TAB>expected OR just source If there is an | ||
| * expected value, then it is checked against what is generated. | ||
| */ | ||
| public static void generateDetectionTestData(String copyrightYear) { | ||
|
|
||
| OutputInt errorCount = new OutputInt(); | ||
|
|
||
| try (final var out = | ||
| new DiffingPrintWriter(LinkUtilities.DATA_DIR_DEV, "LinkDetectionTest.txt"); ) { | ||
| writeTestHeader( | ||
| out.tempPrintWriter, | ||
| HEADER_DETECT_TEST, | ||
| "LinkDetectionTest", | ||
| "LinkDetectionTest", | ||
| copyrightYear); | ||
|
|
||
| out.println("\n# Misc. test cases\n"); | ||
|
|
||
|
|
@@ -364,16 +391,20 @@ static void generateDetectionTestData() { | |
| } | ||
| } | ||
|
|
||
| public static void generateFormattingTestData(String copyrightYear) { | ||
|
|
||
| OutputInt errorCount = new OutputInt(); | ||
|
|
||
| try (final var out = | ||
| new DiffingPrintWriter(LinkUtilities.DATA_DIR_DEV, "LinkFormattingTest.txt"); ) { | ||
| writeTestHeader( | ||
| out.tempPrintWriter, | ||
| HEADER_FORMAT_TEST, | ||
| "LinkFormattingTest", | ||
| "LinkFormattingTest", | ||
| copyrightYear); | ||
|
|
||
| out.tempPrintWriter.println("\n# Selected test cases\n"); | ||
|
|
||
| List<String> comments = new ArrayList<>(); | ||
| Output<Integer> lineCount = new Output<>(0); | ||
|
|
@@ -439,7 +470,7 @@ static void generateFormattingTestData() { | |
| comments.clear(); | ||
| return; | ||
| } | ||
| outputTestCase(out.tempPrintWriter, comments, internals, actual); | ||
| }); | ||
|
|
||
| out.println("\n# Wikipedia test cases\n"); | ||
|
|
@@ -480,7 +511,7 @@ static void generateFormattingTestData() { | |
|
|
||
| String actual = internals.minimalEscape(true, null); | ||
|
|
||
| outputTestCase(out.tempPrintWriter, comments, internals, actual); | ||
| }); | ||
| } catch (IOException e) { | ||
| throw new UncheckedIOException(e); | ||
|
|
||
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Oops, something went wrong.
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
We should definitely write 2026 now.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Yes, but we should make this change consistently and globally by updating MakeUnicodeFiles.txt. This will rewrite the whole UCD. Let’s do that in another PR.