CLDR-16755 Error fixing/testing for links in PathDescriptions (#4978)

Author: btangmu

tools/cldr-apps/src/test/java/org/unicode/cldr/util/TestCLDRLinks.java

@@ -100,9 +100,10 @@ public static Stream<Arguments> pathDescriptionProvider() {
 
         // this gets all URLs in references
         PathDescriptionParser pathDescriptionParser = new PathDescriptionParser();
-        pathDescriptionParser.parse(PathDescription.getPathDescriptionString());
+        String fileName = PathDescription.pathDescriptionFileName;
+        pathDescriptionParser.parse(PathDescription.getBigString(fileName));
         for (final String url : urlsFromString(pathDescriptionParser.getReferences())) {
-            urls.putIfAbsent(url, "PathDescriptions.md");
+            urls.putIfAbsent(url, fileName);
         }
 
         assertNotEquals(0, urls.size(), "PathDescription had no urls");

tools/cldr-code/src/main/java/org/unicode/cldr/util/PathDescription.java

@@ -18,13 +18,17 @@
 
 public class PathDescription {
     /** Remember to quote any [ character! */
+    public static final String pathDescriptionFileName = "PathDescriptions.md";
+
+    public static final String pathDescriptionHintsFileName = "PathDescriptionHints.md";
+
     private static final String pathDescriptionString =
-            CldrUtility.getUTF8Data("PathDescriptions.md")
+            CldrUtility.getUTF8Data(pathDescriptionFileName)
                     .lines()
                     .collect(Collectors.joining("\n"));
 
     private static final String pathDescriptionHintsString =
-            CldrUtility.getUTF8Data("PathDescriptionHints.md")
+            CldrUtility.getUTF8Data(pathDescriptionHintsFileName)
                     .lines()
                     .collect(Collectors.joining("\n"));
 
@@ -64,8 +68,15 @@ public enum ErrorHandling {
     private static final String references = parser.getReferences();
 
     /** for tests, returns the big string */
-    static String getPathDescriptionString() {
-        return pathDescriptionString;
+    static String getBigString(String fileName) {
+        switch (fileName) {
+            case pathDescriptionFileName:
+                return pathDescriptionString;
+            case pathDescriptionHintsFileName:
+                return pathDescriptionHintsString;
+            default:
+                throw new IllegalArgumentException();
+        }
     }
 
     /** for tests */

tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/PathDescriptionHints.md

@@ -294,6 +294,7 @@ warning, see info panel on right
 
 <!--
 This section is appended to every markdown fragment.
-All links should be https://cldr.unicode.org/translation/
-Currently, for hints, there are no reference links.
+All links should be cldr.unicode.org/translation/
+Currently, for hints, there are no actual reference links yet, but a "Placeholder" reference link is included for testing. 
 -->
+[Placeholder]: https://cldr.unicode.org/translation/units

tools/cldr-code/src/main/resources/org/unicode/cldr/util/data/PathDescriptions.md

@@ -220,19 +220,19 @@ The name of the language variant with code {0}. For more information, please see
 
 - `^//ldml/characters/exemplarCharacters$`
 
-Defines the set of characters used in your language. _To change this item, you have to flag it for review\!_ See [Changing Protected Items](https://cldr.unicode.org/translation/getting-started/guide#change-protected-items). Before filing any tickets to request changes, be sure to also read [Exemplar Characters].
+Defines the set of characters used in your language. _To change this item, you have to flag it for review\!_ See [Changing Protected Items]. Before filing any tickets to request changes, be sure to also read [Exemplar Characters].
 
 ###
 
 - `^//ldml/characters/exemplarCharacters\[@type="([^"]*)"]`
 
-Defines the set of characters used in your language for the “{1}” category. _To change this item, you have to flag it for review\!_ See [Changing Protected Items](https://cldr.unicode.org/translation/getting-started/guide#change-protected-items). Before filing any tickets to request changes, be sure to also read [Exemplar Characters].
+Defines the set of characters used in your language for the “{1}” category. _To change this item, you have to flag it for review\!_ See [Changing Protected Items]. Before filing any tickets to request changes, be sure to also read [Exemplar Characters].
 
 ###
 
 - `^//ldml/characters/parseLenients`
 
-Defines sets of characters that are treated as equivalent in parsing. _To change this item, you have to flag it for review\!_ See [Changing Protected Items](https://cldr.unicode.org/translation/getting-started/guide#change-protected-items). Before filing any tickets to request changes, be sure to also read [Exemplar Characters].
+Defines sets of characters that are treated as equivalent in parsing. _To change this item, you have to flag it for review\!_ See [Changing Protected Items]. Before filing any tickets to request changes, be sure to also read [Exemplar Characters].
 
 ###
 
@@ -1087,9 +1087,10 @@ A set of keywords for a character or sequence. For more information, see [Short
 
 <!--
 This section is appended to every markdown fragment.
-All links should be https://cldr.unicode.org/translation/
+All links should be cldr.unicode.org/translation/
 -->
 
+[Changing Protected Items]: https://cldr.unicode.org/translation/getting-started/guide#change-protected-items
 [Characters]: https://cldr.unicode.org/translation/characters
 [Character Labels]: https://cldr.unicode.org/translation/characters/character-labels
 [Compound Units]: https://cldr.unicode.org/translation/units/unit-names-and-patterns#compound-units

tools/cldr-code/src/test/java/org/unicode/cldr/util/TestPathDescription.java

@@ -12,20 +12,42 @@
 public class TestPathDescription {
     @Test
     public void testParseGiantString() {
+        parseOneString(PathDescription.pathDescriptionFileName);
+        parseOneString(PathDescription.pathDescriptionHintsFileName);
+    }
+
+    private void parseOneString(String fileName) {
+        final String bigString = PathDescription.getBigString(fileName);
         final PathDescriptionParser parser = new PathDescriptionParser();
-        RegexLookup<Pair<String, String>> lookup =
-                parser.parse(PathDescription.getPathDescriptionString());
+        final RegexLookup<Pair<String, String>> lookup = parser.parse(bigString);
+
         assertNotNull(lookup);
-        assertFalse(lookup.size() == 0, "lookup is empty");
+        assertNotEquals(0, lookup.size(), "lookup is empty");
+
         String references = parser.getReferences();
         assertNotNull(references);
-        assertFalse(parser.getReferences().trim().isEmpty());
-
+        assertFalse(references.trim().isEmpty());
         // To print out the regex tree:
         // System.out.println(lookup.toString());
         assertFalse(
-                parser.getReferences().contains("#h."),
-                "PathDescriptions.md refers to broken anchor #h.… (old Google Sites)");
+                references.contains("#h."),
+                fileName + " refers to broken anchor #h.… (old Google Sites)");
+
+        String badLine = containsHttpWithoutLeftBracket(bigString);
+        assertNull(
+                badLine,
+                fileName
+                        + " contains http in line that does not start with left bracket: "
+                        + badLine);
+    }
+
+    private String containsHttpWithoutLeftBracket(String s) {
+        for (String line : s.split("\\R")) {
+            if (!line.isBlank() && line.charAt(0) != '[' && line.contains("http")) {
+                return line;
+            }
+        }
+        return null;
     }
 
     @ParameterizedTest
@@ -36,7 +58,7 @@ public void testParseGiantString() {
                 "//ldml/dates/timeZoneNames/zone[@type=\"Asia/Kuching\"]/exemplarCity"
             })
     public void testPresent(final String xpath) {
-        assertNotNull(PathDescription.getPathHandling().get(xpath), () -> xpath);
+        assertNotNull(PathDescription.getPathHandling().get(xpath), xpath);
     }
 
     @Test
@@ -73,13 +95,12 @@ void testNoPlaceholders() {
                         "Remaining placeholders (sampling of xpaths) from PathDescriptions.md:\n"
                                 + xpathsWithPlaceholders.entrySet().stream()
                                         .map(
-                                                e -> {
-                                                    return urls.forXpath(locale, e.getValue())
-                                                            + " "
-                                                            + e.getKey()
-                                                            + " "
-                                                            + e.getValue();
-                                                })
+                                                e ->
+                                                        urls.forXpath(locale, e.getValue())
+                                                                + " "
+                                                                + e.getKey()
+                                                                + " "
+                                                                + e.getValue())
                                         .collect(Collectors.joining("\n")));
     }
 }