jenkins-bot merged this change.

View Change

[bugfix] Re-enable resolveHtmlEntities

Bug: T57222
Change-Id: Icf2c7e47ffe3c906ea7aab9e653affbadef0955f
---
M pywikibot/cosmetic_changes.py
M pywikibot/page.py
M tests/cosmetic_changes_tests.py
3 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/pywikibot/cosmetic_changes.py b/pywikibot/cosmetic_changes.py
index 9c3a541..7752809 100755
--- a/pywikibot/cosmetic_changes.py
+++ b/pywikibot/cosmetic_changes.py
@@ -254,8 +254,7 @@
             self.translateAndCapitalizeNamespaces,
             self.translateMagicWords,
             self.replaceDeprecatedTemplates,
-            # FIXME: fix bugs and re-enable
-            # self.resolveHtmlEntities,
+            self.resolveHtmlEntities,
             self.removeEmptySections,
             self.removeUselessSpaces,
             self.removeNonBreakingSpaceBeforePercent,
@@ -621,9 +620,9 @@
         """Replace HTML entities with unicode."""
         ignore = [
             38,     # Ampersand (&)
-            39,     # Single quotation mark (") - bug T26093
+            39,     # Single quotation mark (") per T26093
             60,     # Less than (<)
-            62,     # Great than (>)
+            62,     # Greater than (>)
             91,     # Opening square bracket ([)
                     # - sometimes used intentionally inside links
             93,     # Closing square bracket (])
@@ -637,8 +636,8 @@
             8207,   # Right-to-left mark (&rtl;)
         ]
         if self.template:
-            ignore += [58]
-        text = pywikibot.html2unicode(text, ignore=ignore)
+            ignore += [58]  # Colon (:)
+        text = pywikibot.html2unicode(text, ignore=ignore, exceptions=['code'])
         return text
 
     def removeEmptySections(self, text):
diff --git a/pywikibot/page.py b/pywikibot/page.py
index 570cb6a..a8ab8a6 100644
--- a/pywikibot/page.py
+++ b/pywikibot/page.py
@@ -5925,7 +5925,7 @@
 # Utility functions for parsing page titles
 
 
-def html2unicode(text, ignore=None):
+def html2unicode(text, ignore=None, exceptions=None):
     """
     Replace HTML entities with equivalent unicode.
 
@@ -5977,6 +5977,10 @@
                       ignore)) | {129, 141, 157})
 
     def handle_entity(match):
+        if textlib.isDisabled(match.string, match.start(), tags=exceptions):
+            # match.string stores original text so we do not need
+            # to pass it to handle_entity, ♥ Python
+            return match.group(0)
         if match.group('decimal'):
             unicodeCodepoint = int(match.group('decimal'))
         elif match.group('hex'):
diff --git a/tests/cosmetic_changes_tests.py b/tests/cosmetic_changes_tests.py
index 9695aae..59779a6 100644
--- a/tests/cosmetic_changes_tests.py
+++ b/tests/cosmetic_changes_tests.py
@@ -55,6 +55,9 @@
         self.assertEqual(
             '&# # #0#>#x',
             self.cct.resolveHtmlEntities('&# # #0#>#x'))
+        self.assertEqual(
+            '<code>&#32;</code>',
+            self.cct.resolveHtmlEntities('<code>&#32;</code>'))
 
     def test_removeEmptySections(self):
         """Test removeEmptySections method."""

To view, visit change 434309. To unsubscribe, visit settings.