jenkins-bot merged this change.

View Change

textlib.extract_sections: Remove footer from the last section

pywikibot.cosmetic_changes.py:
  - Use list.extend instead of concatenation.
textlib_tests.py:
  - Add a few tests for the bug at hand.
  - Remove the `dry` attribute when inheriting from
    DefaultDrySiteTestCase. The parent class sets the attributes.

Bug: T199751
Change-Id: Id67d5ab256ff6960e204fdae4c87ba7c2ff6f91e
---
M pywikibot/cosmetic_changes.py
M pywikibot/textlib.py
M tests/textlib_tests.py
3 files changed, 52 insertions(+), 10 deletions(-)

diff --git a/pywikibot/cosmetic_changes.py b/pywikibot/cosmetic_changes.py
index 6e3ff66..3130081 100755
--- a/pywikibot/cosmetic_changes.py
+++ b/pywikibot/cosmetic_changes.py
@@ -702,7 +702,7 @@
                            - len(current_heading.lstrip('=')))
             next_dep = len(next_heading) - len(next_heading.lstrip('='))
             if strip_section[1].strip() or current_dep < next_dep:
-                new_body = new_body + list(sections[i])
+                new_body.extend(sections[i])
         return header + ''.join(new_body) + footer
 
     def removeUselessSpaces(self, text):
diff --git a/pywikibot/textlib.py b/pywikibot/textlib.py
index 1e29666..d63a4be 100644
--- a/pywikibot/textlib.py
+++ b/pywikibot/textlib.py
@@ -907,12 +907,18 @@
     sections = _extract_sections(text, headings)
     # Find header and footer contents
     header = text[:headings[0].start] if headings else text
-    last_section_contents = sections[-1].content if sections else header
     cat_regex, interwiki_regex = _get_regexes(('category', 'interwiki'), site)
     langlink_pattern = interwiki_regex.pattern.replace(':?', '')
+    last_section_content = sections[-1].content if sections else header
     footer = re.search(
         r'(%s)*\Z' % r'|'.join((langlink_pattern, cat_regex.pattern, r'\s+')),
-        last_section_contents).group().strip()
+        last_section_content).group().lstrip()
+    if footer:
+        if sections:
+            sections[-1] = _Section(
+                sections[-1].title, last_section_content[:-len(footer)])
+        else:
+            header = header[:-len(footer)]
     return header, sections, footer
 
 
diff --git a/tests/textlib_tests.py b/tests/textlib_tests.py
index 078f1d6..67db849 100644
--- a/tests/textlib_tests.py
+++ b/tests/textlib_tests.py
@@ -15,7 +15,7 @@
 
 import pywikibot
 import pywikibot.textlib as textlib
-from pywikibot.textlib import _MultiTemplateMatchBuilder
+from pywikibot.textlib import _MultiTemplateMatchBuilder, extract_sections
 
 from pywikibot import config, UnknownSite
 from pywikibot.site import _IWEntry
@@ -143,8 +143,6 @@
 
     """Test category formatting."""
 
-    dry = True
-
     catresult = ('[[Category:Cat1]]%(LS)s[[Category:Cat2]]%(LS)s'
                  % {'LS': config.LS})
 
@@ -184,8 +182,6 @@
     with both a newline and an empty string as separators.
     """
 
-    dry = True
-
     old = ('[[Category:Cat1]]%(LS)s[[Category:Cat2|]]%(LS)s'
            '[[Category:Cat1| ]]%(LS)s[[Category:Cat2|key]]'
            % {'LS': config.LS})
@@ -1411,8 +1407,6 @@
 
     """Test _MultiTemplateMatchBuilder."""
 
-    dry = True
-
     @classmethod
     def setUpClass(cls):
         """Cache namespace 10 (Template) case sensitivity."""
@@ -1575,6 +1569,48 @@
                         '{{linkfa|fr}}\n', '{{linkfa|bar}}']))
 
 
+class TestExtractSections(DefaultDrySiteTestCase):
+
+    """Test the extract_sections function."""
+
+    def test_no_sections_no_footer(self):
+        """Test for text having no sections or footer."""
+        self.assertEqual(
+            extract_sections('text', self.site),
+            ('text', [], '')
+        )
+
+    def test_no_sections_with_footer(self):
+        """Test for text having footer but no section."""
+        self.assertEqual(
+            extract_sections('text\n\n[[Category:A]]', self.site),
+            ('text\n\n', [], '[[Category:A]]')
+        )
+
+    def test_with_section_no_footer(self):
+        """Test for text having sections but no footer."""
+        self.assertEqual(
+            extract_sections(
+                'text\n\n'
+                '==title==\n'
+                'content',
+                self.site),
+            ('text\n\n', [('==title==', '\ncontent')], '')
+        )
+
+    def test_with_section_with_footer(self):
+        """Test for text having sections and footer."""
+        self.assertEqual(
+            extract_sections(
+                'text\n\n'
+                '==title==\n'
+                'content\n'
+                '[[Category:A]]\n',
+                self.site),
+            ('text\n\n', [('==title==', '\ncontent\n')], '[[Category:A]]\n')
+        )
+
+
 if __name__ == '__main__':  # pragma: no cover
     try:
         unittest.main()

To view, visit change 446301. To unsubscribe, or for help writing mail filters, visit settings.