fix regex matching on revisions with deleted text or comments

RegexPair.matchmake crashed with a TypeError when a capture-group
pattern was applied to a revision whose text or comment was deleted or
suppressed (content is None). Guard both matching paths against None,
and make the no-capture-group path emit a None column for such
revisions instead of omitting the key entirely.

This carries forward the fix Kaylea Champion and Mako Hill made on the
mako_changes-20230429 branch (7e6cd5b), which predated the rewrite.

Adds a unit test for matchmake(None) and an end-to-end test against the
ikwiki dump, which contains revisions with deleted text and comments.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
(cherry picked from commit dbcae5c64e)

src/wikiq/__init__.py

@@ -463,7 +463,8 @@ class RegexPair(object):
         # if there are named capture groups in the regex
         if self.has_groups:
             # if there are matches of some sort in this revision content, fill the lists for each cap_group
-            if self.pattern.search(content) is not None:
+            # content can be None when the text or comment was deleted/suppressed
+            if content is not None and self.pattern.search(content) is not None:
                 m = self.pattern.finditer(content)
                 matchobjects = list(m)
 
@@ -491,12 +492,11 @@ class RegexPair(object):
         # there are no capture groups, we just search for all the matches of the regex
         else:
             # given that there are matches to be made
-            if type(content) in (str, bytes):
+            if content is not None and self.pattern.search(content) is not None:
-                if self.pattern.search(content) is not None:
+                m = self.pattern.findall(content)
-                    m = self.pattern.findall(content)
+                temp_dict[self.label] = ", ".join(m)
-                    temp_dict[self.label] = ", ".join(m)
+            else:
-                else:
+                temp_dict[self.label] = None
-                    temp_dict[self.label] = None
 
         return temp_dict
 

test/Wikiq_Unit_Test.py

@@ -12,7 +12,7 @@ import pytest
 from pandas import DataFrame
 from pandas.testing import assert_frame_equal, assert_series_equal
 
-from wikiq import build_table, build_schema
+from wikiq import build_table, build_schema, RegexPair
 from wikiq_test_utils import (
     BASELINE_DIR,
     IKWIKI,
@@ -391,6 +391,35 @@ def test_capturegroup_regex():
         baseline = pd.read_table(tester.baseline_file)
         assert_frame_equal(test, baseline, check_like=True)
 
+def test_regex_none_content():
+    # deleted or suppressed revisions yield None for text and comments, and
+    # matchmake must tolerate that in both the capture-group and plain paths
+    pair = RegexPair(r"(?P<letter>\b[a-zA-Z]{3}\b)|(?P<number>\b\d+\b)", "cap")
+    assert pair.matchmake(None) == {"cap_letter": None, "cap_number": None}
+
+    pair = RegexPair(r"\b\d{3}\b", "digits")
+    assert pair.matchmake(None) == {"digits": None}
+
+def test_regex_deleted_revisions():
+    # the ikwiki dump contains revisions with deleted text and deleted
+    # comments; regex matching must handle them rather than crashing
+    tester = WikiqTester(wiki=IKWIKI, case_name="regex_deleted")
+
+    try:
+        tester.call_wikiq(
+            "-RP '(?P<npov>npov|NPOV)' -RPl npov",
+            "-CP '(?P<talk>[Tt]alk)' -CPl talk",
+        )
+    except subprocess.CalledProcessError as exc:
+        pytest.fail(exc.stderr.decode("utf8"))
+
+    test = pd.read_table(tester.output)
+
+    deleted = test[test["deleted"]]
+    assert len(deleted) > 0
+    assert deleted["npov_npov"].isna().all()
+    assert deleted["talk_talk"].isna().all()
+
 def test_external_links_only():
     """Test that --external-links extracts external links correctly."""
     import mwparserfromhell