fix: don't linkify inside inline HTML markup tokens (link-patterns extra)

CHANGES.md

@@ -2,6 +2,8 @@
 
 ## python-markdown2 2.5.6 (not yet released)
 
+- Fix the `link-patterns` extra replacing matches inside inline HTML markup tokens (tag attributes, HTML comments, processing instructions, and `<word@example.com>` style auto-links) (#752)
+
 - [pull #762] Speed up documents with many links by skipping the backslash-escape scan for text without a backslash
 - [pull #748] Speed up `_unescape_special_chars` by skipping text with no hashes and dropping the full-text comparison per pass (#635)
 - [pull #749] URL-encode destinations generated by the `link-patterns` extra (#55)

lib/markdown2.py

@@ -3918,6 +3918,18 @@ def run(self, text: str):
                         continue
                     break
 
+                if not is_inside_link:
+                    # Also exclude markdown2's own inline HTML markup tokens
+                    # (tags, comments, processing instructions, and
+                    # <word@example.com> style auto-links): a match inside
+                    # one of them would corrupt the markup or destroy the
+                    # auto-link (e.g. linkifying an attribute value).
+                    for match in self.md._sorta_html_tokenize_re.finditer(text):
+                        m_start, m_end = match.span(1)
+                        if m_start <= start and end <= m_end:
+                            is_inside_link = True
+                            break
+
                 if is_inside_link:
                     continue
 

test/tm-cases/link_patterns_in_html_tags_issue752.html

@@ -0,0 +1,7 @@
+<p>See <span title="word"><a href="/w/word">word</a></span> here.</p>
+
+<p><a href="mailto:word@example.com">word@example.com</a></p>
+
+<p><img src="/x.png" alt="word"></p>
+
+<p>A <a href="/w/word">word</a> in prose.</p>

test/tm-cases/link_patterns_in_html_tags_issue752.opts

@@ -0,0 +1,5 @@
+{"extras": ["link-patterns"],
+ "link_patterns": [
+    (re.compile(r"\b(word)\b"), r"/w/\1"),
+ ],
+}

test/tm-cases/link_patterns_in_html_tags_issue752.text

@@ -0,0 +1,7 @@
+See <span title="word">word</span> here.
+
+<word@example.com>
+
+<img src="/x.png" alt="word">
+
+A word in prose.