Merge pull request #522 from Crozzers/middle-word-em

Add `middle-word-em` extra

CHANGES.md

@@ -3,6 +3,7 @@
 ## python-markdown2 2.4.10 (not yet released)
 
 - [pull #520] Allow more relative links in safe mode (issue #517)
+- [pull #522] Add `middle-word-em` extra
 
 
 ## python-markdown2 2.4.9

lib/markdown2.py

@@ -66,6 +66,9 @@
   some limitations.
 * metadata: Extract metadata from a leading '---'-fenced block.
   See <https://github.com/trentm/python-markdown2/issues/77> for details.
+* middle-word-em: Allows or disallows emphasis syntax in the middle of words,
+  defaulting to allow. Disabling this means that `this_text_here` will not be
+  converted to `this<em>text</em>here`.
 * nofollow: Add `rel="nofollow"` to add `<a>` tags with an href. See
   <http://en.wikipedia.org/wiki/Nofollow>.
 * numbering: Support of generic counters.  Non standard extension to
@@ -2299,17 +2302,24 @@ def _do_tg_spoiler(self, text):
         return text
 
     _strong_re = re.compile(r"(\*\*|__)(?=\S)(.+?[*_]*)(?<=\S)\1", re.S)
-    _em_re = re.compile(r"(\*|_)(?=\S)(.+?)(?<=\S)\1", re.S)
+    _em_re = r"(\*|_)(?=\S)(.+?)(?<=\S)\1"
     _code_friendly_strong_re = re.compile(r"\*\*(?=\S)(.+?[*_]*)(?<=\S)\*\*", re.S)
-    _code_friendly_em_re = re.compile(r"\*(?=\S)(.+?)(?<=\S)\*", re.S)
+    _code_friendly_em_re = r"\*(?=\S)(.+?)(?<=\S)\*"
     def _do_italics_and_bold(self, text):
+        if self.extras.get('middle-word-em', True) is False:
+            code_friendly_em_re = r'(?<=\b)%s(?=\b)' % self._code_friendly_em_re
+            em_re = r'(?<=\b)%s(?=\b)' % self._em_re
+        else:
+            code_friendly_em_re = self._code_friendly_em_re
+            em_re = self._em_re
+
         # <strong> must go first:
         if "code-friendly" in self.extras:
             text = self._code_friendly_strong_re.sub(r"<strong>\1</strong>", text)
-            text = self._code_friendly_em_re.sub(r"<em>\1</em>", text)
+            text = re.sub(code_friendly_em_re, r"<em>\1</em>", text, flags=re.S)
         else:
             text = self._strong_re.sub(r"<strong>\2</strong>", text)
-            text = self._em_re.sub(r"<em>\2</em>", text)
+            text = re.sub(em_re, r"<em>\2</em>", text, flags=re.S)
         return text
 
     # "smarty-pants" extra: Very liberal in interpreting a single prime as an

test/tm-cases/middle_word_em.html

@@ -0,0 +1,5 @@
+<p>When middle word emphasis is disabled strings like 'self.this_long_attr' should not
+become <code>self.this&lt;em&gt;long&lt;/em&gt;attr</code>.</p>
+
+<p>Emphasis will <em>only</em> occur when the word is surrounded with whitespace.
+This should still work with <em>my_filename</em>.</p>

test/tm-cases/middle_word_em.opts

@@ -0,0 +1 @@
+{'extras': {'middle-word-em': False}}

test/tm-cases/middle_word_em.text

@@ -0,0 +1,5 @@
+When middle word emphasis is disabled strings like 'self.this_long_attr' should not
+become `self.this<em>long</em>attr`.
+
+Emphasis will _only_ occur when the word is surrounded with whitespace.
+This should still work with _my_filename_.