Flexible inline (#629)

Add new InlineProcessor class that handles inline processing much better and allows for more flexibility. This adds new InlineProcessors that no longer utilize unnecessary pretext and posttext captures. New class can accept the buffer that is being worked on and manually process the text without regex and return new replacement bounds. This helps us to handle links in a better way and handle nested brackets and logic that is too much for regular expression. The refactor also allows image links to have links/paths with spaces like links. Ref #551, #613, #590, #161.

6 files changed, 38 insertions, 38 deletions

diff --git a/markdown/extensions/abbr.py b/markdown/extensions/abbr.py
index 2553aac..5e8845b 100644
--- a/markdown/extensions/abbr.py
+++ b/markdown/extensions/abbr.py
@@ -20,7 +20,7 @@ from __future__ import absolute_import
 from __future__ import unicode_literals
 from . import Extension
 from ..preprocessors import Preprocessor
-from ..inlinepatterns import Pattern
+from ..inlinepatterns import InlineProcessor
 from ..util import etree, AtomicString
 import re
 
@@ -52,7 +52,7 @@ class AbbrPreprocessor(Preprocessor):
                 abbr = m.group('abbr').strip()
                 title = m.group('title').strip()
                 self.markdown.inlinePatterns['abbr-%s' % abbr] = \
-                    AbbrPattern(self._generate_pattern(abbr), title)
+                    AbbrInlineProcessor(self._generate_pattern(abbr), title)
                 # Preserve the line to prevent raw HTML indexing issue.
                 # https://github.com/Python-Markdown/markdown/issues/584
                 new_text.append('')
@@ -76,18 +76,18 @@ class AbbrPreprocessor(Preprocessor):
         return r'(?P<abbr>\b%s\b)' % (r''.join(chars))
 
 
-class AbbrPattern(Pattern):
+class AbbrInlineProcessor(InlineProcessor):
     """ Abbreviation inline pattern. """
 
     def __init__(self, pattern, title):
-        super(AbbrPattern, self).__init__(pattern)
+        super(AbbrInlineProcessor, self).__init__(pattern)
         self.title = title
 
-    def handleMatch(self, m):
+    def handleMatch(self, m, data):
         abbr = etree.Element('abbr')
         abbr.text = AtomicString(m.group('abbr'))
         abbr.set('title', self.title)
-        return abbr
+        return abbr, m.start(0), m.end(0)
 
 
 def makeExtension(**kwargs):  # pragma: no cover
diff --git a/markdown/extensions/footnotes.py b/markdown/extensions/footnotes.py
index d16cf84..a957278 100644
--- a/markdown/extensions/footnotes.py
+++ b/markdown/extensions/footnotes.py
@@ -17,7 +17,7 @@ from __future__ import absolute_import
 from __future__ import unicode_literals
 from . import Extension
 from ..preprocessors import Preprocessor
-from ..inlinepatterns import Pattern
+from ..inlinepatterns import InlineProcessor
 from ..treeprocessors import Treeprocessor
 from ..postprocessors import Postprocessor
 from .. import util
@@ -77,7 +77,7 @@ class FootnoteExtension(Extension):
         # Insert an inline pattern before ImageReferencePattern
         FOOTNOTE_RE = r'\[\^([^\]]*)\]'  # blah blah [^1] blah
         md.inlinePatterns.add(
-            "footnote", FootnotePattern(FOOTNOTE_RE, self), "<reference"
+            "footnote", FootnoteInlineProcessor(FOOTNOTE_RE, self), "<reference"
         )
         # Insert a tree-processor that would actually add the footnote div
         # This must be before all other treeprocessors (i.e., inline and
@@ -315,15 +315,15 @@ class FootnotePreprocessor(Preprocessor):
         return items, i
 
 
-class FootnotePattern(Pattern):
+class FootnoteInlineProcessor(InlineProcessor):
     """ InlinePattern for footnote markers in a document's body text. """
 
     def __init__(self, pattern, footnotes):
-        super(FootnotePattern, self).__init__(pattern)
+        super(FootnoteInlineProcessor, self).__init__(pattern)
         self.footnotes = footnotes
 
-    def handleMatch(self, m):
-        id = m.group(2)
+    def handleMatch(self, m, data):
+        id = m.group(1)
         if id in self.footnotes.footnotes.keys():
             sup = util.etree.Element("sup")
             a = util.etree.SubElement(sup, "a")
@@ -333,9 +333,9 @@ class FootnotePattern(Pattern):
                 a.set('rel', 'footnote')  # invalid in HTML5
             a.set('class', 'footnote-ref')
             a.text = util.text_type(self.footnotes.footnotes.index(id) + 1)
-            return sup
+            return sup, m.start(0), m.end(0)
         else:
-            return None
+            return None, None, None
 
 
 class FootnotePostTreeprocessor(Treeprocessor):
diff --git a/markdown/extensions/nl2br.py b/markdown/extensions/nl2br.py
index 687d1eb..5b9373f 100644
--- a/markdown/extensions/nl2br.py
+++ b/markdown/extensions/nl2br.py
@@ -19,7 +19,7 @@ License: [BSD](http://www.opensource.org/licenses/bsd-license.php)
 from __future__ import absolute_import
 from __future__ import unicode_literals
 from . import Extension
-from ..inlinepatterns import SubstituteTagPattern
+from ..inlinepatterns import SubstituteTagInlineProcessor
 
 BR_RE = r'\n'
 
@@ -27,7 +27,7 @@ BR_RE = r'\n'
 class Nl2BrExtension(Extension):
 
     def extendMarkdown(self, md, md_globals):
-        br_tag = SubstituteTagPattern(BR_RE, 'br')
+        br_tag = SubstituteTagInlineProcessor(BR_RE, 'br')
         md.inlinePatterns.add('nl', br_tag, '_end')
 
 
diff --git a/markdown/extensions/smart_strong.py b/markdown/extensions/smart_strong.py
index 1b00f84..f34531d 100644
--- a/markdown/extensions/smart_strong.py
+++ b/markdown/extensions/smart_strong.py
@@ -18,10 +18,10 @@ License: [BSD](http://www.opensource.org/licenses/bsd-license.php)
 from __future__ import absolute_import
 from __future__ import unicode_literals
 from . import Extension
-from ..inlinepatterns import SimpleTagPattern
+from ..inlinepatterns import SimpleTagInlineProcessor
 
-SMART_STRONG_RE = r'(?<!\w)(_{2})(?!_)(.+?)(?<!_)\2(?!\w)'
-STRONG_RE = r'(\*{2})(.+?)\2'
+SMART_STRONG_RE = r'(?<!\w)(_{2})(?!_)(.+?)(?<!_)\1(?!\w)'
+STRONG_RE = r'(\*{2})(.+?)\1'
 
 
 class SmartEmphasisExtension(Extension):
@@ -29,10 +29,10 @@ class SmartEmphasisExtension(Extension):
 
     def extendMarkdown(self, md, md_globals):
         """ Modify inline patterns. """
-        md.inlinePatterns['strong'] = SimpleTagPattern(STRONG_RE, 'strong')
+        md.inlinePatterns['strong'] = SimpleTagInlineProcessor(STRONG_RE, 'strong')
         md.inlinePatterns.add(
             'strong2',
-            SimpleTagPattern(SMART_STRONG_RE, 'strong'),
+            SimpleTagInlineProcessor(SMART_STRONG_RE, 'strong'),
             '>emphasis2'
         )
 
diff --git a/markdown/extensions/smarty.py b/markdown/extensions/smarty.py
index 35c78a8..189651f 100644
--- a/markdown/extensions/smarty.py
+++ b/markdown/extensions/smarty.py
@@ -83,7 +83,7 @@ smartypants.py license:
 
 from __future__ import unicode_literals
 from . import Extension
-from ..inlinepatterns import HtmlPattern, HTML_RE
+from ..inlinepatterns import HtmlInlineProcessor, HTML_RE
 from ..odict import OrderedDict
 from ..treeprocessors import InlineProcessor
 
@@ -150,21 +150,21 @@ remainingDoubleQuotesRegex = r'"'
 HTML_STRICT_RE = HTML_RE + r'(?!\>)'
 
 
-class SubstituteTextPattern(HtmlPattern):
+class SubstituteTextPattern(HtmlInlineProcessor):
     def __init__(self, pattern, replace, markdown_instance):
         """ Replaces matches with some text. """
-        HtmlPattern.__init__(self, pattern)
+        HtmlInlineProcessor.__init__(self, pattern)
         self.replace = replace
         self.markdown = markdown_instance
 
-    def handleMatch(self, m):
+    def handleMatch(self, m, data):
         result = ''
         for part in self.replace:
             if isinstance(part, int):
                 result += m.group(part)
             else:
                 result += self.markdown.htmlStash.store(part)
-        return result
+        return result, m.start(0), m.end(0)
 
 
 class SmartyExtension(Extension):
@@ -233,11 +233,11 @@ class SmartyExtension(Extension):
             (doubleQuoteSetsRe, (ldquo + lsquo,)),
             (singleQuoteSetsRe, (lsquo + ldquo,)),
             (decadeAbbrRe, (rsquo,)),
-            (openingSingleQuotesRegex, (2, lsquo)),
+            (openingSingleQuotesRegex, (1, lsquo)),
             (closingSingleQuotesRegex, (rsquo,)),
-            (closingSingleQuotesRegex2, (rsquo, 2)),
+            (closingSingleQuotesRegex2, (rsquo, 1)),
             (remainingSingleQuotesRegex, (lsquo,)),
-            (openingDoubleQuotesRegex, (2, ldquo)),
+            (openingDoubleQuotesRegex, (1, ldquo)),
             (closingDoubleQuotesRegex, (rdquo,)),
             (closingDoubleQuotesRegex2, (rdquo,)),
             (remainingDoubleQuotesRegex, (ldquo,))
@@ -255,7 +255,7 @@ class SmartyExtension(Extension):
             self.educateAngledQuotes(md)
             # Override HTML_RE from inlinepatterns.py so that it does not
             # process tags with duplicate closing quotes.
-            md.inlinePatterns["html"] = HtmlPattern(HTML_STRICT_RE, md)
+            md.inlinePatterns["html"] = HtmlInlineProcessor(HTML_STRICT_RE, md)
         if configs['smart_dashes']:
             self.educateDashes(md)
         inlineProcessor = InlineProcessor(md)
diff --git a/markdown/extensions/wikilinks.py b/markdown/extensions/wikilinks.py
index a4a3515..b535d9c 100644
--- a/markdown/extensions/wikilinks.py
+++ b/markdown/extensions/wikilinks.py
@@ -18,7 +18,7 @@ License: [BSD](http://www.opensource.org/licenses/bsd-license.php)
 from __future__ import absolute_import
 from __future__ import unicode_literals
 from . import Extension
-from ..inlinepatterns import Pattern
+from ..inlinepatterns import InlineProcessor
 from ..util import etree
 import re
 
@@ -46,20 +46,20 @@ class WikiLinkExtension(Extension):
 
         # append to end of inline patterns
         WIKILINK_RE = r'\[\[([\w0-9_ -]+)\]\]'
-        wikilinkPattern = WikiLinks(WIKILINK_RE, self.getConfigs())
+        wikilinkPattern = WikiLinksInlineProcessor(WIKILINK_RE, self.getConfigs())
         wikilinkPattern.md = md
         md.inlinePatterns.add('wikilink', wikilinkPattern, "<not_strong")
 
 
-class WikiLinks(Pattern):
+class WikiLinksInlineProcessor(InlineProcessor):
     def __init__(self, pattern, config):
-        super(WikiLinks, self).__init__(pattern)
+        super(WikiLinksInlineProcessor, self).__init__(pattern)
         self.config = config
 
-    def handleMatch(self, m):
-        if m.group(2).strip():
+    def handleMatch(self, m, data):
+        if m.group(1).strip():
             base_url, end_url, html_class = self._getMeta()
-            label = m.group(2).strip()
+            label = m.group(1).strip()
             url = self.config['build_url'](label, base_url, end_url)
             a = etree.Element('a')
             a.text = label
@@ -68,7 +68,7 @@ class WikiLinks(Pattern):
                 a.set('class', html_class)
         else:
             a = ''
-        return a
+        return a, m.start(0), m.end(0)
 
     def _getMeta(self):
         """ Return meta data or config data. """