From c2cca0cefe6fb9977a23008af17641531e3b9e43 Mon Sep 17 00:00:00 2001
From: Waylan Limberg <waylan@gmail.com>
Date: Fri, 17 Jun 2011 10:32:22 -0400
Subject: Added attribute list extension inspired by Maruku's attribute list
 feature. See issue #7. Also likely to become a replacement for the headerid
 extension (with a little more work - need a forceid option) which means it
 will also address issue #16. The extension works with some limited testing.
 Still needs tests and documentation. Currently breaks toc extension - which
 should run after attr_list, not before.

---
 markdown/extensions/attr_list.py | 122 +++++++++++++++++++++++++++++++++++++++
 1 file changed, 122 insertions(+)
 create mode 100644 markdown/extensions/attr_list.py

diff --git a/markdown/extensions/attr_list.py b/markdown/extensions/attr_list.py
new file mode 100644
index 0000000..7a4014f
--- /dev/null
+++ b/markdown/extensions/attr_list.py
@@ -0,0 +1,122 @@
+"""
+Attribute List Extension for Python-Markdown
+============================================
+
+Adds attribute list syntax. Inspired by 
+[maruku](http://maruku.rubyforge.org/proposal.html#attribute_lists)'s
+feature of the same name.
+
+Copyright 2011 [Waylan Limberg](http://achinghead.com/).
+
+Contact: markdown@freewisdom.org
+
+License: BSD (see ../../LICENSE for details) 
+
+Dependencies:
+* [Python 2.4+](http://python.org)
+* [Markdown 2.1+](http://www.freewisdom.org/projects/python-markdown/)
+
+"""
+
+import markdown
+import re
+from markdown.util import isBlockLevel
+
+def _handle_double_quote(s, t):
+    k, v = t.split('=')
+    return k, v.strip('"')
+
+def _handle_single_quote(s, t):
+    k, v = t.split('=')
+    return k, v.strip("'")
+
+def _handle_key_value(s, t): 
+    return t.split('=')
+
+def _handle_word(s, t):
+    if t.startswith('.'):
+        return u'.', t[1:]
+    if t.startswith('#'):
+        return u'id', t[1:]
+    return t, t
+
+_scanner = re.Scanner([
+    (r'[^ ]+=".*?"', _handle_double_quote),
+    (r"[^ ]+='.*?'", _handle_single_quote),
+    (r'[^ ]+=[^ ]*', _handle_key_value),
+    (r'[^ ]+', _handle_word),
+    (r' ', None)
+])
+
+def get_attrs(str):
+    """ Parse attribute list and return a list of attribute tuples. """
+    return _scanner.scan(str)[0]
+
+def isheader(elem):
+    return elem.tag in ['h1', 'h2', 'h3', 'h4', 'h5', 'h6']
+
+class AttrListTreeprocessor(markdown.treeprocessors.Treeprocessor):
+    
+    BASE_RE = r'\{\:?([^\}]*)\}'
+    HEADER_RE = re.compile(r'[ ]*%s[ ]*$' % BASE_RE)
+    BLOCK_RE = re.compile(r'\n[ ]*%s[ ]*$' % BASE_RE)
+    INLINE_RE = re.compile(r'^%s' % BASE_RE)
+
+    def run(self, doc):
+        for elem in doc.getiterator():
+            #import pdb; pdb.set_trace()
+            if isBlockLevel(elem.tag):
+                # Block level: check for attrs on last line of text
+                RE = self.BLOCK_RE
+                if isheader(elem):
+                    # header: check for attrs at end of line
+                    RE = self.HEADER_RE
+                if len(elem) and elem[-1].tail:
+                    # has children. Get from tail of last child
+                    m = RE.search(elem[-1].tail)
+                    if m:
+                        self.assign_attrs(elem, m.group(1))
+                        elem[-1].tail = elem[-1].tail[:m.start()]
+                        if isheader(elem):
+                            # clean up trailing #s
+                            elem[-1].tail = elem[-1].tail.rstrip('#').rstrip()
+                elif elem.text:
+                    # no children. Get from text.
+                    m = RE.search(elem.text)
+                    if m:
+                        self.assign_attrs(elem, m.group(1))
+                        elem.text = elem.text[:m.start()]
+                        if isheader(elem):
+                            # clean up trailing #s
+                            elem.text = elem.text.rstrip('#').rstrip()
+            else:
+                # inline: check for attrs at start of tail
+                if elem.tail:
+                    m = self.INLINE_RE.match(elem.tail)
+                    if m:
+                        self.assign_attrs(elem, m.group(1))
+                        elem.tail = elem.tail[m.end():]
+
+    def assign_attrs(self, elem, attrs):
+        """ Assign attrs to element. """
+        for k, v in get_attrs(attrs):
+            if k == '.':
+                # add to class
+                cls = elem.get('class')
+                if cls:
+                    elem.set('class', '%s %s' % (cls, v))
+                else:
+                    elem.set('class', v)
+            else:
+                # assing attr k with v
+                elem.set(k, v)
+
+
+class AttrListExtension(markdown.extensions.Extension):
+    def extendMarkdown(self, md, md_globals):
+        # insert after 'inline' treeprocessor
+        md.treeprocessors.add('attr_list', AttrListTreeprocessor(md), '>inline')
+
+
+def makeExtension(configs={}):
+    return AttrListExtension(configs=configs)
-- 
cgit v1.2.3