Docserver: Support markdown for HTML content. Request thirdparty submission review.

third_party/markdown/extensions/toc.py

Index: third_party/markdown/extensions/toc.py
diff --git a/third_party/markdown/extensions/toc.py b/third_party/markdown/extensions/toc.py
new file mode 100644
index 0000000000000000000000000000000000000000..6934dd339944cbfbf360ffac8f47d0d9b84b665f
--- /dev/null
+++ b/third_party/markdown/extensions/toc.py
@@ -0,0 +1,253 @@
+# markdown is released under the BSD license
+# Copyright 2007, 2008 The Python Markdown Project (v. 1.7 and later)
+# Copyright 2004, 2005, 2006 Yuri Takhteyev (v. 0.2-1.6b)
+# Copyright 2004 Manfred Stienstra (the original version)
+# 
+# All rights reserved.
+# 
+# Redistribution and use in source and binary forms, with or without
+# modification, are permitted provided that the following conditions are met:
+# 
+# *   Redistributions of source code must retain the above copyright
+#     notice, this list of conditions and the following disclaimer.
+# *   Redistributions in binary form must reproduce the above copyright
+#     notice, this list of conditions and the following disclaimer in the
+#     documentation and/or other materials provided with the distribution.
+# *   Neither the name of the <organization> nor the
+#     names of its contributors may be used to endorse or promote products
+#     derived from this software without specific prior written permission.
+# 
+# THIS SOFTWARE IS PROVIDED BY THE PYTHON MARKDOWN PROJECT ''AS IS'' AND ANY
+# EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
+# WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
+# DISCLAIMED. IN NO EVENT SHALL ANY CONTRIBUTORS TO THE PYTHON MARKDOWN PROJECT
+# BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
+# CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
+# SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
+# INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
+# CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
+# ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
+# POSSIBILITY OF SUCH DAMAGE.
+
+
+"""
+Table of Contents Extension for Python-Markdown
+* * *
+
+(c) 2008 [Jack Miller](http://codezen.org)
+
+Dependencies:
+* [Markdown 2.1+](http://packages.python.org/Markdown/)
+
+"""
+
+from __future__ import absolute_import
+from __future__ import unicode_literals
+from . import Extension
+from ..treeprocessors import Treeprocessor
+from ..util import etree
+from .headerid import slugify, unique, itertext
+import re
+
+
+def order_toc_list(toc_list):
+    """Given an unsorted list with errors and skips, return a nested one.
+    [{'level': 1}, {'level': 2}]
+    =>
+    [{'level': 1, 'children': [{'level': 2, 'children': []}]}]
+    
+    A wrong list is also converted:
+    [{'level': 2}, {'level': 1}]
+    =>
+    [{'level': 2, 'children': []}, {'level': 1, 'children': []}]
+    """
+    
+    def build_correct(remaining_list, prev_elements=[{'level': 1000}]):
+        
+        if not remaining_list:
+            return [], []
+        
+        current = remaining_list.pop(0)
+        if not 'children' in current.keys():
+            current['children'] = []
+        
+        if not prev_elements:
+            # This happens for instance with [8, 1, 1], ie. when some
+            # header level is outside a scope. We treat it as a
+            # top-level
+            next_elements, children = build_correct(remaining_list, [current])
+            current['children'].append(children)
+            return [current] + next_elements, []
+        
+        prev_element = prev_elements.pop()
+        children = []
+        next_elements = []
+        # Is current part of the child list or next list?
+        if current['level'] > prev_element['level']:
+            #print "%d is a child of %d" % (current['level'], prev_element['level'])
+            prev_elements.append(prev_element)
+            prev_elements.append(current)
+            prev_element['children'].append(current)
+            next_elements2, children2 = build_correct(remaining_list, prev_elements)
+            children += children2
+            next_elements += next_elements2
+        else:
+            #print "%d is ancestor of %d" % (current['level'], prev_element['level'])
+            if not prev_elements:
+                #print "No previous elements, so appending to the next set"
+                next_elements.append(current)
+                prev_elements = [current]
+                next_elements2, children2 = build_correct(remaining_list, prev_elements)
+                current['children'].extend(children2)
+            else:
+                #print "Previous elements, comparing to those first"
+                remaining_list.insert(0, current)
+                next_elements2, children2 = build_correct(remaining_list, prev_elements)
+                children.extend(children2)
+            next_elements += next_elements2
+        
+        return next_elements, children
+    
+    ordered_list, __ = build_correct(toc_list)
+    return ordered_list
+
+
+class TocTreeprocessor(Treeprocessor):
+    
+    # Iterator wrapper to get parent and child all at once
+    def iterparent(self, root):
+        for parent in root.getiterator():
+            for child in parent:
+                yield parent, child
+    
+    def add_anchor(self, c, elem_id): #@ReservedAssignment
+        if self.use_anchors:
+            anchor = etree.Element("a")
+            anchor.text = c.text
+            anchor.attrib["href"] = "#" + elem_id
+            anchor.attrib["class"] = "toclink"
+            c.text = ""
+            for elem in c.getchildren():
+                anchor.append(elem)
+                c.remove(elem)
+            c.append(anchor)
+    
+    def build_toc_etree(self, div, toc_list):
+        # Add title to the div
+        if self.config["title"]:
+            header = etree.SubElement(div, "span")
+            header.attrib["class"] = "toctitle"
+            header.text = self.config["title"]
+
+        def build_etree_ul(toc_list, parent):
+            ul = etree.SubElement(parent, "ul")
+            for item in toc_list:
+                # List item link, to be inserted into the toc div
+                li = etree.SubElement(ul, "li")
+                link = etree.SubElement(li, "a")
+                link.text = item.get('name', '')
+                link.attrib["href"] = '#' + item.get('id', '')
+                if item['children']:
+                    build_etree_ul(item['children'], li)
+            return ul
+        
+        return build_etree_ul(toc_list, div)
+        
+    def run(self, doc):
+
+        div = etree.Element("div")
+        div.attrib["class"] = "toc"
+        header_rgx = re.compile("[Hh][123456]")
+        
+        self.use_anchors = self.config["anchorlink"] in [1, '1', True, 'True', 'true']
+        
+        # Get a list of id attributes
+        used_ids = set()
+        for c in doc.getiterator():
+            if "id" in c.attrib:
+                used_ids.add(c.attrib["id"])
+
+        toc_list = []
+        marker_found = False
+        for (p, c) in self.iterparent(doc):
+            text = ''.join(itertext(c)).strip()
+            if not text:
+                continue
+
+            # To keep the output from screwing up the
+            # validation by putting a <div> inside of a <p>
+            # we actually replace the <p> in its entirety.
+            # We do not allow the marker inside a header as that
+            # would causes an enless loop of placing a new TOC 
+            # inside previously generated TOC.
+            if c.text and c.text.strip() == self.config["marker"] and \
+               not header_rgx.match(c.tag) and c.tag not in ['pre', 'code']:
+                for i in range(len(p)):
+                    if p[i] == c:
+                        p[i] = div
+                        break
+                marker_found = True
+                            
+            if header_rgx.match(c.tag):
+                
+                # Do not override pre-existing ids 
+                if not "id" in c.attrib:
+                    elem_id = unique(self.config["slugify"](text, '-'), used_ids)
+                    c.attrib["id"] = elem_id
+                else:
+                    elem_id = c.attrib["id"]
+
+                tag_level = int(c.tag[-1])
+                
+                toc_list.append({'level': tag_level,
+                    'id': elem_id,
+                    'name': text})
+                
+                self.add_anchor(c, elem_id)
+                
+        toc_list_nested = order_toc_list(toc_list)
+        self.build_toc_etree(div, toc_list_nested)
+        prettify = self.markdown.treeprocessors.get('prettify')
+        if prettify: prettify.run(div)
+        if not marker_found:
+            # serialize and attach to markdown instance.
+            toc = self.markdown.serializer(div)
+            for pp in self.markdown.postprocessors.values():
+                toc = pp.run(toc)
+            self.markdown.toc = toc
+
+
+class TocExtension(Extension):
+    
+    TreeProcessorClass = TocTreeprocessor
+    
+    def __init__(self, configs=[]):
+        self.config = { "marker" : ["[TOC]", 
+                            "Text to find and replace with Table of Contents -"
+                            "Defaults to \"[TOC]\""],
+                        "slugify" : [slugify,
+                            "Function to generate anchors based on header text-"
+                            "Defaults to the headerid ext's slugify function."],
+                        "title" : [None,
+                            "Title to insert into TOC <div> - "
+                            "Defaults to None"],
+                        "anchorlink" : [0,
+                            "1 if header should be a self link"
+                            "Defaults to 0"]}
+
+        for key, value in configs:
+            self.setConfig(key, value)
+
+    def extendMarkdown(self, md, md_globals):
+        tocext = self.TreeProcessorClass(md)
+        tocext.config = self.getConfigs()
+        # Headerid ext is set to '>prettify'. With this set to '_end',
+        # it should always come after headerid ext (and honor ids assinged 
+        # by the header id extension) if both are used. Same goes for 
+        # attr_list extension. This must come last because we don't want
+        # to redefine ids after toc is created. But we do want toc prettified.
+        md.treeprocessors.add("toc", tocext, "_end")
+
+
+def makeExtension(configs={}):
+    return TocExtension(configs=configs)