diff options
author | Waylan Limberg <waylan@gmail.com> | 2008-08-09 22:55:44 -0400 |
---|---|---|
committer | Waylan Limberg <waylan@gmail.com> | 2008-08-09 22:55:44 -0400 |
commit | 2b7e391fcd51d3468133f628f2e013574cf16536 (patch) | |
tree | 9aeda2cb0999ecab0531eedb762a7d4f2a233204 /mdx | |
parent | b941beb7973025d359f3e7839a5b99ea7f62c534 (diff) | |
download | markdown-2b7e391fcd51d3468133f628f2e013574cf16536.tar.gz markdown-2b7e391fcd51d3468133f628f2e013574cf16536.tar.bz2 markdown-2b7e391fcd51d3468133f628f2e013574cf16536.zip |
reorganized the extensions into a seperate dir. Much cleaner looking file system IMO.
Diffstat (limited to 'mdx')
-rw-r--r-- | mdx/__init__.py | 0 | ||||
-rw-r--r-- | mdx/mdx_codehilite.py | 218 | ||||
-rw-r--r-- | mdx/mdx_extra.py | 52 | ||||
-rw-r--r-- | mdx/mdx_fenced_code.py | 105 | ||||
-rw-r--r-- | mdx/mdx_footnotes.py | 276 | ||||
-rw-r--r-- | mdx/mdx_headerid.py | 202 | ||||
-rw-r--r-- | mdx/mdx_imagelinks.py | 135 | ||||
-rw-r--r-- | mdx/mdx_meta.py | 81 | ||||
-rw-r--r-- | mdx/mdx_rss.py | 118 | ||||
-rw-r--r-- | mdx/mdx_tables.py | 72 | ||||
-rw-r--r-- | mdx/mdx_wikilink.py | 140 |
11 files changed, 1399 insertions, 0 deletions
diff --git a/mdx/__init__.py b/mdx/__init__.py new file mode 100644 index 0000000..e69de29 --- /dev/null +++ b/mdx/__init__.py diff --git a/mdx/mdx_codehilite.py b/mdx/mdx_codehilite.py new file mode 100644 index 0000000..73c1a79 --- /dev/null +++ b/mdx/mdx_codehilite.py @@ -0,0 +1,218 @@ +#!/usr/bin/python + +""" +CodeHilite Extension for Python-Markdown +======================================= + +Adds code/syntax highlighting to standard Python-Markdown code blocks. + +By [Waylan Limberg](http://achinghead.com/). + +Project website: http://achinghead.com/markdown-wikilinks/ +Contact: waylan [at] gmail [dot] com + +License: [BSD](http://www.opensource.org/licenses/bsd-license.php) + +Version: 0.2 (April 30, 2008) + +Dependencies: +* [Python 2.3+](http://python.org/) +* [Markdown 1.7+](http://www.freewisdom.org/projects/python-markdown/) +* [Pygments](http://pygments.org/) + +""" + +import markdown + +# --------------- CONSTANTS YOU MIGHT WANT TO MODIFY ----------------- + +try: + TAB_LENGTH = markdown.TAB_LENGTH +except AttributeError: + TAB_LENGTH = 4 + + +# ------------------ The Main CodeHilite Class ---------------------- +class CodeHilite: + """ + Determine language of source code, and pass it into the pygments hilighter. + + Basic Usage: + >>> code = CodeHilite(src = text) + >>> html = code.hilite() + + * src: Can be a string or any object with a .readline attribute. + + * linenos: (Boolen) Turns line numbering 'on' or 'off' (off by default). + + Low Level Usage: + >>> code = CodeHilite() + >>> code.src = text # String or anything with a .readline attribute + >>> code.linenos = True # True or False; Turns line numbering on or of. + >>> html = code.hilite() + + """ + + def __init__(self, src=None, linenos = False): + self.src = src + self.lang = None + self.linenos = linenos + + def hilite(self): + """ + Pass code to the [Pygments](http://pygments.pocoo.org/) highliter with + optional line numbers. The output should then be styled with css to + your liking. No styles are applied by default - only styling hooks + (i.e.: <span class="k">). + + returns : A string of html. + + """ + + self.src = self.src.strip('\n') + + self._getLang() + + try: + from pygments import highlight + from pygments.lexers import get_lexer_by_name, guess_lexer, TextLexer + from pygments.formatters import HtmlFormatter + except ImportError: + # just escape and pass through + txt = self._escape(self.src) + '''if num: + txt = self._number(txt) + else : + txt = '<div class="codehilite"><pre>%s</pre></div>\n'% txt''' + txt = self._number(txt) + return txt + else: + try: + lexer = get_lexer_by_name(self.lang) + except ValueError: + try: + lexer = guess_lexer(self.src) + except ValueError: + lexer = TextLexer() + formatter = HtmlFormatter(linenos=self.linenos, cssclass="codehilite") + return highlight(self.src, lexer, formatter) + + def _escape(self, txt): + """ basic html escaping """ + txt = txt.replace('&', '&') + txt = txt.replace('<', '<') + txt = txt.replace('>', '>') + txt = txt.replace('"', '"') + return txt + + def _number(self, txt): + """ Use <ol> for line numbering """ + # Fix Whitespace + txt = txt.replace('\t', ' '*TAB_LENGTH) + txt = txt.replace(" "*4, " ") + txt = txt.replace(" "*3, " ") + txt = txt.replace(" "*2, " ") + + # Add line numbers + lines = txt.splitlines() + txt = '<div class="codehilite"><pre><ol>\n' + for line in lines: + txt += '\t<li>%s</li>\n'% line + txt += '</ol></pre></div>\n' + return txt + + + def _getLang(self): + """ + Determines language of a code block from shebang lines and whether said + line should be removed or left in place. If the sheband line contains a + path (even a single /) then it is assumed to be a real shebang lines and + left alone. However, if no path is given (e.i.: #!python or :::python) + then it is assumed to be a mock shebang for language identifitation of a + code fragment and removed from the code block prior to processing for + code highlighting. When a mock shebang (e.i: #!python) is found, line + numbering is turned on. When colons are found in place of a shebang + (e.i.: :::python), line numbering is left in the current state - off + by default. + + """ + + import re + + #split text into lines + lines = self.src.split("\n") + #pull first line to examine + fl = lines.pop(0) + + c = re.compile(r''' + (?:(?:::+)|(?P<shebang>[#]!)) #shebang or 2 or more colons + (?P<path>(?:/\w+)*[/ ])? # zero or 1 path ending in either a / or a single space + (?P<lang>\w*) # the language (a single / or space before lang is a path) + ''', re.VERBOSE) + # search first line for shebang + m = c.search(fl) + if m: + # we have a match + try: + self.lang = m.group('lang').lower() + except IndexError: + self.lang = None + if m.group('path'): + # path exists - restore first line + lines.insert(0, fl) + if m.group('shebang'): + # shebang exists - use line numbers + self.linenos = True + else: + # No match + lines.insert(0, fl) + + self.src = "\n".join(lines).strip("\n") + + + +# ------------------ The Markdown Extension ------------------------------- +class CodeHiliteExtention(markdown.Extension): + def __init__(self, configs): + # define default configs + self.config = { + 'force_linenos' : [False, "Force line numbers - Default: False"] + } + + # Override defaults with user settings + for key, value in configs: + # self.config[key][0] = value + self.setConfig(key, value) + + def extendMarkdown(self, md, md_globals): + + def _hiliteCodeBlock(parent_elem, lines, inList): + """ + Overrides `_processCodeBlock` method in standard Markdown class + and sends code blocks to a code highlighting proccessor. The result + is then stored in the HtmlStash, a placeholder is inserted into + the dom and the remainder of the text file is processed recursively. + + * parent_elem: DOM element to which the content will be added + * lines: a list of lines + * inList: a level + + returns: None + + """ + + detabbed, theRest = md.blockGuru.detectTabbed(lines) + text = "\n".join(detabbed).rstrip()+"\n" + code = CodeHilite(text, linenos=self.config['force_linenos'][0]) + placeholder = md.htmlStash.store(code.hilite(), safe=True) + if parent_elem.text: + parent_elem.text += placeholder + else: + parent_elem.text = placeholder + md._processSection(parent_elem, theRest, inList) + + md._processCodeBlock = _hiliteCodeBlock + +def makeExtension(configs={}): + return CodeHiliteExtention(configs=configs) + diff --git a/mdx/mdx_extra.py b/mdx/mdx_extra.py new file mode 100644 index 0000000..e99bec4 --- /dev/null +++ b/mdx/mdx_extra.py @@ -0,0 +1,52 @@ +#!/usr/bin/env python +""" +Python-Markdown Extra Extension +=============================== + +A compilation of various Python-Markdown extensions that imitates +[PHP Markdown Extra](http://michelf.com/projects/php-markdown/extra/). + +As no-one has yet written a Definition List extension for Python- +Markdown, definition lists are not yet supported by Extra. + +Note that each of the individual extensions still need to be available +on your PYTHONPATH. This extension simply wraps them all up as a +convenience so that only one extension needs to be listed when +initiating Markdown. See the documentation for each individual +extension for specifics about that extension. + +In the event that one or more of the supported extensions are not +available for import, Markdown will simply continue without that +extension. If you would like to be notified of such failures, +you may set Python-Markdown's logger level to "WARN". + +There may be additional extensions that are distributed with +Python-Markdown that are not included here in Extra. Those extensions +are not part of PHP Markdown Extra, and therefore, not part of +Python-Markdown Extra. If you really would like Extra to include +additional extensions, we suggest creating your own clone of Extra +under a differant name. You could also edit the `extensions` global +variable defined below, but be aware that such changes may be lost +when you upgrade to any future version of Python-Markdown. + +""" + +import markdown + +extensions = ['fenced_code', + 'footnotes', + 'headerid', + 'tables', + 'abbr', + ] + + +class ExtraExtension(markdown.Extension): + """ Add various extensions to Markdown class.""" + + def extendMarkdown(self, md, md_globals): + """ Register extension instances. """ + md.registerExtensions(extensions, self.config) + +def makeExtension(configs={}): + return ExtraExtension(configs=dict(configs)) diff --git a/mdx/mdx_fenced_code.py b/mdx/mdx_fenced_code.py new file mode 100644 index 0000000..c3d9f7f --- /dev/null +++ b/mdx/mdx_fenced_code.py @@ -0,0 +1,105 @@ +#!/usr/bin/env python + +""" +Fenced Code Extension for Python Markdown +========================================= + +This extension adds Fenced Code Blocks to Python-Markdown. + + >>> import markdown + >>> text = ''' + ... A paragraph before a fenced code block: + ... + ... ~~~ + ... Fenced code block + ... ~~~ + ... ''' + >>> html = markdown.markdown(text, extensions=['fenced_code']) + >>> html + u'<p>A paragraph before a fenced code block:\\n</p>\\n<pre><code>Fenced code block\\n</code></pre>' + +Works with safe_mode also (we check this because we are using the HtmlStash): + + >>> markdown.markdown(text, extensions=['fenced_code'], safe_mode='replace') + u'<p>A paragraph before a fenced code block:\\n</p>\\n<pre><code>Fenced code block\\n</code></pre>' + +Include tilde's in a code block and wrap with blank lines: + + >>> text = ''' + ... ~~~~~~~~ + ... + ... ~~~~ + ... + ... ~~~~~~~~''' + >>> markdown.markdown(text, extensions=['fenced_code']) + u'<pre><code>\\n~~~~\\n\\n</code></pre>' + +Multiple blocks and language tags: + + >>> text = ''' + ... ~~~~ + ... block one + ... ~~~~{.python} + ... + ... ~~~~ + ... <p>block two</p> + ... ~~~~{.html}''' + >>> markdown.markdown(text, extensions=['fenced_code']) + u'<pre><code class="python">block one\\n</code></pre>\\n\\n<pre><code class="html"><p>block two</p>\\n</code></pre>' + +""" + +import markdown, re + +# Global vars +FENCED_BLOCK_RE = re.compile( \ + r'(?P<fence>^~{3,})[ ]*\n(?P<code>.*?)(?P=fence)[ ]*(\{\.(?P<lang>[a-zA-Z0-9_-]*)\})?[ ]*$', + re.MULTILINE|re.DOTALL + ) +CODE_WRAP = '<pre><code%s>%s</code></pre>' +LANG_TAG = ' class="%s"' + + +class FencedCodeExtension(markdown.Extension): + + def extendMarkdown(self, md, md_globals): + """ Add FencedBlockPreprocessor to the Markdown instance. """ + + FENCED_BLOCK_PREPROCESSOR = FencedBlockPreprocessor() + FENCED_BLOCK_PREPROCESSOR.md = md + md.textPreprocessors.insert(0, FENCED_BLOCK_PREPROCESSOR) + + +class FencedBlockPreprocessor(markdown.TextPreprocessor): + + def run(self, text): + """ Match and store Fenced Code Blocks in the HtmlStash. """ + while 1: + m = FENCED_BLOCK_RE.search(text) + if m: + lang = '' + if m.group('lang'): + lang = LANG_TAG % m.group('lang') + code = CODE_WRAP % (lang, self._escape(m.group('code'))) + placeholder = self.md.htmlStash.store(code, safe=True) + text = '%s\n%s\n%s'% (text[:m.start()], placeholder, text[m.end():]) + else: + break + return text + + def _escape(self, txt): + """ basic html escaping """ + txt = txt.replace('&', '&') + txt = txt.replace('<', '<') + txt = txt.replace('>', '>') + txt = txt.replace('"', '"') + return txt + + +def makeExtension(configs=None): + return FencedCodeExtension() + + +if __name__ == "__main__": + import doctest + doctest.testmod() diff --git a/mdx/mdx_footnotes.py b/mdx/mdx_footnotes.py new file mode 100644 index 0000000..b46efbb --- /dev/null +++ b/mdx/mdx_footnotes.py @@ -0,0 +1,276 @@ +""" +========================= FOOTNOTES ================================= + +This section adds footnote handling to markdown. It can be used as +an example for extending python-markdown with relatively complex +functionality. While in this case the extension is included inside +the module itself, it could just as easily be added from outside the +module. Not that all markdown classes above are ignorant about +footnotes. All footnote functionality is provided separately and +then added to the markdown instance at the run time. + +Footnote functionality is attached by calling extendMarkdown() +method of FootnoteExtension. The method also registers the +extension to allow it's state to be reset by a call to reset() +method. + +Example: + Footnotes[^1] have a label[^label] and a definition[^!DEF]. + + [^1]: This is a footnote + [^label]: A footnote on "label" + [^!DEF]: The footnote for definition + +""" + +FN_BACKLINK_TEXT = "zz1337820767766393qq" + + +import re, markdown, random +from markdown import etree + +class FootnoteExtension (markdown.Extension): + + DEF_RE = re.compile(r'(\ ?\ ?\ ?)\[\^([^\]]*)\]:\s*(.*)') + SHORT_USE_RE = re.compile(r'\[\^([^\]]*)\]', re.M) # [^a] + + def __init__ (self, configs) : + + self.config = {'PLACE_MARKER' : + ["///Footnotes Go Here///", + "The text string that marks where the footnotes go"]} + + for key, value in configs : + self.config[key][0] = value + + self.reset() + + def extendMarkdown(self, md, md_globals) : + + self.md = md + + # Stateless extensions do not need to be registered + md.registerExtension(self) + + # Insert a preprocessor before ReferencePreprocessor + index = md.preprocessors.index(md_globals['REFERENCE_PREPROCESSOR']) + preprocessor = FootnotePreprocessor(self) + preprocessor.md = md + md.preprocessors.insert(index, preprocessor) + + # Insert an inline pattern before ImageReferencePattern + FOOTNOTE_RE = r'\[\^([^\]]*)\]' # blah blah [^1] blah + index = md.inlinePatterns.index(md_globals['IMAGE_REFERENCE_PATTERN']) + md.inlinePatterns.insert(index, FootnotePattern(FOOTNOTE_RE, self)) + + # Insert a post-processor that would actually add the footnote div + postprocessor = FootnotePostprocessor(self) + postprocessor.extension = self + + md.postprocessors.append(postprocessor) + + textPostprocessor = FootnoteTextPostprocessor(self) + + md.textPostprocessors.append(textPostprocessor) + + + def reset(self) : + # May be called by Markdown is state reset is desired + + self.footnote_suffix = "-" + str(int(random.random()*1000000000)) + self.used_footnotes={} + self.footnotes = {} + + def findFootnotesPlaceholder(self, root): + + def finder(element): + for child in element: + if child.text: + if child.text.find(self.getConfig("PLACE_MARKER")) > -1: + return child, True + if child.tail: + if child.tail.find(self.getConfig("PLACE_MARKER")) > -1: + return (child, element), False + finder(child) + return None + + res = finder(root) + return res + + + def setFootnote(self, id, text) : + self.footnotes[id] = text + + def makeFootnoteId(self, num) : + return 'fn%d%s' % (num, self.footnote_suffix) + + def makeFootnoteRefId(self, num) : + return 'fnr%d%s' % (num, self.footnote_suffix) + + def makeFootnotesDiv (self, root) : + """Creates the div with class='footnote' and populates it with + the text of the footnotes. + + @returns: the footnote div as a dom element """ + + if not self.footnotes.keys() : + return None + + div = etree.Element("div") + div.set('class', 'footnote') + hr = etree.SubElement(div, "hr") + ol = etree.SubElement(div, "ol") + + + footnotes = [(self.used_footnotes[id], id) + for id in self.footnotes.keys()] + footnotes.sort() + + for i, id in footnotes : + li = etree.SubElement(ol, "li") + li.set("id", self.makeFootnoteId(i)) + + self.md._processSection(li, self.footnotes[id].split("\n"), looseList=1) + + backlink = etree.Element("a") + backlink.set("href", "#" + self.makeFootnoteRefId(i)) + backlink.set("class", "footnoteBackLink") + backlink.set("title", + "Jump back to footnote %d in the text" % i) + backlink.text = FN_BACKLINK_TEXT + + if li.getchildren(): + node = li[-1] + if node.text: + li.append(backlink) + elif node.tag == "p": + node.append(backlink) + else: + p = etree.SubElement(li, "p") + p.append(backlink) + div = self.md.applyInlinePatterns(etree.ElementTree(div)).getroot() + return div + + +class FootnotePreprocessor : + + def __init__ (self, footnotes) : + self.footnotes = footnotes + + def run(self, lines) : + + self.blockGuru = markdown.BlockGuru() + lines = self._handleFootnoteDefinitions (lines) + + # Make a hash of all footnote marks in the text so that we + # know in what order they are supposed to appear. (This + # function call doesn't really substitute anything - it's just + # a way to get a callback for each occurence. + + text = "\n".join(lines) + self.footnotes.SHORT_USE_RE.sub(self.recordFootnoteUse, text) + + return text.split("\n") + + + def recordFootnoteUse(self, match) : + + id = match.group(1) + id = id.strip() + nextNum = len(self.footnotes.used_footnotes.keys()) + 1 + self.footnotes.used_footnotes[id] = nextNum + + + def _handleFootnoteDefinitions(self, lines) : + """Recursively finds all footnote definitions in the lines. + + @param lines: a list of lines of text + @returns: a string representing the text with footnote + definitions removed """ + + i, id, footnote = self._findFootnoteDefinition(lines) + + if id : + + plain = lines[:i] + + detabbed, theRest = self.blockGuru.detectTabbed(lines[i+1:]) + + self.footnotes.setFootnote(id, + footnote + "\n" + + "\n".join(detabbed)) + + more_plain = self._handleFootnoteDefinitions(theRest) + return plain + [""] + more_plain + + else : + return lines + + def _findFootnoteDefinition(self, lines) : + """Finds the first line of a footnote definition. + + @param lines: a list of lines of text + @returns: the index of the line containing a footnote definition """ + + counter = 0 + for line in lines : + m = self.footnotes.DEF_RE.match(line) + if m : + return counter, m.group(2), m.group(3) + counter += 1 + return counter, None, None + + +class FootnotePattern (markdown.Pattern) : + + def __init__ (self, pattern, footnotes) : + + markdown.Pattern.__init__(self, pattern) + self.footnotes = footnotes + + def handleMatch(self, m) : + sup = etree.Element("sup") + a = etree.SubElement(sup, "a") + id = m.group(2) + num = self.footnotes.used_footnotes[id] + sup.set('id', self.footnotes.makeFootnoteRefId(num)) + a.set('href', '#' + self.footnotes.makeFootnoteId(num)) + a.text = str(num) + return sup + +class FootnotePostprocessor (markdown.Postprocessor): + + def __init__ (self, footnotes) : + self.footnotes = footnotes + + def run(self, root): + footnotesDiv = self.footnotes.makeFootnotesDiv(root) + if footnotesDiv: + result = self.extension.findFootnotesPlaceholder(root) + + if result: + node, isText = result + if isText: + node.text = None + node.getchildren().insert(0, footnotesDiv) + else: + child, element = node + ind = element.getchildren().find(child) + element.getchildren().insert(ind + 1, footnotesDiv) + child.tail = None + + fnPlaceholder.parent.replaceChild(fnPlaceholder, footnotesDiv) + else : + root.append(footnotesDiv) + +class FootnoteTextPostprocessor (markdown.Postprocessor): + + def __init__ (self, footnotes) : + self.footnotes = footnotes + + def run(self, text) : + return text.replace(FN_BACKLINK_TEXT, "↩") + +def makeExtension(configs=[]): + return FootnoteExtension(configs=configs) + diff --git a/mdx/mdx_headerid.py b/mdx/mdx_headerid.py new file mode 100644 index 0000000..8947338 --- /dev/null +++ b/mdx/mdx_headerid.py @@ -0,0 +1,202 @@ +#!/usr/bin/python + +""" +HeaderID Extension for Python-Markdown +====================================== + +Adds ability to set HTML IDs for headers. + +Basic usage: + + >>> import markdown + >>> text = "# Some Header # {#some_id}" + >>> md = markdown.markdown(text, ['headerid']) + >>> md + u'<h1 id="some_id">Some Header</h1>' + +All header IDs are unique: + + >>> text = ''' + ... #Header + ... #Another Header {#header} + ... #Third Header {#header}''' + >>> md = markdown.markdown(text, ['headerid']) + >>> md + u'<h1 id="header">Header</h1>\\n\\n<h1 id="header_1">Another Header</h1>\\n\\n<h1 id="header_2">Third Header</h1>' + +To fit within a html template's hierarchy, set the header base level: + + >>> text = ''' + ... #Some Header + ... ## Next Level''' + >>> md = markdown.markdown(text, ['headerid(level=3)']) + >>> md + u'<h3 id="some_header">Some Header</h3>\\n\\n<h4 id="next_level">Next Level</h4>' + +Turn off auto generated IDs: + + >>> text = ''' + ... # Some Header + ... # Header with ID # { #foo }''' + >>> md = markdown.markdown(text, ['headerid(forceid=False)']) + >>> md + u'<h1>Some Header</h1>\\n\\n<h1 id="foo">Header with ID</h1>' + +Use with MetaData extension: + + >>> text = '''header_level: 2 + ... header_forceid: Off + ... + ... # A Header''' + >>> md = markdown.markdown(text, ['headerid', 'meta']) + >>> md + u'<h2>A Header</h2>' + +By [Waylan Limberg](http://achinghead.com/). + +Project website: http://achinghead.com/markdown-headerid/ +Contact: waylan [at] gmail [dot] com + +License: [BSD](http://www.opensource.org/licenses/bsd-license.php) + +Version: 0.1 (May 2, 2008) + +Dependencies: +* [Python 2.3+](http://python.org) +* [Markdown 1.7+](http://www.freewisdom.org/projects/python-markdown/) + +""" + +import markdown +from markdown import etree +import re +from string import ascii_lowercase, digits, punctuation + +ID_CHARS = ascii_lowercase + digits + '-_' + +HEADER_RE = re.compile(r'''^(\#{1,6}) # group(1) = string of hashes + ( [^{^#]*) # group(2) = Header text + [\#]* # optional closing hashes (not counted) + (?:[ \t]*\{[ \t]*\#([-_:a-zA-Z0-9]+)[ \t]*\})? # group(3) = id attr''', + re.VERBOSE) + +IDCOUNT_RE = re.compile(r'^(.*)_([0-9]+)$') + +class HeaderIdExtension (markdown.Extension) : + def __init__(self, configs): + # set defaults + self.config = { + 'level' : ['1', 'Base level for headers.'], + 'forceid' : ['True', 'Force all headers to have an id.'], + 'toc_id' : ['toc', 'Set html id of wrapper div for TOC.'], + 'toc_marker': ['///TOC///', 'Marker to identify position of TOC.'] + } + + for key, value in configs: + self.setConfig(key, value) + + + def extendMarkdown(self, md, md_globals) : + + md.IDs = [] + md.toc = Toc(self.getConfig('toc_id'), self.getConfig('toc_marker')) + + def _processHeaderId(parent_elem, paragraph) : + ''' + Overrides _processHeader of Markdown() and + adds an 'id' to the header. + ''' + m = HEADER_RE.match(paragraph[0]) + if m : + start_level, force_id = _get_meta() + level = len(m.group(1)) + start_level + if level > 6: + level = 6 + h = etree.Element("h%d" % level) + parent_elem.append(h) + inline = etree.SubElement(h, "inline") + inline.text = m.group(2).strip() + i = '' + if m.group(3): + i = _unique_id(m.group(3)) + elif force_id: + i = _create_id(m.group(2).strip()) + if i: + h.set('id', i) + md.toc.append(i, inline.text) + else : + message(CRITICAL, "We've got a problem header!") + + md._processHeader = _processHeaderId + + def _get_meta(): + ''' Return meta data suported by this ext as a tuple ''' + level = int(self.config['level'][0]) - 1 + force = _str2bool(self.config['forceid'][0]) + if hasattr(md, 'Meta'): + if md.Meta.has_key('header_level'): + level = int(md.Meta['header_level'][0]) - 1 + if md.Meta.has_key('header_forceid'): + force = _str2bool(md.Meta['header_forceid'][0]) + return level, force + + def _str2bool(s, default=False): + ''' Convert a string to a booleen value. ''' + s = str(s) + if s.lower() in ['0', 'f', 'false', 'off', 'no', 'n']: + return False + elif s.lower() in ['1', 't', 'true', 'on', 'yes', 'y']: + return True + return default + + def _unique_id(id): + ''' Ensure ID is unique. Append '_1', '_2'... if not ''' + while id in md.IDs: + m = IDCOUNT_RE.match(id) + if m: + id = '%s_%d'% (m.group(1), int(m.group(2))+1) + else: + id = '%s_%d'% (id, 1) + md.IDs.append(id) + return id + + + def _create_id(header): + ''' Return ID from Header text. ''' + h = '' + for c in header.lower().replace(' ', '_'): + if c in ID_CHARS: + h += c + elif c not in punctuation: + h += '+' + return _unique_id(h) + +class Toc(): + """ Store a Table of Contents from a documents Headers. """ + def __init__(self, html_id, marker): + self.html_id = html_id + self.marker = marker + self.ids = [] + self.labels = [] + + def append(self, id, label): + """ Append an item to the store. """ + self.ids.append(id) + self.labels.append(label) + + def render(self): + """ Render the TOC as HTML and return unicode. """ + out = u'<div id="%s"><ul>\n' % self.html_id + for c in range(len(self.ids)): + out += u'<li><a href="#%s">%s</a></li>\n'%(self.ids[c], self.labels[c]) + out += u'</ul></div>' + return out + + +def makeExtension(configs=None) : + return HeaderIdExtension(configs=configs) + +if __name__ == "__main__": + import doctest + doctest.testmod() + diff --git a/mdx/mdx_imagelinks.py b/mdx/mdx_imagelinks.py new file mode 100644 index 0000000..e545b24 --- /dev/null +++ b/mdx/mdx_imagelinks.py @@ -0,0 +1,135 @@ +""" +========================= IMAGE LINKS ================================= + + +Turns paragraphs like + +<~~~~~~~~~~~~~~~~~~~~~~~~ +dir/subdir +dir/subdir +dir/subdir +~~~~~~~~~~~~~~ +dir/subdir +dir/subdir +dir/subdir +~~~~~~~~~~~~~~~~~~~> + +Into mini-photo galleries. + +""" + +import re, markdown +import url_manager + + +IMAGE_LINK = """<a href="%s"><img src="%s" title="%s"/></a>""" +SLIDESHOW_LINK = """<a href="%s" target="_blank">[slideshow]</a>""" +ALBUM_LINK = """ <a href="%s">[%s]</a>""" + + +class ImageLinksExtension (markdown.Extension): + + def __init__ (self) : + self.reset() + + def extendMarkdown(self, md, md_globals) : + + self.md = md + + # Stateless extensions do not need to be registered + md.registerExtension(self) + + # Insert a preprocessor before all preprocessors + + preprocessor = ImageLinkPreprocessor() + preprocessor.md = md + md.preprocessors.insert(0, preprocessor) + + def reset(self) : + # May be called by Markdown is state reset is desired + pass + + +class ImageLinkPreprocessor (markdown.Preprocessor): + + def run(self, lines) : + + url = url_manager.BlogEntryUrl(url_manager.BlogUrl("all"), + "2006/08/29/the_rest_of_our") + + + all_images = [] + blocks = [] + in_image_block = False + + new_lines = [] + + for line in lines : + + if line.startswith("<~~~~~~~") : + albums = [] + rows = [] + in_image_block = True + + if not in_image_block : + + new_lines.append(line) + + else : + + line = line.strip() + + if line.endswith("~~~~~~>") or not line : + in_image_block = False + new_block = "<div><br/><center><span class='image-links'>\n" + + album_url_hash = {} + + for row in rows : + for photo_url, title in row : + new_block += " " + new_block += IMAGE_LINK % (photo_url, + photo_url.get_thumbnail(), + title) + + album_url_hash[str(photo_url.get_album())] = 1 + + new_block += "<br/>" + + new_block += "</span>" + new_block += SLIDESHOW_LINK % url.get_slideshow() + + album_urls = album_url_hash.keys() + album_urls.sort() + + if len(album_urls) == 1 : + new_block += ALBUM_LINK % (album_urls[0], "complete album") + else : + for i in range(len(album_urls)) : + new_block += ALBUM_LINK % (album_urls[i], + "album %d" % (i + 1) ) + + new_lines.append(new_block + "</center><br/></div>") + + elif line[1:6] == "~~~~~" : + rows.append([]) # start a new row + else : + parts = line.split() + line = parts[0] + title = " ".join(parts[1:]) + + album, photo = line.split("/") + photo_url = url.get_photo(album, photo, + len(all_images)+1) + all_images.append(photo_url) + rows[-1].append((photo_url, title)) + + if not album in albums : + albums.append(album) + + return new_lines + + +def makeExtension(configs) : + return ImageLinksExtension(configs) + diff --git a/mdx/mdx_meta.py b/mdx/mdx_meta.py new file mode 100644 index 0000000..30dea8a --- /dev/null +++ b/mdx/mdx_meta.py @@ -0,0 +1,81 @@ +#!usr/bin/python + +''' +Meta Data Extension for Python-Markdown +========================================== + +This extension adds Meta Data handling to markdown. + + >>> import markdown + >>> text = """Title: A Test Doc. + ... Author: Waylan Limberg + ... John Doe + ... Blank_Data: + ... + ... The body. This is paragraph one. + ... """ + >>> md = markdown.Markdown(text, ['meta']) + >>> md.convert() + u'<p>The body. This is paragraph one.\\n</p>' + >>> md.Meta + {u'blank_data': [u''], u'author': [u'Waylan Limberg', u'John Doe'], u'title': [u'A Test Doc.']} + +Make sure text without Meta Data still works (markdown < 1.6b returns a <p>). + + >>> text = ' Some Code - not extra lines of meta data.' + >>> md = markdown.Markdown(text, ['meta']) + >>> md.convert() + u'<pre><code>Some Code - not extra lines of meta data.\\n</code></pre>' + >>> md.Meta + {} + +''' + +import markdown, re + +# Global Vars +META_RE = re.compile(r'^[ ]{0,3}(?P<key>[A-Za-z0-9_-]+):\s*(?P<value>.*)') +META_MORE_RE = re.compile(r'^[ ]{4,}(?P<value>.*)') + +class MetaExtension (markdown.Extension) : + def __init__(self, configs): + pass + + def extendMarkdown(self, md, md_globals) : + self.md = md + + # Insert meta preprocessor first + META_PREPROCESSOR = MetaPreprocessor() + META_PREPROCESSOR.md = md + md.preprocessors.insert(0, META_PREPROCESSOR) + +class MetaPreprocessor(markdown.Preprocessor) : + def run(self, lines) : + meta = {} + key = None + while 1: + line = lines.pop(0) + if line.strip() == '': + break # blank line - done + m1 = META_RE.match(line) + if m1: + key = m1.group('key').lower().strip() + meta[key] = [m1.group('value').strip()] + else: + m2 = META_MORE_RE.match(line) + if m2 and key: + # Add another line to existing key + meta[key].append(m2.group('value').strip()) + else: + lines.insert(0, line) + break # no meta data - done + self.md.Meta = meta + return lines + + +def makeExtension(configs=None) : + return MetaExtension(configs=configs) + +if __name__ == "__main__": + import doctest + doctest.testmod() diff --git a/mdx/mdx_rss.py b/mdx/mdx_rss.py new file mode 100644 index 0000000..b88b9b5 --- /dev/null +++ b/mdx/mdx_rss.py @@ -0,0 +1,118 @@ +import markdown +from markdown import etree + +DEFAULT_URL = "http://www.freewisdom.org/projects/python-markdown/" +DEFAULT_CREATOR = "Yuri Takhteyev" +DEFAULT_TITLE = "Markdown in Python" +GENERATOR = "http://www.freewisdom.org/projects/python-markdown/markdown2rss" + +month_map = { "Jan" : "01", + "Feb" : "02", + "March" : "03", + "April" : "04", + "May" : "05", + "June" : "06", + "July" : "07", + "August" : "08", + "September" : "09", + "October" : "10", + "November" : "11", + "December" : "12" } + +def get_time(heading): + + heading = heading.split("-")[0] + heading = heading.strip().replace(",", " ").replace(".", " ") + + month, date, year = heading.split() + month = month_map[month] + + return rdftime(" ".join((month, date, year, "12:00:00 AM"))) + +def rdftime(time): + + time = time.replace(":", " ") + time = time.replace("/", " ") + time = time.split() + return "%s-%s-%sT%s:%s:%s-08:00" % (time[0], time[1], time[2], + time[3], time[4], time[5]) + + +def get_date(text): + return "date" + +class RssExtension (markdown.Extension): + + def extendMarkdown(self, md, md_globals): + + self.config = { 'URL' : [DEFAULT_URL, "Main URL"], + 'CREATOR' : [DEFAULT_CREATOR, "Feed creator's name"], + 'TITLE' : [DEFAULT_TITLE, "Feed title"] } + + md.xml_mode = True + + # Insert a post-processor that would actually add the title tag + postprocessor = RssPostProcessor(self) + postprocessor.ext = self + md.postprocessors.append(postprocessor) + md.stripTopLevelTags = 0 + md.docType = '<?xml version="1.0" encoding="utf-8"?>\n' + +class RssPostProcessor (markdown.Postprocessor): + + def __init__(self, md): + + pass + + def run (self, root): + + rss = etree.Element("rss") + rss.set("version", "2.0") + + channel = etree.SubElement(rss, "channel") + + for tag, text in (("title", self.ext.getConfig("TITLE")), + ("link", self.ext.getConfig("URL")), + ("description", None)): + + element = etree.SubElement(channel, tag) + element.text = text + + for child in root: + + + if child.tag in ["h1", "h2", "h3", "h4", "h5"] : + + heading = child.text.strip() + + item = etree.SubElement(channel, "item") + + link = etree.SubElement(item, "link") + link.text = self.ext.getConfig("URL") + + title = etree.SubElement(item, "title") + title.text = heading + + guid = ''.join([x for x in heading if x.isalnum()]) + + guidElem = etree.SubElement(item, "guid") + guidElem.text = guid + guidElem.set("isPermaLink", "false") + + elif child.tag in ["p"] : + if item: + description = etree.SubElement(item, "description") + if len(child): + content = "\n".join([etree.tostring(node) + for node in child]) + else: + content = child.text + pholder = self.stash.store("<![CDATA[ %s]]>" % content) + description.text = pholder + + return rss + + +def makeExtension(configs): + + return RssExtension(configs) diff --git a/mdx/mdx_tables.py b/mdx/mdx_tables.py new file mode 100644 index 0000000..829044c --- /dev/null +++ b/mdx/mdx_tables.py @@ -0,0 +1,72 @@ +#!/usr/bin/env python + +""" +Table extension for Python-Markdown +""" + +import markdown +from markdown import etree + +class TablePattern(markdown.Pattern) : + def __init__ (self, md): + markdown.Pattern.__init__(self, r'(^|\n)\|([^\n]*)\|') + self.md = md + + def handleMatch(self, m): + + # a single line represents a row + tr = etree.Element('tr') + + # chunks between pipes represent cells + + for t in m.group(3).split('|'): + + if len(t) >= 2 and t.startswith('*') and t.endswith('*'): + # if a cell is bounded by asterisks, it is a <th> + td = etree.Element('th') + t = t[1:-1] + else: + # otherwise it is a <td> + td = etree.Element('td') + + # add text ot inline section, later it will be + # processed by core + inline = etree.SubElement(td, "inline") + inline.text = t + + tr.append(td) + tr.tail = "\n" + + return tr + + +class TablePostprocessor: + + def _findElement(self, element, name): + result = [] + for child in element: + if child.tag == name: + result.append(child) + result += self._findElement(child, name) + return result + + def run(self, root): + + for element in self._findElement(root, "p"): + for child in element: + if child.tail: + element.tag = "table" + break + + + + +class TableExtension(markdown.Extension): + def extendMarkdown(self, md, md_globals): + md.inlinePatterns.insert(0, TablePattern(md)) + md.postprocessors.append(TablePostprocessor()) + + +def makeExtension(configs): + return TableExtension(configs) + diff --git a/mdx/mdx_wikilink.py b/mdx/mdx_wikilink.py new file mode 100644 index 0000000..47037a6 --- /dev/null +++ b/mdx/mdx_wikilink.py @@ -0,0 +1,140 @@ +#!/usr/bin/env python + +''' +WikiLink Extention for Python-Markdown +====================================== + +Converts CamelCase words to relative links. Requires Python-Markdown 1.6+ + +Basic usage: + + >>> import markdown + >>> text = "Some text with a WikiLink." + >>> md = markdown.markdown(text, ['wikilink']) + >>> md + u'<p>Some text with a <a href="/WikiLink/" class="wikilink">WikiLink</a>.\\n</p>' + +To define custom settings the simple way: + + >>> md = markdown.markdown(text, + ... ['wikilink(base_url=/wiki/,end_url=.html,html_class=foo)'] + ... ) + >>> md + u'<p>Some text with a <a href="/wiki/WikiLink.html" class="foo">WikiLink</a>.\\n</p>' + +Custom settings the complex way: + + >>> md = markdown.Markdown( + ... extensions = ['wikilink'], + ... extension_configs = {'wikilink': [ + ... ('base_url', 'http://example.com/'), + ... ('end_url', '.html'), + ... ('html_class', '') ]}, + ... safe_mode = True) + >>> md.convert(text) + u'<p>Some text with a <a href="http://example.com/WikiLink.html">WikiLink</a>.\\n</p>' + +Use MetaData with mdx_meta.py (Note the blank html_class in MetaData): + + >>> text = """wiki_base_url: http://example.com/ + ... wiki_end_url: .html + ... wiki_html_class: + ... + ... Some text with a WikiLink.""" + >>> md = markdown.Markdown(extensions=['meta', 'wikilink']) + >>> md.convert(text) + u'<p>Some text with a <a href="http://example.com/WikiLink.html">WikiLink</a>.\\n</p>' + +MetaData should not carry over to next document: + + >>> md.convert("No MetaData here.") + u'<p>No <a href="/MetaData/" class="wikilink">MetaData</a> here.\\n</p>' + +From the command line: + + python markdown.py -x wikilink(base_url=http://example.com/,end_url=.html,html_class=foo) src.txt + +By [Waylan Limberg](http://achinghead.com/). + +Project website: http://achinghead.com/markdown-wikilinks/ +Contact: waylan [at] gmail [dot] com + +License: [BSD](http://www.opensource.org/licenses/bsd-license.php) + +Version: 0.6 (May 2, 2008) + +Dependencies: +* [Python 2.3+](http://python.org) +* [Markdown 1.6+](http://www.freewisdom.org/projects/python-markdown/) +''' + +import markdown +from markdown import etree + +class WikiLinkExtension (markdown.Extension) : + def __init__(self, configs): + # set extension defaults + self.config = { + 'base_url' : ['/', 'String to append to beginning or URL.'], + 'end_url' : ['/', 'String to append to end of URL.'], + 'html_class' : ['wikilink', 'CSS hook. Leave blank for none.'] + } + + # Override defaults with user settings + for key, value in configs : + self.setConfig(key, value) + + def extendMarkdown(self, md, md_globals): + self.md = md + + # append to end of inline patterns + WIKILINK_RE = r'''(?P<escape>\\|\b)(?P<camelcase>([A-Z]+[a-z-_]+){2,})\b''' + WIKILINK_PATTERN = WikiLinks(WIKILINK_RE, self.config) + WIKILINK_PATTERN.md = md + md.inlinePatterns.append(WIKILINK_PATTERN) + + +class WikiLinks (markdown.BasePattern) : + def __init__(self, pattern, config): + markdown.BasePattern.__init__(self, pattern) + self.config = config + + def handleMatch(self, m): + if m.group('escape') == '\\': + a = m.group('camelcase') + else: + base_url, end_url, html_class = self._getMeta() + url = '%s%s%s'% (base_url, m.group('camelcase'), end_url) + label = m.group('camelcase').replace('_', ' ') + a = etree.Element('a') + a.text = label + a.set('href', url) + if html_class: + a.set('class', html_class) + return a + + def _getMeta(self): + """ Return meta data or config data. """ + base_url = self.config['base_url'][0] + end_url = self.config['end_url'][0] + html_class = self.config['html_class'][0] + if hasattr(self.md, 'Meta'): + if self.md.Meta.has_key('wiki_base_url'): + base_url = self.md.Meta['wiki_base_url'][0] + if self.md.Meta.has_key('wiki_end_url'): + end_url = self.md.Meta['wiki_end_url'][0] + if self.md.Meta.has_key('wiki_html_class'): + html_class = self.md.Meta['wiki_html_class'][0] + return base_url, end_url, html_class + + def type(self): + return "WLink" + + +def makeExtension(configs=None) : + return WikiLinkExtension(configs=configs) + +if __name__ == "__main__": + import doctest + doctest.testmod() + |