Mercurial > repos > saskia-hiltemann > ireport
changeset 4:a4813532bbc6 draft
Added MarkDown support
| author | saskia-hiltemann |
|---|---|
| date | Tue, 07 Oct 2014 08:41:30 -0400 |
| parents | 4a6ebda2a3ae |
| children | 4e21ce709269 |
| files | Markdown/markdown2.py Markdown/markdown2.pyc Markdown/test README.md createHTML.sh iReport.sh iReport.xml ireport_css.css ireport_javascript.js ireport_jquery.js md.css |
| diffstat | 11 files changed, 3490 insertions(+), 182 deletions(-) [+] |
line wrap: on
line diff
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Markdown/markdown2.py Tue Oct 07 08:41:30 2014 -0400 @@ -0,0 +1,2440 @@ +#!/usr/bin/env python +# Copyright (c) 2012 Trent Mick. +# Copyright (c) 2007-2008 ActiveState Corp. +# License: MIT (http://www.opensource.org/licenses/mit-license.php) + +from __future__ import generators + +r"""A fast and complete Python implementation of Markdown. + +[from http://daringfireball.net/projects/markdown/] +> Markdown is a text-to-HTML filter; it translates an easy-to-read / +> easy-to-write structured text format into HTML. Markdown's text +> format is most similar to that of plain text email, and supports +> features such as headers, *emphasis*, code blocks, blockquotes, and +> links. +> +> Markdown's syntax is designed not as a generic markup language, but +> specifically to serve as a front-end to (X)HTML. You can use span-level +> HTML tags anywhere in a Markdown document, and you can use block level +> HTML tags (like <div> and <table> as well). + +Module usage: + + >>> import markdown2 + >>> markdown2.markdown("*boo!*") # or use `html = markdown_path(PATH)` + u'<p><em>boo!</em></p>\n' + + >>> markdowner = Markdown() + >>> markdowner.convert("*boo!*") + u'<p><em>boo!</em></p>\n' + >>> markdowner.convert("**boom!**") + u'<p><strong>boom!</strong></p>\n' + +This implementation of Markdown implements the full "core" syntax plus a +number of extras (e.g., code syntax coloring, footnotes) as described on +<https://github.com/trentm/python-markdown2/wiki/Extras>. +""" + +cmdln_desc = """A fast and complete Python implementation of Markdown, a +text-to-HTML conversion tool for web writers. + +Supported extra syntax options (see -x|--extras option below and +see <https://github.com/trentm/python-markdown2/wiki/Extras> for details): + +* code-friendly: Disable _ and __ for em and strong. +* cuddled-lists: Allow lists to be cuddled to the preceding paragraph. +* fenced-code-blocks: Allows a code block to not have to be indented + by fencing it with '```' on a line before and after. Based on + <http://github.github.com/github-flavored-markdown/> with support for + syntax highlighting. +* footnotes: Support footnotes as in use on daringfireball.net and + implemented in other Markdown processors (tho not in Markdown.pl v1.0.1). +* header-ids: Adds "id" attributes to headers. The id value is a slug of + the header text. +* html-classes: Takes a dict mapping html tag names (lowercase) to a + string to use for a "class" tag attribute. Currently only supports + "pre" and "code" tags. Add an issue if you require this for other tags. +* markdown-in-html: Allow the use of `markdown="1"` in a block HTML tag to + have markdown processing be done on its contents. Similar to + <http://michelf.com/projects/php-markdown/extra/#markdown-attr> but with + some limitations. +* metadata: Extract metadata from a leading '---'-fenced block. + See <https://github.com/trentm/python-markdown2/issues/77> for details. +* nofollow: Add `rel="nofollow"` to add `<a>` tags with an href. See + <http://en.wikipedia.org/wiki/Nofollow>. +* pyshell: Treats unindented Python interactive shell sessions as <code> + blocks. +* link-patterns: Auto-link given regex patterns in text (e.g. bug number + references, revision number references). +* smarty-pants: Replaces ' and " with curly quotation marks or curly + apostrophes. Replaces --, ---, ..., and . . . with en dashes, em dashes, + and ellipses. +* toc: The returned HTML string gets a new "toc_html" attribute which is + a Table of Contents for the document. (experimental) +* xml: Passes one-liner processing instructions and namespaced XML tags. +* tables: Tables using the same format as GFM + <https://help.github.com/articles/github-flavored-markdown#tables> and + PHP-Markdown Extra <https://michelf.ca/projects/php-markdown/extra/#table>. +* wiki-tables: Google Code Wiki-style tables. See + <http://code.google.com/p/support/wiki/WikiSyntax#Tables>. +""" + +# Dev Notes: +# - Python's regex syntax doesn't have '\z', so I'm using '\Z'. I'm +# not yet sure if there implications with this. Compare 'pydoc sre' +# and 'perldoc perlre'. + +__version_info__ = (2, 3, 1) +__version__ = '.'.join(map(str, __version_info__)) +__author__ = "Trent Mick" + +import os +import sys +from pprint import pprint, pformat +import re +import logging +try: + from hashlib import md5 +except ImportError: + from md5 import md5 +import optparse +from random import random, randint +import codecs + + +#---- Python version compat + +try: + from urllib.parse import quote # python3 +except ImportError: + from urllib import quote # python2 + +if sys.version_info[:2] < (2,4): + from sets import Set as set + def reversed(sequence): + for i in sequence[::-1]: + yield i + +# Use `bytes` for byte strings and `unicode` for unicode strings (str in Py3). +if sys.version_info[0] <= 2: + py3 = False + try: + bytes + except NameError: + bytes = str + base_string_type = basestring +elif sys.version_info[0] >= 3: + py3 = True + unicode = str + base_string_type = str + + + +#---- globals + +DEBUG = False +log = logging.getLogger("markdown") + +DEFAULT_TAB_WIDTH = 4 + + +SECRET_SALT = bytes(randint(0, 1000000)) +def _hash_text(s): + return 'md5-' + md5(SECRET_SALT + s.encode("utf-8")).hexdigest() + +# Table of hash values for escaped characters: +g_escape_table = dict([(ch, _hash_text(ch)) + for ch in '\\`*_{}[]()>#+-.!']) + + + +#---- exceptions + +class MarkdownError(Exception): + pass + + + +#---- public api + +def markdown_path(path, encoding="utf-8", + html4tags=False, tab_width=DEFAULT_TAB_WIDTH, + safe_mode=None, extras=None, link_patterns=None, + use_file_vars=False): + fp = codecs.open(path, 'r', encoding) + text = fp.read() + fp.close() + return Markdown(html4tags=html4tags, tab_width=tab_width, + safe_mode=safe_mode, extras=extras, + link_patterns=link_patterns, + use_file_vars=use_file_vars).convert(text) + +def markdown(text, html4tags=False, tab_width=DEFAULT_TAB_WIDTH, + safe_mode=None, extras=None, link_patterns=None, + use_file_vars=False): + return Markdown(html4tags=html4tags, tab_width=tab_width, + safe_mode=safe_mode, extras=extras, + link_patterns=link_patterns, + use_file_vars=use_file_vars).convert(text) + +class Markdown(object): + # The dict of "extras" to enable in processing -- a mapping of + # extra name to argument for the extra. Most extras do not have an + # argument, in which case the value is None. + # + # This can be set via (a) subclassing and (b) the constructor + # "extras" argument. + extras = None + + urls = None + titles = None + html_blocks = None + html_spans = None + html_removed_text = "[HTML_REMOVED]" # for compat with markdown.py + + # Used to track when we're inside an ordered or unordered list + # (see _ProcessListItems() for details): + list_level = 0 + + _ws_only_line_re = re.compile(r"^[ \t]+$", re.M) + + def __init__(self, html4tags=False, tab_width=4, safe_mode=None, + extras=None, link_patterns=None, use_file_vars=False): + if html4tags: + self.empty_element_suffix = ">" + else: + self.empty_element_suffix = " />" + self.tab_width = tab_width + + # For compatibility with earlier markdown2.py and with + # markdown.py's safe_mode being a boolean, + # safe_mode == True -> "replace" + if safe_mode is True: + self.safe_mode = "replace" + else: + self.safe_mode = safe_mode + + # Massaging and building the "extras" info. + if self.extras is None: + self.extras = {} + elif not isinstance(self.extras, dict): + self.extras = dict([(e, None) for e in self.extras]) + if extras: + if not isinstance(extras, dict): + extras = dict([(e, None) for e in extras]) + self.extras.update(extras) + assert isinstance(self.extras, dict) + if "toc" in self.extras and not "header-ids" in self.extras: + self.extras["header-ids"] = None # "toc" implies "header-ids" + self._instance_extras = self.extras.copy() + + self.link_patterns = link_patterns + self.use_file_vars = use_file_vars + self._outdent_re = re.compile(r'^(\t|[ ]{1,%d})' % tab_width, re.M) + + self._escape_table = g_escape_table.copy() + if "smarty-pants" in self.extras: + self._escape_table['"'] = _hash_text('"') + self._escape_table["'"] = _hash_text("'") + + def reset(self): + self.urls = {} + self.titles = {} + self.html_blocks = {} + self.html_spans = {} + self.list_level = 0 + self.extras = self._instance_extras.copy() + if "footnotes" in self.extras: + self.footnotes = {} + self.footnote_ids = [] + if "header-ids" in self.extras: + self._count_from_header_id = {} # no `defaultdict` in Python 2.4 + if "metadata" in self.extras: + self.metadata = {} + + # Per <https://developer.mozilla.org/en-US/docs/HTML/Element/a> "rel" + # should only be used in <a> tags with an "href" attribute. + _a_nofollow = re.compile(r"<(a)([^>]*href=)", re.IGNORECASE) + + def convert(self, text): + """Convert the given text.""" + # Main function. The order in which other subs are called here is + # essential. Link and image substitutions need to happen before + # _EscapeSpecialChars(), so that any *'s or _'s in the <a> + # and <img> tags get encoded. + + # Clear the global hashes. If we don't clear these, you get conflicts + # from other articles when generating a page which contains more than + # one article (e.g. an index page that shows the N most recent + # articles): + self.reset() + + if not isinstance(text, unicode): + #TODO: perhaps shouldn't presume UTF-8 for string input? + text = unicode(text, 'utf-8') + + if self.use_file_vars: + # Look for emacs-style file variable hints. + emacs_vars = self._get_emacs_vars(text) + if "markdown-extras" in emacs_vars: + splitter = re.compile("[ ,]+") + for e in splitter.split(emacs_vars["markdown-extras"]): + if '=' in e: + ename, earg = e.split('=', 1) + try: + earg = int(earg) + except ValueError: + pass + else: + ename, earg = e, None + self.extras[ename] = earg + + # Standardize line endings: + text = re.sub("\r\n|\r", "\n", text) + + # Make sure $text ends with a couple of newlines: + text += "\n\n" + + # Convert all tabs to spaces. + text = self._detab(text) + + # Strip any lines consisting only of spaces and tabs. + # This makes subsequent regexen easier to write, because we can + # match consecutive blank lines with /\n+/ instead of something + # contorted like /[ \t]*\n+/ . + text = self._ws_only_line_re.sub("", text) + + # strip metadata from head and extract + if "metadata" in self.extras: + text = self._extract_metadata(text) + + text = self.preprocess(text) + + if "fenced-code-blocks" in self.extras and not self.safe_mode: + text = self._do_fenced_code_blocks(text) + + if self.safe_mode: + text = self._hash_html_spans(text) + + # Turn block-level HTML blocks into hash entries + text = self._hash_html_blocks(text, raw=True) + + if "fenced-code-blocks" in self.extras and self.safe_mode: + text = self._do_fenced_code_blocks(text) + + # Strip link definitions, store in hashes. + if "footnotes" in self.extras: + # Must do footnotes first because an unlucky footnote defn + # looks like a link defn: + # [^4]: this "looks like a link defn" + text = self._strip_footnote_definitions(text) + text = self._strip_link_definitions(text) + + text = self._run_block_gamut(text) + + if "footnotes" in self.extras: + text = self._add_footnotes(text) + + text = self.postprocess(text) + + text = self._unescape_special_chars(text) + + if self.safe_mode: + text = self._unhash_html_spans(text) + + if "nofollow" in self.extras: + text = self._a_nofollow.sub(r'<\1 rel="nofollow"\2', text) + + text += "\n" + + rv = UnicodeWithAttrs(text) + if "toc" in self.extras: + rv._toc = self._toc + if "metadata" in self.extras: + rv.metadata = self.metadata + return rv + + def postprocess(self, text): + """A hook for subclasses to do some postprocessing of the html, if + desired. This is called before unescaping of special chars and + unhashing of raw HTML spans. + """ + return text + + def preprocess(self, text): + """A hook for subclasses to do some preprocessing of the Markdown, if + desired. This is called after basic formatting of the text, but prior + to any extras, safe mode, etc. processing. + """ + return text + + # Is metadata if the content starts with '---'-fenced `key: value` + # pairs. E.g. (indented for presentation): + # --- + # foo: bar + # another-var: blah blah + # --- + _metadata_pat = re.compile("""^---[ \t]*\n((?:[ \t]*[^ \t:]+[ \t]*:[^\n]*\n)+)---[ \t]*\n""") + + def _extract_metadata(self, text): + # fast test + if not text.startswith("---"): + return text + match = self._metadata_pat.match(text) + if not match: + return text + + tail = text[len(match.group(0)):] + metadata_str = match.group(1).strip() + for line in metadata_str.split('\n'): + key, value = line.split(':', 1) + self.metadata[key.strip()] = value.strip() + + return tail + + + _emacs_oneliner_vars_pat = re.compile(r"-\*-\s*([^\r\n]*?)\s*-\*-", re.UNICODE) + # This regular expression is intended to match blocks like this: + # PREFIX Local Variables: SUFFIX + # PREFIX mode: Tcl SUFFIX + # PREFIX End: SUFFIX + # Some notes: + # - "[ \t]" is used instead of "\s" to specifically exclude newlines + # - "(\r\n|\n|\r)" is used instead of "$" because the sre engine does + # not like anything other than Unix-style line terminators. + _emacs_local_vars_pat = re.compile(r"""^ + (?P<prefix>(?:[^\r\n|\n|\r])*?) + [\ \t]*Local\ Variables:[\ \t]* + (?P<suffix>.*?)(?:\r\n|\n|\r) + (?P<content>.*?\1End:) + """, re.IGNORECASE | re.MULTILINE | re.DOTALL | re.VERBOSE) + + def _get_emacs_vars(self, text): + """Return a dictionary of emacs-style local variables. + + Parsing is done loosely according to this spec (and according to + some in-practice deviations from this): + http://www.gnu.org/software/emacs/manual/html_node/emacs/Specifying-File-Variables.html#Specifying-File-Variables + """ + emacs_vars = {} + SIZE = pow(2, 13) # 8kB + + # Search near the start for a '-*-'-style one-liner of variables. + head = text[:SIZE] + if "-*-" in head: + match = self._emacs_oneliner_vars_pat.search(head) + if match: + emacs_vars_str = match.group(1) + assert '\n' not in emacs_vars_str + emacs_var_strs = [s.strip() for s in emacs_vars_str.split(';') + if s.strip()] + if len(emacs_var_strs) == 1 and ':' not in emacs_var_strs[0]: + # While not in the spec, this form is allowed by emacs: + # -*- Tcl -*- + # where the implied "variable" is "mode". This form + # is only allowed if there are no other variables. + emacs_vars["mode"] = emacs_var_strs[0].strip() + else: + for emacs_var_str in emacs_var_strs: + try: + variable, value = emacs_var_str.strip().split(':', 1) + except ValueError: + log.debug("emacs variables error: malformed -*- " + "line: %r", emacs_var_str) + continue + # Lowercase the variable name because Emacs allows "Mode" + # or "mode" or "MoDe", etc. + emacs_vars[variable.lower()] = value.strip() + + tail = text[-SIZE:] + if "Local Variables" in tail: + match = self._emacs_local_vars_pat.search(tail) + if match: + prefix = match.group("prefix") + suffix = match.group("suffix") + lines = match.group("content").splitlines(0) + #print "prefix=%r, suffix=%r, content=%r, lines: %s"\ + # % (prefix, suffix, match.group("content"), lines) + + # Validate the Local Variables block: proper prefix and suffix + # usage. + for i, line in enumerate(lines): + if not line.startswith(prefix): + log.debug("emacs variables error: line '%s' " + "does not use proper prefix '%s'" + % (line, prefix)) + return {} + # Don't validate suffix on last line. Emacs doesn't care, + # neither should we. + if i != len(lines)-1 and not line.endswith(suffix): + log.debug("emacs variables error: line '%s' " + "does not use proper suffix '%s'" + % (line, suffix)) + return {} + + # Parse out one emacs var per line. + continued_for = None + for line in lines[:-1]: # no var on the last line ("PREFIX End:") + if prefix: line = line[len(prefix):] # strip prefix + if suffix: line = line[:-len(suffix)] # strip suffix + line = line.strip() + if continued_for: + variable = continued_for + if line.endswith('\\'): + line = line[:-1].rstrip() + else: + continued_for = None + emacs_vars[variable] += ' ' + line + else: + try: + variable, value = line.split(':', 1) + except ValueError: + log.debug("local variables error: missing colon " + "in local variables entry: '%s'" % line) + continue + # Do NOT lowercase the variable name, because Emacs only + # allows "mode" (and not "Mode", "MoDe", etc.) in this block. + value = value.strip() + if value.endswith('\\'): + value = value[:-1].rstrip() + continued_for = variable + else: + continued_for = None + emacs_vars[variable] = value + + # Unquote values. + for var, val in list(emacs_vars.items()): + if len(val) > 1 and (val.startswith('"') and val.endswith('"') + or val.startswith('"') and val.endswith('"')): + emacs_vars[var] = val[1:-1] + + return emacs_vars + + # Cribbed from a post by Bart Lateur: + # <http://www.nntp.perl.org/group/perl.macperl.anyperl/154> + _detab_re = re.compile(r'(.*?)\t', re.M) + def _detab_sub(self, match): + g1 = match.group(1) + return g1 + (' ' * (self.tab_width - len(g1) % self.tab_width)) + def _detab(self, text): + r"""Remove (leading?) tabs from a file. + + >>> m = Markdown() + >>> m._detab("\tfoo") + ' foo' + >>> m._detab(" \tfoo") + ' foo' + >>> m._detab("\t foo") + ' foo' + >>> m._detab(" foo") + ' foo' + >>> m._detab(" foo\n\tbar\tblam") + ' foo\n bar blam' + """ + if '\t' not in text: + return text + return self._detab_re.subn(self._detab_sub, text)[0] + + # I broke out the html5 tags here and add them to _block_tags_a and + # _block_tags_b. This way html5 tags are easy to keep track of. + _html5tags = '|article|aside|header|hgroup|footer|nav|section|figure|figcaption' + + _block_tags_a = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math|ins|del' + _block_tags_a += _html5tags + + _strict_tag_block_re = re.compile(r""" + ( # save in \1 + ^ # start of line (with re.M) + <(%s) # start tag = \2 + \b # word break + (.*\n)*? # any number of lines, minimally matching + </\2> # the matching end tag + [ \t]* # trailing spaces/tabs + (?=\n+|\Z) # followed by a newline or end of document + ) + """ % _block_tags_a, + re.X | re.M) + + _block_tags_b = 'p|div|h[1-6]|blockquote|pre|table|dl|ol|ul|script|noscript|form|fieldset|iframe|math' + _block_tags_b += _html5tags + + _liberal_tag_block_re = re.compile(r""" + ( # save in \1 + ^ # start of line (with re.M) + <(%s) # start tag = \2 + \b # word break + (.*\n)*? # any number of lines, minimally matching + .*</\2> # the matching end tag + [ \t]* # trailing spaces/tabs + (?=\n+|\Z) # followed by a newline or end of document + ) + """ % _block_tags_b, + re.X | re.M) + + _html_markdown_attr_re = re.compile( + r'''\s+markdown=("1"|'1')''') + def _hash_html_block_sub(self, match, raw=False): + html = match.group(1) + if raw and self.safe_mode: + html = self._sanitize_html(html) + elif 'markdown-in-html' in self.extras and 'markdown=' in html: + first_line = html.split('\n', 1)[0] + m = self._html_markdown_attr_re.search(first_line) + if m: + lines = html.split('\n') + middle = '\n'.join(lines[1:-1]) + last_line = lines[-1] + first_line = first_line[:m.start()] + first_line[m.end():] + f_key = _hash_text(first_line) + self.html_blocks[f_key] = first_line + l_key = _hash_text(last_line) + self.html_blocks[l_key] = last_line + return ''.join(["\n\n", f_key, + "\n\n", middle, "\n\n", + l_key, "\n\n"]) + key = _hash_text(html) + self.html_blocks[key] = html + return "\n\n" + key + "\n\n" + + def _hash_html_blocks(self, text, raw=False): + """Hashify HTML blocks + + We only want to do this for block-level HTML tags, such as headers, + lists, and tables. That's because we still want to wrap <p>s around + "paragraphs" that are wrapped in non-block-level tags, such as anchors, + phrase emphasis, and spans. The list of tags we're looking for is + hard-coded. + + @param raw {boolean} indicates if these are raw HTML blocks in + the original source. It makes a difference in "safe" mode. + """ + if '<' not in text: + return text + + # Pass `raw` value into our calls to self._hash_html_block_sub. + hash_html_block_sub = _curry(self._hash_html_block_sub, raw=raw) + + # First, look for nested blocks, e.g.: + # <div> + # <div> + # tags for inner block must be indented. + # </div> + # </div> + # + # The outermost tags must start at the left margin for this to match, and + # the inner nested divs must be indented. + # We need to do this before the next, more liberal match, because the next + # match will start at the first `<div>` and stop at the first `</div>`. + text = self._strict_tag_block_re.sub(hash_html_block_sub, text) + + # Now match more liberally, simply from `\n<tag>` to `</tag>\n` + text = self._liberal_tag_block_re.sub(hash_html_block_sub, text) + + # Special case just for <hr />. It was easier to make a special + # case than to make the other regex more complicated. + if "<hr" in text: + _hr_tag_re = _hr_tag_re_from_tab_width(self.tab_width) + text = _hr_tag_re.sub(hash_html_block_sub, text) + + # Special case for standalone HTML comments: + if "<!--" in text: + start = 0 + while True: + # Delimiters for next comment block. + try: + start_idx = text.index("<!--", start) + except ValueError: + break + try: + end_idx = text.index("-->", start_idx) + 3 + except ValueError: + break + + # Start position for next comment block search. + start = end_idx + + # Validate whitespace before comment. + if start_idx: + # - Up to `tab_width - 1` spaces before start_idx. + for i in range(self.tab_width - 1): + if text[start_idx - 1] != ' ': + break + start_idx -= 1 + if start_idx == 0: + break + # - Must be preceded by 2 newlines or hit the start of + # the document. + if start_idx == 0: + pass + elif start_idx == 1 and text[0] == '\n': + start_idx = 0 # to match minute detail of Markdown.pl regex + elif text[start_idx-2:start_idx] == '\n\n': + pass + else: + break + + # Validate whitespace after comment. + # - Any number of spaces and tabs. + while end_idx < len(text): + if text[end_idx] not in ' \t': + break + end_idx += 1 + # - Must be following by 2 newlines or hit end of text. + if text[end_idx:end_idx+2] not in ('', '\n', '\n\n'): + continue + + # Escape and hash (must match `_hash_html_block_sub`). + html = text[start_idx:end_idx] + if raw and self.safe_mode: + html = self._sanitize_html(html) + key = _hash_text(html) + self.html_blocks[key] = html + text = text[:start_idx] + "\n\n" + key + "\n\n" + text[end_idx:] + + if "xml" in self.extras: + # Treat XML processing instructions and namespaced one-liner + # tags as if they were block HTML tags. E.g., if standalone + # (i.e. are their own paragraph), the following do not get + # wrapped in a <p> tag: + # <?foo bar?> + # + # <xi:include xmlns:xi="http://www.w3.org/2001/XInclude" href="chapter_1.md"/> + _xml_oneliner_re = _xml_oneliner_re_from_tab_width(self.tab_width) + text = _xml_oneliner_re.sub(hash_html_block_sub, text) + + return text + + def _strip_link_definitions(self, text): + # Strips link definitions from text, stores the URLs and titles in + # hash references. + less_than_tab = self.tab_width - 1 + + # Link defs are in the form: + # [id]: url "optional title" + _link_def_re = re.compile(r""" + ^[ ]{0,%d}\[(.+)\]: # id = \1 + [ \t]* + \n? # maybe *one* newline + [ \t]* + <?(.+?)>? # url = \2 + [ \t]* + (?: + \n? # maybe one newline + [ \t]* + (?<=\s) # lookbehind for whitespace + ['"(] + ([^\n]*) # title = \3 + ['")] + [ \t]* + )? # title is optional + (?:\n+|\Z) + """ % less_than_tab, re.X | re.M | re.U) + return _link_def_re.sub(self._extract_link_def_sub, text) + + def _extract_link_def_sub(self, match): + id, url, title = match.groups() + key = id.lower() # Link IDs are case-insensitive + self.urls[key] = self._encode_amps_and_angles(url) + if title: + self.titles[key] = title + return "" + + def _extract_footnote_def_sub(self, match): + id, text = match.groups() + text = _dedent(text, skip_first_line=not text.startswith('\n')).strip() + normed_id = re.sub(r'\W', '-', id) + # Ensure footnote text ends with a couple newlines (for some + # block gamut matches). + self.footnotes[normed_id] = text + "\n\n" + return "" + + def _strip_footnote_definitions(self, text): + """A footnote definition looks like this: + + [^note-id]: Text of the note. + + May include one or more indented paragraphs. + + Where, + - The 'note-id' can be pretty much anything, though typically it + is the number of the footnote. + - The first paragraph may start on the next line, like so: + + [^note-id]: + Text of the note. + """ + less_than_tab = self.tab_width - 1 + footnote_def_re = re.compile(r''' + ^[ ]{0,%d}\[\^(.+)\]: # id = \1 + [ \t]* + ( # footnote text = \2 + # First line need not start with the spaces. + (?:\s*.*\n+) + (?: + (?:[ ]{%d} | \t) # Subsequent lines must be indented. + .*\n+ + )* + ) + # Lookahead for non-space at line-start, or end of doc. + (?:(?=^[ ]{0,%d}\S)|\Z) + ''' % (less_than_tab, self.tab_width, self.tab_width), + re.X | re.M) + return footnote_def_re.sub(self._extract_footnote_def_sub, text) + + _hr_re = re.compile(r'^[ ]{0,3}([-_*][ ]{0,2}){3,}$', re.M) + + def _run_block_gamut(self, text): + # These are all the transformations that form block-level + # tags like paragraphs, headers, and list items. + + if "fenced-code-blocks" in self.extras: + text = self._do_fenced_code_blocks(text) + + text = self._do_headers(text) + + # Do Horizontal Rules: + # On the number of spaces in horizontal rules: The spec is fuzzy: "If + # you wish, you may use spaces between the hyphens or asterisks." + # Markdown.pl 1.0.1's hr regexes limit the number of spaces between the + # hr chars to one or two. We'll reproduce that limit here. + hr = "\n<hr"+self.empty_element_suffix+"\n" + text = re.sub(self._hr_re, hr, text) + + text = self._do_lists(text) + + if "pyshell" in self.extras: + text = self._prepare_pyshell_blocks(text) + if "wiki-tables" in self.extras: + text = self._do_wiki_tables(text) + if "tables" in self.extras: + text = self._do_tables(text) + + text = self._do_code_blocks(text) + + text = self._do_block_quotes(text) + + # We already ran _HashHTMLBlocks() before, in Markdown(), but that + # was to escape raw HTML in the original Markdown source. This time, + # we're escaping the markup we've just created, so that we don't wrap + # <p> tags around block-level tags. + text = self._hash_html_blocks(text) + + text = self._form_paragraphs(text) + + return text + + def _pyshell_block_sub(self, match): + lines = match.group(0).splitlines(0) + _dedentlines(lines) + indent = ' ' * self.tab_width + s = ('\n' # separate from possible cuddled paragraph + + indent + ('\n'+indent).join(lines) + + '\n\n') + return s + + def _prepare_pyshell_blocks(self, text): + """Ensure that Python interactive shell sessions are put in + code blocks -- even if not properly indented. + """ + if ">>>" not in text: + return text + + less_than_tab = self.tab_width - 1 + _pyshell_block_re = re.compile(r""" + ^([ ]{0,%d})>>>[ ].*\n # first line + ^(\1.*\S+.*\n)* # any number of subsequent lines + ^\n # ends with a blank line + """ % less_than_tab, re.M | re.X) + + return _pyshell_block_re.sub(self._pyshell_block_sub, text) + + def _table_sub(self, match): + head, underline, body = match.groups() + + # Determine aligns for columns. + cols = [cell.strip() for cell in underline.strip('| \t\n').split('|')] + align_from_col_idx = {} + for col_idx, col in enumerate(cols): + if col[0] == ':' and col[-1] == ':': + align_from_col_idx[col_idx] = ' align="center"' + elif col[0] == ':': + align_from_col_idx[col_idx] = ' align="left"' + elif col[-1] == ':': + align_from_col_idx[col_idx] = ' align="right"' + + # thead + hlines = ['<table>', '<thead>', '<tr>'] + cols = [cell.strip() for cell in head.strip('| \t\n').split('|')] + for col_idx, col in enumerate(cols): + hlines.append(' <th%s>%s</th>' % ( + align_from_col_idx.get(col_idx, ''), + self._run_span_gamut(col) + )) + hlines.append('</tr>') + hlines.append('</thead>') + + # tbody + hlines.append('<tbody>') + for line in body.strip('\n').split('\n'): + hlines.append('<tr>') + cols = [cell.strip() for cell in line.strip('| \t\n').split('|')] + for col_idx, col in enumerate(cols): + hlines.append(' <td%s>%s</td>' % ( + align_from_col_idx.get(col_idx, ''), + self._run_span_gamut(col) + )) + hlines.append('</tr>') + hlines.append('</tbody>') + hlines.append('</table>') + + return '\n'.join(hlines) + '\n' + + def _do_tables(self, text): + """Copying PHP-Markdown and GFM table syntax. Some regex borrowed from + https://github.com/michelf/php-markdown/blob/lib/Michelf/Markdown.php#L2538 + """ + less_than_tab = self.tab_width - 1 + table_re = re.compile(r''' + (?:(?<=\n\n)|\A\n?) # leading blank line + + ^[ ]{0,%d} # allowed whitespace + (.*[|].*) \n # $1: header row (at least one pipe) + + ^[ ]{0,%d} # allowed whitespace + ( # $2: underline row + # underline row with leading bar + (?: \|\ *:?-+:?\ * )+ \|? \n + | + # or, underline row without leading bar + (?: \ *:?-+:?\ *\| )+ (?: \ *:?-+:?\ * )? \n + ) + + ( # $3: data rows + (?: + ^[ ]{0,%d}(?!\ ) # ensure line begins with 0 to less_than_tab spaces + .*\|.* \n + )+ + ) + ''' % (less_than_tab, less_than_tab, less_than_tab), re.M | re.X) + return table_re.sub(self._table_sub, text) + + def _wiki_table_sub(self, match): + ttext = match.group(0).strip() + #print 'wiki table: %r' % match.group(0) + rows = [] + for line in ttext.splitlines(0): + line = line.strip()[2:-2].strip() + row = [c.strip() for c in re.split(r'(?<!\\)\|\|', line)] + rows.append(row) + #pprint(rows) + hlines = ['<table>', '<tbody>'] + for row in rows: + hrow = ['<tr>'] + for cell in row: + hrow.append('<td>') + hrow.append(self._run_span_gamut(cell)) + hrow.append('</td>') + hrow.append('</tr>') + hlines.append(''.join(hrow)) + hlines += ['</tbody>', '</table>'] + return '\n'.join(hlines) + '\n' + + def _do_wiki_tables(self, text): + # Optimization. + if "||" not in text: + return text + + less_than_tab = self.tab_width - 1 + wiki_table_re = re.compile(r''' + (?:(?<=\n\n)|\A\n?) # leading blank line + ^([ ]{0,%d})\|\|.+?\|\|[ ]*\n # first line + (^\1\|\|.+?\|\|\n)* # any number of subsequent lines + ''' % less_than_tab, re.M | re.X) + return wiki_table_re.sub(self._wiki_table_sub, text) + + def _run_span_gamut(self, text): + # These are all the transformations that occur *within* block-level + # tags like paragraphs, headers, and list items. + + text = self._do_code_spans(text) + + text = self._escape_special_chars(text) + + # Process anchor and image tags. + text = self._do_links(text) + + # Make links out of things like `<http://example.com/>` + # Must come after _do_links(), because you can use < and > + # delimiters in inline links like [this](<url>). + text = self._do_auto_links(text) + + if "link-patterns" in self.extras: + text = self._do_link_patterns(text) + + text = self._encode_amps_and_angles(text) + + text = self._do_italics_and_bold(text) + + if "smarty-pants" in self.extras: + text = self._do_smart_punctuation(text) + + # Do hard breaks: + if "break-on-newline" in self.extras: + text = re.sub(r" *\n", "<br%s\n" % self.empty_element_suffix, text) + else: + text = re.sub(r" {2,}\n", " <br%s\n" % self.empty_element_suffix, text) + + return text + + # "Sorta" because auto-links are identified as "tag" tokens. + _sorta_html_tokenize_re = re.compile(r""" + ( + # tag + </? + (?:\w+) # tag name + (?:\s+(?:[\w-]+:)?[\w-]+=(?:".*?"|'.*?'))* # attributes + \s*/?> + | + # auto-link (e.g., <http://www.activestate.com/>) + <\w+[^>]*> + | + <!--.*?--> # comment + | + <\?.*?\?> # processing instruction + ) + """, re.X) + + def _escape_special_chars(self, text): + # Python markdown note: the HTML tokenization here differs from + # that in Markdown.pl, hence the behaviour for subtle cases can + # differ (I believe the tokenizer here does a better job because + # it isn't susceptible to unmatched '<' and '>' in HTML tags). + # Note, however, that '>' is not allowed in an auto-link URL + # here. + escaped = [] + is_html_markup = False + for token in self._sorta_html_tokenize_re.split(text): + if is_html_markup: + # Within tags/HTML-comments/auto-links, encode * and _ + # so they don't conflict with their use in Markdown for + # italics and strong. We're replacing each such + # character with its corresponding MD5 checksum value; + # this is likely overkill, but it should prevent us from + # colliding with the escape values by accident. + escaped.append(token.replace('*', self._escape_table['*']) + .replace('_', self._escape_table['_'])) + else: + escaped.append(self._encode_backslash_escapes(token)) + is_html_markup = not is_html_markup + return ''.join(escaped) + + def _hash_html_spans(self, text): + # Used for safe_mode. + + def _is_auto_link(s): + if ':' in s and self._auto_link_re.match(s): + return True + elif '@' in s and self._auto_email_link_re.match(s): + return True + return False + + tokens = [] + is_html_markup = False + for token in self._sorta_html_tokenize_re.split(text): + if is_html_markup and not _is_auto_link(token): + sanitized = self._sanitize_html(token) + key = _hash_text(sanitized) + self.html_spans[key] = sanitized + tokens.append(key) + else: + tokens.append(token) + is_html_markup = not is_html_markup + return ''.join(tokens) + + def _unhash_html_spans(self, text): + for key, sanitized in list(self.html_spans.items()): + text = text.replace(key, sanitized) + return text + + def _sanitize_html(self, s): + if self.safe_mode == "replace": + return self.html_removed_text + elif self.safe_mode == "escape": + replacements = [ + ('&', '&'), + ('<', '<'), + ('>', '>'), + ] + for before, after in replacements: + s = s.replace(before, after) + return s + else: + raise MarkdownError("invalid value for 'safe_mode': %r (must be " + "'escape' or 'replace')" % self.safe_mode) + + _inline_link_title = re.compile(r''' + ( # \1 + [ \t]+ + (['"]) # quote char = \2 + (?P<title>.*?) + \2 + )? # title is optional + \)$ + ''', re.X | re.S) + _tail_of_reference_link_re = re.compile(r''' + # Match tail of: [text][id] + [ ]? # one optional space + (?:\n[ ]*)? # one optional newline followed by spaces + \[ + (?P<id>.*?) + \] + ''', re.X | re.S) + + _whitespace = re.compile(r'\s*') + + _strip_anglebrackets = re.compile(r'<(.*)>.*') + + def _find_non_whitespace(self, text, start): + """Returns the index of the first non-whitespace character in text + after (and including) start + """ + match = self._whitespace.match(text, start) + return match.end() + + def _find_balanced(self, text, start, open_c, close_c): + """Returns the index where the open_c and close_c characters balance + out - the same number of open_c and close_c are encountered - or the + end of string if it's reached before the balance point is found. + """ + i = start + l = len(text) + count = 1 + while count > 0 and i < l: + if text[i] == open_c: + count += 1 + elif text[i] == close_c: + count -= 1 + i += 1 + return i + + def _extract_url_and_title(self, text, start): + """Extracts the url and (optional) title from the tail of a link""" + # text[start] equals the opening parenthesis + idx = self._find_non_whitespace(text, start+1) + if idx == len(text): + return None, None, None + end_idx = idx + has_anglebrackets = text[idx] == "<" + if has_anglebrackets: + end_idx = self._find_balanced(text, end_idx+1, "<", ">") + end_idx = self._find_balanced(text, end_idx, "(", ")") + match = self._inline_link_title.search(text, idx, end_idx) + if not match: + return None, None, None + url, title = text[idx:match.start()], match.group("title") + if has_anglebrackets: + url = self._strip_anglebrackets.sub(r'\1', url) + return url, title, end_idx + + def _do_links(self, text): + """Turn Markdown link shortcuts into XHTML <a> and <img> tags. + + This is a combination of Markdown.pl's _DoAnchors() and + _DoImages(). They are done together because that simplified the + approach. It was necessary to use a different approach than + Markdown.pl because of the lack of atomic matching support in + Python's regex engine used in $g_nested_brackets. + """ + MAX_LINK_TEXT_SENTINEL = 3000 # markdown2 issue 24 + + # `anchor_allowed_pos` is used to support img links inside + # anchors, but not anchors inside anchors. An anchor's start + # pos must be `>= anchor_allowed_pos`. + anchor_allowed_pos = 0 + + curr_pos = 0 + while True: # Handle the next link. + # The next '[' is the start of: + # - an inline anchor: [text](url "title") + # - a reference anchor: [text][id] + # - an inline img:  + # - a reference img: ![text][id] + # - a footnote ref: [^id] + # (Only if 'footnotes' extra enabled) + # - a footnote defn: [^id]: ... + # (Only if 'footnotes' extra enabled) These have already + # been stripped in _strip_footnote_definitions() so no + # need to watch for them. + # - a link definition: [id]: url "title" + # These have already been stripped in + # _strip_link_definitions() so no need to watch for them. + # - not markup: [...anything else... + try: + start_idx = text.index('[', curr_pos) + except ValueError: + break + text_length = len(text) + + # Find the matching closing ']'. + # Markdown.pl allows *matching* brackets in link text so we + # will here too. Markdown.pl *doesn't* currently allow + # matching brackets in img alt text -- we'll differ in that + # regard. + bracket_depth = 0 + for p in range(start_idx+1, min(start_idx+MAX_LINK_TEXT_SENTINEL, + text_length)): + ch = text[p] + if ch == ']': + bracket_depth -= 1 + if bracket_depth < 0: + break + elif ch == '[': + bracket_depth += 1 + else: + # Closing bracket not found within sentinel length. + # This isn't markup. + curr_pos = start_idx + 1 + continue + link_text = text[start_idx+1:p] + + # Possibly a footnote ref? + if "footnotes" in self.extras and link_text.startswith("^"): + normed_id = re.sub(r'\W', '-', link_text[1:]) + if normed_id in self.footnotes: + self.footnote_ids.append(normed_id) + result = '<sup class="footnote-ref" id="fnref-%s">' \ + '<a href="#fn-%s">%s</a></sup>' \ + % (normed_id, normed_id, len(self.footnote_ids)) + text = text[:start_idx] + result + text[p+1:] + else: + # This id isn't defined, leave the markup alone. + curr_pos = p+1 + continue + + # Now determine what this is by the remainder. + p += 1 + if p == text_length: + return text + + # Inline anchor or img? + if text[p] == '(': # attempt at perf improvement + url, title, url_end_idx = self._extract_url_and_title(text, p) + if url is not None: + # Handle an inline anchor or img. + is_img = start_idx > 0 and text[start_idx-1] == "!" + if is_img: + start_idx -= 1 + + # We've got to encode these to avoid conflicting + # with italics/bold. + url = url.replace('*', self._escape_table['*']) \ + .replace('_', self._escape_table['_']) + if title: + title_str = ' title="%s"' % ( + _xml_escape_attr(title) + .replace('*', self._escape_table['*']) + .replace('_', self._escape_table['_'])) + else: + title_str = '' + if is_img: + img_class_str = self._html_class_str_from_tag("img") + result = '<img src="%s" alt="%s"%s%s%s' \ + % (url.replace('"', '"'), + _xml_escape_attr(link_text), + title_str, img_class_str, self.empty_element_suffix) + if "smarty-pants" in self.extras: + result = result.replace('"', self._escape_table['"']) + curr_pos = start_idx + len(result) + text = text[:start_idx] + result + text[url_end_idx:] + elif start_idx >= anchor_allowed_pos: + result_head = '<a href="%s"%s>' % (url, title_str) + result = '%s%s</a>' % (result_head, link_text) + if "smarty-pants" in self.extras: + result = result.replace('"', self._escape_table['"']) + # <img> allowed from curr_pos on, <a> from + # anchor_allowed_pos on. + curr_pos = start_idx + len(result_head) + anchor_allowed_pos = start_idx + len(result) + text = text[:start_idx] + result + text[url_end_idx:] + else: + # Anchor not allowed here. + curr_pos = start_idx + 1 + continue + + # Reference anchor or img? + else: + match = self._tail_of_reference_link_re.match(text, p) + if match: + # Handle a reference-style anchor or img. + is_img = start_idx > 0 and text[start_idx-1] == "!" + if is_img: + start_idx -= 1 + link_id = match.group("id").lower() + if not link_id: + link_id = link_text.lower() # for links like [this][] + if link_id in self.urls: + url = self.urls[link_id] + # We've got to encode these to avoid conflicting + # with italics/bold. + url = url.replace('*', self._escape_table['*']) \ + .replace('_', self._escape_table['_']) + title = self.titles.get(link_id) + if title: + before = title + title = _xml_escape_attr(title) \ + .replace('*', self._escape_table['*']) \ + .replace('_', self._escape_table['_']) + title_str = ' title="%s"' % title + else: + title_str = '' + if is_img: + img_class_str = self._html_class_str_from_tag("img") + result = '<img src="%s" alt="%s"%s%s%s' \ + % (url.replace('"', '"'), + link_text.replace('"', '"'), + title_str, img_class_str, self.empty_element_suffix) + if "smarty-pants" in self.extras: + result = result.replace('"', self._escape_table['"']) + curr_pos = start_idx + len(result) + text = text[:start_idx] + result + text[match.end():] + elif start_idx >= anchor_allowed_pos: + result = '<a href="%s"%s>%s</a>' \ + % (url, title_str, link_text) + result_head = '<a href="%s"%s>' % (url, title_str) + result = '%s%s</a>' % (result_head, link_text) + if "smarty-pants" in self.extras: + result = result.replace('"', self._escape_table['"']) + # <img> allowed from curr_pos on, <a> from + # anchor_allowed_pos on. + curr_pos = start_idx + len(result_head) + anchor_allowed_pos = start_idx + len(result) + text = text[:start_idx] + result + text[match.end():] + else: + # Anchor not allowed here. + curr_pos = start_idx + 1 + else: + # This id isn't defined, leave the markup alone. + curr_pos = match.end() + continue + + # Otherwise, it isn't markup. + curr_pos = start_idx + 1 + + return text + + def header_id_from_text(self, text, prefix, n): + """Generate a header id attribute value from the given header + HTML content. + + This is only called if the "header-ids" extra is enabled. + Subclasses may override this for different header ids. + + @param text {str} The text of the header tag + @param prefix {str} The requested prefix for header ids. This is the + value of the "header-ids" extra key, if any. Otherwise, None. + @param n {int} The <hN> tag number, i.e. `1` for an <h1> tag. + @returns {str} The value for the header tag's "id" attribute. Return + None to not have an id attribute and to exclude this header from + the TOC (if the "toc" extra is specified). + """ + header_id = _slugify(text) + if prefix and isinstance(prefix, base_string_type): + header_id = prefix + '-' + header_id + if header_id in self._count_from_header_id: + self._count_from_header_id[header_id] += 1 + header_id += '-%s' % self._count_from_header_id[header_id] + else: + self._count_from_header_id[header_id] = 1 + return header_id + + _toc = None + def _toc_add_entry(self, level, id, name): + if self._toc is None: + self._toc = [] + self._toc.append((level, id, self._unescape_special_chars(name))) + + _h_re_base = r''' + (^(.+)[ \t]*\n(=+|-+)[ \t]*\n+) + | + (^(\#{1,6}) # \1 = string of #'s + [ \t]%s + (.+?) # \2 = Header text + [ \t]* + (?<!\\) # ensure not an escaped trailing '#' + \#* # optional closing #'s (not counted) + \n+ + ) + ''' + + _h_re = re.compile(_h_re_base % '*', re.X | re.M) + _h_re_tag_friendly = re.compile(_h_re_base % '+', re.X | re.M) + + def _h_sub(self, match): + if match.group(1) is not None: + # Setext header + n = {"=": 1, "-": 2}[match.group(3)[0]] + header_group = match.group(2) + else: + # atx header + n = len(match.group(5)) + header_group = match.group(6) + + demote_headers = self.extras.get("demote-headers") + if demote_headers: + n = min(n + demote_headers, 6) + header_id_attr = "" + if "header-ids" in self.extras: + header_id = self.header_id_from_text(header_group, + self.extras["header-ids"], n) + if header_id: + header_id_attr = ' id="%s"' % header_id + html = self._run_span_gamut(header_group) + if "toc" in self.extras and header_id: + self._toc_add_entry(n, header_id, html) + return "<h%d%s>%s</h%d>\n\n" % (n, header_id_attr, html, n) + + def _do_headers(self, text): + # Setext-style headers: + # Header 1 + # ======== + # + # Header 2 + # -------- + + # atx-style headers: + # # Header 1 + # ## Header 2 + # ## Header 2 with closing hashes ## + # ... + # ###### Header 6 + + if 'tag-friendly' in self.extras: + return self._h_re_tag_friendly.sub(self._h_sub, text) + return self._h_re.sub(self._h_sub, text) + + _marker_ul_chars = '*+-' + _marker_any = r'(?:[%s]|\d+\.)' % _marker_ul_chars + _marker_ul = '(?:[%s])' % _marker_ul_chars + _marker_ol = r'(?:\d+\.)' + + def _list_sub(self, match): + lst = match.group(1) + lst_type = match.group(3) in self._marker_ul_chars and "ul" or "ol" + result = self._process_list_items(lst) + if self.list_level: + return "<%s>\n%s</%s>\n" % (lst_type, result, lst_type) + else: + return "<%s>\n%s</%s>\n\n" % (lst_type, result, lst_type) + + def _do_lists(self, text): + # Form HTML ordered (numbered) and unordered (bulleted) lists. + + # Iterate over each *non-overlapping* list match. + pos = 0 + while True: + # Find the *first* hit for either list style (ul or ol). We + # match ul and ol separately to avoid adjacent lists of different + # types running into each other (see issue #16). + hits = [] + for marker_pat in (self._marker_ul, self._marker_ol): + less_than_tab = self.tab_width - 1 + whole_list = r''' + ( # \1 = whole list + ( # \2 + [ ]{0,%d} + (%s) # \3 = first list item marker + [ \t]+ + (?!\ *\3\ ) # '- - - ...' isn't a list. See 'not_quite_a_list' test case. + ) + (?:.+?) + ( # \4 + \Z + | + \n{2,} + (?=\S) + (?! # Negative lookahead for another list item marker + [ \t]* + %s[ \t]+ + ) + ) + ) + ''' % (less_than_tab, marker_pat, marker_pat) + if self.list_level: # sub-list + list_re = re.compile("^"+whole_list, re.X | re.M | re.S) + else: + list_re = re.compile(r"(?:(?<=\n\n)|\A\n?)"+whole_list, + re.X | re.M | re.S) + match = list_re.search(text, pos) + if match: + hits.append((match.start(), match)) + if not hits: + break + hits.sort() + match = hits[0][1] + start, end = match.span() + middle = self._list_sub(match) + text = text[:start] + middle + text[end:] + pos = start + len(middle) # start pos for next attempted match + + return text + + _list_item_re = re.compile(r''' + (\n)? # leading line = \1 + (^[ \t]*) # leading whitespace = \2 + (?P<marker>%s) [ \t]+ # list marker = \3 + ((?:.+?) # list item text = \4 + (\n{1,2})) # eols = \5 + (?= \n* (\Z | \2 (?P<next_marker>%s) [ \t]+)) + ''' % (_marker_any, _marker_any), + re.M | re.X | re.S) + + _last_li_endswith_two_eols = False + def _list_item_sub(self, match): + item = match.group(4) + leading_line = match.group(1) + leading_space = match.group(2) + if leading_line or "\n\n" in item or self._last_li_endswith_two_eols: + item = self._run_block_gamut(self._outdent(item)) + else: + # Recursion for sub-lists: + item = self._do_lists(self._outdent(item)) + if item.endswith('\n'): + item = item[:-1] + item = self._run_span_gamut(item) + self._last_li_endswith_two_eols = (len(match.group(5)) == 2) + return "<li>%s</li>\n" % item + + def _process_list_items(self, list_str): + # Process the contents of a single ordered or unordered list, + # splitting it into individual list items. + + # The $g_list_level global keeps track of when we're inside a list. + # Each time we enter a list, we increment it; when we leave a list, + # we decrement. If it's zero, we're not in a list anymore. + # + # We do this because when we're not inside a list, we want to treat + # something like this: + # + # I recommend upgrading to version + # 8. Oops, now this line is treated + # as a sub-list. + # + # As a single paragraph, despite the fact that the second line starts + # with a digit-period-space sequence. + # + # Whereas when we're inside a list (or sub-list), that line will be + # treated as the start of a sub-list. What a kludge, huh? This is + # an aspect of Markdown's syntax that's hard to parse perfectly + # without resorting to mind-reading. Perhaps the solution is to + # change the syntax rules such that sub-lists must start with a + # starting cardinal number; e.g. "1." or "a.". + self.list_level += 1 + self._last_li_endswith_two_eols = False + list_str = list_str.rstrip('\n') + '\n' + list_str = self._list_item_re.sub(self._list_item_sub, list_str) + self.list_level -= 1 + return list_str + + def _get_pygments_lexer(self, lexer_name): + try: + from pygments import lexers, util + except ImportError: + return None + try: + return lexers.get_lexer_by_name(lexer_name) + except util.ClassNotFound: + return None + + def _color_with_pygments(self, codeblock, lexer, **formatter_opts): + import pygments + import pygments.formatters + + class HtmlCodeFormatter(pygments.formatters.HtmlFormatter): + def _wrap_code(self, inner): + """A function for use in a Pygments Formatter which + wraps in <code> tags. + """ + yield 0, "<code>" + for tup in inner: + yield tup + yield 0, "</code>" + + def wrap(self, source, outfile): + """Return the source with a code, pre, and div.""" + return self._wrap_div(self._wrap_pre(self._wrap_code(source))) + + formatter_opts.setdefault("cssclass", "codehilite") + formatter = HtmlCodeFormatter(**formatter_opts) + return pygments.highlight(codeblock, lexer, formatter) + + def _code_block_sub(self, match, is_fenced_code_block=False): + lexer_name = None + if is_fenced_code_block: + lexer_name = match.group(1) + if lexer_name: + formatter_opts = self.extras['fenced-code-blocks'] or {} + codeblock = match.group(2) + codeblock = codeblock[:-1] # drop one trailing newline + else: + codeblock = match.group(1) + codeblock = self._outdent(codeblock) + codeblock = self._detab(codeblock) + codeblock = codeblock.lstrip('\n') # trim leading newlines + codeblock = codeblock.rstrip() # trim trailing whitespace + + # Note: "code-color" extra is DEPRECATED. + if "code-color" in self.extras and codeblock.startswith(":::"): + lexer_name, rest = codeblock.split('\n', 1) + lexer_name = lexer_name[3:].strip() + codeblock = rest.lstrip("\n") # Remove lexer declaration line. + formatter_opts = self.extras['code-color'] or {} + + if lexer_name: + def unhash_code( codeblock ): + for key, sanitized in list(self.html_spans.items()): + codeblock = codeblock.replace(key, sanitized) + replacements = [ + ("&", "&"), + ("<", "<"), + (">", ">") + ] + for old, new in replacements: + codeblock = codeblock.replace(old, new) + return codeblock + lexer = self._get_pygments_lexer(lexer_name) + if lexer: + codeblock = unhash_code( codeblock ) + colored = self._color_with_pygments(codeblock, lexer, + **formatter_opts) + return "\n\n%s\n\n" % colored + + codeblock = self._encode_code(codeblock) + pre_class_str = self._html_class_str_from_tag("pre") + code_class_str = self._html_class_str_from_tag("code") + return "\n\n<pre%s><code%s>%s\n</code></pre>\n\n" % ( + pre_class_str, code_class_str, codeblock) + + def _html_class_str_from_tag(self, tag): + """Get the appropriate ' class="..."' string (note the leading + space), if any, for the given tag. + """ + if "html-classes" not in self.extras: + return "" + try: + html_classes_from_tag = self.extras["html-classes"] + except TypeError: + return "" + else: + if tag in html_classes_from_tag: + return ' class="%s"' % html_classes_from_tag[tag] + return "" + + def _do_code_blocks(self, text): + """Process Markdown `<pre><code>` blocks.""" + code_block_re = re.compile(r''' + (?:\n\n|\A\n?) + ( # $1 = the code block -- one or more lines, starting with a space/tab + (?: + (?:[ ]{%d} | \t) # Lines must start with a tab or a tab-width of spaces + .*\n+ + )+ + ) + ((?=^[ ]{0,%d}\S)|\Z) # Lookahead for non-space at line-start, or end of doc + # Lookahead to make sure this block isn't already in a code block. + # Needed when syntax highlighting is being used. + (?![^<]*\</code\>) + ''' % (self.tab_width, self.tab_width), + re.M | re.X) + return code_block_re.sub(self._code_block_sub, text) + + _fenced_code_block_re = re.compile(r''' + (?:\n\n|\A\n?) + ^```([\w+-]+)?[ \t]*\n # opening fence, $1 = optional lang + (.*?) # $2 = code block content + ^```[ \t]*\n # closing fence + ''', re.M | re.X | re.S) + + def _fenced_code_block_sub(self, match): + return self._code_block_sub(match, is_fenced_code_block=True); + + def _do_fenced_code_blocks(self, text): + """Process ```-fenced unindented code blocks ('fenced-code-blocks' extra).""" + return self._fenced_code_block_re.sub(self._fenced_code_block_sub, text) + + # Rules for a code span: + # - backslash escapes are not interpreted in a code span + # - to include one or or a run of more backticks the delimiters must + # be a longer run of backticks + # - cannot start or end a code span with a backtick; pad with a + # space and that space will be removed in the emitted HTML + # See `test/tm-cases/escapes.text` for a number of edge-case + # examples. + _code_span_re = re.compile(r''' + (?<!\\) + (`+) # \1 = Opening run of ` + (?!`) # See Note A test/tm-cases/escapes.text + (.+?) # \2 = The code block + (?<!`) + \1 # Matching closer + (?!`) + ''', re.X | re.S) + + def _code_span_sub(self, match): + c = match.group(2).strip(" \t") + c = self._encode_code(c) + return "<code>%s</code>" % c + + def _do_code_spans(self, text): + # * Backtick quotes are used for <code></code> spans. + # + # * You can use multiple backticks as the delimiters if you want to + # include literal backticks in the code span. So, this input: + # + # Just type ``foo `bar` baz`` at the prompt. + # + # Will translate to: + # + # <p>Just type <code>foo `bar` baz</code> at the prompt.</p> + # + # There's no arbitrary limit to the number of backticks you + # can use as delimters. If you need three consecutive backticks + # in your code, use four for delimiters, etc. + # + # * You can use spaces to get literal backticks at the edges: + # + # ... type `` `bar` `` ... + # + # Turns to: + # + # ... type <code>`bar`</code> ... + return self._code_span_re.sub(self._code_span_sub, text) + + def _encode_code(self, text): + """Encode/escape certain characters inside Markdown code runs. + The point is that in code, these characters are literals, + and lose their special Markdown meanings. + """ + replacements = [ + # Encode all ampersands; HTML entities are not + # entities within a Markdown code span. + ('&', '&'), + # Do the angle bracket song and dance: + ('<', '<'), + ('>', '>'), + ] + for before, after in replacements: + text = text.replace(before, after) + hashed = _hash_text(text) + self._escape_table[text] = hashed + return hashed + + _strong_re = re.compile(r"(\*\*|__)(?=\S)(.+?[*_]*)(?<=\S)\1", re.S) + _em_re = re.compile(r"(\*|_)(?=\S)(.+?)(?<=\S)\1", re.S) + _code_friendly_strong_re = re.compile(r"\*\*(?=\S)(.+?[*_]*)(?<=\S)\*\*", re.S) + _code_friendly_em_re = re.compile(r"\*(?=\S)(.+?)(?<=\S)\*", re.S) + def _do_italics_and_bold(self, text): + # <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) + else: + text = self._strong_re.sub(r"<strong>\2</strong>", text) + text = self._em_re.sub(r"<em>\2</em>", text) + return text + + # "smarty-pants" extra: Very liberal in interpreting a single prime as an + # apostrophe; e.g. ignores the fact that "round", "bout", "twer", and + # "twixt" can be written without an initial apostrophe. This is fine because + # using scare quotes (single quotation marks) is rare. + _apostrophe_year_re = re.compile(r"'(\d\d)(?=(\s|,|;|\.|\?|!|$))") + _contractions = ["tis", "twas", "twer", "neath", "o", "n", + "round", "bout", "twixt", "nuff", "fraid", "sup"] + def _do_smart_contractions(self, text): + text = self._apostrophe_year_re.sub(r"’\1", text) + for c in self._contractions: + text = text.replace("'%s" % c, "’%s" % c) + text = text.replace("'%s" % c.capitalize(), + "’%s" % c.capitalize()) + return text + + # Substitute double-quotes before single-quotes. + _opening_single_quote_re = re.compile(r"(?<!\S)'(?=\S)") + _opening_double_quote_re = re.compile(r'(?<!\S)"(?=\S)') + _closing_single_quote_re = re.compile(r"(?<=\S)'") + _closing_double_quote_re = re.compile(r'(?<=\S)"(?=(\s|,|;|\.|\?|!|$))') + def _do_smart_punctuation(self, text): + """Fancifies 'single quotes', "double quotes", and apostrophes. + Converts --, ---, and ... into en dashes, em dashes, and ellipses. + + Inspiration is: <http://daringfireball.net/projects/smartypants/> + See "test/tm-cases/smarty_pants.text" for a full discussion of the + support here and + <http://code.google.com/p/python-markdown2/issues/detail?id=42> for a + discussion of some diversion from the original SmartyPants. + """ + if "'" in text: # guard for perf + text = self._do_smart_contractions(text) + text = self._opening_single_quote_re.sub("‘", text) + text = self._closing_single_quote_re.sub("’", text) + + if '"' in text: # guard for perf + text = self._opening_double_quote_re.sub("“", text) + text = self._closing_double_quote_re.sub("”", text) + + text = text.replace("---", "—") + text = text.replace("--", "–") + text = text.replace("...", "…") + text = text.replace(" . . . ", "…") + text = text.replace(". . .", "…") + return text + + _block_quote_re = re.compile(r''' + ( # Wrap whole match in \1 + ( + ^[ \t]*>[ \t]? # '>' at the start of a line + .+\n # rest of the first line + (.+\n)* # subsequent consecutive lines + \n* # blanks + )+ + ) + ''', re.M | re.X) + _bq_one_level_re = re.compile('^[ \t]*>[ \t]?', re.M); + + _html_pre_block_re = re.compile(r'(\s*<pre>.+?</pre>)', re.S) + def _dedent_two_spaces_sub(self, match): + return re.sub(r'(?m)^ ', '', match.group(1)) + + def _block_quote_sub(self, match): + bq = match.group(1) + bq = self._bq_one_level_re.sub('', bq) # trim one level of quoting + bq = self._ws_only_line_re.sub('', bq) # trim whitespace-only lines + bq = self._run_block_gamut(bq) # recurse + + bq = re.sub('(?m)^', ' ', bq) + # These leading spaces screw with <pre> content, so we need to fix that: + bq = self._html_pre_block_re.sub(self._dedent_two_spaces_sub, bq) + + return "<blockquote>\n%s\n</blockquote>\n\n" % bq + + def _do_block_quotes(self, text): + if '>' not in text: + return text + return self._block_quote_re.sub(self._block_quote_sub, text) + + def _form_paragraphs(self, text): + # Strip leading and trailing lines: + text = text.strip('\n') + + # Wrap <p> tags. + grafs = [] + for i, graf in enumerate(re.split(r"\n{2,}", text)): + if graf in self.html_blocks: + # Unhashify HTML blocks + grafs.append(self.html_blocks[graf]) + else: + cuddled_list = None + if "cuddled-lists" in self.extras: + # Need to put back trailing '\n' for `_list_item_re` + # match at the end of the paragraph. + li = self._list_item_re.search(graf + '\n') + # Two of the same list marker in this paragraph: a likely + # candidate for a list cuddled to preceding paragraph + # text (issue 33). Note the `[-1]` is a quick way to + # consider numeric bullets (e.g. "1." and "2.") to be + # equal. + if (li and len(li.group(2)) <= 3 and li.group("next_marker") + and li.group("marker")[-1] == li.group("next_marker")[-1]): + start = li.start() + cuddled_list = self._do_lists(graf[start:]).rstrip("\n") + assert cuddled_list.startswith("<ul>") or cuddled_list.startswith("<ol>") + graf = graf[:start] + + # Wrap <p> tags. + graf = self._run_span_gamut(graf) + grafs.append("<p>" + graf.lstrip(" \t") + "</p>") + + if cuddled_list: + grafs.append(cuddled_list) + + return "\n\n".join(grafs) + + def _add_footnotes(self, text): + if self.footnotes: + footer = [ + '<div class="footnotes">', + '<hr' + self.empty_element_suffix, + '<ol>', + ] + for i, id in enumerate(self.footnote_ids): + if i != 0: + footer.append('') + footer.append('<li id="fn-%s">' % id) + footer.append(self._run_block_gamut(self.footnotes[id])) + backlink = ('<a href="#fnref-%s" ' + 'class="footnoteBackLink" ' + 'title="Jump back to footnote %d in the text.">' + '↩</a>' % (id, i+1)) + if footer[-1].endswith("</p>"): + footer[-1] = footer[-1][:-len("</p>")] \ + + ' ' + backlink + "</p>" + else: + footer.append("\n<p>%s</p>" % backlink) + footer.append('</li>') + footer.append('</ol>') + footer.append('</div>') + return text + '\n\n' + '\n'.join(footer) + else: + return text + + # Ampersand-encoding based entirely on Nat Irons's Amputator MT plugin: + # http://bumppo.net/projects/amputator/ + _ampersand_re = re.compile(r'&(?!#?[xX]?(?:[0-9a-fA-F]+|\w+);)') + _naked_lt_re = re.compile(r'<(?![a-z/?\$!])', re.I) + _naked_gt_re = re.compile(r'''(?<![a-z0-9?!/'"-])>''', re.I) + + def _encode_amps_and_angles(self, text): + # Smart processing for ampersands and angle brackets that need + # to be encoded. + text = self._ampersand_re.sub('&', text) + + # Encode naked <'s + text = self._naked_lt_re.sub('<', text) + + # Encode naked >'s + # Note: Other markdown implementations (e.g. Markdown.pl, PHP + # Markdown) don't do this. + text = self._naked_gt_re.sub('>', text) + return text + + def _encode_backslash_escapes(self, text): + for ch, escape in list(self._escape_table.items()): + text = text.replace("\\"+ch, escape) + return text + + _auto_link_re = re.compile(r'<((https?|ftp):[^\'">\s]+)>', re.I) + def _auto_link_sub(self, match): + g1 = match.group(1) + return '<a href="%s">%s</a>' % (g1, g1) + + _auto_email_link_re = re.compile(r""" + < + (?:mailto:)? + ( + [-.\w]+ + \@ + [-\w]+(\.[-\w]+)*\.[a-z]+ + ) + > + """, re.I | re.X | re.U) + def _auto_email_link_sub(self, match): + return self._encode_email_address( + self._unescape_special_chars(match.group(1))) + + def _do_auto_links(self, text): + text = self._auto_link_re.sub(self._auto_link_sub, text) + text = self._auto_email_link_re.sub(self._auto_email_link_sub, text) + return text + + def _encode_email_address(self, addr): + # Input: an email address, e.g. "foo@example.com" + # + # Output: the email address as a mailto link, with each character + # of the address encoded as either a decimal or hex entity, in + # the hopes of foiling most address harvesting spam bots. E.g.: + # + # <a href="mailto:foo@e + # xample.com">foo + # @example.com</a> + # + # Based on a filter by Matthew Wickline, posted to the BBEdit-Talk + # mailing list: <http://tinyurl.com/yu7ue> + chars = [_xml_encode_email_char_at_random(ch) + for ch in "mailto:" + addr] + # Strip the mailto: from the visible part. + addr = '<a href="%s">%s</a>' \ + % (''.join(chars), ''.join(chars[7:])) + return addr + + def _do_link_patterns(self, text): + """Caveat emptor: there isn't much guarding against link + patterns being formed inside other standard Markdown links, e.g. + inside a [link def][like this]. + + Dev Notes: *Could* consider prefixing regexes with a negative + lookbehind assertion to attempt to guard against this. + """ + link_from_hash = {} + for regex, repl in self.link_patterns: + replacements = [] + for match in regex.finditer(text): + if hasattr(repl, "__call__"): + href = repl(match) + else: + href = match.expand(repl) + replacements.append((match.span(), href)) + for (start, end), href in reversed(replacements): + escaped_href = ( + href.replace('"', '"') # b/c of attr quote + # To avoid markdown <em> and <strong>: + .replace('*', self._escape_table['*']) + .replace('_', self._escape_table['_'])) + link = '<a href="%s">%s</a>' % (escaped_href, text[start:end]) + hash = _hash_text(link) + link_from_hash[hash] = link + text = text[:start] + hash + text[end:] + for hash, link in list(link_from_hash.items()): + text = text.replace(hash, link) + return text + + def _unescape_special_chars(self, text): + # Swap back in all the special characters we've hidden. + for ch, hash in list(self._escape_table.items()): + text = text.replace(hash, ch) + return text + + def _outdent(self, text): + # Remove one level of line-leading tabs or spaces + return self._outdent_re.sub('', text) + + +class MarkdownWithExtras(Markdown): + """A markdowner class that enables most extras: + + - footnotes + - code-color (only has effect if 'pygments' Python module on path) + + These are not included: + - pyshell (specific to Python-related documenting) + - code-friendly (because it *disables* part of the syntax) + - link-patterns (because you need to specify some actual + link-patterns anyway) + """ + extras = ["footnotes", "code-color"] + + +#---- internal support functions + +class UnicodeWithAttrs(unicode): + """A subclass of unicode used for the return value of conversion to + possibly attach some attributes. E.g. the "toc_html" attribute when + the "toc" extra is used. + """ + metadata = None + _toc = None + def toc_html(self): + """Return the HTML for the current TOC. + + This expects the `_toc` attribute to have been set on this instance. + """ + if self._toc is None: + return None + + def indent(): + return ' ' * (len(h_stack) - 1) + lines = [] + h_stack = [0] # stack of header-level numbers + for level, id, name in self._toc: + if level > h_stack[-1]: + lines.append("%s<ul>" % indent()) + h_stack.append(level) + elif level == h_stack[-1]: + lines[-1] += "</li>" + else: + while level < h_stack[-1]: + h_stack.pop() + if not lines[-1].endswith("</li>"): + lines[-1] += "</li>" + lines.append("%s</ul></li>" % indent()) + lines.append('%s<li><a href="#%s">%s</a>' % ( + indent(), id, name)) + while len(h_stack) > 1: + h_stack.pop() + if not lines[-1].endswith("</li>"): + lines[-1] += "</li>" + lines.append("%s</ul>" % indent()) + return '\n'.join(lines) + '\n' + toc_html = property(toc_html) + +## {{{ http://code.activestate.com/recipes/577257/ (r1) +_slugify_strip_re = re.compile(r'[^\w\s-]') +_slugify_hyphenate_re = re.compile(r'[-\s]+') +def _slugify(value): + """ + Normalizes string, converts to lowercase, removes non-alpha characters, + and converts spaces to hyphens. + + From Django's "django/template/defaultfilters.py". + """ + import unicodedata + value = unicodedata.normalize('NFKD', value).encode('ascii', 'ignore').decode() + value = _slugify_strip_re.sub('', value).strip().lower() + return _slugify_hyphenate_re.sub('-', value) +## end of http://code.activestate.com/recipes/577257/ }}} + + +# From http://aspn.activestate.com/ASPN/Cookbook/Python/Recipe/52549 +def _curry(*args, **kwargs): + function, args = args[0], args[1:] + def result(*rest, **kwrest): + combined = kwargs.copy() + combined.update(kwrest) + return function(*args + rest, **combined) + return result + +# Recipe: regex_from_encoded_pattern (1.0) +def _regex_from_encoded_pattern(s): + """'foo' -> re.compile(re.escape('foo')) + '/foo/' -> re.compile('foo') + '/foo/i' -> re.compile('foo', re.I) + """ + if s.startswith('/') and s.rfind('/') != 0: + # Parse it: /PATTERN/FLAGS + idx = s.rfind('/') + pattern, flags_str = s[1:idx], s[idx+1:] + flag_from_char = { + "i": re.IGNORECASE, + "l": re.LOCALE, + "s": re.DOTALL, + "m": re.MULTILINE, + "u": re.UNICODE, + } + flags = 0 + for char in flags_str: + try: + flags |= flag_from_char[char] + except KeyError: + raise ValueError("unsupported regex flag: '%s' in '%s' " + "(must be one of '%s')" + % (char, s, ''.join(list(flag_from_char.keys())))) + return re.compile(s[1:idx], flags) + else: # not an encoded regex + return re.compile(re.escape(s)) + +# Recipe: dedent (0.1.2) +def _dedentlines(lines, tabsize=8, skip_first_line=False): + """_dedentlines(lines, tabsize=8, skip_first_line=False) -> dedented lines + + "lines" is a list of lines to dedent. + "tabsize" is the tab width to use for indent width calculations. + "skip_first_line" is a boolean indicating if the first line should + be skipped for calculating the indent width and for dedenting. + This is sometimes useful for docstrings and similar. + + Same as dedent() except operates on a sequence of lines. Note: the + lines list is modified **in-place**. + """ + DEBUG = False + if DEBUG: + print("dedent: dedent(..., tabsize=%d, skip_first_line=%r)"\ + % (tabsize, skip_first_line)) + indents = [] + margin = None + for i, line in enumerate(lines): + if i == 0 and skip_first_line: continue + indent = 0 + for ch in line: + if ch == ' ': + indent += 1 + elif ch == '\t': + indent += tabsize - (indent % tabsize) + elif ch in '\r\n': + continue # skip all-whitespace lines + else: + break + else: + continue # skip all-whitespace lines + if DEBUG: print("dedent: indent=%d: %r" % (indent, line)) + if margin is None: + margin = indent + else: + margin = min(margin, indent) + if DEBUG: print("dedent: margin=%r" % margin) + + if margin is not None and margin > 0: + for i, line in enumerate(lines): + if i == 0 and skip_first_line: continue + removed = 0 + for j, ch in enumerate(line): + if ch == ' ': + removed += 1 + elif ch == '\t': + removed += tabsize - (removed % tabsize) + elif ch in '\r\n': + if DEBUG: print("dedent: %r: EOL -> strip up to EOL" % line) + lines[i] = lines[i][j:] + break + else: + raise ValueError("unexpected non-whitespace char %r in " + "line %r while removing %d-space margin" + % (ch, line, margin)) + if DEBUG: + print("dedent: %r: %r -> removed %d/%d"\ + % (line, ch, removed, margin)) + if removed == margin: + lines[i] = lines[i][j+1:] + break + elif removed > margin: + lines[i] = ' '*(removed-margin) + lines[i][j+1:] + break + else: + if removed: + lines[i] = lines[i][removed:] + return lines + +def _dedent(text, tabsize=8, skip_first_line=False): + """_dedent(text, tabsize=8, skip_first_line=False) -> dedented text + + "text" is the text to dedent. + "tabsize" is the tab width to use for indent width calculations. + "skip_first_line" is a boolean indicating if the first line should + be skipped for calculating the indent width and for dedenting. + This is sometimes useful for docstrings and similar. + + textwrap.dedent(s), but don't expand tabs to spaces + """ + lines = text.splitlines(1) + _dedentlines(lines, tabsize=tabsize, skip_first_line=skip_first_line) + return ''.join(lines) + + +class _memoized(object): + """Decorator that caches a function's return value each time it is called. + If called later with the same arguments, the cached value is returned, and + not re-evaluated. + + http://wiki.python.org/moin/PythonDecoratorLibrary + """ + def __init__(self, func): + self.func = func + self.cache = {} + def __call__(self, *args): + try: + return self.cache[args] + except KeyError: + self.cache[args] = value = self.func(*args) + return value + except TypeError: + # uncachable -- for instance, passing a list as an argument. + # Better to not cache than to blow up entirely. + return self.func(*args) + def __repr__(self): + """Return the function's docstring.""" + return self.func.__doc__ + + +def _xml_oneliner_re_from_tab_width(tab_width): + """Standalone XML processing instruction regex.""" + return re.compile(r""" + (?: + (?<=\n\n) # Starting after a blank line + | # or + \A\n? # the beginning of the doc + ) + ( # save in $1 + [ ]{0,%d} + (?: + <\?\w+\b\s+.*?\?> # XML processing instruction + | + <\w+:\w+\b\s+.*?/> # namespaced single tag + ) + [ \t]* + (?=\n{2,}|\Z) # followed by a blank line or end of document + ) + """ % (tab_width - 1), re.X) +_xml_oneliner_re_from_tab_width = _memoized(_xml_oneliner_re_from_tab_width) + +def _hr_tag_re_from_tab_width(tab_width): + return re.compile(r""" + (?: + (?<=\n\n) # Starting after a blank line + | # or + \A\n? # the beginning of the doc + ) + ( # save in \1 + [ ]{0,%d} + <(hr) # start tag = \2 + \b # word break + ([^<>])*? # + /?> # the matching end tag + [ \t]* + (?=\n{2,}|\Z) # followed by a blank line or end of document + ) + """ % (tab_width - 1), re.X) +_hr_tag_re_from_tab_width = _memoized(_hr_tag_re_from_tab_width) + + +def _xml_escape_attr(attr, skip_single_quote=True): + """Escape the given string for use in an HTML/XML tag attribute. + + By default this doesn't bother with escaping `'` to `'`, presuming that + the tag attribute is surrounded by double quotes. + """ + escaped = (attr + .replace('&', '&') + .replace('"', '"') + .replace('<', '<') + .replace('>', '>')) + if not skip_single_quote: + escaped = escaped.replace("'", "'") + return escaped + + +def _xml_encode_email_char_at_random(ch): + r = random() + # Roughly 10% raw, 45% hex, 45% dec. + # '@' *must* be encoded. I [John Gruber] insist. + # Issue 26: '_' must be encoded. + if r > 0.9 and ch not in "@_": + return ch + elif r < 0.45: + # The [1:] is to drop leading '0': 0x63 -> x63 + return '&#%s;' % hex(ord(ch))[1:] + else: + return '&#%s;' % ord(ch) + + + +#---- mainline + +class _NoReflowFormatter(optparse.IndentedHelpFormatter): + """An optparse formatter that does NOT reflow the description.""" + def format_description(self, description): + return description or "" + +def _test(): + import doctest + doctest.testmod() + +def main(argv=None): + if argv is None: + argv = sys.argv + if not logging.root.handlers: + logging.basicConfig() + + usage = "usage: %prog [PATHS...]" + version = "%prog "+__version__ + parser = optparse.OptionParser(prog="markdown2", usage=usage, + version=version, description=cmdln_desc, + formatter=_NoReflowFormatter()) + parser.add_option("-v", "--verbose", dest="log_level", + action="store_const", const=logging.DEBUG, + help="more verbose output") + parser.add_option("--encoding", + help="specify encoding of text content") + parser.add_option("--html4tags", action="store_true", default=False, + help="use HTML 4 style for empty element tags") + parser.add_option("-s", "--safe", metavar="MODE", dest="safe_mode", + help="sanitize literal HTML: 'escape' escapes " + "HTML meta chars, 'replace' replaces with an " + "[HTML_REMOVED] note") + parser.add_option("-x", "--extras", action="append", + help="Turn on specific extra features (not part of " + "the core Markdown spec). See above.") + parser.add_option("--use-file-vars", + help="Look for and use Emacs-style 'markdown-extras' " + "file var to turn on extras. See " + "<https://github.com/trentm/python-markdown2/wiki/Extras>") + parser.add_option("--link-patterns-file", + help="path to a link pattern file") + parser.add_option("--self-test", action="store_true", + help="run internal self-tests (some doctests)") + parser.add_option("--compare", action="store_true", + help="run against Markdown.pl as well (for testing)") + parser.set_defaults(log_level=logging.INFO, compare=False, + encoding="utf-8", safe_mode=None, use_file_vars=False) + opts, paths = parser.parse_args() + log.setLevel(opts.log_level) + + if opts.self_test: + return _test() + + if opts.extras: + extras = {} + for s in opts.extras: + splitter = re.compile("[,;: ]+") + for e in splitter.split(s): + if '=' in e: + ename, earg = e.split('=', 1) + try: + earg = int(earg) + except ValueError: + pass + else: + ename, earg = e, None + extras[ename] = earg + else: + extras = None + + if opts.link_patterns_file: + link_patterns = [] + f = open(opts.link_patterns_file) + try: + for i, line in enumerate(f.readlines()): + if not line.strip(): continue + if line.lstrip().startswith("#"): continue + try: + pat, href = line.rstrip().rsplit(None, 1) + except ValueError: + raise MarkdownError("%s:%d: invalid link pattern line: %r" + % (opts.link_patterns_file, i+1, line)) + link_patterns.append( + (_regex_from_encoded_pattern(pat), href)) + finally: + f.close() + else: + link_patterns = None + + from os.path import join, dirname, abspath, exists + markdown_pl = join(dirname(dirname(abspath(__file__))), "test", + "Markdown.pl") + if not paths: + paths = ['-'] + for path in paths: + if path == '-': + text = sys.stdin.read() + else: + fp = codecs.open(path, 'r', opts.encoding) + text = fp.read() + fp.close() + if opts.compare: + from subprocess import Popen, PIPE + print("==== Markdown.pl ====") + p = Popen('perl %s' % markdown_pl, shell=True, stdin=PIPE, stdout=PIPE, close_fds=True) + p.stdin.write(text.encode('utf-8')) + p.stdin.close() + perl_html = p.stdout.read().decode('utf-8') + if py3: + sys.stdout.write(perl_html) + else: + sys.stdout.write(perl_html.encode( + sys.stdout.encoding or "utf-8", 'xmlcharrefreplace')) + print("==== markdown2.py ====") + html = markdown(text, + html4tags=opts.html4tags, + safe_mode=opts.safe_mode, + extras=extras, link_patterns=link_patterns, + use_file_vars=opts.use_file_vars) + if py3: + sys.stdout.write(html) + else: + sys.stdout.write(html.encode( + sys.stdout.encoding or "utf-8", 'xmlcharrefreplace')) + if extras and "toc" in extras: + log.debug("toc_html: " + + html.toc_html.encode(sys.stdout.encoding or "utf-8", 'xmlcharrefreplace')) + if opts.compare: + test_dir = join(dirname(dirname(abspath(__file__))), "test") + if exists(join(test_dir, "test_markdown2.py")): + sys.path.insert(0, test_dir) + from test_markdown2 import norm_html_from_html + norm_html = norm_html_from_html(html) + norm_perl_html = norm_html_from_html(perl_html) + else: + norm_html = html + norm_perl_html = perl_html + print("==== match? %r ====" % (norm_perl_html == norm_html)) + + +if __name__ == "__main__": + sys.exit( main(sys.argv) )
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/Markdown/test Tue Oct 07 08:41:30 2014 -0400 @@ -0,0 +1,1 @@ +hi
--- a/README.md Tue Sep 30 09:56:12 2014 -0400 +++ b/README.md Tue Oct 07 08:41:30 2014 -0400 @@ -10,15 +10,21 @@ email: s.hiltemann@erasmusmc.nl +Installation Instructions +-------------------------- +This package uses (but does not install) Bash, Perl and Python. + +If Pandoc ((johnmacfarlane.net/pandoc/index.html)) is installed on your system PATH (command 'pandoc'), any MarkDown text items will be rendered using Pandoc (allows many markdown syntax extensions). +If Pandoc is not present, a simple markdown conversion script is used (only handles vanilla syntax). -Planned changes +TODOs --------------- - ~~option to download iReport webpage~~ -- more pluggable code to add content item types etc. -- markdown instead of plain text/html in text fields. -- multiple columns in table converted to weblinks. -- table colums link to archive files in history +- ~~markdown instead of plain text/html in text fields.~~ +- Support for large tables +- Multiple columns in table converted to weblinks. +- Table colums link to archive files in history - .. -- ..suggestions anyone? +- ..suggestions?
--- a/createHTML.sh Tue Sep 30 09:56:12 2014 -0400 +++ b/createHTML.sh Tue Oct 07 08:41:30 2014 -0400 @@ -1,3 +1,6 @@ +## +## Create Cover Page +## function makeIntroPage ( ){ echo "Creating Intro Page" title="$1" @@ -11,7 +14,6 @@ <head> </head> <body> - <!-- dummy intro page, since first page will not have any javascript/css features enabled unless specified in universe_wsgi.ini file, but subsequent pages will --> <br/> <br/> <center> @@ -27,76 +29,138 @@ } - +## +## Create HTML content for the tabs specified by user +## function makeTabContent ( ){ - tab=$1 #name of current tab - itemslist=$2 #list of all items - contentline="<br/>" - imgcount=0 - #echo -e "\n Creating items. itemslist: $itemslist" + tab=$1 # name of current tab + itemslist=$2 # list of all items + contentline="" # HTML code for tab + imgcount=0 # keep track of the number of images on the current tab for item in $itemslist do - #echo -e "\n -> item : $item" + ## Parse items lists item=${item/::/:emptycol:} declare -a myarr=(`echo $item |sed 's/:/ /g'`) - #echo "break: ${myarr[3]}" + + ## Create the tab contents HTML code if [ ${myarr[0]} == $tab ] then - ## add contents of text field to page#### + ## + ## Text Field + ## if [ ${myarr[1]} == "text" ] then text=${myarr[2]} - ## allow some html formatting tags - text=${text//==lt==strong==gt==/<strong>} # search for strong tags - text=${text//==lt====slash==strong==gt==/<\/strong>} # search for strong tags - text=${text//==lt==em==gt==/<em>} # search for strong tags - text=${text//==lt====slash==em==gt==/<\/em>} # search for strong tags + md=${myarr[4]} - text=${text//==lt==b==gt==/<strong>} # search for strong tags - text=${text//==lt====slash==b==gt==/<\/strong>} # search for strong tags - text=${text//==lt==i==gt==/<em>} # search for strong tags - text=${text//==lt====slash==i==gt==/<\/em>} # search for strong tags + # if markdown, convert to html + if [ $md == "Y" ] + then + ## resubstitute sanitized charachters + text=${text//==space==/ } + text=${text//==colon==/:} + text=${text//==comma==/,} + text=${text//==slash==/\/} + text=${text//==lt==/<} + text=${text//==gt==/>} + text=${text//==apos==/\'} + text=${text//==quote==/\"} + text=${text//==backtick==/\`} + text=${text//==dollar==/$} + text=${text//==bar==/|} + text=${text//&&/&} + text=${text//\\n/\\n} + text=${text//\\t/\\t} + text=${text//\&r\&n/\\n} + text=${text//\&r/\\n} + text=${text//\&n/\\n} + text=${text//\&c/:} + + + ## convert markdown in textfield to html + echo -e "$text" > mytext.md + + if [ -z `type -p pandoc` ] + then + # pandoc missing + ${repositorypath}/Markdown/markdown2.py mytext.md > mytext.html + + else + # pandoc exists + echo "pandoc exists" + pandoc -o mytext.html mytext.md + pandoc -o standalone.html -s mytext.md + + #get css generated by pandoc and add as scoped attribute (HTML5) + pandocstyle=`sed -n '/<style/,/style>/p' standalone.html` + fi + + markdowntext=$(cat mytext.html) + contentline="${contentline}\n<div class=\"markdown-body\">${pandocstyle} ${markdowntext}</div>\n" + + else # If not markdown, print verbatim (with exception of few html tags) - text=${text//==lt==br==gt==/<br\/>} # search for strong tags - text=${text//==lt====br==slash==gt==/<br\/>} # search for strong tags - text=${text//==lt==h1==gt==/<h1>} # search for h1-h6 tags - text=${text//==lt==h2==gt==/<h2>} # search for h1-h6 tags - text=${text//==lt==h3==gt==/<h3>} # search for h1-h6 tags - text=${text//==lt==h4==gt==/<h4>} # search for h1-h6 tags - text=${text//==lt==h5==gt==/<h5>} # search for h1-h6 tags - text=${text//==lt==h6==gt==/<h6>} # search for h1-h6 tags - text=${text//==lt====slash==h1==gt==/<\/h1>} # search for h1-h6 closing tags - text=${text//==lt====slash==h2==gt==/<\/h2>} # search for h1-h6 closing tags - text=${text//==lt====slash==h3==gt==/<\/h3>} # search for h1-h6 closing tags - text=${text//==lt====slash==h4==gt==/<\/h4>} # search for h1-h6 closing tags - text=${text//==lt====slash==h5==gt==/<\/h5>} # search for h1-h6 closing tags - text=${text//==lt====slaxh==h6==gt==/<\/h6>} # search for h1-h6 closing tags + ## allow some html formatting tags + text=${text//==lt==strong==gt==/<strong>} # search for strong tags + text=${text//==lt====slash==strong==gt==/<\/strong>} # search for strong tags + text=${text//==lt==em==gt==/<em>} # search for strong tags + text=${text//==lt====slash==em==gt==/<\/em>} # search for strong tags + + text=${text//==lt==b==gt==/<strong>} # search for strong tags + text=${text//==lt====slash==b==gt==/<\/strong>} # search for strong tags + text=${text//==lt==i==gt==/<em>} # search for strong tags + text=${text//==lt====slash==i==gt==/<\/em>} # search for strong tags + + text=${text//==lt==br==gt==/<br\/>} # search for strong tags + text=${text//==lt====br==slash==gt==/<br\/>} # search for strong tags + text=${text//==lt==h1==gt==/<h1>} # search for h1-h6 tags + text=${text//==lt==h2==gt==/<h2>} # search for h1-h6 tags + text=${text//==lt==h3==gt==/<h3>} # search for h1-h6 tags + text=${text//==lt==h4==gt==/<h4>} # search for h1-h6 tags + text=${text//==lt==h5==gt==/<h5>} # search for h1-h6 tags + text=${text//==lt==h6==gt==/<h6>} # search for h1-h6 tags + text=${text//==lt====slash==h1==gt==/<\/h1>} # search for h1-h6 closing tags + text=${text//==lt====slash==h2==gt==/<\/h2>} # search for h1-h6 closing tags + text=${text//==lt====slash==h3==gt==/<\/h3>} # search for h1-h6 closing tags + text=${text//==lt====slash==h4==gt==/<\/h4>} # search for h1-h6 closing tags + text=${text//==lt====slash==h5==gt==/<\/h5>} # search for h1-h6 closing tags + text=${text//==lt====slaxh==h6==gt==/<\/h6>} # search for h1-h6 closing tags + + ## display everything else verbatim + text=${text//==space==/ } + text=${text//==colon==/:} + text=${text//==comma==/,} + text=${text//==slash==/\/} + text=${text//==lt==/<} + text=${text//==gt==/>} + text=${text//==apos==/'} + text=${text//==quote==/"} + text=${text//&&/&} + text=${text//\\n/<br/>} + text=${text//\\t/ } + text=${text//\&r\&n/<br/>} + text=${text//\&r/<br/>} + text=${text//\&n/<br/>} + text=${text//\&c/:} + text=${text//==backtick==/`} + text=${text//==dollar==/$} + text=${text//==bar==/|} + contentline="${contentline}\n${text}\n" + fi - ## display everything else verbatim - text=${text//==space==/ } - text=${text//==colon==/:} - text=${text//==comma==/,} - text=${text//==slash==/\/} - text=${text//==lt==/<} - text=${text//==gt==/>} - text=${text//==apos==/'} - text=${text//==quote==/"} - text=${text//&&/&} - text=${text//\\n/<br/>} - text=${text//\\t/ } - text=${text//\&r\&n/<br/>} - text=${text//\&r/<br/>} - text=${text//\&n/<br/>} - text=${text//\&c/:} - contentline="${contentline}${text}" + fi - ## add contents of a text file to page + ## + ## Text File + ## if [ ${myarr[1]} == "textfile" ] then tfile=${myarr[2]} + md=${myarr[4]} fname=`basename ${tfile}` fname=${fname%.*} fname="${fname}.txt" @@ -106,11 +170,37 @@ numlines=`wc -l ${tfile} | cut -d" " -f1` minheight=$[$numlines*17] - contentline="${contentline}<iframe class=\"invisibleframe\" src=\"${fname}\" width=\"100%\" height=\"$minheight\"> </iframe>" + # if markdown, convert to html + if [ $md == "Y" ] + then + + if [ -z `type -p pandoc` ] + then + # pandoc missing + ${repositorypath}/Markdown/markdown2.py ${tfile} > mytext.html + + else + # pandoc exists + pandoc -o mytext.html ${tfile} + pandoc -o standalone.html -s ${tfile} + + # get css generated by pandoc and add as scoped attribute (HTML5) + pandocstyle=`sed -n '/<style/,/style>/p' standalone.html` + + fi + + markdowntext=$(cat mytext.html) + contentline="${contentline}\n<div class=\"markdown-body\">${pandocstyle} ${markdowntext}</div>\n" + else + contentline="${contentline}\n<iframe class=\"invisibleframe\" src=\"${fname}\" width=\"100%\" height=\"$minheight\"> </iframe>\n" + fi fi - ## add image file to page + ## + ## Image + ## if [ ${myarr[1]} == "image" ] + then imgcount=$[$imgcount+1] #restore file suffix for html @@ -165,6 +255,10 @@ fi fi + + ## + ## Table + ## if [ ${myarr[1]} == "table" ] then maxlines=50000 @@ -223,8 +317,7 @@ print $0 } }END{}' ${tsvfile} > ${tsvfile}2 - #echo "converted file: " - #cat ${tsvfile}2 + else cp ${tsvfile} ${tsvfile}2 fi @@ -232,14 +325,10 @@ if [ $fancy == "Y" ] then perl ${repositorypath}/tsv2html.pl < ${tsvfile}2 > ${galaxypath}/htmltable_${fname}.html - #contentline="${contentline}\n<div class=\"resizable\" id=\"iframe${iframecount}\"><iframe src=\"htmltable_${fname}.html\" style=\"max-width: 100%;vertical-align: top;\" onload=\"resizeIframe(this)\"></iframe></div>" - #contentline="${contentline}\n<iframe class=\"resizable\" id=\"iframe${iframecount}\" src=\"htmltable_${fname}.html\" style=\"max-width: 100%;vertical-align: top;\" onload=\"resizeIframe(this)\"></iframe>" - contentline="${contentline}\n<iframe class=\"invisibleframe fancyiframe\" src=\"htmltable_${fname}.html\" width=\"100%\" style=\"min-height: 300px; overflow-y: hidden; overflow-x: scroll\" ></iframe>" - + contentline="${contentline}\n<iframe class=\"invisibleframe fancyiframe\" src=\"htmltable_${fname}.html\" width=\"100%\" style=\"min-height: 525px; overflow-y: hidden; overflow-x: scroll\" ></iframe>" iframecount=$[$iframecount+1] else perl ${repositorypath}/tsv2html_simple.pl < ${tsvfile}2 > ${galaxypath}/htmltable_${fname}.html - #contentline="${contentline}\n<iframe class=\"invisibleframe\" id=\"iframe${iframecount}\" style=\"max-width: 100%; vertical-align: top;\" src=\"htmltable_${fname}.html\" onload=\"resizeIframe(this)\"></iframe>" contentline="${contentline}\n<iframe class=\"unfancyiframe invisibleframe\" src=\"htmltable_${fname}.html\" scrolling=\"no\" style=\"max-width: 100%; vertical-align: top;\" onload=\"resizeIframe(this)\"></iframe>" iframecount=$[$iframecount+1] fi @@ -252,6 +341,9 @@ fi fi + ## + ## PDF + ## if [[ ${myarr[1]} == "pdf" ]] then pdffile=${myarr[2]} @@ -262,14 +354,31 @@ width=1000 height=800 - #contentline="${contentline}<object data=\"${fname}\" type=\"application/pdf\" width=\"1000\" height=\"1000\"><p>It appears you have no PDF plugin for your browser. No biggie... you can <a href=\"${fname}\">click here to download the PDF file.</a></p></object>" echo -e "<html><body><object data=\"${pdfname}\" type=\"application/pdf\" width=\"$width\" height=\"$height\"><embed src=\"${pdfname}\" type=\"application/pdf\" /><p>It appears you have no PDF plugin for your browser. No biggie... you can <a href=\"${pdfname}\">click here to download the PDF file.</a></p></object></body></html>" > "${galaxypath}/${fname}.html" width=$[$width+10] height=$[$height+10] - contentline="${contentline}<iframe src=\"${fname}.html\" width=\"${width}\" height=\"${height}\"></iframe>\n" + contentline="${contentline}\n<iframe src=\"${fname}.html\" width=\"${width}\" height=\"${height}\"></iframe>\n" fi - ## link to a location on the web, open in new window + + ## + ## HTML + ## + if [[ ${myarr[1]} == "htmlfile" ]] + then + htmlfile=${myarr[2]} + height=${myarr[4]} + fname=`basename ${htmlfile}` + fname=${fname%.dat} + htmlname="${fname}.html" + cp ${htmlfile} "${galaxypath}/${htmlname}" + + contentline="${contentline}\n<iframe class=\"invisibleframe\" src=\"${htmlname}\" width=\"100%\" height=\"${height}px\"></iframe>\n" + fi + + ## + ## Web Link + ## if [ ${myarr[1]} == "weblink" ] then url=${myarr[2]} @@ -280,7 +389,9 @@ contentline="${contentline}<a href=\"${url}\" target=\"_blank\">${linktext}</a>" fi - ## link to a file in the history + ## + ## Link to Dataset + ## if [ ${myarr[1]} == "link" ] then linkfile=${myarr[2]} @@ -324,7 +435,9 @@ contentline="${contentline}<a href=\"${linkfilename}\">${linktext}</a>" fi - ## link to files in an archive in the history item + ## + ## Links to Archive Contents + ## if [[ ${myarr[1]} == "links" ]] then #echo "making links:" @@ -421,7 +534,7 @@ if [[ ${myarr[3]} == "Y" ]] then - contentline="${contentline}<br/>" + contentline="${contentline}<br/>\n" fi fi done @@ -429,13 +542,15 @@ echo "${contentline}" } - +## +## Create HTML content for iReport +## createMainPage (){ page=$1 - tabtitles=$2 #comma-separated list of tab titles - tabitems=$3 - iframecount=1 - minwidth=$4 + tabtitles=$2 # comma-separated list of tab titles + tabitems=$3 # colon-sparated list of tabs specifications + iframecount=1 # keep track of number of iFrames so that they can be referenced by ID + minwidth=$4 # width of page echo "createMainPage: tabitems: $tabitems. tabtitles: $tabtitles" # create correct number of tabs @@ -445,15 +560,15 @@ tabtitles=${tabtitles//==colon==/:} tabslist="<ul>\n" mytabs="" + for title in $tabtitles do - #create list of tabs - + # Create list of tabs count=$[count+1] title2=${title//_s_/ } tabslist="${tabslist} <li><a href=\"#tabs-${count}\">${title2}</a></li>\n" - #create tabs with content + # Create tabs with content tabcontent=$(makeTabContent $title "$tabitems") mytabs="${mytabs}\n<div id=\"tabs-${count}\">\n" mytabs="${mytabs}${tabcontent}" @@ -461,99 +576,27 @@ done tabslist="${tabslist}</ul>" - #output the webpage + ## Output the webpage echo -e "<!doctype html> -<head> + <head> <meta charset=\"utf-8\"> - <title>jQuery UI Tabs - Default functionality</title> - - - <link rel=\"stylesheet\" href=\"jquery-ui.css\"> - <script src=\"jquery-1.10.2.js\"></script> - <script src=\"jquery-ui.js\"></script> + <title>iReport</title> + <link rel=\"stylesheet\" href=\"jquery-ui.css\"> + <link rel=\"stylesheet\" href=\"ireport_css.css\"> + <link rel=\"stylesheet\" href=\"md.css\"> + <script type=\"text/javascript\" src=\"jquery-1.10.2.js\"></script> + <script type=\"text/javascript\" src=\"jquery-ui.js\"></script> <script type=\"text/javascript\" src=\"iframe-resizer/src/iframeResizer.js\"></script> <script type=\"text/javascript\" src=\"jquery.zoom.js\"></script> - - <script> - \$(function() { - \$( \"#tabs\" ).tabs(); - }); - - \$(function() { - \$( \".resizable\" ).resizable(); - }); - - \$(document).ready(function(){ - \$('.zoomme').zoom(); - \$('#ex2').zoom({ on:'grab' }); - \$('#ex3').zoom({ on:'click' }); - \$('#ex4').zoom({ on:'toggle' }); - \$('.fancyiframe').iFrameResize({ - heightCalculationMethod: 'max', - minHeight: 250, - scrolling: true, - checkOrigin: false, - bodyMargin: 15 - }); - \$('.unfancyiframe').iFrameResize({ - heightCalculationMethod: 'max', - scrolling: false, - checkOrigin: false - }); - }); - - </script> - + <script type=\"text/javascript\" src=\"ireport_jquery.js\"></script> + <script type=\"text/javascript\" src=\"ireport_javascript.js\"></script> + </head> + <body> + <div id=\"tabs\" style=\"display:inline-block; min-height:100%; min-width:${minwidth}px\"> + $tabslist - <script language=\"javascript\" type=\"text/javascript\"> - function resizeIframe(obj) { - oldheight=obj.style.height - oldwidth=obj.style.width - obj.style.height = obj.contentWindow.document.body.scrollHeight + 4 + 'px'; - obj.style.width = obj.contentWindow.document.body.scrollWidth + 4 + 'px'; - - if(obj.style.height < 50){ - obj.style.height=oldheight - } - } - </script> -<style type=\"text/css\"> - body { - min-width: ${minwidth}px; - width: ${minwidth}px; - min-height: 100%; - } - .invisibleframe{ - border: 0px; - overflow: hidden - } - .mylinks{ - color: blue !important; - } - .mylinks:visited { - color: #551A8B !important; - } -</style> - <style > - .zoomme { - display: inline-block; - } -</style> - - -</head> -<body> - -<div id=\"tabs\" style=\"display:inline-block; min-height:100%; min-width:${minwidth}px\"> -$tabslist - -$mytabs -</div> - - -</body> + $mytabs + </div> + </body> </html>" > $page - - - } \ No newline at end of file
--- a/iReport.sh Tue Sep 30 09:56:12 2014 -0400 +++ b/iReport.sh Tue Oct 07 08:41:30 2014 -0400 @@ -65,7 +65,7 @@ fi echo -e "coverimage3: $coverimage" -## Copy supporting files to output directory +## Copy supporting files from repository to output directory cp ${repositorypath}/jquery.dataTables.css ${galaxypath}/jquery.dataTables.css cp ${repositorypath}/jquery.dataTables.js ${galaxypath}/jquery.dataTables.js cp -R ${repositorypath}/iframe-resizer/ ${galaxypath}/iframe-resizer/ @@ -74,6 +74,9 @@ cp ${repositorypath}/jquery-ui.css ${galaxypath}/jquery-ui.css cp ${repositorypath}/jquery-1.10.2.js ${galaxypath}/jquery-1.10.2.js cp ${repositorypath}/jquery-ui.js ${galaxypath}/jquery-ui.js +cp ${repositorypath}/md.css ${galaxypath}/md.css +cp ${repositorypath}/ireport_css.css ${galaxypath}/ireport_css.css +cp ${repositorypath}/ireport_jquery.js ${galaxypath}/ireport_jquery.js echo "done copying resource files" ls ${galaxypath}
--- a/iReport.xml Tue Sep 30 09:56:12 2014 -0400 +++ b/iReport.xml Tue Oct 07 08:41:30 2014 -0400 @@ -1,12 +1,11 @@ -<tool id="iReport" name="iReport" version="1"> - <description> create an HTML report </description> +<tool id="iReport-dev" name="iReport-dev" version="1"> + <description> create an HTML report-dev </description> <requirements> <requirement type="set_environment">REPOSITORY_PATH</requirement> </requirements> - <command interpreter="bash"> - - iReport.sh + <command interpreter="bash"> + iReport.sh --toolpath \$REPOSITORY_PATH --galaxypath ${report.files_path} --htmlout ${report} @@ -27,16 +26,24 @@ --item "${t.tabtitle}:${u.filetype.itemtype}:${u.filetype.item}:${u.filetype.break}:${__app__.security.encode_id($u.filetype.item.id)}:${u.filetype.ireport}:${u.filetype.item2}" #else if $u.filetype.itemtype == "weblink" --item "${t.tabtitle}:${u.filetype.itemtype}:${u.filetype.item}:${u.filetype.break}:${u.filetype.item2}" + #else if $u.filetype.itemtype == "text" + --item "${t.tabtitle}:${u.filetype.itemtype}:${u.filetype.item}:${u.filetype.break}:${u.filetype.md}" + #else if $u.filetype.itemtype == "textfile" + --item "${t.tabtitle}:${u.filetype.itemtype}:${u.filetype.item}:${u.filetype.break}:${u.filetype.md}" + #else if $u.filetype.itemtype == "htmlfile" + --item "${t.tabtitle}:${u.filetype.itemtype}:${u.filetype.item}:${u.filetype.break}:${u.filetype.height}" #else --item "${t.tabtitle}:${u.filetype.itemtype}:${u.filetype.item}:${u.filetype.break}" #end if #end for #end for --label "${label}" - </command> + </command> - <inputs> - <param name="label" type="text" size="100" label="Name of Report" /> + <inputs> + <param name="label" type="text" size="100" label="Name of Report" > + <validator type="empty_field" /> + </param> <param name="coverimage" type="text" size="100" label="Link to cover image" help="Optional. A default image will be used if not specified"/> <param name="minwidth" type="integer" min="0" max="5000" value="1200" label="Width of page (in pixels)" /> <repeat name="tabs" title="Tab" default="1" > @@ -51,6 +58,7 @@ <remove value="&"/> <remove value=":"/> <remove value=" "/> + <remove value="`"/> </valid> <mapping initial="none"> <add source="\" target="\\"/> @@ -60,8 +68,10 @@ <add source="
" target="&r"/> <add source=":" target="==colon=="/> <add source=" " target="_s_"/> + <add source="`" target="==backtick=="/> </mapping> </sanitizer> + <validator type="empty_field" /> </param> <repeat name="content" title="Content-Item" default="1"> <conditional name="filetype"> @@ -69,15 +79,17 @@ <option value="" > Please choose item type </option> <option value="text" > Text Field </option> <option value="textfile" > Text File from history </option> + <option value="htmlfile"> HTML File from history </option> <option value="image"> Image </option> <option value="pdf" > PDF File </option> <option value="table"> Table </option> - <option value="link" > Link to file </option> - <option value="links"> Links to files in archive</option> + <option value="link" > Link to Dataset </option> + <option value="links"> Links to Files in Archive Dataset </option> <option value="weblink" > Web link </option> <validator type="empty_field" /> </param> <when value="text"> + <param name="md" type="boolean" truevalue="Y" falsevalue="n" checked="false" label="Text in MarkDown format?" help="If checked, text file or field will be interpreted as markdown"/> <param name="item" type="text" area="true" size="10x100" label="Text to display." help="can explicitly add whitespace adding \n in your text for a newline or \t for a tab. HTML tags em, strong, b, i, h1-h6 tags" > <sanitizer> <valid initial="default"> @@ -95,6 +107,9 @@ <remove value="&"/> <remove value=":"/> <remove value=" "/> + <remove value="`"/> + <remove value="$"/> + <remove value="|"/> </valid> <mapping initial="none"> <add source="\" target="\\"/> @@ -110,18 +125,28 @@ <add source="'" target="==apos=="/> <add source=""" target="==quote=="/> <add source=":" target="==colon=="/> + <add source="`" target="==backtick=="/> + <add source="$" target="==dollar=="/> + <add source="|" target="==bar=="/> </mapping> </sanitizer> + <validator type="empty_field" /> </param> <param name="break" type="boolean" checked="False" truevalue="Y" falsevalue="N" label="Insert break after item?"/> </when> <when value="textfile"> + <param name="md" type="boolean" truevalue="Y" falsevalue="n" checked="false" label="Text in MarkDown format?" help="If checked, text file or field will be interpreted as markdown. Will use pandoc if this is installed on the system, else uses a custom script"/> <param name="item" type="data" label="Text File" help="Text file to display verbatim"/> <param name="break" type="boolean" checked="False" truevalue="Y" falsevalue="N" label="Insert break after item?" help="Insert a line break to force next item to appear below this one. If unchecked, the browser will decide layout"/> </when> + <when value="htmlfile"> + <param name="item" type="data" label="HTML File" help="Contents of html file will be displayed in an iframe"/> + <param name="height" type="integer" min="0" max="500000" value="350" label="Height (in pixels)" help="Height of the iFrame displaying the html page"/> + <param name="break" type="boolean" checked="False" truevalue="Y" falsevalue="N" label="Insert break after item?" help="Insert a line break to force next item to appear below this one. If unchecked, the browser will decide layout"/> + </when> <when value="image"> <param name="item" type="data" label="Image File" format="png,svg,jpg,jpeg" help="Supported formats: png, jpg, svg. If image is scaled by choice of width, zoom-on-mousover effect is added."/> - <param name="zoomlevel" type="integer" min="0" max="5000" value="250" label="Width (in pixels)" help="enter 0 to keep original size" /> + <param name="zoomlevel" type="integer" min="0" max="5000" value="250" label="Width (in pixels)" help="enter 0 to keep original size" /> <param name="zoomenable" type="boolean" checked="True" truevalue="Y" falsevalue="N" label="Enable zoom-on-mouseover effect?" help="If checked and nonzero width, zoom-on-mousover effect added"/> <param name="align" type="select" label="Alignment of image (float)" help="Use left or right align to have images and text next to each other. Always specify image first (with alignment), then text, if you want to show them side by side." > <option value="none" > default (recommended) </option> @@ -224,6 +249,42 @@ </outputs> <help> - Description of tool for the users +============ +iReport +============ + +iReport is a tool for the easy creation of HTML reports from Galaxy datasets. Ideal to use as final step in a pipeline to display all results in a single, interactive report. + + +**What's new** + +- MarkDown support +- HTML content item type +- Link to download entire iReport on cover page + + + +**How to use** + +- Specify report title and cover image (url) +- Add any number of named tabs +- Add content items to each tab + +1. Text Field +2. Text File +3. PDF File +4. HTML File +5. Table +6. Image File +7. Links (URL/dataset) +8. Links to all files in an archive dataset + +**Example History** + +http://galaxy-demo.trait-ctmm.cloudlet.sara.nl/u/saskia-hiltemann/h/gcc2014-ireport-about-ireport + + + + </help> </tool>
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ireport_css.css Tue Oct 07 08:41:30 2014 -0400 @@ -0,0 +1,25 @@ + body { + min-width: ${minwidth}px; + width: ${minwidth}px; + min-height: 100%; + } + .invisibleframe{ + border: 0px; + overflow: hidden; + min-height: 350px !important; + } + .mylinks{ + color: blue !important; + } + .mylinks:visited { + color: #551A8B !important; + } + .zoomme { + display: inline-block; + } + .markdown-body { + min-width: ${minwidth}px; + max-width: ${minwidth}px; + margin: 0 auto; + padding: 30px; + } \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ireport_javascript.js Tue Oct 07 08:41:30 2014 -0400 @@ -0,0 +1,9 @@ + function resizeIframe(obj) { + oldheight=obj.style.height + oldwidth=obj.style.width + obj.style.height = obj.contentWindow.document.body.scrollHeight + 4 + 'px'; + obj.style.width = obj.contentWindow.document.body.scrollWidth + 4 + 'px'; + if(obj.style.height < 50){ + obj.style.height=oldheight + } + } \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/ireport_jquery.js Tue Oct 07 08:41:30 2014 -0400 @@ -0,0 +1,24 @@ +$(function() { + $("#tabs" ).tabs(); + }); + $(function() { + $(".resizable" ).resizable(); + }); + $(document).ready(function(){ + $('.zoomme').zoom(); + $('#ex2').zoom({ on:'grab' }); + $('#ex3').zoom({ on:'click' }); + $('#ex4').zoom({ on:'toggle' }); + $('.fancyiframe').iFrameResize({ + heightCalculationMethod: 'max', + minHeight: 250, + scrolling: true, + checkOrigin: false, + bodyMargin: 15 + }); + $('.unfancyiframe').iFrameResize({ + heightCalculationMethod: 'max', + scrolling: false, + checkOrigin: false + }); + }); \ No newline at end of file
--- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/md.css Tue Oct 07 08:41:30 2014 -0400 @@ -0,0 +1,696 @@ +@font-face { + font-family: octicons-anchor; + src: url(data:font/woff;charset=utf-8;base64,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) format('woff'); +} + +.markdown-body { + -ms-text-size-adjust: 100%; + -webkit-text-size-adjust: 100%; + color: #333; + overflow: hidden; + font-family: "Helvetica Neue", Helvetica, "Segoe UI", Arial, freesans, sans-serif; + font-size: 16px; + line-height: 1.6; + word-wrap: break-word; +} + +.markdown-body a { + background: transparent; +} + +.markdown-body a:active, +.markdown-body a:hover { + outline: 0; +} + +.markdown-body strong { + font-weight: bold; +} + +.markdown-body h1 { + font-size: 2em; + margin: 0.67em 0; +} + +.markdown-body img { + border: 0; +} + +.markdown-body hr { + -moz-box-sizing: content-box; + box-sizing: content-box; + height: 0; +} + +.markdown-body pre { + overflow: auto; +} + +.markdown-body code, +.markdown-body kbd, +.markdown-body pre { + font-family: monospace, monospace; + font-size: 1em; +} + +.markdown-body input { + color: inherit; + font: inherit; + margin: 0; +} + +.markdown-body html input[disabled] { + cursor: default; +} + +.markdown-body input { + line-height: normal; +} + +.markdown-body input[type="checkbox"] { + -moz-box-sizing: border-box; + box-sizing: border-box; + padding: 0; +} + +.markdown-body table { + border-collapse: collapse; + border-spacing: 0; +} + +.markdown-body td, +.markdown-body th { + padding: 0; +} + +.markdown-body * { + -moz-box-sizing: border-box; + box-sizing: border-box; +} + +.markdown-body input { + font: 13px/1.4 Helvetica, arial, freesans, clean, sans-serif, "Segoe UI Emoji", "Segoe UI Symbol"; +} + +.markdown-body a { + color: #4183c4; + text-decoration: none; +} + +.markdown-body a:hover, +.markdown-body a:focus, +.markdown-body a:active { + text-decoration: underline; +} + +.markdown-body hr { + height: 0; + margin: 15px 0; + overflow: hidden; + background: transparent; + border: 0; + border-bottom: 1px solid #ddd; +} + +.markdown-body hr:before { + display: table; + content: ""; +} + +.markdown-body hr:after { + display: table; + clear: both; + content: ""; +} + +.markdown-body h1, +.markdown-body h2, +.markdown-body h3, +.markdown-body h4, +.markdown-body h5, +.markdown-body h6 { + margin-top: 15px; + margin-bottom: 15px; + line-height: 1.1; +} + +.markdown-body h1 { + font-size: 30px; +} + +.markdown-body h2 { + font-size: 21px; +} + +.markdown-body h3 { + font-size: 16px; +} + +.markdown-body h4 { + font-size: 14px; +} + +.markdown-body h5 { + font-size: 12px; +} + +.markdown-body h6 { + font-size: 11px; +} + +.markdown-body blockquote { + margin: 0; +} + +.markdown-body ul, +.markdown-body ol { + padding: 0; + margin-top: 0; + margin-bottom: 0; +} + +.markdown-body ol ol, +.markdown-body ul ol { + list-style-type: lower-roman; +} + +.markdown-body ul ul ol, +.markdown-body ul ol ol, +.markdown-body ol ul ol, +.markdown-body ol ol ol { + list-style-type: lower-alpha; +} + +.markdown-body dd { + margin-left: 0; +} + +.markdown-body code { + font: 12px Consolas, "Liberation Mono", Menlo, Courier, monospace; +} + +.markdown-body pre { + margin-top: 0; + margin-bottom: 0; + font: 12px Consolas, "Liberation Mono", Menlo, Courier, monospace; +} + +.markdown-body kbd { + background-color: #e7e7e7; + background-image: -webkit-linear-gradient(#fefefe, #e7e7e7); + background-image: linear-gradient(#fefefe, #e7e7e7); + background-repeat: repeat-x; + border-radius: 2px; + border: 1px solid #cfcfcf; + color: #000; + padding: 3px 5px; + line-height: 10px; + font: 11px Consolas, "Liberation Mono", Menlo, Courier, monospace; + display: inline-block; +} + +.markdown-body>*:first-child { + margin-top: 0 !important; +} + +.markdown-body>*:last-child { + margin-bottom: 0 !important; +} + +.markdown-body .anchor { + position: absolute; + top: 0; + bottom: 0; + left: 0; + display: block; + padding-right: 6px; + padding-left: 30px; + margin-left: -30px; +} + +.markdown-body .anchor:focus { + outline: none; +} + +.markdown-body h1, +.markdown-body h2, +.markdown-body h3, +.markdown-body h4, +.markdown-body h5, +.markdown-body h6 { + position: relative; + margin-top: 1em; + margin-bottom: 16px; + font-weight: bold; + line-height: 1.4; +} + +.markdown-body h1 .octicon-link, +.markdown-body h2 .octicon-link, +.markdown-body h3 .octicon-link, +.markdown-body h4 .octicon-link, +.markdown-body h5 .octicon-link, +.markdown-body h6 .octicon-link { + display: none; + color: #000; + vertical-align: middle; +} + +.markdown-body h1:hover .anchor, +.markdown-body h2:hover .anchor, +.markdown-body h3:hover .anchor, +.markdown-body h4:hover .anchor, +.markdown-body h5:hover .anchor, +.markdown-body h6:hover .anchor { + height: 1em; + padding-left: 8px; + margin-left: -30px; + line-height: 1; + text-decoration: none; +} + +.markdown-body h1:hover .anchor .octicon-link, +.markdown-body h2:hover .anchor .octicon-link, +.markdown-body h3:hover .anchor .octicon-link, +.markdown-body h4:hover .anchor .octicon-link, +.markdown-body h5:hover .anchor .octicon-link, +.markdown-body h6:hover .anchor .octicon-link { + display: inline-block; +} + +.markdown-body h1 { + padding-bottom: 0.3em; + font-size: 2.25em; + line-height: 1.2; + border-bottom: 1px solid #eee; +} + +.markdown-body h2 { + padding-bottom: 0.3em; + font-size: 1.75em; + line-height: 1.225; + border-bottom: 1px solid #eee; +} + +.markdown-body h3 { + font-size: 1.5em; + line-height: 1.43; +} + +.markdown-body h4 { + font-size: 1.25em; +} + +.markdown-body h5 { + font-size: 1em; +} + +.markdown-body h6 { + font-size: 1em; + color: #777; +} + +.markdown-body p, +.markdown-body blockquote, +.markdown-body ul, +.markdown-body ol, +.markdown-body dl, +.markdown-body table, +.markdown-body pre { + margin-top: 0; + margin-bottom: 16px; +} + +.markdown-body hr { + height: 4px; + padding: 0; + margin: 16px 0; + background-color: #e7e7e7; + border: 0 none; +} + +.markdown-body ul, +.markdown-body ol { + padding-left: 2em; +} + +.markdown-body ul ul, +.markdown-body ul ol, +.markdown-body ol ol, +.markdown-body ol ul { + margin-top: 0; + margin-bottom: 0; +} + +.markdown-body li>p { + margin-top: 16px; +} + +.markdown-body dl { + padding: 0; +} + +.markdown-body dl dt { + padding: 0; + margin-top: 16px; + font-size: 1em; + font-style: italic; + font-weight: bold; +} + +.markdown-body dl dd { + padding: 0 16px; + margin-bottom: 16px; +} + +.markdown-body blockquote { + padding: 0 15px; + color: #777; + border-left: 4px solid #ddd; +} + +.markdown-body blockquote>:first-child { + margin-top: 0; +} + +.markdown-body blockquote>:last-child { + margin-bottom: 0; +} + +.markdown-body table { + display: block; + width: 100%; + overflow: auto; + word-break: normal; + word-break: keep-all; +} + +.markdown-body table th { + font-weight: bold; +} + +.markdown-body table th, +.markdown-body table td { + padding: 6px 13px; + border: 1px solid #ddd; +} + +.markdown-body table tr { + background-color: #fff; + border-top: 1px solid #ccc; +} + +.markdown-body table tr:nth-child(2n) { + background-color: #f8f8f8; +} + +.markdown-body img { + max-width: 100%; + -moz-box-sizing: border-box; + box-sizing: border-box; +} + +.markdown-body code { + padding: 0; + padding-top: 0.2em; + padding-bottom: 0.2em; + margin: 0; + font-size: 85%; + background-color: rgba(0,0,0,0.04); + border-radius: 3px; +} + +.markdown-body code:before, +.markdown-body code:after { + letter-spacing: -0.2em; + content: "\00a0"; +} + +.markdown-body pre>code { + padding: 0; + margin: 0; + font-size: 100%; + word-break: normal; + white-space: pre; + background: transparent; + border: 0; +} + +.markdown-body .highlight { + margin-bottom: 16px; +} + +.markdown-body .highlight pre, +.markdown-body pre { + padding: 16px; + overflow: auto; + font-size: 85%; + line-height: 1.45; + background-color: #f7f7f7; + border-radius: 3px; +} + +.markdown-body .highlight pre { + margin-bottom: 0; + word-break: normal; +} + +.markdown-body pre { + word-wrap: normal; +} + +.markdown-body pre code { + display: inline; + max-width: initial; + padding: 0; + margin: 0; + overflow: initial; + line-height: inherit; + word-wrap: normal; + background-color: transparent; + border: 0; +} + +.markdown-body pre code:before, +.markdown-body pre code:after { + content: normal; +} + +.markdown-body .highlight { + background: #fff; +} + +.markdown-body .highlight .mf, +.markdown-body .highlight .mh, +.markdown-body .highlight .mi, +.markdown-body .highlight .mo, +.markdown-body .highlight .il, +.markdown-body .highlight .m { + color: #945277; +} + +.markdown-body .highlight .s, +.markdown-body .highlight .sb, +.markdown-body .highlight .sc, +.markdown-body .highlight .sd, +.markdown-body .highlight .s2, +.markdown-body .highlight .se, +.markdown-body .highlight .sh, +.markdown-body .highlight .si, +.markdown-body .highlight .sx, +.markdown-body .highlight .s1 { + color: #df5000; +} + +.markdown-body .highlight .kc, +.markdown-body .highlight .kd, +.markdown-body .highlight .kn, +.markdown-body .highlight .kp, +.markdown-body .highlight .kr, +.markdown-body .highlight .kt, +.markdown-body .highlight .k, +.markdown-body .highlight .o { + font-weight: bold; +} + +.markdown-body .highlight .kt { + color: #458; +} + +.markdown-body .highlight .c, +.markdown-body .highlight .cm, +.markdown-body .highlight .c1 { + color: #998; + font-style: italic; +} + +.markdown-body .highlight .cp, +.markdown-body .highlight .cs { + color: #999; + font-weight: bold; +} + +.markdown-body .highlight .cs { + font-style: italic; +} + +.markdown-body .highlight .n { + color: #333; +} + +.markdown-body .highlight .na, +.markdown-body .highlight .nv, +.markdown-body .highlight .vc, +.markdown-body .highlight .vg, +.markdown-body .highlight .vi { + color: #008080; +} + +.markdown-body .highlight .nb { + color: #0086B3; +} + +.markdown-body .highlight .nc { + color: #458; + font-weight: bold; +} + +.markdown-body .highlight .no { + color: #094e99; +} + +.markdown-body .highlight .ni { + color: #800080; +} + +.markdown-body .highlight .ne { + color: #990000; + font-weight: bold; +} + +.markdown-body .highlight .nf { + color: #945277; + font-weight: bold; +} + +.markdown-body .highlight .nn { + color: #555; +} + +.markdown-body .highlight .nt { + color: #000080; +} + +.markdown-body .highlight .err { + color: #a61717; + background-color: #e3d2d2; +} + +.markdown-body .highlight .gd { + color: #000; + background-color: #fdd; +} + +.markdown-body .highlight .gd .x { + color: #000; + background-color: #faa; +} + +.markdown-body .highlight .ge { + font-style: italic; +} + +.markdown-body .highlight .gr { + color: #aa0000; +} + +.markdown-body .highlight .gh { + color: #999; +} + +.markdown-body .highlight .gi { + color: #000; + background-color: #dfd; +} + +.markdown-body .highlight .gi .x { + color: #000; + background-color: #afa; +} + +.markdown-body .highlight .go { + color: #888; +} + +.markdown-body .highlight .gp { + color: #555; +} + +.markdown-body .highlight .gs { + font-weight: bold; +} + +.markdown-body .highlight .gu { + color: #800080; + font-weight: bold; +} + +.markdown-body .highlight .gt { + color: #aa0000; +} + +.markdown-body .highlight .ow { + font-weight: bold; +} + +.markdown-body .highlight .w { + color: #bbb; +} + +.markdown-body .highlight .sr { + color: #017936; +} + +.markdown-body .highlight .ss { + color: #8b467f; +} + +.markdown-body .highlight .bp { + color: #999; +} + +.markdown-body .highlight .gc { + color: #999; + background-color: #EAF2F5; +} + +.markdown-body .octicon { + font: normal normal 16px octicons-anchor; + line-height: 1; + display: inline-block; + text-decoration: none; + -webkit-font-smoothing: antialiased; + -moz-osx-font-smoothing: grayscale; + -webkit-user-select: none; + -moz-user-select: none; + -ms-user-select: none; + user-select: none; +} + +.markdown-body .octicon-link:before { + content: '\f05c'; +} + +.markdown-body .task-list-item { + list-style-type: none; +} + +.markdown-body .task-list-item+.task-list-item { + margin-top: 3px; +} + +.markdown-body .task-list-item input { + float: left; + margin: 0.3em 0 0.25em -1.6em; + vertical-align: middle; +} \ No newline at end of file