def _parse_meta(self, header, body):
header = m.html(to_unicode(header))
titles = re.findall(r'<h1>(.*)</h1>', header)
if not titles:
logging.error('There is no title')
title = None
else:
title = titles[0]
meta = {'title': title}
items = re.findall(r'<li>(.*?)</li>', header, re.S)
for item in items:
index = item.find(':')
key = item[:index].rstrip()
value = item[index + 1:].lstrip()
meta[key] = value
desc = re.findall(r'<p>(.*?)</p>', header, re.S)
if desc:
meta['description'] = '\n\n'.join(desc)
#: keep body in meta data as source text
meta['source_text'] = body
_toc = m.Markdown(m.HtmlTocRenderer(), 0)
meta['toc'] = _toc.render(body)
return meta
def docs(docfile):
toc = ['intro', 'install', 'gettingstarted', 'advanced', 'contributing']
titles = {
'intro': 'Introduction',
'install': 'Installation',
'gettingstarted': 'Getting Started',
'advanced': 'Advanced Usage',
'contributing': 'Contributing'
}
docs_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), 'docs'))
source_path = os.path.abspath(os.path.join(docs_dir, '%s.md' % docfile))
# Check just in case somehow a path outside docs dir is constructed
if not source_path.startswith(docs_dir):
abort(404)
try:
with open(source_path) as mf:
content = hoedown.html(mf.read())
prev_i = toc.index(docfile) - 1
prev = toc[prev_i] if prev_i >= 0 else None
next_i = toc.index(docfile) + 1
next = toc[next_i] if next_i < len(toc) else None
return render_template('docs.html',
current=docfile,
prev=prev,
next=next,
content=content,
toc=toc,
titles=titles)
except IOError:
abort(404)
def docs(docfile):
toc = [
'intro', 'install', 'gettingstarted', 'reading', 'records',
'tokenization', 'pos', 'cem', 'lexicon', 'abbreviations', 'cli',
'scrape', 'contributing'
]
titles = {
'intro': 'Introduction',
'install': 'Installation',
'gettingstarted': 'Getting Started',
'reading': 'Reading Documents',
'records': 'Chemical Records',
'tokenization': 'Tokenization',
'pos': 'Part-of-speech Tagging',
'cem': 'Chemical Named Entities',
'lexicon': 'Lexicon',
'abbreviations': 'Abbreviation Detection',
'cli': 'Command Line Interface',
'scrape': 'Scraping Structured Data',
'contributing': 'Contributing'
}
docs_dir = os.path.abspath(os.path.join(os.path.dirname(__file__), 'docs'))
source_path = os.path.abspath(os.path.join(docs_dir, '%s.md' % docfile))
# Check just in case somehow a path outside docs dir is constructed
if not source_path.startswith(docs_dir):
abort(404)
try:
with open(source_path) as mf:
content = hoedown.html(mf.read().decode('utf-8'))
prev_i = toc.index(docfile) - 1
prev = toc[prev_i] if prev_i >= 0 else None
next_i = toc.index(docfile) + 1
next = toc[next_i] if next_i < len(toc) else None
return render_template('docs.html',
current=docfile,
prev=prev,
next=next,
content=content,
toc=toc,
titles=titles)
except IOError:
abort(404)
def markdown(text):
text = FS_RE.sub(fs_replace, text)
return markupsafe.Markup(hoedown.html(
text, extensions=MARKDOWN_EXTENSIONS, render_flags=MARKDOWN_RENDER_FLAGS))
def markdown(text):
return markupsafe.Markup(
hoedown.html(text, extensions=MARKDOWN_EXTENSIONS, render_flags=MARKDOWN_RENDER_FLAGS))
def markdown(content):
return hoedown.html(content,
extensions=hoedown.EXT_FENCED_CODE
| hoedown.EXT_HIGHLIGHT | hoedown.EXT_AUTOLINK
| hoedown.EXT_TABLES | hoedown.EXT_STRIKETHROUGH
| hoedown.EXT_UNDERLINE)
def setup(self):
self.r = lambda html: hoedown.html(html, render_flags=HTML_SMARTYPANTS)
def markdown(text):
return markupsafe.Markup(
hoedown.html(text,
extensions=MARKDOWN_EXTENSIONS,
render_flags=MARKDOWN_RENDER_FLAGS))
