def parseHTML(str):
doc = html5lib.parse(u(str), treebuilder='lxml', namespaceHTMLElements=False)
body = doc.getroot()[1]
if body.text is None:
return list(body.iterchildren())
else:
return [body.text] + list(body.iterchildren())
def die(msg, *formatArgs):
msg = u"\033[1;31mFATAL ERROR:\033[0m "+u(msg).format(*map(u, formatArgs))
if msg not in messages:
messages.add(msg)
print msg
if not config.debug:
sys.exit(1)
def parseHTML(str):
doc = html5lib.parse(u(str),
treebuilder='lxml',
namespaceHTMLElements=False)
body = doc.getroot()[1]
if body.text is None:
return list(body.iterchildren())
else:
return [body.text] + list(body.iterchildren())
def linkTextsFromElement(el, preserveCasing=False):
from lib.htmlhelpers import textContent
if el.get('title') == '':
return []
elif el.get('title'):
texts = [u(x.strip()) for x in el.get('title').split('|')]
else:
texts = [textContent(el).strip()]
if preserveCasing:
return texts
else:
return [t.lower() for t in texts]
def linkTextsFromElement(el, preserveCasing=False):
from lib.htmlhelpers import textContent
if el.get('title') == '':
return []
elif el.get('title'):
texts = [u(x.strip()) for x in el.get('title').split('|')]
else:
texts = [textContent(el).strip()]
if preserveCasing:
return texts
else:
return [t.lower() for t in texts]
def setSpecData(self, spec):
if spec.status in ("ED", "DREAM", "UD"):
self.specStatus = "ED"
else:
self.specStatus = "TR"
# I'll want to make this more complex later,
# to enforce pubrules linking policy.
self.specLevel = spec.level
self.specName = spec.shortname
self.specVName = spec.shortname + "-" + u(spec.level)
# Need to get a real versioned shortname,
# with the possibility of overriding the "shortname-level" pattern.
self.removeSameSpecRefs()
def setSpecData(self, spec):
if spec.status in ("ED", "DREAM", "UD"):
self.specStatus = "ED"
else:
self.specStatus = "TR"
# I'll want to make this more complex later,
# to enforce pubrules linking policy.
self.specLevel = spec.level
self.specName = spec.shortname
self.specVName = spec.shortname + "-" + u(spec.level)
# Need to get a real versioned shortname,
# with the possibility of overriding the "shortname-level" pattern.
self.removeSameSpecRefs()
def innerHTML(el):
if el is None:
return u''
return u((el.text or u'') +
u''.join(u(html.tostring(x, encoding="unicode")) for x in el))
def innerHTML(el):
if el is None:
return u''
return u((el.text or u'') + u''.join(u(html.tostring(x, encoding="unicode")) for x in el))
def outerHTML(el):
if el is None:
return u''
return u(html.tostring(el, with_tail=False, encoding="unicode"))
def say(msg, *formatArgs):
if not config.quiet:
print u(msg).format(*map(u, formatArgs))
def warn(msg, *formatArgs):
if not config.quiet:
msg = u"\033[1;33mWARNING:\033[0m "+u(msg).format(*map(u, formatArgs))
if msg not in messages:
messages.add(msg)
print msg
def escapeAttr(str):
return u(str).replace(u'&', u'&').replace(u"'", u''').replace(
u'"', u'"')
def escapeHTML(str):
# Escape HTML
return u(str).replace(u'&', u'&').replace(u'<', u'<')
def parseDocument(str):
doc = html5lib.parse(u(str),
treebuilder='lxml',
namespaceHTMLElements=False)
return doc
def parseDocument(str):
doc = html5lib.parse(u(str), treebuilder='lxml', namespaceHTMLElements=False)
return doc
def textContent(el):
return u(html.tostring(el, method='text', with_tail=False, encoding="unicode"))
def textContent(el):
return u(
html.tostring(el, method='text', with_tail=False, encoding="unicode"))
def headingLevelOfElement(el):
for el in relevantHeadings(el, levels=[2, 3, 4, 5, 6]):
if el.get('data-level') is not None:
return u(el.get('data-level'))
return None
def escapeAttr(str):
return u(str).replace(u'&', u'&').replace(u"'", u''').replace(u'"', u'"')
def escapeHTML(str):
# Escape HTML
return u(str).replace(u'&', u'&').replace(u'<', u'<')
def outerHTML(el):
if el is None:
return u''
return u(html.tostring(el, with_tail=False, encoding="unicode"))
def headingLevelOfElement(el):
for el in relevantHeadings(el, levels=[2,3,4,5,6]):
if el.get('data-level') is not None:
return u(el.get('data-level'))
return None