def to_html(cls, kb_entry):
r = kb_entry.body.replace("\r", "")
parsed = parseString(title=kb_entry.subject, raw=r, wikidb=cls.NOCDB(kb_entry))
preprocess(parsed)
xhtml = MWXHTMLWriter()
xhtml.writeBook(parsed)
block = ET.tostring(xhtml.xmlbody)
return block
def getXHTML(wikitext):
db = DummyDB()
r = parseString(title="test", raw=wikitext, wikidb=db)
preprocess(r)
show(sys.stdout, r)
dbw = MWXHTMLWriter()
dbw.writeBook(r)
return dbw.asstring()
def getXHTML(wikitext):
db = DummyDB()
r = parseString(title="", raw=wikitext, wikidb=db)
preprocess(r)
dbw = MWXHTMLWriter()
with SuppressOutput():
dbw.writeBook(r)
return dbw.asstring()
def getXHTML(wikitext, title, language):
db = DummyDB()
db.normalize_and_get_page = noop
r = parseString(title=title, raw=wikitext, wikidb=db, lang=language)
if not r:
return None
preprocess(r)
removeLangLinks(r)
dbw = MWXHTMLWriter()
dbw.writeBook(r)
return dbw.asstring()
def getXHTML(wikitext, title, language):
db = DummyDB()
db.normalize_and_get_page = noop
r = parseString(title=title, raw=wikitext, wikidb=db, lang=language)
if not r:
return None
preprocess(r)
removeLangLinks(r)
dbw = MWXHTMLWriter()
dbw.writeBook(r)
return dbw.asstring()
def _servXML(self, args, query, dialect="mwxml"):
if not len(args):
self._doc(error="require articlename")
return
unknown = [k for k in query if k not in ("debug", "imageresolver")]
if unknown:
return self._doc(error="unknown option %r" % unknown)
title = args.pop()
base_url = "http://%s/" % ("/".join(args) or default_baseurl)
debug = bool(query.setdefault("debug", [default_debug])[0])
language = "en" # FIXME
namespace="en.wikipedia.org" # FIXME
print "_servXML", title, base_url, debug
db = mwapidb.WikiDB(base_url)
db.print_template = None # deactivate print template lookups
tree = db.getParsedArticle(title, revision=None)
if dialect == "mwxhtml":
xhtmlwriter.preprocess(tree)
dbw = xhtmlwriter.MWXHTMLWriter(imagesrcresolver=imagesrcresolver,
debug=False)
elif dialect == "mwxml":
advtree.buildAdvancedTree(tree) # this should be optional
dbw = xhtmlwriter.MWXMLWriter() # 1:1 XML from parse tree
elif dialect == "dbxml":
from mwlib import docbookwriter
docbookwriter.preprocess(tree)
dbw = docbookwriter.DocBookWriter(imagesrcresolver=imagesrcresolver,
debug=debug)
else:
raise Exception, "unkonwn export"
dbw.writeBook(tree)
if debug:
dbw.writeparsetree(tree)
response = dbw.asstring()
self.send_response(200)
self.send_header("Content-type", "text/xml")
self.send_header("Content-length", str(len(response)))
self.end_headers()
self.wfile.write(response)
# shut down the connection
self.wfile.flush()
def to_html(cls, kb_entry):
from mwlib.uparser import parseString
from mwlib.xhtmlwriter import MWXHTMLWriter, preprocess
try:
import xml.etree.ElementTree as ET
except:
from elementtree import ElementTree as ET
r = kb_entry.body.replace("\r", "")
parsed = parseString(title=kb_entry.subject,
raw=r,
wikidb=cls.NOCDB(kb_entry))
preprocess(parsed)
xhtml = MWXHTMLWriter()
xhtml.writeBook(parsed)
block = ET.tostring(xhtml.xmlbody)
return block
def get_xhtml(wikitext):
r = parseString(title="", raw=wikitext)
preprocess(r)
dbw = MyWriter()
dbw.writeBook(r)
text = dbw.asstring()
text = re.sub('<p />', '', text)
text = re.sub('<p> ', '<p>', text)
text = re.sub(' </p>', '</p>', text)
text = re.sub('</p><p>', '</p>\n<p>', text)
text = re.sub(' <br />       ', '</p>\n<p>', text)
text = re.sub('      ', '<p>', text)
text = re.sub('</dd><dd>', '</dd>\n<dd>', text)
text = re.sub('<body><div class="mwx.article"><h1 />', '', text)
text = re.sub('</div></body>', '', text)
return text
def run(self):
raw = u'\n'.join(self.content)
# empty wikidb
db = DummyDB()
# run parser and pre-processors
parsed = parseString(title='Export', raw=raw, wikidb=db)
preprocess(parsed)
# write XHTML
xhtml = MWXHTMLWriter()
xhtml.writeBook(parsed)
# remove the H1 heading (title) from the document
article = xhtml.xmlbody.getchildren()[0]
article.remove(article.getchildren()[0]) # remove caption
# render to string
block = ET.tostring(xhtml.xmlbody)
return [nodes.raw('', block, format='html')]
