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 simpleparse(raw): # !!! USE FOR DEBUGGING ONLY !!!
import sys
from mwlib import dummydb, parser
from mwlib.uparser import parseString
input = raw.decode('utf8')
r = parseString(title="title", raw=input, wikidb=dummydb.DummyDB())
buildAdvancedTree(r)
parser.show(sys.stdout, r, 0)
return r
def simpleparse(raw): # !!! USE FOR DEBUGGING ONLY !!! does not use post processors
import sys
from mwlib import dummydb
db = dummydb.DummyDB()
tokens = scanner.tokenize(raw)
r=parser.Parser(tokens, "unknown").parse()
parser.show(sys.stdout, r, 0)
return r
def simpleparse(
raw): # !!! USE FOR DEBUGGING ONLY !!! does not use post processors
import sys
from mwlib import dummydb
db = dummydb.DummyDB()
tokens = scanner.tokenize(raw)
r = parser.Parser(tokens, "unknown").parse()
parser.show(sys.stdout, r, 0)
return r
def getXML(wikitext):
db = DummyDB()
r = parseString(title="test", raw=wikitext, wikidb=db)
print "before preprocess"
show(sys.stdout, r)
preprocess(r)
print "after preprocess"
show(sys.stdout, r)
dbw = DocBookWriter()
dbw.dbwriteArticle(r)
return dbw.asstring()
def main():
for fn in sys.argv[1:]:
from mwlib.dummydb import DummyDB
from mwlib.uparser import parseString
db = DummyDB()
input = unicode(open(fn).read(), 'utf8')
r = parseString(title=fn, raw=input, wikidb=db)
parser.show(sys.stdout, r)
preprocess(r)
parser.show(sys.stdout, r)
dbw = MWXHTMLWriter()
dbw.writeBook(r)
nf = open("%s.html" % fn, "w")
nf.write(dbw.asstring())
def main():
for fn in sys.argv[1:]:
from mwlib.dummydb import DummyDB
from mwlib.uparser import parseString
db = DummyDB()
input = unicode(open(fn).read(), 'utf8')
r = parseString(title=fn, raw=input, wikidb=db)
parser.show(sys.stdout, r)
preprocess(r)
parser.show(sys.stdout, r)
dbw = MWXHTMLWriter()
dbw.writeBook(r)
nf = open("%s.html" % fn, "w")
nf.write(dbw.asstring())
def xwriteGenericElement(self, t):
if not hasattr(t, "starttext"):
if hasattr(t, "_tag"):
e = ET.Element(t._tag)
setVList(e, t)
return e
else:
return
else:
# parse html and return ET elements
stuff = t.starttext + t.endtext
try:
if not t.endtext and not "/" in t.starttext:
stuff = t.starttext[:-1] + "/>"
p = ET.fromstring(stuff)
except Exception, e:
parser.show(sys.stdout, t)
#raise e
p = None
def test_definitiondescription():
raw = u"""
== test ==
:One
::Two
:::Three
::::Four
"""
db = DummyDB()
r = parseString(title="t", raw=raw, wikidb=db)
parser.show(sys.stdout, r)
buildAdvancedTree(r)
dd = r.getChildNodesByClass(DefinitionDescription)
print "DD:", dd
for c in dd:
assert c.indentlevel == 1
assert len(dd) == 4
def main():
for fn in sys.argv[1:]:
from mwlib.dummydb import DummyDB
from mwlib.uparser import parseString
db = DummyDB()
input = unicode(open(fn).read(), 'utf8')
r = parseString(title=fn, raw=input, wikidb=db)
#parser.show(sys.stdout, r)
# advtree.buildAdvancedTree(r)
#tc = TreeCleaner(r)
# tc.cleanAll()
preprocess(r)
parser.show(sys.stdout, r)
odf = ODFWriter()
odf.writeTest(r)
doc = odf.getDoc()
# doc.toXml("%s.xml"%fn)
doc.save(fn, True)
def test_definitiondescription():
raw = u"""
== test ==
:One
::Two
:::Three
::::Four
"""
db = DummyDB()
r = parseString(title="t", raw=raw, wikidb=db)
parser.show(sys.stdout, r)
buildAdvancedTree(r)
dd = r.getChildNodesByClass(DefinitionDescription)
print "DD:", dd
for c in dd:
assert c.indentlevel == 1
assert len(dd) == 4
def main():
for fn in sys.argv[1:]:
from mwlib.dummydb import DummyDB
from mwlib.uparser import parseString
db = DummyDB()
input = unicode(open(fn).read(), 'utf8')
r = parseString(title=fn, raw=input, wikidb=db)
#parser.show(sys.stdout, r)
#advtree.buildAdvancedTree(r)
#tc = TreeCleaner(r)
#tc.cleanAll()
preprocess(r)
parser.show(sys.stdout, r)
odf = ODFWriter()
odf.writeTest(r)
doc = odf.getDoc()
#doc.toXml("%s.xml"%fn)
doc.save(fn, True)
def xwriteGenericElement(self, t):
if not hasattr(t, "starttext"):
if hasattr(t, "_tag"):
e = ET.Element(t._tag)
setVList(e, t)
return e
else:
log("skipping %r" % t)
return
else:
# parse html and return ET elements
stuff = t.starttext + t.endtext
try:
if not t.endtext and not "/" in t.starttext:
stuff = t.starttext[:-1] + "/>"
p = ET.fromstring(stuff)
except Exception, e:
log("failed to parse %r \n" % t)
parser.show(sys.stdout, t)
#raise e
p = None
import codecs
import sys
import wcb
if __name__ == "__main__":
argparser = argparse.ArgumentParser(description='Prints the syntax tree of an article')
argparser.add_argument('--advanced', '-a', action='store_true', help="Convert to advtree")
argparser.add_argument('article')
argparser.add_argument('--file', '-f', action='store_true', help="read article from FILE")
args = argparser.parse_args()
env = wiki.makewiki(wcb.paths["wikiconf"])
if args.file:
try:
f = codecs.open(args.article, encoding='utf-8')
raw = f.read()
except ValueError as excp:
sys.exit(unicode(excp).encode("ascii", "backslashreplace") + "\n")
tree = uparser.parseString(title='Nameless', raw=raw, wikidb=env.wiki, lang=env.wiki.siteinfo["general"]["lang"])
else:
tree = env.wiki.getParsedArticle(args.article)
if tree:
if args.advanced:
advtree.buildAdvancedTree(tree)
parser.show(sys.stdout, tree, 0)
else:
print 'Could not find article "' + args.article + '"'
def showTree(tree):
parser.show(sys.stdout, tree, 0)
def showTree(tree):
parser.show(sys.stdout, tree, 0)
def show(tree):
parser.show(sys.stdout, tree)
def writeparsetree(self, tree):
out = StringIO.StringIO()
parser.show(out, tree)
self.root.append(ET.Comment(out.getvalue().replace("--", " - - ")))
def writeparsetree(self, tree):
out = StringIO.StringIO()
parser.show(out, tree)
self.root.append(ET.Comment(out.getvalue().replace("--", " - - ")))
def show(tree):
parser.show(sys.stdout, tree)
