Python uparser.parseString函数代码示例

def test_colspan():
    raw = '''<table><tr><td colspan="bogus">no colspan </td></tr></table>'''
    r = parseString(title='t', raw=raw)
    buildAdvancedTree(r)
    assert r.getChildNodesByClass(Cell)[0].colspan is 1

    raw = '''<table><tr><td colspan="-1">no colspan </td></tr></table>'''
    r = parseString(title='t', raw=raw)
    buildAdvancedTree(r)
    assert r.getChildNodesByClass(Cell)[0].colspan is 1

    raw = '''<table><tr><td colspan="2">colspan1</td></tr></table>'''
    r = parseString(title='t', raw=raw)
    buildAdvancedTree(r)
    assert r.getChildNodesByClass(Cell)[0].colspan is 2

def test_identity():
    raw = """
<br/>
<br/>
<br/>
<br/>
<br/>
<br/>
<br/>
<br/>
""".decode("utf8")

    db = DummyDB()
    r = parseString(title="X33", raw=raw, wikidb=db)
    buildAdvancedTree(r)
    _treesanity(r)

    brs = r.getChildNodesByClass(BreakingReturn)
    for i, br in enumerate(brs):
        assert br in br.siblings
        assert i == _idIndex(br.parent.children, br)
        assert len([x for x in br.parent.children if x is not br]) == len(brs) - 1
        for bbr in brs:
            if br is bbr:
                continue
            assert br == bbr
            assert br is not bbr

def test_copy():
    raw = """
===[[Leuchtturm|Leuchttürme]] auf Fehmarn===
*[[Leuchtturm Flügge]] super da
*[[Leuchtturm Marienleuchte]] da auch
*[[Leuchtturm Strukkamphuk]] spitze
*[[Leuchtturm Staberhuk]] supi
*[[Leuchtturm Westermarkelsdorf]]
""".decode(
        "utf8"
    )

    db = DummyDB()
    r = parseString(title="X33", raw=raw, wikidb=db)
    buildAdvancedTree(r)
    c = r.copy()
    _treesanity(c)

    def _check(n1, n2):
        assert n1.caption == n2.caption
        assert n1.__class__ == n2.__class__
        assert len(n1.children) == len(n2.children)
        for i, c1 in enumerate(n1):
            _check(c1, n2.children[i])

    _check(r, c)

def convert_pagecontent(title, content):
    """
    Convert a string in Mediawiki content format to a string in
    Dokuwiki content format.
    """

    # this is a hack for mwlib discarding the content of <nowiki> tags
    # and replacing them with plaintext parsed HTML versions of the
    # content (pragmatic, but not what we want)
    nowiki_plaintext = []

    # Instead we save the content here, replace it with the "magic" placeholder
    # tag <__yamdwe_nowiki> and the index where the content was saved, then pass
    # the list of nowiki content into the parser as context.
    def add_nowiki_block(match):
        nowiki_plaintext.append(match.group(0))
        return "<__yamdwe_nowiki>%d</__yamdwe_nowiki>" % (len(nowiki_plaintext)-1,)
    content = re.sub(r"<nowiki>.+?</nowiki>", add_nowiki_block, content)

    root = uparser.parseString(title, content) # create parse tree
    context = {}
    context["list_stack"] = []
    context["nowiki_plaintext"] = nowiki_plaintext # hacky way of attaching to child nodes
    result = convert(root, context, False)

    # mwlib doesn't parse NOTOC, so check for it manually
    if re.match(r"^\s*__NOTOC__\s*$", content, re.MULTILINE):
        result = "~~NOTOC~~"+("\n" if not result.startswith("\n") else "")+result
    return result

    def getUserLinks(raw):
        def isUserLink(node):
            return isinstance(node, parser.NamespaceLink) and node.namespace == 2  # NS_USER

        result = list(set([u.target for u in uparser.parseString(title, raw=raw, wikidb=wikidb).filter(isUserLink)]))
        result.sort()
        return result

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 test_tag_expand_vs_uniq():
    db = DictDB(
        Foo = """{{#tag:pre|inside pre}}"""
        )
    r=uparser.parseString(title="Foo", wikidb=db)
    core.show(r)
    pre = r.find(parser.PreFormatted)
    assert len(pre)==1, "expected a preformatted node"

def getAdvTree(fn):
    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)
    buildAdvancedTree(r)
    return r

def parse_tree(file_name):
    dp = dumpparser.DumpParser("data/wiki-data.xml")
    data = []
    for recipe in dp:
        data.append( (recipe.pageid,
                      recipe.title,
                      parser.parseString(recipe.text, recipe.text)) )
    return data

def parse_wiki(name, wiki, make_math_png=False):
    c = cdbwiki.WikiDB(default_wiki_dir)
    a = uparser.parseString(name, raw=wiki, wikidb=c)
    out = StringIO.StringIO()
    mr = rendermath.Renderer(basedir=default_math_dir,
            lazy=(not make_math_png))
    w = htmlwriter.HTMLWriter(out, images=None, math_renderer=mr)
    w.write(a)
    return out.getvalue()

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 test_ulist():
    """http://code.pediapress.com/wiki/ticket/222"""
    raw = u"""
* A item
*: B Previous item continues.
"""
    r = parseString(title='t', raw=raw)
    buildAdvancedTree(r)
#    parser.show(sys.stdout, r)
    assert len(r.getChildNodesByClass(Item)) == 1

 def getParsedArticle(self, title, revision=None):
     raw = self.getRawArticle(title, revision=revision)
     if raw is None:
         return None
     article = self._getArticle(title, revision=revision)
     lang = None
     source = self.getSource(title, revision=revision)
     if source is not None:
         lang = source.get('language')
     return uparser.parseString(title=title, raw=raw, wikidb=self, lang=lang)

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()