xmllib.py

来自「mallet是自然语言处理、机器学习领域的一个开源项目。」· Python 代码 · 共 930 行 · 第 1/3 页

                    version, encoding, standalone = res.group('version',
                                                              'encoding',
                                                              'standalone')
                    if version[1:-1] != '1.0':
                        raise Error('only XML version 1.0 supported')
                    if encoding: encoding = encoding[1:-1]
                    if standalone: standalone = standalone[1:-1]
                    self.handle_xml(encoding, standalone)
                    i = res.end(0)
                    continue
                res = procopen.match(rawdata, i)
                if res:
                    k = self.parse_proc(i)
                    if k < 0: break
                    self.lineno = self.lineno + rawdata[i:k].count('\n')
                    i = k
                    continue
                res = doctype.match(rawdata, i)
                if res:
                    if self.literal:
                        data = rawdata[i]
                        self.handle_data(data)
                        self.lineno = self.lineno + data.count('\n')
                        i = i+1
                        continue
                    if self.__seen_doctype:
                        self.syntax_error('multiple DOCTYPE elements')
                    if self.__seen_starttag:
                        self.syntax_error('DOCTYPE not at beginning of document')
                    k = self.parse_doctype(res)
                    if k < 0: break
                    self.__seen_doctype = res.group('name')
                    if self.__map_case:
                        self.__seen_doctype = self.__seen_doctype.lower()
                    self.lineno = self.lineno + rawdata[i:k].count('\n')
                    i = k
                    continue
            elif rawdata[i] == '&':
                if self.literal:
                    data = rawdata[i]
                    self.handle_data(data)
                    i = i+1
                    continue
                res = charref.match(rawdata, i)
                if res is not None:
                    i = res.end(0)
                    if rawdata[i-1] != ';':
                        self.syntax_error("`;' missing in charref")
                        i = i-1
                    if not self.stack:
                        self.syntax_error('data not in content')
                    self.handle_charref(res.group('char')[:-1])
                    self.lineno = self.lineno + res.group(0).count('\n')
                    continue
                res = entityref.match(rawdata, i)
                if res is not None:
                    i = res.end(0)
                    if rawdata[i-1] != ';':
                        self.syntax_error("`;' missing in entityref")
                        i = i-1
                    name = res.group('name')
                    if self.__map_case:
                        name = name.lower()
                    if self.entitydefs.has_key(name):
                        self.rawdata = rawdata = rawdata[:res.start(0)] + self.entitydefs[name] + rawdata[i:]
                        n = len(rawdata)
                        i = res.start(0)
                    else:
                        self.unknown_entityref(name)
                    self.lineno = self.lineno + res.group(0).count('\n')
                    continue
            elif rawdata[i] == ']':
                if self.literal:
                    data = rawdata[i]
                    self.handle_data(data)
                    i = i+1
                    continue
                if n-i < 3:
                    break
                if cdataclose.match(rawdata, i):
                    self.syntax_error("bogus `]]>'")
                self.handle_data(rawdata[i])
                i = i+1
                continue
            else:
                raise Error('neither < nor & ??')
            # We get here only if incomplete matches but
            # nothing else
            break
        # end while
        if i > 0:
            self.__at_start = 0
        if end and i < n:
            data = rawdata[i]
            self.syntax_error("bogus `%s'" % data)
            if not self.__accept_utf8 and illegal.search(data):
                self.syntax_error('illegal character in content')
            self.handle_data(data)
            self.lineno = self.lineno + data.count('\n')
            self.rawdata = rawdata[i+1:]
            return self.goahead(end)
        self.rawdata = rawdata[i:]
        if end:
            if not self.__seen_starttag:
                self.syntax_error('no elements in file')
            if self.stack:
                self.syntax_error('missing end tags')
                while self.stack:
                    self.finish_endtag(self.stack[-1][0])

    # Internal -- parse comment, return length or -1 if not terminated
    def parse_comment(self, i):
        rawdata = self.rawdata
        if rawdata[i:i+4] != '<!--':
            raise Error('unexpected call to handle_comment')
        res = commentclose.search(rawdata, i+4)
        if res is None:
            return -1
        if doubledash.search(rawdata, i+4, res.start(0)):
            self.syntax_error("`--' inside comment")
        if rawdata[res.start(0)-1] == '-':
            self.syntax_error('comment cannot end in three dashes')
        if not self.__accept_utf8 and \
           illegal.search(rawdata, i+4, res.start(0)):
            self.syntax_error('illegal character in comment')
        self.handle_comment(rawdata[i+4: res.start(0)])
        return res.end(0)

    # Internal -- handle DOCTYPE tag, return length or -1 if not terminated
    def parse_doctype(self, res):
        rawdata = self.rawdata
        n = len(rawdata)
        name = res.group('name')
        if self.__map_case:
            name = name.lower()
        pubid, syslit = res.group('pubid', 'syslit')
        if pubid is not None:
            pubid = pubid[1:-1]         # remove quotes
            pubid = ' '.join(pubid.split()) # normalize
        if syslit is not None: syslit = syslit[1:-1] # remove quotes
        j = k = res.end(0)
        if k >= n:
            return -1
        if rawdata[k] == '[':
            level = 0
            k = k+1
            dq = sq = 0
            while k < n:
                c = rawdata[k]
                if not sq and c == '"':
                    dq = not dq
                elif not dq and c == "'":
                    sq = not sq
                elif sq or dq:
                    pass
                elif level <= 0 and c == ']':
                    res = endbracket.match(rawdata, k+1)
                    if res is None:
                        return -1
                    self.handle_doctype(name, pubid, syslit, rawdata[j+1:k])
                    return res.end(0)
                elif c == '<':
                    level = level + 1
                elif c == '>':
                    level = level - 1
                    if level < 0:
                        self.syntax_error("bogus `>' in DOCTYPE")
                k = k+1
        res = endbracketfind.match(rawdata, k)
        if res is None:
            return -1
        if endbracket.match(rawdata, k) is None:
            self.syntax_error('garbage in DOCTYPE')
        self.handle_doctype(name, pubid, syslit, None)
        return res.end(0)

    # Internal -- handle CDATA tag, return length or -1 if not terminated
    def parse_cdata(self, i):
        rawdata = self.rawdata
        if rawdata[i:i+9] != '<![CDATA[':
            raise Error('unexpected call to parse_cdata')
        res = cdataclose.search(rawdata, i+9)
        if res is None:
            return -1
        if not self.__accept_utf8 and \
           illegal.search(rawdata, i+9, res.start(0)):
            self.syntax_error('illegal character in CDATA')
        if not self.stack:
            self.syntax_error('CDATA not in content')
        self.handle_cdata(rawdata[i+9:res.start(0)])
        return res.end(0)

    __xml_namespace_attributes = {'ns':None, 'src':None, 'prefix':None}
    # Internal -- handle a processing instruction tag
    def parse_proc(self, i):
        rawdata = self.rawdata
        end = procclose.search(rawdata, i)
        if end is None:
            return -1
        j = end.start(0)
        if not self.__accept_utf8 and illegal.search(rawdata, i+2, j):
            self.syntax_error('illegal character in processing instruction')
        res = tagfind.match(rawdata, i+2)
        if res is None:
            raise Error('unexpected call to parse_proc')
        k = res.end(0)
        name = res.group(0)
        if self.__map_case:
            name = name.lower()
        if name == 'xml:namespace':
            self.syntax_error('old-fashioned namespace declaration')
            self.__use_namespaces = -1
            # namespace declaration
            # this must come after the <?xml?> declaration (if any)
            # and before the <!DOCTYPE> (if any).
            if self.__seen_doctype or self.__seen_starttag:
                self.syntax_error('xml:namespace declaration too late in document')
            attrdict, namespace, k = self.parse_attributes(name, k, j)
            if namespace:
                self.syntax_error('namespace declaration inside namespace declaration')
            for attrname in attrdict.keys():
                if not self.__xml_namespace_attributes.has_key(attrname):
                    self.syntax_error("unknown attribute `%s' in xml:namespace tag" % attrname)
            if not attrdict.has_key('ns') or not attrdict.has_key('prefix'):
                self.syntax_error('xml:namespace without required attributes')
            prefix = attrdict.get('prefix')
            if ncname.match(prefix) is None:
                self.syntax_error('xml:namespace illegal prefix value')
                return end.end(0)
            if self.__namespaces.has_key(prefix):
                self.syntax_error('xml:namespace prefix not unique')
            self.__namespaces[prefix] = attrdict['ns']
        else:
            if name.lower() == 'xml':
                self.syntax_error('illegal processing instruction target name')
            self.handle_proc(name, rawdata[k:j])
        return end.end(0)

    # Internal -- parse attributes between i and j
    def parse_attributes(self, tag, i, j):
        rawdata = self.rawdata
        attrdict = {}
        namespace = {}
        while i < j:
            res = attrfind.match(rawdata, i)
            if res is None:
                break
            attrname, attrvalue = res.group('name', 'value')
            if self.__map_case:
                attrname = attrname.lower()
            i = res.end(0)
            if attrvalue is None:
                self.syntax_error("no value specified for attribute `%s'" % attrname)
                attrvalue = attrname
            elif attrvalue[:1] == "'" == attrvalue[-1:] or \
                 attrvalue[:1] == '"' == attrvalue[-1:]:
                attrvalue = attrvalue[1:-1]
            elif not self.__accept_unquoted_attributes:
                self.syntax_error("attribute `%s' value not quoted" % attrname)
            res = xmlns.match(attrname)
            if res is not None:
                # namespace declaration
                ncname = res.group('ncname')
                namespace[ncname or ''] = attrvalue or None
                if not self.__use_namespaces:
                    self.__use_namespaces = len(self.stack)+1
                continue
            if '<' in attrvalue:
                self.syntax_error("`<' illegal in attribute value")
            if attrdict.has_key(attrname):
                self.syntax_error("attribute `%s' specified twice" % attrname)
            attrvalue = attrvalue.translate(attrtrans)
            attrdict[attrname] = self.translate_references(attrvalue)
        return attrdict, namespace, i

    # Internal -- handle starttag, return length or -1 if not terminated
    def parse_starttag(self, i):
        rawdata = self.rawdata
        # i points to start of tag
        end = endbracketfind.match(rawdata, i+1)
        if end is None:
            return -1
        tag = starttagmatch.match(rawdata, i)
        if tag is None or tag.end(0) != end.end(0):
            self.syntax_error('garbage in starttag')
            return end.end(0)
        nstag = tagname = tag.group('tagname')
        if self.__map_case:
            nstag = tagname = nstag.lower()
        if not self.__seen_starttag and self.__seen_doctype and \
           tagname != self.__seen_doctype:
            self.syntax_error('starttag does not match DOCTYPE')
        if self.__seen_starttag and not self.stack:
            self.syntax_error('multiple elements on top level')
        k, j = tag.span('attrs')
        attrdict, nsdict, k = self.parse_attributes(tagname, k, j)
        self.stack.append((tagname, nsdict, nstag))
        if self.__use_namespaces:
            res = qname.match(tagname)
        else:
            res = None
        if res is not None:
            prefix, nstag = res.group('prefix', 'local')
            if prefix is None:
                prefix = ''
            ns = None
            for t, d, nst in self.stack:
                if d.has_key(prefix):
                    ns = d[prefix]
            if ns is None and prefix != '':