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

                ns = self.__namespaces.get(prefix)
            if ns is not None:
                nstag = ns + ' ' + nstag
            elif prefix != '':
                nstag = prefix + ':' + nstag # undo split
            self.stack[-1] = tagname, nsdict, nstag
        # translate namespace of attributes
        attrnamemap = {} # map from new name to old name (used for error reporting)
        for key in attrdict.keys():
            attrnamemap[key] = key
        if self.__use_namespaces:
            nattrdict = {}
            for key, val in attrdict.items():
                okey = key
                res = qname.match(key)
                if res is not None:
                    aprefix, key = res.group('prefix', 'local')
                    if self.__map_case:
                        key = key.lower()
                    if aprefix is None:
                        aprefix = ''
                    ans = None
                    for t, d, nst in self.stack:
                        if d.has_key(aprefix):
                            ans = d[aprefix]
                    if ans is None and aprefix != '':
                        ans = self.__namespaces.get(aprefix)
                    if ans is not None:
                        key = ans + ' ' + key
                    elif aprefix != '':
                        key = aprefix + ':' + key
                    elif ns is not None:
                        key = ns + ' ' + key
                nattrdict[key] = val
                attrnamemap[key] = okey
            attrdict = nattrdict
        attributes = self.attributes.get(nstag)
        if attributes is not None:
            for key in attrdict.keys():
                if not attributes.has_key(key):
                    self.syntax_error("unknown attribute `%s' in tag `%s'" % (attrnamemap[key], tagname))
            for key, val in attributes.items():
                if val is not None and not attrdict.has_key(key):
                    attrdict[key] = val
        method = self.elements.get(nstag, (None, None))[0]
        self.finish_starttag(nstag, attrdict, method)
        if tag.group('slash') == '/':
            self.finish_endtag(tagname)
        return tag.end(0)

    # Internal -- parse endtag
    def parse_endtag(self, i):
        rawdata = self.rawdata
        end = endbracketfind.match(rawdata, i+1)
        if end is None:
            return -1
        res = tagfind.match(rawdata, i+2)
        if res is None:
            if self.literal:
                self.handle_data(rawdata[i])
                return i+1
            if not self.__accept_missing_endtag_name:
                self.syntax_error('no name specified in end tag')
            tag = self.stack[-1][0]
            k = i+2
        else:
            tag = res.group(0)
            if self.__map_case:
                tag = tag.lower()
            if self.literal:
                if not self.stack or tag != self.stack[-1][0]:
                    self.handle_data(rawdata[i])
                    return i+1
            k = res.end(0)
        if endbracket.match(rawdata, k) is None:
            self.syntax_error('garbage in end tag')
        self.finish_endtag(tag)
        return end.end(0)

    # Internal -- finish processing of start tag
    def finish_starttag(self, tagname, attrdict, method):
        if method is not None:
            self.handle_starttag(tagname, method, attrdict)
        else:
            self.unknown_starttag(tagname, attrdict)

    # Internal -- finish processing of end tag
    def finish_endtag(self, tag):
        self.literal = 0
        if not tag:
            self.syntax_error('name-less end tag')
            found = len(self.stack) - 1
            if found < 0:
                self.unknown_endtag(tag)
                return
        else:
            found = -1
            for i in range(len(self.stack)):
                if tag == self.stack[i][0]:
                    found = i
            if found == -1:
                self.syntax_error('unopened end tag')
                return
        while len(self.stack) > found:
            if found < len(self.stack) - 1:
                self.syntax_error('missing close tag for %s' % self.stack[-1][2])
            nstag = self.stack[-1][2]
            method = self.elements.get(nstag, (None, None))[1]
            if method is not None:
                self.handle_endtag(nstag, method)
            else:
                self.unknown_endtag(nstag)
            if self.__use_namespaces == len(self.stack):
                self.__use_namespaces = 0
            del self.stack[-1]

    # Overridable -- handle xml processing instruction
    def handle_xml(self, encoding, standalone):
        pass

    # Overridable -- handle DOCTYPE
    def handle_doctype(self, tag, pubid, syslit, data):
        pass

    # Overridable -- handle start tag
    def handle_starttag(self, tag, method, attrs):
        method(attrs)

    # Overridable -- handle end tag
    def handle_endtag(self, tag, method):
        method()

    # Example -- handle character reference, no need to override
    def handle_charref(self, name):
        try:
            if name[0] == 'x':
                n = int(name[1:], 16)
            else:
                n = int(name)
        except ValueError:
            self.unknown_charref(name)
            return
        if not 0 <= n <= 255:
            self.unknown_charref(name)
            return
        self.handle_data(chr(n))

    # Definition of entities -- derived classes may override
    entitydefs = {'lt': '&#60;',        # must use charref
                  'gt': '&#62;',
                  'amp': '&#38;',       # must use charref
                  'quot': '&#34;',
                  'apos': '&#39;',
                  }

    # Example -- handle data, should be overridden
    def handle_data(self, data):
        pass

    # Example -- handle cdata, could be overridden
    def handle_cdata(self, data):
        pass

    # Example -- handle comment, could be overridden
    def handle_comment(self, data):
        pass

    # Example -- handle processing instructions, could be overridden
    def handle_proc(self, name, data):
        pass

    # Example -- handle relatively harmless syntax errors, could be overridden
    def syntax_error(self, message):
        raise Error('Syntax error at line %d: %s' % (self.lineno, message))

    # To be overridden -- handlers for unknown objects
    def unknown_starttag(self, tag, attrs): pass
    def unknown_endtag(self, tag): pass
    def unknown_charref(self, ref): pass
    def unknown_entityref(self, name):
        self.syntax_error("reference to unknown entity `&%s;'" % name)


class TestXMLParser(XMLParser):

    def __init__(self, **kw):
        self.testdata = ""
        apply(XMLParser.__init__, (self,), kw)

    def handle_xml(self, encoding, standalone):
        self.flush()
        print 'xml: encoding =',encoding,'standalone =',standalone

    def handle_doctype(self, tag, pubid, syslit, data):
        self.flush()
        print 'DOCTYPE:',tag, `data`

    def handle_data(self, data):
        self.testdata = self.testdata + data
        if len(`self.testdata`) >= 70:
            self.flush()

    def flush(self):
        data = self.testdata
        if data:
            self.testdata = ""
            print 'data:', `data`

    def handle_cdata(self, data):
        self.flush()
        print 'cdata:', `data`

    def handle_proc(self, name, data):
        self.flush()
        print 'processing:',name,`data`

    def handle_comment(self, data):
        self.flush()
        r = `data`
        if len(r) > 68:
            r = r[:32] + '...' + r[-32:]
        print 'comment:', r

    def syntax_error(self, message):
        print 'error at line %d:' % self.lineno, message

    def unknown_starttag(self, tag, attrs):
        self.flush()
        if not attrs:
            print 'start tag: <' + tag + '>'
        else:
            print 'start tag: <' + tag,
            for name, value in attrs.items():
                print name + '=' + '"' + value + '"',
            print '>'

    def unknown_endtag(self, tag):
        self.flush()
        print 'end tag: </' + tag + '>'

    def unknown_entityref(self, ref):
        self.flush()
        print '*** unknown entity ref: &' + ref + ';'

    def unknown_charref(self, ref):
        self.flush()
        print '*** unknown char ref: &#' + ref + ';'

    def close(self):
        XMLParser.close(self)
        self.flush()

def test(args = None):
    import sys, getopt
    from time import time

    if not args:
        args = sys.argv[1:]

    opts, args = getopt.getopt(args, 'st')
    klass = TestXMLParser
    do_time = 0
    for o, a in opts:
        if o == '-s':
            klass = XMLParser
        elif o == '-t':
            do_time = 1

    if args:
        file = args[0]
    else:
        file = 'test.xml'

    if file == '-':
        f = sys.stdin
    else:
        try:
            f = open(file, 'r')
        except IOError, msg:
            print file, ":", msg
            sys.exit(1)

    data = f.read()
    if f is not sys.stdin:
        f.close()

    x = klass()
    t0 = time()
    try:
        if do_time:
            x.feed(data)
            x.close()
        else:
            for c in data:
                x.feed(c)
            x.close()
    except Error, msg:
        t1 = time()
        print msg
        if do_time:
            print 'total time: %g' % (t1-t0)
        sys.exit(1)
    t1 = time()
    if do_time:
        print 'total time: %g' % (t1-t0)


if __name__ == '__main__':
    test()