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

"""A parser for XML, using the derived class as static DTD."""

# Author: Sjoerd Mullender.

import re
import string


version = '0.3'

class Error(RuntimeError):
    pass

# Regular expressions used for parsing

_S = '[ \t\r\n]+'                       # white space
_opS = '[ \t\r\n]*'                     # optional white space
_Name = '[a-zA-Z_:][-a-zA-Z0-9._:]*'    # valid XML name
_QStr = "(?:'[^']*'|\"[^\"]*\")"        # quoted XML string
illegal = re.compile('[^\t\r\n -\176\240-\377]') # illegal chars in content
interesting = re.compile('[]&<]')

amp = re.compile('&')
ref = re.compile('&(' + _Name + '|#[0-9]+|#x[0-9a-fA-F]+)[^-a-zA-Z0-9._:]')
entityref = re.compile('&(?P<name>' + _Name + ')[^-a-zA-Z0-9._:]')
charref = re.compile('&#(?P<char>[0-9]+[^0-9]|x[0-9a-fA-F]+[^0-9a-fA-F])')
space = re.compile(_S + '$')
newline = re.compile('\n')

attrfind = re.compile(
    _S + '(?P<name>' + _Name + ')'
    '(' + _opS + '=' + _opS +
    '(?P<value>'+_QStr+'|[-a-zA-Z0-9.:+*%?!\(\)_#=~]+))?')
starttagopen = re.compile('<' + _Name)
starttagend = re.compile(_opS + '(?P<slash>/?)>')
starttagmatch = re.compile('<(?P<tagname>'+_Name+')'
                      '(?P<attrs>(?:'+attrfind.pattern+')*)'+
                      starttagend.pattern)
endtagopen = re.compile('</')
endbracket = re.compile(_opS + '>')
endbracketfind = re.compile('(?:[^>\'"]|'+_QStr+')*>')
tagfind = re.compile(_Name)
cdataopen = re.compile(r'<!\[CDATA\[')
cdataclose = re.compile(r'\]\]>')
# this matches one of the following:
# SYSTEM SystemLiteral
# PUBLIC PubidLiteral SystemLiteral
_SystemLiteral = '(?P<%s>'+_QStr+')'
_PublicLiteral = '(?P<%s>"[-\'\(\)+,./:=?;!*#@$_%% \n\ra-zA-Z0-9]*"|' \
                        "'[-\(\)+,./:=?;!*#@$_%% \n\ra-zA-Z0-9]*')"
_ExternalId = '(?:SYSTEM|' \
                 'PUBLIC'+_S+_PublicLiteral%'pubid'+ \
              ')'+_S+_SystemLiteral%'syslit'
doctype = re.compile('<!DOCTYPE'+_S+'(?P<name>'+_Name+')'
                     '(?:'+_S+_ExternalId+')?'+_opS)
xmldecl = re.compile('<\?xml'+_S+
                     'version'+_opS+'='+_opS+'(?P<version>'+_QStr+')'+
                     '(?:'+_S+'encoding'+_opS+'='+_opS+
                        "(?P<encoding>'[A-Za-z][-A-Za-z0-9._]*'|"
                        '"[A-Za-z][-A-Za-z0-9._]*"))?'
                     '(?:'+_S+'standalone'+_opS+'='+_opS+
                        '(?P<standalone>\'(?:yes|no)\'|"(?:yes|no)"))?'+
                     _opS+'\?>')
procopen = re.compile(r'<\?(?P<proc>' + _Name + ')' + _opS)
procclose = re.compile(_opS + r'\?>')
commentopen = re.compile('<!--')
commentclose = re.compile('-->')
doubledash = re.compile('--')
attrtrans = string.maketrans(' \r\n\t', '    ')

# definitions for XML namespaces
_NCName = '[a-zA-Z_][-a-zA-Z0-9._]*'    # XML Name, minus the ":"
ncname = re.compile(_NCName + '$')
qname = re.compile('(?:(?P<prefix>' + _NCName + '):)?' # optional prefix
                   '(?P<local>' + _NCName + ')$')

xmlns = re.compile('xmlns(?::(?P<ncname>'+_NCName+'))?$')

# XML parser base class -- find tags and call handler functions.
# Usage: p = XMLParser(); p.feed(data); ...; p.close().
# The dtd is defined by deriving a class which defines methods with
# special names to handle tags: start_foo and end_foo to handle <foo>
# and </foo>, respectively.  The data between tags is passed to the
# parser by calling self.handle_data() with some data as argument (the
# data may be split up in arbitrary chunks).

class XMLParser:
    attributes = {}                     # default, to be overridden
    elements = {}                       # default, to be overridden

    # parsing options, settable using keyword args in __init__
    __accept_unquoted_attributes = 0
    __accept_missing_endtag_name = 0
    __map_case = 0
    __accept_utf8 = 0
    __translate_attribute_references = 1

    # Interface -- initialize and reset this instance
    def __init__(self, **kw):
        self.__fixed = 0
        if kw.has_key('accept_unquoted_attributes'):
            self.__accept_unquoted_attributes = kw['accept_unquoted_attributes']
        if kw.has_key('accept_missing_endtag_name'):
            self.__accept_missing_endtag_name = kw['accept_missing_endtag_name']
        if kw.has_key('map_case'):
            self.__map_case = kw['map_case']
        if kw.has_key('accept_utf8'):
            self.__accept_utf8 = kw['accept_utf8']
        if kw.has_key('translate_attribute_references'):
            self.__translate_attribute_references = kw['translate_attribute_references']
        self.reset()

    def __fixelements(self):
        self.__fixed = 1
        self.elements = {}
        self.__fixdict(self.__dict__)
        self.__fixclass(self.__class__)

    def __fixclass(self, kl):
        self.__fixdict(kl.__dict__)
        for k in kl.__bases__:
            self.__fixclass(k)

    def __fixdict(self, dict):
        for key in dict.keys():
            if key[:6] == 'start_':
                tag = key[6:]
                start, end = self.elements.get(tag, (None, None))
                if start is None:
                    self.elements[tag] = getattr(self, key), end
            elif key[:4] == 'end_':
                tag = key[4:]
                start, end = self.elements.get(tag, (None, None))
                if end is None:
                    self.elements[tag] = start, getattr(self, key)

    # Interface -- reset this instance.  Loses all unprocessed data
    def reset(self):
        self.rawdata = ''
        self.stack = []
        self.nomoretags = 0
        self.literal = 0
        self.lineno = 1
        self.__at_start = 1
        self.__seen_doctype = None
        self.__seen_starttag = 0
        self.__use_namespaces = 0
        self.__namespaces = {'xml':None}   # xml is implicitly declared
        # backward compatibility hack: if elements not overridden,
        # fill it in ourselves
        if self.elements is XMLParser.elements:
            self.__fixelements()

    # For derived classes only -- enter literal mode (CDATA) till EOF
    def setnomoretags(self):
        self.nomoretags = self.literal = 1

    # For derived classes only -- enter literal mode (CDATA)
    def setliteral(self, *args):
        self.literal = 1

    # Interface -- feed some data to the parser.  Call this as
    # often as you want, with as little or as much text as you
    # want (may include '\n').  (This just saves the text, all the
    # processing is done by goahead().)
    def feed(self, data):
        self.rawdata = self.rawdata + data
        self.goahead(0)

    # Interface -- handle the remaining data
    def close(self):
        self.goahead(1)
        if self.__fixed:
            self.__fixed = 0
            # remove self.elements so that we don't leak
            del self.elements

    # Interface -- translate references
    def translate_references(self, data, all = 1):
        if not self.__translate_attribute_references:
            return data
        i = 0
        while 1:
            res = amp.search(data, i)
            if res is None:
                return data
            s = res.start(0)
            res = ref.match(data, s)
            if res is None:
                self.syntax_error("bogus `&'")
                i = s+1
                continue
            i = res.end(0)
            str = res.group(1)
            rescan = 0
            if str[0] == '#':
                if str[1] == 'x':
                    str = chr(int(str[2:], 16))
                else:
                    str = chr(int(str[1:]))
                if data[i - 1] != ';':
                    self.syntax_error("`;' missing after char reference")
                    i = i-1
            elif all:
                if self.entitydefs.has_key(str):
                    str = self.entitydefs[str]
                    rescan = 1
                elif data[i - 1] != ';':
                    self.syntax_error("bogus `&'")
                    i = s + 1 # just past the &
                    continue
                else:
                    self.syntax_error("reference to unknown entity `&%s;'" % str)
                    str = '&' + str + ';'
            elif data[i - 1] != ';':
                self.syntax_error("bogus `&'")
                i = s + 1 # just past the &
                continue

            # when we get here, str contains the translated text and i points
            # to the end of the string that is to be replaced
            data = data[:s] + str + data[i:]
            if rescan:
                i = s
            else:
                i = s + len(str)

    # Interface - return a dictionary of all namespaces currently valid
    def getnamespace(self):
        nsdict = {}
        for t, d, nst in self.stack:
            nsdict.update(d)
        return nsdict

    # Internal -- handle data as far as reasonable.  May leave state
    # and data to be processed by a subsequent call.  If 'end' is
    # true, force handling all data as if followed by EOF marker.
    def goahead(self, end):
        rawdata = self.rawdata
        i = 0
        n = len(rawdata)
        while i < n:
            if i > 0:
                self.__at_start = 0
            if self.nomoretags:
                data = rawdata[i:n]
                self.handle_data(data)
                self.lineno = self.lineno + data.count('\n')
                i = n
                break
            res = interesting.search(rawdata, i)
            if res:
                j = res.start(0)
            else:
                j = n
            if i < j:
                data = rawdata[i:j]
                if self.__at_start and space.match(data) is None:
                    self.syntax_error('illegal data at start of file')
                self.__at_start = 0
                if not self.stack and space.match(data) is None:
                    self.syntax_error('data not in content')
                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')
            i = j
            if i == n: break
            if rawdata[i] == '<':
                if starttagopen.match(rawdata, i):
                    if self.literal:
                        data = rawdata[i]
                        self.handle_data(data)
                        self.lineno = self.lineno + data.count('\n')
                        i = i+1
                        continue
                    k = self.parse_starttag(i)
                    if k < 0: break
                    self.__seen_starttag = 1
                    self.lineno = self.lineno + rawdata[i:k].count('\n')
                    i = k
                    continue
                if endtagopen.match(rawdata, i):
                    k = self.parse_endtag(i)
                    if k < 0: break
                    self.lineno = self.lineno + rawdata[i:k].count('\n')
                    i =  k
                    continue
                if commentopen.match(rawdata, i):
                    if self.literal:
                        data = rawdata[i]
                        self.handle_data(data)
                        self.lineno = self.lineno + data.count('\n')
                        i = i+1
                        continue
                    k = self.parse_comment(i)
                    if k < 0: break
                    self.lineno = self.lineno + rawdata[i:k].count('\n')
                    i = k
                    continue
                if cdataopen.match(rawdata, i):
                    k = self.parse_cdata(i)
                    if k < 0: break
                    self.lineno = self.lineno + rawdata[i:k].count('\n')
                    i = k
                    continue
                res = xmldecl.match(rawdata, i)
                if res:
                    if not self.__at_start:
                        self.syntax_error("<?xml?> declaration not at start of document")