[XML-SIG] New version of xmllib
Sjoerd Mullender
Sjoerd.Mullender@cwi.nl
Fri, 18 Dec 1998 18:33:02 +0100
------- =_aaaaaaaaaa0
Content-Type: text/plain; charset="us-ascii"
Content-ID: <10433.914002226.1@bireme.cwi.nl>
Here is my current version of xmllib.py and the documentation. This
version has some API changes with respect to the version currently in
Python (also the one in 1.5.2a).
This version supports XML namespaces.
-- Sjoerd Mullender <Sjoerd.Mullender@cwi.nl>
<URL:http://www.cwi.nl/~sjoerd/>
------- =_aaaaaaaaaa0
Content-Type: text/plain; charset="us-ascii"
Content-ID: <10433.914002226.2@bireme.cwi.nl>
Content-Description: xmllib.py
Content-Disposition: attachment; filename="xmllib.py"
# A parser for XML, using the derived class as static DTD.
# Author: Sjoerd Mullender.
import re
import string
version = '0.2'
# 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 arbutrary chunks). Entity references are
# passed by calling self.handle_entityref() with the entity reference
# as argument.
class XMLParser:
attributes = {} # default, to be overridden
elements = {} # default, to be overridden
# Interface -- initialize and reset this instance
def __init__(self):
self.reset()
# 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.__namespaces = {'xml':None} # xml is implicitly declared
# 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)
# Interface -- translate references
def translate_references(self, data, all = 1):
i = 0
while 1:
res = amp.search(data, i)
if res is None:
return data
res = ref.match(data, res.start(0))
if res is None:
self.syntax_error("bogus `&'")
i =i+1
continue
i = res.end(0)
if data[i - 1] != ';':
self.syntax_error("`;' missing after entity/char reference")
i = i-1
str = res.group(1)
pre = data[:res.start(0)]
post = data[i:]
if str[0] == '#':
if str[1] == 'x':
str = chr(string.atoi(str[2:], 16))
else:
str = chr(string.atoi(str[1:]))
data = pre + str + post
i = res.start(0)+len(str)
elif all:
if self.entitydefs.has_key(str):
data = pre + self.entitydefs[str] + post
i = res.start(0) # rescan substituted text
else:
self.syntax_error('reference to unknown entity')
# can't do it, so keep the entity ref in
data = pre + '&' + str + ';' + post
i = res.start(0) + len(str) + 2
else:
# just translating character references
pass # i is already postioned correctly
# 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 + string.count(data, '\n')
i = n
break
res = interesting.search(rawdata, i)
if res:
j = res.start(0)
else:
j = n
if i < j:
if self.__at_start:
self.syntax_error('illegal data at start of file')
self.__at_start = 0
data = rawdata[i:j]
if not self.stack and space.match(data) is None:
self.syntax_error('data not in content')
if illegal.search(data):
self.syntax_error('illegal character in content')
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\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 + string.count(data, '\n')
i = i+1
continue
k = self.parse_starttag(i)
if k < 0: break
self.__seen_starttag = 1
self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
i = k
continue
if endtagopen.match(rawdata, i):
k = self.parse_endtag(i)
if k < 0: break
self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
i = k
continue
if commentopen.match(rawdata, i):
if self.literal:
data = rawdata[i]
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\n')
i = i+1
continue
k = self.parse_comment(i)
if k < 0: break
self.lineno = self.lineno + string.count(rawdata[i:k], '\n')
i = k
continue
if cdataopen.match(rawdata, i):
k = self.parse_cdata(i)
if k < 0: break
self.lineno = self.lineno + string.count(rawdata[i:i], '\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")
version, encoding, standalone = res.group('version',
'encoding',
'standalone')
if version[1:-1] != '1.0':
raise RuntimeError, '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 + string.count(rawdata[i:k], '\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 + string.count(data, '\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')
self.lineno = self.lineno + string.count(rawdata[i:k], '\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 + string.count(res.group(0), '\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.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.syntax_error('reference to unknown entity')
self.unknown_entityref(name)
self.lineno = self.lineno + string.count(res.group(0), '\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 RuntimeError, '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 illegal.search(data):
self.syntax_error('illegal character in content')
self.handle_data(data)
self.lineno = self.lineno + string.count(data, '\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 RuntimeError, '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 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')
pubid, syslit = res.group('pubid', 'syslit')
if pubid is not None:
pubid = pubid[1:-1] # remove quotes
pubid = string.join(string.split(pubid)) # 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 RuntimeError, 'unexpected call to parse_cdata'
res = cdataclose.search(rawdata, i+9)
if res is None:
return -1
if 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 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 RuntimeError, 'unexpected call to parse_proc'
k = res.end(0)
name = res.group(0)
if name == 'xml:namespace':
self.syntax_error('old-fashioned namespace declaration')
# 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 string.find(string.lower(name), 'xml') >= 0:
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')
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]
else:
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
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 = string.translate(attrvalue, 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 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))
res = qname.match(tagname)
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 != '':
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
nattrdict = {}
for key, val in attrdict.items():
res = qname.match(key)
if res is not None:
aprefix, key = res.group('prefix', 'local')
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
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'" % (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
self.syntax_error('no name specified in end tag')
tag = ''
k = i+2
else:
tag = res.group(0)
if self.literal:
if not self.stack or tag != self.stack[-1][0]:
self.handle_data(rawdata[i])
return i+1
self.literal = 0
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):
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')
method = self.elements.get(tag, (None, None))[1]
if method is not None:
self.handle_endtag(tag, method)
else:
self.unknown_endtag(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)
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 = string.atoi(name[1:], 16)
else:
n = string.atoi(name)
except string.atoi_error:
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': '<', # must use charref
'gt': '>',
'amp': '&', # must use charref
'quot': '"',
'apos': ''',
}
# Example -- handle entity reference, no need to override
def handle_entityref(self, name):
table = self.entitydefs
if table.has_key(name):
self.handle_data(table[name])
else:
self.unknown_entityref(name)
return
# 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 RuntimeError, '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, ref): pass
class TestXMLParser(XMLParser):
def __init__(self):
self.testdata = ""
XMLParser.__init__(self)
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_entity(self, name, strval, pubid, syslit, ndata):
self.flush()
print 'ENTITY:',`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
if not args:
args = sys.argv[1:]
if args and args[0] == '-s':
args = args[1:]
klass = XMLParser
else:
klass = TestXMLParser
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()
try:
for c in data:
x.feed(c)
x.close()
except RuntimeError, msg:
print msg
sys.exit(1)
if __name__ == '__main__':
test()
------- =_aaaaaaaaaa0
Content-Type: text/plain; charset="us-ascii"
Content-ID: <10433.914002226.3@bireme.cwi.nl>
Content-Description: libxmllib.tex
Content-Disposition: attachment; filename="libxmllib.tex"
\section{\module{xmllib} ---
A parser for XML documents.}
% Author: Sjoerd Mullender
\declaremodule{standard}{xmllib}
\modulesynopsis{A parser for XML documents.}
\index{XML}
This module defines a class \class{XMLParser} which serves as the basis
for parsing text files formatted in XML (eXtended Markup Language).
\begin{classdesc}{XMLParser}{}
The \class{XMLParser} class must be instantiated without arguments.
\end{classdesc}
This class provides the following interface methods and instance variables:
\begin{memberdesc}{attributes}
A mapping of element names to mappings. The latter mapping maps
attribute names that are valid for the element to the default value of
the attribute, or if there is no default to \code{None}. The default
value is the empty dictionary.
\end{memberdesc}
\begin{memberdesc}{elements}
A mapping of element names to tuples. The tuples contain a function
for handling the start and end tag respectively of the element, or
\code{None} if the method \method{unknown_starttag()} or
\method{unknown_endtag()} is to be called. The default value is the
empty dictionary.
\end{memberdesc}
\begin{memberdesc}{entitydefs}
A mapping of entitynames to their values. The default value contains
definitions for \code{'lt'}, \code{'gt'}, \code{'amp'}, \code{'quot'},
and \code{'apos'}.
\end{memberdesc}
\begin{methoddesc}{reset}{}
Reset the instance. Loses all unprocessed data. This is called
implicitly at the instantiation time.
\end{methoddesc}
\begin{methoddesc}{setnomoretags}{}
Stop processing tags. Treat all following input as literal input
(CDATA).
\end{methoddesc}
\begin{methoddesc}{setliteral}{}
Enter literal mode (CDATA mode). This mode is automatically exited
when the close tag matching the last unclosed open tag is encountered.
\end{methoddesc}
\begin{methoddesc}{feed}{data}
Feed some text to the parser. It is processed insofar as it consists
of complete tags; incomplete data is buffered until more data is
fed or \method{close()} is called.
\end{methoddesc}
\begin{methoddesc}{close}{}
Force processing of all buffered data as if it were followed by an
end-of-file mark. This method may be redefined by a derived class to
define additional processing at the end of the input, but the
redefined version should always call \method{close()}.
\end{methoddesc}
\begin{methoddesc}{translate_references}{data}
Translate all entity and character references in \var{data} and
returns the translated string.
\end{methoddesc}
\begin{methoddesc}{handle_xml}{encoding, standalone}
This method is called when the \samp{<?xml ...?>} tag is processed.
The arguments are the values of the encoding and standalone attributes
in the tag. Both encoding and standalone are optional. The values
passed to \method{handle_xml()} default to \code{None} and the string
\code{'no'} respectively.
\end{methoddesc}
\begin{methoddesc}{handle_doctype}{tag, data}
This method is called when the \samp{<!DOCTYPE...>} tag is processed.
The arguments are the name of the root element and the uninterpreted
contents of the tag, starting after the white space after the name of
the root element.
\end{methoddesc}
\begin{methoddesc}{handle_starttag}{tag, method, attributes}
This method is called to handle start tags for which a start tag
handler is defined in the instance variable \member{elements}. The
\var{tag} argument is the name of the tag, and the \var{method}
argument is the function (method) which should be used to support semantic
interpretation of the start tag. The \var{attributes} argument is a
dictionary of attributes, the key being the \var{name} and the value
being the \var{value} of the attribute found inside the tag's
\code{<>} brackets. Character and entity references in the
\var{value} have been interpreted. For instance, for the start tag
\code{<A HREF="http://www.cwi.nl/">}, this method would be called as
\code{handle_starttag('A', self.elements['A'][0], \{'HREF': 'http://www.cwi.nl/'\})}.
The base implementation simply calls \var{method} with \var{attributes}
as the only argument.
\end{methoddesc}
\begin{methoddesc}{handle_endtag}{tag, method}
This method is called to handle endtags for which an end tag handler
is defined in the instance variable \member{elements}. The \var{tag}
argument is the name of the tag, and the \var{method} argument is the
function (method) which should be used to support semantic
interpretation of the end tag. For instance, for the endtag
\code{</A>}, this method would be called as \code{handle_endtag('A',
self.elements['A'][1])}. The base implementation simply calls
\var{method}.
\end{methoddesc}
\begin{methoddesc}{handle_data}{data}
This method is called to process arbitrary data. It is intended to be
overridden by a derived class; the base class implementation does
nothing.
\end{methoddesc}
\begin{methoddesc}{handle_charref}{ref}
This method is called to process a character reference of the form
\samp{\&\#\var{ref};}. \var{ref} can either be a decimal number,
or a hexadecimal number when preceded by an \character{x}.
In the base implementation, \var{ref} must be a number in the
range 0-255. It translates the character to \ASCII{} and calls the
method \method{handle_data()} with the character as argument. If
\var{ref} is invalid or out of range, the method
\code{unknown_charref(\var{ref})} is called to handle the error. A
subclass must override this method to provide support for character
references outside of the \ASCII{} range.
\end{methoddesc}
\begin{methoddesc}{handle_entityref}{ref}
This method is called to process a general entity reference of the
form \samp{\&\var{ref};} where \var{ref} is an general entity
reference. It looks for \var{ref} in the instance (or class)
variable \member{entitydefs} which should be a mapping from entity
names to corresponding translations.
If a translation is found, it calls the method \method{handle_data()}
with the translation; otherwise, it calls the method
\code{unknown_entityref(\var{ref})}. The default \member{entitydefs}
defines translations for \code{\&}, \code{\&apos}, \code{\>},
\code{\<}, and \code{\"}.
\end{methoddesc}
\begin{methoddesc}{handle_comment}{comment}
This method is called when a comment is encountered. The
\var{comment} argument is a string containing the text between the
\samp{<!--} and \samp{-->} delimiters, but not the delimiters
themselves. For example, the comment \samp{<!--text-->} will
cause this method to be called with the argument \code{'text'}. The
default method does nothing.
\end{methoddesc}
\begin{methoddesc}{handle_cdata}{data}
This method is called when a CDATA element is encountered. The
\var{data} argument is a string containing the text between the
\samp{<![CDATA[} and \samp{]]>} delimiters, but not the delimiters
themselves. For example, the entity \samp{<![CDATA[text]]>} will
cause this method to be called with the argument \code{'text'}. The
default method does nothing, and is intended to be overridden.
\end{methoddesc}
\begin{methoddesc}{handle_proc}{name, data}
This method is called when a processing instruction (PI) is
encountered. The \var{name} is the PI target, and the \var{data}
argument is a string containing the text between the PI target and the
closing delimiter, but not the delimiter itself. For example, the
instruction \samp{<?XML text?>} will cause this method to be called
with the arguments \code{'XML'} and \code{'text'}. The default method
does nothing. Note that if a document starts with \samp{<?xml
...?>}, \method{handle_xml()} is called to handle it.
\end{methoddesc}
\begin{methoddesc}{handle_special}{data}
This method is called when a declaration is encountered. The
\var{data} argument is a string containing the text between the
\samp{<!} and \samp{>} delimiters, but not the delimiters
themselves. For example, the entity \samp{<!ENTITY text>} will
cause this method to be called with the argument \code{'ENTITY text'}. The
default method does nothing. Note that \samp{<!DOCTYPE ...>} is
handled separately if it is located at the start of the document.
\end{methoddesc}
\begin{methoddesc}{syntax_error}{message}
This method is called when a syntax error is encountered. The
\var{message} is a description of what was wrong. The default method
raises a \exception{RuntimeError} exception. If this method is
overridden, it is permissable for it to return. This method is only
called when the error can be recovered from. Unrecoverable errors
raise a \exception{RuntimeError} without first calling
\method{syntax_error()}.
\end{methoddesc}
\begin{methoddesc}{unknown_starttag}{tag, attributes}
This method is called to process an unknown start tag. It is intended
to be overridden by a derived class; the base class implementation
does nothing.
\end{methoddesc}
\begin{methoddesc}{unknown_endtag}{tag}
This method is called to process an unknown end tag. It is intended
to be overridden by a derived class; the base class implementation
does nothing.
\end{methoddesc}
\begin{methoddesc}{unknown_charref}{ref}
This method is called to process unresolvable numeric character
references. It is intended to be overridden by a derived class; the
base class implementation does nothing.
\end{methoddesc}
\begin{methoddesc}{unknown_entityref}{ref}
This method is called to process an unknown entity reference. It is
intended to be overridden by a derived class; the base class
implementation does nothing.
\end{methoddesc}
\subsection{XML Namespaces}
This module has support for XML namespaces as defined in the XML
Namespaces proposed recommendation.
Tag and attribute names that are defined in an XML namespace are
handled as if the name of the tag or element consisted of the
namespace (i.e. the URL that defines the namespace) followed by a
space and the name of the tag or attribute. For instance, the tag
\code{<html xmlns='http://www.w3.org/TR/REC-html40'>} is treated as if
the tag name was \code{'http://www.w3.org/TR/REC-html40 html'}, and
the tag \code{<html:a href='http://frob.com'>} inside the above
mentioned element is treated as if the tag name were
\code{'http://www.w3.org/TR/REC-html40 a'} and the attribute name as
if it were \code{'http://www.w3.org/TR/REC-html40 src'}.
An older draft of the XML Namespaces proposal is also recognized, but
triggers a warning.
------- =_aaaaaaaaaa0--