I'm having a problem using lxml.etree to make a treebuilding parser that validates; I have test code where invalid xml
is detected and an error raised when the line below target=ET.TreeBuilder(), is commented out.
The validation error looks as expected > python tlxml.py invalid.rml
re.compile('^.*(?:\\W|\\b)(?P<fn>dynamic_rml\\.dtd|rml\\.dtd|rml_0_2\\.dtd|rml_0_3\\.dtd|rml_1_0\\.dtd)$',
re.MULTILINE)
Resolving url='../rml.dtd' context=<lxml.etree._ParserContext object at
0x7f66103273c0> dtdPath='rml.dtd'
Traceback (most recent call last):
File "/home/robin/devel/reportlab/REPOS/rlextra/tmp/tlxml.py", line 78, in
<module>
tree = ET.parse(sys.argv[1],parser)
File "src/lxml/etree.pyx", line 3521, in lxml.etree.parse
File "src/lxml/parser.pxi", line 1859, in lxml.etree._parseDocument
File "src/lxml/parser.pxi", line 1885, in lxml.etree._parseDocumentFromURL
File "src/lxml/parser.pxi", line 1789, in lxml.etree._parseDocFromFile
File "src/lxml/parser.pxi", line 1177, in
lxml.etree._BaseParser._parseDocFromFile
File "src/lxml/parser.pxi", line 615, in
lxml.etree._ParserContext._handleParseResultDoc
File "src/lxml/parser.pxi", line 725, in lxml.etree._handleParseResult
File "src/lxml/parser.pxi", line 654, in lxml.etree._raiseParseError
File "invalid.rml", line 23
lxml.etree.XMLSyntaxError: No declaration for attribute x of element place1,
line 23, column 55
when I have the target=etree.TreeBuilder() active the validation does not work and the tree is formed and passed to the
primitive tuple tree builder so the output looks like
$ python tlxml.py invalid.rml
Resolving url='../rml.dtd' context=<lxml.etree._TargetParserContext object at 0x7f73d7b159c0> dtdPath='rml.dtd'
('document',
{'filename': 'test_000_simple.pdf', 'invariant': '1'},
['\n\n',
('stylesheet',
> ........
None,
44),
'\n \t\t\n \t\t'],
40),
'\n'],
35),
'\n\n'],
2)
If I use the standard example EchoTarget the validation also fails. So I assume that the target argument makes the
validation fail. Is there a way to get validation to work with a target?
The code is
######################################################################################################
from pprint import pprint
from lxml import etree as ET
import sys, os, re
from rlextra.rml2pdf.rml2pdf import CompatibleDTDNames as rmlDTDPat
rmlDTDPat = re.compile('^.*(?:\\W|\\b)(?P<fn>%s)$' % '|'.join((re.escape(_) for
_ in rmlDTDPat)),re.M)
class TT:
def __init__(self):
pass
def __call__(self,e):
return (e.tag,e.attrib or None,self.content(e),e.sourceline)
def content(self,e):
t = e.text
if len(e)==0 and t is None:
return t
else:
r = [].append
if t is not None: r(t)
for c in e:
r(self(c))
t = c.tail
if t is not None:
r(t)
return r.__self__
class RMLDTDResolver(ET.Resolver):
__dtds = None
def resolve(self, url, id, context):
m = rmlDTDPat.match(url)
if m:
if self.__dtds is None:
from rlextra import rml2pdf
self.__dtds = {}
for fn in ('rml.dtd','dynamic_rml.dtd'):
with
open(os.path.join(os.path.dirname(rml2pdf.__file__),fn),'r') as _:
self.__dtds[fn] = _.read()
fn = m.group('fn')
dtdPath = 'rml.dtd' if fn.startswith('rml') else 'dynamic.dtd'
print(f"Resolving url={url!r} context={context!r} {dtdPath=}")
return self.resolve_string(
self.__dtds[dtdPath],
context,
)
else:
return None
parser = ET.XMLParser(
load_dtd=True,
dtd_validation=True,
attribute_defaults=True,
no_network=True,
remove_comments=True,
remove_pis=True,
strip_cdata=True,
resolve_entities=True,
target=ET.TreeBuilder(), #if commented the parser
validates
)
parser.resolvers.add(RMLDTDResolver())
tree = ET.parse(sys.argv[1],parser)
pprint(TT()(tree))
######################################################################################################
--
https://mail.python.org/mailman/listinfo/python-list
