1
0
mirror of https://gitlab.gnome.org/GNOME/libxml2.git synced 2025-07-17 18:21:05 +03:00
Files
libxml2/python/tests/reader2.py
Daniel Veillard 067bae5ff8 seriously changed the way data are pushed to the underlying parser, go by
* xmlreader.c: seriously changed the way data are pushed to
  the underlying parser, go by block of 512 bytes instead of
  tryng to detect tag boundaries at that level. Changed the
  way empty element are detected and tagged.
* python/tests/reader.py python/tests/reader2.py
  python/tests/reader3.py: small changes mostly due to context
  reporting being different and DTD node being reported. Some
  errors previously undetected are now caught and fixed.
* doc/xmlreader.html: flagged last section as TODO
Daniel
2003-01-05 01:27:54 +00:00

257 lines
5.0 KiB
Python
Executable File

#!/usr/bin/python -u
#
# this tests the DTD validation with the XmlTextReader interface
#
import sys
import glob
import string
import StringIO
import libxml2
# Memory debug specific
libxml2.debugMemory(1)
err=""
expect="""../../test/valid/rss.xml:172: validity error: Element rss does not carry attribute version
</rss>
^
../../test/valid/xlink.xml:450: validity error: ID dt-arc already defined
<p><termdef id="dt-arc" term="Arc">An <term>arc</term> is contained within an
^
../../test/valid/xlink.xml:530: validity error: attribute def line 199 references an unknown ID "dt-xlg"
^
"""
def callback(ctx, str):
global err
err = err + "%s" % (str)
libxml2.registerErrorHandler(callback, "")
valid_files = glob.glob("../../test/valid/*.x*")
valid_files.sort()
for file in valid_files:
if string.find(file, "t8") != -1:
continue
reader = libxml2.newTextReaderFilename(file)
#print "%s:" % (file)
reader.SetParserProp(libxml2.PARSER_VALIDATE, 1)
ret = reader.Read()
while ret == 1:
ret = reader.Read()
if ret != 0:
print "Error parsing and validating %s" % (file)
#sys.exit(1)
if err != expect:
print err
#
# another separate test based on Stephane Bidoul one
#
s = """
<!DOCTYPE test [
<!ELEMENT test (x,b)>
<!ELEMENT x (c)>
<!ELEMENT b (#PCDATA)>
<!ELEMENT c (#PCDATA)>
<!ENTITY x "<x><c>xxx</c></x>">
]>
<test>
&x;
<b>bbb</b>
</test>
"""
expect="""10,test
1,test
3,#text
1,x
1,c
3,#text
15,c
15,x
3,#text
1,b
3,#text
15,b
3,#text
15,test
"""
res=""
err=""
input = libxml2.inputBuffer(StringIO.StringIO(s))
reader = input.newTextReader("test2")
reader.SetParserProp(libxml2.PARSER_LOADDTD,1)
reader.SetParserProp(libxml2.PARSER_DEFAULTATTRS,1)
reader.SetParserProp(libxml2.PARSER_SUBST_ENTITIES,1)
reader.SetParserProp(libxml2.PARSER_VALIDATE,1)
while reader.Read() == 1:
res = res + "%s,%s\n" % (reader.NodeType(),reader.Name())
if res != expect:
print "test2 failed: unexpected output"
print res
sys.exit(1)
if err != "":
print "test2 failed: validation error found"
print err
sys.exit(1)
#
# Another test for external entity parsing and validation
#
s = """<!DOCTYPE test [
<!ELEMENT test (x)>
<!ELEMENT x (#PCDATA)>
<!ENTITY e SYSTEM "tst.ent">
]>
<test>
&e;
</test>
"""
tst_ent = """<x>hello</x>"""
expect="""10 test
1 test
3 #text
1 x
3 #text
15 x
3 #text
15 test
"""
res=""
def myResolver(URL, ID, ctxt):
if URL == "tst.ent":
return(StringIO.StringIO(tst_ent))
return None
libxml2.setEntityLoader(myResolver)
input = libxml2.inputBuffer(StringIO.StringIO(s))
reader = input.newTextReader("test3")
reader.SetParserProp(libxml2.PARSER_LOADDTD,1)
reader.SetParserProp(libxml2.PARSER_DEFAULTATTRS,1)
reader.SetParserProp(libxml2.PARSER_SUBST_ENTITIES,1)
reader.SetParserProp(libxml2.PARSER_VALIDATE,1)
while reader.Read() == 1:
res = res + "%s %s\n" % (reader.NodeType(),reader.Name())
if res != expect:
print "test3 failed: unexpected output"
print res
sys.exit(1)
if err != "":
print "test3 failed: validation error found"
print err
sys.exit(1)
#
# Another test for recursive entity parsing, validation, and replacement of
# entities, making sure the entity ref node doesn't show up in that case
#
s = """<!DOCTYPE test [
<!ELEMENT test (x, x)>
<!ELEMENT x (y)>
<!ELEMENT y (#PCDATA)>
<!ENTITY x "<x>&y;</x>">
<!ENTITY y "<y>yyy</y>">
]>
<test>
&x;
&x;
</test>"""
expect="""10 test 0
1 test 0
3 #text 1
1 x 1
1 y 2
3 #text 3
15 y 2
15 x 1
3 #text 1
1 x 1
1 y 2
3 #text 3
15 y 2
15 x 1
3 #text 1
15 test 0
"""
res=""
err=""
input = libxml2.inputBuffer(StringIO.StringIO(s))
reader = input.newTextReader("test4")
reader.SetParserProp(libxml2.PARSER_LOADDTD,1)
reader.SetParserProp(libxml2.PARSER_DEFAULTATTRS,1)
reader.SetParserProp(libxml2.PARSER_SUBST_ENTITIES,1)
reader.SetParserProp(libxml2.PARSER_VALIDATE,1)
while reader.Read() == 1:
res = res + "%s %s %d\n" % (reader.NodeType(),reader.Name(),reader.Depth())
if res != expect:
print "test4 failed: unexpected output"
print res
sys.exit(1)
if err != "":
print "test4 failed: validation error found"
print err
sys.exit(1)
#
# The same test but without entity substitution this time
#
s = """<!DOCTYPE test [
<!ELEMENT test (x, x)>
<!ELEMENT x (y)>
<!ELEMENT y (#PCDATA)>
<!ENTITY x "<x>&y;</x>">
<!ENTITY y "<y>yyy</y>">
]>
<test>
&x;
&x;
</test>"""
expect="""10 test 0
1 test 0
3 #text 1
5 x 1
3 #text 1
5 x 1
3 #text 1
15 test 0
"""
res=""
err=""
input = libxml2.inputBuffer(StringIO.StringIO(s))
reader = input.newTextReader("test4")
reader.SetParserProp(libxml2.PARSER_VALIDATE,1)
while reader.Read() == 1:
res = res + "%s %s %d\n" % (reader.NodeType(),reader.Name(),reader.Depth())
if res != expect:
print "test5 failed: unexpected output"
print res
if err != "":
print "test5 failed: validation error found"
print err
#
# cleanup
#
del input
del reader
# Memory debug specific
libxml2.cleanupParser()
if libxml2.debugMemory(1) == 0:
print "OK"
else:
print "Memory leak %d bytes" % (libxml2.debugMemory(1))
libxml2.dumpMemory()