Skip to content

bpo-6686: Fix Lib.xml.sax.expatreader.GetProperty to return a string object #9715

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
ghost wants to merge 8 commits into from
Closed

bpo-6686: Fix Lib.xml.sax.expatreader.GetProperty to return a string object #9715

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
ad2faee
bpo 6686: xml.sax.xmlreader.XMLReader.getProperty
Oct 4, 2018
01146ad
Merge remote-tracking branch 'origin' into Issue6686
JonathanGossage Oct 4, 2018
6bd0b47
Merge branch 'master' of https://github.com/python/cpython into Issue…
JonathanGossage Oct 5, 2018
3c616f7
Cleanup style.
JonathanGossage Oct 5, 2018
afd7b3f
bpo-6686 Upgrade tests to chect input equal output.
JonathanGossage Oct 5, 2018
b6ce633
Upgrade test of property_xml_string to check all valid encodings
JonathanGossage Oct 15, 2018
26451d2
Merge branch 'master' of https://github.com/python/cpython.git into I…
JonathanGossage Oct 15, 2018
c2bb9db
Handle all supported encodings.
JonathanGossage Oct 17, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
74 changes: 72 additions & 2 deletions Lib/test/test_sax.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -13,7 +13,8 @@
from xml.sax.saxutils import XMLGenerator, escape, unescape, quoteattr, \
XMLFilterBase, prepare_input_source
from xml.sax.expatreader import create_parser
from xml.sax.handler import feature_namespaces, feature_external_ges
from xml.sax.handler import feature_namespaces, feature_external_ges,\
property_xml_string
from xml.sax.xmlreader import InputSource, AttributesImpl, AttributesNSImpl
from io import BytesIO, StringIO
import codecs
Expand Down Expand Up @@ -1311,6 +1312,73 @@ def test_nsattrs_wattr(self):
self.assertEqual(attrs.getQNameByName((ns_uri, "attr")), "ns:attr")


# ===========================================================================

@matrixise matrixise Oct 6, 2018

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Hi,

Could you remove these comments, they don't need to be in the source code.
Thank you

@taleinat taleinat Oct 7, 2018

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

If you look at the rest of this test module, you'll see that it is in keeping with its existing style. IMO this is fine.

#
# Sax parser property tests
#
# Currently only tests the condition reported in issue bpo-6686

@taleinat taleinat Oct 7, 2018 •
edited
Loading

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This note (the second line) shouldn't be in this comment block though, it should be in the class itself.

@ghost ghost Oct 8, 2018

Copy link
Copy Markdown
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Can you point me at something that discusses this idiom? I don't understand the rationale.

#
# ===========================================================================

class PropertyContentHandler(ContentHandler):
def __init__(self, test_harness, reader, test, *args, **kwargs):
super().__init__(*args, **kwargs)
self.test_harness = test_harness
self.reader = reader
self.test_data = test

def startElement(self, name, attr):
property_ = self.reader.getProperty(property_xml_string)
self.test_harness.assertIsInstance(property_, bytes)
if self.test_harness.test_data is not None:
prop = property_
self.test_harness\
.assertEqual(prop.decode(encoding=self.test_data[0]),
self.test_data[1][1])
super().startElement(name, attr)


class SaxPropertyTest(unittest.TestCase):
def __init__(self, *args, **kwargs):
super().__init__(*args, **kwargs)
self.result = None
self.test_data = [['ascii', ['Hello']],
['utf-8', ['abc˦']],
['iso-8859-1', ['ghiéñ']]]
for t in self.test_data:
d = '<test>{}</test>\n'.format(t[1][0])
t[1].append(d)

def test_property_xml_string_from_bytes(self):
for prolog in (True, False):
for t in self.test_data:
reader = create_parser()
reader.setContentHandler(PropertyContentHandler(self,
reader,
t))
source = InputSource()
data = b''
if prolog:
data += b'<?xml version="1.0" encoding="'
data += '{}'.format(t[0]).encode(encoding='ascii')
data += b'"?>\n'
data += t[1][1].encode(t[0])
source.setByteStream(BytesIO(data))
if not prolog:
source.setEncoding(t[0])
reader.parse(source)
pass

def test_property_xml_str_from_str(self):
self.test_data = None
reader = create_parser()
reader.setContentHandler(PropertyContentHandler(self,
reader,
None))
in_ = '<?xml version="1.0" encoding="UTF-8"?>\n<test>Hi there</test>'
reader.parse(StringIO(in_))


def test_main():
run_unittest(MakeParserTest,
ParseTest,
Expand All @@ -1323,7 +1391,9 @@ def test_main():
StreamReaderWriterXmlgenTest,
ExpatReaderTest,
ErrorReportingTest,
XmlReaderTest)
XmlReaderTest,
SaxPropertyTest)


if __name__ == "__main__":
test_main()
6 changes: 4 additions & 2 deletions Lib/xml/sax/expatreader.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,6 @@
pyexpat.__version__ == '2.22'.
"""

version = "0.20"

from xml.sax._exceptions import *
from xml.sax.handler import feature_validation, feature_namespaces
from xml.sax.handler import feature_namespace_prefixes
Expand All @@ -27,6 +25,8 @@
raise SAXReaderNotAvailable("expat not supported", None)
from xml.sax import xmlreader, saxutils, handler

version = "0.20"

AttributesImpl = xmlreader.AttributesImpl
AttributesNSImpl = xmlreader.AttributesNSImpl

Expand Down Expand Up @@ -266,12 +266,14 @@ def _reset_lex_handler_prop(self):
parser.EndCdataSectionHandler = None
parser.StartDoctypeDeclHandler = None
parser.EndDoctypeDeclHandler = None
parser.XmlDeclHandler = None
else:
parser.CommentHandler = lex.comment
parser.StartCdataSectionHandler = lex.startCDATA
parser.EndCdataSectionHandler = lex.endCDATA
parser.StartDoctypeDeclHandler = self.start_doctype_decl
parser.EndDoctypeDeclHandler = lex.endDTD
parser.XmlDeclHandler = lex.xml_decl_handler

def reset(self):
if self._namespaces:
Expand Down
1 change: 1 addition & 0 deletions Misc/ACKS
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -572,6 +572,7 @@ Chris Gonnerman
Shelley Gooch
David Goodger
Elliot Gorokhovsky
Jonathan Gossage
Hans de Graaff
Tim Graham
Kim Gräsman
Expand Down