* Implement C14N 2.0 as a new canonicalize() function in ElementTree.
Missing features:
- prefix renaming in XPath expressions (tag and attribute text is supported)
- preservation of original prefixes given redundant namespace declarations
Functions
^^^^^^^^^
+.. function:: canonicalize(xml_data=None, *, out=None, from_file=None, **options)
+
+ `C14N 2.0 <https://www.w3.org/TR/xml-c14n2/>`_ transformation function.
+
+ Canonicalization is a way to normalise XML output in a way that allows
+ byte-by-byte comparisons and digital signatures. It reduced the freedom
+ that XML serializers have and instead generates a more constrained XML
+ representation. The main restrictions regard the placement of namespace
+ declarations, the ordering of attributes, and ignorable whitespace.
+
+ This function takes an XML data string (*xml_data*) or a file path or
+ file-like object (*from_file*) as input, converts it to the canonical
+ form, and writes it out using the *out* file(-like) object, if provided,
+ or returns it as a text string if not. The output file receives text,
+ not bytes. It should therefore be opened in text mode with ``utf-8``
+ encoding.
+
+ Typical uses::
+
+ xml_data = "<root>...</root>"
+ print(canonicalize(xml_data))
+
+ with open("c14n_output.xml", mode='w', encoding='utf-8') as out_file:
+ canonicalize(xml_data, out=out_file)
+
+ with open("c14n_output.xml", mode='w', encoding='utf-8') as out_file:
+ canonicalize(from_file="inputfile.xml", out=out_file)
+
+ The configuration *options* are as follows:
+
+ - *with_comments*: set to true to include comments (default: false)
+ - *strip_text*: set to true to strip whitespace before and after text content
+ (default: false)
+ - *rewrite_prefixes*: set to true to replace namespace prefixes by "n{number}"
+ (default: false)
+ - *qname_aware_tags*: a set of qname aware tag names in which prefixes
+ should be replaced in text content (default: empty)
+ - *qname_aware_attrs*: a set of qname aware attribute names in which prefixes
+ should be replaced in text content (default: empty)
+ - *exclude_attrs*: a set of attribute names that should not be serialised
+ - *exclude_tags*: a set of tag names that should not be serialised
+
+ In the option list above, "a set" refers to any collection or iterable of
+ strings, no ordering is expected.
+
+ .. versionadded:: 3.8
+
.. function:: Comment(text=None)
.. versionadded:: 3.8
+.. class:: C14NWriterTarget(write, *, \
+ with_comments=False, strip_text=False, rewrite_prefixes=False, \
+ qname_aware_tags=None, qname_aware_attrs=None, \
+ exclude_attrs=None, exclude_tags=None)
+
+ A `C14N 2.0 <https://www.w3.org/TR/xml-c14n2/>`_ writer. Arguments are the
+ same as for the :func:`canonicalize` function. This class does not build a
+ tree but translates the callback events directly into a serialised form
+ using the *write* function.
+
+ .. versionadded:: 3.8
+
+
.. _elementtree-xmlparser-objects:
XMLParser Objects
external entities by default.
(Contributed by Christian Heimes in :issue:`17239`.)
+* The :mod:`xml.etree.ElementTree` module provides a new function
+ :func:`–xml.etree.ElementTree.canonicalize()` that implements C14N 2.0.
+ (Contributed by Stefan Behnel in :issue:`13611`.)
+
Optimizations
=============
import itertools
import locale
import operator
+import os
import pickle
import sys
import textwrap
import warnings
import weakref
+from functools import partial
from itertools import product, islice
from test import support
from test.support import TESTFN, findfile, import_fresh_module, gc_collect, swap_attr
self.assertIsInstance(pyET.Element.__init__, types.FunctionType)
self.assertIsInstance(pyET.XMLParser.__init__, types.FunctionType)
+
+# --------------------------------------------------------------------
+
+def c14n_roundtrip(xml, **options):
+ return pyET.canonicalize(xml, **options)
+
+
+class C14NTest(unittest.TestCase):
+ maxDiff = None
+
+ #
+ # simple roundtrip tests (from c14n.py)
+
+ def test_simple_roundtrip(self):
+ # Basics
+ self.assertEqual(c14n_roundtrip("<doc/>"), '<doc></doc>')
+ self.assertEqual(c14n_roundtrip("<doc xmlns='uri'/>"), # FIXME
+ '<doc xmlns="uri"></doc>')
+ self.assertEqual(c14n_roundtrip("<prefix:doc xmlns:prefix='uri'/>"),
+ '<prefix:doc xmlns:prefix="uri"></prefix:doc>')
+ self.assertEqual(c14n_roundtrip("<doc xmlns:prefix='uri'><prefix:bar/></doc>"),
+ '<doc><prefix:bar xmlns:prefix="uri"></prefix:bar></doc>')
+ self.assertEqual(c14n_roundtrip("<elem xmlns:wsu='http://docs.oasis-open.org/wss/2004/01/oasis-200401-wss-wssecurity-utility-1.0.xsd' xmlns:SOAP-ENV='http://schemas.xmlsoap.org/soap/envelope/' />"),
+ '<elem></elem>')
+
+ # C14N spec
+ self.assertEqual(c14n_roundtrip("<doc>Hello, world!<!-- Comment 1 --></doc>"),
+ '<doc>Hello, world!</doc>')
+ self.assertEqual(c14n_roundtrip("<value>2</value>"),
+ '<value>2</value>')
+ self.assertEqual(c14n_roundtrip('<compute><![CDATA[value>"0" && value<"10" ?"valid":"error"]]></compute>'),
+ '<compute>value>"0" && value<"10" ?"valid":"error"</compute>')
+ self.assertEqual(c14n_roundtrip('''<compute expr='value>"0" && value<"10" ?"valid":"error"'>valid</compute>'''),
+ '<compute expr="value>"0" && value<"10" ?"valid":"error"">valid</compute>')
+ self.assertEqual(c14n_roundtrip("<norm attr=' '   
	 ' '/>"),
+ '<norm attr=" \' 
	 \' "></norm>')
+ self.assertEqual(c14n_roundtrip("<normNames attr=' A   
	 B '/>"),
+ '<normNames attr=" A 
	 B "></normNames>')
+ self.assertEqual(c14n_roundtrip("<normId id=' '   
	 ' '/>"),
+ '<normId id=" \' 
	 \' "></normId>')
+
+ # fragments from PJ's tests
+ #self.assertEqual(c14n_roundtrip("<doc xmlns:x='http://example.com/x' xmlns='http://example.com/default'><b y:a1='1' xmlns='http://example.com/default' a3='3' xmlns:y='http://example.com/y' y:a2='2'/></doc>"),
+ #'<doc xmlns:x="http://example.com/x"><b xmlns:y="http://example.com/y" a3="3" y:a1="1" y:a2="2"></b></doc>')
+
+ def test_c14n_exclusion(self):
+ xml = textwrap.dedent("""\
+ <root xmlns:x="http://example.com/x">
+ <a x:attr="attrx">
+ <b>abtext</b>
+ </a>
+ <b>btext</b>
+ <c>
+ <x:d>dtext</x:d>
+ </c>
+ </root>
+ """)
+ self.assertEqual(
+ c14n_roundtrip(xml, strip_text=True),
+ '<root>'
+ '<a xmlns:x="http://example.com/x" x:attr="attrx"><b>abtext</b></a>'
+ '<b>btext</b>'
+ '<c><x:d xmlns:x="http://example.com/x">dtext</x:d></c>'
+ '</root>')
+ self.assertEqual(
+ c14n_roundtrip(xml, strip_text=True, exclude_attrs=['{http://example.com/x}attr']),
+ '<root>'
+ '<a><b>abtext</b></a>'
+ '<b>btext</b>'
+ '<c><x:d xmlns:x="http://example.com/x">dtext</x:d></c>'
+ '</root>')
+ self.assertEqual(
+ c14n_roundtrip(xml, strip_text=True, exclude_tags=['{http://example.com/x}d']),
+ '<root>'
+ '<a xmlns:x="http://example.com/x" x:attr="attrx"><b>abtext</b></a>'
+ '<b>btext</b>'
+ '<c></c>'
+ '</root>')
+ self.assertEqual(
+ c14n_roundtrip(xml, strip_text=True, exclude_attrs=['{http://example.com/x}attr'],
+ exclude_tags=['{http://example.com/x}d']),
+ '<root>'
+ '<a><b>abtext</b></a>'
+ '<b>btext</b>'
+ '<c></c>'
+ '</root>')
+ self.assertEqual(
+ c14n_roundtrip(xml, strip_text=True, exclude_tags=['a', 'b']),
+ '<root>'
+ '<c><x:d xmlns:x="http://example.com/x">dtext</x:d></c>'
+ '</root>')
+ self.assertEqual(
+ c14n_roundtrip(xml, exclude_tags=['a', 'b']),
+ '<root>\n'
+ ' \n'
+ ' \n'
+ ' <c>\n'
+ ' <x:d xmlns:x="http://example.com/x">dtext</x:d>\n'
+ ' </c>\n'
+ '</root>')
+ self.assertEqual(
+ c14n_roundtrip(xml, strip_text=True, exclude_tags=['{http://example.com/x}d', 'b']),
+ '<root>'
+ '<a xmlns:x="http://example.com/x" x:attr="attrx"></a>'
+ '<c></c>'
+ '</root>')
+ self.assertEqual(
+ c14n_roundtrip(xml, exclude_tags=['{http://example.com/x}d', 'b']),
+ '<root>\n'
+ ' <a xmlns:x="http://example.com/x" x:attr="attrx">\n'
+ ' \n'
+ ' </a>\n'
+ ' \n'
+ ' <c>\n'
+ ' \n'
+ ' </c>\n'
+ '</root>')
+
+ #
+ # basic method=c14n tests from the c14n 2.0 specification. uses
+ # test files under xmltestdata/c14n-20.
+
+ # note that this uses generated C14N versions of the standard ET.write
+ # output, not roundtripped C14N (see above).
+
+ def test_xml_c14n2(self):
+ datadir = findfile("c14n-20", subdir="xmltestdata")
+ full_path = partial(os.path.join, datadir)
+
+ files = [filename[:-4] for filename in sorted(os.listdir(datadir))
+ if filename.endswith('.xml')]
+ input_files = [
+ filename for filename in files
+ if filename.startswith('in')
+ ]
+ configs = {
+ filename: {
+ # <c14n2:PrefixRewrite>sequential</c14n2:PrefixRewrite>
+ option.tag.split('}')[-1]: ((option.text or '').strip(), option)
+ for option in ET.parse(full_path(filename) + ".xml").getroot()
+ }
+ for filename in files
+ if filename.startswith('c14n')
+ }
+
+ tests = {
+ input_file: [
+ (filename, configs[filename.rsplit('_', 1)[-1]])
+ for filename in files
+ if filename.startswith(f'out_{input_file}_')
+ and filename.rsplit('_', 1)[-1] in configs
+ ]
+ for input_file in input_files
+ }
+
+ # Make sure we found all test cases.
+ self.assertEqual(30, len([
+ output_file for output_files in tests.values()
+ for output_file in output_files]))
+
+ def get_option(config, option_name, default=None):
+ return config.get(option_name, (default, ()))[0]
+
+ for input_file, output_files in tests.items():
+ for output_file, config in output_files:
+ keep_comments = get_option(
+ config, 'IgnoreComments') == 'true' # no, it's right :)
+ strip_text = get_option(
+ config, 'TrimTextNodes') == 'true'
+ rewrite_prefixes = get_option(
+ config, 'PrefixRewrite') == 'sequential'
+ if 'QNameAware' in config:
+ qattrs = [
+ f"{{{el.get('NS')}}}{el.get('Name')}"
+ for el in config['QNameAware'][1].findall(
+ '{http://www.w3.org/2010/xml-c14n2}QualifiedAttr')
+ ]
+ qtags = [
+ f"{{{el.get('NS')}}}{el.get('Name')}"
+ for el in config['QNameAware'][1].findall(
+ '{http://www.w3.org/2010/xml-c14n2}Element')
+ ]
+ else:
+ qtags = qattrs = None
+
+ # Build subtest description from config.
+ config_descr = ','.join(
+ f"{name}={value or ','.join(c.tag.split('}')[-1] for c in children)}"
+ for name, (value, children) in sorted(config.items())
+ )
+
+ with self.subTest(f"{output_file}({config_descr})"):
+ if input_file == 'inNsRedecl' and not rewrite_prefixes:
+ self.skipTest(
+ f"Redeclared namespace handling is not supported in {output_file}")
+ if input_file == 'inNsSuperfluous' and not rewrite_prefixes:
+ self.skipTest(
+ f"Redeclared namespace handling is not supported in {output_file}")
+ if 'QNameAware' in config and config['QNameAware'][1].find(
+ '{http://www.w3.org/2010/xml-c14n2}XPathElement') is not None:
+ self.skipTest(
+ f"QName rewriting in XPath text is not supported in {output_file}")
+
+ f = full_path(input_file + ".xml")
+ if input_file == 'inC14N5':
+ # Hack: avoid setting up external entity resolution in the parser.
+ with open(full_path('world.txt'), 'rb') as entity_file:
+ with open(f, 'rb') as f:
+ f = io.BytesIO(f.read().replace(b'&ent2;', entity_file.read()))
+
+ text = ET.canonicalize(
+ from_file=f,
+ with_comments=keep_comments,
+ strip_text=strip_text,
+ rewrite_prefixes=rewrite_prefixes,
+ qname_aware_tags=qtags, qname_aware_attrs=qattrs)
+
+ with open(full_path(output_file + ".xml"), 'r', encoding='utf8') as f:
+ expected = f.read()
+ if input_file == 'inC14N3':
+ # FIXME: cET resolves default attributes but ET does not!
+ expected = expected.replace(' attr="default"', '')
+ text = text.replace(' attr="default"', '')
+ self.assertEqual(expected, text)
+
# --------------------------------------------------------------------
XMLParserTest,
XMLPullParserTest,
BugsTest,
+ KeywordArgsTest,
+ C14NTest,
]
# These tests will only run for the pure-Python version that doesn't import
--- /dev/null
+<dsig:CanonicalizationMethod xmlns:dsig="http://www.w3.org/2000/09/xmldsig#" xmlns:c14n2="http://www.w3.org/2010/xml-c14n2" Algorithm="http://www.w3.org/2010/xml-c14n2">
+ <c14n2:IgnoreComments>true</c14n2:IgnoreComments>
+</dsig:CanonicalizationMethod>
+
--- /dev/null
+<dsig:CanonicalizationMethod xmlns:dsig="http://www.w3.org/2000/09/xmldsig#" Algorithm="http://www.w3.org/2010/xml-c14n2">
+</dsig:CanonicalizationMethod>
+
--- /dev/null
+<dsig:CanonicalizationMethod xmlns:dsig="http://www.w3.org/2000/09/xmldsig#" xmlns:c14n2="http://www.w3.org/2010/xml-c14n2" Algorithm="http://www.w3.org/2010/xml-c14n2">
+ <c14n2:PrefixRewrite>sequential</c14n2:PrefixRewrite>
+</dsig:CanonicalizationMethod>
+
--- /dev/null
+<dsig:CanonicalizationMethod xmlns:dsig="http://www.w3.org/2000/09/xmldsig#" xmlns:c14n2="http://www.w3.org/2010/xml-c14n2" Algorithm="http://www.w3.org/2010/xml-c14n2">
+ <c14n2:PrefixRewrite>sequential</c14n2:PrefixRewrite>
+ <c14n2:QNameAware>
+ <c14n2:QualifiedAttr Name="type" NS="http://www.w3.org/2001/XMLSchema-instance"/>
+ </c14n2:QNameAware>
+</dsig:CanonicalizationMethod>
+
--- /dev/null
+<dsig:CanonicalizationMethod xmlns:dsig="http://www.w3.org/2000/09/xmldsig#" xmlns:c14n2="http://www.w3.org/2010/xml-c14n2" Algorithm="http://www.w3.org/2010/xml-c14n2">
+ <c14n2:PrefixRewrite>sequential</c14n2:PrefixRewrite>
+ <c14n2:QNameAware>
+ <c14n2:Element Name="bar" NS="http://a"/>
+ <c14n2:XPathElement Name="IncludedXPath" NS="http://www.w3.org/2010/xmldsig2#"/>
+ </c14n2:QNameAware>
+</dsig:CanonicalizationMethod>
+
--- /dev/null
+<dsig:CanonicalizationMethod xmlns:dsig="http://www.w3.org/2000/09/xmldsig#" xmlns:c14n2="http://www.w3.org/2010/xml-c14n2" Algorithm="http://www.w3.org/2010/xml-c14n2">
+ <c14n2:QNameAware>
+ <c14n2:QualifiedAttr Name="type" NS="http://www.w3.org/2001/XMLSchema-instance"/>
+ </c14n2:QNameAware>
+</dsig:CanonicalizationMethod>
+
--- /dev/null
+<dsig:CanonicalizationMethod xmlns:dsig="http://www.w3.org/2000/09/xmldsig#" xmlns:c14n2="http://www.w3.org/2010/xml-c14n2" Algorithm="http://www.w3.org/2010/xml-c14n2">
+ <c14n2:QNameAware>
+ <c14n2:Element Name="bar" NS="http://a"/>
+ </c14n2:QNameAware>
+</dsig:CanonicalizationMethod>
+
--- /dev/null
+<dsig:CanonicalizationMethod xmlns:dsig="http://www.w3.org/2000/09/xmldsig#" xmlns:c14n2="http://www.w3.org/2010/xml-c14n2" Algorithm="http://www.w3.org/2010/xml-c14n2">
+ <c14n2:QNameAware>
+ <c14n2:Element Name="bar" NS="http://a"/>
+ <c14n2:XPathElement Name="IncludedXPath" NS="http://www.w3.org/2010/xmldsig2#"/>
+ </c14n2:QNameAware>
+</dsig:CanonicalizationMethod>
+
--- /dev/null
+<dsig:CanonicalizationMethod xmlns:dsig="http://www.w3.org/2000/09/xmldsig#" xmlns:c14n2="http://www.w3.org/2010/xml-c14n2" Algorithm="http://www.w3.org/2010/xml-c14n2">
+ <c14n2:TrimTextNodes>true</c14n2:TrimTextNodes>
+</dsig:CanonicalizationMethod>
+
--- /dev/null
+<?xml version="1.0" encoding="UTF-8"?>
+
+<!ELEMENT doc (#PCDATA)>
+
+
+
--- /dev/null
+<?xml version="1.0"?>
+<xsl:stylesheet version="1.0"
+ xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
+ >
+</xsl:stylesheet>
--- /dev/null
+<?xml version="1.0"?>
+
+<?xml-stylesheet href="doc.xsl"
+ type="text/xsl" ?>
+
+<!DOCTYPE doc SYSTEM "doc.dtd">
+
+<doc>Hello, world!<!-- Comment 1 --></doc>
+
+<?pi-without-data ?>
+
+<!-- Comment 2 -->
+
+<!-- Comment 3 -->
--- /dev/null
+<doc>
+ <clean> </clean>
+ <dirty> A B </dirty>
+ <mixed>
+ A
+ <clean> </clean>
+ B
+ <dirty> A B </dirty>
+ C
+ </mixed>
+</doc>
--- /dev/null
+<!DOCTYPE doc [<!ATTLIST e9 attr CDATA "default">]>
+<doc>
+ <e1 />
+ <e2 ></e2>
+ <e3 name = "elem3" id="elem3" />
+ <e4 name="elem4" id="elem4" ></e4>
+ <e5 a:attr="out" b:attr="sorted" attr2="all" attr="I'm"
+ xmlns:b="http://www.ietf.org"
+ xmlns:a="http://www.w3.org"
+ xmlns="http://example.org"/>
+ <e6 xmlns="" xmlns:a="http://www.w3.org">
+ <e7 xmlns="http://www.ietf.org">
+ <e8 xmlns="" xmlns:a="http://www.w3.org">
+ <e9 xmlns="" xmlns:a="http://www.ietf.org"/>
+ </e8>
+ </e7>
+ </e6>
+</doc>
--- /dev/null
+<!DOCTYPE doc [
+<!ATTLIST normId id ID #IMPLIED>
+<!ATTLIST normNames attr NMTOKENS #IMPLIED>
+]>
+<doc>
+ <text>First line
 Second line</text>
+ <value>2</value>
+ <compute><![CDATA[value>"0" && value<"10" ?"valid":"error"]]></compute>
+ <compute expr='value>"0" && value<"10" ?"valid":"error"'>valid</compute>
+ <norm attr=' '   
	 ' '/>
+ <normNames attr=' A   
	 B '/>
+ <normId id=' '  
	 ' '/>
+</doc>
--- /dev/null
+<!DOCTYPE doc [
+<!ATTLIST doc attrExtEnt CDATA #IMPLIED>
+<!ENTITY ent1 "Hello">
+<!ENTITY ent2 SYSTEM "world.txt">
+<!ENTITY entExt SYSTEM "earth.gif" NDATA gif>
+<!NOTATION gif SYSTEM "viewgif.exe">
+]>
+<doc attrExtEnt="entExt">
+ &ent1;, &ent2;!
+</doc>
+
+<!-- Let world.txt contain "world" (excluding the quotes) -->
--- /dev/null
+<?xml version="1.0" encoding="ISO-8859-1"?>
+<doc>©</doc>
--- /dev/null
+<a:foo xmlns:a="http://a" xmlns:b="http://b" xmlns:child="http://c" xmlns:soap-env="http://schemas.xmlsoap.org/wsdl/soap/" xmlns:xsd="http://www.w3.org/2001/XMLSchema">
+ <a:bar>xsd:string</a:bar>
+ <dsig2:IncludedXPath xmlns:dsig2="http://www.w3.org/2010/xmldsig2#">/soap-env:body/child::b:foo[@att1 != "c:val" and @att2 != 'xsd:string']</dsig2:IncludedXPath>
+</a:foo>
--- /dev/null
+<foo xmlns:a="http://a" xmlns:b="http://b">
+ <b:bar b:att1="val" att2="val"/>
+</foo>
--- /dev/null
+<a:foo xmlns:a="http://a" xmlns:b="http://b" xmlns:c="http://c">
+ <b:bar/>
+ <b:bar/>
+ <b:bar/>
+ <a:bar b:att1="val"/>
+</a:foo>
--- /dev/null
+<foo xmlns:a="http://z3" xmlns:b="http://z2" a:att1="val1" b:att2="val2">
+ <bar xmlns="http://z0" xmlns:a="http://z2" a:att1="val1" b:att2="val2" xmlns:b="http://z3" />
+</foo>
--- /dev/null
+<a:foo xmlns:a="http://z3" xmlns:b="http://z2" b:att1="val1" c:att3="val3" b:att2="val2" xmlns:c="http://z1" xmlns:d="http://z0">
+ <c:bar/>
+ <c:bar d:att3="val3"/>
+</a:foo>
--- /dev/null
+<foo xmlns:a="http://z0" xmlns:b="http://z0" a:att1="val1" b:att2="val2" xmlns="http://z0">
+ <c:bar xmlns:a="http://z0" xmlns:c="http://z0" c:att3="val3"/>
+ <d:bar xmlns:d="http://z0"/>
+</foo>
--- /dev/null
+<foo xmlns="http://z0" xml:id="23">
+ <bar xsi:type="xsd:string" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema">data</bar>
+</foo>
--- /dev/null
+<?xml-stylesheet href="doc.xsl"
+ type="text/xsl" ?>
+<doc>Hello, world!<!-- Comment 1 --></doc>
+<?pi-without-data?>
+<!-- Comment 2 -->
+<!-- Comment 3 -->
\ No newline at end of file
--- /dev/null
+<?xml-stylesheet href="doc.xsl"
+ type="text/xsl" ?>
+<doc>Hello, world!</doc>
+<?pi-without-data?>
\ No newline at end of file
--- /dev/null
+<doc>
+ <clean> </clean>
+ <dirty> A B </dirty>
+ <mixed>
+ A
+ <clean> </clean>
+ B
+ <dirty> A B </dirty>
+ C
+ </mixed>
+</doc>
\ No newline at end of file
--- /dev/null
+<doc><clean></clean><dirty>A B</dirty><mixed>A<clean></clean>B<dirty>A B</dirty>C</mixed></doc>
\ No newline at end of file
--- /dev/null
+<doc>
+ <e1></e1>
+ <e2></e2>
+ <e3 id="elem3" name="elem3"></e3>
+ <e4 id="elem4" name="elem4"></e4>
+ <e5 xmlns="http://example.org" xmlns:a="http://www.w3.org" xmlns:b="http://www.ietf.org" attr="I'm" attr2="all" b:attr="sorted" a:attr="out"></e5>
+ <e6>
+ <e7 xmlns="http://www.ietf.org">
+ <e8 xmlns="">
+ <e9 attr="default"></e9>
+ </e8>
+ </e7>
+ </e6>
+</doc>
\ No newline at end of file
--- /dev/null
+<n0:doc xmlns:n0="">
+ <n0:e1></n0:e1>
+ <n0:e2></n0:e2>
+ <n0:e3 id="elem3" name="elem3"></n0:e3>
+ <n0:e4 id="elem4" name="elem4"></n0:e4>
+ <n1:e5 xmlns:n1="http://example.org" xmlns:n2="http://www.ietf.org" xmlns:n3="http://www.w3.org" attr="I'm" attr2="all" n2:attr="sorted" n3:attr="out"></n1:e5>
+ <n0:e6>
+ <n2:e7 xmlns:n2="http://www.ietf.org">
+ <n0:e8>
+ <n0:e9 attr="default"></n0:e9>
+ </n0:e8>
+ </n2:e7>
+ </n0:e6>
+</n0:doc>
\ No newline at end of file
--- /dev/null
+<doc><e1></e1><e2></e2><e3 id="elem3" name="elem3"></e3><e4 id="elem4" name="elem4"></e4><e5 xmlns="http://example.org" xmlns:a="http://www.w3.org" xmlns:b="http://www.ietf.org" attr="I'm" attr2="all" b:attr="sorted" a:attr="out"></e5><e6><e7 xmlns="http://www.ietf.org"><e8 xmlns=""><e9 attr="default"></e9></e8></e7></e6></doc>
\ No newline at end of file
--- /dev/null
+<doc>
+ <text>First line
+Second line</text>
+ <value>2</value>
+ <compute>value>"0" && value<"10" ?"valid":"error"</compute>
+ <compute expr="value>"0" && value<"10" ?"valid":"error"">valid</compute>
+ <norm attr=" ' 
	 ' "></norm>
+ <normNames attr="A 
	 B"></normNames>
+ <normId id="' 
	 '"></normId>
+</doc>
\ No newline at end of file
--- /dev/null
+<doc><text>First line
+Second line</text><value>2</value><compute>value>"0" && value<"10" ?"valid":"error"</compute><compute expr="value>"0" && value<"10" ?"valid":"error"">valid</compute><norm attr=" ' 
	 ' "></norm><normNames attr="A 
	 B"></normNames><normId id="' 
	 '"></normId></doc>
\ No newline at end of file
--- /dev/null
+<doc attrExtEnt="entExt">
+ Hello, world!
+</doc>
\ No newline at end of file
--- /dev/null
+<doc attrExtEnt="entExt">Hello, world!</doc>
\ No newline at end of file
--- /dev/null
+<doc>©</doc>
\ No newline at end of file
--- /dev/null
+<a:foo xmlns:a="http://a">
+ <a:bar>xsd:string</a:bar>
+ <dsig2:IncludedXPath xmlns:dsig2="http://www.w3.org/2010/xmldsig2#">/soap-env:body/child::b:foo[@att1 != "c:val" and @att2 != 'xsd:string']</dsig2:IncludedXPath>
+</a:foo>
\ No newline at end of file
--- /dev/null
+<n0:foo xmlns:n0="http://a">
+ <n0:bar xmlns:n1="http://www.w3.org/2001/XMLSchema">n1:string</n0:bar>
+ <n4:IncludedXPath xmlns:n2="http://b" xmlns:n3="http://schemas.xmlsoap.org/wsdl/soap/" xmlns:n4="http://www.w3.org/2010/xmldsig2#">/n3:body/child::n2:foo[@att1 != "c:val" and @att2 != 'xsd:string']</n4:IncludedXPath>
+</n0:foo>
\ No newline at end of file
--- /dev/null
+<a:foo xmlns:a="http://a">
+ <a:bar xmlns:xsd="http://www.w3.org/2001/XMLSchema">xsd:string</a:bar>
+ <dsig2:IncludedXPath xmlns:dsig2="http://www.w3.org/2010/xmldsig2#">/soap-env:body/child::b:foo[@att1 != "c:val" and @att2 != 'xsd:string']</dsig2:IncludedXPath>
+</a:foo>
\ No newline at end of file
--- /dev/null
+<a:foo xmlns:a="http://a">
+ <a:bar xmlns:xsd="http://www.w3.org/2001/XMLSchema">xsd:string</a:bar>
+ <dsig2:IncludedXPath xmlns:b="http://b" xmlns:dsig2="http://www.w3.org/2010/xmldsig2#" xmlns:soap-env="http://schemas.xmlsoap.org/wsdl/soap/">/soap-env:body/child::b:foo[@att1 != "c:val" and @att2 != 'xsd:string']</dsig2:IncludedXPath>
+</a:foo>
\ No newline at end of file
--- /dev/null
+<foo>
+ <b:bar xmlns:b="http://b" att2="val" b:att1="val"></b:bar>
+</foo>
\ No newline at end of file
--- /dev/null
+<n0:foo xmlns:n0="">
+ <n1:bar xmlns:n1="http://b" att2="val" n1:att1="val"></n1:bar>
+</n0:foo>
\ No newline at end of file
--- /dev/null
+<a:foo xmlns:a="http://a">
+ <b:bar xmlns:b="http://b"></b:bar>
+ <b:bar xmlns:b="http://b"></b:bar>
+ <b:bar xmlns:b="http://b"></b:bar>
+ <a:bar xmlns:b="http://b" b:att1="val"></a:bar>
+</a:foo>
\ No newline at end of file
--- /dev/null
+<n0:foo xmlns:n0="http://a">
+ <n1:bar xmlns:n1="http://b"></n1:bar>
+ <n1:bar xmlns:n1="http://b"></n1:bar>
+ <n1:bar xmlns:n1="http://b"></n1:bar>
+ <n0:bar xmlns:n1="http://b" n1:att1="val"></n0:bar>
+</n0:foo>
\ No newline at end of file
--- /dev/null
+<foo xmlns:a="http://z3" xmlns:b="http://z2" b:att2="val2" a:att1="val1">
+ <bar xmlns="http://z0" xmlns:a="http://z2" xmlns:b="http://z3" a:att1="val1" b:att2="val2"></bar>
+</foo>
\ No newline at end of file
--- /dev/null
+<n0:foo xmlns:n0="" xmlns:n1="http://z2" xmlns:n2="http://z3" n1:att2="val2" n2:att1="val1">
+ <n3:bar xmlns:n3="http://z0" n1:att1="val1" n2:att2="val2"></n3:bar>
+</n0:foo>
\ No newline at end of file
--- /dev/null
+<a:foo xmlns:a="http://z3" xmlns:b="http://z2" xmlns:c="http://z1" c:att3="val3" b:att1="val1" b:att2="val2">
+ <c:bar></c:bar>
+ <c:bar xmlns:d="http://z0" d:att3="val3"></c:bar>
+</a:foo>
\ No newline at end of file
--- /dev/null
+<n2:foo xmlns:n0="http://z1" xmlns:n1="http://z2" xmlns:n2="http://z3" n0:att3="val3" n1:att1="val1" n1:att2="val2">
+ <n0:bar></n0:bar>
+ <n0:bar xmlns:n3="http://z0" n3:att3="val3"></n0:bar>
+</n2:foo>
\ No newline at end of file
--- /dev/null
+<foo xmlns="http://z0" xmlns:a="http://z0" xmlns:b="http://z0" a:att1="val1" b:att2="val2">
+ <c:bar xmlns:c="http://z0" c:att3="val3"></c:bar>
+ <d:bar xmlns:d="http://z0"></d:bar>
+</foo>
\ No newline at end of file
--- /dev/null
+<n0:foo xmlns:n0="http://z0" n0:att1="val1" n0:att2="val2">
+ <n0:bar n0:att3="val3"></n0:bar>
+ <n0:bar></n0:bar>
+</n0:foo>
\ No newline at end of file
--- /dev/null
+<foo xmlns="http://z0" xml:id="23">
+ <bar xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:type="xsd:string">data</bar>
+</foo>
\ No newline at end of file
--- /dev/null
+<n0:foo xmlns:n0="http://z0" xml:id="23">
+ <n0:bar xmlns:n1="http://www.w3.org/2001/XMLSchema-instance" n1:type="xsd:string">data</n0:bar>
+</n0:foo>
\ No newline at end of file
--- /dev/null
+<n0:foo xmlns:n0="http://z0" xml:id="23">
+ <n0:bar xmlns:n1="http://www.w3.org/2001/XMLSchema" xmlns:n2="http://www.w3.org/2001/XMLSchema-instance" n2:type="n1:string">data</n0:bar>
+</n0:foo>
\ No newline at end of file
--- /dev/null
+<foo xmlns="http://z0" xml:id="23">
+ <bar xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:type="xsd:string">data</bar>
+</foo>
\ No newline at end of file
--- /dev/null
+world
\ No newline at end of file
"XML", "XMLID",
"XMLParser", "XMLPullParser",
"register_namespace",
+ "canonicalize", "C14NWriterTarget",
]
VERSION = "1.3.0"
del self.target, self._target
+# --------------------------------------------------------------------
+# C14N 2.0
+
+def canonicalize(xml_data=None, *, out=None, from_file=None, **options):
+ """Convert XML to its C14N 2.0 serialised form.
+
+ If *out* is provided, it must be a file or file-like object that receives
+ the serialised canonical XML output (text, not bytes) through its ``.write()``
+ method. To write to a file, open it in text mode with encoding "utf-8".
+ If *out* is not provided, this function returns the output as text string.
+
+ Either *xml_data* (an XML string) or *from_file* (a file path or
+ file-like object) must be provided as input.
+
+ The configuration options are the same as for the ``C14NWriterTarget``.
+ """
+ if xml_data is None and from_file is None:
+ raise ValueError("Either 'xml_data' or 'from_file' must be provided as input")
+ sio = None
+ if out is None:
+ sio = out = io.StringIO()
+
+ parser = XMLParser(target=C14NWriterTarget(out.write, **options))
+
+ if xml_data is not None:
+ parser.feed(xml_data)
+ parser.close()
+ elif from_file is not None:
+ parse(from_file, parser=parser)
+
+ return sio.getvalue() if sio is not None else None
+
+
+_looks_like_prefix_name = re.compile(r'^\w+:\w+$', re.UNICODE).match
+
+
+class C14NWriterTarget:
+ """
+ Canonicalization writer target for the XMLParser.
+
+ Serialises parse events to XML C14N 2.0.
+
+ The *write* function is used for writing out the resulting data stream
+ as text (not bytes). To write to a file, open it in text mode with encoding
+ "utf-8" and pass its ``.write`` method.
+
+ Configuration options:
+
+ - *with_comments*: set to true to include comments
+ - *strip_text*: set to true to strip whitespace before and after text content
+ - *rewrite_prefixes*: set to true to replace namespace prefixes by "n{number}"
+ - *qname_aware_tags*: a set of qname aware tag names in which prefixes
+ should be replaced in text content
+ - *qname_aware_attrs*: a set of qname aware attribute names in which prefixes
+ should be replaced in text content
+ - *exclude_attrs*: a set of attribute names that should not be serialised
+ - *exclude_tags*: a set of tag names that should not be serialised
+ """
+ def __init__(self, write, *,
+ with_comments=False, strip_text=False, rewrite_prefixes=False,
+ qname_aware_tags=None, qname_aware_attrs=None,
+ exclude_attrs=None, exclude_tags=None):
+ self._write = write
+ self._data = []
+ self._with_comments = with_comments
+ self._strip_text = strip_text
+ self._exclude_attrs = set(exclude_attrs) if exclude_attrs else None
+ self._exclude_tags = set(exclude_tags) if exclude_tags else None
+
+ self._rewrite_prefixes = rewrite_prefixes
+ if qname_aware_tags:
+ self._qname_aware_tags = set(qname_aware_tags)
+ else:
+ self._qname_aware_tags = None
+ if qname_aware_attrs:
+ self._find_qname_aware_attrs = set(qname_aware_attrs).intersection
+ else:
+ self._find_qname_aware_attrs = None
+
+ # Stack with globally and newly declared namespaces as (uri, prefix) pairs.
+ self._declared_ns_stack = [[
+ ("http://www.w3.org/XML/1998/namespace", "xml"),
+ ]]
+ # Stack with user declared namespace prefixes as (uri, prefix) pairs.
+ self._ns_stack = []
+ if not rewrite_prefixes:
+ self._ns_stack.append(list(_namespace_map.items()))
+ self._ns_stack.append([])
+ self._prefix_map = {}
+ self._preserve_space = [False]
+ self._pending_start = None
+ self._root_seen = False
+ self._root_done = False
+ self._ignored_depth = 0
+
+ def _iter_namespaces(self, ns_stack, _reversed=reversed):
+ for namespaces in _reversed(ns_stack):
+ if namespaces: # almost no element declares new namespaces
+ yield from namespaces
+
+ def _resolve_prefix_name(self, prefixed_name):
+ prefix, name = prefixed_name.split(':', 1)
+ for uri, p in self._iter_namespaces(self._ns_stack):
+ if p == prefix:
+ return f'{{{uri}}}{name}'
+ raise ValueError(f'Prefix {prefix} of QName "{prefixed_name}" is not declared in scope')
+
+ def _qname(self, qname, uri=None):
+ if uri is None:
+ uri, tag = qname[1:].rsplit('}', 1) if qname[:1] == '{' else ('', qname)
+ else:
+ tag = qname
+
+ prefixes_seen = set()
+ for u, prefix in self._iter_namespaces(self._declared_ns_stack):
+ if u == uri and prefix not in prefixes_seen:
+ return f'{prefix}:{tag}' if prefix else tag, tag, uri
+ prefixes_seen.add(prefix)
+
+ # Not declared yet => add new declaration.
+ if self._rewrite_prefixes:
+ if uri in self._prefix_map:
+ prefix = self._prefix_map[uri]
+ else:
+ prefix = self._prefix_map[uri] = f'n{len(self._prefix_map)}'
+ self._declared_ns_stack[-1].append((uri, prefix))
+ return f'{prefix}:{tag}', tag, uri
+
+ if not uri and '' not in prefixes_seen:
+ # No default namespace declared => no prefix needed.
+ return tag, tag, uri
+
+ for u, prefix in self._iter_namespaces(self._ns_stack):
+ if u == uri:
+ self._declared_ns_stack[-1].append((uri, prefix))
+ return f'{prefix}:{tag}' if prefix else tag, tag, uri
+
+ raise ValueError(f'Namespace "{uri}" is not declared in scope')
+
+ def data(self, data):
+ if not self._ignored_depth:
+ self._data.append(data)
+
+ def _flush(self, _join_text=''.join):
+ data = _join_text(self._data)
+ del self._data[:]
+ if self._strip_text and not self._preserve_space[-1]:
+ data = data.strip()
+ if self._pending_start is not None:
+ args, self._pending_start = self._pending_start, None
+ qname_text = data if data and _looks_like_prefix_name(data) else None
+ self._start(*args, qname_text)
+ if qname_text is not None:
+ return
+ if data and self._root_seen:
+ self._write(_escape_cdata_c14n(data))
+
+ def start_ns(self, prefix, uri):
+ if self._ignored_depth:
+ return
+ # we may have to resolve qnames in text content
+ if self._data:
+ self._flush()
+ self._ns_stack[-1].append((uri, prefix))
+
+ def start(self, tag, attrs):
+ if self._exclude_tags is not None and (
+ self._ignored_depth or tag in self._exclude_tags):
+ self._ignored_depth += 1
+ return
+ if self._data:
+ self._flush()
+
+ new_namespaces = []
+ self._declared_ns_stack.append(new_namespaces)
+
+ if self._qname_aware_tags is not None and tag in self._qname_aware_tags:
+ # Need to parse text first to see if it requires a prefix declaration.
+ self._pending_start = (tag, attrs, new_namespaces)
+ return
+ self._start(tag, attrs, new_namespaces)
+
+ def _start(self, tag, attrs, new_namespaces, qname_text=None):
+ if self._exclude_attrs is not None and attrs:
+ attrs = {k: v for k, v in attrs.items() if k not in self._exclude_attrs}
+
+ qnames = {tag, *attrs}
+ resolved_names = {}
+
+ # Resolve prefixes in attribute and tag text.
+ if qname_text is not None:
+ qname = resolved_names[qname_text] = self._resolve_prefix_name(qname_text)
+ qnames.add(qname)
+ if self._find_qname_aware_attrs is not None and attrs:
+ qattrs = self._find_qname_aware_attrs(attrs)
+ if qattrs:
+ for attr_name in qattrs:
+ value = attrs[attr_name]
+ if _looks_like_prefix_name(value):
+ qname = resolved_names[value] = self._resolve_prefix_name(value)
+ qnames.add(qname)
+ else:
+ qattrs = None
+ else:
+ qattrs = None
+
+ # Assign prefixes in lexicographical order of used URIs.
+ parse_qname = self._qname
+ parsed_qnames = {n: parse_qname(n) for n in sorted(
+ qnames, key=lambda n: n.split('}', 1))}
+
+ # Write namespace declarations in prefix order ...
+ if new_namespaces:
+ attr_list = [
+ ('xmlns:' + prefix if prefix else 'xmlns', uri)
+ for uri, prefix in new_namespaces
+ ]
+ attr_list.sort()
+ else:
+ # almost always empty
+ attr_list = []
+
+ # ... followed by attributes in URI+name order
+ if attrs:
+ for k, v in sorted(attrs.items()):
+ if qattrs is not None and k in qattrs and v in resolved_names:
+ v = parsed_qnames[resolved_names[v]][0]
+ attr_qname, attr_name, uri = parsed_qnames[k]
+ # No prefix for attributes in default ('') namespace.
+ attr_list.append((attr_qname if uri else attr_name, v))
+
+ # Honour xml:space attributes.
+ space_behaviour = attrs.get('{http://www.w3.org/XML/1998/namespace}space')
+ self._preserve_space.append(
+ space_behaviour == 'preserve' if space_behaviour
+ else self._preserve_space[-1])
+
+ # Write the tag.
+ write = self._write
+ write('<' + parsed_qnames[tag][0])
+ if attr_list:
+ write(''.join([f' {k}="{_escape_attrib_c14n(v)}"' for k, v in attr_list]))
+ write('>')
+
+ # Write the resolved qname text content.
+ if qname_text is not None:
+ write(_escape_cdata_c14n(parsed_qnames[resolved_names[qname_text]][0]))
+
+ self._root_seen = True
+ self._ns_stack.append([])
+
+ def end(self, tag):
+ if self._ignored_depth:
+ self._ignored_depth -= 1
+ return
+ if self._data:
+ self._flush()
+ self._write(f'</{self._qname(tag)[0]}>')
+ self._preserve_space.pop()
+ self._root_done = len(self._preserve_space) == 1
+ self._declared_ns_stack.pop()
+ self._ns_stack.pop()
+
+ def comment(self, text):
+ if not self._with_comments:
+ return
+ if self._ignored_depth:
+ return
+ if self._root_done:
+ self._write('\n')
+ elif self._root_seen and self._data:
+ self._flush()
+ self._write(f'<!--{_escape_cdata_c14n(text)}-->')
+ if not self._root_seen:
+ self._write('\n')
+
+ def pi(self, target, data):
+ if self._ignored_depth:
+ return
+ if self._root_done:
+ self._write('\n')
+ elif self._root_seen and self._data:
+ self._flush()
+ self._write(
+ f'<?{target} {_escape_cdata_c14n(data)}?>' if data else f'<?{target}?>')
+ if not self._root_seen:
+ self._write('\n')
+
+
+def _escape_cdata_c14n(text):
+ # escape character data
+ try:
+ # it's worth avoiding do-nothing calls for strings that are
+ # shorter than 500 character, or so. assume that's, by far,
+ # the most common case in most applications.
+ if '&' in text:
+ text = text.replace('&', '&')
+ if '<' in text:
+ text = text.replace('<', '<')
+ if '>' in text:
+ text = text.replace('>', '>')
+ if '\r' in text:
+ text = text.replace('\r', '
')
+ return text
+ except (TypeError, AttributeError):
+ _raise_serialization_error(text)
+
+
+def _escape_attrib_c14n(text):
+ # escape attribute value
+ try:
+ if '&' in text:
+ text = text.replace('&', '&')
+ if '<' in text:
+ text = text.replace('<', '<')
+ if '"' in text:
+ text = text.replace('"', '"')
+ if '\t' in text:
+ text = text.replace('\t', '	')
+ if '\n' in text:
+ text = text.replace('\n', '
')
+ if '\r' in text:
+ text = text.replace('\r', '
')
+ return text
+ except (TypeError, AttributeError):
+ _raise_serialization_error(text)
+
+
+# --------------------------------------------------------------------
+
# Import the C accelerators
try:
# Element is going to be shadowed by the C implementation. We need to keep
--- /dev/null
+The xml.etree.ElementTree packages gained support for C14N 2.0 serialisation.
+Patch by Stefan Behnel.
projects / python / commitdiff