Change pyexpat test suite to exercise the .returns_unicode attribute,

parsing the sample data once with 8-bit strings and once with Unicode.

diff --git a/Lib/test/output/test_pyexpat b/Lib/test/output/test_pyexpat
index 6cba827553d091c816f0436d925ceee78f01b49d..b6facf9e22e2b4d68f838b8682f5be6887fe90bd 100644 (file)
--- a/Lib/test/output/test_pyexpat
+++ b/Lib/test/output/test_pyexpat
@@ -1,31 +1,91 @@
 test_pyexpat
 PI:
-       xml-stylesheet href="stylesheet.css"
+       'xml-stylesheet' 'href="stylesheet.css"'
 Comment:
        ' comment data '
 Notation declared: ('notation', None, 'notation.jpeg', None)
 Unparsed entity decl:
        ('unparsed_entity', None, 'entity.file', None, 'notation')
 Start element:
-       root {}
+       'root' {'attr1': 'value1', 'attr2': 'value2\341\275\200'}
 NS decl:
-       myns http://www.python.org/namespace
+       'myns' 'http://www.python.org/namespace'
 Start element:
-       http://www.python.org/namespace!subelement {}
+       'http://www.python.org/namespace!subelement' {}
 Character data:
        'Contents of subelements'
 End element:
-       http://www.python.org/namespace!subelement
+       'http://www.python.org/namespace!subelement'
 End of NS decl:
-       myns
+       'myns'
 Start element:
-       sub2 {}
+       'sub2' {}
 Start of CDATA section
 Character data:
        'contents of CDATA section'
 End of CDATA section
 End element:
-       sub2
-External entity ref: http://www.python.org/namespace=http://www.w3.org/XML/1998/namespace\fexternal_entity None entity.file None
+       'sub2'
+External entity ref: ('http://www.python.org/namespace=http://www.w3.org/XML/1998/namespace\014external_entity', None, 'entity.file', None)
 End element:
-       root
+       'root'
+PI:
+       u'xml-stylesheet' u'href="stylesheet.css"'
+Comment:
+       u' comment data '
+Notation declared: (u'notation', None, u'notation.jpeg', None)
+Unparsed entity decl:
+       (u'unparsed_entity', None, u'entity.file', None, u'notation')
+Start element:
+       u'root' {u'attr1': u'value1', u'attr2': u'value2\u1F40'}
+NS decl:
+       u'myns' u'http://www.python.org/namespace'
+Start element:
+       u'http://www.python.org/namespace!subelement' {}
+Character data:
+       u'Contents of subelements'
+End element:
+       u'http://www.python.org/namespace!subelement'
+End of NS decl:
+       u'myns'
+Start element:
+       u'sub2' {}
+Start of CDATA section
+Character data:
+       u'contents of CDATA section'
+End of CDATA section
+End element:
+       u'sub2'
+External entity ref: (u'http://www.python.org/namespace=http://www.w3.org/XML/1998/namespace\014external_entity', None, u'entity.file', None)
+End element:
+       u'root'
+PI:
+       u'xml-stylesheet' u'href="stylesheet.css"'
+Comment:
+       u' comment data '
+Notation declared: (u'notation', None, u'notation.jpeg', None)
+Unparsed entity decl:
+       (u'unparsed_entity', None, u'entity.file', None, u'notation')
+Start element:
+       u'root' {u'attr1': u'value1', u'attr2': u'value2\u1F40'}
+NS decl:
+       u'myns' u'http://www.python.org/namespace'
+Start element:
+       u'http://www.python.org/namespace!subelement' {}
+Character data:
+       u'Contents of subelements'
+End element:
+       u'http://www.python.org/namespace!subelement'
+End of NS decl:
+       u'myns'
+Start element:
+       u'sub2' {}
+Start of CDATA section
+Character data:
+       u'contents of CDATA section'
+End of CDATA section
+End element:
+       u'sub2'
+External entity ref: (u'http://www.python.org/namespace=http://www.w3.org/XML/1998/namespace\014external_entity', None, u'entity.file', None)
+End element:
+       u'root'

diff --git a/Lib/test/test_pyexpat.py b/Lib/test/test_pyexpat.py
index 9f6d8d08b658245d658d6505281fdcd27219b32b..d6bd84b30f607bdb72c2a12b01977a37b5b4da11 100644 (file)
--- a/Lib/test/test_pyexpat.py
+++ b/Lib/test/test_pyexpat.py
@@ -10,10 +10,10 @@ import pyexpat
                 
 class Outputter:
     def StartElementHandler(self, name, attrs):
-        print 'Start element:\n\t', name, attrs
+        print 'Start element:\n\t', repr(name), attrs
         
     def EndElementHandler(self, name):
-        print 'End element:\n\t', name
+        print 'End element:\n\t', repr(name)
 
     def CharacterDataHandler(self, data):
         data = string.strip(data)
@@ -22,13 +22,13 @@ class Outputter:
             print '\t', repr(data)
 
     def ProcessingInstructionHandler(self, target, data):
-        print 'PI:\n\t', target, data
+        print 'PI:\n\t', repr(target), repr(data)
 
     def StartNamespaceDeclHandler(self, prefix, uri):
-        print 'NS decl:\n\t', prefix, uri
+        print 'NS decl:\n\t', repr(prefix), repr(uri)
 
     def EndNamespaceDeclHandler(self, prefix):
-        print 'End of NS decl:\n\t', prefix
+        print 'End of NS decl:\n\t', repr(prefix)
 
     def StartCdataSectionHandler(self):
         print 'Start of CDATA section'
@@ -51,8 +51,9 @@ class Outputter:
         print 'Not standalone'
         return 1
         
-    def ExternalEntityRefHandler(self, context, base, sysId, pubId):
-        print 'External entity ref:', context, base, sysId, pubId
+    def ExternalEntityRefHandler(self, *args):
+        context, base, sysId, pubId = args
+        print 'External entity ref:', args
         return 1
 
     def DefaultHandler(self, userData):
@@ -64,7 +65,14 @@ class Outputter:
 
 out = Outputter()
 parser = pyexpat.ParserCreate(namespace_separator='!')
-for name in ['StartElementHandler', 'EndElementHandler',
+
+# Test getting/setting returns_unicode
+parser.returns_unicode = 0 ; assert parser.returns_unicode == 0
+parser.returns_unicode = 1 ; assert parser.returns_unicode == 1
+parser.returns_unicode = 2 ; assert parser.returns_unicode == 1
+parser.returns_unicode = 0 ; assert parser.returns_unicode == 0
+
+HANDLER_NAMES = ['StartElementHandler', 'EndElementHandler',
              'CharacterDataHandler', 'ProcessingInstructionHandler',
              'UnparsedEntityDeclHandler', 'NotationDeclHandler',
              'StartNamespaceDeclHandler', 'EndNamespaceDeclHandler',
@@ -73,7 +81,8 @@ for name in ['StartElementHandler', 'EndElementHandler',
              'DefaultHandler', 'DefaultHandlerExpand',
              #'NotStandaloneHandler',
              'ExternalEntityRefHandler'
-             ]:
+             ]
+for name in HANDLER_NAMES:
     setattr(parser, name, getattr(out, name) )
 
 data = """<?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
@@ -88,7 +97,7 @@ data = """<?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
 %unparsed_entity;
 ]>
 
-<root>
+<root attr1="value1" attr2="value2&#8000;">
 <myns:subelement xmlns:myns="http://www.python.org/namespace">
      Contents of subelements
 </myns:subelement>
@@ -97,6 +106,8 @@ data = """<?xml version="1.0" encoding="iso-8859-1" standalone="no"?>
 </root>
 """
 
+# Produce UTF-8 output
+parser.returns_unicode = 0
 try:
     parser.Parse(data, 1)
 except pyexpat.error:
@@ -105,3 +116,33 @@ except pyexpat.error:
     print '** Column', parser.ErrorColumnNumber
     print '** Byte', parser.ErrorByteIndex
 
+# Try the parse again, this time producing Unicode output
+parser = pyexpat.ParserCreate(namespace_separator='!')
+parser.returns_unicode = 1
+
+for name in HANDLER_NAMES:
+    setattr(parser, name, getattr(out, name) )
+try:
+    parser.Parse(data, 1)
+except pyexpat.error:
+    print '** Error', parser.ErrorCode, pyexpat.ErrorString( parser.ErrorCode)
+    print '** Line', parser.ErrorLineNumber
+    print '** Column', parser.ErrorColumnNumber
+    print '** Byte', parser.ErrorByteIndex
+
+# Try parsing a file
+parser = pyexpat.ParserCreate(namespace_separator='!')
+parser.returns_unicode = 1
+
+for name in HANDLER_NAMES:
+    setattr(parser, name, getattr(out, name) )
+import StringIO
+file = StringIO.StringIO(data)
+try:
+    parser.ParseFile(file)
+except pyexpat.error:
+    print '** Error', parser.ErrorCode, pyexpat.ErrorString( parser.ErrorCode)
+    print '** Line', parser.ErrorLineNumber
+    print '** Column', parser.ErrorColumnNumber
+    print '** Byte', parser.ErrorByteIndex
+