1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
|
#!/usr/bin/python -u
#
# this tests the DTD validation with the XmlTextReader interface
#
import sys
import glob
import string
import libxml2
try:
import StringIO
str_io = StringIO.StringIO
except:
import io
str_io = io.StringIO
# Memory debug specific
libxml2.debugMemory(1)
err=""
expect="""../../test/valid/rss.xml:177: element rss: validity error : Element rss does not carry attribute version
</rss>
^
../../test/valid/xlink.xml:450: element termdef: validity error : ID dt-arc already defined
<p><termdef id="dt-arc" term="Arc">An <ter
^
../../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 file.find("t8") != -1:
continue
if file == "../../test/valid/rss.xml":
continue
if file == "../../test/valid/xlink.xml":
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
14,#text
1,x
1,c
3,#text
15,c
15,x
14,#text
1,b
3,#text
15,b
14,#text
15,test
"""
res=""
err=""
input = libxml2.inputBuffer(str_io(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
14 #text
1 x
3 #text
15 x
14 #text
15 test
"""
res=""
def myResolver(URL, ID, ctxt):
if URL == "tst.ent":
return(str_io(tst_ent))
return None
libxml2.setEntityLoader(myResolver)
input = libxml2.inputBuffer(str_io(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
14 #text 1
1 x 1
1 y 2
3 #text 3
15 y 2
15 x 1
14 #text 1
1 x 1
1 y 2
3 #text 3
15 y 2
15 x 1
14 #text 1
15 test 0
"""
res=""
err=""
input = libxml2.inputBuffer(str_io(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
14 #text 1
5 x 1
14 #text 1
5 x 1
14 #text 1
15 test 0
"""
res=""
err=""
input = libxml2.inputBuffer(str_io(s))
reader = input.newTextReader("test5")
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()
|
