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
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
|
import re
import pytest
# "gen" is the abbreviated name for "getentityname.py"
import gen
def test_should_raise_valueerror_in_rm_xml_comment_with_missing_closecomment():
with pytest.raises(ValueError, match=".* Missing '-->' .*"):
gen.remove_xml_comments("<!-- Wrong XML comment")
def test_should_raise_valueerror_in_rm_xml_comment_with_doubledashes():
with pytest.raises(ValueError):
gen.remove_xml_comments("<!-- Not--allowed-->")
@pytest.mark.parametrize("space", [
# space
" ",
# tab
"\t",
# newline
"\n",
# return
"\r"
])
def test_regex_space(space):
assert re.search(gen.SPACE, space)
@pytest.mark.parametrize("name", [
"a",
"A",
"abc",
"_",
"_ab",
":",
":foo",
"a:foo",
])
def test_regex_name(name):
assert re.search(gen.NAME, name)
#@pytest.mark.parametrize("qstr", [
#"'a'",
#'"a"',
#"'abc.def'",
#"'http://example.org/foo'",
#"'http://example.org/foo%20bar#xyz'",
#"'http://example.org/foo%20\"bar#xyz'",
#])
#def test_regex_qstr(qstr):
#assert re.search(gen.QSTR, qstr)
@pytest.mark.parametrize("sysid", [
"'a'",
'"a"',
"'abc.def'",
"'http://example.org/foo'",
"'http://example.org/foo%20bar#xyz'",
"'http://example.org/foo%20\"bar#xyz'",
])
def test_regex_systemliteral(sysid):
assert re.search(gen.SYSTEMLITERAL, sysid)
@pytest.mark.parametrize("pubid", [
"'-//OASIS//DTD DocBook XML V4.5//EN'",
'"-//OASIS//DTD DocBook XML V4.5//EN"',
"'ISO 8879:1986//ENTITIES Added Math Symbols: Arrow Relations//EN//XML'",
'"-//W3C//ENTITIES Extra for MathML 2.0//EN"',
'"urn:oasis:names:tc:entity:xmlns:xml:catalog"',
'"-//OASIS//DTD Entity Resolution XML Catalog V1.0//EN"',
'"http://www.w3.org/Graphics/SVG/1.1/rng/svg11.rng"',
])
def test_regex_publicliteral(pubid):
assert re.search(gen.PUBLICLITERAL, pubid)
@pytest.mark.parametrize("extid", [
"SYSTEM 'foo.dtd'",
'SYSTEM "foo.dtd"',
'SYSTEM\n"foo.dtd"',
'SYSTEM\t"foo.dtd"',
'''PUBLIC "-//OASIS//DTD DocBook XML V4.5//EN" "http://www.oasis-open.org/docbook/xml/4.5/docbookx.dtd"''',
'''PUBLIC\n"-//OASIS//DTD DocBook XML V4.5//EN"\n"http://www.oasis-open.org/docbook/xml/4.5/docbookx.dtd"''',
])
def test_regex_externalid(extid):
assert re.search(gen.EXTERNALID, extid, re.DOTALL|re.VERBOSE|re.MULTILINE)
@pytest.mark.parametrize("entity, expected", [
# no. 1
("""<!ENTITY % ents SYSTEM "entities.ent">""",
{'PEDecl': 'ents', 'pubid': None, 'sysid': '"entities.ent"'}
),
# no. 2
("""<!ENTITY\n% ents\nSYSTEM\n"entities.ent"\n >""",
{'PEDecl': 'ents', 'pubid': None, 'sysid': '"entities.ent"'}
),
# no. 3
("""<!ENTITY % ents PUBLIC "urn:x-test:tom" "http://www.example.org/ent">""",
{'PEDecl': 'ents',
'pubid': '"urn:x-test:tom"',
'sysid': '"http://www.example.org/ent"'}
),
# no. 4
("""<!ENTITY\n%\n\tents PUBLIC\t"urn:x-test:tom"\r "http://www.example.org/ent"\n >""",
{'PEDecl': 'ents',
'pubid': '"urn:x-test:tom"',
'sysid': '"http://www.example.org/ent"'}
),
# no. 5
("""<!ENTITY % phrases-entities SYSTEM "phrases-decl.ent">""",
{'PEDecl': 'phrases-entities',
'pubid': None,
'sysid': '"phrases-decl.ent"'}
),
])
def test_regex_entity(entity, expected):
match = re.search(gen.ENTITY, entity, re.DOTALL|re.VERBOSE|re.MULTILINE)
assert match
resultdict = match.groupdict()
resultdict.pop("quote", None)
assert resultdict == expected
DOCTYPE_TEST_DATA = (
# ID-Name, Data, Expected
# no. 1
("normal",
"<!DOCTYPE chapter>",
dict(Name='chapter', pubid=None, sysid=None)
),
# no. 2
("normal-with-linebreaks",
"<!DOCTYPE\nchapter \n>",
dict(Name='chapter', pubid=None, sysid=None)
),
# no. 3
("with-empty-intsubset",
"<!DOCTYPE\nchapter []\n>",
dict(Name='chapter', pubid=None, sysid=None)
),
# no. 4
("with-intsubset-oneline",
"""
<!DOCTYPE chapter [<!ENTITY % ents SYSTEM "entities.ent">]>""",
dict(Name='chapter', pubid=None, sysid=None)
),
# no. 5
("with-linebreaks",
"""
<!DOCTYPE
chapter
[
<!ENTITY % ents SYSTEM "entities.ent">
]
>""",
dict(Name='chapter', pubid=None, sysid=None)
),
# no. 6
("with-xml-declaration",
"""<?xml version="1.0"?>
<!DOCTYPE chapter
[
<!ENTITY % ents SYSTEM "entities.ent">
]>
""",
dict(Name='chapter', pubid=None, sysid=None)
),
# no. 7
("with-xml-declaration",
"""<?xml version="1.0"?>
<!DOCTYPE chapter SYSTEM "foo.dtd"
[
<!ENTITY % ents SYSTEM "entities.ent">
]>
""",
dict(Name='chapter',
pubid=None,
sysid='"foo.dtd"')
),
# no. 8
("with-public-identifier",
"""<!DOCTYPE chapter PUBLIC
"-//OASIS//DTD DocBook XML V4.5//EN"
"http://www.oasis-open.org/docbook/xml/4.5/docbookx.dtd"
[
<!ENTITY % ents SYSTEM "entities.ent">
]>
""",
dict(Name='chapter',
pubid='"-//OASIS//DTD DocBook XML V4.5//EN"',
sysid='"http://www.oasis-open.org/docbook/xml/4.5/docbookx.dtd"')
),
# no. 9
("with-public-identifier",
"""<!DOCTYPE chapter
PUBLIC
"-//OASIS//DTD DocBook XML V4.5//EN"
"http://www.oasis-open.org/docbook/xml/4.5/docbookx.dtd"
[
<!ENTITY % ents SYSTEM "entities.ent">
]
>""",
dict(Name='chapter',
pubid='"-//OASIS//DTD DocBook XML V4.5//EN"',
sysid='"http://www.oasis-open.org/docbook/xml/4.5/docbookx.dtd"')
),
# no. 10
("with-comment-before-doctype",
"""<!--
A very
long
XML
comment
-->
<!DOCTYPE chapter
[
<!ENTITY % ents SYSTEM "entities.ent">
]>
""",
dict(Name='chapter', pubid=None, sysid=None)
),
# no. 11
)
@pytest.mark.parametrize("header, expected",
[(data, expected) for _, data, expected in DOCTYPE_TEST_DATA],
ids=[name for name, _, _ in DOCTYPE_TEST_DATA]
)
def test_regex_doctype(header, expected):
# match = re.search(gen.DOCTYPE, header, re.VERBOSE|re.DOTALL|re.MULTILINE)
match = gen.r_DOCTYPE.search(header)
assert match
resultdict = match.groupdict()
resultdict.pop('IntSubset', None)
resultdict.pop("quote", None)
assert resultdict == expected
ENTITIES_TEST_DATA = (
# ID-Name, Data, Expected
# no. 1
("system",
"""<!ENTITY % ent SYSTEM "foo.ent">""",
{'PEDecl': 'ent',
'sysid': '"foo.ent"',
'pubid': None}
),
# no. 2
("public",
"""<!ENTITY % ent PUBLIC "-//TEST//ENTITIES V1.0//EN" "http://example.org/foo.ent">""",
{'PEDecl': 'ent',
'pubid': '"-//TEST//ENTITIES V1.0//EN"',
'sysid': '"http://example.org/foo.ent"',
}
),
# no. 3
("with-linebreaks",
"""
<!ENTITY % here
SYSTEM
"here.ent">
""",
{'PEDecl': 'here',
'sysid': '"here.ent"',
'pubid': None
}
),
)
@pytest.mark.parametrize("ent, expected",
[(data, expected) for _, data, expected in ENTITIES_TEST_DATA],
ids=[name for name, _, _ in ENTITIES_TEST_DATA]
)
def test_should_match_entities(ent, expected):
match = gen.r_ENTITY.search(ent)
assert match
# Remove quotes
# print(">>> match:", match.groupdict())
resultdict = match.groupdict()
resultdict.pop("quote", None)
assert resultdict == expected
def test_joinents():
assert gen.joinEnts(["a", "b"], "-") == "a-b"
|
