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
312
313
314
315
316
317
318
319
320
321
|
import re
import pytest
from linkify_it import LinkifyIt, SchemaError
from linkify_it.main import Match
from linkify_it.tlds import TLDS
def test_pretest_false():
linkifyit = LinkifyIt()
assert linkifyit.pretest("nolink") is False
def test_create_instance_with_schemas():
schemas = {"my:": {"validate": r"^\/\/[a-z]+"}}
linkifyit = LinkifyIt(schemas)
match = linkifyit.match("google.com. my:// my://asdf!")
assert match[0].text == "google.com"
assert match[1].text == "my://asdf"
def test_match_class():
linkifyit = LinkifyIt()
match = Match(linkifyit, 0)
assert (
match.__repr__()
== "linkify_it.main.Match({'schema': '', 'index': -1, 'last_index': -1, 'raw': '', 'text': '', 'url': ''})" # noqa: E501
)
def test_api_extend_tlds():
linkifyit = LinkifyIt()
assert linkifyit.test("google.myroot") is False
linkifyit.tlds("myroot", True)
assert linkifyit.test("google.myroot") is True
assert linkifyit.test("google.xyz") is False
# ref - http://data.iana.org/TLD/tlds-alpha-by-domain.txt
linkifyit.tlds(TLDS)
assert linkifyit.test("google.xyz") is True
assert linkifyit.test("google.myroot") is False
def test_api_add_rule_as_regex_with_default_normalizer():
linkifyit = LinkifyIt().add("my:", {"validate": re.compile(r"^\/\/[a-z]+")})
match = linkifyit.match("google.com. my:// my://asdf!")
assert match[0].text == "google.com"
assert match[1].text == "my://asdf"
def test_api_add_rule_as_regex_with_default_normalizer_with_no_compile():
linkifyit = LinkifyIt().add("my:", {"validate": r"^\/\/[a-z]+"})
match = linkifyit.match("google.com. my:// my://asdf!")
assert match[0].text == "google.com"
assert match[1].text == "my://asdf"
def test_api_add_rule_with_normalizer():
def func_normalize(self, m):
m.text = re.sub(r"^my://", "", m.text).upper()
m.url = m.url.upper()
linkifyit = LinkifyIt().add(
"my:", {"validate": re.compile(r"^\/\/[a-z]+"), "normalize": func_normalize}
)
match = linkifyit.match("google.com. my:// my://asdf!")
assert match[1].text == "ASDF"
assert match[1].url == "MY://ASDF"
def test_api_add_rule_with_normalizer_no_cimpile():
def func_normalize(self, m):
m.text = re.sub(r"^my://", "", m.text).upper()
m.url = m.url.upper()
linkifyit = LinkifyIt().add(
"my:", {"validate": r"^\/\/[a-z]+", "normalize": func_normalize}
)
match = linkifyit.match("google.com. my:// my://asdf!")
assert match[1].text == "ASDF"
assert match[1].url == "MY://ASDF"
def test_api_disable_rule():
linkifyit = LinkifyIt()
assert linkifyit.test("http://google.com")
assert linkifyit.test("foo@bar.com")
linkifyit.add("http:", None)
linkifyit.add("mailto:", None)
assert not linkifyit.test("http://google.com")
assert not linkifyit.test("foo@bar.com")
def test_api_add_bad_definition():
with pytest.raises(SchemaError):
linkifyit = LinkifyIt({"fuzzy_link": False})
linkifyit = LinkifyIt()
with pytest.raises(SchemaError):
linkifyit.add("test:", [])
linkifyit = LinkifyIt()
with pytest.raises(SchemaError):
linkifyit.add("test:", {"validate": []})
linkifyit = LinkifyIt()
with pytest.raises(SchemaError):
def func():
return False
linkifyit.add("test:", {"validate": func, "normalize": "bad"})
def test_api_at_position():
linkifyit = LinkifyIt()
assert linkifyit.test_schema_at("http://google.com", "http:", 5)
assert linkifyit.test_schema_at("http://google.com", "HTTP:", 5)
assert not linkifyit.test_schema_at("http://google.com", "http:", 6)
assert not linkifyit.test_schema_at("http://google.com", "bad_schema:", 6)
def test_api_correct_cache_value():
linkifyit = LinkifyIt()
match = linkifyit.match(".com. http://google.com google.com ftp://google.com")
assert match[0].text == "http://google.com"
assert match[1].text == "google.com"
assert match[2].text == "ftp://google.com"
def test_api_normalize():
linkifyit = LinkifyIt()
match = linkifyit.match("mailto:foo@bar.com")[0]
# assert match.text == "foo@bar.com"
assert match.url == "mailto:foo@bar.com"
match = linkifyit.match("foo@bar.com")[0]
# assert match.text == "foo@bar.com"
assert match.url == "mailto:foo@bar.com"
def test_api_twitter_rule():
linkifyit = LinkifyIt()
def validate(self, text, pos):
tail = text[pos:]
if not self.re.get("twitter"):
self.re["twitter"] = re.compile(
"^([a-zA-Z0-9_]){1,15}(?!_)(?=$|" + self.re["src_ZPCc"] + ")"
)
if self.re["twitter"].search(tail):
if pos > 2 and tail[pos - 2] == "@":
return False
return len(self.re["twitter"].search(tail).group())
return 0
def normalize(self, m):
m.url = "https://twitter.com/" + re.sub(r"^@", "", m.url)
linkifyit.add("@", {"validate": validate, "normalize": normalize})
assert linkifyit.match("hello, @gamajoba_!")[0].text == "@gamajoba_"
assert linkifyit.match(":@givi")[0].text == "@givi"
assert linkifyit.match(":@givi")[0].url == "https://twitter.com/givi"
assert not linkifyit.test("@@invalid")
def test_api_twitter_rule_no_compile():
linkifyit = LinkifyIt()
def validate(self, text, pos):
tail = text[pos:]
if not self.re.get("twitter"):
self.re["twitter"] = (
"^([a-zA-Z0-9_]){1,15}(?!_)(?=$|" + self.re["src_ZPCc"] + ")"
)
if re.search(self.re["twitter"], tail):
if pos > 2 and tail[pos - 2] == "@":
return False
return len(re.search(self.re["twitter"], tail).group())
return 0
def normalize(self, m):
m.url = "https://twitter.com/" + re.sub(r"^@", "", m.url)
linkifyit.add("@", {"validate": validate, "normalize": normalize})
assert linkifyit.match("hello, @gamajoba_!")[0].text == "@gamajoba_"
assert linkifyit.match(":@givi")[0].text == "@givi"
assert linkifyit.match(":@givi")[0].url == "https://twitter.com/givi"
assert not linkifyit.test("@@invalid")
def test_api_set_option_fuzzylink():
linkifyit = LinkifyIt(options={"fuzzy_link": False})
assert not linkifyit.test("google.com")
linkifyit.set({"fuzzy_link": True})
assert linkifyit.test("google.com")
assert linkifyit.match("google.com")[0].text == "google.com"
def test_api_set_option_fuzzyemail():
linkifyit = LinkifyIt(options={"fuzzy_email": False})
assert not linkifyit.test("foo@bar.com")
linkifyit.set({"fuzzy_email": True})
assert linkifyit.test("foo@bar.com")
assert linkifyit.match("foo@bar.com")[0].text == "foo@bar.com"
def test_api_set_option_fuzzyip():
linkifyit = LinkifyIt()
assert not linkifyit.test("1.1.1.1")
linkifyit.set({"fuzzy_ip": True})
assert linkifyit.test("1.1.1.1")
assert linkifyit.match("1.1.1.1")[0].text == "1.1.1.1"
def test_api_shoud_not_hang_in_fuzzy_mode_with_sequence_of_astrals():
linkifyit = LinkifyIt()
linkifyit.set({"fuzzy_link": True})
linkifyit.match("😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡😡 .com")
def test_api_shoud_accept_triple_minus():
linkifyit = LinkifyIt()
assert linkifyit.match("http://e.com/foo---bar")[0].text == "http://e.com/foo---bar"
assert linkifyit.match("text@example.com---foo") is None
linkifyit = LinkifyIt(None, {"---": True})
assert linkifyit.match("http://e.com/foo---bar")[0].text == "http://e.com/foo"
assert linkifyit.match("text@example.com---foo")[0].text == "text@example.com"
# issue #25. Schema key containing - not producing matches
@pytest.mark.parametrize(
"escape_str",
{".", "?", "*", "+", "^", "$", "[", "]", "\\", "(", ")", "{", "}", "|", "-"},
)
def test_api_add_alias_rule_with_excape_re_string(escape_str):
linkifyit = LinkifyIt()
linkifyit.add("foo{}bar:".format(escape_str), "http:")
assert linkifyit.test("Check foo{}bar://test".format(escape_str)) is True
def test_api_blank_test_match_at_the_start():
linkifyit = LinkifyIt()
assert not linkifyit.match_at_start("")
def test_api_should_find_a_match_at_the_start():
linkifyit = LinkifyIt()
linkifyit = LinkifyIt(options={"fuzzy_link": True})
linkifyit.set({"fuzzy_link": True})
assert not linkifyit.test("@@invalid")
assert not linkifyit.match_at_start("google.com 123")
assert not linkifyit.match_at_start(" http://google.com 123")
def test_api_match_a_start_should_not_interfere_with_normal_match():
linkifyit = LinkifyIt()
str = "http://google.com http://google.com"
assert linkifyit.match_at_start(str)
assert len(linkifyit.match(str)) == 2
str = "aaa http://google.com http://google.com"
assert not linkifyit.match_at_start(str)
assert len(linkifyit.match(str)) == 2
def test_api_should_not_match_incomplete_links():
# regression test for https://github.com/markdown-it/markdown-it/issues/868
linkifyit = LinkifyIt()
assert not linkifyit.match_at_start("http://")
assert not linkifyit.match_at_start("https://")
|
