textutils 0.9.1 → 0.9.2
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +7 -0
- data/Manifest.txt +4 -0
- data/lib/textutils/filter/code_filter.rb +1 -0
- data/lib/textutils/filter/comment_filter.rb +1 -0
- data/lib/textutils/filter/erb_django_filter.rb +1 -0
- data/lib/textutils/filter/erb_filter.rb +1 -0
- data/lib/textutils/filter/string_filter.rb +170 -0
- data/lib/textutils/helper/title_helper.rb +7 -116
- data/lib/textutils/parser/name_parser.rb +12 -0
- data/lib/textutils/utils.rb +2 -0
- data/lib/textutils/version.rb +2 -1
- data/lib/textutils.rb +3 -0
- data/test/test_asciify.rb +43 -0
- data/test/test_slugify.rb +40 -0
- data/test/test_title_helper.rb +0 -6
- metadata +50 -29
checksums.yaml
ADDED
@@ -0,0 +1,7 @@
|
|
1
|
+
---
|
2
|
+
SHA1:
|
3
|
+
metadata.gz: 56b6dcc77d437cdddb1df9336366d74465c9b0e3
|
4
|
+
data.tar.gz: 642a609e8e6c5df8c11e12b9c2c468cb8dd6fa53
|
5
|
+
SHA512:
|
6
|
+
metadata.gz: 1d7811b15d502395861cab8ce2ca15d4419d9744c3e58fee44a431804026e489776fdc84b60a33e95ab963abaf778fd6ffd21c54fcd37072498c6ed7caeda144
|
7
|
+
data.tar.gz: 5dd72d6fb3f4977cf9f8d8eb8982b21f5cf4165fcbaed28ff2a8fc396a46c6d9fc37d9df95bb4af5f5b359a70fb10896dcdf3d43ceb36afe57ffea93b338633b
|
data/Manifest.txt
CHANGED
@@ -10,6 +10,7 @@ lib/textutils/filter/code_filter.rb
|
|
10
10
|
lib/textutils/filter/comment_filter.rb
|
11
11
|
lib/textutils/filter/erb_django_filter.rb
|
12
12
|
lib/textutils/filter/erb_filter.rb
|
13
|
+
lib/textutils/filter/string_filter.rb
|
13
14
|
lib/textutils/helper/address_helper.rb
|
14
15
|
lib/textutils/helper/date_helper.rb
|
15
16
|
lib/textutils/helper/hypertext_helper.rb
|
@@ -19,6 +20,7 @@ lib/textutils/helper/unicode_helper.rb
|
|
19
20
|
lib/textutils/helper/value_helper.rb
|
20
21
|
lib/textutils/helper/xml_helper.rb
|
21
22
|
lib/textutils/page.rb
|
23
|
+
lib/textutils/parser/name_parser.rb
|
22
24
|
lib/textutils/patterns.rb
|
23
25
|
lib/textutils/reader/code_reader.rb
|
24
26
|
lib/textutils/reader/fixture_reader.rb
|
@@ -34,7 +36,9 @@ lib/textutils/utils.rb
|
|
34
36
|
lib/textutils/version.rb
|
35
37
|
test/helper.rb
|
36
38
|
test/test_address_helper.rb
|
39
|
+
test/test_asciify.rb
|
37
40
|
test/test_hypertext_helper.rb
|
41
|
+
test/test_slugify.rb
|
38
42
|
test/test_taglist.rb
|
39
43
|
test/test_title_finder.rb
|
40
44
|
test/test_title_helper.rb
|
@@ -0,0 +1,170 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
|
4
|
+
module TextUtils
|
5
|
+
module StringFilter
|
6
|
+
|
7
|
+
## turn accented char into ascii look alike if possible
|
8
|
+
##
|
9
|
+
## todo: add some more
|
10
|
+
## see http://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references for more
|
11
|
+
|
12
|
+
## see http://en.wikipedia.org/wiki/Latin_characters_in_Unicode !!! -- add more chars for conversion
|
13
|
+
## http://en.wikipedia.org/wiki/List_of_Latin_letters
|
14
|
+
|
15
|
+
## todo: add unicode codepoint name ???
|
16
|
+
|
17
|
+
ASCIIFY_MAPPINGS = [
|
18
|
+
['ß', 'ss'], # -- Latin small letter sharp s (ess-zed); see German Eszett // ß
|
19
|
+
|
20
|
+
['æ', 'ae'], # -- Latin small letter ae (Latin small ligature ae) // æ
|
21
|
+
['ä', 'ae'], # -- Latin small letter a with diaeresis // ä
|
22
|
+
['ā', 'a' ], # e.g. Liepājas, Kāṭhmāḍaũ
|
23
|
+
['á', 'a' ], # e.g. Bogotá, Králové
|
24
|
+
['à', 'a' ], # e.g. Thành Phố Hồ Chí Minh [Saigon]
|
25
|
+
['ã', 'a' ], # e.g São Paulo
|
26
|
+
['ă', 'a' ], # e.g. Chișinău
|
27
|
+
['â', 'a' ], # e.g Goiânia
|
28
|
+
['å', 'a' ], # e.g. Vålerenga
|
29
|
+
['ą', 'a' ], # e.g. Śląsk
|
30
|
+
|
31
|
+
['ç', 'c' ], # e.g. São Gonçalo, Iguaçu, Neftçi
|
32
|
+
['ć', 'c' ], # e.g. Budućnost
|
33
|
+
['č', 'c' ], # e.g. Tradiční, Výčepní
|
34
|
+
|
35
|
+
['ḍ', 'd' ], # e.g. Kāṭhmāḍaũ [Kathmandu]
|
36
|
+
|
37
|
+
['é', 'e' ], # e.g. Vélez, Králové
|
38
|
+
['è', 'e' ], # e.g. Rivières
|
39
|
+
['ê', 'e' ], # e.g. Grêmio
|
40
|
+
['ě', 'e' ], # e.g. Budějovice
|
41
|
+
['ĕ', 'e' ], # e.g. Svĕtlý
|
42
|
+
['ė', 'e' ], # e.g. Vėtra
|
43
|
+
['ë', 'e' ], # e.g. Skënderbeu
|
44
|
+
|
45
|
+
['ğ', 'g' ], # e.g. Qarabağ
|
46
|
+
|
47
|
+
['ḥ', 'h' ], # e.g. Ad-Dawḥah [Doha]
|
48
|
+
|
49
|
+
['ì', 'i' ], # e.g. Potosì
|
50
|
+
['í', 'i' ], # e.g. Ústí
|
51
|
+
['ï', 'i' ], # e.g. El Djazaïr
|
52
|
+
['ī', 'i' ], # e.g. Al-Iskandarīyah [Alexandria]
|
53
|
+
|
54
|
+
['ł', 'l' ], # e.g. Wisła, Wrocław
|
55
|
+
['ñ', 'n' ], # e.g. Porteño
|
56
|
+
['ň', 'n' ], # e.g. Plzeň, Třeboň
|
57
|
+
|
58
|
+
['ö', 'oe'],
|
59
|
+
['ő', 'o' ], # e.g. Győri
|
60
|
+
['ó', 'o' ], # e.g. Colón, Łódź, Kraków
|
61
|
+
['õ', 'o' ], # e.g. Nõmme
|
62
|
+
['ô', 'o' ], # e.g. Amazônia (pt)
|
63
|
+
['ō', 'o' ], # e.g. Tōkyō, Pishōr
|
64
|
+
['ŏ', 'o' ], # e.g. P'yŏngyang [Pyongyang]
|
65
|
+
['ø', 'o' ], # e.g. Fuglafjørdur, København
|
66
|
+
['ố', 'o' ], # e.g. Thành Phố Hồ Chí Minh [Saigon]
|
67
|
+
['ồ', 'o' ], # e.g. Thành Phố Hồ Chí Minh [Saigon]
|
68
|
+
['ộ', 'o' ], # e.g. Hà Nội [Hanoi]
|
69
|
+
|
70
|
+
['ř', 'r' ], # e.g. Třeboň
|
71
|
+
|
72
|
+
['ș', 's' ], # e.g. Chișinău, București
|
73
|
+
['ş', 's' ], # e.g. Beşiktaş
|
74
|
+
['š', 's' ], # e.g. Košice
|
75
|
+
['ṣ', 's' ], # e.g. Al-Mawṣil [Mosul]
|
76
|
+
|
77
|
+
['ť', 't' ], # e.g. Měšťan
|
78
|
+
['ṭ', 't' ], # e.g. Al-Kharṭūm [Khartoum], Kāṭhmāḍaũ
|
79
|
+
|
80
|
+
['ü', 'ue'],
|
81
|
+
['ú', 'u' ], # e.g. Fútbol
|
82
|
+
['ù', 'u' ], # e.g. Xyauyù (it)
|
83
|
+
['ū', 'u' ], # e.g. Sūduva
|
84
|
+
['ů', 'u' ], # e.g. Sládkův
|
85
|
+
['ũ', 'u' ], # e.g. Kāṭhmāḍaũ [Kathmandu]
|
86
|
+
|
87
|
+
['ı', 'u' ], # e.g. Bakı # use u?? (Baku) why-why not?
|
88
|
+
|
89
|
+
['x̌', 'x'], # e.g. Pex̌awar [Peshawar]
|
90
|
+
|
91
|
+
['ý', 'y' ], # e.g. Nefitrovaný
|
92
|
+
['ź', 'z' ], # e.g. Łódź
|
93
|
+
['ž', 'z' ], # e.g. Domžale, Petržalka
|
94
|
+
['ż', 'z' ], # e.g. Lomża (polish)
|
95
|
+
|
96
|
+
['Æ', 'Ae' ], # -- Latin capital letter AE
|
97
|
+
['Á', 'A' ], # e.g. Águila (es)
|
98
|
+
['Å', 'A' ], # e.g. Åland Islands -- Latin capital letter A with ring above // Å
|
99
|
+
|
100
|
+
['Ç', 'C' ], # -- Latin capital letter C with cedilla -- Ç
|
101
|
+
['Č', 'C' ], # e.g. České
|
102
|
+
|
103
|
+
['Ḥ', 'H' ], # e.g. Ḥalab [Aleppo]
|
104
|
+
['Ḫ', 'H' ], # e.g. Ḫamīs Mušayṭ
|
105
|
+
['İ', 'I' ], # e.g. İnter
|
106
|
+
['Í', 'I' ], # e.g. ÍBV
|
107
|
+
['Ł', 'L' ], # e.g. Łódź
|
108
|
+
|
109
|
+
['Ö', 'Oe' ], # e.g. Örebro -- Latin capital letter O with diaeresis // Ö
|
110
|
+
['Ō', 'O' ], # e.g. Ōsaka [Osaka] --
|
111
|
+
['Ø', 'O' ], # e.g. Nogne Ø Imperial Stout (no) -- Latin capital letter O with stroke (Latin capital letter O slash) // Ø
|
112
|
+
|
113
|
+
['Ř', 'R' ], # e.g. Řezák
|
114
|
+
|
115
|
+
['Ś', 'S' ], # e.g. Śląsk
|
116
|
+
['Š', 'S' ], # e.g. MŠK -- Latin capital letter S with caron // Š
|
117
|
+
['Ş', 'S' ], # e.g. Şüvälan
|
118
|
+
['Ṣ', 'S' ], # e.g. Ṣan'ā' [Sana'a]
|
119
|
+
|
120
|
+
['Ṭ', 'T' ], # e.g. Ṭarābulus [Tripoli]
|
121
|
+
['Ú', 'U' ], # e.g. Ústí, Újpest
|
122
|
+
['Ž', 'Z' ], # e.g. Žilina
|
123
|
+
['Ż', 'Z' ] # e.g. Żywiec (polish) -- Latin captial letter Z with caron
|
124
|
+
]
|
125
|
+
|
126
|
+
|
127
|
+
def asciify( content, options={} )
|
128
|
+
### fix: use content.each_char and hash_map or similar instead of gsub
|
129
|
+
|
130
|
+
ASCIIFY_MAPPINGS.each do |mapping|
|
131
|
+
content = content.gsub( mapping[0], mapping[1] )
|
132
|
+
end
|
133
|
+
content
|
134
|
+
end
|
135
|
+
|
136
|
+
def slugify( content, options={} )
|
137
|
+
|
138
|
+
## NOTE: for now we do NOT strip non-word characters!!!!
|
139
|
+
## if it is an accented char, add it to asciify first!!!
|
140
|
+
|
141
|
+
## converts to lowercase,
|
142
|
+
## removes non-word characters (alphanumerics and underscores)
|
143
|
+
## and converts spaces to hyphens.
|
144
|
+
## Also strips leading and trailing whitespace.
|
145
|
+
|
146
|
+
# 1) asciify and downcase
|
147
|
+
content = asciify( content ).downcase
|
148
|
+
|
149
|
+
# 2) replace special chars w/space e.g $&%?!§#=*+._/()[]{}
|
150
|
+
## -- check in [] do we need to espcae / () [] {}
|
151
|
+
content = content.gsub( /[$&%?!§#=*+._\/\(\)\[\]\{\}]/, ' ' ) ## -- replace w/ dash (-)
|
152
|
+
content = content.gsub( /["']/, '' ) ## -- remove (use replace too? why? why not? add others???
|
153
|
+
|
154
|
+
# 3) strip leading and trailing spaces; squeeze spaces (e.g. more than one into one space)
|
155
|
+
content = content.strip
|
156
|
+
content = content.gsub( / {2,}/, ' ' )
|
157
|
+
|
158
|
+
# 4) replace remaining (inner) spaces ( ) with dash (-)
|
159
|
+
content = content.gsub( ' ', '-' )
|
160
|
+
content
|
161
|
+
end
|
162
|
+
|
163
|
+
|
164
|
+
end # module StringFilter
|
165
|
+
|
166
|
+
module Filter
|
167
|
+
include StringFilter
|
168
|
+
end # module Filter
|
169
|
+
|
170
|
+
end # module TextUtils
|
@@ -1,6 +1,12 @@
|
|
1
1
|
# encoding: utf-8
|
2
2
|
|
3
3
|
|
4
|
+
###
|
5
|
+
#
|
6
|
+
# fix: move to filter!!!!
|
7
|
+
# follows fn( content ) pattern!!!
|
8
|
+
|
9
|
+
|
4
10
|
module TextUtils
|
5
11
|
module TitleHelper
|
6
12
|
|
@@ -75,122 +81,7 @@ module TextUtils
|
|
75
81
|
|
76
82
|
key = strip_special_chars( key )
|
77
83
|
|
78
|
-
|
79
|
-
##
|
80
|
-
## todo: add some more
|
81
|
-
## see http://en.wikipedia.org/wiki/List_of_XML_and_HTML_character_entity_references for more
|
82
|
-
|
83
|
-
## todo: add unicode codepoint name
|
84
|
-
|
85
|
-
|
86
|
-
alternatives = [
|
87
|
-
['ß', 'ss'],
|
88
|
-
|
89
|
-
['æ', 'ae'],
|
90
|
-
['ä', 'ae'],
|
91
|
-
['ā', 'a' ], # e.g. Liepājas, Kāṭhmāḍaũ
|
92
|
-
['á', 'a' ], # e.g. Bogotá, Králové
|
93
|
-
['à', 'a' ], # e.g. Thành Phố Hồ Chí Minh [Saigon]
|
94
|
-
['ã', 'a' ], # e.g São Paulo
|
95
|
-
['ă', 'a' ], # e.g. Chișinău
|
96
|
-
['â', 'a' ], # e.g Goiânia
|
97
|
-
['å', 'a' ], # e.g. Vålerenga
|
98
|
-
['ą', 'a' ], # e.g. Śląsk
|
99
|
-
|
100
|
-
['ç', 'c' ], # e.g. São Gonçalo, Iguaçu, Neftçi
|
101
|
-
['ć', 'c' ], # e.g. Budućnost
|
102
|
-
['č', 'c' ], # e.g. Tradiční, Výčepní
|
103
|
-
|
104
|
-
['ḍ', 'd' ], # e.g. Kāṭhmāḍaũ [Kathmandu]
|
105
|
-
|
106
|
-
['é', 'e' ], # e.g. Vélez, Králové
|
107
|
-
['è', 'e' ], # e.g. Rivières
|
108
|
-
['ê', 'e' ], # e.g. Grêmio
|
109
|
-
['ě', 'e' ], # e.g. Budějovice
|
110
|
-
['ĕ', 'e' ], # e.g. Svĕtlý
|
111
|
-
['ė', 'e' ], # e.g. Vėtra
|
112
|
-
['ë', 'e' ], # e.g. Skënderbeu
|
113
|
-
|
114
|
-
['ğ', 'g' ], # e.g. Qarabağ
|
115
|
-
|
116
|
-
['ḥ', 'h' ], # e.g. Ad-Dawḥah [Doha]
|
117
|
-
|
118
|
-
['ì', 'i' ], # e.g. Potosì
|
119
|
-
['í', 'i' ], # e.g. Ústí
|
120
|
-
['ï', 'i' ], # e.g. El Djazaïr
|
121
|
-
['ī', 'i' ], # e.g. Al-Iskandarīyah [Alexandria]
|
122
|
-
|
123
|
-
['ł', 'l' ], # e.g. Wisła, Wrocław
|
124
|
-
['ñ', 'n' ], # e.g. Porteño
|
125
|
-
['ň', 'n' ], # e.g. Plzeň, Třeboň
|
126
|
-
|
127
|
-
['ö', 'oe'],
|
128
|
-
['ő', 'o' ], # e.g. Győri
|
129
|
-
['ó', 'o' ], # e.g. Colón, Łódź, Kraków
|
130
|
-
['õ', 'o' ], # e.g. Nõmme
|
131
|
-
['ô', 'o' ], # e.g. Amazônia (pt)
|
132
|
-
['ō', 'o' ], # e.g. Tōkyō, Pishōr
|
133
|
-
['ŏ', 'o' ], # e.g. P'yŏngyang [Pyongyang]
|
134
|
-
['ø', 'o' ], # e.g. Fuglafjørdur, København
|
135
|
-
['ố', 'o' ], # e.g. Thành Phố Hồ Chí Minh [Saigon]
|
136
|
-
['ồ', 'o' ], # e.g. Thành Phố Hồ Chí Minh [Saigon]
|
137
|
-
['ộ', 'o' ], # e.g. Hà Nội [Hanoi]
|
138
|
-
|
139
|
-
['ř', 'r' ], # e.g. Třeboň
|
140
|
-
|
141
|
-
['ș', 's' ], # e.g. Chișinău, București
|
142
|
-
['ş', 's' ], # e.g. Beşiktaş
|
143
|
-
['š', 's' ], # e.g. Košice
|
144
|
-
['ṣ', 's' ], # e.g. Al-Mawṣil [Mosul]
|
145
|
-
|
146
|
-
['ť', 't' ], # e.g. Měšťan
|
147
|
-
['ṭ', 't' ], # e.g. Al-Kharṭūm [Khartoum], Kāṭhmāḍaũ
|
148
|
-
|
149
|
-
['ü', 'ue'],
|
150
|
-
['ú', 'u' ], # e.g. Fútbol
|
151
|
-
['ù', 'u' ], # e.g. Xyauyù (it)
|
152
|
-
['ū', 'u' ], # e.g. Sūduva
|
153
|
-
['ů', 'u' ], # e.g. Sládkův
|
154
|
-
['ũ', 'u' ], # e.g. Kāṭhmāḍaũ [Kathmandu]
|
155
|
-
|
156
|
-
['ı', 'u' ], # e.g. Bakı # use u?? (Baku) why-why not?
|
157
|
-
|
158
|
-
['x̌', 'x'], # e.g. Pex̌awar [Peshawar]
|
159
|
-
|
160
|
-
['ý', 'y' ], # e.g. Nefitrovaný
|
161
|
-
['ź', 'z' ], # e.g. Łódź
|
162
|
-
['ž', 'z' ], # e.g. Domžale, Petržalka
|
163
|
-
['ż', 'z' ], # e.g. Lomża (polish)
|
164
|
-
|
165
|
-
['Á', 'a' ], # e.g. Águila (es)
|
166
|
-
['Č', 'c' ], # e.g. České
|
167
|
-
|
168
|
-
['Ḥ', 'h' ], # e.g. Ḥalab [Aleppo]
|
169
|
-
['Ḫ', 'h' ], # e.g. Ḫamīs Mušayṭ
|
170
|
-
['İ', 'i' ], # e.g. İnter
|
171
|
-
['Í', 'i' ], # e.g. ÍBV
|
172
|
-
['Ł', 'l' ], # e.g. Łódź
|
173
|
-
|
174
|
-
['Ö', 'oe' ], # e.g. Örebro
|
175
|
-
['Ō', 'o' ], # e.g. Ōsaka [Osaka]
|
176
|
-
['Ø', 'o' ], # e.g. Nogne Ø Imperial Stout (no)
|
177
|
-
|
178
|
-
['Ř', 'r' ], # e.g. Řezák
|
179
|
-
|
180
|
-
['Ś', 's' ], # e.g. Śląsk
|
181
|
-
['Š', 's' ], # e.g. MŠK
|
182
|
-
['Ş', 's' ], # e.g. Şüvälan
|
183
|
-
['Ṣ', 's' ], # e.g. Ṣan'ā' [Sana'a]
|
184
|
-
|
185
|
-
['Ṭ', 't' ], # e.g. Ṭarābulus [Tripoli]
|
186
|
-
['Ú', 'u' ], # e.g. Ústí, Újpest
|
187
|
-
['Ž', 'z' ], # e.g. Žilina
|
188
|
-
['Ż', 'z' ] # e.g. Żywiec (polish)
|
189
|
-
]
|
190
|
-
|
191
|
-
alternatives.each do |alt|
|
192
|
-
key = key.gsub( alt[0], alt[1] )
|
193
|
-
end
|
84
|
+
key = TextUtils.asciify( key ).downcase ## see filter/string_filter
|
194
85
|
|
195
86
|
key
|
196
87
|
end # method title_to_key
|
data/lib/textutils/utils.rb
CHANGED
data/lib/textutils/version.rb
CHANGED
data/lib/textutils.rb
CHANGED
@@ -30,6 +30,7 @@ require 'textutils/filter/code_filter'
|
|
30
30
|
require 'textutils/filter/comment_filter'
|
31
31
|
require 'textutils/filter/erb_django_filter'
|
32
32
|
require 'textutils/filter/erb_filter'
|
33
|
+
require 'textutils/filter/string_filter'
|
33
34
|
|
34
35
|
require 'textutils/helper/date_helper'
|
35
36
|
require 'textutils/helper/hypertext_helper'
|
@@ -45,6 +46,8 @@ require 'textutils/utils'
|
|
45
46
|
require 'textutils/core_ext/file'
|
46
47
|
require 'textutils/core_ext/time'
|
47
48
|
|
49
|
+
require 'textutils/parser/name_parser'
|
50
|
+
|
48
51
|
require 'textutils/reader/code_reader'
|
49
52
|
require 'textutils/reader/hash_reader'
|
50
53
|
require 'textutils/reader/hash_reader_v2'
|
@@ -0,0 +1,43 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
|
4
|
+
require 'helper'
|
5
|
+
|
6
|
+
|
7
|
+
class TestAsciify < MiniTest::Unit::TestCase
|
8
|
+
|
9
|
+
def test_asciify
|
10
|
+
|
11
|
+
txt_io = [
|
12
|
+
[ 'São Paulo', 'Sao Paulo' ],
|
13
|
+
[ 'São Gonçalo', 'Sao Goncalo' ],
|
14
|
+
[ 'Výčepní', 'Vycepni' ],
|
15
|
+
[ 'Żubr', 'Zubr' ],
|
16
|
+
[ 'Żywiec', 'Zywiec' ],
|
17
|
+
[ 'Lomża Export', 'Lomza Export' ],
|
18
|
+
[ 'Nogne Ø Imperial Stout', 'Nogne O Imperial Stout' ],
|
19
|
+
[ 'Xyauyù', 'Xyauyu' ],
|
20
|
+
[ 'Águila', 'Aguila' ],
|
21
|
+
[ 'Arena Amazônia', 'Arena Amazonia' ],
|
22
|
+
[ 'Tōkyō', 'Tokyo' ],
|
23
|
+
[ 'Ōsaka', 'Osaka' ],
|
24
|
+
[ 'El Djazaïr', 'El Djazair' ],
|
25
|
+
[ 'Al-Kharṭūm', 'Al-Khartum' ],
|
26
|
+
[ 'Ṭarābulus', 'Tarabulus' ],
|
27
|
+
[ 'Al-Iskandarīyah', 'Al-Iskandariyah' ],
|
28
|
+
[ 'Pex̌awar', 'Pexawar'],
|
29
|
+
[ 'Pishōr', 'Pishor' ],
|
30
|
+
[ 'Pishāwar', 'Pishawar' ],
|
31
|
+
[ 'Islām ābād', 'Islam abad' ],
|
32
|
+
[ 'Thành Phố Hồ Chí Minh', 'Thanh Pho Ho Chi Minh' ],
|
33
|
+
[ 'Åland Islands', 'Aland Islands' ]
|
34
|
+
]
|
35
|
+
|
36
|
+
txt_io.each do |txt|
|
37
|
+
assert_equal txt[1], TextUtils.asciify( txt[0] )
|
38
|
+
end
|
39
|
+
end # method test_asciify
|
40
|
+
|
41
|
+
|
42
|
+
end # class TestAsciify
|
43
|
+
|
@@ -0,0 +1,40 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
|
3
|
+
require 'helper'
|
4
|
+
|
5
|
+
class TestSlugify < MiniTest::Unit::TestCase
|
6
|
+
|
7
|
+
def test_slugify
|
8
|
+
|
9
|
+
txt_io = [
|
10
|
+
[ 'São Paulo', 'sao-paulo' ],
|
11
|
+
[ 'São Gonçalo', 'sao-goncalo' ],
|
12
|
+
[ 'Výčepní', 'vycepni' ],
|
13
|
+
[ 'Żubr', 'zubr' ],
|
14
|
+
[ 'Żywiec', 'zywiec' ],
|
15
|
+
[ 'Lomża Export', 'lomza-export' ],
|
16
|
+
[ 'Nogne Ø Imperial Stout', 'nogne-o-imperial-stout' ],
|
17
|
+
[ 'Xyauyù', 'xyauyu' ],
|
18
|
+
[ 'Águila', 'aguila' ],
|
19
|
+
[ 'Arena Amazônia', 'arena-amazonia' ],
|
20
|
+
[ 'Tōkyō', 'tokyo' ],
|
21
|
+
[ 'Ōsaka', 'osaka' ],
|
22
|
+
[ 'El Djazaïr', 'el-djazair' ],
|
23
|
+
[ 'Al-Kharṭūm', 'al-khartum' ],
|
24
|
+
[ 'Ṭarābulus', 'tarabulus' ],
|
25
|
+
[ 'Al-Iskandarīyah', 'al-iskandariyah' ],
|
26
|
+
[ 'Pex̌awar', 'pexawar'],
|
27
|
+
[ 'Pishōr', 'pishor' ],
|
28
|
+
[ 'Pishāwar', 'pishawar' ],
|
29
|
+
[ 'Islām ābād', 'islam-abad' ],
|
30
|
+
[ 'Thành Phố Hồ Chí Minh', 'thanh-pho-ho-chi-minh' ],
|
31
|
+
[ 'Åland Islands', 'aland-islands' ]
|
32
|
+
]
|
33
|
+
|
34
|
+
txt_io.each do |txt|
|
35
|
+
assert_equal txt[1], TextUtils.slugify( txt[0] )
|
36
|
+
end
|
37
|
+
end # method test_slugify
|
38
|
+
|
39
|
+
|
40
|
+
end # class TestSlugify
|
data/test/test_title_helper.rb
CHANGED
metadata
CHANGED
@@ -1,77 +1,93 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: textutils
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.9.
|
5
|
-
prerelease:
|
4
|
+
version: 0.9.2
|
6
5
|
platform: ruby
|
7
6
|
authors:
|
8
7
|
- Gerald Bauer
|
9
8
|
autorequire:
|
10
9
|
bindir: bin
|
11
10
|
cert_chain: []
|
12
|
-
date: 2014-03-
|
11
|
+
date: 2014-03-28 00:00:00.000000000 Z
|
13
12
|
dependencies:
|
14
13
|
- !ruby/object:Gem::Dependency
|
15
14
|
name: props
|
16
|
-
requirement:
|
17
|
-
none: false
|
15
|
+
requirement: !ruby/object:Gem::Requirement
|
18
16
|
requirements:
|
19
17
|
- - ! '>='
|
20
18
|
- !ruby/object:Gem::Version
|
21
19
|
version: '0'
|
22
20
|
type: :runtime
|
23
21
|
prerelease: false
|
24
|
-
version_requirements:
|
22
|
+
version_requirements: !ruby/object:Gem::Requirement
|
23
|
+
requirements:
|
24
|
+
- - ! '>='
|
25
|
+
- !ruby/object:Gem::Version
|
26
|
+
version: '0'
|
25
27
|
- !ruby/object:Gem::Dependency
|
26
28
|
name: logutils
|
27
|
-
requirement:
|
28
|
-
none: false
|
29
|
+
requirement: !ruby/object:Gem::Requirement
|
29
30
|
requirements:
|
30
31
|
- - ~>
|
31
32
|
- !ruby/object:Gem::Version
|
32
33
|
version: '0.5'
|
33
34
|
type: :runtime
|
34
35
|
prerelease: false
|
35
|
-
version_requirements:
|
36
|
+
version_requirements: !ruby/object:Gem::Requirement
|
37
|
+
requirements:
|
38
|
+
- - ~>
|
39
|
+
- !ruby/object:Gem::Version
|
40
|
+
version: '0.5'
|
36
41
|
- !ruby/object:Gem::Dependency
|
37
42
|
name: activesupport
|
38
|
-
requirement:
|
39
|
-
none: false
|
43
|
+
requirement: !ruby/object:Gem::Requirement
|
40
44
|
requirements:
|
41
45
|
- - ! '>='
|
42
46
|
- !ruby/object:Gem::Version
|
43
47
|
version: '0'
|
44
48
|
type: :runtime
|
45
49
|
prerelease: false
|
46
|
-
version_requirements:
|
50
|
+
version_requirements: !ruby/object:Gem::Requirement
|
51
|
+
requirements:
|
52
|
+
- - ! '>='
|
53
|
+
- !ruby/object:Gem::Version
|
54
|
+
version: '0'
|
47
55
|
- !ruby/object:Gem::Dependency
|
48
56
|
name: rdoc
|
49
|
-
requirement:
|
50
|
-
none: false
|
57
|
+
requirement: !ruby/object:Gem::Requirement
|
51
58
|
requirements:
|
52
59
|
- - ~>
|
53
60
|
- !ruby/object:Gem::Version
|
54
|
-
version: '
|
61
|
+
version: '4.0'
|
55
62
|
type: :development
|
56
63
|
prerelease: false
|
57
|
-
version_requirements:
|
64
|
+
version_requirements: !ruby/object:Gem::Requirement
|
65
|
+
requirements:
|
66
|
+
- - ~>
|
67
|
+
- !ruby/object:Gem::Version
|
68
|
+
version: '4.0'
|
58
69
|
- !ruby/object:Gem::Dependency
|
59
70
|
name: hoe
|
60
|
-
requirement:
|
61
|
-
none: false
|
71
|
+
requirement: !ruby/object:Gem::Requirement
|
62
72
|
requirements:
|
63
73
|
- - ~>
|
64
74
|
- !ruby/object:Gem::Version
|
65
|
-
version: '3.
|
75
|
+
version: '3.6'
|
66
76
|
type: :development
|
67
77
|
prerelease: false
|
68
|
-
version_requirements:
|
78
|
+
version_requirements: !ruby/object:Gem::Requirement
|
79
|
+
requirements:
|
80
|
+
- - ~>
|
81
|
+
- !ruby/object:Gem::Version
|
82
|
+
version: '3.6'
|
69
83
|
description: textutils - Text Filters, Helpers, Readers and More
|
70
84
|
email: ruby-talk@ruby-lang.org
|
71
85
|
executables: []
|
72
86
|
extensions: []
|
73
87
|
extra_rdoc_files:
|
88
|
+
- HISTORY.md
|
74
89
|
- Manifest.txt
|
90
|
+
- README.md
|
75
91
|
files:
|
76
92
|
- HISTORY.md
|
77
93
|
- Manifest.txt
|
@@ -85,6 +101,7 @@ files:
|
|
85
101
|
- lib/textutils/filter/comment_filter.rb
|
86
102
|
- lib/textutils/filter/erb_django_filter.rb
|
87
103
|
- lib/textutils/filter/erb_filter.rb
|
104
|
+
- lib/textutils/filter/string_filter.rb
|
88
105
|
- lib/textutils/helper/address_helper.rb
|
89
106
|
- lib/textutils/helper/date_helper.rb
|
90
107
|
- lib/textutils/helper/hypertext_helper.rb
|
@@ -94,6 +111,7 @@ files:
|
|
94
111
|
- lib/textutils/helper/value_helper.rb
|
95
112
|
- lib/textutils/helper/xml_helper.rb
|
96
113
|
- lib/textutils/page.rb
|
114
|
+
- lib/textutils/parser/name_parser.rb
|
97
115
|
- lib/textutils/patterns.rb
|
98
116
|
- lib/textutils/reader/code_reader.rb
|
99
117
|
- lib/textutils/reader/fixture_reader.rb
|
@@ -109,7 +127,9 @@ files:
|
|
109
127
|
- lib/textutils/version.rb
|
110
128
|
- test/helper.rb
|
111
129
|
- test/test_address_helper.rb
|
130
|
+
- test/test_asciify.rb
|
112
131
|
- test/test_hypertext_helper.rb
|
132
|
+
- test/test_slugify.rb
|
113
133
|
- test/test_taglist.rb
|
114
134
|
- test/test_title_finder.rb
|
115
135
|
- test/test_title_helper.rb
|
@@ -120,6 +140,7 @@ files:
|
|
120
140
|
homepage: https://github.com/rubylibs/textutils
|
121
141
|
licenses:
|
122
142
|
- Public Domain
|
143
|
+
metadata: {}
|
123
144
|
post_install_message:
|
124
145
|
rdoc_options:
|
125
146
|
- --main
|
@@ -127,29 +148,29 @@ rdoc_options:
|
|
127
148
|
require_paths:
|
128
149
|
- lib
|
129
150
|
required_ruby_version: !ruby/object:Gem::Requirement
|
130
|
-
none: false
|
131
151
|
requirements:
|
132
152
|
- - ! '>='
|
133
153
|
- !ruby/object:Gem::Version
|
134
154
|
version: 1.9.2
|
135
155
|
required_rubygems_version: !ruby/object:Gem::Requirement
|
136
|
-
none: false
|
137
156
|
requirements:
|
138
157
|
- - ! '>='
|
139
158
|
- !ruby/object:Gem::Version
|
140
159
|
version: '0'
|
141
160
|
requirements: []
|
142
161
|
rubyforge_project: textutils
|
143
|
-
rubygems_version: 1.
|
162
|
+
rubygems_version: 2.1.10
|
144
163
|
signing_key:
|
145
|
-
specification_version:
|
164
|
+
specification_version: 4
|
146
165
|
summary: textutils - Text Filters, Helpers, Readers and More
|
147
166
|
test_files:
|
167
|
+
- test/test_address_helper.rb
|
168
|
+
- test/test_asciify.rb
|
169
|
+
- test/test_hypertext_helper.rb
|
170
|
+
- test/test_slugify.rb
|
171
|
+
- test/test_taglist.rb
|
148
172
|
- test/test_title_finder.rb
|
149
|
-
- test/
|
173
|
+
- test/test_title_helper.rb
|
150
174
|
- test/test_title_mapper.rb
|
175
|
+
- test/test_unicode_helper.rb
|
151
176
|
- test/test_values_reader.rb
|
152
|
-
- test/test_taglist.rb
|
153
|
-
- test/test_hypertext_helper.rb
|
154
|
-
- test/test_title_helper.rb
|
155
|
-
- test/test_address_helper.rb
|