cmassimo-friendly_id 3.0.4.2
Sign up to get free protection for your applications and to get access to all the features.
- data/Changelog.md +277 -0
- data/Contributors.md +39 -0
- data/Guide.md +561 -0
- data/LICENSE +19 -0
- data/README.md +83 -0
- data/Rakefile +66 -0
- data/extras/README.txt +3 -0
- data/extras/bench.rb +36 -0
- data/extras/extras.rb +38 -0
- data/extras/prof.rb +14 -0
- data/extras/template-gem.rb +26 -0
- data/extras/template-plugin.rb +28 -0
- data/generators/friendly_id/friendly_id_generator.rb +30 -0
- data/generators/friendly_id/templates/create_slugs.rb +18 -0
- data/lib/friendly_id.rb +73 -0
- data/lib/friendly_id/active_record.rb +52 -0
- data/lib/friendly_id/active_record_adapter/configuration.rb +67 -0
- data/lib/friendly_id/active_record_adapter/finders.rb +156 -0
- data/lib/friendly_id/active_record_adapter/simple_model.rb +123 -0
- data/lib/friendly_id/active_record_adapter/slug.rb +66 -0
- data/lib/friendly_id/active_record_adapter/slugged_model.rb +238 -0
- data/lib/friendly_id/active_record_adapter/tasks.rb +69 -0
- data/lib/friendly_id/configuration.rb +113 -0
- data/lib/friendly_id/finders.rb +109 -0
- data/lib/friendly_id/railtie.rb +20 -0
- data/lib/friendly_id/sequel.rb +5 -0
- data/lib/friendly_id/slug_string.rb +391 -0
- data/lib/friendly_id/slugged.rb +102 -0
- data/lib/friendly_id/status.rb +35 -0
- data/lib/friendly_id/test.rb +291 -0
- data/lib/friendly_id/version.rb +9 -0
- data/lib/generators/friendly_id_generator.rb +25 -0
- data/lib/tasks/friendly_id.rake +19 -0
- data/rails/init.rb +2 -0
- data/test/active_record_adapter/ar_test_helper.rb +119 -0
- data/test/active_record_adapter/basic_slugged_model_test.rb +14 -0
- data/test/active_record_adapter/cached_slug_test.rb +61 -0
- data/test/active_record_adapter/core.rb +98 -0
- data/test/active_record_adapter/custom_normalizer_test.rb +20 -0
- data/test/active_record_adapter/custom_table_name_test.rb +22 -0
- data/test/active_record_adapter/scoped_model_test.rb +118 -0
- data/test/active_record_adapter/simple_test.rb +76 -0
- data/test/active_record_adapter/slug_test.rb +34 -0
- data/test/active_record_adapter/slugged.rb +30 -0
- data/test/active_record_adapter/slugged_status_test.rb +25 -0
- data/test/active_record_adapter/sti_test.rb +22 -0
- data/test/active_record_adapter/support/database.jdbcsqlite3.yml +2 -0
- data/test/active_record_adapter/support/database.mysql.yml +4 -0
- data/test/active_record_adapter/support/database.postgres.yml +6 -0
- data/test/active_record_adapter/support/database.sqlite3.yml +2 -0
- data/test/active_record_adapter/support/models.rb +87 -0
- data/test/active_record_adapter/tasks_test.rb +82 -0
- data/test/friendly_id_test.rb +55 -0
- data/test/slug_string_test.rb +88 -0
- data/test/test_helper.rb +15 -0
- metadata +168 -0
@@ -0,0 +1,20 @@
|
|
1
|
+
module FriendlyId
|
2
|
+
class Railtie < Rails::Railtie
|
3
|
+
|
4
|
+
initializer "friendly_id.configure_rails_initialization" do |app|
|
5
|
+
# Experimental Sequel support. See: http://github.com/norman/friendly_id_sequel
|
6
|
+
if app.config.generators.rails[:orm] == :sequel
|
7
|
+
require "friendly_id/sequel"
|
8
|
+
else
|
9
|
+
# Only Sequel and ActiveRecord are currently supported; AR is the default.
|
10
|
+
# Want Datamapper support? http://github.com/norman/friendly_id/issues#issue/24
|
11
|
+
require "friendly_id/active_record"
|
12
|
+
end
|
13
|
+
end
|
14
|
+
|
15
|
+
rake_tasks do
|
16
|
+
load "tasks/friendly_id.rake"
|
17
|
+
end
|
18
|
+
|
19
|
+
end
|
20
|
+
end
|
@@ -0,0 +1,391 @@
|
|
1
|
+
# encoding: utf-8
|
2
|
+
module FriendlyId
|
3
|
+
|
4
|
+
# This class provides some string-manipulation methods specific to slugs.
|
5
|
+
# Its Unicode support is provided by ActiveSupport::Multibyte::Chars; this
|
6
|
+
# is needed primarily for Unicode encoding normalization and proper
|
7
|
+
# calculation of string lengths.
|
8
|
+
#
|
9
|
+
# Note that this class includes many "bang methods" such as {#clean!} and {#normalize!}
|
10
|
+
# that perform actions on the string in-place. Each of these methods has a
|
11
|
+
# corresponding "bangless" method (i.e., +SlugString#clean!+ and +SlugString#clean+)
|
12
|
+
# which does not appear in the documentation because it is generated dynamically.
|
13
|
+
#
|
14
|
+
# All of the bang methods return an instance of String, while the bangless
|
15
|
+
# versions return an instance of FriendlyId::SlugString, so that calls to
|
16
|
+
# methods specific to this class can be chained:
|
17
|
+
#
|
18
|
+
# string = SlugString.new("hello world")
|
19
|
+
# string.with_dashes! # => "hello-world"
|
20
|
+
# string.with_dashes # => <FriendlyId::SlugString:0x000001013e1590 @wrapped_string="hello-world">
|
21
|
+
#
|
22
|
+
# @see http://www.utf8-chartable.de/unicode-utf8-table.pl?utf8=dec Unicode character table
|
23
|
+
# @see FriendlyId::SlugString::dump_approximations
|
24
|
+
class SlugString < ActiveSupport::Multibyte::Chars
|
25
|
+
|
26
|
+
# All values are Unicode decimal characters or character arrays.
|
27
|
+
APPROXIMATIONS = {
|
28
|
+
:common => Hash[
|
29
|
+
192, 65, 193, 65, 194, 65, 195, 65, 196, 65, 197, 65, 198, [65, 69],
|
30
|
+
199, 67, 200, 69, 201, 69, 202, 69, 203, 69, 204, 73, 205, 73, 206,
|
31
|
+
73, 207, 73, 208, 68, 209, 78, 210, 79, 211, 79, 212, 79, 213, 79,
|
32
|
+
214, 79, 215, 120, 216, 79, 217, 85, 218, 85, 219, 85, 220, 85, 221,
|
33
|
+
89, 222, [84, 104], 223, [115, 115], 224, 97, 225, 97, 226, 97, 227,
|
34
|
+
97, 228, 97, 229, 97, 230, [97, 101], 231, 99, 232, 101, 233, 101,
|
35
|
+
234, 101, 235, 101, 236, 105, 237, 105, 238, 105, 239, 105, 240, 100,
|
36
|
+
241, 110, 242, 111, 243, 111, 244, 111, 245, 111, 246, 111, 248, 111,
|
37
|
+
249, 117, 250, 117, 251, 117, 252, 117, 253, 121, 254, [116, 104],
|
38
|
+
255, 121, 256, 65, 257, 97, 258, 65, 259, 97, 260, 65, 261, 97, 262,
|
39
|
+
67, 263, 99, 264, 67, 265, 99, 266, 67, 267, 99, 268, 67, 269, 99,
|
40
|
+
270, 68, 271, 100, 272, 68, 273, 100, 274, 69, 275, 101, 276, 69, 277,
|
41
|
+
101, 278, 69, 279, 101, 280, 69, 281, 101, 282, 69, 283, 101, 284, 71,
|
42
|
+
285, 103, 286, 71, 287, 103, 288, 71, 289, 103, 290, 71, 291, 103,
|
43
|
+
292, 72, 293, 104, 294, 72, 295, 104, 296, 73, 297, 105, 298, 73, 299,
|
44
|
+
105, 300, 73, 301, 105, 302, 73, 303, 105, 304, 73, 305, 105, 306,
|
45
|
+
[73, 74], 307, [105, 106], 308, 74, 309, 106, 310, 75, 311, 107, 312,
|
46
|
+
107, 313, 76, 314, 108, 315, 76, 316, 108, 317, 76, 318, 108, 319, 76,
|
47
|
+
320, 108, 321, 76, 322, 108, 323, 78, 324, 110, 325, 78, 326, 110,
|
48
|
+
327, 78, 328, 110, 329, [39, 110], 330, [78, 71], 331, [110, 103],
|
49
|
+
332, 79, 333, 111, 334, 79, 335, 111, 336, 79, 337, 111, 338, [79,
|
50
|
+
69], 339, [111, 101], 340, 82, 341, 114, 342, 82, 343, 114, 344, 82,
|
51
|
+
345, 114, 346, 83, 347, 115, 348, 83, 349, 115, 350, 83, 351, 115,
|
52
|
+
352, 83, 353, 115, 354, 84, 355, 116, 356, 84, 357, 116, 358, 84, 359,
|
53
|
+
116, 360, 85, 361, 117, 362, 85, 363, 117, 364, 85, 365, 117, 366, 85,
|
54
|
+
367, 117, 368, 85, 369, 117, 370, 85, 371, 117, 372, 87, 373, 119,
|
55
|
+
374, 89, 375, 121, 376, 89, 377, 90, 378, 122, 379, 90, 380, 122, 381,
|
56
|
+
90, 382, 122
|
57
|
+
].freeze,
|
58
|
+
:german => Hash[252, [117, 101], 246, [111, 101], 228, [97, 101]],
|
59
|
+
:spanish => Hash[209, [78, 110], 241, [110, 110]]
|
60
|
+
}
|
61
|
+
|
62
|
+
# CP-1252 decimal byte => UTF-8 approximation as an array of bytes
|
63
|
+
CP1252 = {
|
64
|
+
128 => [226, 130, 172],
|
65
|
+
129 => nil,
|
66
|
+
130 => [226, 128, 154],
|
67
|
+
131 => [198, 146],
|
68
|
+
132 => [226, 128, 158],
|
69
|
+
133 => [226, 128, 166],
|
70
|
+
134 => [226, 128, 160],
|
71
|
+
135 => [226, 128, 161],
|
72
|
+
136 => [203, 134],
|
73
|
+
137 => [226, 128, 176],
|
74
|
+
138 => [197, 160],
|
75
|
+
139 => [226, 128, 185],
|
76
|
+
140 => [197, 146],
|
77
|
+
141 => nil,
|
78
|
+
142 => [197, 189],
|
79
|
+
143 => nil,
|
80
|
+
144 => nil,
|
81
|
+
145 => [226, 128, 152],
|
82
|
+
146 => [226, 128, 153],
|
83
|
+
147 => [226, 128, 156],
|
84
|
+
148 => [226, 128, 157],
|
85
|
+
149 => [226, 128, 162],
|
86
|
+
150 => [226, 128, 147],
|
87
|
+
151 => [226, 128, 148],
|
88
|
+
152 => [203, 156],
|
89
|
+
153 => [226, 132, 162],
|
90
|
+
154 => [197, 161],
|
91
|
+
155 => [226, 128, 186],
|
92
|
+
156 => [197, 147],
|
93
|
+
157 => nil,
|
94
|
+
158 => [197, 190],
|
95
|
+
159 => [197, 184]
|
96
|
+
}
|
97
|
+
|
98
|
+
cattr_accessor :approximations
|
99
|
+
self.approximations = []
|
100
|
+
|
101
|
+
# This method can be used by developers wishing to debug the
|
102
|
+
# {APPROXIMATIONS} hashes, which are written in a hard-to-read format.
|
103
|
+
# @return Hash
|
104
|
+
# @example
|
105
|
+
#
|
106
|
+
# > ruby -rrubygems -rlib/friendly_id -e 'p FriendlyId::SlugString.dump_approximations'
|
107
|
+
#
|
108
|
+
# {:common =>
|
109
|
+
# {"À"=>"A", "Á"=>"A", "Â"=>"A", "Ã"=>"A", "Ä"=>"A", "Å"=>"A", "Æ"=>"AE",
|
110
|
+
# "Ç"=>"C", "È"=>"E", "É"=>"E", "Ê"=>"E", "Ë"=>"E", "Ì"=>"I", "Í"=>"I",
|
111
|
+
# "Î"=>"I", "Ï"=>"I", "Ð"=>"D", "Ñ"=>"N", "Ò"=>"O", "Ó"=>"O", "Ô"=>"O",
|
112
|
+
# "Õ"=>"O", "Ö"=>"O", "×"=>"x", "Ø"=>"O", "Ù"=>"U", "Ú"=>"U", "Û"=>"U",
|
113
|
+
# "Ü"=>"U", "Ý"=>"Y", "Þ"=>"Th", "ß"=>"ss", "à"=>"a", "á"=>"a", "â"=>"a",
|
114
|
+
# "ã"=>"a", "ä"=>"a", "å"=>"a", "æ"=>"ae", "ç"=>"c", "è"=>"e", "é"=>"e",
|
115
|
+
# "ê"=>"e", "ë"=>"e", "ì"=>"i", "í"=>"i", "î"=>"i", "ï"=>"i", "ð"=>"d",
|
116
|
+
# "ñ"=>"n", "ò"=>"o", "ó"=>"o", "ô"=>"o", "õ"=>"o", "ö"=>"o", "ø"=>"o",
|
117
|
+
# "ù"=>"u", "ú"=>"u", "û"=>"u", "ü"=>"u", "ý"=>"y", "þ"=>"th", "ÿ"=>"y",
|
118
|
+
# "Ā"=>"A", "ā"=>"a", "Ă"=>"A", "ă"=>"a", "Ą"=>"A", "ą"=>"a", "Ć"=>"C",
|
119
|
+
# "ć"=>"c", "Ĉ"=>"C", "ĉ"=>"c", "Ċ"=>"C", "ċ"=>"c", "Č"=>"C", "č"=>"c",
|
120
|
+
# "Ď"=>"D", "ď"=>"d", "Đ"=>"D", "đ"=>"d", "Ē"=>"E", "ē"=>"e", "Ĕ"=>"E",
|
121
|
+
# "ĕ"=>"e", "Ė"=>"E", "ė"=>"e", "Ę"=>"E", "ę"=>"e", "Ě"=>"E", "ě"=>"e",
|
122
|
+
# "Ĝ"=>"G", "ĝ"=>"g", "Ğ"=>"G", "ğ"=>"g", "Ġ"=>"G", "ġ"=>"g", "Ģ"=>"G",
|
123
|
+
# "ģ"=>"g", "Ĥ"=>"H", "ĥ"=>"h", "Ħ"=>"H", "ħ"=>"h", "Ĩ"=>"I", "ĩ"=>"i",
|
124
|
+
# "Ī"=>"I", "ī"=>"i", "Ĭ"=>"I", "ĭ"=>"i", "Į"=>"I", "į"=>"i", "İ"=>"I",
|
125
|
+
# "ı"=>"i", "IJ"=>"IJ", "ij"=>"ij", "Ĵ"=>"J", "ĵ"=>"j", "Ķ"=>"K", "ķ"=>"k",
|
126
|
+
# "ĸ"=>"k", "Ĺ"=>"L", "ĺ"=>"l", "Ļ"=>"L", "ļ"=>"l", "Ľ"=>"L", "ľ"=>"l",
|
127
|
+
# "Ŀ"=>"L", "ŀ"=>"l", "Ł"=>"L", "ł"=>"l", "Ń"=>"N", "ń"=>"n", "Ņ"=>"N",
|
128
|
+
# "ņ"=>"n", "Ň"=>"N", "ň"=>"n", "ʼn"=>"'n", "Ŋ"=>"NG", "ŋ"=>"ng",
|
129
|
+
# "Ō"=>"O", "ō"=>"o", "Ŏ"=>"O", "ŏ"=>"o", "Ő"=>"O", "ő"=>"o", "Œ"=>"OE",
|
130
|
+
# "œ"=>"oe", "Ŕ"=>"R", "ŕ"=>"r", "Ŗ"=>"R", "ŗ"=>"r", "Ř"=>"R", "ř"=>"r",
|
131
|
+
# "Ś"=>"S", "ś"=>"s", "Ŝ"=>"S", "ŝ"=>"s", "Ş"=>"S", "ş"=>"s", "Š"=>"S",
|
132
|
+
# "š"=>"s", "Ţ"=>"T", "ţ"=>"t", "Ť"=>"T", "ť"=>"t", "Ŧ"=>"T", "ŧ"=>"t",
|
133
|
+
# "Ũ"=>"U", "ũ"=>"u", "Ū"=>"U", "ū"=>"u", "Ŭ"=>"U", "ŭ"=>"u", "Ů"=>"U",
|
134
|
+
# "ů"=>"u", "Ű"=>"U", "ű"=>"u", "Ų"=>"U", "ų"=>"u", "Ŵ"=>"W", "ŵ"=>"w",
|
135
|
+
# "Ŷ"=>"Y", "ŷ"=>"y", "Ÿ"=>"Y", "Ź"=>"Z", "ź"=>"z", "Ż"=>"Z", "ż"=>"z",
|
136
|
+
# "Ž"=>"Z", "ž"=>"z"},
|
137
|
+
# :german => {"ü"=>"ue", "ö"=>"oe", "ä"=>"ae"},
|
138
|
+
# :spanish => {"Ñ"=>"Nn", "ñ"=>"nn"}}
|
139
|
+
def self.dump_approximations
|
140
|
+
Hash[APPROXIMATIONS.map do |name, approx|
|
141
|
+
[name, Hash[approx.map {|key, value| [[key].pack("U*"), [value].flatten.pack("U*")]}]]
|
142
|
+
end]
|
143
|
+
end
|
144
|
+
|
145
|
+
|
146
|
+
# @param string [String] The string to use as the basis of the SlugString.
|
147
|
+
def initialize(string)
|
148
|
+
super string.to_s
|
149
|
+
tidy_bytes!
|
150
|
+
end
|
151
|
+
|
152
|
+
# Approximate an ASCII string. This works only for Western strings using
|
153
|
+
# characters that are Roman-alphabet characters + diacritics. Non-letter
|
154
|
+
# characters are left unmodified.
|
155
|
+
#
|
156
|
+
# string = SlugString.new "Łódź, Poland"
|
157
|
+
# string.approximate_ascii # => "Lodz, Poland"
|
158
|
+
# string = SlugString.new "日本"
|
159
|
+
# string.approximate_ascii # => "日本"
|
160
|
+
#
|
161
|
+
# You can pass any key(s) from {APPROXIMATIONS} as arguments. This allows
|
162
|
+
# for contextual approximations. By default; +:spanish+ and +:german+ are
|
163
|
+
# provided:
|
164
|
+
#
|
165
|
+
# string = SlugString.new "Jürgen Müller"
|
166
|
+
# string.approximate_ascii # => "Jurgen Muller"
|
167
|
+
# string.approximate_ascii :german # => "Juergen Mueller"
|
168
|
+
# string = SlugString.new "¡Feliz año!"
|
169
|
+
# string.approximate_ascii # => "¡Feliz ano!"
|
170
|
+
# string.approximate_ascii :spanish # => "¡Feliz anno!"
|
171
|
+
#
|
172
|
+
# You can modify the built-in approximations, or add your own:
|
173
|
+
#
|
174
|
+
# # Make Spanish use "nh" rather than "nn"
|
175
|
+
# FriendlyId::SlugString::APPROXIMATIONS[:spanish] = {
|
176
|
+
# # Ñ => "Nh"
|
177
|
+
# 209 => [78, 104],
|
178
|
+
# # ñ => "nh"
|
179
|
+
# 241 => [110, 104]
|
180
|
+
# }
|
181
|
+
#
|
182
|
+
# It's also possible to use a custom approximation for all strings:
|
183
|
+
#
|
184
|
+
# FriendlyId::SlugString.approximations << :german
|
185
|
+
#
|
186
|
+
# Notice that this method does not simply convert to ASCII; if you want
|
187
|
+
# to remove non-ASCII characters such as "¡" and "¿", use {#to_ascii!}:
|
188
|
+
#
|
189
|
+
# string.approximate_ascii!(:spanish) # => "¡Feliz anno!"
|
190
|
+
# string.to_ascii! # => "Feliz anno!"
|
191
|
+
# @param *args <Symbol>
|
192
|
+
# @return String
|
193
|
+
def approximate_ascii!(*args)
|
194
|
+
@maps = (self.class.approximations + args + [:common]).flatten.uniq
|
195
|
+
@wrapped_string = normalize_utf8(:c).unpack("U*").map { |char| approx_char(char) }.flatten.pack("U*")
|
196
|
+
end
|
197
|
+
|
198
|
+
# Removes leading and trailing spaces or dashses, and replaces multiple
|
199
|
+
# whitespace characters with a single space.
|
200
|
+
# @return String
|
201
|
+
def clean!
|
202
|
+
@wrapped_string = @wrapped_string.gsub(/\A\-|\-\z/, "").gsub(/\s+/u, " ").strip
|
203
|
+
end
|
204
|
+
|
205
|
+
# Lowercases the string. Note that this works for Unicode strings,
|
206
|
+
# though your milage may vary with Greek and Turkic strings.
|
207
|
+
# @return String
|
208
|
+
def downcase!
|
209
|
+
@wrapped_string = apply_mapping :lowercase_mapping
|
210
|
+
end
|
211
|
+
|
212
|
+
# Remove any non-word characters.
|
213
|
+
# @return String
|
214
|
+
def word_chars!
|
215
|
+
@wrapped_string = normalize_utf8(:c).unpack("U*").map { |char|
|
216
|
+
case char
|
217
|
+
# control chars
|
218
|
+
when 0..31
|
219
|
+
# punctuation; 45 is "-" (HYPHEN-MINUS) and allowed
|
220
|
+
when 33..44
|
221
|
+
# more puncuation
|
222
|
+
when 46..47
|
223
|
+
# more puncuation and other symbols
|
224
|
+
when 58..64
|
225
|
+
# brackets and other symbols
|
226
|
+
when 91..96
|
227
|
+
# braces, pipe, tilde, etc.
|
228
|
+
when 123..191
|
229
|
+
else char
|
230
|
+
end
|
231
|
+
}.compact.pack("U*")
|
232
|
+
end
|
233
|
+
|
234
|
+
# Normalize the string for a given {FriendlyId::Configuration}.
|
235
|
+
# @param config [FriendlyId::Configuration]
|
236
|
+
# @return String
|
237
|
+
def normalize_for!(config)
|
238
|
+
approximate_ascii! if config.approximate_ascii?
|
239
|
+
to_ascii! if config.strip_non_ascii?
|
240
|
+
normalize!
|
241
|
+
end
|
242
|
+
|
243
|
+
alias :normalize_utf8 :normalize rescue NoMethodError
|
244
|
+
|
245
|
+
# Normalize the string for use as a FriendlyId. Note that in
|
246
|
+
# this context, +normalize+ means, strip, remove non-letters/numbers,
|
247
|
+
# downcasing and converting whitespace to dashes.
|
248
|
+
# ActiveSupport::Multibyte::Chars#normalize is aliased to +normalize_utf8+
|
249
|
+
# in this subclass.
|
250
|
+
# @return String
|
251
|
+
def normalize!
|
252
|
+
clean!
|
253
|
+
word_chars!
|
254
|
+
downcase!
|
255
|
+
with_dashes!
|
256
|
+
end
|
257
|
+
|
258
|
+
# Attempt to replace invalid UTF-8 bytes with valid ones. This method
|
259
|
+
# naively assumes if you have invalid UTF8 bytes, they are either Windows
|
260
|
+
# CP-1252 or ISO8859-1. In practice this isn't a bad assumption, but may not
|
261
|
+
# always work.
|
262
|
+
#
|
263
|
+
# Passing +true+ will forcibly tidy all bytes, assuming that the string's
|
264
|
+
# encoding is CP-1252 or ISO-8859-1.
|
265
|
+
def tidy_bytes!(force = false)
|
266
|
+
|
267
|
+
if force
|
268
|
+
@wrapped_string = @wrapped_string.unpack("C*").map do |b|
|
269
|
+
tidy_byte(b)
|
270
|
+
end.flatten.compact.pack("C*").unpack("U*").pack("U*")
|
271
|
+
end
|
272
|
+
|
273
|
+
bytes = @wrapped_string.unpack("C*")
|
274
|
+
conts_expected = 0
|
275
|
+
last_lead = 0
|
276
|
+
|
277
|
+
bytes.each_index do |i|
|
278
|
+
|
279
|
+
byte = bytes[i]
|
280
|
+
is_ascii = byte < 128
|
281
|
+
is_cont = byte > 127 && byte < 192
|
282
|
+
is_lead = byte > 191 && byte < 245
|
283
|
+
is_unused = byte > 240
|
284
|
+
is_restricted = byte > 244
|
285
|
+
|
286
|
+
# Impossible or highly unlikely byte? Clean it.
|
287
|
+
if is_unused || is_restricted
|
288
|
+
bytes[i] = tidy_byte(byte)
|
289
|
+
elsif is_cont
|
290
|
+
# Not expecting contination byte? Clean up. Otherwise, now expect one less.
|
291
|
+
conts_expected == 0 ? bytes[i] = tidy_byte(byte) : conts_expected -= 1
|
292
|
+
else
|
293
|
+
if conts_expected > 0
|
294
|
+
# Expected continuation, but got ASCII or leading? Clean backwards up to
|
295
|
+
# the leading byte.
|
296
|
+
(1..(i - last_lead)).each {|j| bytes[i - j] = tidy_byte(bytes[i - j])}
|
297
|
+
conts_expected = 0
|
298
|
+
end
|
299
|
+
if is_lead
|
300
|
+
# Final byte is leading? Clean it.
|
301
|
+
if i == bytes.length - 1
|
302
|
+
bytes[i] = tidy_byte(bytes.last)
|
303
|
+
else
|
304
|
+
# Valid leading byte? Expect continuations determined by position of
|
305
|
+
# first zero bit, with max of 3.
|
306
|
+
conts_expected = byte < 224 ? 1 : byte < 240 ? 2 : 3
|
307
|
+
last_lead = i
|
308
|
+
end
|
309
|
+
end
|
310
|
+
end
|
311
|
+
end
|
312
|
+
@wrapped_string = bytes.empty? ? "" : bytes.flatten.compact.pack("C*").unpack("U*").pack("U*")
|
313
|
+
end
|
314
|
+
|
315
|
+
# Delete any non-ascii characters.
|
316
|
+
# @return String
|
317
|
+
def to_ascii!
|
318
|
+
if ">= 1.9".respond_to?(:force_encoding)
|
319
|
+
@wrapped_string.encode!("ASCII", :invalid => :replace, :undef => :replace,
|
320
|
+
:replace => "")
|
321
|
+
else
|
322
|
+
@wrapped_string = tidy_bytes.normalize_utf8(:c).unpack("U*").reject {|char| char > 127}.pack("U*")
|
323
|
+
end
|
324
|
+
end
|
325
|
+
|
326
|
+
# Truncate the string to +max+ length.
|
327
|
+
# @return String
|
328
|
+
def truncate!(max)
|
329
|
+
@wrapped_string = self[0...max].to_s if length > max
|
330
|
+
end
|
331
|
+
|
332
|
+
# Upper-cases the string. Note that this works for Unicode strings,
|
333
|
+
# though your milage may vary with Greek and Turkic strings.
|
334
|
+
# @return String
|
335
|
+
def upcase!
|
336
|
+
@wrapped_string = apply_mapping :uppercase_mapping
|
337
|
+
end
|
338
|
+
|
339
|
+
# Validate that the slug string is not blank or reserved, and truncate
|
340
|
+
# it to the max length if necessary.
|
341
|
+
# @param config [FriendlyId::Configuration]
|
342
|
+
# @return String
|
343
|
+
# @raise FriendlyId::BlankError
|
344
|
+
# @raise FriendlyId::ReservedError
|
345
|
+
def validate_for!(config)
|
346
|
+
truncate!(config.max_length)
|
347
|
+
raise FriendlyId::BlankError if blank?
|
348
|
+
raise FriendlyId::ReservedError if config.reserved?(self)
|
349
|
+
self
|
350
|
+
end
|
351
|
+
|
352
|
+
# Replaces whitespace with dashes ("-").
|
353
|
+
# @return String
|
354
|
+
def with_dashes!
|
355
|
+
@wrapped_string = @wrapped_string.gsub(/[\s\-]+/u, "-")
|
356
|
+
end
|
357
|
+
|
358
|
+
%w[approximate_ascii clean downcase word_chars normalize normalize_for tidy_bytes
|
359
|
+
to_ascii truncate upcase with_dashes].each do |method|
|
360
|
+
class_eval(<<-EOM)
|
361
|
+
def #{method}(*args)
|
362
|
+
send_to_new_instance(:#{method}!, *args)
|
363
|
+
end
|
364
|
+
EOM
|
365
|
+
end
|
366
|
+
|
367
|
+
private
|
368
|
+
|
369
|
+
# Look up the character's approximation in the configured maps.
|
370
|
+
def approx_char(char)
|
371
|
+
@maps.each do |map|
|
372
|
+
if new_char = APPROXIMATIONS[map][char]
|
373
|
+
return new_char
|
374
|
+
end
|
375
|
+
end
|
376
|
+
char
|
377
|
+
end
|
378
|
+
|
379
|
+
# Used as the basis of the bangless methods.
|
380
|
+
def send_to_new_instance(*args)
|
381
|
+
string = SlugString.new self
|
382
|
+
string.send(*args)
|
383
|
+
string
|
384
|
+
end
|
385
|
+
|
386
|
+
def tidy_byte(byte)
|
387
|
+
byte < 160 ? CP1252[byte] : byte < 192 ? [194, byte] : [195, byte - 64]
|
388
|
+
end
|
389
|
+
|
390
|
+
end
|
391
|
+
end
|
@@ -0,0 +1,102 @@
|
|
1
|
+
module FriendlyId
|
2
|
+
module Slugged
|
3
|
+
|
4
|
+
class Status < FriendlyId::Status
|
5
|
+
|
6
|
+
attr_accessor :sequence, :slug
|
7
|
+
|
8
|
+
# Did the find operation use the best possible id? True if +id+ is
|
9
|
+
# numeric, but the model has no slug, or +id+ is friendly and current
|
10
|
+
def best?
|
11
|
+
current? || (numeric? && !record.slug)
|
12
|
+
end
|
13
|
+
|
14
|
+
# Did the find operation use the current slug?
|
15
|
+
def current?
|
16
|
+
!! slug && slug.current?
|
17
|
+
end
|
18
|
+
|
19
|
+
# Did the find operation use a friendly id?
|
20
|
+
def friendly?
|
21
|
+
!! (name or slug)
|
22
|
+
end
|
23
|
+
|
24
|
+
def friendly_id=(friendly_id)
|
25
|
+
@name, @sequence = friendly_id.parse_friendly_id(record.friendly_id_config.sequence_separator)
|
26
|
+
end
|
27
|
+
|
28
|
+
# Did the find operation use an outdated slug?
|
29
|
+
def outdated?
|
30
|
+
!current?
|
31
|
+
end
|
32
|
+
|
33
|
+
# The slug that was used to find the model.
|
34
|
+
def slug
|
35
|
+
@slug ||= record.find_slug(name, sequence)
|
36
|
+
end
|
37
|
+
|
38
|
+
end
|
39
|
+
|
40
|
+
module Model
|
41
|
+
attr_accessor :slug
|
42
|
+
|
43
|
+
def find_slug
|
44
|
+
raise NotImplementedError
|
45
|
+
end
|
46
|
+
|
47
|
+
def friendly_id_config
|
48
|
+
self.class.friendly_id_config
|
49
|
+
end
|
50
|
+
|
51
|
+
# Get the {FriendlyId::Status} after the find has been performed.
|
52
|
+
def friendly_id_status
|
53
|
+
@friendly_id_status ||= Status.new(:record => self)
|
54
|
+
end
|
55
|
+
|
56
|
+
# The friendly id.
|
57
|
+
def friendly_id
|
58
|
+
slug.to_friendly_id if slug?
|
59
|
+
end
|
60
|
+
|
61
|
+
# Clean up the string before setting it as the friendly_id. You can override
|
62
|
+
# this method to add your own custom normalization routines.
|
63
|
+
# @param string An instance of {FriendlyId::SlugString}.
|
64
|
+
# @return [String]
|
65
|
+
def normalize_friendly_id(string)
|
66
|
+
string.normalize_for!(friendly_id_config).to_s
|
67
|
+
end
|
68
|
+
|
69
|
+
# Does the instance have a slug?
|
70
|
+
def slug?
|
71
|
+
!! slug
|
72
|
+
end
|
73
|
+
|
74
|
+
private
|
75
|
+
|
76
|
+
# Get the processed string used as the basis of the friendly id.
|
77
|
+
def slug_text
|
78
|
+
base = send(friendly_id_config.method)
|
79
|
+
unless base.nil? && friendly_id_config.allow_nil?
|
80
|
+
text = normalize_friendly_id(SlugString.new(base))
|
81
|
+
SlugString.new(text.to_s).validate_for!(friendly_id_config).to_s
|
82
|
+
end
|
83
|
+
end
|
84
|
+
|
85
|
+
# Has the slug text changed?
|
86
|
+
def slug_text_changed?
|
87
|
+
slug_text != slug.name
|
88
|
+
end
|
89
|
+
|
90
|
+
# Has the basis of our friendly id changed, requiring the generation of a
|
91
|
+
# new slug?
|
92
|
+
def new_slug_needed?
|
93
|
+
if friendly_id_config.allow_nil?
|
94
|
+
(!slug? && !slug_text.blank?) || (slug? && slug_text_changed?)
|
95
|
+
else
|
96
|
+
!slug? || slug_text_changed?
|
97
|
+
end
|
98
|
+
end
|
99
|
+
|
100
|
+
end
|
101
|
+
end
|
102
|
+
end
|