byk 0.4.0 → 0.5.0
Sign up to get free protection for your applications and to get access to all the features.
- checksums.yaml +4 -4
- data/CHANGELOG.md +6 -2
- data/README.md +10 -6
- data/ext/byk/byk.c +135 -137
- data/lib/byk/version.rb +1 -1
- metadata +2 -2
checksums.yaml
CHANGED
|
@@ -1,7 +1,7 @@
|
|
|
1
1
|
---
|
|
2
2
|
SHA1:
|
|
3
|
-
metadata.gz:
|
|
4
|
-
data.tar.gz:
|
|
3
|
+
metadata.gz: 70b44d7687698d589bad7ddd888824bb58d4146d
|
|
4
|
+
data.tar.gz: a9c6c155c85533e0d16e8515176929faaf456613
|
|
5
5
|
SHA512:
|
|
6
|
-
metadata.gz:
|
|
7
|
-
data.tar.gz:
|
|
6
|
+
metadata.gz: 4543d2bc442e1bfcbb5bc5030a4cbb3cfdc456e68a7a4da2b623039109f0faa52aad4f335c1856f574d4b51a82f9ba5fb4f97beee8dc364126064df6b3cf70b5
|
|
7
|
+
data.tar.gz: a852ce68e4635d1af3f48e0e29c7b987c53f216d63fcbe9102c05ba825eb3c74cc7317bf807d9f9ec687312a5962f73533eaa12e822407a326d3bfcb3d0901b7
|
data/CHANGELOG.md
CHANGED
|
@@ -1,9 +1,13 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
### Byk 0.5.0 (2015-04-18)
|
|
4
|
+
|
|
5
|
+
* Performance tuning and refactoring, up to 5x speedup
|
|
6
|
+
* Dropped the unused optional arg
|
|
7
|
+
|
|
3
8
|
### Byk 0.4.0 (2015-04-17)
|
|
4
9
|
|
|
5
|
-
* Performance tuning and refactoring
|
|
6
|
-
* Updated benchmark
|
|
10
|
+
* Performance tuning and refactoring
|
|
7
11
|
* Introduced changelog
|
|
8
12
|
|
|
9
13
|
### Byk 0.3.0 (2015-04-16)
|
data/README.md
CHANGED
|
@@ -71,8 +71,9 @@ Note that these methods take into account the
|
|
|
71
71
|
|
|
72
72
|
## How fast is fast?
|
|
73
73
|
|
|
74
|
-
About [
|
|
75
|
-
my hardware
|
|
74
|
+
About [10-40x faster](benchmark) than the baseline Ruby implementation
|
|
75
|
+
on my hardware, depending on the string's Cyrillic content ratio. YMMV
|
|
76
|
+
of course.
|
|
76
77
|
|
|
77
78
|
|
|
78
79
|
## Raison d'être
|
|
@@ -88,10 +89,13 @@ with Ruby extensions, so there :smile_cat:
|
|
|
88
89
|
|
|
89
90
|
## Compatibility
|
|
90
91
|
|
|
91
|
-
Byk is supported under MRI Ruby >= 1.9.2.
|
|
92
|
-
|
|
93
|
-
|
|
94
|
-
|
|
92
|
+
Byk is supported under MRI Ruby >= 1.9.2.
|
|
93
|
+
|
|
94
|
+
I don't plan to support 1.8.7 or older due to substantial C API
|
|
95
|
+
changes between 1.8 and 1.9.
|
|
96
|
+
|
|
97
|
+
It doesn't build under Rubinius currently, but I intend to support it
|
|
98
|
+
in future releases.
|
|
95
99
|
|
|
96
100
|
|
|
97
101
|
## License
|
data/ext/byk/byk.c
CHANGED
|
@@ -1,25 +1,11 @@
|
|
|
1
|
-
#include <stdio.h>
|
|
2
1
|
#include <ruby.h>
|
|
3
2
|
#include <ruby/encoding.h>
|
|
4
3
|
|
|
5
|
-
#ifndef rb_check_arity
|
|
6
|
-
#define rb_check_arity rb_check_arity
|
|
7
|
-
|
|
8
|
-
NORETURN(void rb_error_arity(int, int, int));
|
|
9
|
-
|
|
10
|
-
static inline void
|
|
11
|
-
rb_check_arity(int argc, int min, int max)
|
|
12
|
-
{
|
|
13
|
-
if ((argc < min) || (max != -1 && argc > max))
|
|
14
|
-
rb_error_arity(argc, min, max);
|
|
15
|
-
}
|
|
16
|
-
#endif
|
|
17
|
-
|
|
18
4
|
#define STR_ENC_GET(str) rb_enc_from_index(ENCODING_GET(str))
|
|
19
5
|
|
|
20
|
-
#define STR_CAT_COND_ASCII(ascii, dest, chr, ascii_chr, len, enc)
|
|
21
|
-
ascii ?
|
|
22
|
-
|
|
6
|
+
#define STR_CAT_COND_ASCII(ascii, dest, chr, ascii_chr, len, enc) \
|
|
7
|
+
ascii ? rb_str_buf_cat(dest, chr, len) \
|
|
8
|
+
: str_cat_char(dest, ascii_chr, enc)
|
|
23
9
|
|
|
24
10
|
enum {
|
|
25
11
|
LAT_CAP_TJ=262,
|
|
@@ -112,25 +98,23 @@ str_cat_char(VALUE str, unsigned int c, rb_encoding *enc)
|
|
|
112
98
|
char s[16];
|
|
113
99
|
int n = rb_enc_codelen(c, enc);
|
|
114
100
|
rb_enc_mbcput(c, s, enc);
|
|
115
|
-
|
|
101
|
+
rb_str_buf_cat(str, s, n);
|
|
116
102
|
}
|
|
117
103
|
|
|
118
104
|
static VALUE
|
|
119
|
-
str_to_latin(
|
|
105
|
+
str_to_latin(VALUE str, int ascii, int bang)
|
|
120
106
|
{
|
|
121
107
|
VALUE dest;
|
|
122
108
|
long dest_len;
|
|
123
|
-
char *pos, *end;
|
|
124
|
-
rb_encoding *enc;
|
|
125
109
|
int len, next_len;
|
|
126
110
|
int seen_upper = 0;
|
|
127
111
|
int force_upper = 0;
|
|
112
|
+
char *pos = RSTRING_PTR(str);
|
|
113
|
+
char *end, *seq_start = 0;
|
|
128
114
|
unsigned int codepoint = 0;
|
|
129
115
|
unsigned int next_codepoint = 0;
|
|
116
|
+
rb_encoding *enc;
|
|
130
117
|
|
|
131
|
-
rb_check_arity(argc, 0, 1);
|
|
132
|
-
|
|
133
|
-
pos = RSTRING_PTR(str);
|
|
134
118
|
if (!pos || RSTRING_LEN(str) == 0) return str;
|
|
135
119
|
|
|
136
120
|
end = RSTRING_END(str);
|
|
@@ -146,134 +130,148 @@ str_to_latin(int argc, VALUE *argv, VALUE str, int ascii, int bang)
|
|
|
146
130
|
next_codepoint = rb_enc_codepoint_len(pos + len, end, &next_len, enc);
|
|
147
131
|
}
|
|
148
132
|
|
|
149
|
-
force_upper = seen_upper || is_upper_case(next_codepoint);
|
|
150
|
-
seen_upper = is_upper_case(codepoint);
|
|
151
|
-
|
|
152
133
|
/* Latin -> "ASCII Latin" conversion */
|
|
153
134
|
if (ascii && codepoint >= LAT_CAP_TJ && codepoint <= LAT_ZH) {
|
|
135
|
+
if (seq_start) {
|
|
136
|
+
/* flush the sequence */
|
|
137
|
+
rb_str_buf_cat(dest, seq_start, pos - seq_start);
|
|
138
|
+
seq_start = 0;
|
|
139
|
+
}
|
|
154
140
|
switch (codepoint) {
|
|
155
141
|
case LAT_TJ:
|
|
156
|
-
case LAT_CH:
|
|
157
|
-
case LAT_DJ:
|
|
158
|
-
case LAT_SH:
|
|
159
|
-
case LAT_ZH:
|
|
142
|
+
case LAT_CH: rb_str_buf_cat(dest, "c", 1); break;
|
|
143
|
+
case LAT_DJ: rb_str_buf_cat(dest, "dj", 2); break;
|
|
144
|
+
case LAT_SH: rb_str_buf_cat(dest, "s", 1); break;
|
|
145
|
+
case LAT_ZH: rb_str_buf_cat(dest, "z", 1); break;
|
|
160
146
|
case LAT_CAP_TJ:
|
|
161
|
-
case LAT_CAP_CH:
|
|
162
|
-
case LAT_CAP_SH:
|
|
163
|
-
case LAT_CAP_ZH:
|
|
164
|
-
|
|
147
|
+
case LAT_CAP_CH: rb_str_buf_cat(dest, "C", 1); break;
|
|
148
|
+
case LAT_CAP_SH: rb_str_buf_cat(dest, "S", 1); break;
|
|
149
|
+
case LAT_CAP_ZH: rb_str_buf_cat(dest, "Z", 1); break;
|
|
165
150
|
case LAT_CAP_DJ:
|
|
166
|
-
|
|
167
|
-
|
|
151
|
+
(seen_upper || is_upper_case(next_codepoint))
|
|
152
|
+
? rb_str_buf_cat(dest, "DJ", 2)
|
|
153
|
+
: rb_str_buf_cat(dest, "Dj", 2);
|
|
168
154
|
break;
|
|
169
155
|
default:
|
|
170
|
-
|
|
156
|
+
rb_str_buf_cat(dest, pos, len);
|
|
171
157
|
}
|
|
172
158
|
}
|
|
173
159
|
|
|
174
|
-
/*
|
|
160
|
+
/* Mark a start of inconsequential sequence */
|
|
175
161
|
else if (codepoint < CYR_CAP_DJ || codepoint > CYR_DZ) {
|
|
176
|
-
|
|
162
|
+
if (!seq_start)
|
|
163
|
+
seq_start = pos;
|
|
177
164
|
}
|
|
178
165
|
|
|
179
166
|
/* Cyrillic -> Latin conversion */
|
|
180
|
-
else
|
|
181
|
-
|
|
182
|
-
|
|
183
|
-
|
|
184
|
-
|
|
185
|
-
case CYR_G: rb_enc_str_buf_cat(dest, "g", 1, enc); break;
|
|
186
|
-
case CYR_D: rb_enc_str_buf_cat(dest, "d", 1, enc); break;
|
|
187
|
-
case CYR_E: rb_enc_str_buf_cat(dest, "e", 1, enc); break;
|
|
188
|
-
case CYR_Z: rb_enc_str_buf_cat(dest, "z", 1, enc); break;
|
|
189
|
-
case CYR_I: rb_enc_str_buf_cat(dest, "i", 1, enc); break;
|
|
190
|
-
case CYR_K: rb_enc_str_buf_cat(dest, "k", 1, enc); break;
|
|
191
|
-
case CYR_L: rb_enc_str_buf_cat(dest, "l", 1, enc); break;
|
|
192
|
-
case CYR_M: rb_enc_str_buf_cat(dest, "m", 1, enc); break;
|
|
193
|
-
case CYR_N: rb_enc_str_buf_cat(dest, "n", 1, enc); break;
|
|
194
|
-
case CYR_O: rb_enc_str_buf_cat(dest, "o", 1, enc); break;
|
|
195
|
-
case CYR_P: rb_enc_str_buf_cat(dest, "p", 1, enc); break;
|
|
196
|
-
case CYR_R: rb_enc_str_buf_cat(dest, "r", 1, enc); break;
|
|
197
|
-
case CYR_S: rb_enc_str_buf_cat(dest, "s", 1, enc); break;
|
|
198
|
-
case CYR_T: rb_enc_str_buf_cat(dest, "t", 1, enc); break;
|
|
199
|
-
case CYR_U: rb_enc_str_buf_cat(dest, "u", 1, enc); break;
|
|
200
|
-
case CYR_F: rb_enc_str_buf_cat(dest, "f", 1, enc); break;
|
|
201
|
-
case CYR_H: rb_enc_str_buf_cat(dest, "h", 1, enc); break;
|
|
202
|
-
case CYR_C: rb_enc_str_buf_cat(dest, "c", 1, enc); break;
|
|
203
|
-
case CYR_J: rb_enc_str_buf_cat(dest, "j", 1, enc); break;
|
|
204
|
-
case CYR_LJ: rb_enc_str_buf_cat(dest, "lj", 2, enc); break;
|
|
205
|
-
case CYR_NJ: rb_enc_str_buf_cat(dest, "nj", 2, enc); break;
|
|
206
|
-
case CYR_DJ: STR_CAT_COND_ASCII(ascii, dest, "dj", LAT_DJ, 2, enc); break;
|
|
207
|
-
case CYR_TJ: STR_CAT_COND_ASCII(ascii, dest, "c", LAT_TJ, 1, enc); break;
|
|
208
|
-
case CYR_CH: STR_CAT_COND_ASCII(ascii, dest, "c", LAT_CH, 1, enc); break;
|
|
209
|
-
case CYR_ZH: STR_CAT_COND_ASCII(ascii, dest, "z", LAT_ZH, 1, enc); break;
|
|
210
|
-
case CYR_SH: STR_CAT_COND_ASCII(ascii, dest, "s", LAT_SH, 1, enc); break;
|
|
211
|
-
case CYR_DZ:
|
|
212
|
-
rb_enc_str_buf_cat(dest, "d", 1, enc);
|
|
213
|
-
STR_CAT_COND_ASCII(ascii, dest, "z", LAT_ZH, 1, enc);
|
|
214
|
-
break;
|
|
215
|
-
default:
|
|
216
|
-
rb_enc_str_buf_cat(dest, pos, len, enc);
|
|
167
|
+
else {
|
|
168
|
+
if (seq_start) {
|
|
169
|
+
/* flush the sequence */
|
|
170
|
+
rb_str_buf_cat(dest, seq_start, pos - seq_start);
|
|
171
|
+
seq_start = 0;
|
|
217
172
|
}
|
|
218
|
-
}
|
|
219
173
|
|
|
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
|
-
rb_enc_str_buf_cat(dest, (force_upper ? "NJ" : "Nj"), 2, enc);
|
|
254
|
-
break;
|
|
255
|
-
case CYR_CAP_DJ:
|
|
256
|
-
STR_CAT_COND_ASCII(ascii, dest, (force_upper ? "DJ" : "Dj"), LAT_CAP_DJ, 2, enc);
|
|
257
|
-
break;
|
|
258
|
-
case CYR_CAP_DZ:
|
|
259
|
-
rb_enc_str_buf_cat(dest, "D", 1, enc);
|
|
260
|
-
if (force_upper) {
|
|
261
|
-
STR_CAT_COND_ASCII(ascii, dest, "Z", LAT_CAP_ZH, 1, enc);
|
|
262
|
-
}
|
|
263
|
-
else {
|
|
174
|
+
if (codepoint >= CYR_A) {
|
|
175
|
+
switch (codepoint) {
|
|
176
|
+
case CYR_A: rb_str_buf_cat(dest, "a", 1); break;
|
|
177
|
+
case CYR_B: rb_str_buf_cat(dest, "b", 1); break;
|
|
178
|
+
case CYR_V: rb_str_buf_cat(dest, "v", 1); break;
|
|
179
|
+
case CYR_G: rb_str_buf_cat(dest, "g", 1); break;
|
|
180
|
+
case CYR_D: rb_str_buf_cat(dest, "d", 1); break;
|
|
181
|
+
case CYR_E: rb_str_buf_cat(dest, "e", 1); break;
|
|
182
|
+
case CYR_Z: rb_str_buf_cat(dest, "z", 1); break;
|
|
183
|
+
case CYR_I: rb_str_buf_cat(dest, "i", 1); break;
|
|
184
|
+
case CYR_J: rb_str_buf_cat(dest, "j", 1); break;
|
|
185
|
+
case CYR_K: rb_str_buf_cat(dest, "k", 1); break;
|
|
186
|
+
case CYR_L: rb_str_buf_cat(dest, "l", 1); break;
|
|
187
|
+
case CYR_M: rb_str_buf_cat(dest, "m", 1); break;
|
|
188
|
+
case CYR_N: rb_str_buf_cat(dest, "n", 1); break;
|
|
189
|
+
case CYR_O: rb_str_buf_cat(dest, "o", 1); break;
|
|
190
|
+
case CYR_P: rb_str_buf_cat(dest, "p", 1); break;
|
|
191
|
+
case CYR_R: rb_str_buf_cat(dest, "r", 1); break;
|
|
192
|
+
case CYR_S: rb_str_buf_cat(dest, "s", 1); break;
|
|
193
|
+
case CYR_T: rb_str_buf_cat(dest, "t", 1); break;
|
|
194
|
+
case CYR_U: rb_str_buf_cat(dest, "u", 1); break;
|
|
195
|
+
case CYR_F: rb_str_buf_cat(dest, "f", 1); break;
|
|
196
|
+
case CYR_H: rb_str_buf_cat(dest, "h", 1); break;
|
|
197
|
+
case CYR_C: rb_str_buf_cat(dest, "c", 1); break;
|
|
198
|
+
case CYR_LJ: rb_str_buf_cat(dest, "lj", 2); break;
|
|
199
|
+
case CYR_NJ: rb_str_buf_cat(dest, "nj", 2); break;
|
|
200
|
+
case CYR_DJ: STR_CAT_COND_ASCII(ascii, dest, "dj", LAT_DJ, 2, enc); break;
|
|
201
|
+
case CYR_TJ: STR_CAT_COND_ASCII(ascii, dest, "c", LAT_TJ, 1, enc); break;
|
|
202
|
+
case CYR_CH: STR_CAT_COND_ASCII(ascii, dest, "c", LAT_CH, 1, enc); break;
|
|
203
|
+
case CYR_ZH: STR_CAT_COND_ASCII(ascii, dest, "z", LAT_ZH, 1, enc); break;
|
|
204
|
+
case CYR_SH: STR_CAT_COND_ASCII(ascii, dest, "s", LAT_SH, 1, enc); break;
|
|
205
|
+
case CYR_DZ:
|
|
206
|
+
rb_str_buf_cat(dest, "d", 1);
|
|
264
207
|
STR_CAT_COND_ASCII(ascii, dest, "z", LAT_ZH, 1, enc);
|
|
208
|
+
break;
|
|
209
|
+
default:
|
|
210
|
+
rb_str_buf_cat(dest, pos, len);
|
|
211
|
+
}
|
|
212
|
+
}
|
|
213
|
+
else {
|
|
214
|
+
force_upper = seen_upper || is_upper_case(next_codepoint);
|
|
215
|
+
|
|
216
|
+
switch (codepoint) {
|
|
217
|
+
case CYR_CAP_A: rb_str_buf_cat(dest, "A", 1); break;
|
|
218
|
+
case CYR_CAP_B: rb_str_buf_cat(dest, "B", 1); break;
|
|
219
|
+
case CYR_CAP_V: rb_str_buf_cat(dest, "V", 1); break;
|
|
220
|
+
case CYR_CAP_G: rb_str_buf_cat(dest, "G", 1); break;
|
|
221
|
+
case CYR_CAP_D: rb_str_buf_cat(dest, "D", 1); break;
|
|
222
|
+
case CYR_CAP_E: rb_str_buf_cat(dest, "E", 1); break;
|
|
223
|
+
case CYR_CAP_Z: rb_str_buf_cat(dest, "Z", 1); break;
|
|
224
|
+
case CYR_CAP_I: rb_str_buf_cat(dest, "I", 1); break;
|
|
225
|
+
case CYR_CAP_J: rb_str_buf_cat(dest, "J", 1); break;
|
|
226
|
+
case CYR_CAP_K: rb_str_buf_cat(dest, "K", 1); break;
|
|
227
|
+
case CYR_CAP_L: rb_str_buf_cat(dest, "L", 1); break;
|
|
228
|
+
case CYR_CAP_M: rb_str_buf_cat(dest, "M", 1); break;
|
|
229
|
+
case CYR_CAP_N: rb_str_buf_cat(dest, "N", 1); break;
|
|
230
|
+
case CYR_CAP_O: rb_str_buf_cat(dest, "O", 1); break;
|
|
231
|
+
case CYR_CAP_P: rb_str_buf_cat(dest, "P", 1); break;
|
|
232
|
+
case CYR_CAP_R: rb_str_buf_cat(dest, "R", 1); break;
|
|
233
|
+
case CYR_CAP_S: rb_str_buf_cat(dest, "S", 1); break;
|
|
234
|
+
case CYR_CAP_T: rb_str_buf_cat(dest, "T", 1); break;
|
|
235
|
+
case CYR_CAP_U: rb_str_buf_cat(dest, "U", 1); break;
|
|
236
|
+
case CYR_CAP_F: rb_str_buf_cat(dest, "F", 1); break;
|
|
237
|
+
case CYR_CAP_H: rb_str_buf_cat(dest, "H", 1); break;
|
|
238
|
+
case CYR_CAP_C: rb_str_buf_cat(dest, "C", 1); break;
|
|
239
|
+
case CYR_CAP_LJ: rb_str_buf_cat(dest, (force_upper ? "LJ" : "Lj"), 2); break;
|
|
240
|
+
case CYR_CAP_NJ: rb_str_buf_cat(dest, (force_upper ? "NJ" : "Nj"), 2); break;
|
|
241
|
+
case CYR_CAP_TJ: STR_CAT_COND_ASCII(ascii, dest, "C", LAT_CAP_TJ, 1, enc); break;
|
|
242
|
+
case CYR_CAP_CH: STR_CAT_COND_ASCII(ascii, dest, "C", LAT_CAP_CH, 1, enc); break;
|
|
243
|
+
case CYR_CAP_ZH: STR_CAT_COND_ASCII(ascii, dest, "Z", LAT_CAP_ZH, 1, enc); break;
|
|
244
|
+
case CYR_CAP_SH: STR_CAT_COND_ASCII(ascii, dest, "S", LAT_CAP_SH, 1, enc); break;
|
|
245
|
+
case CYR_CAP_DJ: STR_CAT_COND_ASCII(ascii, dest, (force_upper ? "DJ" : "Dj"), LAT_CAP_DJ, 2, enc); break;
|
|
246
|
+
case CYR_CAP_DZ:
|
|
247
|
+
rb_str_buf_cat(dest, "D", 1);
|
|
248
|
+
if (force_upper) {
|
|
249
|
+
STR_CAT_COND_ASCII(ascii, dest, "Z", LAT_CAP_ZH, 1, enc);
|
|
250
|
+
}
|
|
251
|
+
else {
|
|
252
|
+
STR_CAT_COND_ASCII(ascii, dest, "z", LAT_ZH, 1, enc);
|
|
253
|
+
}
|
|
254
|
+
break;
|
|
255
|
+
default:
|
|
256
|
+
rb_str_buf_cat(dest, pos, len);
|
|
265
257
|
}
|
|
266
|
-
break;
|
|
267
|
-
default:
|
|
268
|
-
rb_enc_str_buf_cat(dest, pos, len, enc);
|
|
269
258
|
}
|
|
270
259
|
}
|
|
260
|
+
|
|
261
|
+
seen_upper = is_upper_case(codepoint);
|
|
262
|
+
|
|
271
263
|
pos += len;
|
|
272
264
|
len = next_len;
|
|
265
|
+
|
|
273
266
|
codepoint = next_codepoint;
|
|
274
267
|
next_codepoint = 0;
|
|
275
268
|
}
|
|
276
269
|
|
|
270
|
+
if (seq_start) {
|
|
271
|
+
/* flush the last sequence */
|
|
272
|
+
rb_str_buf_cat(dest, seq_start, pos - seq_start);
|
|
273
|
+
}
|
|
274
|
+
|
|
277
275
|
if (bang) {
|
|
278
276
|
rb_str_shared_replace(str, dest);
|
|
279
277
|
}
|
|
@@ -286,29 +284,29 @@ str_to_latin(int argc, VALUE *argv, VALUE str, int ascii, int bang)
|
|
|
286
284
|
}
|
|
287
285
|
|
|
288
286
|
static VALUE
|
|
289
|
-
rb_str_to_latin(
|
|
290
|
-
return str_to_latin(
|
|
287
|
+
rb_str_to_latin(VALUE str) {
|
|
288
|
+
return str_to_latin(str, 0, 0);
|
|
291
289
|
}
|
|
292
290
|
|
|
293
291
|
static VALUE
|
|
294
|
-
rb_str_to_latin_bang(
|
|
295
|
-
return str_to_latin(
|
|
292
|
+
rb_str_to_latin_bang(VALUE str) {
|
|
293
|
+
return str_to_latin(str, 0, 1);
|
|
296
294
|
}
|
|
297
295
|
|
|
298
296
|
static VALUE
|
|
299
|
-
rb_str_to_ascii_latin(
|
|
300
|
-
return str_to_latin(
|
|
297
|
+
rb_str_to_ascii_latin(VALUE str) {
|
|
298
|
+
return str_to_latin(str, 1, 0);
|
|
301
299
|
}
|
|
302
300
|
|
|
303
301
|
static VALUE
|
|
304
|
-
rb_str_to_ascii_latin_bang(
|
|
305
|
-
return str_to_latin(
|
|
302
|
+
rb_str_to_ascii_latin_bang(VALUE str) {
|
|
303
|
+
return str_to_latin(str, 1, 1);
|
|
306
304
|
}
|
|
307
305
|
|
|
308
306
|
void Init_byk_native(void)
|
|
309
307
|
{
|
|
310
|
-
rb_define_method(rb_cString, "to_latin",
|
|
311
|
-
rb_define_method(rb_cString, "to_latin!", rb_str_to_latin_bang,
|
|
312
|
-
rb_define_method(rb_cString, "to_ascii_latin", rb_str_to_ascii_latin,
|
|
313
|
-
rb_define_method(rb_cString, "to_ascii_latin!", rb_str_to_ascii_latin_bang,
|
|
308
|
+
rb_define_method(rb_cString, "to_latin", rb_str_to_latin, 0);
|
|
309
|
+
rb_define_method(rb_cString, "to_latin!", rb_str_to_latin_bang, 0);
|
|
310
|
+
rb_define_method(rb_cString, "to_ascii_latin", rb_str_to_ascii_latin, 0);
|
|
311
|
+
rb_define_method(rb_cString, "to_ascii_latin!", rb_str_to_ascii_latin_bang, 0);
|
|
314
312
|
}
|
data/lib/byk/version.rb
CHANGED
metadata
CHANGED
|
@@ -1,14 +1,14 @@
|
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
|
2
2
|
name: byk
|
|
3
3
|
version: !ruby/object:Gem::Version
|
|
4
|
-
version: 0.
|
|
4
|
+
version: 0.5.0
|
|
5
5
|
platform: ruby
|
|
6
6
|
authors:
|
|
7
7
|
- Nikola Topalović
|
|
8
8
|
autorequire:
|
|
9
9
|
bindir: bin
|
|
10
10
|
cert_chain: []
|
|
11
|
-
date: 2015-04-
|
|
11
|
+
date: 2015-04-18 00:00:00.000000000 Z
|
|
12
12
|
dependencies:
|
|
13
13
|
- !ruby/object:Gem::Dependency
|
|
14
14
|
name: rake-compiler
|