patrickod-raspell 1.1
Sign up to get free protection for your applications and to get access to all the features.
- data/CHANGELOG +6 -0
- data/LICENSE +342 -0
- data/README +78 -0
- data/Rakefile +16 -0
- data/ext/extconf.rb +6 -0
- data/ext/raspell.c +726 -0
- data/ext/raspell.h +13 -0
- data/lib/raspell_stub.rb +113 -0
- data/raspell.gemspec +31 -0
- data/test/simple_test.rb +36 -0
- metadata +68 -0
data/ext/raspell.c
ADDED
@@ -0,0 +1,726 @@
|
|
1
|
+
|
2
|
+
#include "raspell.h"
|
3
|
+
|
4
|
+
extern void Init_dictinfo();
|
5
|
+
extern void Init_aspell();
|
6
|
+
|
7
|
+
void Init_raspell() {
|
8
|
+
cAspellError = rb_define_class("AspellError", rb_eStandardError);
|
9
|
+
Init_dictinfo();
|
10
|
+
Init_aspell();
|
11
|
+
}
|
12
|
+
|
13
|
+
static AspellDictInfo* get_info(VALUE info) {
|
14
|
+
AspellDictInfo *result;
|
15
|
+
Data_Get_Struct(info, AspellDictInfo, result);
|
16
|
+
return result;
|
17
|
+
}
|
18
|
+
|
19
|
+
static VALUE dictinfo_s_new(int argc, VALUE *argv, VALUE klass) {
|
20
|
+
rb_raise(rb_eException, "not instantiable");
|
21
|
+
}
|
22
|
+
|
23
|
+
static VALUE dictinfo_name(VALUE self) {
|
24
|
+
return rb_str_new2(get_info(self)->name);
|
25
|
+
}
|
26
|
+
|
27
|
+
static VALUE dictinfo_code(VALUE self) {
|
28
|
+
return rb_str_new2(get_info(self)->code);
|
29
|
+
}
|
30
|
+
|
31
|
+
static VALUE dictinfo_jargon(VALUE self) {
|
32
|
+
return rb_str_new2(get_info(self)->jargon);
|
33
|
+
}
|
34
|
+
|
35
|
+
static VALUE dictinfo_size(VALUE self) {
|
36
|
+
return INT2FIX(get_info(self)->size);
|
37
|
+
}
|
38
|
+
|
39
|
+
static VALUE dictinfo_size_str(VALUE self) {
|
40
|
+
return rb_str_new2(get_info(self)->size_str);
|
41
|
+
}
|
42
|
+
|
43
|
+
void Init_dictinfo() {
|
44
|
+
//CLASS DEFINITION=========================================================
|
45
|
+
cDictInfo = rb_define_class("AspellDictInfo", rb_cObject);
|
46
|
+
|
47
|
+
//CLASS METHODS============================================================
|
48
|
+
rb_define_singleton_method(cDictInfo, "new", dictinfo_s_new, 0);
|
49
|
+
|
50
|
+
//METHODS =================================================================
|
51
|
+
rb_define_method(cDictInfo, "name", dictinfo_name, 0);
|
52
|
+
rb_define_method(cDictInfo, "code", dictinfo_code, 0);
|
53
|
+
rb_define_method(cDictInfo, "jargon", dictinfo_jargon, 0);
|
54
|
+
rb_define_method(cDictInfo, "size", dictinfo_size, 0);
|
55
|
+
rb_define_method(cDictInfo, "size_str", dictinfo_size_str, 0);
|
56
|
+
}
|
57
|
+
|
58
|
+
extern VALUE rb_cFile;
|
59
|
+
|
60
|
+
/**
|
61
|
+
* This method is called from the garbage collector during finalization.
|
62
|
+
* @param p pointer to spellchecker-object.
|
63
|
+
*/
|
64
|
+
static void aspell_free(void *p) {
|
65
|
+
delete_aspell_speller(p);
|
66
|
+
}
|
67
|
+
|
68
|
+
/**
|
69
|
+
* Check for an error - raise exception if so.
|
70
|
+
* @param speller the spellchecker-object.
|
71
|
+
* @return void
|
72
|
+
* @exception Exception if there was an error.
|
73
|
+
*/
|
74
|
+
static void check_for_error(AspellSpeller * speller) {
|
75
|
+
if (aspell_speller_error(speller) != 0) {
|
76
|
+
rb_raise(cAspellError, aspell_speller_error_message(speller));
|
77
|
+
}
|
78
|
+
}
|
79
|
+
|
80
|
+
/**
|
81
|
+
* Set a specific option, that is known by aspell.
|
82
|
+
* @param config the config object of a specific spellchecker.
|
83
|
+
* @param key the option to set (eg: lang).
|
84
|
+
* @param value the value of the option to set (eg: "us_US").
|
85
|
+
* @exception Exception if key not known, or value undefined.
|
86
|
+
*/
|
87
|
+
static void set_option(AspellConfig *config, char *key, char *value) {
|
88
|
+
//printf("set option: %s = %s\n", key, value);
|
89
|
+
if (aspell_config_replace(config, key, value) == 0) {
|
90
|
+
rb_raise(cAspellError, aspell_config_error_message(config));
|
91
|
+
}
|
92
|
+
//check config:
|
93
|
+
if (aspell_config_error(config) != 0) {
|
94
|
+
rb_raise(cAspellError, aspell_config_error_message(config));
|
95
|
+
}
|
96
|
+
}
|
97
|
+
|
98
|
+
static void set_options(AspellConfig *config, VALUE hash) {
|
99
|
+
VALUE options = rb_funcall(hash, rb_intern("keys"), 0);
|
100
|
+
int count=RARRAY_LEN(options);
|
101
|
+
int c = 0;
|
102
|
+
//set all values
|
103
|
+
while(c<count) {
|
104
|
+
//fetch option
|
105
|
+
VALUE option = RARRAY_PTR(options)[c];
|
106
|
+
VALUE value = rb_funcall(hash, rb_intern("fetch"), 1, option);
|
107
|
+
if (TYPE(option)!=T_STRING) rb_raise(cAspellError, "Given key must be a string.");
|
108
|
+
if (TYPE(value )!=T_STRING) rb_raise(cAspellError, "Given value must be a string.");
|
109
|
+
set_option(config, STR2CSTR(option), STR2CSTR(value));
|
110
|
+
c++;
|
111
|
+
}
|
112
|
+
}
|
113
|
+
|
114
|
+
/**
|
115
|
+
* Extract c-struct speller from ruby object.
|
116
|
+
* @param speller the speller as ruby object.
|
117
|
+
* @return the speller as c-struct.
|
118
|
+
*/
|
119
|
+
static AspellSpeller* get_speller(VALUE speller) {
|
120
|
+
AspellSpeller *result;
|
121
|
+
Data_Get_Struct(speller, AspellSpeller, result);
|
122
|
+
return result;
|
123
|
+
}
|
124
|
+
|
125
|
+
/**
|
126
|
+
* Generate a document checker object from a given speller.
|
127
|
+
* @param speller the speller that shall chech a document.
|
128
|
+
* @return a fresh document checker.
|
129
|
+
*/
|
130
|
+
static AspellDocumentChecker* get_checker(AspellSpeller *speller) {
|
131
|
+
AspellCanHaveError * ret;
|
132
|
+
AspellDocumentChecker * checker;
|
133
|
+
ret = new_aspell_document_checker(speller);
|
134
|
+
if (aspell_error(ret) != 0)
|
135
|
+
rb_raise(cAspellError, aspell_error_message(ret));
|
136
|
+
checker = to_aspell_document_checker(ret);
|
137
|
+
return checker;
|
138
|
+
}
|
139
|
+
|
140
|
+
/**
|
141
|
+
* Utility function that wraps a list of words as ruby array of ruby strings.
|
142
|
+
* @param list an aspell wordlist.
|
143
|
+
* @return an ruby array, containing all words as ruby strings.
|
144
|
+
*/
|
145
|
+
static VALUE get_list(const AspellWordList *list) {
|
146
|
+
VALUE result = rb_ary_new2(aspell_word_list_size(list));
|
147
|
+
if (list != 0) {
|
148
|
+
AspellStringEnumeration * els = aspell_word_list_elements(list);
|
149
|
+
const char * word;
|
150
|
+
while ( (word = aspell_string_enumeration_next(els)) != 0) {
|
151
|
+
rb_ary_push(result, rb_str_new2(word));
|
152
|
+
}
|
153
|
+
delete_aspell_string_enumeration(els);
|
154
|
+
}
|
155
|
+
return result;
|
156
|
+
}
|
157
|
+
|
158
|
+
/**
|
159
|
+
* Generate a regexp from the given word with word boundaries.
|
160
|
+
* @param word the word to match.
|
161
|
+
* @return regular expression, matching exactly the word as whole.
|
162
|
+
*/
|
163
|
+
static VALUE get_wordregexp(VALUE word) {
|
164
|
+
char *cword = STR2CSTR(word);
|
165
|
+
char *result = malloc((strlen(cword)+5)*sizeof(char));
|
166
|
+
*result='\0';
|
167
|
+
strcat(result, "\\b");
|
168
|
+
strcat(result, cword);
|
169
|
+
strcat(result, "\\b");
|
170
|
+
word = rb_reg_new(result, strlen(result), 0);
|
171
|
+
free(result);
|
172
|
+
return word;
|
173
|
+
}
|
174
|
+
|
175
|
+
|
176
|
+
/**
|
177
|
+
* Ctor for aspell objects:
|
178
|
+
* Aspell.new(language, jargon, size, encoding)
|
179
|
+
* Please note: All parameters are optional. If a parameter is omitted, a default value is assumed from
|
180
|
+
* the environment (eg lang from $LANG). To retain default values, you can use nil
|
181
|
+
* as value: to set only size: Aspell.new(nil, nil, "80")
|
182
|
+
* @param language ISO639 language code plus optional ISO 3166 counry code as string (eg: "de" or "us_US")
|
183
|
+
* @param jargon a special jargon of the selected language
|
184
|
+
* @param size the size of the dictionary to chose (if there are options)
|
185
|
+
* @param encoding the encoding to use
|
186
|
+
* @exception Exception if the specified dictionary is not found.
|
187
|
+
*/
|
188
|
+
static VALUE aspell_s_new(int argc, VALUE *argv, VALUE klass) {
|
189
|
+
VALUE vlang, vjargon, vsize, vencoding;
|
190
|
+
const char *tmp;
|
191
|
+
//aspell values
|
192
|
+
AspellCanHaveError * ret;
|
193
|
+
AspellSpeller * speller;
|
194
|
+
AspellConfig * config;
|
195
|
+
|
196
|
+
//create new config
|
197
|
+
config = new_aspell_config();
|
198
|
+
|
199
|
+
//extract values
|
200
|
+
rb_scan_args(argc, argv, "04", &vlang, &vjargon, &vsize, &vencoding);
|
201
|
+
|
202
|
+
//language:
|
203
|
+
if (RTEST(vlang)) set_option(config, "lang", STR2CSTR(vlang));
|
204
|
+
//jargon:
|
205
|
+
if (RTEST(vjargon)) set_option(config, "jargon", STR2CSTR(vjargon));
|
206
|
+
//size:
|
207
|
+
if (RTEST(vsize)) set_option(config, "size", STR2CSTR(vsize));
|
208
|
+
//encoding:
|
209
|
+
if (RTEST(vencoding)) set_option(config, "encoding", STR2CSTR(vencoding));
|
210
|
+
|
211
|
+
//create speller:
|
212
|
+
ret = new_aspell_speller(config);
|
213
|
+
delete_aspell_config(config);
|
214
|
+
if (aspell_error(ret) != 0) {
|
215
|
+
tmp = strdup(aspell_error_message(ret));
|
216
|
+
delete_aspell_can_have_error(ret);
|
217
|
+
rb_raise(cAspellError, tmp);
|
218
|
+
}
|
219
|
+
|
220
|
+
speller = to_aspell_speller(ret);
|
221
|
+
|
222
|
+
//wrap pointer
|
223
|
+
return Data_Wrap_Struct(klass, 0, aspell_free, speller);
|
224
|
+
}
|
225
|
+
|
226
|
+
|
227
|
+
|
228
|
+
/**
|
229
|
+
* Ctor for aspell objects.
|
230
|
+
* This is a custom constructor and takes a hash of config options: key, value pairs.
|
231
|
+
* Common use:
|
232
|
+
*
|
233
|
+
* a = Aspell.new({"lang"=>"de", "jargon"=>"berlin"})
|
234
|
+
*
|
235
|
+
* For a list of config options, see aspell manual.
|
236
|
+
* @param options hash of options
|
237
|
+
*/
|
238
|
+
static VALUE aspell_s_new1(VALUE klass, VALUE options) {
|
239
|
+
//aspell values
|
240
|
+
AspellCanHaveError * ret;
|
241
|
+
AspellSpeller * speller;
|
242
|
+
AspellConfig * config;
|
243
|
+
|
244
|
+
//create new config
|
245
|
+
config = new_aspell_config();
|
246
|
+
|
247
|
+
//set options
|
248
|
+
set_options(config, options);
|
249
|
+
|
250
|
+
//create speller:
|
251
|
+
ret = new_aspell_speller(config);
|
252
|
+
delete_aspell_config(config);
|
253
|
+
if (aspell_error(ret) != 0) {
|
254
|
+
const char *tmp = strdup(aspell_error_message(ret));
|
255
|
+
delete_aspell_can_have_error(ret);
|
256
|
+
rb_raise(cAspellError, tmp);
|
257
|
+
}
|
258
|
+
|
259
|
+
speller = to_aspell_speller(ret);
|
260
|
+
|
261
|
+
//wrap pointer
|
262
|
+
return Data_Wrap_Struct(klass, 0, aspell_free, speller);
|
263
|
+
}
|
264
|
+
|
265
|
+
/**
|
266
|
+
* List all available dictionaries.
|
267
|
+
* @param class object
|
268
|
+
* @return array of AspellDictInfo objects.
|
269
|
+
*/
|
270
|
+
static VALUE aspell_s_list_dicts(VALUE klass) {
|
271
|
+
AspellConfig * config;
|
272
|
+
AspellDictInfoList * dlist;
|
273
|
+
AspellDictInfoEnumeration * dels;
|
274
|
+
const AspellDictInfo * entry;
|
275
|
+
VALUE result = rb_ary_new();
|
276
|
+
|
277
|
+
//get a list of dictionaries
|
278
|
+
config = new_aspell_config();
|
279
|
+
dlist = get_aspell_dict_info_list(config);
|
280
|
+
delete_aspell_config(config);
|
281
|
+
|
282
|
+
//iterate over list - fill ruby array
|
283
|
+
dels = aspell_dict_info_list_elements(dlist);
|
284
|
+
while ( (entry = aspell_dict_info_enumeration_next(dels)) != 0) {
|
285
|
+
rb_ary_push(result, Data_Wrap_Struct(cDictInfo, 0, 0, (AspellDictInfo *)entry));
|
286
|
+
}
|
287
|
+
delete_aspell_dict_info_enumeration(dels);
|
288
|
+
return result;
|
289
|
+
}
|
290
|
+
|
291
|
+
/**
|
292
|
+
* @see set_option.
|
293
|
+
*/
|
294
|
+
static VALUE aspell_set_option(VALUE self, VALUE option, VALUE value) {
|
295
|
+
AspellSpeller *speller = get_speller(self);
|
296
|
+
set_option(aspell_speller_config(speller), STR2CSTR(option), STR2CSTR(value));
|
297
|
+
return self;
|
298
|
+
}
|
299
|
+
|
300
|
+
|
301
|
+
/**
|
302
|
+
* Delete an option.
|
303
|
+
* @param option optionstring to remove from the options.
|
304
|
+
*/
|
305
|
+
static VALUE aspell_remove_option(VALUE self, VALUE option) {
|
306
|
+
AspellSpeller *speller = get_speller(self);
|
307
|
+
aspell_config_remove(aspell_speller_config(speller), STR2CSTR(option));
|
308
|
+
return self;
|
309
|
+
}
|
310
|
+
|
311
|
+
/**
|
312
|
+
* To set the mode, words are suggested.
|
313
|
+
* @param one of Aspell::[ULTRA|FAST|NORMAL|BADSPELLERS]
|
314
|
+
*/
|
315
|
+
static VALUE aspell_set_suggestion_mode(VALUE self, VALUE value) {
|
316
|
+
AspellSpeller *speller = get_speller(self);
|
317
|
+
set_option(aspell_speller_config(speller), "sug-mode", STR2CSTR(value));
|
318
|
+
return self;
|
319
|
+
}
|
320
|
+
|
321
|
+
/**
|
322
|
+
* Returns the personal wordlist as array of strings.
|
323
|
+
* @return array of strings
|
324
|
+
*/
|
325
|
+
static VALUE aspell_personal_wordlist(VALUE self) {
|
326
|
+
AspellSpeller *speller = get_speller(self);
|
327
|
+
return get_list(aspell_speller_personal_word_list(speller));
|
328
|
+
}
|
329
|
+
|
330
|
+
/**
|
331
|
+
* Returns the session wordlist as array of strings.
|
332
|
+
* @return array of strings
|
333
|
+
*/
|
334
|
+
static VALUE aspell_session_wordlist(VALUE self) {
|
335
|
+
AspellSpeller *speller = get_speller(self);
|
336
|
+
return get_list(aspell_speller_session_word_list(speller));
|
337
|
+
}
|
338
|
+
|
339
|
+
/**
|
340
|
+
* Returns the main wordlist as array of strings.
|
341
|
+
* @return array of strings
|
342
|
+
*/
|
343
|
+
static VALUE aspell_main_wordlist(VALUE self) {
|
344
|
+
AspellSpeller *speller = get_speller(self);
|
345
|
+
return get_list(aspell_speller_main_word_list(speller));
|
346
|
+
}
|
347
|
+
|
348
|
+
/**
|
349
|
+
* Synchronize all wordlists with the current session.
|
350
|
+
*/
|
351
|
+
static VALUE aspell_save_all_wordlists(VALUE self) {
|
352
|
+
AspellSpeller *speller = get_speller(self);
|
353
|
+
aspell_speller_save_all_word_lists(speller);
|
354
|
+
check_for_error(speller);
|
355
|
+
return self;
|
356
|
+
}
|
357
|
+
|
358
|
+
/**
|
359
|
+
* Remove all words inside session.
|
360
|
+
*/
|
361
|
+
static VALUE aspell_clear_session(VALUE self) {
|
362
|
+
AspellSpeller *speller = get_speller(self);
|
363
|
+
aspell_speller_clear_session(speller);
|
364
|
+
check_for_error(speller);
|
365
|
+
return self;
|
366
|
+
}
|
367
|
+
|
368
|
+
/**
|
369
|
+
* Suggest words for the given misspelled word.
|
370
|
+
* @param word the misspelled word.
|
371
|
+
* @return array of strings.
|
372
|
+
*/
|
373
|
+
static VALUE aspell_suggest(VALUE self, VALUE word) {
|
374
|
+
AspellSpeller *speller = get_speller(self);
|
375
|
+
return get_list(aspell_speller_suggest(speller, STR2CSTR(word), -1));
|
376
|
+
}
|
377
|
+
|
378
|
+
/**
|
379
|
+
* Add a given word to the list of known words inside my private dictionary.
|
380
|
+
* You have to call aspell_save_all_wordlists to make sure the list gets persistent.
|
381
|
+
* @param word the word to add.
|
382
|
+
*/
|
383
|
+
static VALUE aspell_add_to_personal(VALUE self, VALUE word) {
|
384
|
+
AspellSpeller *speller = get_speller(self);
|
385
|
+
aspell_speller_add_to_personal(speller, STR2CSTR(word), -1);
|
386
|
+
check_for_error(speller);
|
387
|
+
return self;
|
388
|
+
}
|
389
|
+
|
390
|
+
/**
|
391
|
+
* Add a given word to the list of known words just for the lifetime of this object.
|
392
|
+
* @param word the word to add.
|
393
|
+
*/
|
394
|
+
static VALUE aspell_add_to_session(VALUE self, VALUE word) {
|
395
|
+
AspellSpeller *speller = get_speller(self);
|
396
|
+
aspell_speller_add_to_session(speller, STR2CSTR(word), -1);
|
397
|
+
check_for_error(speller);
|
398
|
+
return self;
|
399
|
+
}
|
400
|
+
|
401
|
+
/**
|
402
|
+
* Retrieve the value of a specific option.
|
403
|
+
* The options are listed inside
|
404
|
+
* Aspell::[DictionaryOptions|CheckerOptions|FilterOptions|RunTogetherOptions|MiscOptions|UtilityOptions]
|
405
|
+
* @param word the option as string.
|
406
|
+
*/
|
407
|
+
static VALUE aspell_conf_retrieve(VALUE self, VALUE key) {
|
408
|
+
AspellSpeller *speller = get_speller(self);
|
409
|
+
AspellConfig *config = aspell_speller_config(speller);
|
410
|
+
VALUE result = rb_str_new2(aspell_config_retrieve(config, STR2CSTR(key)));
|
411
|
+
if (aspell_config_error(config) != 0) {
|
412
|
+
rb_raise(cAspellError, aspell_config_error_message(config));
|
413
|
+
}
|
414
|
+
return result;
|
415
|
+
}
|
416
|
+
|
417
|
+
/**
|
418
|
+
* Retrieve the value of a specific option as list.
|
419
|
+
* @param word the option as string.
|
420
|
+
*/
|
421
|
+
static VALUE aspell_conf_retrieve_list(VALUE self, VALUE key) {
|
422
|
+
AspellSpeller *speller = get_speller(self);
|
423
|
+
AspellConfig *config = aspell_speller_config(speller);
|
424
|
+
AspellStringList * list = new_aspell_string_list();
|
425
|
+
AspellMutableContainer * container = aspell_string_list_to_mutable_container(list);
|
426
|
+
AspellStringEnumeration * els;
|
427
|
+
VALUE result = rb_ary_new();
|
428
|
+
const char *option_value;
|
429
|
+
|
430
|
+
//retrieve list
|
431
|
+
aspell_config_retrieve_list(config, STR2CSTR(key), container);
|
432
|
+
//check for error
|
433
|
+
if (aspell_config_error(config) != 0) {
|
434
|
+
char *tmp = strdup(aspell_config_error_message(config));
|
435
|
+
delete_aspell_string_list(list);
|
436
|
+
rb_raise( cAspellError, tmp);
|
437
|
+
}
|
438
|
+
|
439
|
+
//iterate over list
|
440
|
+
els = aspell_string_list_elements(list);
|
441
|
+
while ( (option_value = aspell_string_enumeration_next(els)) != 0) {
|
442
|
+
//push the option value to result
|
443
|
+
rb_ary_push(result, rb_str_new2(option_value));
|
444
|
+
}
|
445
|
+
//free list
|
446
|
+
delete_aspell_string_enumeration(els);
|
447
|
+
delete_aspell_string_list(list);
|
448
|
+
|
449
|
+
return result;
|
450
|
+
}
|
451
|
+
|
452
|
+
/**
|
453
|
+
* Simply dump config.
|
454
|
+
* Not very useful at all.
|
455
|
+
*/
|
456
|
+
static VALUE aspell_dump_config(VALUE self) {
|
457
|
+
AspellSpeller *speller = get_speller(self);
|
458
|
+
AspellConfig *config = aspell_speller_config(speller);
|
459
|
+
AspellKeyInfoEnumeration * key_list = aspell_config_possible_elements( config, 0 );
|
460
|
+
const AspellKeyInfo * entry;
|
461
|
+
|
462
|
+
while ( (entry = aspell_key_info_enumeration_next(key_list) ) ) {
|
463
|
+
printf("%20s: %s\n", entry->name, aspell_config_retrieve(config, entry->name) );
|
464
|
+
}
|
465
|
+
delete_aspell_key_info_enumeration(key_list);
|
466
|
+
return self;
|
467
|
+
}
|
468
|
+
|
469
|
+
/**
|
470
|
+
* Check a given word for correctness.
|
471
|
+
* @param word the word to check
|
472
|
+
* @return true if the word is correct, otherwise false.
|
473
|
+
*/
|
474
|
+
static VALUE aspell_check(VALUE self, VALUE word) {
|
475
|
+
AspellSpeller *speller = get_speller(self);
|
476
|
+
VALUE result = Qfalse;
|
477
|
+
int code = aspell_speller_check(speller, STR2CSTR(word), -1);
|
478
|
+
if (code == 1)
|
479
|
+
result = Qtrue;
|
480
|
+
else if (code == 0)
|
481
|
+
result = Qfalse;
|
482
|
+
else
|
483
|
+
rb_raise( cAspellError, aspell_speller_error_message(speller));
|
484
|
+
return result;
|
485
|
+
}
|
486
|
+
|
487
|
+
/**
|
488
|
+
* This method will check an array of strings for misspelled words.
|
489
|
+
* This method needs a block to work proper. Each misspelled word is yielded,
|
490
|
+
* a correct word as result from the block is assumed.
|
491
|
+
* Common use:
|
492
|
+
*
|
493
|
+
* a = Aspell.new(...)
|
494
|
+
* text = ...
|
495
|
+
* a.correct_lines(text) { |badword|
|
496
|
+
* puts "Error: #{badword}\n"
|
497
|
+
* puts a.suggest(badword).join(" | ")
|
498
|
+
* gets #the input is returned as right word
|
499
|
+
* }
|
500
|
+
*
|
501
|
+
* @param ary the array of strings to check.
|
502
|
+
* @result an array holding all lines with corrected words.
|
503
|
+
*/
|
504
|
+
static VALUE aspell_correct_lines(VALUE self, VALUE ary) {
|
505
|
+
VALUE result = ary;
|
506
|
+
if (rb_block_given_p()) {
|
507
|
+
//create checker
|
508
|
+
AspellSpeller *speller = get_speller(self);
|
509
|
+
AspellDocumentChecker * checker = get_checker(speller);
|
510
|
+
AspellToken token;
|
511
|
+
//some tmp values
|
512
|
+
VALUE vline, sline;
|
513
|
+
VALUE word, rword;
|
514
|
+
char *line;
|
515
|
+
int count=RARRAY_LEN(ary);
|
516
|
+
int c=0;
|
517
|
+
//create new result array
|
518
|
+
result = rb_ary_new();
|
519
|
+
//iterate over array
|
520
|
+
while(c<count) {
|
521
|
+
int offset=0;
|
522
|
+
//fetch line
|
523
|
+
vline = RARRAY_PTR(ary)[c];
|
524
|
+
//save line
|
525
|
+
sline = rb_funcall(vline, rb_intern("dup"), 0);
|
526
|
+
//c representation
|
527
|
+
line = STR2CSTR(vline);
|
528
|
+
//process line
|
529
|
+
aspell_document_checker_process(checker, line, -1);
|
530
|
+
//iterate over all misspelled words
|
531
|
+
while (token = aspell_document_checker_next_misspelling(checker), token.len != 0) {
|
532
|
+
//extract word by start/length qualifier
|
533
|
+
word = rb_funcall(vline, rb_intern("[]"), 2, INT2FIX(token.offset), INT2FIX(token.len));
|
534
|
+
//get the right word from the block
|
535
|
+
rword = rb_yield(word);
|
536
|
+
//nil -> do nothing
|
537
|
+
if(rword == Qnil) continue;
|
538
|
+
//check for string
|
539
|
+
if (TYPE(rword) != T_STRING) rb_raise(cAspellError, "Need a String to substitute");
|
540
|
+
//chomp the string
|
541
|
+
rb_funcall(rword, rb_intern("chomp!"), 0);
|
542
|
+
//empty string -> do nothing
|
543
|
+
if(strlen(STR2CSTR(rword)) == 0) continue;
|
544
|
+
//remember word for later suggestion
|
545
|
+
aspell_speller_store_replacement(speller, STR2CSTR(word), -1, STR2CSTR(rword), -1);
|
546
|
+
//substitute the word by replacement
|
547
|
+
rb_funcall(sline, rb_intern("[]="), 3, INT2FIX(token.offset+offset), INT2FIX(token.len), rword);
|
548
|
+
//adjust offset
|
549
|
+
offset += strlen(STR2CSTR(rword))-strlen(STR2CSTR(word));
|
550
|
+
//printf("replace >%s< with >%s< (offset now %d)\n", STR2CSTR(word), STR2CSTR(rword), offset);
|
551
|
+
}
|
552
|
+
//push the substituted line to result
|
553
|
+
rb_ary_push(result, sline);
|
554
|
+
c++;
|
555
|
+
}
|
556
|
+
//free checker
|
557
|
+
delete_aspell_document_checker(checker);
|
558
|
+
} else {
|
559
|
+
rb_raise(cAspellError, "No block given. How to correct?");
|
560
|
+
}
|
561
|
+
return result;
|
562
|
+
}
|
563
|
+
|
564
|
+
/**
|
565
|
+
* Remember a correction.
|
566
|
+
* This affects the suggestion of other words to fit this correction.
|
567
|
+
* @param badword the bad spelled word as string.
|
568
|
+
* @param badword the correction of the bad spelled word as string.
|
569
|
+
* @result self
|
570
|
+
*/
|
571
|
+
static VALUE aspell_store_replacement(VALUE self, VALUE badword, VALUE rightword) {
|
572
|
+
AspellSpeller *speller = get_speller(self);
|
573
|
+
aspell_speller_store_replacement(speller, STR2CSTR(badword), -1, STR2CSTR(rightword), -1);
|
574
|
+
return self;
|
575
|
+
}
|
576
|
+
|
577
|
+
/**
|
578
|
+
* Simple utility function to correct a file.
|
579
|
+
* The file gets read, content will be checked and write back.
|
580
|
+
* Please note: This method will change the file! - no backup and of course: no warranty!
|
581
|
+
* @param filename the name of the file as String.
|
582
|
+
* @exception Exception due to lack of read/write permissions.
|
583
|
+
*/
|
584
|
+
static VALUE aspell_correct_file(VALUE self, VALUE filename) {
|
585
|
+
if (rb_block_given_p()) {
|
586
|
+
VALUE content = rb_funcall(rb_cFile, rb_intern("readlines"), 1, filename);
|
587
|
+
VALUE newcontent = aspell_correct_lines(self, content);
|
588
|
+
VALUE file = rb_file_open(STR2CSTR(filename), "w+");
|
589
|
+
rb_funcall(file, rb_intern("write"), 1, newcontent);
|
590
|
+
rb_funcall(file, rb_intern("close"), 0);
|
591
|
+
} else {
|
592
|
+
rb_raise(cAspellError, "No block given. How to correct?");
|
593
|
+
}
|
594
|
+
return self;
|
595
|
+
|
596
|
+
}
|
597
|
+
|
598
|
+
/**
|
599
|
+
* Return a list of all misspelled words inside a given array of strings.
|
600
|
+
* @param ary an array of strings to check for.
|
601
|
+
* @return array of strings: words that are misspelled.
|
602
|
+
*/
|
603
|
+
static VALUE aspell_list_misspelled(VALUE self, VALUE ary) {
|
604
|
+
VALUE result = rb_hash_new();
|
605
|
+
//create checker
|
606
|
+
AspellSpeller *speller = get_speller(self);
|
607
|
+
AspellDocumentChecker * checker = get_checker(speller);
|
608
|
+
AspellToken token;
|
609
|
+
VALUE word, vline;
|
610
|
+
int count=RARRAY_LEN(ary);
|
611
|
+
int c=0;
|
612
|
+
//iterate over array
|
613
|
+
while(c<count) {
|
614
|
+
//process line
|
615
|
+
vline = RARRAY_PTR(ary)[c];
|
616
|
+
aspell_document_checker_process(checker, STR2CSTR(vline), -1);
|
617
|
+
//iterate over all misspelled words
|
618
|
+
while (token = aspell_document_checker_next_misspelling(checker), token.len != 0) {
|
619
|
+
//extract word by start/length qualifier
|
620
|
+
word = rb_funcall(vline, rb_intern("[]"), 2, INT2FIX(token.offset), INT2FIX(token.len));
|
621
|
+
rb_hash_aset(result, word, Qnil);
|
622
|
+
//yield block, if given
|
623
|
+
if (rb_block_given_p())
|
624
|
+
rb_yield(word);
|
625
|
+
}
|
626
|
+
c++;
|
627
|
+
}
|
628
|
+
//free checker
|
629
|
+
delete_aspell_document_checker(checker);
|
630
|
+
result = rb_funcall(result, rb_intern("keys"), 0);
|
631
|
+
return result;
|
632
|
+
}
|
633
|
+
|
634
|
+
void Init_aspell() {
|
635
|
+
//CLASS DEFINITION=========================================================
|
636
|
+
cAspell = rb_define_class("Aspell", rb_cObject);
|
637
|
+
|
638
|
+
//CONSTANTS================================================================
|
639
|
+
rb_define_const(cAspell, "ULTRA", rb_str_new2("ultra"));
|
640
|
+
rb_define_const(cAspell, "FAST", rb_str_new2("fast"));
|
641
|
+
rb_define_const(cAspell, "NORMAL", rb_str_new2("normal"));
|
642
|
+
rb_define_const(cAspell, "BADSPELLERS", rb_str_new2("bad-spellers"));
|
643
|
+
rb_define_const(cAspell, "DictionaryOptions", rb_ary_new3( 11,
|
644
|
+
rb_str_new2("master"),
|
645
|
+
rb_str_new2("dict-dir"),
|
646
|
+
rb_str_new2("lang"),
|
647
|
+
rb_str_new2("size"),
|
648
|
+
rb_str_new2("jargon"),
|
649
|
+
rb_str_new2("word-list-path"),
|
650
|
+
rb_str_new2("module-search-order"),
|
651
|
+
rb_str_new2("personal"),
|
652
|
+
rb_str_new2("repl"),
|
653
|
+
rb_str_new2("extra-dicts"),
|
654
|
+
rb_str_new2("strip-accents")));
|
655
|
+
rb_define_const(cAspell, "CheckerOptions", rb_ary_new3( 11,
|
656
|
+
rb_str_new2("ignore"),
|
657
|
+
rb_str_new2("ignore-case"),
|
658
|
+
rb_str_new2("ignore-accents"),
|
659
|
+
rb_str_new2("ignore-repl"),
|
660
|
+
rb_str_new2("save-repl"),
|
661
|
+
rb_str_new2("sug-mode"),
|
662
|
+
rb_str_new2("module-search-order"),
|
663
|
+
rb_str_new2("personal"),
|
664
|
+
rb_str_new2("repl"),
|
665
|
+
rb_str_new2("extra-dicts"),
|
666
|
+
rb_str_new2("strip-accents")));
|
667
|
+
rb_define_const(cAspell, "FilterOptions", rb_ary_new3( 10,
|
668
|
+
rb_str_new2("filter"),
|
669
|
+
rb_str_new2("mode"),
|
670
|
+
rb_str_new2("encoding"),
|
671
|
+
rb_str_new2("add-email-quote"),
|
672
|
+
rb_str_new2("rem-email-quote"),
|
673
|
+
rb_str_new2("email-margin"),
|
674
|
+
rb_str_new2("sgml-check"),
|
675
|
+
rb_str_new2("sgml-extension"),
|
676
|
+
rb_str_new2("tex-command"),
|
677
|
+
rb_str_new2("tex-check-command")));
|
678
|
+
rb_define_const(cAspell, "RunTogetherOptions", rb_ary_new3( 3,
|
679
|
+
rb_str_new2("run-together"),
|
680
|
+
rb_str_new2("run-together-limit"),
|
681
|
+
rb_str_new2("run-together-min")));
|
682
|
+
rb_define_const(cAspell, "MiscOptions", rb_ary_new3( 8,
|
683
|
+
rb_str_new2("conf"),
|
684
|
+
rb_str_new2("conf-dir"),
|
685
|
+
rb_str_new2("data-dir"),
|
686
|
+
rb_str_new2("local-data-dir"),
|
687
|
+
rb_str_new2("home-dir"),
|
688
|
+
rb_str_new2("per-conf"),
|
689
|
+
rb_str_new2("prefix"),
|
690
|
+
rb_str_new2("set-prefix")));
|
691
|
+
|
692
|
+
rb_define_const(cAspell, "UtilityOptions", rb_ary_new3( 4,
|
693
|
+
rb_str_new2("backup"),
|
694
|
+
rb_str_new2("time"),
|
695
|
+
rb_str_new2("reverse"),
|
696
|
+
rb_str_new2("keymapping")));
|
697
|
+
|
698
|
+
//CLASS METHODS============================================================
|
699
|
+
rb_define_singleton_method(cAspell, "new", aspell_s_new, -1);
|
700
|
+
rb_define_singleton_method(cAspell, "new1", aspell_s_new1, 1);
|
701
|
+
rb_define_singleton_method(cAspell, "list_dicts", aspell_s_list_dicts, 0);
|
702
|
+
|
703
|
+
//METHODS =================================================================
|
704
|
+
rb_define_method(cAspell, "add_to_personal", aspell_add_to_personal, 1);
|
705
|
+
rb_define_method(cAspell, "add_to_session", aspell_add_to_personal, 1);
|
706
|
+
rb_define_method(cAspell, "check", aspell_check, 1);
|
707
|
+
rb_define_method(cAspell, "correct_lines", aspell_correct_lines, 1);
|
708
|
+
rb_define_method(cAspell, "correct_file", aspell_correct_file, 1);
|
709
|
+
rb_define_method(cAspell, "clear_session", aspell_clear_session, 0);
|
710
|
+
rb_define_method(cAspell, "dump_config", aspell_dump_config, 0);
|
711
|
+
rb_define_method(cAspell, "list_misspelled", aspell_list_misspelled, 1);
|
712
|
+
//This seems not to be very useful ...
|
713
|
+
//rb_define_method(cAspell, "main_wordlist", aspell_main_wordlist, 0);
|
714
|
+
rb_define_method(cAspell, "personal_wordlist", aspell_personal_wordlist, 0);
|
715
|
+
rb_define_method(cAspell, "save_all_word_lists", aspell_save_all_wordlists, 0);
|
716
|
+
rb_define_method(cAspell, "session_wordlist", aspell_session_wordlist, 0);
|
717
|
+
rb_define_method(cAspell, "set_option", aspell_set_option, 2);
|
718
|
+
rb_define_method(cAspell, "store_replacement", aspell_store_replacement, 2);
|
719
|
+
rb_define_method(cAspell, "remove_option", aspell_remove_option, 1);
|
720
|
+
rb_define_method(cAspell, "get_option", aspell_conf_retrieve, 1);
|
721
|
+
rb_define_method(cAspell, "get_option_as_list", aspell_conf_retrieve_list, 1);
|
722
|
+
rb_define_method(cAspell, "suggest", aspell_suggest, 1);
|
723
|
+
rb_define_method(cAspell, "suggestion_mode=", aspell_set_suggestion_mode, 1);
|
724
|
+
}
|
725
|
+
|
726
|
+
|