summaryrefslogtreecommitdiff
path: root/ext/standard/metaphone.c
blob: 62c6df64aacfb976d27b9c01c90ef05e7c0ee927 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
/*
   +----------------------------------------------------------------------+
   | PHP Version 5                                                        |
   +----------------------------------------------------------------------+
   | Copyright (c) 1997-2013 The PHP Group                                |
   +----------------------------------------------------------------------+
   | This source file is subject to version 3.01 of the PHP license,      |
   | that is bundled with this package in the file LICENSE, and is        |
   | available through the world-wide-web at the following url:           |
   | http://www.php.net/license/3_01.txt                                  |
   | If you did not receive a copy of the PHP license and are unable to   |
   | obtain it through the world-wide-web, please send a note to          |
   | license@php.net so we can mail you a copy immediately.               |
   +----------------------------------------------------------------------+
   | Author: Thies C. Arntzen <thies@thieso.net>                          |
   +----------------------------------------------------------------------+
*/

/* $Id$ */

/*
	Based on CPANs "Text-Metaphone-1.96" by Michael G Schwern <schwern@pobox.com> 
*/

#include "php.h"
#include "php_metaphone.h"

static int metaphone(unsigned char *word, int word_len, long max_phonemes, char **phoned_word, int traditional);

/* {{{ proto string metaphone(string text[, int phones])
   Break english phrases down into their phonemes */
PHP_FUNCTION(metaphone)
{
	char *str;
	char *result = 0;
	int str_len;
	long phones = 0;

	if (zend_parse_parameters(ZEND_NUM_ARGS() TSRMLS_CC, "s|l", &str, &str_len,
							  &phones) == FAILURE) {
		return;
	}

	if (metaphone((unsigned char *)str, str_len, phones, &result, 1) == 0) {
		RETVAL_STRING(result, 0);
	} else {
		if (result) {
			efree(result);
		}
		RETURN_FALSE;
	}
}
/* }}} */

/* 
   this is now the original code by Michael G Schwern:
   i've changed it just a slightly bit (use emalloc, 
   get rid of includes etc) 
	- thies - 13.09.1999
*/

/*-----------------------------  */
/* this used to be "metaphone.h" */
/*-----------------------------  */

/* Special encodings */
#define  SH 	'X'
#define  TH		'0'

/*-----------------------------  */
/* end of "metaphone.h"          */
/*-----------------------------  */

/*----------------------------- */
/* this used to be "metachar.h" */
/*----------------------------- */

/* Metachar.h ... little bits about characters for metaphone */
/*-- Character encoding array & accessing macros --*/
/* Stolen directly out of the book... */
char _codes[26] =
{
	1, 16, 4, 16, 9, 2, 4, 16, 9, 2, 0, 2, 2, 2, 1, 4, 0, 2, 4, 4, 1, 0, 0, 0, 8, 0
/*  a  b c  d e f g  h i j k l m n o p q r s t u v w x y z */
};


#define ENCODE(c) (isalpha(c) ? _codes[((toupper(c)) - 'A')] : 0)

#define isvowel(c)  (ENCODE(c) & 1)		/* AEIOU */

/* These letters are passed through unchanged */
#define NOCHANGE(c) (ENCODE(c) & 2)		/* FJMNR */

/* These form dipthongs when preceding H */
#define AFFECTH(c)  (ENCODE(c) & 4)		/* CGPST */

/* These make C and G soft */
#define MAKESOFT(c) (ENCODE(c) & 8)		/* EIY */

/* These prevent GH from becoming F */
#define NOGHTOF(c)  (ENCODE(c) & 16)	/* BDH */

/*----------------------------- */
/* end of "metachar.h"          */
/*----------------------------- */

/* I suppose I could have been using a character pointer instead of
 * accesssing the array directly... */

/* Look at the next letter in the word */
#define Next_Letter (toupper(word[w_idx+1]))
/* Look at the current letter in the word */
#define Curr_Letter (toupper(word[w_idx]))
/* Go N letters back. */
#define Look_Back_Letter(n)	(w_idx >= n ? toupper(word[w_idx-n]) : '\0')
/* Previous letter.  I dunno, should this return null on failure? */
#define Prev_Letter (Look_Back_Letter(1))
/* Look two letters down.  It makes sure you don't walk off the string. */
#define After_Next_Letter	(Next_Letter != '\0' ? toupper(word[w_idx+2]) \
											     : '\0')
#define Look_Ahead_Letter(n) (toupper(Lookahead(word+w_idx, n)))


/* Allows us to safely look ahead an arbitrary # of letters */
/* I probably could have just used strlen... */
static char Lookahead(char *word, int how_far)
{
	char letter_ahead = '\0';	/* null by default */
	int idx;
	for (idx = 0; word[idx] != '\0' && idx < how_far; idx++);
	/* Edge forward in the string... */

	letter_ahead = word[idx];	/* idx will be either == to how_far or
								 * at the end of the string
								 */
	return letter_ahead;
}


/* phonize one letter
 * We don't know the buffers size in advance. On way to solve this is to just
 * re-allocate the buffer size. We're using an extra of 2 characters (this
 * could be one though; or more too). */
#define Phonize(c)	{ \
						if (p_idx >= max_buffer_len) { \
							*phoned_word = safe_erealloc(*phoned_word, 2, sizeof(char), max_buffer_len); \
							max_buffer_len += 2; \
						} \
						(*phoned_word)[p_idx++] = c; \
					}
/* Slap a null character on the end of the phoned word */
#define End_Phoned_Word	{ \
							if (p_idx == max_buffer_len) { \
								*phoned_word = safe_erealloc(*phoned_word, 1, sizeof(char), max_buffer_len); \
							} \
							(*phoned_word)[p_idx] = '\0'; \
						}
/* How long is the phoned word? */
#define Phone_Len	(p_idx)

/* Note is a letter is a 'break' in the word */
#define Isbreak(c)  (!isalpha(c))

/* {{{ metaphone
 */
static int metaphone(unsigned char *word, int word_len, long max_phonemes, char **phoned_word, int traditional)
{
	int w_idx = 0;				/* point in the phonization we're at. */
	int p_idx = 0;				/* end of the phoned phrase */
	int max_buffer_len = 0;		/* maximum length of the destination buffer */

/*-- Parameter checks --*/
	/* Negative phoneme length is meaningless */

	if (max_phonemes < 0)
		return -1;

	/* Empty/null string is meaningless */
	/* Overly paranoid */
	/* assert(word != NULL && word[0] != '\0'); */

	if (word == NULL)
		return -1;

/*-- Allocate memory for our phoned_phrase --*/
	if (max_phonemes == 0) {	/* Assume largest possible */
		max_buffer_len = word_len;
		*phoned_word = safe_emalloc(sizeof(char), word_len, 1);
	} else {
		max_buffer_len = max_phonemes;
		*phoned_word = safe_emalloc(sizeof(char), max_phonemes, 1);
	}


/*-- The first phoneme has to be processed specially. --*/
	/* Find our first letter */
	for (; !isalpha(Curr_Letter); w_idx++) {
		/* On the off chance we were given nothing but crap... */
		if (Curr_Letter == '\0') {
			End_Phoned_Word
				return SUCCESS;	/* For testing */
		}
	}

	switch (Curr_Letter) {
		/* AE becomes E */
	case 'A':
		if (Next_Letter == 'E') {
			Phonize('E');
			w_idx += 2;
		}
		/* Remember, preserve vowels at the beginning */
		else {
			Phonize('A');
			w_idx++;
		}
		break;
		/* [GKP]N becomes N */
	case 'G':
	case 'K':
	case 'P':
		if (Next_Letter == 'N') {
			Phonize('N');
			w_idx += 2;
		}
		break;
		/* WH becomes W, 
		   WR becomes R 
		   W if followed by a vowel */
	case 'W':
		if (Next_Letter == 'R') {
			Phonize(Next_Letter);
			w_idx += 2;
		} else if (Next_Letter == 'H' || isvowel(Next_Letter)) {
			Phonize('W');
			w_idx += 2;
		}
		/* else ignore */
		break;
		/* X becomes S */
	case 'X':
		Phonize('S');
		w_idx++;
		break;
		/* Vowels are kept */
		/* We did A already
		   case 'A':
		   case 'a':
		 */
	case 'E':
	case 'I':
	case 'O':
	case 'U':
		Phonize(Curr_Letter);
		w_idx++;
		break;
	default:
		/* do nothing */
		break;
	}



	/* On to the metaphoning */
	for (; Curr_Letter != '\0' &&
		 (max_phonemes == 0 || Phone_Len < max_phonemes);
		 w_idx++) {
		/* How many letters to skip because an eariler encoding handled     
		 * multiple letters */
		unsigned short int skip_letter = 0;


		/* THOUGHT:  It would be nice if, rather than having things like...
		 * well, SCI.  For SCI you encode the S, then have to remember
		 * to skip the C.  So the phonome SCI invades both S and C.  It would
		 * be better, IMHO, to skip the C from the S part of the encoding.
		 * Hell, I'm trying it.
		 */

		/* Ignore non-alphas */
		if (!isalpha(Curr_Letter))
			continue;

		/* Drop duplicates, except CC */
		if (Curr_Letter == Prev_Letter &&
			Curr_Letter != 'C')
			continue;

		switch (Curr_Letter) {
			/* B -> B unless in MB */
		case 'B':
			if (Prev_Letter != 'M')
				Phonize('B');
			break;
			/* 'sh' if -CIA- or -CH, but not SCH, except SCHW.
			 * (SCHW is handled in S)
			 *  S if -CI-, -CE- or -CY-
			 *  dropped if -SCI-, SCE-, -SCY- (handed in S)
			 *  else K
			 */
		case 'C':
			if (MAKESOFT(Next_Letter)) {	/* C[IEY] */
				if (After_Next_Letter == 'A' &&
					Next_Letter == 'I') {	/* CIA */
					Phonize(SH);
				}
				/* SC[IEY] */
				else if (Prev_Letter == 'S') {
					/* Dropped */
				} else {
					Phonize('S');
				}
			} else if (Next_Letter == 'H') {
				if ((!traditional) && (After_Next_Letter == 'R' || Prev_Letter == 'S')) {	/* Christ, School */
					Phonize('K');
				} else {
					Phonize(SH);
				}
				skip_letter++;
			} else {
				Phonize('K');
			}
			break;
			/* J if in -DGE-, -DGI- or -DGY-
			 * else T
			 */
		case 'D':
			if (Next_Letter == 'G' &&
				MAKESOFT(After_Next_Letter)) {
				Phonize('J');
				skip_letter++;
			} else
				Phonize('T');
			break;
			/* F if in -GH and not B--GH, D--GH, -H--GH, -H---GH
			 * else dropped if -GNED, -GN, 
			 * else dropped if -DGE-, -DGI- or -DGY- (handled in D)
			 * else J if in -GE-, -GI, -GY and not GG
			 * else K
			 */
		case 'G':
			if (Next_Letter == 'H') {
				if (!(NOGHTOF(Look_Back_Letter(3)) ||
					  Look_Back_Letter(4) == 'H')) {
					Phonize('F');
					skip_letter++;
				} else {
					/* silent */
				}
			} else if (Next_Letter == 'N') {
				if (Isbreak(After_Next_Letter) ||
					(After_Next_Letter == 'E' &&
					 Look_Ahead_Letter(3) == 'D')) {
					/* dropped */
				} else
					Phonize('K');
			} else if (MAKESOFT(Next_Letter) &&
					   Prev_Letter != 'G') {
				Phonize('J');
			} else {
				Phonize('K');
			}
			break;
			/* H if before a vowel and not after C,G,P,S,T */
		case 'H':
			if (isvowel(Next_Letter) &&
				!AFFECTH(Prev_Letter))
				Phonize('H');
			break;
			/* dropped if after C
			 * else K
			 */
		case 'K':
			if (Prev_Letter != 'C')
				Phonize('K');
			break;
			/* F if before H
			 * else P
			 */
		case 'P':
			if (Next_Letter == 'H') {
				Phonize('F');
			} else {
				Phonize('P');
			}
			break;
			/* K
			 */
		case 'Q':
			Phonize('K');
			break;
			/* 'sh' in -SH-, -SIO- or -SIA- or -SCHW-
			 * else S
			 */
		case 'S':
			if (Next_Letter == 'I' &&
				(After_Next_Letter == 'O' ||
				 After_Next_Letter == 'A')) {
				Phonize(SH);
			} else if (Next_Letter == 'H') {
				Phonize(SH);
				skip_letter++;
			} else if ((!traditional) && (Next_Letter == 'C' && Look_Ahead_Letter(2) == 'H' && Look_Ahead_Letter(3) == 'W')) {
				Phonize(SH);
				skip_letter += 2;
			} else {
				Phonize('S');
			}
			break;
			/* 'sh' in -TIA- or -TIO-
			 * else 'th' before H
			 * else T
			 */
		case 'T':
			if (Next_Letter == 'I' &&
				(After_Next_Letter == 'O' ||
				 After_Next_Letter == 'A')) {
				Phonize(SH);
			} else if (Next_Letter == 'H') {
				Phonize(TH);
				skip_letter++;
			} else if (!(Next_Letter == 'C' && After_Next_Letter == 'H')) {
				Phonize('T');
			}
			break;
			/* F */
		case 'V':
			Phonize('F');
			break;
			/* W before a vowel, else dropped */
		case 'W':
			if (isvowel(Next_Letter))
				Phonize('W');
			break;
			/* KS */
		case 'X':
			Phonize('K');
			Phonize('S');
			break;
			/* Y if followed by a vowel */
		case 'Y':
			if (isvowel(Next_Letter))
				Phonize('Y');
			break;
			/* S */
		case 'Z':
			Phonize('S');
			break;
			/* No transformation */
		case 'F':
		case 'J':
		case 'L':
		case 'M':
		case 'N':
		case 'R':
			Phonize(Curr_Letter);
			break;
		default:
			/* nothing */
			break;
		}						/* END SWITCH */

		w_idx += skip_letter;
	}							/* END FOR */

	End_Phoned_Word;

	return 0;
}								/* END metaphone */
/* }}} */

/*
 * Local variables:
 * tab-width: 4
 * c-basic-offset: 4
 * End:
 * vim600: sw=4 ts=4 fdm=marker
 * vim<600: sw=4 ts=4
 */