File: word_util.c

package info (click to toggle)
swish++ 6.1.5-2
  • links: PTS
  • area: main
  • in suites: squeeze
  • size: 2,256 kB
  • ctags: 1,759
  • sloc: ansic: 11,931; lisp: 804; sh: 629; perl: 366; makefile: 80
file content (293 lines) | stat: -rw-r--r-- 6,867 bytes parent folder | download | duplicates (6)
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
/*
**	SWISH++
**	word_util.c
**
**	Copyright (C) 1998  Paul J. Lucas
**
**	This program is free software; you can redistribute it and/or modify
**	it under the terms of the GNU General Public License as published by
**	the Free Software Foundation; either version 2 of the License, or
**	(at your option) any later version.
**
**	This program is distributed in the hope that it will be useful,
**	but WITHOUT ANY WARRANTY; without even the implied warranty of
**	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
**	GNU General Public License for more details.
**
**	You should have received a copy of the GNU General Public License
**	along with this program; if not, write to the Free Software
**	Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
*/

// standard
#include <cctype>
#ifdef DEBUG_is_ok_word
#include <iostream>
#endif

// local
#include "config.h"
#include "platform.h"
#include "word_util.h"

using namespace std;

//*****************************************************************************
//
// SYNOPSIS
//
	bool is_ok_word( char const *word )
//
// DESCRIPTION
//
//	Determine whether a given word should be indexed or not using several
//	heuristics.
//
//	First, a word is checked to see if it looks like an acronym.  A word is
//	considered an acronym only if it starts with a capital letter and is
//	composed exclusively of capital letters, digits, and punctuation
//	symbols, e.g., "AT&T."  If a word looks like an acronym, it is OK and
//	no further checks are done.
//
//	Second, there are several other checks that are applied.  A word is not
//	indexed if it:
//
//	1. Is less that Word_Min_Size characters and is not an acronym.
//
//	2. Contains less than Word_Min_Vowels.
//
//	3. Contains more than Word_Max_Consec_Same of the same character
//	   consecutively (not including digits).
//
//	4. Contains more than Word_Max_Consec_Consonants consecutive
//	   consonants.
//
//	5. Contains more than Word_Max_Consec_Vowels consecutive vowels.
//
//	6. Contains more than Word_Max_Consec_Puncts consecutive punctuation
//	   characters.
//
// PARAMETERS
//
//	word	The word to be checked.
//
// RETURN VALUE
//
//	Returns true only if the word should be indexed.
//
// EXAMPLES
//
//	AT&T	OK
//	cccp	not OK -- no vowels
//	CCCP	OK -- acronym
//	eieio	not OK -- too many consec. vowels
//
//*****************************************************************************
{
	register char const *c;

#	ifdef DEBUG_is_ok_word
	cerr << '\t' << word << ' ';
#	endif

	////////// Survey the characters in the word //////////////////////////

	int digits = 0;
	int puncts = 0;
	int uppers = 0;
	int vowels = 0;
	for ( c = word; *c; ++c ) {
		if ( is_digit( *c ) ) {
			++digits;
			continue;
		};
		if ( is_punct( *c ) ) {
			++puncts;
			continue;
		}
		if ( is_upper( *c ) )
			++uppers;
		if ( is_vowel( tolower( *c ) ) )
			++vowels;
	}
	int const len = c - word;

	if ( is_upper( *word ) && uppers + digits + puncts == len ) {
#		ifdef DEBUG_is_ok_word
		cerr << "(potential acronym)\n";
#		endif
		return true;
	}

	if ( len < Word_Min_Size ) {
#		ifdef DEBUG_is_ok_word
		cerr << "(len < Word_Min_Size)\n";
#		endif
		return false;
	}

	if ( vowels < Word_Min_Vowels ) {
#		ifdef DEBUG_is_ok_word
		cerr << "(vowels < Word_Min_Vowels)\n";
#		endif
		return false;
	}

	////////// Perform consecutive-character checks ///////////////////////

	int consec_consonants = 0;
	int consec_vowels = 0;
	int consec_same = 0;
	int consec_puncts = 0;
	register char last_c = '\0';

	for ( c = word; *c; ++c ) {

		if ( is_digit( *c ) ) {
			consec_consonants = 0;
			consec_vowels = 0;
			consec_puncts = 0;
			last_c = '\0';	// consec_same doesn't apply to digits
			continue;
		}

		if ( is_punct( *c ) ) {
			if ( ++consec_puncts > Word_Max_Consec_Puncts ) {
#				ifdef DEBUG_is_ok_word
				cerr << "(exceeded consec puncts)\n";
#				endif
				return false;
			}
			consec_consonants = 0;
			consec_vowels = 0;
			continue;
		}

		if ( *c == last_c ) {
			if ( ++consec_same > Word_Max_Consec_Same ) {
#				ifdef DEBUG_is_ok_word
				cerr << "(exceeded consec same)\n";
#				endif
				return false;
			}
		} else {
			consec_same = 0;
			last_c = *c;
		}

		if ( is_vowel( tolower( *c ) ) ) {
			if ( ++consec_vowels > Word_Max_Consec_Vowels ) {
#				ifdef DEBUG_is_ok_word
				cerr << "(exceeded consec vowels)\n";
#				endif
				return false;
			}
			consec_consonants = 0;
			consec_puncts = 0;
			continue;
		}

		if ( ++consec_consonants > Word_Max_Consec_Consonants ) {
#			ifdef DEBUG_is_ok_word
			cerr << "(exceeded consec consonants)\n";
#			endif
			return false;
		}
		consec_vowels = 0;
		consec_puncts = 0;
	}

#	ifdef DEBUG_is_ok_word
	cerr << "\n";
#	endif
	return true;
}

//*****************************************************************************
//
// SYNOPSIS
//
	bool move_if_match(
		char const *&c, char const *end, char const *s,
		bool ignore_case
	)
//
// SYNOPSIS
//
//	Compares a string starting at the given iterator to another.
//
// PARAMETERS
//
//	c		The iterator to use.  If the string matches, it is
//			repositioned at the first character past the string;
//			otherwise it is not touched.
//
//	end		The iterator marking the end of the range to search.
//
//	s		The string to compare against.  If ignore_case is true,
//			then this string must be in lower case.
//
//	ignore_case	True if case should be ignored.
//
// RETURN VALUE
//
//	Returns true only if the string matches.
//
//*****************************************************************************
{
	register char const *d = c;
	if ( ignore_case )
		while ( *s && d != end && *s == to_lower( *d ) )
			++s, ++d;
	else
		while ( *s && d != end && *s == *d )
			++s, ++d;
	if ( *s )			// didn't match before null
		return false;
	c = d;
	return true;
}

//*****************************************************************************
//
// SYNOPSIS
//
	bool move_if_match(
		encoded_char_range::const_iterator &c, char const *s,
		bool ignore_case
	)
//
// SYNOPSIS
//
//	Compares a string starting at the given iterator to another.
//
// PARAMETERS
//
//	c		The iterator to use.  If the string matches, it is
//			repositioned at the first character past the string;
//			otherwise it is not touched.
//
//	s		The string to compare against.  If ignore_case is true,
//			then this string must be in lower case.
//
//	ignore_case	True if case should be ignored.
//
// RETURN VALUE
//
//	Returns true only if the string matches.
//
//*****************************************************************************
{
	encoded_char_range::const_iterator d = c;
	if ( ignore_case )
		while ( *s && !d.at_end() && *s == to_lower( *d ) )
			++s, ++d;
	else
		while ( *s && !d.at_end() && *s == *d )
			++s, ++d;
	if ( *s )			// didn't match before null
		return false;
	c = d;
	return true;
}
/* vim:set noet sw=8 ts=8: */