File: language.cc

package info (click to toggle)
ht 2.1.0%2Brepack1-2
  • links: PTS, VCS
  • area: main
  • in suites: stretch
  • size: 5,712 kB
  • ctags: 15,753
  • sloc: cpp: 88,932; ansic: 12,693; sh: 4,081; lex: 226; makefile: 184; yacc: 128
file content (269 lines) | stat: -rw-r--r-- 6,287 bytes parent folder | download | duplicates (7)
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
/*
 *	HT Editor
 *	language.cc
 *
 * 	Copyright (C) 1999-2002 Sebastian Biallas (sb@biallas.net)
 *
 * 	This program is free software; you can redistribute it and/or modify
 * 	it under the terms of the GNU General Public License version 2 as
 * 	published by the Free Software Foundation.
 *
 * 	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.
 *
 */

#include <string.h>
#include "htdebug.h"
#include "strtools.h"
#include "language.h"
#include "tools.h"

/*
 *	' ' = separator -> skip
 *	INV = invalid char -> error
 */
byte mapchar[] = {
	' ',' ',' ',' ',' ',' ',' ',' ',' ',' ', 10,' ',' ',' ',' ',' ', // 0-15
	' ',' ',' ',' ',' ',' ',' ',' ',' ',' ',' ',' ',' ',' ',' ',' ', // 16-31
	' ','!','"','#','$','%','&', 39,'(',')','*','+',',','-','.','/', // 32-47
	'0','0','0','0','0','0','0','0','0','0',':',';','<','=','>','?', // 48-63
	'@','A','A','A','A','A','A','A','A','A','A','A','A','A','A','A', // 64-79
	'A','A','A','A','A','A','A','A','A','A','A','[', 92,']','^','_', // 80-95
	INV,'A','A','A','A','A','A','A','A','A','A','A','A','A','A','A', // 96-111
	'A','A','A','A','A','A','A','A','A','A','A','{','|','}','~',INV, // 112-127
	INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,
	INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,
	INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,
	INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,
	INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,
	INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,
	INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,
	INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV,INV
};

int analy_string__raw_test(const byte *s, int len)
{
	// could be a "" string
	if (!len) return 1;

	int all_word_len=0;
	int bad_chars=0;
	int words=0;
	bool word_start=false;
	for (int i=0; i<len; i++) {
		byte mc = mapchar[s[i]];
		if (s[i] == '\n' || s[i] == '\t') {
			if (word_start) {
				words++;
				word_start = false;
			}
		} else if (s[i] < 32 || mc == INV) {
			if (word_start) {
				words++;
				word_start = false;
			}
			bad_chars++;
			if (s[i] == 0) {
				bad_chars += 50;
			}
		} else if (s[i] == ' ') {
			if (word_start) {
				words++;
				word_start = false;
			}
		} else if (mc == 'A' || mc == '0') {
			word_start = true;
			all_word_len++;
		} else {
			// symbols (+-/* ...)
			// currently the same as ' '
			if (word_start) {
				words++;
				word_start = false;
			}
		}
	}
	if (word_start) {
		words++;
		word_start = false;
	}
	// more than 10% badchars --> no string
	if (bad_chars*10>len) return -1;
	// no words found
	if (!words) return len/2-bad_chars*5+1;
	int average_word_len = all_word_len / words;
	int av_res[10] = {1, 2, 4, 8, 16, 16, 10, 8, 6, 3};
	int av_plus = 0;
	if (average_word_len > 1 && average_word_len < 12) av_plus = av_res[average_word_len - 2];
	return words*2 + av_plus - bad_chars*5 + len/5 + average_word_len;
}

/*
 *	CLASS analy_string
 */
void analy_string::init(const byte *s, int Len)
{
	string = ht_malloc(Len);
	memcpy(string, s, Len);
	len = Len;
}

void analy_string::done()
{
	free(string);
}

int  analy_string::length()
{
	return len;
}

void analy_string::set_len(int Len)
{
	len = Len;
}

/*
 *	CLASS analy_raw_string
 */
void analy_raw_string::render_string(char *result, int maxlen)
{
}

int analy_raw_string::string_test(const byte *s, int testlen, int &foundlen)
{
	foundlen = 0;
	return 0;
}

const char *analy_raw_string::name()
{
	return "raw";
}

/*
 *	CLASS analy_c_string
 */
void analy_c_string::render_string(char *result, int maxlen)
{
	assert(maxlen);
	maxlen--;
	int Len = MIN(len, maxlen);
	if (Len) Len--;
	memcpy(result, string, Len);
	result[Len]=0;          
}

int analy_c_string::string_test(const byte *s, int testlen, int &foundlen)
{
	// search for \0
	byte *np = (byte *)memchr(s, 0, testlen);
	if (!np) return -1;
	int len = np-s+1;
	foundlen = len;
	return analy_string__raw_test(s, len-1);
}

const char *analy_c_string::name()
{
	return "strz";
}

/*
 *	CLASS analy_unicode_string
 */
void analy_unicode_string::render_string(char *result, int maxlen)
{
	wide_char_to_multi_byte(result, string, maxlen);
}

int analy_unicode_string::string_test(const byte *s, int testlen, int &foundlen)
{
	// this is not good
	byte *a = ht_malloc(testlen/2+1);
	wide_char_to_multi_byte((char*)a, s, testlen/2);
	// search for \0
	byte *np = (byte *)memchr(a, 0, testlen/2);
	if (!np) {
		free(a);
		return -1;
	}
	int len = np-a;
	foundlen = len*2+2;
	int res = analy_string__raw_test(a, len);
	free(a);
	return res;
}

const char *analy_unicode_string::name()
{
	return "strw";
}

/*
 *	CLASS analy_pascal_string
 */
void analy_pascal_string::render_string(char *result, int maxlen)
{
	assert(maxlen);
	maxlen--;
	int Len = MIN(*string, maxlen);
	if (Len) memcpy(result, string+1, Len);
	result[Len]=0;
}

int analy_pascal_string::string_test(const byte *s, int testlen, int &foundlen)
{
	int len = *s;
	if (len>testlen) return -1;
	foundlen = len+1;
	return analy_string__raw_test(s+1, len);
}

const char *analy_pascal_string::name()
{
	return "strp";
}

#define STRING_TESTS 2
analy_string *string_test(const byte *s, int testlen)
{
	if (!testlen) return NULL;     
	int p[STRING_TESTS+1];
	int len[STRING_TESTS];
	p[0] = analy_c_string::string_test(s, testlen, len[0]);
	p[1] = analy_unicode_string::string_test(s, testlen, len[1]);
//	p[2] = analy_pascal_string::string_test(s, testlen, len[2]);
	p[STRING_TESTS] = 5;
	int j = STRING_TESTS;
	for (int i=0; i < STRING_TESTS; i++) {
		if (p[i] > p[j]) j = i;
	}
	analy_string *as = NULL;;
	switch (j) {
		case 0:
			as = new analy_c_string();
			break;
		case 1:
			as = new analy_unicode_string();
			break;
/*		case 2:
			as = new analy_pascal_string();
			break;*/
		default:
			break;
	}
	if (as) {
		as->init(s, testlen);
		as->set_len(len[j]);
	}
	return as;
}