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
|
/* Place in the public domain by Sam Trenholme 2000 */
/* js_string routines that depend on the code page (encoding) that we
are in */
#include "JsStr.h"
/* js_newline_chars: returns a set of newline characters for a given
encoding
input: an empty js_string object we look at the codepage of
output: JS_ERROR (-1) on error, JS_SUCCESS (1) on success */
int js_newline_chars(js_string *js) {
/* Sanity check */
if(js_has_sanity(js) == -1)
return -1;
/* Handle different encodings differently */
switch(js->encoding) {
case JS_BINARY:
js->unit_count = 0;
return JS_SUCCESS;
case JS_US_ASCII:
case JS_ISO_8859_1:
if(js->unit_size != 1)
return -1; /* This string is not sane */
if(js_octets(js) < 2)
return -1; /* No overflows ever */
*(js->string) = '\r';
*(js->string + 1) = '\n';
js->unit_count = 2;
return JS_SUCCESS;
}
/* We only get here if it is an unhandled encoding */
return JS_ERROR;
}
/* js_space_chars: returns a set of whitespace characters for a given
encoding
input: an empty js_string object we look at the codepage of
output: JS_ERROR (-1) on error, JS_SUCCESS (1) on success */
int js_space_chars(js_string *js) {
/* Sanity check */
if(js_has_sanity(js) == -1)
return -1;
/* Handle different encodings differently */
switch(js->encoding) {
case JS_BINARY:
js->unit_count = 0;
return JS_SUCCESS;
case JS_US_ASCII:
case JS_ISO_8859_1:
if(js->unit_size != 1)
return -1; /* This string is not sane */
if(js_octets(js) < 3)
return -1; /* No overflows ever */
*(js->string) = ' ';
*(js->string + 1) = '\t';
if(js->encoding != JS_US_ASCII) {
*(js->string + 2) = 160; /* Non-breaking space */
js->unit_count = 3;
}
else
js->unit_count = 2;
return JS_SUCCESS;
}
/* We only get here if it is an unhandled encoding */
return JS_ERROR;
}
/* js_atoi: Convert a number, starting at a given offset, into an integer
input: js_string object to look at, place in string to start looking at
output: integer we find at the given point, 0 on error (ugh) */
unsigned int js_atoi(js_string *js, int offset) {
int value, sign;
if(js_has_sanity(js) == JS_ERROR)
return 0;
/* Return 0 if encoding unsupported */
if(js->encoding != JS_US_ASCII && js->encoding != JS_ISO_8859_1)
return 0;
/* All supported encodings use the same codes for numerical digits */
else {
if(offset >= js->unit_count)
return 0;
value = 0;
sign = 1;
while(offset < js->unit_count && *(js->string + offset) >= '0'
&& *(js->string + offset) <= '9') {
value *= 10;
value += *(js->string + offset) - '0';
offset++;
}
value *= sign;
return value;
}
return 0; /* We should never get here */
}
/* js_tolower: Convert a js_string object in to all lower case letters.
input: js_string object to convert
output: JS_ERROR on error, JS_SUCCESS on success */
int js_tolower(js_string *js) {
int counter;
if(js_has_sanity(js) == JS_ERROR)
return JS_ERROR;
if(js->unit_size != 1) /* All supported encodings have one octet
per character */
return JS_ERROR;
if(js->encoding == JS_US_ASCII) {
for(counter = 0; counter < js->unit_count; counter++)
if(*(js->string + counter) >= 'A' &&
*(js->string + counter) <= 'Z')
*(js->string + counter) += 32;
}
else if(js->encoding == JS_ISO_8859_1) {
for(counter = 0; counter < js->unit_count; counter++) {
if(*(js->string + counter) >= 'A' &&
*(js->string + counter) <= 'Z')
*(js->string + counter) += 32;
if(*(js->string + counter) >= 192 /* À */ &&
*(js->string + counter) <= 214 /* Ö */)
*(js->string + counter) += 32;
/* Why they had to put × and the corresponding ÷ smack dab in
the middle of the international letters is a mystery to me */
if(*(js->string + counter) >= 216 /* Ø */ &&
*(js->string + counter) <= 222 /* Þ */)
*(js->string + counter) += 32;
}
}
/* Return 0 if encoding unsupported */
else
return 0;
return JS_SUCCESS;
}
/* js_anq_chars: Give a list of alpha(numeric) characters for a given
encoding.
input: js_string object to fill with the data in question,
whether or not we include numbers and the _ symbol
(0 = no, 1 = yes, 2 = only numbers)
output: pointer to js_string obejct on success, 0 on error
*/
js_string *js_anq_chars(js_string *js, int do_nums) {
int place = 0,do_lets = 1;
unsigned char counter;
/* Sanity check */
if(js_has_sanity(js) == JS_ERROR)
return 0;
/* If we are doing only numbers, then we don't use letters */
if(do_nums == 2)
do_lets = 0;
/* Action is based on encoding */
switch(js->encoding) {
case JS_ISO_8859_1:
if(js_octets(js) < 192)
return 0; /* No overflows ever */
if(do_lets == 1) {
/* À to Ö */
for(counter=192;counter<=214;counter++) {
*(js->string + place) = counter;
place++;
}
/* Ø to ö */
for(counter=216;counter<=246;counter++) {
*(js->string + place) = counter;
place++;
}
/* ø to þ */
for(counter=248;counter<255;counter++) {
*(js->string + place) = counter;
place++;
}
/* ÿ ( We do it this way because counter is always <= 255 ) */
*(js->string + place) = 255;
place++;
}
case JS_US_ASCII:
if(js_octets(js) < 96)
return 0;
if(do_lets == 1) {
/* A to Z */
for(counter='A';counter<='Z';counter++) {
*(js->string + place) = counter;
place++;
}
/* a to z */
for(counter='a';counter<='z';counter++) {
*(js->string + place) = counter;
place++;
}
}
if(do_nums == 1 || do_nums == 2) {
/* 0 to 9 */
for(counter='0';counter<='9';counter++) {
*(js->string + place) = counter;
place++;
}
/* _ */
if(do_nums != 2) /* If not numbers only */ {
*(js->string + place) = '_';
place++;
}
}
js->unit_count = place;
break;
default:
return 0;
}
return js;
}
/* js_alpha_chars: Give a list of alphabetic characters for a given
encoding. (not including _)
input: js_string object to fill with the data in question,
output: pointer to js_string obejct on success, 0 on error
*/
js_string *js_alpha_chars(js_string *js) {
return js_anq_chars(js,0);
}
/* js_an_chars: Give a list of alphanumeric characters for a given
encoding. (including _)
input: js_string object to fill with the data in question,
output: pointer to js_string obejct on success, 0 on error
*/
js_string *js_an_chars(js_string *js) {
return js_anq_chars(js,1);
}
/* js_numbers: Give a list of numeric characters for a given
encoding. (no _)
input: js_string object to fill with the data in question,
output: pointer to js_string obejct on success, 0 on error
*/
js_string *js_numbers(js_string *js) {
return js_anq_chars(js,2);
}
|
