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
|
#include "owl.h"
/* Returns a copy of 'in' with each line indented 'n'
* characters. Result must be freed with g_free. */
CALLER_OWN char *owl_text_indent(const char *in, int n, bool indent_first_line)
{
const char *ptr1, *ptr2, *last;
GString *out = g_string_new("");
int i;
bool indent_this_line = indent_first_line;
last=in+strlen(in)-1;
ptr1=in;
while (ptr1<=last) {
if (indent_this_line) {
for (i = 0; i < n; i++) {
g_string_append_c(out, ' ');
}
}
indent_this_line = true;
ptr2=strchr(ptr1, '\n');
if (!ptr2) {
g_string_append(out, ptr1);
break;
} else {
g_string_append_len(out, ptr1, ptr2-ptr1+1);
}
ptr1=ptr2+1;
}
return g_string_free(out, false);
}
int owl_text_num_lines(const char *in)
{
int lines, i;
lines=0;
for (i=0; in[i]!='\0'; i++) {
if (in[i]=='\n') lines++;
}
/* if the last char wasn't a \n there's one more line */
if (i>0 && in[i-1]!='\n') lines++;
return(lines);
}
/* caller must free the return */
CALLER_OWN char *owl_text_htmlstrip(const char *in)
{
const char *ptr1, *end, *ptr2, *ptr3;
char *out, *out2;
out=g_new(char, strlen(in)+30);
strcpy(out, "");
ptr1=in;
end=in+strlen(in);
while(ptr1<end) {
/* look for an open bracket */
ptr2=strchr(ptr1, '<');
/* if none, copy in from here to end and exit */
if (ptr2==NULL) {
strcat(out, ptr1);
break;
}
/* otherwise copy in everything before the open bracket */
if (ptr2>ptr1) {
strncat(out, ptr1, ptr2-ptr1);
}
/* find the close bracket */
ptr3=strchr(ptr2, '>');
/* if there is no close, copy as you are and exit */
if (!ptr3) {
strcat(out, ptr2);
break;
}
/* look for things we know */
if (!strncasecmp(ptr2, "<BODY", 5) ||
!strncasecmp(ptr2, "<FONT", 5) ||
!strncasecmp(ptr2, "<HTML", 5) ||
!strncasecmp(ptr2, "</FONT", 6) ||
!strncasecmp(ptr2, "</HTML", 6) ||
!strncasecmp(ptr2, "</BODY", 6)) {
/* advance to beyond the angle brakcet and go again */
ptr1=ptr3+1;
continue;
}
if (!strncasecmp(ptr2, "<BR>", 4)) {
strcat(out, "\n");
ptr1=ptr3+1;
continue;
}
/* if it wasn't something we know, copy to the > and go again */
strncat(out, ptr2, ptr3-ptr2+1);
ptr1=ptr3+1;
}
out2=owl_text_substitute(out, "<", "<");
g_free(out);
out=owl_text_substitute(out2, ">", ">");
g_free(out2);
out2=owl_text_substitute(out, "&", "&");
g_free(out);
out=owl_text_substitute(out2, """, "\"");
g_free(out2);
out2=owl_text_substitute(out, " ", " ");
g_free(out);
out=owl_text_substitute(out2, " ", " ");
g_free(out2);
out2=owl_text_substitute(out, " ", " ");
g_free(out);
out=owl_text_substitute(out2, "&endash;", "--");
g_free(out2);
out2=owl_text_substitute(out, "&emdash;", "---");
g_free(out);
return(out2);
}
/* Caller must free return */
CALLER_OWN char *owl_text_expand_tabs(const char *in)
{
int len = 0;
const char *p = in;
char *ret, *out;
int col;
col = 0;
while(*p) {
gunichar c = g_utf8_get_char(p);
const char *q = g_utf8_next_char(p);
switch (c) {
case '\t':
do { len++; col++; } while (col % OWL_TAB_WIDTH);
p = q;
continue;
case '\n':
col = 0;
break;
default:
col += mk_wcwidth(c);
break;
}
len += q - p;
p = q;
}
ret = g_new(char, len + 1);
p = in;
out = ret;
col = 0;
while(*p) {
gunichar c = g_utf8_get_char(p);
const char *q = g_utf8_next_char(p);
switch (c) {
case '\t':
do {*(out++) = ' '; col++; } while (col % OWL_TAB_WIDTH);
p = q;
continue;
case '\n':
col = 0;
break;
default:
col += mk_wcwidth(c);
break;
}
memcpy(out, p, q - p);
out += q - p;
p = q;
}
*out = 0;
return ret;
}
/* caller must free the return */
CALLER_OWN char *owl_text_wordwrap(const char *in, int col)
{
char *out;
int cur, lastspace, len, lastnewline;
out=g_strdup(in);
len=strlen(in);
cur=0;
lastspace=-1;
lastnewline=-1;
while (cur<(len-1)) {
if (out[cur]==' ') {
lastspace=cur;
cur++;
continue;
} else if (out[cur]=='\n') {
lastnewline=cur;
cur++;
continue;
}
/* do we need to wrap? */
if ( (cur-(lastnewline+1)) > col ) {
if (lastspace==-1 ||
(lastnewline>0 && (lastspace<=lastnewline))) {
/* we can't help, sorry */
cur++;
continue;
}
/* turn the last space into a newline */
out[lastspace]='\n';
lastnewline=lastspace;
lastspace=-1;
cur++;
continue;
}
cur++;
continue;
}
return(out);
}
/* this modifies 'in' */
void owl_text_wordunwrap(char *in)
{
int i, j;
j=strlen(in);
for (i=0; i<j; i++) {
if ( (in[i]=='\n') &&
((i>0) && (i<(j-1))) &&
(in[i-1]!='\n') &&
(in[i+1]!='\n') )
in[i]=' ';
}
}
/* return 1 if a string is only whitespace, otherwise 0 */
int only_whitespace(const char *s)
{
if (g_utf8_validate(s,-1,NULL)) {
const char *p;
for(p = s; p[0]; p=g_utf8_next_char(p)) {
if (!g_unichar_isspace(g_utf8_get_char(p))) return 0;
}
}
else {
int i;
for (i=0; s[i]; i++) {
if (!isspace((int) s[i])) return(0);
}
}
return(1);
}
/* Return a string with any occurances of 'from' replaced with 'to'.
* Caller must free returned string.
*/
CALLER_OWN char *owl_text_substitute(const char *in, const char *from, const char *to)
{
char **split = g_strsplit(in, from, 0), *out;
out = g_strjoinv(to, split);
g_strfreev(split);
return out;
}
/* Return a string which is like 'in' except that every instance of
* any character in 'toquote' found in 'in' is preceeded by the string
* 'quotestr'. For example, owl_text_quote(in, "+*.", "\") would
* place a backslash before every '+', '*' or '.' in 'in'. It is
* permissable for a character in 'quotestr' to be in 'toquote'.
* On success returns the string, on error returns NULL.
*/
CALLER_OWN char *owl_text_quote(const char *in, const char *toquote, const char *quotestr)
{
int i, x, r, place, escape;
int in_len, toquote_len, quotestr_len;
char *out;
in_len=strlen(in);
toquote_len=strlen(toquote);
quotestr_len=strlen(quotestr);
place=0;
escape = 0;
for (i=0; i<in_len; i++) {
if(strchr(toquote, in[i]) != NULL)
escape++;
}
out = g_new(char, in_len + quotestr_len*escape+1);
for (i=0; i<in_len; i++) {
/* check if it's a character that needs quoting */
for (x=0; x<toquote_len; x++) {
if (in[i]==toquote[x]) {
/* quote it */
for (r=0; r<quotestr_len; r++) {
out[place+r]=quotestr[r];
}
place+=quotestr_len;
break;
}
}
/* either way, we now copy over the character */
out[place]=in[i];
place++;
}
out[place]='\0';
return(out);
}
|