[7d4fbcd] | 1 | #include <stdio.h> |
---|
| 2 | #include <string.h> |
---|
| 3 | #include <stdlib.h> |
---|
[995eb4b] | 4 | #include <ctype.h> |
---|
[7d4fbcd] | 5 | #include "owl.h" |
---|
| 6 | |
---|
[1aee7d9] | 7 | static const char fileIdent[] = "$Id$"; |
---|
| 8 | |
---|
[ab31454] | 9 | void owl_text_indent(char *out, char *in, int n) |
---|
| 10 | { |
---|
[7d4fbcd] | 11 | char *ptr1, *ptr2, *last; |
---|
| 12 | int i; |
---|
| 13 | |
---|
| 14 | strcpy(out, ""); |
---|
| 15 | |
---|
| 16 | last=in+strlen(in)-1; |
---|
| 17 | ptr1=in; |
---|
| 18 | while (ptr1<=last) { |
---|
| 19 | for (i=0; i<n; i++) { |
---|
| 20 | strcat(out, " "); |
---|
| 21 | } |
---|
| 22 | ptr2=strchr(ptr1, '\n'); |
---|
| 23 | if (!ptr2) { |
---|
| 24 | strcat(out, ptr1); |
---|
| 25 | break; |
---|
| 26 | } else { |
---|
| 27 | strncat(out, ptr1, ptr2-ptr1+1); |
---|
| 28 | } |
---|
| 29 | ptr1=ptr2+1; |
---|
| 30 | } |
---|
| 31 | } |
---|
| 32 | |
---|
[ab31454] | 33 | int owl_text_num_lines(char *in) |
---|
| 34 | { |
---|
[7d4fbcd] | 35 | int lines, i; |
---|
| 36 | |
---|
| 37 | lines=0; |
---|
| 38 | for (i=0; in[i]!='\0'; i++) { |
---|
| 39 | if (in[i]=='\n') lines++; |
---|
| 40 | } |
---|
| 41 | |
---|
| 42 | /* if the last char wasn't a \n there's one more line */ |
---|
[1bb1e67] | 43 | if (i>0 && in[i-1]!='\n') lines++; |
---|
[7d4fbcd] | 44 | |
---|
| 45 | return(lines); |
---|
| 46 | } |
---|
| 47 | |
---|
[3abf28b] | 48 | |
---|
| 49 | /* caller must free the return */ |
---|
[ab31454] | 50 | char *owl_text_htmlstrip(char *in) |
---|
| 51 | { |
---|
[8d24696] | 52 | char *ptr1, *end, *ptr2, *ptr3, *out, *out2; |
---|
[3abf28b] | 53 | |
---|
| 54 | out=owl_malloc(strlen(in)+30); |
---|
| 55 | strcpy(out, ""); |
---|
| 56 | |
---|
| 57 | ptr1=in; |
---|
| 58 | end=in+strlen(in); |
---|
| 59 | |
---|
| 60 | while(ptr1<end) { |
---|
| 61 | /* look for an open bracket */ |
---|
| 62 | ptr2=strchr(ptr1, '<'); |
---|
| 63 | |
---|
[dafd919] | 64 | /* if none, copy in from here to end and exit */ |
---|
[3abf28b] | 65 | if (ptr2==NULL) { |
---|
| 66 | strcat(out, ptr1); |
---|
[8d24696] | 67 | break; |
---|
[3abf28b] | 68 | } |
---|
| 69 | |
---|
| 70 | /* otherwise copy in everything before the open bracket */ |
---|
| 71 | if (ptr2>ptr1) { |
---|
| 72 | strncat(out, ptr1, ptr2-ptr1); |
---|
| 73 | } |
---|
| 74 | |
---|
| 75 | /* find the close bracket */ |
---|
| 76 | ptr3=strchr(ptr2, '>'); |
---|
| 77 | |
---|
| 78 | /* if there is no close, copy as you are and exit */ |
---|
| 79 | if (!ptr3) { |
---|
| 80 | strcat(out, ptr2); |
---|
[8d24696] | 81 | break; |
---|
[3abf28b] | 82 | } |
---|
| 83 | |
---|
| 84 | /* look for things we know */ |
---|
[3bcf125] | 85 | if (!strncasecmp(ptr2, "<BODY", 5) || |
---|
[dafd919] | 86 | !strncasecmp(ptr2, "<FONT", 5) || |
---|
[3abf28b] | 87 | !strncasecmp(ptr2, "<HTML", 5) || |
---|
| 88 | !strncasecmp(ptr2, "</FONT", 6) || |
---|
| 89 | !strncasecmp(ptr2, "</HTML", 6) || |
---|
| 90 | !strncasecmp(ptr2, "</BODY", 6)) { |
---|
| 91 | |
---|
| 92 | /* advance to beyond the angle brakcet and go again */ |
---|
| 93 | ptr1=ptr3+1; |
---|
| 94 | continue; |
---|
| 95 | } |
---|
[75e3879] | 96 | if (!strncasecmp(ptr2, "<BR>", 4)) { |
---|
| 97 | strcat(out, "\n"); |
---|
| 98 | ptr1=ptr3+1; |
---|
| 99 | continue; |
---|
| 100 | } |
---|
[3abf28b] | 101 | |
---|
| 102 | /* if it wasn't something we know, copy to the > and go again */ |
---|
[75e3879] | 103 | strncat(out, ptr2, ptr3-ptr2+1); |
---|
[3abf28b] | 104 | ptr1=ptr3+1; |
---|
| 105 | } |
---|
[8d24696] | 106 | |
---|
[e3d9c77] | 107 | out2=owl_text_substitute(out, "<", "<"); |
---|
[8d24696] | 108 | owl_free(out); |
---|
[e3d9c77] | 109 | out=owl_text_substitute(out2, ">", ">"); |
---|
[8d24696] | 110 | owl_free(out2); |
---|
[e3d9c77] | 111 | out2=owl_text_substitute(out, "&", "&"); |
---|
[8d24696] | 112 | owl_free(out); |
---|
[e3d9c77] | 113 | out=owl_text_substitute(out2, """, "\""); |
---|
[8d24696] | 114 | owl_free(out2); |
---|
[e3d9c77] | 115 | out2=owl_text_substitute(out, " ", " "); |
---|
[8d24696] | 116 | owl_free(out); |
---|
[e3d9c77] | 117 | out=owl_text_substitute(out2, " ", " "); |
---|
[8d24696] | 118 | owl_free(out2); |
---|
[e3d9c77] | 119 | out2=owl_text_substitute(out, " ", " "); |
---|
[8d24696] | 120 | owl_free(out); |
---|
[e3d9c77] | 121 | out=owl_text_substitute(out2, "&endash;", "--"); |
---|
[8d24696] | 122 | owl_free(out2); |
---|
[e3d9c77] | 123 | out2=owl_text_substitute(out, "&emdash;", "---"); |
---|
[8d24696] | 124 | owl_free(out); |
---|
| 125 | |
---|
| 126 | return(out2); |
---|
[3abf28b] | 127 | } |
---|
[ab31454] | 128 | |
---|
[3e8ff1e] | 129 | #define OWL_TAB_WIDTH 8 |
---|
| 130 | |
---|
| 131 | /* Caller must free return */ |
---|
| 132 | char *owl_text_expand_tabs(char *in) |
---|
| 133 | { |
---|
| 134 | int ntabs = 0; |
---|
| 135 | char *p = in; |
---|
| 136 | char *ret, *out; |
---|
| 137 | int col; |
---|
| 138 | |
---|
| 139 | while(*p) { |
---|
| 140 | if (*(p++) == '\t') ntabs++; |
---|
| 141 | } |
---|
| 142 | |
---|
| 143 | ret = owl_malloc(strlen(in) + 1 + OWL_TAB_WIDTH * ntabs); |
---|
| 144 | |
---|
| 145 | p = in; |
---|
| 146 | out = ret; |
---|
| 147 | |
---|
| 148 | col = 0; |
---|
| 149 | while(*p) { |
---|
| 150 | switch(*p) { |
---|
| 151 | case '\t': |
---|
| 152 | do {*(out++) = ' '; col++; } while (col % OWL_TAB_WIDTH); |
---|
| 153 | break; |
---|
| 154 | case '\n': |
---|
| 155 | col = -1; |
---|
| 156 | default: |
---|
| 157 | col++; |
---|
| 158 | *(out++) = *p; |
---|
| 159 | } |
---|
| 160 | p++; |
---|
| 161 | } |
---|
| 162 | |
---|
| 163 | *out = 0; |
---|
| 164 | |
---|
| 165 | return ret; |
---|
| 166 | } |
---|
| 167 | |
---|
[ab31454] | 168 | /* caller must free the return */ |
---|
| 169 | char *owl_text_wordwrap(char *in, int col) |
---|
| 170 | { |
---|
| 171 | char *out; |
---|
| 172 | int cur, lastspace, len, lastnewline; |
---|
| 173 | |
---|
| 174 | out=owl_strdup(in); |
---|
| 175 | len=strlen(in); |
---|
| 176 | cur=0; |
---|
| 177 | lastspace=-1; |
---|
| 178 | lastnewline=-1; |
---|
| 179 | |
---|
| 180 | while (cur<(len-1)) { |
---|
| 181 | if (out[cur]==' ') { |
---|
| 182 | lastspace=cur; |
---|
| 183 | cur++; |
---|
| 184 | continue; |
---|
| 185 | } else if (out[cur]=='\n') { |
---|
| 186 | lastnewline=cur; |
---|
| 187 | cur++; |
---|
| 188 | continue; |
---|
| 189 | } |
---|
| 190 | |
---|
| 191 | /* do we need to wrap? */ |
---|
| 192 | if ( (cur-(lastnewline+1)) > col ) { |
---|
| 193 | if (lastspace==-1 || |
---|
| 194 | (lastnewline>0 && (lastspace<=lastnewline))) { |
---|
| 195 | /* we can't help, sorry */ |
---|
| 196 | cur++; |
---|
| 197 | continue; |
---|
| 198 | } |
---|
| 199 | |
---|
| 200 | /* turn the last space into a newline */ |
---|
| 201 | out[lastspace]='\n'; |
---|
| 202 | lastnewline=lastspace; |
---|
| 203 | lastspace=-1; |
---|
| 204 | cur++; |
---|
| 205 | continue; |
---|
| 206 | } |
---|
| 207 | |
---|
| 208 | cur++; |
---|
| 209 | continue; |
---|
| 210 | } |
---|
| 211 | return(out); |
---|
| 212 | } |
---|
[e3d9c77] | 213 | |
---|
[f82e233] | 214 | /* this modifies 'in' */ |
---|
| 215 | void owl_text_wordunwrap(char *in) |
---|
| 216 | { |
---|
| 217 | int i, j; |
---|
| 218 | |
---|
| 219 | j=strlen(in); |
---|
| 220 | for (i=0; i<j; i++) { |
---|
| 221 | if ( (in[i]=='\n') && |
---|
| 222 | ((i>0) && (i<(j-1))) && |
---|
| 223 | (in[i-1]!='\n') && |
---|
| 224 | (in[i+1]!='\n') ) |
---|
| 225 | in[i]=' '; |
---|
| 226 | } |
---|
| 227 | } |
---|
| 228 | |
---|
[e3d9c77] | 229 | /* exactly like strstr but case insensitive */ |
---|
| 230 | char *stristr(char *a, char *b) |
---|
| 231 | { |
---|
[28ee32b] | 232 | char *x, *y; |
---|
| 233 | char *ret = NULL; |
---|
| 234 | if ((x = g_utf8_casefold(a, -1)) != NULL) { |
---|
| 235 | if ((y = g_utf8_casefold(b, -1)) != NULL) { |
---|
| 236 | ret = strstr(x, y); |
---|
| 237 | if (ret != NULL) { |
---|
| 238 | ret = ret - x + a; |
---|
| 239 | } |
---|
| 240 | g_free(y); |
---|
| 241 | } |
---|
| 242 | g_free(x); |
---|
[e3d9c77] | 243 | } |
---|
| 244 | return(ret); |
---|
| 245 | } |
---|
| 246 | |
---|
| 247 | /* return 1 if a string is only whitespace, otherwise 0 */ |
---|
| 248 | int only_whitespace(char *s) |
---|
| 249 | { |
---|
[28ee32b] | 250 | if (g_utf8_validate(s,-1,NULL)) { |
---|
| 251 | char *p; |
---|
| 252 | for(p = s; p[0]; p=g_utf8_next_char(p)) { |
---|
| 253 | if (!g_unichar_isspace(g_utf8_get_char(p))) return 0; |
---|
| 254 | } |
---|
| 255 | } |
---|
| 256 | else { |
---|
| 257 | int i; |
---|
| 258 | for (i=0; s[i]; i++) { |
---|
| 259 | if (!isspace((int) s[i])) return(0); |
---|
| 260 | } |
---|
[e3d9c77] | 261 | } |
---|
| 262 | return(1); |
---|
| 263 | } |
---|
| 264 | |
---|
| 265 | char *owl_getquoting(char *line) |
---|
| 266 | { |
---|
| 267 | if (line[0]=='\0') return("'"); |
---|
| 268 | if (strchr(line, '\'')) return("\""); |
---|
| 269 | if (strchr(line, '"')) return("'"); |
---|
| 270 | if (strchr(line, ' ')) return("'"); |
---|
| 271 | return(""); |
---|
| 272 | } |
---|
| 273 | |
---|
| 274 | /* Return a string with any occurances of 'from' replaced with 'to'. |
---|
| 275 | * Does not currently handle backslash quoting, but may in the future. |
---|
| 276 | * Caller must free returned string. |
---|
| 277 | */ |
---|
| 278 | char *owl_text_substitute(char *in, char *from, char *to) |
---|
| 279 | { |
---|
| 280 | |
---|
| 281 | char *out; |
---|
| 282 | int outlen, tolen, fromlen, inpos=0, outpos=0; |
---|
| 283 | |
---|
| 284 | if (!*from) return owl_strdup(in); |
---|
| 285 | |
---|
| 286 | outlen = strlen(in)+1; |
---|
| 287 | tolen = strlen(to); |
---|
| 288 | fromlen = strlen(from); |
---|
[34509d5] | 289 | out = owl_malloc(outlen); |
---|
[e3d9c77] | 290 | |
---|
| 291 | while (in[inpos]) { |
---|
| 292 | if (!strncmp(in+inpos, from, fromlen)) { |
---|
| 293 | outlen += tolen; |
---|
| 294 | out = owl_realloc(out, outlen); |
---|
| 295 | strcpy(out+outpos, to); |
---|
| 296 | inpos += fromlen; |
---|
| 297 | outpos += tolen; |
---|
| 298 | } else { |
---|
| 299 | out[outpos] = in[inpos]; |
---|
| 300 | inpos++; outpos++; |
---|
| 301 | } |
---|
| 302 | } |
---|
| 303 | out[outpos] = '\0'; |
---|
| 304 | return(out); |
---|
| 305 | } |
---|
| 306 | |
---|
| 307 | /* replace all instances of character a in buff with the character |
---|
| 308 | * b. buff must be null terminated. |
---|
| 309 | */ |
---|
| 310 | void owl_text_tr(char *buff, char a, char b) |
---|
| 311 | { |
---|
| 312 | int i; |
---|
| 313 | |
---|
| 314 | owl_function_debugmsg("In: %s", buff); |
---|
| 315 | for (i=0; buff[i]!='\0'; i++) { |
---|
| 316 | if (buff[i]==a) buff[i]=b; |
---|
| 317 | } |
---|
| 318 | owl_function_debugmsg("Out: %s", buff); |
---|
| 319 | } |
---|
| 320 | |
---|
| 321 | /* Return a string which is like 'in' except that every instance of |
---|
| 322 | * any character in 'toquote' found in 'in' is preceeded by the string |
---|
| 323 | * 'quotestr'. For example, owl_text_quote(in, "+*.", "\") would |
---|
| 324 | * place a backslash before every '+', '*' or '.' in 'in'. It is |
---|
| 325 | * permissable for a character in 'quotestr' to be in 'toquote'. |
---|
| 326 | * On success returns the string, on error returns NULL. |
---|
| 327 | */ |
---|
| 328 | char *owl_text_quote(char *in, char *toquote, char *quotestr) |
---|
| 329 | { |
---|
[72db971] | 330 | int i, x, r, place, escape; |
---|
[e3d9c77] | 331 | int in_len, toquote_len, quotestr_len; |
---|
| 332 | char *out; |
---|
| 333 | |
---|
| 334 | in_len=strlen(in); |
---|
| 335 | toquote_len=strlen(toquote); |
---|
| 336 | quotestr_len=strlen(quotestr); |
---|
| 337 | out=owl_malloc((in_len*quotestr_len)+30); |
---|
| 338 | place=0; |
---|
[72db971] | 339 | escape = 0; |
---|
| 340 | for (i=0; i<in_len; i++) { |
---|
| 341 | if(strchr(toquote, in[i]) != NULL) |
---|
| 342 | escape++; |
---|
| 343 | } |
---|
| 344 | out = owl_malloc(in_len + quotestr_len*escape+1); |
---|
[e3d9c77] | 345 | for (i=0; i<in_len; i++) { |
---|
| 346 | |
---|
| 347 | /* check if it's a character that needs quoting */ |
---|
| 348 | for (x=0; x<toquote_len; x++) { |
---|
| 349 | if (in[i]==toquote[x]) { |
---|
| 350 | /* quote it */ |
---|
| 351 | for (r=0; r<quotestr_len; r++) { |
---|
| 352 | out[place+r]=quotestr[r]; |
---|
| 353 | } |
---|
| 354 | place+=quotestr_len; |
---|
| 355 | break; |
---|
| 356 | } |
---|
| 357 | } |
---|
| 358 | |
---|
| 359 | /* either way, we now copy over the character */ |
---|
| 360 | out[place]=in[i]; |
---|
| 361 | place++; |
---|
| 362 | } |
---|
| 363 | out[place]='\0'; |
---|
| 364 | return(out); |
---|
| 365 | } |
---|