common/SC_TextUtils.cpp

   1 /*
   2         SuperCollider real time audio synthesis system
   3         Copyright (c) 2002 James McCartney. All rights reserved.
   4         http://www.audiosynth.com
   5         Copyright (c) 2012 Tim Blechmann. All rights reserved.
   6
   7     This program is free software; you can redistribute it and/or modify
   8     it under the terms of the GNU General Public License as published by
   9     the Free Software Foundation; either version 2 of the License, or
  10     (at your option) any later version.
  11
  12     This program is distributed in the hope that it will be useful,
  13     but WITHOUT ANY WARRANTY; without even the implied warranty of
  14     MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  15     GNU General Public License for more details.
  16
  17     You should have received a copy of the GNU General Public License
  18     along with this program; if not, write to the Free Software
  19     Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301  USA
  20 */
  21
  22 #include <cstring>
  23
  24 #define OPENCURLY '{'
  25 #define CLOSCURLY '}'
  26
  27 int rtf2txt(char* txt)
  28 {
  29         int rdpos=0, wrpos=0;
  30         char c;
  31         if (strncmp(txt,"{\\rtf",5)!=0) return 0;  // OK, not an RTF file
  32 text:
  33         switch (txt[wrpos]=txt[rdpos++])
  34         {
  35         case 0:
  36                 /*{
  37                                         char fname[32];
  38                                         sprintf(fname, "rtf2txt_out%d.txt", bugctr++);
  39                                         FILE *fp = fopen(fname, "w");
  40                                         fwrite(txt,wrpos,1,fp);
  41                                         fclose(fp);
  42                                 }*/
  43                 return wrpos;
  44         case OPENCURLY:
  45         case CLOSCURLY:
  46         case '\n': goto text;
  47         case '\\':
  48                 if (strncmp(txt+rdpos,"fonttbl",7)==0
  49                         || strncmp(txt+rdpos,"filetbl",7)==0
  50                         || strncmp(txt+rdpos,"colortbl",8)==0
  51                         || strncmp(txt+rdpos,"stylesheet",10)==0
  52                         )
  53                 {
  54                         int level = 1;
  55                         while(level && (c=txt[rdpos++]) != 0) {
  56                                 if (c == OPENCURLY) level++;
  57                                 else if (c == CLOSCURLY) level--;
  58                         }
  59                 } else if (strncmp(txt+rdpos,"\'a0",3)==0 || (strncmp(txt+rdpos,"\'A0",3)==0))
  60                 {
  61                         txt[wrpos++] = ' '; rdpos = rdpos + 3;
  62                 } else {
  63                         if (txt[rdpos]==CLOSCURLY || txt[rdpos]==OPENCURLY
  64                                 || txt[rdpos]=='\\' || txt[rdpos]=='\t'|| txt[rdpos]=='\n')
  65                         { txt[wrpos++] = txt[rdpos++]; goto text; }
  66                         if (strncmp(txt+rdpos,"tab",3)==0) { txt[wrpos++] = '\t'; }
  67                         if (strncmp(txt+rdpos,"par",3)==0) { txt[wrpos++] = '\n'; }
  68
  69                         while((c=txt[rdpos++]) && c!=' ' && c!='\\');
  70                         if (c=='\\') rdpos--;
  71                 }
  72                 goto text;
  73         default :
  74                 wrpos++;
  75                 goto text;
  76         }
  77 }
  78
  79 // strips HTML down to plaintext tags in a fairly simple-minded way
  80 int html2txt(char* txt)
  81 {
  82         int rdpos=-1, wrpos=0, bodypos=-1;
  83         bool intag = false;
  84
  85         // First check if we can find a BODY tag to start at
  86         while(bodypos == -1 && txt[++rdpos] != 0){
  87                 if(strncmp(txt+rdpos, "<body", 5) == 0) // FIXME: should be case-insensitive, ideally
  88                         bodypos = rdpos;
  89         }
  90         if(bodypos != -1)
  91                 rdpos = bodypos;
  92         else
  93                 rdpos = 0;
  94
  95         // Now we start from our start, and add the non-tag text to the result
  96         while(txt[rdpos] != 0){
  97                 if(intag){
  98                         if(txt[rdpos++] == '>')
  99                                 intag = false;
 100                 }else{
 101                         if(txt[rdpos] == '<'){
 102                                 intag = true;
 103                                 ++rdpos;
 104                         }else{
 105                                 /*
 106                                 if(strncmp(txt+rdpos, "&amp;", 5)==0){
 107                                         txt[wrpos++] = '&';
 108                                         rdpos += 5;
 109                                 }else if(strncmp(txt+rdpos, "&nbsp;", 6)==0){
 110                                         txt[wrpos++] = ' ';
 111                                         rdpos += 6;
 112                                 }else if(strncmp(txt+rdpos, "&lt;", 4)==0){
 113                                         txt[wrpos++] = '<';
 114                                         rdpos += 4;
 115                                 }else if(strncmp(txt+rdpos, "&gt;", 4)==0){
 116                                         txt[wrpos++] = '>';
 117                                         rdpos += 4;
 118                                 }else{
 119                                 */
 120                                         txt[wrpos++] = txt[rdpos++];
 121                                 //}
 122                         }
 123                 }
 124         }
 125         txt[wrpos] = 0;
 126         return wrpos;
 127 }
 128