Rev 11132 | Details | Compare with Previous | Last modification | View Log | RSS feed
| Rev | Author | Line No. | Line |
|---|---|---|---|
| 10 | reyssat | 1 | /* Copyright (C) 1998-2003 XIAO, Gang of Universite de Nice - Sophia Antipolis |
| 2 | * |
||
| 3 | * This program is free software; you can redistribute it and/or modify |
||
| 4 | * it under the terms of the GNU General Public License as published by |
||
| 5 | * the Free Software Foundation; either version 2 of the License, or |
||
| 6 | * (at your option) any later version. |
||
| 7 | * |
||
| 8 | * This program is distributed in the hope that it will be useful, |
||
| 9 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
||
| 10 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the |
||
| 11 | * GNU General Public License for more details. |
||
| 12 | * |
||
| 13 | * You should have received a copy of the GNU General Public License |
||
| 14 | * along with this program; if not, write to the Free Software |
||
| 15 | * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. |
||
| 16 | */ |
||
| 17 | |||
| 7676 | bpr | 18 | /* Extract text from phtml file */ |
| 10 | reyssat | 19 | |
| 20 | /*************** Customization: change values hereafter ****************/ |
||
| 21 | |||
| 7676 | bpr | 22 | /* limit of data buffers */ |
| 10 | reyssat | 23 | #define buflim 1024*1024*16 |
| 24 | |||
| 25 | /***************** Nothing should need change hereafter *****************/ |
||
| 26 | |||
| 27 | #include "../Lib/libwims.h" |
||
| 28 | char filename[1024]=""; |
||
| 29 | char *filebuf; |
||
| 30 | int filelen=0; |
||
| 31 | |||
| 7676 | bpr | 32 | /* get the file */ |
| 10 | reyssat | 33 | void prepare_file(void) |
| 34 | { |
||
| 12248 | bpr | 35 | FILE *f; |
| 36 | long int flen; |
||
| 10 | reyssat | 37 | |
| 12248 | bpr | 38 | filelen=0; |
| 39 | f=fopen(filename,"r"); if(f==NULL) return; |
||
| 40 | fseek(f,0,SEEK_END);flen=ftell(f); fseek(f,0,SEEK_SET); |
||
| 41 | if(flen>buflim) return; |
||
| 42 | filebuf=xmalloc(2*flen+1024);flen=fread(filebuf,1,flen,f); |
||
| 43 | fclose(f); |
||
| 44 | if(flen>0 && flen<buflim) filebuf[flen]=0; else flen=0; |
||
| 45 | filelen=flen; |
||
| 10 | reyssat | 46 | } |
| 47 | |||
| 48 | void processbuf(void) |
||
| 49 | { |
||
| 12248 | bpr | 50 | char *p; |
| 51 | deaccent(filebuf); |
||
| 52 | for(p=filebuf; *p; p++) *p=tolower(*p); |
||
| 53 | for(p=strpbrk(filebuf,"'-"); p!=NULL; p=strpbrk(p+1,"'-")) *p=' '; |
||
| 54 | for(p=strstr(filebuf," "); p!=NULL; p=strstr(p+1," ")) { |
||
| 55 | *p=' '; ovlstrcpy(p+1,p+6); |
||
| 56 | } |
||
| 10 | reyssat | 57 | } |
| 58 | |||
| 59 | void output(void) |
||
| 60 | { |
||
| 12248 | bpr | 61 | char *p, *pp, lastc; |
| 62 | p=find_word_start(filebuf); lastc=0; |
||
| 63 | if(*p=='!' || *p==':') goto cont1; |
||
| 64 | for(;*p;p++) { |
||
| 65 | if(*p=='\n') { |
||
| 66 | if(!isspace(lastc)) {printf(" "); lastc=' ';} |
||
| 67 | cont2: p=find_word_start(p); |
||
| 68 | if(*p=='!' || *p==':') { |
||
| 69 | if(lastc!=' ') printf(". "); |
||
| 70 | lastc=' '; |
||
| 71 | cont1: p=strchr(p,'\n'); |
||
| 72 | if(p==NULL) return; |
||
| 73 | if(*(p-1)=='\\') {p++; goto cont1;} |
||
| 74 | goto cont2; |
||
| 7676 | bpr | 75 | } |
| 12248 | bpr | 76 | for(pp=p; isalnum(*pp) || *pp=='_' || *pp=='$'; pp++); |
| 77 | pp=find_word_start(pp); |
||
| 78 | if(*pp=='=') goto cont1; |
||
| 79 | } |
||
| 80 | if(*p=='\\' && *(p+1)=='\n') { |
||
| 81 | printf("\n"); p++; continue; |
||
| 82 | } |
||
| 83 | if(*p=='<' && (isalpha(*(p+1)) || *(p+1)=='/')) { |
||
| 84 | p=strchr(p,'>'); goto nextp; |
||
| 85 | } |
||
| 86 | if(*p=='$') { |
||
| 87 | if(lastc != ' ') { |
||
| 88 | if(!isspace(lastc)) printf(" "); |
||
| 89 | printf(". "); lastc=' '; |
||
| 7676 | bpr | 90 | } |
| 12248 | bpr | 91 | p++; |
| 92 | if(*p=='(') {p=find_matching(p+1,')'); goto nextp;} |
||
| 93 | if(*p=='[') {p=find_matching(p+1,']'); goto nextp;} |
||
| 94 | while(isalnum(*p) || *p=='_') p++; |
||
| 95 | p--; continue; |
||
| 96 | } |
||
| 97 | if(*p=='&') { |
||
| 98 | char *p2; |
||
| 99 | for(p2=p+1; isalnum(*p2) || *p2=='#'; p2++); |
||
| 100 | if(*p2==';') { |
||
| 101 | p++; if(isalpha(*p)) {printf("%c",*p); lastc=*p;} |
||
| 102 | p=p2; continue; |
||
| 7676 | bpr | 103 | } |
| 12248 | bpr | 104 | } |
| 105 | if(!isspace(*p) && strchr(":!?.;,\"()[]{}=/\\+*^%@~`<>|",*p)==NULL) |
||
| 106 | {printf("%c",*p); lastc=*p;} |
||
| 107 | else { |
||
| 108 | if(isspace(*p) && !isspace(lastc)) { |
||
| 109 | printf(" "); lastc=' '; |
||
| 7676 | bpr | 110 | } |
| 12248 | bpr | 111 | if(!isspace(*p)) { |
| 112 | switch(lastc) { |
||
| 113 | case ' ': printf(". "); lastc=' '; break; |
||
| 114 | case ' ': break; |
||
| 115 | default: printf(" . "); lastc=' '; break; |
||
| 116 | } |
||
| 7676 | bpr | 117 | } |
| 10 | reyssat | 118 | } |
| 12248 | bpr | 119 | nextp: if(p==NULL || *p==0) break; |
| 120 | } |
||
| 10 | reyssat | 121 | } |
| 122 | |||
| 123 | int main(int argc, char *argv[]) |
||
| 124 | { |
||
| 12248 | bpr | 125 | if(argc<=1) return 0; |
| 126 | snprintf(filename,sizeof(filename)-128,"%s",argv[1]); |
||
| 127 | prepare_file(); |
||
| 128 | processbuf(); |
||
| 129 | output(); |
||
| 130 | return 0; |
||
| 10 | reyssat | 131 | } |
| 132 |