Logo Search packages:      
Sourcecode: unhtml version File versions

esc.c

#define DEBUG 0        /* 1:dummy main 2:numerical ascii codes off */ 

#include "esc.h"
#include <stdio.h>
#include <stdlib.h>
#include <ctype.h>

#define THRU    0       /* THRU mode simply prints chars */ 
#define HOLD    1       /* HOLD mode stocks chars in bff[] */
#define MXBF    7       /* length of longest escape sequence excluding '&' */
#define CHARSET 256     /* set to 256 if ISO-8859-1 (European) */

static int  scmp(char *, char *);
static int  flush(int);

static int  mode=THRU;
static char bff[MXBF];
static int  index=0;

#if DEBUG == 1  /* dummy main */
void main(){
char ch;
while( (ch=getchar()) != EOF)
       m_putchar(ch);
       m_putchar(EOF);
}
#endif

struct table {
        char * seq;
        int n;
}       ktbl[] = {
{"gt;"     ,   62},
{"lt;"     ,   60},
{"amp;"    ,   38},
{"quot;"   ,   34},
#if         CHARSET == 128
{"nbsp;"   ,   32},
{"shy;"    ,   45},
#elif       CHARSET == 256
{"nbsp;"   ,  160},
{"iexcl;"  ,  161},
{"cent;"   ,  162},
{"pound;"  ,  163},
{"curren;" ,  164},
{"yen;"    ,  165},
{"brvbar;" ,  166},
{"sect;"   ,  167},
{"uml;"    ,  168},
{"copy;"   ,  169},
{"ordf;"   ,  170},
{"laquo;"  ,  171},
{"not;"    ,  172},
{"shy;"    ,  173},
{"reg;"    ,  174},
{"macr;"   ,  175},
{"deg;"    ,  176},
{"plusmn;" ,  177},
{"sup2;"   ,  178},
{"sup3;"   ,  179},
{"acute;"  ,  180},
{"micro;"  ,  181},
{"para;"   ,  182},
{"middot;" ,  183},
{"cedil;"  ,  184},
{"sup1;"   ,  185},
{"ordm;"   ,  186},
{"raquo;"  ,  187},
{"frac14;" ,  188},
{"frac12;" ,  189},
{"frac34;" ,  190},
{"iquest;" ,  191},
{"Agrave;" ,  192},
{"Aacute;" ,  193},
{"Acirc;"  ,  194},
{"Atilde;" ,  195},
{"Auml;"   ,  196},
{"Aring;"  ,  197},
{"AElig;"  ,  198},
{"Ccedil;" ,  199},
{"Egrave;" ,  200},
{"Eacute;" ,  201},
{"Ecirc;"  ,  202},
{"Euml;"   ,  203},
{"Igrave;" ,  204},
{"Iacute;" ,  205},
{"Icirc;"  ,  206},
{"Iuml;"   ,  207},
{"ETH;"    ,  208},
{"Ntilde;" ,  209},
{"Ograve;" ,  210},
{"Oacute;" ,  211},
{"Ocirc;"  ,  212},
{"Otilde;" ,  213},
{"Ouml;"   ,  214},
{"times;"  ,  215},
{"Oslash;" ,  216},
{"Ugrave;" ,  217},
{"Uacute;" ,  218},
{"Ucirc;"  ,  219},
{"Uuml;"   ,  220},
{"Yacute;" ,  221},
{"THORN;"  ,  222},
{"szlig;"  ,  223},
{"agrave;" ,  224},
{"aacute;" ,  225},
{"acirc;"  ,  226},
{"atilde;" ,  227},
{"auml;"   ,  228},
{"aring;"  ,  229},
{"aelig;"  ,  230},
{"ccedil;" ,  231},
{"egrave;" ,  232},
{"eacute;" ,  233},
{"ecirc;"  ,  234},
{"euml;"   ,  235},
{"igrave;" ,  236},
{"iacute;" ,  237},
{"icirc;"  ,  238},
{"iuml;"   ,  239},
{"eth;"    ,  240},
{"ntilde;" ,  241},
{"ograve;" ,  242},
{"oacute;" ,  243},
{"ocirc;"  ,  244},
{"otilde;" ,  245},
{"ouml;"   ,  246},
{"divide;" ,  247},
{"oslash;" ,  248},
{"ugrave;" ,  249},
{"uacute;" ,  250},
{"ucirc;"  ,  251},
{"uuml;"   ,  252},
{"yacute;" ,  253},
{"thorn;"  ,  254},
{"yuml;"   ,  255},
#endif
{""        ,    0}
};

int
m_putchar(int chr){
struct table *ptr;
if ( mode == THRU ) switch (chr){
      case '&': mode=HOLD; return '&';
      case EOF: return EOF;
      default : return putchar(chr);  /* most chars pass through here */
        }

/*   mode == HOLD   */
else switch (chr) {
      case '&': return flush(HOLD);
      case EOF: return flush(THRU);
      case ';': bff[index++]=';';     /* delimiter */
              for(ptr=ktbl; !scmp(ptr->seq,bff); ptr++)
                  ;
              chr= ptr->n;          /* chr == 0 if no match */
#if DEBUG == 0 || DEBUG == 2
              if(chr==0 && bff[0]=='#')    /* numerical ascii code */
 /* without the following strong tests seqs like "&#14K;" would fall through */
                  {
                  if( (bff[1]=='X' || bff[1]=='x')
                        && isxdigit(bff[2]) && isxdigit(bff[3]) )
                              /* hexadecimal */
                              /* /&#[Xx][0-9A-Da-d][0-9A-Da-d];/ */
                        chr=strtoul( &bff[2], NULL, 16 );

                  else if( (bff[2]==';'
                          && isdigit(bff[1]) ) 
                              /* decimal */
                              /* /&#[0-9];/ */
                       ||      (bff[3]==';'
                          && isdigit(bff[1]) && isdigit(bff[2]) )
                              /* decimal */
                              /* /&#[0-9][0-9];/ */
                       ||  (bff[4]==';'
                          && (bff[1]=='1' || bff[1]=='2')
                          && isdigit(bff[2]) && isdigit(bff[3]) ) 
                              /* decimal */
                              /* /&#[12][0-9][0-9];/ */
                                )
                        chr=strtoul( &bff[1], NULL, 10);
                  }
#endif
              if( ( chr<0 ) || ( chr==0) 
              ||  (   0<=chr && chr<=  8 )  ||  (  11<=chr && chr<= 12 )
              ||  (  14<=chr && chr<= 31 )  ||  ( 127<=chr && chr<=159 )
              ||  ( CHARSET<=chr ) 
                )  return flush(THRU); /* no match or undefined */

              else { index=0; mode=THRU; return putchar(chr); }
              /* print converted character */

      default : bff[index++]=chr;
              return(index==MXBF)?flush(THRU):chr;
        }
}


static int
flush(int md){          /* sends chars in bff to output stream */
      int r;   int idx;
      register int i;
      idx=index; index=0; mode=md;
      if((r=putchar('&'))==EOF) return EOF;
      for(i=0;i<idx;i++)
            if((r=putchar(bff[i]))==EOF) return EOF;
      return r;
}

static int
scmp(char *s1, char *s2){              /* compares 2 strings */
while (1)
        {
      if(*s1   == '\0'  ) return 1; /* note that only s1 is checked */
      if(*s1++ != *s2++ ) return 0;
        }
}
/* returns 1 if s1 points to an empty string "" */

Generated by  Doxygen 1.6.0   Back to index