Print this page
5051 import mdocml-1.12.3
Reviewed by: Yuri Pankov <yuri.pankov@nexenta.com>
Approved by: TBD

@@ -1,9 +1,9 @@
-/*      $Id: html.c,v 1.150 2011/10/05 21:35:17 kristaps Exp $ */
+/*      $Id: html.c,v 1.152 2013/08/08 20:07:47 schwarze Exp $ */
 /*
  * Copyright (c) 2008, 2009, 2010, 2011 Kristaps Dzonsons <kristaps@bsd.lv>
- * Copyright (c) 2011 Ingo Schwarze <schwarze@openbsd.org>
+ * Copyright (c) 2011, 2012, 2013 Ingo Schwarze <schwarze@openbsd.org>
  *
  * Permission to use, copy, modify, and distribute this software for any
  * purpose with or without fee is hereby granted, provided that the above
  * copyright notice and this permission notice appear in all copies.
  *

@@ -233,10 +233,13 @@
                 font = HTMLFONT_ITALIC;
                 break;
         case (ESCAPE_FONTBOLD):
                 font = HTMLFONT_BOLD;
                 break;
+        case (ESCAPE_FONTBI):
+                font = HTMLFONT_BI;
+                break;
         case (ESCAPE_FONT):
                 /* FALLTHROUGH */
         case (ESCAPE_FONTROMAN):
                 font = HTMLFONT_NONE;
                 break;

@@ -251,21 +254,31 @@
         }
 
         h->metal = h->metac;
         h->metac = font;
 
-        if (HTMLFONT_NONE != font)
-                h->metaf = HTMLFONT_BOLD == font ?
-                        print_otag(h, TAG_B, 0, NULL) :
+        switch (font) {
+        case (HTMLFONT_ITALIC):
+                h->metaf = print_otag(h, TAG_I, 0, NULL);
+                break;
+        case (HTMLFONT_BOLD):
+                h->metaf = print_otag(h, TAG_B, 0, NULL);
+                break;
+        case (HTMLFONT_BI):
+                h->metaf = print_otag(h, TAG_B, 0, NULL);
                         print_otag(h, TAG_I, 0, NULL);
+                break;
+        default:
+                break;
+        }
 }
 
 int
 html_strlen(const char *cp)
 {
-        int              ssz, sz;
-        const char      *seq, *p;
+        size_t           rsz;
+        int              skip, sz;
 
         /*
          * Account for escaped sequences within string length
          * calculations.  This follows the logic in term_strlen() as we
          * must calculate the width of produced strings.

@@ -272,30 +285,45 @@
          * Assume that characters are always width of "1".  This is
          * hacky, but it gets the job done for approximation of widths.
          */
 
         sz = 0;
-        while (NULL != (p = strchr(cp, '\\'))) {
-                sz += (int)(p - cp);
-                ++cp;
-                switch (mandoc_escape(&cp, &seq, &ssz)) {
+        skip = 0;
+        while (1) {
+                rsz = strcspn(cp, "\\");
+                if (rsz) {
+                        cp += rsz;
+                        if (skip) {
+                                skip = 0;
+                                rsz--;
+                        }
+                        sz += rsz;
+                }
+                if ('\0' == *cp)
+                        break;
+                cp++;
+                switch (mandoc_escape(&cp, NULL, NULL)) {
                 case (ESCAPE_ERROR):
                         return(sz);
                 case (ESCAPE_UNICODE):
                         /* FALLTHROUGH */
                 case (ESCAPE_NUMBERED):
                         /* FALLTHROUGH */
                 case (ESCAPE_SPECIAL):
+                        if (skip)
+                                skip = 0;
+                        else
                         sz++;
                         break;
+                case (ESCAPE_SKIPCHAR):
+                        skip = 1;
+                        break;
                 default:
                         break;
                 }
         }
-
-        assert(sz >= 0);
-        return(sz + strlen(cp));
+        return(sz);
 }
 
 static int
 print_encode(struct html *h, const char *p, int norecurse)
 {

@@ -306,10 +334,16 @@
         static const char rejs[6] = { '\\', '<', '>', '&', ASCII_HYPH, '\0' };
 
         nospace = 0;
 
         while ('\0' != *p) {
+                if (HTML_SKIPCHAR & h->flags && '\\' != *p) {
+                        h->flags &= ~HTML_SKIPCHAR;
+                        p++;
+                        continue;
+                }
+
                 sz = strcspn(p, rejs);
 
                 fwrite(p, 1, sz, stdout);
                 p += (int)sz;
 

@@ -336,10 +370,37 @@
                 esc = mandoc_escape(&p, &seq, &len);
                 if (ESCAPE_ERROR == esc)
                         break;
 
                 switch (esc) {
+                case (ESCAPE_FONT):
+                        /* FALLTHROUGH */
+                case (ESCAPE_FONTPREV):
+                        /* FALLTHROUGH */
+                case (ESCAPE_FONTBOLD):
+                        /* FALLTHROUGH */
+                case (ESCAPE_FONTITALIC):
+                        /* FALLTHROUGH */
+                case (ESCAPE_FONTBI):
+                        /* FALLTHROUGH */
+                case (ESCAPE_FONTROMAN):
+                        if (0 == norecurse)
+                                print_metaf(h, esc);
+                        continue;
+                case (ESCAPE_SKIPCHAR):
+                        h->flags |= HTML_SKIPCHAR;
+                        continue;
+                default:
+                        break;
+                }
+
+                if (h->flags & HTML_SKIPCHAR) {
+                        h->flags &= ~HTML_SKIPCHAR;
+                        continue;
+                }
+
+                switch (esc) {
                 case (ESCAPE_UNICODE):
                         /* Skip passed "u" header. */
                         c = mchars_num2uc(seq + 1, len - 1);
                         if ('\0' != c)
                                 printf("&#x%x;", c);

@@ -354,23 +415,10 @@
                         if (c > 0)
                                 printf("&#%d;", c);
                         else if (-1 == c && 1 == len)
                                 putchar((int)*seq);
                         break;
-                case (ESCAPE_FONT):
-                        /* FALLTHROUGH */
-                case (ESCAPE_FONTPREV):
-                        /* FALLTHROUGH */
-                case (ESCAPE_FONTBOLD):
-                        /* FALLTHROUGH */
-                case (ESCAPE_FONTITALIC):
-                        /* FALLTHROUGH */
-                case (ESCAPE_FONTROMAN):
-                        if (norecurse)
-                                break;
-                        print_metaf(h, esc);
-                        break;
                 case (ESCAPE_NOSPACE):
                         if ('\0' == *p)
                                 nospace = 1;
                         break;
                 default:

@@ -509,14 +557,24 @@
                 } else
                         printf("&#160;");
         }
 
         assert(NULL == h->metaf);
-        if (HTMLFONT_NONE != h->metac)
-                h->metaf = HTMLFONT_BOLD == h->metac ?
-                        print_otag(h, TAG_B, 0, NULL) :
+        switch (h->metac) {
+        case (HTMLFONT_ITALIC):
+                h->metaf = print_otag(h, TAG_I, 0, NULL);
+                break;
+        case (HTMLFONT_BOLD):
+                h->metaf = print_otag(h, TAG_B, 0, NULL);
+                break;
+        case (HTMLFONT_BI):
+                h->metaf = print_otag(h, TAG_B, 0, NULL);
                         print_otag(h, TAG_I, 0, NULL);
+                break;
+        default:
+                break;
+        }
 
         assert(word);
         if ( ! print_encode(h, word, 0)) {
                 if ( ! (h->flags & HTML_NONOSPACE))
                         h->flags &= ~HTML_NOSPACE;