rewrite the main mdoc text parser, mdoc_ptext(),

making it easier to understand and fixing various bugs:
* correctly strip whitespace from the end of text lines
* issue consistent warnings regarding trailing spaces and tabs
* escaped backslashes no longer escape the following character
ok kristaps@

diff --git a/mdoc.c b/mdoc.c
index 1fb6372d5eeb68586460190e24d6c23d1420cb4b..19920954863f2bc95173aa1a0f201b18e4a2652c 100644 (file)
--- a/mdoc.c
+++ b/mdoc.c
@@ -1,4 +1,4 @@
-/*     $Id: mdoc.c,v 1.136 2010/05/17 22:11:42 kristaps Exp $ */
+/*     $Id: mdoc.c,v 1.137 2010/05/24 13:39:47 schwarze Exp $ */
 /*
  * Copyright (c) 2008, 2009 Kristaps Dzonsons <kristaps@kth.se>
  *
@@ -542,7 +542,7 @@ mdoc_node_delete(struct mdoc *m, struct mdoc_node *p)
 static int
 mdoc_ptext(struct mdoc *m, int line, char *buf, int offs)
 {
-       int              i;
+       char            *c, *ws, *end;
 
        /* Ignore bogus comments. */
 
@@ -556,18 +556,51 @@ mdoc_ptext(struct mdoc *m, int line, char *buf, int offs)
        if (SEC_NONE == m->lastnamed)
                return(mdoc_pmsg(m, line, offs, MANDOCERR_NOTEXT));
 
-       /* Literal just gets pulled in as-is. */
-       
-       if (MDOC_LITERAL & m->flags)
-               return(mdoc_word_alloc(m, line, offs, buf + offs));
-
-       /* Check for a blank line, which may also consist of spaces. */
+       /*
+        * Search for the beginning of unescaped trailing whitespace (ws)
+        * and for the first character not to be output (end).
+        */
+       ws = NULL;
+       for (c = end = buf + offs; *c; c++) {
+               switch (*c) {
+               case ' ':
+                       if (NULL == ws)
+                               ws = c;
+                       continue;
+               case '\t':
+                       /*
+                        * Always warn about trailing tabs,
+                        * even outside literal context,
+                        * where they should be put on the next line.
+                        */
+                       if (NULL == ws)
+                               ws = c;
+                       /*
+                        * Strip trailing tabs in literal context only;
+                        * outside, they affect the next line.
+                        */
+                       if (MDOC_LITERAL & m->flags)
+                               continue;
+                       break;
+               case '\\':
+                       /* Skip the escaped character, too, if any. */
+                       if (c[1])
+                               c++;
+                       /* FALLTHROUGH */
+               default:
+                       ws = NULL;
+                       break;
+               }
+               end = c + 1;
+       }
+       *end = '\0';
 
-       for (i = offs; ' ' == buf[i]; i++)
-               /* Skip to first non-space. */ ;
+       if (ws)
+               if ( ! mdoc_pmsg(m, line, (int)(ws-buf), MANDOCERR_EOLNSPACE))
+                       return(0);
 
-       if ('\0' == buf[i]) {
-               if ( ! mdoc_pmsg(m, line, offs, MANDOCERR_NOBLANKLN))
+       if ('\0' == buf[offs] && ! (MDOC_LITERAL & m->flags)) {
+               if ( ! mdoc_pmsg(m, line, (int)(c-buf), MANDOCERR_NOBLANKLN))
                        return(0);
 
                /*
@@ -582,41 +615,21 @@ mdoc_ptext(struct mdoc *m, int line, char *buf, int offs)
                return(1);
        }
 
-       /* 
-        * Warn if the last un-escaped character is whitespace. Then
-        * strip away the remaining spaces (tabs stay!).   
-        */
-
-       i = (int)strlen(buf);
-       assert(i);
-
-       if (' ' == buf[i - 1] || '\t' == buf[i - 1]) {
-               if (i > 1 && '\\' != buf[i - 2])
-                       if ( ! mdoc_pmsg(m, line, i - 1, MANDOCERR_EOLNSPACE))
-                               return(0);
-
-               for (--i; i && ' ' == buf[i]; i--)
-                       /* Spin back to non-space. */ ;
-
-               /* Jump ahead of escaped whitespace. */
-               i += '\\' == buf[i] ? 2 : 1;
-
-               buf[i] = '\0';
-       }
-
-       /* Allocate the whole word. */
-
-       if ( ! mdoc_word_alloc(m, line, offs, buf + offs))
+       if ( ! mdoc_word_alloc(m, line, offs, buf+offs))
                return(0);
 
+       if (MDOC_LITERAL & m->flags)
+               return(1);
+
        /*
         * End-of-sentence check.  If the last character is an unescaped
         * EOS character, then flag the node as being the end of a
         * sentence.  The front-end will know how to interpret this.
         */
 
-       assert(i);
-       if (mandoc_eos(buf, (size_t)i))
+       assert(buf < end);
+
+       if (mandoc_eos(buf+offs, (size_t)(end-buf-offs)))
                m->last->flags |= MDOC_EOS;
 
        return(1);