Character-encoding checked for all text (arguments/values).

diff --git a/argv.c b/argv.c
index e9eafffcc09cc5d36a373e519b3aec2de7dc9381..663d5d5e3220056bebac506b29f1e433eef605f1 100644 (file)
--- a/argv.c
+++ b/argv.c
@@ -1,4 +1,4 @@
-/* $Id: argv.c,v 1.30 2009/02/24 11:43:13 kristaps Exp $ */
+/* $Id: argv.c,v 1.31 2009/02/24 13:46:54 kristaps Exp $ */
 /*
  * Copyright (c) 2008 Kristaps Dzonsons <kristaps@kth.se>
  *
@@ -267,7 +267,7 @@ static int
 args(struct mdoc *mdoc, int line, 
                int *pos, char *buf, int fl, char **v)
 {
-       int               i, c;
+       int               i;
        char             *p, *pp;
 
        assert(*pos > 0);
@@ -290,14 +290,11 @@ args(struct mdoc *mdoc, int line,
         */
 
        if ((fl & ARGS_DELIM) && mdoc_iscdelim(buf[*pos])) {
-               for (i = *pos; (c = buf[i]); ) {
-                       if ( ! mdoc_iscdelim(c))
+               for (i = *pos; buf[i]; ) {
+                       if ( ! mdoc_iscdelim(buf[i]))
                                break;
                        i++;
-                       if (0 == buf[i] || ! isspace(c))
-                               break;
-                       i++;
-                       while (buf[i] && isspace(c))
+                       while (buf[i] && isspace((int)buf[i]))
                                i++;
                }
                if (0 == buf[i]) {
@@ -404,8 +401,8 @@ args(struct mdoc *mdoc, int line,
                /* Do non-tabsep look-ahead here. */
                
                if ( ! (ARGS_TABSEP & fl))
-                       while ((c = buf[*pos])) {
-                               if (isspace(c))
+                       while (buf[*pos]) {
+                               if (isspace((int)buf[*pos]))
                                        if ('\\' != buf[*pos - 1])
                                                break;
                                (*pos)++;

diff --git a/mdoc.3 b/mdoc.3
index 059d8cf5973857240c22451f4b5545a958cff553..0adf9302fc0c084aa7331e8d47bbfdb834c25617 100644 (file)
--- a/mdoc.3
+++ b/mdoc.3
@@ -1,4 +1,4 @@
-.\" $Id: mdoc.3,v 1.9 2009/02/23 15:19:47 kristaps Exp $
+.\" $Id: mdoc.3,v 1.10 2009/02/24 13:46:54 kristaps Exp $
 .\"
 .\" Copyright (c) 2009 Kristaps Dzonsons <kristaps@kth.se>
 .\"
@@ -16,7 +16,7 @@
 .\" TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
 .\" PERFORMANCE OF THIS SOFTWARE.
 .\" 
-.Dd $Mdocdate: February 23 2009 $
+.Dd $Mdocdate: February 24 2009 $
 .Dt mdoc 3
 .Os
 .\" SECTION
@@ -89,7 +89,9 @@ This section further defines the
 .Sx Functions 
 and
 .Sx Variables
-available to programmers.  The last sub-section,
+available to programmers.  Following that,
+.Sx Character Encoding
+describes input format.  Lastly, 
 .Sx Abstract Syntax Tree ,
 documents the output tree.
 .\" SUBSECTION
@@ -174,6 +176,21 @@ An array of string-ified token names.
 An array of string-ified token argument names.
 .El
 .\" SUBSECTION
+.Ss Character Encoding
+The
+.Xr mdoc 3
+library accepts only printable ASCII characters as defined by
+.Xr isprint 3 .
+Non-ASCII character sequences are escaped with an escape character 
+.Sq \\
+and followed by either an open-parenthesis 
+.Sq \&(
+for two-character sequences; an open-bracket
+.Sq \&[
+for n-character sequences (terminated at a close-bracket
+.Sq \&] ) ;
+or one of a small set of single characters for other escapes.
+.\" SUBSECTION
 .Ss Abstract Syntax Tree
 The 
 .Nm

diff --git a/strings.c b/strings.c
index c3b0403d6ce31fb3377a9e5572efdfdb472e8a99..fe400b37fcf1ada01de2495702db64f76f7fffab 100644 (file)
--- a/strings.c
+++ b/strings.c
@@ -1,4 +1,4 @@
-/* $Id: strings.c,v 1.16 2009/02/24 11:43:13 kristaps Exp $ */
+/* $Id: strings.c,v 1.17 2009/02/24 13:46:54 kristaps Exp $ */
 /*
  * Copyright (c) 2008 Kristaps Dzonsons <kristaps@kth.se>
  *
@@ -55,14 +55,16 @@ mdoc_isescape(const char *p)
                /* FALLTHROUGH */
        case (' '):
                /* FALLTHROUGH */
+       case ('&'):
+               /* FALLTHROUGH */
        case ('.'):
                /* FALLTHROUGH */
        case ('e'):
                return(2);
        case ('('):
-               if (0 == *++p)
+               if (0 == *++p || ! isgraph(*p))
                        return(0);
-               if (0 == *++p)
+               if (0 == *++p || ! isgraph(*p))
                        return(0);
                return(4);
        case ('['):
@@ -72,7 +74,7 @@ mdoc_isescape(const char *p)
        }
 
        for (c = 3, p++; *p && ']' != *p; p++, c++)
-               if (isspace(*p))
+               if ( ! isgraph(*p))
                        break;
 
        return(*p == ']' ? c : 0);

diff --git a/term.c b/term.c
index 46514e4d1ccdd8694eee75af134d45ca0b32f21a..4d3be795394fd3822e5d0125eaffcffdbbcc9923 100644 (file)
--- a/term.c
+++ b/term.c
@@ -1,4 +1,4 @@
-/* $Id: term.c,v 1.12 2009/02/23 15:19:47 kristaps Exp $ */
+/* $Id: term.c,v 1.13 2009/02/24 13:46:54 kristaps Exp $ */
 /*
  * Copyright (c) 2009 Kristaps Dzonsons <kristaps@kth.se>
  *
@@ -1054,7 +1054,7 @@ termp_sq_pre(DECL_ARGS)
 
        if (MDOC_BODY != node->type)
                return(1);
-       word(p, "`");
+       word(p, "\'");
        p->flags |= TERMP_NOSPACE;
        return(1);
 }

diff --git a/validate.c b/validate.c
index cbc02554e83d13dd9c9bea636590522347d1de45..439a232d1030a6aad9e9f66fd88e85031763c7c8 100644 (file)
--- a/validate.c
+++ b/validate.c
@@ -1,4 +1,4 @@
-/* $Id: validate.c,v 1.55 2009/02/24 12:20:52 kristaps Exp $ */
+/* $Id: validate.c,v 1.56 2009/02/24 13:46:54 kristaps Exp $ */
 /*
  * Copyright (c) 2008 Kristaps Dzonsons <kristaps@kth.se>
  *
@@ -17,6 +17,7 @@
  * PERFORMANCE OF THIS SOFTWARE.
  */
 #include <assert.h>
+#include <ctype.h>
 #include <stdlib.h>
 
 #include "private.h"
@@ -396,6 +397,9 @@ check_text(struct mdoc *mdoc, size_t line, size_t pos, const char *p)
        size_t           c;
 
        for ( ; *p; p++) {
+               if ( ! isprint(*p) && '\t' != *p)
+                       return(mdoc_perr(mdoc, line, pos,
+                                       "invalid characters"));
                if ('\\' != *p)
                        continue;
                if ((c = mdoc_isescape(p))) {
@@ -403,7 +407,7 @@ check_text(struct mdoc *mdoc, size_t line, size_t pos, const char *p)
                        continue;
                }
                return(mdoc_perr(mdoc, line, pos,
-                               "invalid escape sequence"));
+                                       "invalid escape sequence"));
        }
 
        return(1);