[PATCH] Use gnulib's mbswidth module

[Miloslav Trmac]

Hello,
the attached patch against texinfo CVS modifies makeinfo to use the
mbswidth module from gnulib instead of using private string_width ().

mbswidth() requires mbrtowc (), while string_width () required only
mbtowc().  Therefore this patch requires newer a newer libc to support
multibyte characters; OTOH this allows correct handling of partial
multibyte characters when filling paragraphs.

To use the patch, import the mbswidth module from gnulib.

        * configure.ac: Remove unnecessary wcwidth () test.  Add missing
        setlocale () test.
        * makeinfo/makeinfo.c (string_width): Remove.
        * makeinfo/makeinfo.h (string_width): Remove declaration.

        * makeinfo/cmds.c (cm_center)
        * makeinfo/index.c (insert_index_output_line_no, cm_printindex):
        * makeinfo/makeinfo.c (do_flush_right_indentation)
        * makeinfo/multi.c (output_multitable_row): Use mbswidth () and
        mbsnwidth () instead of string_width ().

Thanks,
        Mirek

Index: configure.ac
===================================================================
RCS file: /sources/texinfo/texinfo/configure.ac,v
retrieving revision 1.67
diff -u -r1.67 configure.ac
--- configure.ac        27 Dec 2006 16:20:17 -0000      1.67
+++ configure.ac        24 Jan 2007 19:27:41 -0000
@@ -81,8 +81,8 @@
 # in theory only pre-sysvr3 systems needed this and it's not likely
 # that anyone compiling new texinfo still has such a thing? we'll see.
 # AC_FUNC_SETVBUF_REVERSED
-AC_CHECK_FUNCS(bzero getcwd memset setvbuf sigaction sigprocmask \
-               sigsetmask strchr wcwidth)
+AC_CHECK_FUNCS(bzero getcwd memset setlocale setvbuf sigaction sigprocmask \
+               sigsetmask strchr)
 AC_REPLACE_FUNCS(memcpy memmove strdup strerror)
 
 # We want to recognize djgpp to avoid the useless warning about no
Index: makeinfo/cmds.c
===================================================================
RCS file: /sources/texinfo/texinfo/makeinfo/cmds.c,v
retrieving revision 1.68
diff -u -r1.68 cmds.c
--- makeinfo/cmds.c     7 Jan 2007 22:59:08 -0000       1.68
+++ makeinfo/cmds.c     24 Jan 2007 19:27:41 -0000
@@ -19,6 +19,7 @@
    Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.  */
 
 #include "system.h"
+#include "mbswidth.h"
 #include "cmds.h"
 #include "defun.h"
 #include "files.h"
@@ -1545,7 +1546,7 @@
 
            output_paragraph_offset = ++i;
            length = output_paragraph_offset - start;
-          width = string_width ((char *)(output_paragraph + start), length);
+          width = mbsnwidth ((char *)(output_paragraph + start), length, 0);
 
            if (width < (fill_column - fudge_factor))
              {
Index: makeinfo/index.c
===================================================================
RCS file: /sources/texinfo/texinfo/makeinfo/index.c,v
retrieving revision 1.21
diff -u -r1.21 index.c
--- makeinfo/index.c    11 Dec 2006 14:59:59 -0000      1.21
+++ makeinfo/index.c    24 Jan 2007 19:27:41 -0000
@@ -19,6 +19,7 @@
    Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301, USA.  */
 
 #include "system.h"
+#include "mbswidth.h"
 #include "files.h"
 #include "footnote.h"
 #include "html.h"
@@ -673,11 +674,11 @@
     int i = output_paragraph_offset; 
     while (0 < i && output_paragraph[i-1] != '\n')
       i--;
-    last_column = string_width ((char *)(output_paragraph + i),
-                               output_paragraph_offset - i);
+    last_column = mbsnwidth ((char *)(output_paragraph + i),
+                            output_paragraph_offset - i, 0);
   }
 
-  out_line_no_width = string_width (out_line_no_str, strlen (out_line_no_str));
+  out_line_no_width = mbswidth (out_line_no_str, 0);
   if (last_column + out_line_no_width > fill_column)
     {
       insert ('\n');
@@ -895,7 +896,7 @@
                 {
                  int width;
 
-                 width = string_width (index->entry, strlen (index->entry));
+                 width = mbswidth (index->entry, 0);
                   sprintf (line, "* %*s  ", width < MIN_ENTRY_COLUMNS
                           ? -(strlen (index->entry)
                               + (MIN_ENTRY_COLUMNS - width))
Index: makeinfo/makeinfo.c
===================================================================
RCS file: /sources/texinfo/texinfo/makeinfo/makeinfo.c,v
retrieving revision 1.89
diff -u -r1.89 makeinfo.c
--- makeinfo/makeinfo.c 11 Dec 2006 14:59:59 -0000      1.89
+++ makeinfo/makeinfo.c 24 Jan 2007 19:27:42 -0000
@@ -22,6 +22,7 @@
 
 #include "system.h"
 #include "getopt.h"
+#include "mbswidth.h"
 
 #define COMPILING_MAKEINFO
 #include "makeinfo.h"
@@ -39,10 +40,6 @@
 #include "toc.h"
 #include "xml.h"
 
-#ifdef HAVE_WCWIDTH
-# include <wchar.h>
-#endif
-
 /* You can change some of the behavior of Makeinfo by changing the
    following defines: */
 
@@ -2463,45 +2460,6 @@
     }
 }
 
-/* Return the number of columns necessary for displaying STRING of LEN
-   bytes. */
-int
-string_width (const char *string, size_t length)
-{
-#ifdef HAVE_WCWIDTH
-  int width;
-
-  mbtowc (NULL, NULL, 0);
-  width = 0;
-  while (length > 0)
-    {
-      wchar_t wc;
-      int l, w;
-
-      l = mbtowc (&wc, string, length);
-      if (l == -1)
-       {
-         mbtowc (NULL, NULL, 0);
-         w = 1;
-         l = 1;
-       }
-      else
-       {
-         if (l == 0)
-           l = 1;
-         w = wcwidth (wc);
-         if (w == -1)
-           w = 1;
-       }
-      width += w;
-      string += l;
-      length -= l;
-    }
-  return width;
-#endif
-  return length;
-}
-
 /* Return the 0-based number of the current output column */
 int
 current_output_column (void)
@@ -2530,7 +2488,7 @@
        }
       if (i < j)
        {
-         column += string_width ((char *)(output_paragraph + i), j - i);
+         column += mbsnwidth ((char *)(output_paragraph + i), j - i, 0);
          i = j;
        }
       if (i < output_paragraph_offset)
@@ -2808,15 +2766,6 @@
        output_paragraph_offset++;
        column = current_output_column ();
        output_paragraph_offset--;
-       /* The string_width () in current_output_column () cannot predict
-          future incoming bytes.  So if output_paragraph ends in a partial
-          multibyte character, its bytes are counted as separate column
-          positions.  This may push column past fill_column, even though the
-          finished multibyte character would fit on the current line.
-
-          This is too hard to fix without modifying add_char () to recieve
-          complete multibyte characters at a time, and causes only slightly
-          incorrect paragraph filling, so we punt.  */
         if (column > fill_column)
           {
             if (filling_enabled && !html)
@@ -3211,7 +3160,8 @@
     {
       int width;
 
-      width = string_width((char *)output_paragraph, output_paragraph_offset);
+      width = mbsnwidth ((char *)output_paragraph, output_paragraph_offset - 1,
+                        0) + 1;
       if (width < fill_column)
         {
           int i;
Index: makeinfo/makeinfo.h
===================================================================
RCS file: /sources/texinfo/texinfo/makeinfo/makeinfo.h,v
retrieving revision 1.22
diff -u -r1.22 makeinfo.h
--- makeinfo/makeinfo.h 11 Dec 2006 14:59:59 -0000      1.22
+++ makeinfo/makeinfo.h 24 Jan 2007 19:27:42 -0000
@@ -369,7 +369,6 @@
   search_forward (char *string, int from),
   search_forward_until_pos (char *string, int from, int end_pos),
   next_nonwhitespace_character (void),
-  string_width (const char *string, size_t length),
   current_output_column (void),
   fs_error (char *filename);
 
Index: makeinfo/multi.c
===================================================================
RCS file: /sources/texinfo/texinfo/makeinfo/multi.c,v
retrieving revision 1.13
diff -u -r1.13 multi.c
--- makeinfo/multi.c    11 Dec 2006 14:59:59 -0000      1.13
+++ makeinfo/multi.c    24 Jan 2007 19:27:42 -0000
@@ -21,6 +21,7 @@
    Originally written by address@hidden (Paul Rubin).  */
 
 #include "system.h"
+#include "mbswidth.h"
 #include "cmds.h"
 #include "insertion.h"
 #include "makeinfo.h"
@@ -468,7 +469,7 @@
       /* Do not output trailing blanks if we're in the last column and
          there will be no trailing |.  */
       if (i < last_column && !vsep)
-        for (s = string_width ((char *)&CHAR_AT (0), j);
+        for (s = mbsnwidth ((char *)&CHAR_AT (0), j, 0);
             s <= envs[i].fill_column; s++)
           out_char (' ');
       if (vsep)