about summary refs log tree commit diff
diff options
context:
space:
mode:
-rw-r--r--ChangeLog11
-rw-r--r--iconv/gconv_trans.c35
-rw-r--r--locale/C-ctype.c6
-rw-r--r--locale/categories.def52
-rw-r--r--locale/langinfo.h2
-rw-r--r--locale/programs/ld-ctype.c24
-rw-r--r--localedata/tst-trans.c7
7 files changed, 130 insertions, 7 deletions
diff --git a/ChangeLog b/ChangeLog
index fd3bb20c20..165f1bca35 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,5 +1,16 @@
 2000-06-16  Ulrich Drepper  <drepper@redhat.com>
 
+	* locale/langinfo.h: Add entries for default_missing information.
+	* locale/C-ctype.c: Add initializers for new fields.
+	* iconv/gconv_trans.c: If nothing matched, try to use default_missing
+	information.
+	* locale/categories.h: Add entries for all LC_CTYPE values.
+	* locale/programs/ld-ctype.c (ctype_output): Write out default_missing
+	information.
+
+	* localedata/tst-trans.c: Write out an error message if class is
+	not found.
+
 	* iconv/gconv_int.h (norm_add_slashes): Optionally add given suffix.
 	* iconv/gconv_open.c: Remove error handling specification from `from'
 	character set name.
diff --git a/iconv/gconv_trans.c b/iconv/gconv_trans.c
index 829ff5f981..0bb5f00c07 100644
--- a/iconv/gconv_trans.c
+++ b/iconv/gconv_trans.c
@@ -44,12 +44,13 @@ __gconv_transliterate (struct __gconv_step *step,
   uint32_t *winbufend;
   uint_fast32_t low;
   uint_fast32_t high;
+  uint32_t *default_missing;
 
   /* If there is no transliteration information in the locale don't do
      anything and return the error.  */
   size = _NL_CURRENT_WORD (LC_CTYPE, _NL_CTYPE_TRANSLIT_HASH_SIZE);
   if (size == 0)
-    return __GCONV_ILLEGAL_INPUT;
+    goto no_rules;
 
   /* Get the rest of the values.  */
   layers = _NL_CURRENT_WORD (LC_CTYPE, _NL_CTYPE_TRANSLIT_HASH_LAYERS);
@@ -141,6 +142,38 @@ __gconv_transliterate (struct __gconv_step *step,
 	high = idx;
     }
 
+  /* One last chance: use the default replacement.  */
+ no_rules:
+  default_missing = (uint32_t *)
+    _NL_CURRENT (LC_CTYPE, _NL_CTYPE_TRANSLIT_DEFAULT_MISSING);
+  if (default_missing[0] != L'\0')
+    {
+      const unsigned char *toinptr = (const unsigned char *) default_missing;
+      uint32_t len = _NL_CURRENT_WORD (LC_CTYPE,
+				       _NL_CTYPE_TRANSLIT_DEFAULT_MISSING_LEN);
+      int res;
+
+      res = DL_CALL_FCT (step->__fct,
+			 (step, step_data, &toinptr,
+			  (const unsigned char *) (default_missing + len),
+			  (unsigned char **) outbufstart,
+			  irreversible, 0, 0));
+
+      if (res != __GCONV_ILLEGAL_INPUT)
+	{
+	  /* If the conversion succeeds we have to increment the
+	     input buffer.  */
+	  if (res == __GCONV_EMPTY_INPUT)
+	    {
+	      /* We consuming one character.  */
+	      ++*inbufp;
+	      ++*irreversible;
+	    }
+
+	  return res;
+	}
+    }
+
   /* Haven't found a match.  */
   return __GCONV_ILLEGAL_INPUT;
 }
diff --git a/locale/C-ctype.c b/locale/C-ctype.c
index 4ab3f0171e..04eb091e62 100644
--- a/locale/C-ctype.c
+++ b/locale/C-ctype.c
@@ -345,7 +345,7 @@ const struct locale_data _nl_C_LC_CTYPE =
   UNDELETABLE,
   0,
   NULL,
-  62,
+  64,
   {
     { string: _nl_C_LC_CTYPE_class },
     { string: (const char *) _nl_C_LC_CTYPE_toupper },
@@ -422,6 +422,8 @@ const struct locale_data _nl_C_LC_CTYPE =
     { string: "" },
     { string: "" },
     { string: "" },
-    { string: "" }
+    { string: "" },
+    { wstr: (uint32_t *) L"?" },
+    { word: 1 }
   }
 };
diff --git a/locale/categories.def b/locale/categories.def
index 19e06879fd..e1f3f054b9 100644
--- a/locale/categories.def
+++ b/locale/categories.def
@@ -82,6 +82,58 @@ DEFINE_CATEGORY
   DEFINE_ELEMENT (_NL_CTYPE_WIDTH,	  "ctype-width",        std, bytearray)
   DEFINE_ELEMENT (_NL_CTYPE_MB_CUR_MAX,	  "ctype-mb-cur-max",   std, word)
   DEFINE_ELEMENT (_NL_CTYPE_CODESET_NAME, "charmap",		std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_TOUPPER32,    "ctype-toupper32",    std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_TOLOWER32,    "ctype-tolower32",    std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS_MB_LEN, "ctype-indigits_mb-len", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS0_MB, "ctype-indigits0_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS1_MB, "ctype-indigits1_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS2_MB, "ctype-indigits2_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS3_MB, "ctype-indigits3_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS4_MB, "ctype-indigits4_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS5_MB, "ctype-indigits5_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS6_MB, "ctype-indigits6_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS7_MB, "ctype-indigits7_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS8_MB, "ctype-indigits8_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS9_MB, "ctype-indigits9_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS_WC_LEN, "ctype-indigits_wc-len", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS0_WC, "ctype-indigits0_wc", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS1_WC, "ctype-indigits1_wc", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS2_WC, "ctype-indigits2_wc", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS3_WC, "ctype-indigits3_wc", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS4_WC, "ctype-indigits4_wc", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS5_WC, "ctype-indigits5_wc", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS6_WC, "ctype-indigits6_wc", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS7_WC, "ctype-indigits7_wc", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS8_WC, "ctype-indigits8_wc", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_INDIGITS9_WC, "ctype-indigits9_wc", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT0_MB, "ctype-outdigit0_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT1_MB, "ctype-outdigit1_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT2_MB, "ctype-outdigit2_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT3_MB, "ctype-outdigit3_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT4_MB, "ctype-outdigit4_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT5_MB, "ctype-outdigit5_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT6_MB, "ctype-outdigit6_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT7_MB, "ctype-outdigit7_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT8_MB, "ctype-outdigit8_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT9_MB, "ctype-outdigit9_mb", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT0_WC, "ctype-outdigit0_wc", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT1_WC, "ctype-outdigit1_wc", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT2_WC, "ctype-outdigit2_wc", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT3_WC, "ctype-outdigit3_wc", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT4_WC, "ctype-outdigit4_wc", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT5_WC, "ctype-outdigit5_wc", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT6_WC, "ctype-outdigit6_wc", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT7_WC, "ctype-outdigit7_wc", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT8_WC, "ctype-outdigit8_wc", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_OUTDIGIT9_WC, "ctype-outdigit9_wc", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_TRANSLIT_HASH_SIZE, "ctype-translit-hash-size", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_TRANSLIT_HASH_LAYERS, "ctype-translit-hash-layers", std, word)
+  DEFINE_ELEMENT (_NL_CTYPE_TRANSLIT_FROM_IDX, "ctype-translit-from-idx", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_TRANSLIT_FROM_TBL, "ctype-translit-from-tbl", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_TRANSLIT_TO_IDX, "ctype-translit-to-idx", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_TRANSLIT_TO_TBL, "ctype-translit-to-tbl", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_TRANSLIT_DEFAULT_MISSING, "ctype-translit-default-missing", std, string)
+  DEFINE_ELEMENT (_NL_CTYPE_TRANSLIT_DEFAULT_MISSING_LEN, "ctype-translit-default-missing-len", std, word)
   ), _nl_postload_ctype)
 
 
diff --git a/locale/langinfo.h b/locale/langinfo.h
index b5ccac6b88..11ab68ef63 100644
--- a/locale/langinfo.h
+++ b/locale/langinfo.h
@@ -319,6 +319,8 @@ enum
   _NL_CTYPE_TRANSLIT_FROM_TBL,
   _NL_CTYPE_TRANSLIT_TO_IDX,
   _NL_CTYPE_TRANSLIT_TO_TBL,
+  _NL_CTYPE_TRANSLIT_DEFAULT_MISSING,
+  _NL_CTYPE_TRANSLIT_DEFAULT_MISSING_LEN,
   _NL_NUM_LC_CTYPE,
 
   /* LC_MONETARY category: formatting of monetary quantities.
diff --git a/locale/programs/ld-ctype.c b/locale/programs/ld-ctype.c
index 8839a9e8f8..e899649d65 100644
--- a/locale/programs/ld-ctype.c
+++ b/locale/programs/ld-ctype.c
@@ -788,6 +788,7 @@ ctype_output (struct localedef_t *locale, struct charmap_t *charmap,
 		  + ctype->map_collection_nr];
   struct locale_file data;
   uint32_t idx[nelems + 1];
+  uint32_t default_missing_len;
   size_t elem, cnt, offset, total;
   char *cp;
 
@@ -814,8 +815,7 @@ ctype_output (struct localedef_t *locale, struct charmap_t *charmap,
 	  case _NL_ITEM_INDEX (name):					      \
 	    iov[2 + elem + offset].iov_base = (base);			      \
 	    iov[2 + elem + offset].iov_len = (len);			      \
-	    if (elem + 1 < nelems)					      \
-	      idx[elem + 1] = idx[elem] + iov[2 + elem + offset].iov_len;     \
+	    idx[elem + 1] = idx[elem] + iov[2 + elem + offset].iov_len;	      \
 	    break
 
 	  CTYPE_DATA (_NL_CTYPE_CLASS,
@@ -1007,6 +1007,26 @@ ctype_output (struct localedef_t *locale, struct charmap_t *charmap,
 	    idx[elem + 1] = idx[elem] + iov[2 + elem + offset].iov_len;
 	    break;
 
+	  case _NL_ITEM_INDEX(_NL_CTYPE_TRANSLIT_DEFAULT_MISSING):
+	    iov[2 + elem + offset].iov_base =
+	      ctype->default_missing ?: (uint32_t *) L"";
+	    iov[2 + elem + offset].iov_len =
+	      wcslen (iov[2 + elem + offset].iov_base);
+	    idx[elem + 1] = idx[elem] + iov[2 + elem + offset].iov_len;
+	    break;
+
+	  case _NL_ITEM_INDEX(_NL_CTYPE_TRANSLIT_DEFAULT_MISSING_LEN):
+	    default_missing_len = (ctype->default_missing
+				   ? wcslen ((wchar_t *)ctype->default_missing)
+				   : 1);
+	    iov[2 + elem + offset].iov_base = &default_missing_len;
+	    iov[2 + elem + offset].iov_len = sizeof (uint32_t);
+	    /* Remove the following line in case a new entry is added
+	       after _NL_CTYPE_TRANSLIT_DEFAULT_MISSING_LEN.  */
+	    if (elem < nelems)
+	      idx[elem + 1] = idx[elem] + iov[2 + elem + offset].iov_len;
+	    break;
+
 	  default:
 	    assert (! "unknown CTYPE element");
 	  }
diff --git a/localedata/tst-trans.c b/localedata/tst-trans.c
index 03a64de690..8bc64ce069 100644
--- a/localedata/tst-trans.c
+++ b/localedata/tst-trans.c
@@ -1,5 +1,5 @@
 /* Test program for user-defined character maps.
-   Copyright (C) 1999 Free Software Foundation, Inc.
+   Copyright (C) 1999, 2000 Free Software Foundation, Inc.
    This file is part of the GNU C Library.
    Contributed by Ulrich Drepper <drepper@cygnus.com>.
 
@@ -33,7 +33,10 @@ main (void)
 
   t = wctrans ("test");
   if (t == (wctrans_t) 0)
-    exit (1);
+    {
+      puts ("locale data files probably not loaded");
+      exit (1);
+    }
 
   wch = towctrans (L'A', t);
   printf ("towctrans (L'A', t) = %c\n", wch);