summaryrefslogtreecommitdiff
path: root/localedata/gen-unicode-ctype.c
diff options
context:
space:
mode:
authorUlrich Drepper <drepper@redhat.com>2001-06-06 12:55:46 +0000
committerUlrich Drepper <drepper@redhat.com>2001-06-06 12:55:46 +0000
commit601d294296e1de9fc423700db00bccc04a2bf50d (patch)
tree1d274eb4e512431b042e07bf8f8ff4a980407257 /localedata/gen-unicode-ctype.c
parent9a1f675436c5622b7846faa25274a2ef2d743285 (diff)
Update.
2001-06-04 Bruno Haible <haible@clisp.cons.org> * iconv/loop.c (UNICODE_TAG_HANDLER): New macro. * iconv/gconv_simple.c (__gconv_transform_internal_ascii): Invoke UNICODE_TAG_HANDLER. (__gconv_transform_internal_ucs2): Likewise. (__gconv_transform_internal_ucs2reverse): Likewise. * iconvdata/8bit-gap.c (BODY for TO_LOOP): Invoke UNICODE_TAG_HANDLER. * iconvdata/8bit-generic.c (BODY for TO_LOOP): Likewise. * iconvdata/ansi_x3.110.c (BODY for TO_LOOP): Likewise. * iconvdata/big5.c (BODY for TO_LOOP): Likewise. * iconvdata/big5hkscs.c (BODY for TO_LOOP): Likewise. * iconvdata/cp1255.c (BODY for TO_LOOP): Likewise. * iconvdata/cp1258.c (BODY for TO_LOOP): Likewise. * iconvdata/euc-cn.c (BODY for TO_LOOP): Likewise. * iconvdata/euc-jp.c (BODY for TO_LOOP): Likewise. * iconvdata/euc-kr.c (BODY for TO_LOOP): Likewise. * iconvdata/euc-tw.c (BODY for TO_LOOP): Likewise. * iconvdata/gbk.c (BODY for TO_LOOP): Likewise. * iconvdata/ibm930.c (BODY for TO_LOOP): Likewise. * iconvdata/ibm932.c (BODY for TO_LOOP): Likewise. * iconvdata/ibm933.c (BODY for TO_LOOP): Likewise. * iconvdata/ibm935.c (BODY for TO_LOOP): Likewise. * iconvdata/ibm937.c (BODY for TO_LOOP): Likewise. * iconvdata/ibm939.c (BODY for TO_LOOP): Likewise. * iconvdata/ibm943.c (BODY for TO_LOOP): Likewise. * iconvdata/iso646.c (BODY for TO_LOOP): Likewise. * iconvdata/iso8859-1.c (BODY for TO_LOOP): Likewise. * iconvdata/iso_6937.c (BODY for TO_LOOP): Likewise. * iconvdata/iso_6937-2.c (BODY for TO_LOOP): Likewise. * iconvdata/iso-2022-cn.c (BODY for TO_LOOP): Likewise. * iconvdata/iso-2022-cn-ext.c (BODY for TO_LOOP): Likewise. * iconvdata/iso-2022-kr.c (BODY for TO_LOOP): Likewise. * iconvdata/johab.c (BODY for TO_LOOP): Likewise. * iconvdata/sjis.c (BODY for TO_LOOP): Likewise. * iconvdata/t.61.c (BODY for TO_LOOP): Likewise. * iconvdata/uhc.c (BODY for TO_LOOP): Likewise. * iconvdata/unicode.c (BODY for TO_LOOP): Likewise. * iconvdata/iso-2022-jp.c (TAG_none, TAG_language, TAG_language_j, TAG_language_ja, TAG_language_k, TAG_language_ko, TAG_language_z, TAG_language_zh, CURRENT_TAG_MASK): New enum values. (EMIT_SHIFT_TO_INIT): Don't emit an escape sequence if ASCII_set is already selected but set2 or tag are set. (conversion): New enum type. (cvlist_t): New type. (CVLIST, CVLIST_FIRST, CVLIST_REST): New macros. (conversion_lists): New array. (BODY for TO_LOOP): Keep track of Unicode 3.1 language tag. If "ja", prefer conversion to Japanese character sets. If "zh", prefer conversion to GB2312. If "ko", prefer conversion to KSC5601. Small optimizations. (INIT_PARAMS): Add tag. (UPDATE_PARAMS): Add tag. 2001-06-04 Bruno Haible <haible@clisp.cons.org> * locale/programs/locfile.c (write_locale_data): Before creat(), unlink the file, to avoid crashing the processes that mmap it. Change a double slash to a single slash. Free fname in case of error return. 2001-06-02 Jakub Jelinek <jakub@redhat.com> * sysdeps/i386/fpu/s_frexpl.S (__frexpl): Mostly revert 2000-12-03 changes, do the special handling for denormal numbers, not for normalized numbers (patch by <trevin@xmission.com>). * math/test-misc.c (main): Test frexpl with denormal arguments. 2001-06-04 Jakub Jelinek <jakub@redhat.com> * math/libm-test.inc (llround_test): Add two new llround tests. * sysdeps/ieee754/ldbl-96/s_llroundl.c (__llroundl): Don't allow overflow when rounding away from zero. 2001-06-04 Jakub Jelinek <jakub@redhat.com> * math/Makefile (libm-calls): Add e_log2, w_log2, remove s_log2. * math/math_private.h (__ieee754_log2, __ieee754_log2f, __ieee754_log2l): New prototypes. * sysdeps/generic/w_log2.c: New file. * sysdeps/generic/w_log2f.c: New file. * sysdeps/generic/w_log2l.c: New file. * sysdeps/generic/s_log2l.c: Move... * sysdeps/generic/e_log2l.c: ...to here. Rename to __ieee754_log2l. * sysdeps/ieee754/k_standard.c (__kernel_standard): Handle log2(0) and log2(x < 0). * sysdeps/i386/fpu/s_log2.S: Move... * sysdeps/i386/fpu/e_log2.S: ...to here. Rename to __ieee754_log2. * sysdeps/i386/fpu/s_log2f.S: Move... * sysdeps/i386/fpu/e_log2f.S: ...to here. Rename to __ieee754_log2f. * sysdeps/i386/fpu/s_log2l.S: Move... * sysdeps/i386/fpu/e_log2l.S: ...to here. Rename to __ieee754_log2l. * sysdeps/m68k/fpu/s_log2.S: Move... * sysdeps/m68k/fpu/e_log2.S: ...to here. Rename to __ieee754_log2. * sysdeps/m68k/fpu/s_log2f.S: Move... * sysdeps/m68k/fpu/e_log2f.S: ...to here. Rename to __ieee754_log2f. * sysdeps/m68k/fpu/s_log2l.S: Move... * sysdeps/m68k/fpu/e_log2l.S: ...to here. Rename to __ieee754_log2l. * sysdeps/ieee754/dbl-64/s_log2.c: Move... * sysdeps/ieee754/dbl-64/e_log2.c: ...to here. Rename to __ieee754_log2. * sysdeps/ieee754/flt-32/s_log2f.c: Move... * sysdeps/ieee754/flt-32/e_log2f.c: ...to here. Rename to __ieee754_log2f. 2001-06-04 Jakub Jelinek <jakub@redhat.com> * sysdeps/generic/w_exp2.c (u_threshold): Lower threshold so that even arguments which result in denormalized exp2 are accepted. (__exp2): Arguments equal to u_threshold already result into underflow. * sysdeps/generic/w_exp2f.c (u_threshold, __exp2f): Likewise. * sysdeps/generic/w_exp2l.c (u_threshold, __exp2l): Likewise. * sysdeps/ieee754/dbl-64/e_exp2.c (__ieee754_exp2): Lomark was too low, with corrected lowmark use greaterequal, not greater. * sysdeps/ieee754/flt-32/e_exp2f.c (__ieee754_exp2f): Likewise. 2001-06-04 Jakub Jelinek <jakub@redhat.com> * math/libm-test.inc (ilogb_test): Test that ilogb(+-Inf) == INT_MAX. * sysdeps/i386/fpu/s_ilogb.S (__ilogb): Return INT_MAX for +-Inf. * sysdeps/i386/fpu/s_ilogbf.S (__ilogbf): Likewise. * sysdeps/i386/fpu/s_ilogbl.S (__ilogbl): Likewise. * sysdeps/ieee754/dbl-64/s_ilogb.c (__ilogb): Likewise. * sysdeps/ieee754/flt-32/s_ilogbf.c (__ilogbf): Likewise. * sysdeps/ieee754/ldbl-128/s_ilogbl.c (__ilogbl): Likewise. * sysdeps/ieee754/ldbl-96/s_ilogbl.c (__ilogbl): Likewise. 2001-06-04 Jakub Jelinek <jakub@redhat.com> * sysdeps/generic/w_coshl.c (__coshl): Test if finite argument gave non-finite result instead of using constant in generic version. * sysdeps/generic/w_coshf.c (__coshf): Likewise. * sysdeps/generic/w_cosh.c (__cosh): Likewise. * sysdeps/generic/w_exp10.c (o_threshold, u_threshold): Remove. (__exp10): Test if finite argument gave non-finite result. * sysdeps/generic/w_exp10f.c (o_threshold, u_threshold, __exp10f): Likewise. * sysdeps/generic/w_exp10l.c (o_threshold, u_threshold, __exp10l): Likewise. 2001-06-04 Jakub Jelinek <jakub@redhat.com> * sysdeps/ieee754/ldbl-96/e_coshl.c (__ieee754_coshl): Fix overflow threshold constant (log(LDBL_MAX)+M_LN2l). 2001-05-29 Bruno Haible <haible@clisp.cons.org> * locale/programs/ld-ctype.c (idx_table): New struct type. (idx_table_init, idx_table_get, idx_table_add): New functions. (MAX_CHARNAMES_IDX): Remove macro. (locale_ctype_t): Change type of charnames_idx field. (ctype_startup): Change initialization of charnames_idx field. (find_idx): Use idx_table_get and idx_table_add for speed. * locale/programs/charmap.c (charmap_new_char): Fix ucs4 value computation of characters in a range. 2001-05-29 Bruno Haible <haible@clisp.cons.org> * iconvdata/gb18030.c (__fourbyte_to_ucs1): Add mappings for <U03F4>, <U03F5>. (__ucs_to_gb18030_tab1): Likewise. (BODY for FROM_LOOP): Add mapping for <U00010000>..<U0010FFFF>. (BODY for TO_LOOP): Likewise. * iconvdata/tst-table-charmap.sh: Update for charmaps containing <U00xxxxxx> syntax. * iconvdata/tst-table-from.c (bmp_only): New variable. (utf8_decode): If bmp_only, don't return characters outside Unicode plane 0. (main): When testing UTF-8 or GB18030, set bmp_only to 1. Don't print a conversion line if utf8_decode returns NULL. * iconvdata/tst-table-to.c (main): When testing encodings other than UTF-8 and GB18030, loop upto U+30000 instead of U+10000. Use UTF-8 instead of UCS-2 as input. * iconvdata/tst-table.sh: For GB18030, use only the part < 0x10000 of the charmap. 2001-05-29 Bruno Haible <haible@clisp.cons.org> * iconvdata/cns11643l1.c: Update to Unicode 3.1. (__cns11643l1_to_ucs4_tab): Regenerated. (__cns11643l1_from_ucs4_tab12): Regenerated. * iconvdata/cns11643.c: Update to Unicode 3.1. (__cns11643l14_to_ucs4_tab): Remove array. (__cns11643l3_to_ucs4_tab, __cns11643l4_to_ucs4_tab, __cns11643l5_to_ucs4_tab, __cns11643l6_to_ucs4_tab, __cns11643l7_to_ucs4_tab, __cns11643l15_to_ucs4_tab): New arrays. (__cns11643_from_ucs4p0_tab): Renamed from __cns11643_from_ucs4_tab. (__cns11643_from_ucs4p2_tab): New array. * iconvdata/cns11643.h (__cns11643l14_to_ucs4_tab): Remove declaration. (__cns11643l3_to_ucs4_tab, __cns11643l4_to_ucs4_tab, __cns11643l5_to_ucs4_tab, __cns11643l6_to_ucs4_tab, __cns11643l7_to_ucs4_tab, __cns11643l15_to_ucs4_tab): New declarations. (cns11643_to_ucs4): Treat planes 3, 4, 5, 6, 7, 15 instead of 14. (__cns11643_from_ucs4_tab): Remove declaration. (__cns11643_from_ucs4p0_tab, __cns11643_from_ucs4p2_tab): New declarations. (ucs4_to_cns11643): Update for new arrays. Treat U+3400..U+4DFF and U+20000..U+2A6D6. * iconvdata/cns11643l2.h (__cns11643_from_ucs4_tab): Remove declaration. (__cns11643_from_ucs4p0_tab): New declaration. (ucs4_to_cns11643l2): Update for new arrays. * iconvdata/iso-2022-cn-ext.c (BODY for FROM_LOOP): Handle planes 3 to 7. (BODY for TO_LOOP): Handle planes 3 to 7, instead of plane 14. * iconvdata/EUC-TW.irreversible: New file. * iconvdata/tst-table.sh: Use it. * iconvdata/Makefile (distribute): Add CP1255.irreversible, CP1258.irreversible, EUC-TW.irreversible. 2001-05-29 Bruno Haible <haible@clisp.cons.org> * locale/C-translit.h.in: Add transliterations for new Unicode 3.1 mathematical symbols.
Diffstat (limited to 'localedata/gen-unicode-ctype.c')
-rw-r--r--localedata/gen-unicode-ctype.c225
1 files changed, 93 insertions, 132 deletions
diff --git a/localedata/gen-unicode-ctype.c b/localedata/gen-unicode-ctype.c
index 1259aef872..70bea4172d 100644
--- a/localedata/gen-unicode-ctype.c
+++ b/localedata/gen-unicode-ctype.c
@@ -1,5 +1,5 @@
/* Generate a Unicode conforming LC_CTYPE category from a UnicodeData file.
- Copyright (C) 2000 Free Software Foundation, Inc.
+ Copyright (C) 2000-2001 Free Software Foundation, Inc.
This file is part of the GNU C Library.
Contributed by Bruno Haible <haible@clisp.cons.org>, 2000.
@@ -19,9 +19,7 @@
Boston, MA 02111-1307, USA. */
/* Usage example:
- $ gen-unicode /usr/local/share/Unidata/UnicodeData.txt \
- /usr/local/share/Unidata/PropList.txt \
- 3.0
+ $ gen-unicode /usr/local/share/Unidata/UnicodeData.txt 3.1
*/
#include <stdio.h>
@@ -54,7 +52,7 @@ struct unicode_attribute
#define NONE (~(unsigned int)0)
/* The entire contents of the UnicodeData.txt file. */
-struct unicode_attribute unicode_attributes [0x10000];
+struct unicode_attribute unicode_attributes [0x110000];
/* Stores in unicode_attributes[i] the values from the given fields. */
static void
@@ -69,11 +67,14 @@ fill_attribute (unsigned int i,
{
struct unicode_attribute * uni;
- if (i >= 0x10000)
+ if (i >= 0x110000)
{
fprintf (stderr, "index too large\n");
exit (1);
}
+ if (strcmp (field2, "Cs") == 0)
+ /* Surrogates are UTF-16 artefacts, not real characters. Ignore them. */
+ return;
uni = &unicode_attributes[i];
/* Copy the strings. */
uni->name = strdup (field1);
@@ -151,7 +152,7 @@ fill_attributes (const char *unicodedata_filename)
char field14[FIELDLEN];
int lineno = 0;
- for (i = 0; i < 0x10000; i++)
+ for (i = 0; i < 0x110000; i++)
unicode_attributes[i].name = NULL;
stream = fopen (unicodedata_filename, "r");
@@ -247,87 +248,6 @@ fill_attributes (const char *unicodedata_filename)
}
}
-/* The combining property from the PropList.txt file. */
-char unicode_combining[0x10000];
-
-/* Stores in unicode_combining[] the Combining property from the
- PropList.txt file. */
-static void
-fill_combining (const char *proplist_filename)
-{
- unsigned int i;
- FILE *stream;
- char buf[100+1];
-
- for (i = 0; i < 0x10000; i++)
- unicode_combining[i] = 0;
-
- stream = fopen (proplist_filename, "r");
- if (stream == NULL)
- {
- fprintf (stderr, "error during fopen of '%s'\n", proplist_filename);
- exit (1);
- }
-
- /* Search for the "Property dump for: 0x20000004 (Combining)" line. */
- do
- {
- if (fscanf (stream, "%100[^\n]\n", buf) < 1)
- {
- fprintf (stderr, "no combining property found in '%s'\n",
- proplist_filename);
- exit (1);
- }
- }
- while (strstr (buf, "(Combining)") == NULL);
-
- for (;;)
- {
- unsigned int i1, i2;
-
- if (fscanf (stream, "%100[^\n]\n", buf) < 1)
- {
- fprintf (stderr, "premature end of combining property in '%s'\n",
- proplist_filename);
- exit (1);
- }
- if (buf[0] == '*')
- break;
- if (strlen (buf) >= 10 && buf[4] == '.' && buf[5] == '.')
- {
- if (sscanf (buf, "%4X..%4X", &i1, &i2) < 2)
- {
- fprintf (stderr, "parse error in combining property in '%s'\n",
- proplist_filename);
- exit (1);
- }
- }
- else if (strlen (buf) >= 4)
- {
- if (sscanf (buf, "%4X", &i1) < 1)
- {
- fprintf (stderr, "parse error in combining property in '%s'\n",
- proplist_filename);
- exit (1);
- }
- i2 = i1;
- }
- else
- {
- fprintf (stderr, "parse error in combining property in '%s'\n",
- proplist_filename);
- exit (1);
- }
- for (i = i1; i <= i2; i++)
- unicode_combining[i] = 1;
- }
- if (ferror (stream) || fclose (stream))
- {
- fprintf (stderr, "error reading from '%s'\n", proplist_filename);
- exit (1);
- }
-}
-
/* Character mappings. */
static unsigned int
@@ -380,7 +300,15 @@ static bool
is_alpha (unsigned int ch)
{
return (unicode_attributes[ch].name != NULL
- && (unicode_attributes[ch].category[0] == 'L'
+ && ((unicode_attributes[ch].category[0] == 'L'
+ /* Theppitak Karoonboonyanan <thep@links.nectec.or.th> says
+ <U0E2F>, <U0E46> should belong to is_punct. */
+ && (ch != 0x0E2F) && (ch != 0x0E46))
+ /* Theppitak Karoonboonyanan <thep@links.nectec.or.th> says
+ <U0E31>, <U0E34>..<U0E3A>, <U0E47>..<U0E4E> are is_alpha. */
+ || (ch == 0x0E31)
+ || (ch >= 0x0E34 && ch <= 0x0E3A)
+ || (ch >= 0x0E47 && ch <= 0x0E4E)
/* Avoid warning for <U0345>. */
|| (ch == 0x0345)
/* Avoid warnings for <U2160>..<U217F>. */
@@ -528,8 +456,15 @@ is_punct (unsigned int ch)
static bool
is_combining (unsigned int ch)
{
+ /* Up to Unicode 3.0.1 we took the Combining property from the PropList.txt
+ file. In 3.0.1 it was identical to the union of the general categories
+ "Mn", "Mc", "Me". In Unicode 3.1 this property has been dropped from the
+ PropList.txt file, so we take the latter definition. */
return (unicode_attributes[ch].name != NULL
- && unicode_combining[ch] != 0);
+ && unicode_attributes[ch].category[0] == 'M'
+ && (unicode_attributes[ch].category[1] == 'n'
+ || unicode_attributes[ch].category[1] == 'c'
+ || unicode_attributes[ch].category[1] == 'e'));
}
static bool
@@ -541,43 +476,65 @@ is_combining_level3 (unsigned int ch)
&& strtoul (unicode_attributes[ch].combining, NULL, 10) >= 200);
}
+/* Return the UCS symbol string for a Unicode character. */
+static const char *
+ucs_symbol (unsigned int i)
+{
+ static char buf[11+1];
+
+ sprintf (buf, (i < 0x10000 ? "<U%04X>" : "<U%08X>"), i);
+ return buf;
+}
+
+/* Return the UCS symbol range string for a Unicode characters interval. */
+static const char *
+ucs_symbol_range (unsigned int low, unsigned int high)
+{
+ static char buf[24+1];
+
+ strcpy (buf, ucs_symbol (low));
+ strcat (buf, "..");
+ strcat (buf, ucs_symbol (high));
+ return buf;
+}
+
/* Output a character class (= property) table. */
static void
output_charclass (FILE *stream, const char *classname,
bool (*func) (unsigned int))
{
- char table[0x10000];
+ char table[0x110000];
unsigned int i;
bool need_semicolon;
const int max_column = 75;
int column;
- for (i = 0; i < 0x10000; i++)
+ for (i = 0; i < 0x110000; i++)
table[i] = (int) func (i);
fprintf (stream, "%s ", classname);
need_semicolon = false;
column = 1000;
- for (i = 0; i < 0x10000; )
+ for (i = 0; i < 0x110000; )
{
if (!table[i])
i++;
else
{
unsigned int low, high;
- char buf[17];
+ char buf[25];
low = i;
do
i++;
- while (i < 0x10000 && table[i]);
+ while (i < 0x110000 && table[i]);
high = i - 1;
if (low == high)
- sprintf (buf, "<U%04X>", low);
+ strcpy (buf, ucs_symbol (low));
else
- sprintf (buf, "<U%04X>..<U%04X>", low, high);
+ strcpy (buf, ucs_symbol_range (low, high));
if (need_semicolon)
{
@@ -605,24 +562,28 @@ static void
output_charmap (FILE *stream, const char *mapname,
unsigned int (*func) (unsigned int))
{
- char table[0x10000];
+ char table[0x110000];
unsigned int i;
bool need_semicolon;
const int max_column = 75;
int column;
- for (i = 0; i < 0x10000; i++)
+ for (i = 0; i < 0x110000; i++)
table[i] = (func (i) != i);
fprintf (stream, "%s ", mapname);
need_semicolon = false;
column = 1000;
- for (i = 0; i < 0x10000; i++)
+ for (i = 0; i < 0x110000; i++)
if (table[i])
{
- char buf[18];
+ char buf[25+1];
- sprintf (buf, "(<U%04X>,<U%04X>)", i, func (i));
+ strcpy (buf, "(");
+ strcat (buf, ucs_symbol (i));
+ strcat (buf, ",");
+ strcat (buf, ucs_symbol (func (i)));
+ strcat (buf, ")");
if (need_semicolon)
{
@@ -668,7 +629,7 @@ output_tables (const char *filename, const char *version)
fprintf (stream, "escape_char /\n");
fprintf (stream, "comment_char %%\n");
fprintf (stream, "\n");
- fprintf (stream, "%% Generated automatically by gen-unicode for Unicode %s.\n",
+ fprintf (stream, "%% Generated automatically by gen-unicode-ctype for Unicode %s.\n",
version);
fprintf (stream, "\n");
@@ -690,76 +651,76 @@ output_tables (const char *filename, const char *version)
strftime (date, sizeof (date), "%Y-%m-%d", gmtime (&now));
fprintf (stream, "date \"%s\"\n", date);
}
- fprintf (stream, "category \"unicode:2000\";LC_CTYPE\n");
+ fprintf (stream, "category \"unicode:2001\";LC_CTYPE\n");
fprintf (stream, "END LC_IDENTIFICATION\n");
fprintf (stream, "\n");
/* Verifications. */
- for (ch = 0; ch < 0x10000; ch++)
+ for (ch = 0; ch < 0x110000; ch++)
{
/* toupper restriction: "Only characters specified for the keywords
lower and upper shall be specified. */
if (to_upper (ch) != ch && !(is_lower (ch) || is_upper (ch)))
fprintf (stderr,
- "<U%04X> is not upper|lower but toupper(0x%04X) = 0x%04X\n",
- ch, ch, to_upper (ch));
+ "%s is not upper|lower but toupper(0x%04X) = 0x%04X\n",
+ ucs_symbol (ch), ch, to_upper (ch));
/* tolower restriction: "Only characters specified for the keywords
lower and upper shall be specified. */
if (to_lower (ch) != ch && !(is_lower (ch) || is_upper (ch)))
fprintf (stderr,
- "<U%04X> is not upper|lower but tolower(0x%04X) = 0x%04X\n",
- ch, ch, to_lower (ch));
+ "%s is not upper|lower but tolower(0x%04X) = 0x%04X\n",
+ ucs_symbol (ch), ch, to_lower (ch));
/* alpha restriction: "Characters classified as either upper or lower
shall automatically belong to this class. */
if ((is_lower (ch) || is_upper (ch)) && !is_alpha (ch))
- fprintf (stderr, "<U%04X> is upper|lower but not alpha\n", ch);
+ fprintf (stderr, "%s is upper|lower but not alpha\n", ucs_symbol (ch));
/* alpha restriction: "No character specified for the keywords cntrl,
digit, punct or space shall be specified." */
if (is_alpha (ch) && is_cntrl (ch))
- fprintf (stderr, "<U%04X> is alpha and cntrl\n", ch);
+ fprintf (stderr, "%s is alpha and cntrl\n", ucs_symbol (ch));
if (is_alpha (ch) && is_digit (ch))
- fprintf (stderr, "<U%04X> is alpha and digit\n", ch);
+ fprintf (stderr, "%s is alpha and digit\n", ucs_symbol (ch));
if (is_alpha (ch) && is_punct (ch))
- fprintf (stderr, "<U%04X> is alpha and punct\n", ch);
+ fprintf (stderr, "%s is alpha and punct\n", ucs_symbol (ch));
if (is_alpha (ch) && is_space (ch))
- fprintf (stderr, "<U%04X> is alpha and space\n", ch);
+ fprintf (stderr, "%s is alpha and space\n", ucs_symbol (ch));
/* space restriction: "No character specified for the keywords upper,
lower, alpha, digit, graph or xdigit shall be specified."
upper, lower, alpha already checked above. */
if (is_space (ch) && is_digit (ch))
- fprintf (stderr, "<U%04X> is space and digit\n", ch);
+ fprintf (stderr, "%s is space and digit\n", ucs_symbol (ch));
if (is_space (ch) && is_graph (ch))
- fprintf (stderr, "<U%04X> is space and graph\n", ch);
+ fprintf (stderr, "%s is space and graph\n", ucs_symbol (ch));
if (is_space (ch) && is_xdigit (ch))
- fprintf (stderr, "<U%04X> is space and xdigit\n", ch);
+ fprintf (stderr, "%s is space and xdigit\n", ucs_symbol (ch));
/* cntrl restriction: "No character specified for the keywords upper,
lower, alpha, digit, punct, graph, print or xdigit shall be
specified." upper, lower, alpha already checked above. */
if (is_cntrl (ch) && is_digit (ch))
- fprintf (stderr, "<U%04X> is cntrl and digit\n", ch);
+ fprintf (stderr, "%s is cntrl and digit\n", ucs_symbol (ch));
if (is_cntrl (ch) && is_punct (ch))
- fprintf (stderr, "<U%04X> is cntrl and punct\n", ch);
+ fprintf (stderr, "%s is cntrl and punct\n", ucs_symbol (ch));
if (is_cntrl (ch) && is_graph (ch))
- fprintf (stderr, "<U%04X> is cntrl and graph\n", ch);
+ fprintf (stderr, "%s is cntrl and graph\n", ucs_symbol (ch));
if (is_cntrl (ch) && is_print (ch))
- fprintf (stderr, "<U%04X> is cntrl and print\n", ch);
+ fprintf (stderr, "%s is cntrl and print\n", ucs_symbol (ch));
if (is_cntrl (ch) && is_xdigit (ch))
- fprintf (stderr, "<U%04X> is cntrl and xdigit\n", ch);
+ fprintf (stderr, "%s is cntrl and xdigit\n", ucs_symbol (ch));
/* punct restriction: "No character specified for the keywords upper,
lower, alpha, digit, cntrl, xdigit or as the <space> character shall
be specified." upper, lower, alpha, cntrl already checked above. */
if (is_punct (ch) && is_digit (ch))
- fprintf (stderr, "<U%04X> is punct and digit\n", ch);
+ fprintf (stderr, "%s is punct and digit\n", ucs_symbol (ch));
if (is_punct (ch) && is_xdigit (ch))
- fprintf (stderr, "<U%04X> is punct and xdigit\n", ch);
+ fprintf (stderr, "%s is punct and xdigit\n", ucs_symbol (ch));
if (is_punct (ch) && (ch == 0x0020))
- fprintf (stderr, "<U%04X> is punct\n", ch);
+ fprintf (stderr, "%s is punct\n", ucs_symbol (ch));
/* graph restriction: "No character specified for the keyword cntrl
shall be specified." Already checked above. */
@@ -772,9 +733,11 @@ output_tables (const char *filename, const char *version)
I think susv2/xbd/locale.html should speak of "space characters",
not "space character". */
if (is_print (ch) && !(is_graph (ch) || /* ch == 0x0020 */ is_space (ch)))
- fprintf (stderr, "<U%04X> is print but not graph|<space>\n", ch);
+ fprintf (stderr,
+ "%s is print but not graph|<space>\n", ucs_symbol (ch));
if (!is_print (ch) && (is_graph (ch) || ch == 0x0020))
- fprintf (stderr, "<U%04X> is graph|<space> but not print\n", ch);
+ fprintf (stderr,
+ "%s is graph|<space> but not print\n", ucs_symbol (ch));
}
fprintf (stream, "LC_CTYPE\n");
@@ -808,17 +771,15 @@ output_tables (const char *filename, const char *version)
int
main (int argc, char * argv[])
{
- if (argc != 4)
+ if (argc != 3)
{
- fprintf (stderr, "Usage: %s UnicodeData.txt PropList.txt version\n",
- argv[0]);
+ fprintf (stderr, "Usage: %s UnicodeData.txt version\n", argv[0]);
exit (1);
}
fill_attributes (argv[1]);
- fill_combining (argv[2]);
- output_tables ("unicode", argv[3]);
+ output_tables ("unicode", argv[2]);
return 0;
}