about summary refs log tree commit diff
path: root/iconvdata/gb18030.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 /iconvdata/gb18030.c
parent9a1f675436c5622b7846faa25274a2ef2d743285 (diff)
downloadglibc-601d294296e1de9fc423700db00bccc04a2bf50d.tar.gz
glibc-601d294296e1de9fc423700db00bccc04a2bf50d.tar.xz
glibc-601d294296e1de9fc423700db00bccc04a2bf50d.zip
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 'iconvdata/gb18030.c')
-rw-r--r--iconvdata/gb18030.c35
1 files changed, 22 insertions, 13 deletions
diff --git a/iconvdata/gb18030.c b/iconvdata/gb18030.c
index 8b8c472074..e3e9e8a66d 100644
--- a/iconvdata/gb18030.c
+++ b/iconvdata/gb18030.c
@@ -5683,7 +5683,8 @@ static const uint16_t __fourbyte_to_ucs1[] =
   [0x0309] = 0x03e5, [0x030a] = 0x03e6, [0x030b] = 0x03e7, [0x030c] = 0x03e8,
   [0x030d] = 0x03e9, [0x030e] = 0x03ea, [0x030f] = 0x03eb, [0x0310] = 0x03ec,
   [0x0311] = 0x03ed, [0x0312] = 0x03ee, [0x0313] = 0x03ef, [0x0314] = 0x03f0,
-  [0x0315] = 0x03f1, [0x0316] = 0x03f2, [0x0317] = 0x03f3, [0x0324] = 0x0400,
+  [0x0315] = 0x03f1, [0x0316] = 0x03f2, [0x0317] = 0x03f3, [0x0318] = 0x03f4,
+  [0x0319] = 0x03f5, [0x0324] = 0x0400,
   [0x0325] = 0x0402, [0x0326] = 0x0403, [0x0327] = 0x0404, [0x0328] = 0x0405,
   [0x0329] = 0x0406, [0x032a] = 0x0407, [0x032b] = 0x0408, [0x032c] = 0x0409,
   [0x032d] = 0x040a, [0x032e] = 0x040b, [0x032f] = 0x040c, [0x0330] = 0x040d,
@@ -9517,6 +9518,7 @@ static const unsigned char __ucs_to_gb18030_tab1[][2] =
   [0x036b] = "\x23\x0f", [0x036c] = "\x23\x10", [0x036d] = "\x23\x11",
   [0x036e] = "\x23\x12", [0x036f] = "\x23\x13", [0x0370] = "\x23\x14",
   [0x0371] = "\x23\x15", [0x0372] = "\x23\x16", [0x0373] = "\x23\x17",
+  [0x0374] = "\x23\x18", [0x0375] = "\x23\x19",
   [0x0380] = "\x23\x24", [0x0381] = "\xa7\xa7", [0x0382] = "\x23\x25",
   [0x0383] = "\x23\x26", [0x0384] = "\x23\x27", [0x0385] = "\x23\x28",
   [0x0386] = "\x23\x29", [0x0387] = "\x23\x2a", [0x0388] = "\x23\x2b",
@@ -21954,15 +21956,15 @@ static const unsigned char __ucs_to_gb18030_tab2[][2] =
 	}								      \
       else								      \
 	{								      \
-	  /* Two or four byte character.  First test whether the	      \
-	     next character is also available.  */			      \
+	  /* Two or four byte character.  First test whether the next	      \
+	     byte is also available.  */				      \
 	  uint32_t ch2;							      \
 	  unsigned long int idx;					      \
 									      \
 	  if (inptr + 1 >= inend)					      \
 	    {								      \
-	      /* The second character is not available.  Store		      \
-		 the intermediate result.  */				      \
+	      /* The second byte is not available.  Store the		      \
+		 intermediate result.  */				      \
 	      result = __GCONV_INCOMPLETE_INPUT;			      \
 	      break;							      \
 	    }								      \
@@ -21992,7 +21994,7 @@ static const unsigned char __ucs_to_gb18030_tab2[][2] =
 									      \
 	      if (inptr + 3 >= inend)					      \
 	 	{							      \
-		  /* Not all characters are available.  Store		      \
+		  /* Not all bytes are available.  Store		      \
 		     the intermediate result.  */			      \
 		  result = __GCONV_INCOMPLETE_INPUT;			      \
 		  break;						      \
@@ -22035,17 +22037,19 @@ static const unsigned char __ucs_to_gb18030_tab2[][2] =
 		      + ch3 - 0x81) * 10 + ch4 - 0x30;			      \
 									      \
 	      if (idx <= 0x4A18)					      \
-		  ch = __fourbyte_to_ucs1[idx];				      \
+		ch = __fourbyte_to_ucs1[idx];				      \
 	      else if (idx >= 0x4ABD && idx <= 0x4F49)			      \
-		  ch = idx + 0x5543; 					      \
+		ch = idx + 0x5543; 					      \
 	      else if (idx >= 0x4F4D && idx <= 0x4F83)			      \
-		  ch = __fourbyte_to_ucs2[idx-0x4F4D];			      \
+		ch = __fourbyte_to_ucs2[idx-0x4F4D];			      \
 	      else if (idx >= 0x56BD && idx <= 0x8260)			      \
-		  ch = idx + 0x5543; 					      \
+		ch = idx + 0x5543; 					      \
 	      else if (idx >= 0x93A9 && idx <= 0x99F9)			      \
-		  ch = __fourbyte_to_ucs3[idx-0x93A9];			      \
+		ch = __fourbyte_to_ucs3[idx-0x93A9];			      \
+	      else if (idx >= 0x2E248 && idx <= 0x12E247)		      \
+		ch = idx - 0x1E248;					      \
 	      else							      \
-		  ch = 0;						      \
+		ch = 0;							      \
 									      \
 	      if (ch == 0 && *inptr != '\0')				      \
 		{							      \
@@ -22148,6 +22152,11 @@ static const unsigned char __ucs_to_gb18030_tab2[][2] =
 		len = 4;						      \
 	    }								      \
 	  }								      \
+	else if (ch >= 0x10000 && ch <= 0x10FFFF)			      \
+	  {								      \
+	    idx = ch + 0x1E248;						      \
+	    len = 4;							      \
+	  }								      \
 	else  								      \
 	  len = 0;							      \
 									      \
@@ -22175,7 +22184,7 @@ static const unsigned char __ucs_to_gb18030_tab2[][2] =
 	  }								      \
 	else /* len == 4 */						      \
 	  {								      \
-	    /* See whether there is enough room for the second byte we	      \
+	    /* See whether there is enough room for all four bytes we	      \
 	       write.  */						      \
 	    if (__builtin_expect (outptr + 3 >= outend, 0))		      \
 	      {								      \
generated by cgit-pink 1.4.1 (git 2.36.1) at 2024-11-23 02:01:47 +0000