summaryrefslogtreecommitdiff
path: root/lib/unilbrk/lbrktables.c
diff options
context:
space:
mode:
authorDaiki Ueno <ueno@gnu.org>2016-10-12 17:40:37 +0200
committerDaiki Ueno <dueno@redhat.com>2017-10-30 11:13:20 +0100
commited0bf5d5284b787af71b1b95fca1fdb6389fee3c (patch)
tree2825a6954b97ec150986e07b8b2ae32c45ea52b0 /lib/unilbrk/lbrktables.c
parentf466816e06ec3516567c3edcd0219bd1f9b736eb (diff)
downloadgnulib-ed0bf5d5284b787af71b1b95fca1fdb6389fee3c.tar.gz
libunistring: update to Unicode 9.0.0ueno/unicode-9.0.0
* lib/gen-uni-tables.c (fill_properties): Recognize Sentence_Terminal and Prepended_Concatenation_Mark. (is_property_default_ignorable_code_point): Exclude U+08E2. (fill_arabicshaping): Allow missing whitespace when parsing; recognize "AFRICAN FEH", "AFRICAN QAF", and "AFRICAN MOON". (output_blocks): Increase the element size of the level1 table to accommodate more blocks. (get_lbp): Recognize ZWJ, E_Base, and E_Modifier characters; Update each class according to the standard. (get_wbp): Recognize ZWJ, E_Base, E_Modifier, Glue_After_Zwj, and E_Base_GAZ characters. (output_gbp_table): Recognize ZWJ, E_Base, E_Modifier, Glue_After_Zwj, and E_Base_GAZ characters. * lib/unictype.in.h (UC_JOINING_GROUP_AFRICAN_FEH, UC_JOINING_GROUP_AFRICAN_QAF, UC_JOINING_GROUP_AFRICAN_MOON): New enum value. * lib/unilbrk/lbrktables.h (LBP_ZWJ, LBP_EB, LBP_EM): New enum value. * lib/unilbrk/lbrktables.c (unilbrk_table): Extend the table with LBP_ZWJ, LBP_EB, and LBP_EM. * lib/uniwbrk.in.h (WBP_ZWJ, WBP_EB, WBP_EM, WBP_GAZ, WBP_EBG): New enum value. * lib/uniwbrk/u-wordbreaks.h: Implement WB3c, WB15, and WB16. * lib/uniwbrk/wbrktable.h (uniwbrk_prop_index): New variable declaration. * lib/uniwbrk/wbrktable.c (uniwbrk_prop_index): New variable. (uniwbrk_table): Implement WB14. * tests/uniwbrk/test-uc-wordbreaks.c (wordbreakproperty_to_string): Check WBP_ZWJ, WBP_EB, WBP_EM, WBP_GAZ, and WBP_EBG. * modules/unigbrk/u{32,16,8}-grapheme-breaks: No longer depend on uc-is-grapheme-break. * modules/unigbrk/uc-grapheme-breaks: New module. * modules/unigbrk/uc-grapheme-breaks-tests: New module. * lib/unigbrk.in.h (GBP_ZWJ, GBP_EB, GBP_EM, GBP_GAZ, GBP_EBG): New enum value. (uc_grapheme_breaks): New function, replacing uc_is_grapheme_break. * lib/unigbrk/u-grapheme-breaks.h: New file. * lib/unigbrk/u{32,16,8}-grapheme-breaks.c: Rewrite using u-grapheme-breaks.h instead of uc_is_grapheme_break. * lib/unigbrk/uc-grapheme-breaks.c: New file. * lib/unigbrk/uc-is-grapheme-break.c: Partially update to TR29 rev 29. * tests/unigbrk/test-uc-gbrk-prop.c (graphemebreakproperty_to_string): Check GBP_ZWJ, GBP_EB, GBP_EM, GBP_GAZ, and GBP_EBG. * tests/unigbrk/test-uc-grapheme-breaks.c: New test. * tests/unigbrk/test-uc-is-grapheme-break.c (graphemebreakproperty_to_string): Check GBP_ZWJ, GBP_EB, GBP_EM, GBP_GAZ, and GBP_EBG. (main): Skip unsupported rules involving 3 or more characters, namely GB10, GB12, and GB13. * lib/uniwidth/width.c (nonspacing_table_data): Update.
Diffstat (limited to 'lib/unilbrk/lbrktables.c')
-rw-r--r--lib/unilbrk/lbrktables.c61
1 files changed, 32 insertions, 29 deletions
diff --git a/lib/unilbrk/lbrktables.c b/lib/unilbrk/lbrktables.c
index 90ade32096..c5254e69b2 100644
--- a/lib/unilbrk/lbrktables.c
+++ b/lib/unilbrk/lbrktables.c
@@ -23,37 +23,40 @@
/* Define unilbrkprop, table of line breaking properties. */
#include "unilbrk/lbrkprop2.h"
-const unsigned char unilbrk_table[27][27] =
+const unsigned char unilbrk_table[30][30] =
{
/* after */
- /* WJ GL B2 BA BB HY CL CP EX IN NS OP QU IS NU PO PR SY AL H2 H3 ID JL JV JT HL RI */
-/* WJ */ { P, I, I, I, I, I, P, P, P, I, I, I, I, P, I, I, I, P, I, I, I, I, I, I, I, I, I, },
-/* GL */ { P, I, I, I, I, I, P, P, P, I, I, I, I, P, I, I, I, P, I, I, I, I, I, I, I, I, I, },
-/* B2 */ { P, I, P, I, D, I, P, P, P, D, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, D, D, },
-/* BA */ { P, D, D, I, D, I, P, P, P, D, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, D, D, },
-/* BB */ { P, I, I, I, I, I, P, P, P, I, I, I, I, P, I, I, I, P, I, I, I, I, I, I, I, I, I, },
-/* HY */ { P, D, D, I, D, I, P, P, P, D, I, D, I, P, I, D, D, P, D, D, D, D, D, D, D, D, D, },
-/* CL */ { P, I, D, I, D, I, P, P, P, D, P, D, I, P, D, I, I, P, D, D, D, D, D, D, D, D, D, },
-/* CP */ { P, I, D, I, D, I, P, P, P, D, P, D, I, P, I, I, I, P, I, D, D, D, D, D, D, I, D, },
-/* EX */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, D, D, },
-/* IN */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, D, D, },
-/* NS */ { P, I, D, I, D, I, P, P, P, D, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, D, D, },
-/* OP */ { P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, },
-/* QU */ { P, I, I, I, I, I, P, P, P, I, I, P, I, P, I, I, I, P, I, I, I, I, I, I, I, I, I, },
-/* IS */ { P, I, D, I, D, I, P, P, P, D, I, D, I, P, I, D, D, P, D, D, D, D, D, D, D, D, D, },
-/* NU */ { P, I, D, I, D, I, P, P, P, I, I, I, I, P, I, I, I, P, I, D, D, D, D, D, D, I, D, },
-/* PO */ { P, I, D, I, D, I, P, P, P, D, I, I, I, P, I, D, D, P, I, D, D, D, D, D, D, I, D, },
-/* PR */ { P, I, D, I, D, I, P, P, P, D, I, I, I, P, I, D, D, P, I, I, I, I, I, I, I, I, D, },
-/* SY */ { P, I, D, I, D, I, P, P, P, D, I, D, I, P, I, D, D, P, D, D, D, D, D, D, D, I, D, },
-/* AL */ { P, I, D, I, D, I, P, P, P, I, I, I, I, P, I, D, D, P, I, D, D, D, D, D, D, I, D, },
-/* H2 */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, I, I, D, D, },
-/* H3 */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, D, I, D, D, },
-/* ID */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, D, D, D, D, },
-/* JL */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, I, I, D, I, I, D, D, D, },
-/* JV */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, I, I, D, D, },
-/* JT */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, D, I, D, D, },
-/* HL */ { P, I, D, I, D, I, P, P, P, I, I, I, I, P, I, D, D, P, I, D, D, D, D, D, D, I, D, },
-/* RI */ { P, I, D, I, D, I, P, P, P, D, I, D, I, P, D, D, D, P, D, D, D, D, D, D, I, D, I, },
+ /* WJ GL B2 BA BB HY CL CP EX IN NS OP QU IS NU PO PR SY AL H2 H3 ID JL JV JT HL RI ZWJ EB EM */
+/* WJ */ { P, I, I, I, I, I, P, P, P, I, I, I, I, P, I, I, I, P, I, I, I, I, I, I, I, I, I, I, I, I, },
+/* GL */ { P, I, I, I, I, I, P, P, P, I, I, I, I, P, I, I, I, P, I, I, I, I, I, I, I, I, I, I, I, I, },
+/* B2 */ { P, I, P, I, D, I, P, P, P, D, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, D, D, I, D, D, },
+/* BA */ { P, D, D, I, D, I, P, P, P, D, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, D, D, I, D, D, },
+/* BB */ { P, I, I, I, I, I, P, P, P, I, I, I, I, P, I, I, I, P, I, I, I, I, I, I, I, I, I, I, I, I, },
+/* HY */ { P, D, D, I, D, I, P, P, P, D, I, D, I, P, I, D, D, P, D, D, D, D, D, D, D, D, D, I, D, D, },
+/* CL */ { P, I, D, I, D, I, P, P, P, D, P, D, I, P, D, I, I, P, D, D, D, D, D, D, D, D, D, I, D, D, },
+/* CP */ { P, I, D, I, D, I, P, P, P, D, P, D, I, P, I, I, I, P, I, D, D, D, D, D, D, I, D, I, D, D, },
+/* EX */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, D, D, I, D, D, },
+/* IN */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, D, D, I, D, D, },
+/* NS */ { P, I, D, I, D, I, P, P, P, D, I, D, I, P, D, D, D, P, D, D, D, D, D, D, D, D, D, I, D, D, },
+/* OP */ { P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, P, },
+/* QU */ { P, I, I, I, I, I, P, P, P, I, I, P, I, P, I, I, I, P, I, I, I, I, I, I, I, I, I, I, I, I, },
+/* IS */ { P, I, D, I, D, I, P, P, P, D, I, D, I, P, I, D, D, P, D, D, D, D, D, D, D, D, D, I, D, D, },
+/* NU */ { P, I, D, I, D, I, P, P, P, I, I, I, I, P, I, I, I, P, I, D, D, D, D, D, D, I, D, I, D, D, },
+/* PO */ { P, I, D, I, D, I, P, P, P, D, I, I, I, P, I, D, D, P, I, D, D, D, D, D, D, I, D, I, D, D, },
+/* PR */ { P, I, D, I, D, I, P, P, P, D, I, I, I, P, I, D, D, P, I, I, I, I, I, I, I, I, D, I, I, I, },
+/* SY */ { P, I, D, I, D, I, P, P, P, D, I, D, I, P, I, D, D, P, D, D, D, D, D, D, D, I, D, I, D, D, },
+/* AL */ { P, I, D, I, D, I, P, P, P, I, I, I, I, P, I, D, D, P, I, D, D, D, D, D, D, I, D, I, D, D, },
+/* H2 */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, I, I, D, D, I, D, D, },
+/* H3 */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, D, I, D, D, I, D, D, },
+/* ID */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, D, D, D, D, I, D, D, },
+/* JL */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, I, I, D, I, I, D, D, D, I, D, D, },
+/* JV */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, I, I, D, D, I, D, D, },
+/* JT */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, D, I, D, D, I, D, D, },
+/* HL */ { P, I, D, I, D, I, P, P, P, I, I, I, I, P, I, D, D, P, I, D, D, D, D, D, D, I, D, I, D, D, },
+/* RI */ { P, I, D, I, D, I, P, P, P, D, I, D, I, P, D, D, D, P, D, D, D, D, D, D, I, D, I, I, D, D, },
+/* ZWJ */ { P, I, D, I, D, I, P, P, P, D, I, D, I, P, D, D, D, P, D, D, D, I, D, D, I, D, I, I, I, I, },
+/* EB */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, D, I, D, I, I, D, I, },
+/* EM */ { P, I, D, I, D, I, P, P, P, I, I, D, I, P, D, I, D, P, D, D, D, D, D, D, I, D, I, I, D, D, },
/* "" */
/* before */
};