]> Savannah Git Hosting - gnulib.git/commit
Update to Unicode 13.0.0.
authorBruno Haible <bruno@clisp.org>
Fri, 31 Dec 2021 11:20:27 +0000 (12:20 +0100)
committerBruno Haible <bruno@clisp.org>
Fri, 31 Dec 2021 11:20:27 +0000 (12:20 +0100)
commitf2e9cd38b97c58bcd66b804e08186503e00a3e8e
tree712f545d28aab410fe12b9ac93efca3bc682d8de
parent09cf5f3ac960dc7f413186bbda1c8aa2d43944df
Update to Unicode 13.0.0.

* lib/gen-uni-tables.c (is_WBP_MIDLETTER): Add character 0x055F.
(get_wbp): Assign value WBP_ALETTER to the characters 0x02E5..0x02EB,
0x055A, 0x058A, 0xA708..0xA716.

* lib/gen-uni-tables.c (LBP_CP1, LBP_CP2, LBP_OP1, LBP_OP2): New enum
values.
(LBP_OP, LBP_CP): Assign artificial values.
(get_lbp): Use the unicode_width[] table to assign LBP_CP1, LBP_CP2
instead of LBP_CP, and LBP_OP1, LBP_OP2 instead of LBP_OP. Update such
that unilbrk/lbrkprop.txt comes out as expected.
(debug_output_lbp): Print either LBP_CP1 or LBP_CP2 as LBP_CP. Print
either LBP_OP1 or LBP_OP2 as LBP_OP.
(lbp_value_to_string): Handle LBP_CP1, LBP_CP2, LBP_OP1, LBP_OP2 instead
of LBP_CP, LBP_OP.
(output_lbrk_rules_as_tables): Treat LBP_CP and LBP_OP as macros that
map to two table rows/columns. In rule LB30, use only LBP_OP1 instead of
LBP_OP, and only LBP_CP1 instead of LBP_CP. Simplify rule LB22.
* lib/unilbrk/lbrktables.h (LBP_CP1, LBP_CP2, LBP_OP1, LBP_OP2): New
enum values.
(LBP_OP, LBP_CP): Remove enum values.
(unilbrk_table): Update declaration.
* lib/unilbrk/u8-possible-linebreaks.c (u8_possible_linebreaks_loop):
Add a test for East Asian opening parenthesis.
* lib/unilbrk/u16-possible-linebreaks.c (u16_possible_linebreaks_loop):
Likewise.
* lib/unilbrk/u32-possible-linebreaks.c (u32_possible_linebreaks_loop):
Likewise.

* lib/uniwidth/width.c (nonspacing_table_data, nonspacing_table_ind):
Update.
(uc_width): Assign width 2 to the characters 0x16FF0..0x16FF1,
0x18AF3..0x18CD5, 0x18D00..0x18D08, 0x1F6D6..0x1F6D7, 0x1F6FB..0x1F6FC,
0x1F90C, 0x1FA74, 0x1FA83..0x1FA86, 0x1FA96..0x1FAA8, 0x1FAB0..0x1FAB6,
0x1FAC0..0x1FAC2, 0x1FAD0..0x1FAD6.
Assign width 1 to the characters 0x1F93B, 0x1F946.
* tests/uniwidth/test-uc_width2.sh: Expect width 0 for the characters
0x0B55, 0x0D81, 0x1ABF..0x1AC0, 0xA82C, 0x10EAB..0x10EAC, 0x111CF,
0x1193B..0x1193C, 0x1193E, 0x11943, 0x16FE4. Expect width 2 for the
characters 0x16FF0..0x16FF1, 0x18AF3..0x18CD5, 0x18D00..0x18D08,
0x1F6D6..0x1F6D7, 0x1F6FB..0x1F6FC, 0x1F90C, 0x1FA74, 0x1FA83..0x1FA86,
0x1FA96..0x1FAA8, 0x1FAB0..0x1FAB6, 0x1FAC0..0x1FAC2, 0x1FAD0..0x1FAD6.
Expect width 1 for the characters 0x1F93B, 0x1F946.

* All generated files under lib/uni* and tests/uni*: Regenerate.
* tests/uniname/NameAliases.txt: Update.
* tests/uniname/UnicodeData.txt: Update.
* tests/uninorm/NormalizationTest.txt: Update.
* tests/unigbrk/GraphemeBreakTest.txt: Update.
* tests/uniwbrk/WordBreakTest.txt: Update.

* All the affected modules: Bump required libunistring version.
271 files changed:
ChangeLog
lib/gen-uni-tables.c
lib/unicase/cased.h
lib/unicase/ignorable.h
lib/unicase/special-casing-table.gperf
lib/unicase/tocasefold.h
lib/unicase/tolower.h
lib/unicase/totitle.h
lib/unicase/toupper.h
lib/unictype/bidi_of.h
lib/unictype/blocks.h
lib/unictype/categ_C.h
lib/unictype/categ_Cc.h
lib/unictype/categ_Cf.h
lib/unictype/categ_Cn.h
lib/unictype/categ_Co.h
lib/unictype/categ_Cs.h
lib/unictype/categ_L.h
lib/unictype/categ_LC.h
lib/unictype/categ_Ll.h
lib/unictype/categ_Lm.h
lib/unictype/categ_Lo.h
lib/unictype/categ_Lt.h
lib/unictype/categ_Lu.h
lib/unictype/categ_M.h
lib/unictype/categ_Mc.h
lib/unictype/categ_Me.h
lib/unictype/categ_Mn.h
lib/unictype/categ_N.h
lib/unictype/categ_Nd.h
lib/unictype/categ_Nl.h
lib/unictype/categ_No.h
lib/unictype/categ_P.h
lib/unictype/categ_Pc.h
lib/unictype/categ_Pd.h
lib/unictype/categ_Pe.h
lib/unictype/categ_Pf.h
lib/unictype/categ_Pi.h
lib/unictype/categ_Po.h
lib/unictype/categ_Ps.h
lib/unictype/categ_S.h
lib/unictype/categ_Sc.h
lib/unictype/categ_Sk.h
lib/unictype/categ_Sm.h
lib/unictype/categ_So.h
lib/unictype/categ_Z.h
lib/unictype/categ_Zl.h
lib/unictype/categ_Zp.h
lib/unictype/categ_Zs.h
lib/unictype/categ_of.h
lib/unictype/combiningclass.h
lib/unictype/ctype_alnum.h
lib/unictype/ctype_alpha.h
lib/unictype/ctype_blank.h
lib/unictype/ctype_cntrl.h
lib/unictype/ctype_digit.h
lib/unictype/ctype_graph.h
lib/unictype/ctype_lower.h
lib/unictype/ctype_print.h
lib/unictype/ctype_punct.h
lib/unictype/ctype_space.h
lib/unictype/ctype_upper.h
lib/unictype/ctype_xdigit.h
lib/unictype/decdigit.h
lib/unictype/digit.h
lib/unictype/joininggroup_of.h
lib/unictype/joiningtype_of.h
lib/unictype/mirror.h
lib/unictype/numeric.h
lib/unictype/pr_alphabetic.h
lib/unictype/pr_ascii_hex_digit.h
lib/unictype/pr_bidi_arabic_digit.h
lib/unictype/pr_bidi_arabic_right_to_left.h
lib/unictype/pr_bidi_block_separator.h
lib/unictype/pr_bidi_boundary_neutral.h
lib/unictype/pr_bidi_common_separator.h
lib/unictype/pr_bidi_control.h
lib/unictype/pr_bidi_embedding_or_override.h
lib/unictype/pr_bidi_eur_num_separator.h
lib/unictype/pr_bidi_eur_num_terminator.h
lib/unictype/pr_bidi_european_digit.h
lib/unictype/pr_bidi_hebrew_right_to_left.h
lib/unictype/pr_bidi_left_to_right.h
lib/unictype/pr_bidi_non_spacing_mark.h
lib/unictype/pr_bidi_other_neutral.h
lib/unictype/pr_bidi_pdf.h
lib/unictype/pr_bidi_segment_separator.h
lib/unictype/pr_bidi_whitespace.h
lib/unictype/pr_case_ignorable.h
lib/unictype/pr_cased.h
lib/unictype/pr_changes_when_casefolded.h
lib/unictype/pr_changes_when_casemapped.h
lib/unictype/pr_changes_when_lowercased.h
lib/unictype/pr_changes_when_titlecased.h
lib/unictype/pr_changes_when_uppercased.h
lib/unictype/pr_combining.h
lib/unictype/pr_composite.h
lib/unictype/pr_currency_symbol.h
lib/unictype/pr_dash.h
lib/unictype/pr_decimal_digit.h
lib/unictype/pr_default_ignorable_code_point.h
lib/unictype/pr_deprecated.h
lib/unictype/pr_diacritic.h
lib/unictype/pr_emoji.h
lib/unictype/pr_emoji_component.h
lib/unictype/pr_emoji_modifier.h
lib/unictype/pr_emoji_modifier_base.h
lib/unictype/pr_emoji_presentation.h
lib/unictype/pr_extended_pictographic.h
lib/unictype/pr_extender.h
lib/unictype/pr_format_control.h
lib/unictype/pr_grapheme_base.h
lib/unictype/pr_grapheme_extend.h
lib/unictype/pr_grapheme_link.h
lib/unictype/pr_hex_digit.h
lib/unictype/pr_hyphen.h
lib/unictype/pr_id_continue.h
lib/unictype/pr_id_start.h
lib/unictype/pr_ideographic.h
lib/unictype/pr_ids_binary_operator.h
lib/unictype/pr_ids_trinary_operator.h
lib/unictype/pr_ignorable_control.h
lib/unictype/pr_iso_control.h
lib/unictype/pr_join_control.h
lib/unictype/pr_left_of_pair.h
lib/unictype/pr_line_separator.h
lib/unictype/pr_logical_order_exception.h
lib/unictype/pr_lowercase.h
lib/unictype/pr_math.h
lib/unictype/pr_non_break.h
lib/unictype/pr_not_a_character.h
lib/unictype/pr_numeric.h
lib/unictype/pr_other_alphabetic.h
lib/unictype/pr_other_default_ignorable_code_point.h
lib/unictype/pr_other_grapheme_extend.h
lib/unictype/pr_other_id_continue.h
lib/unictype/pr_other_id_start.h
lib/unictype/pr_other_lowercase.h
lib/unictype/pr_other_math.h
lib/unictype/pr_other_uppercase.h
lib/unictype/pr_paired_punctuation.h
lib/unictype/pr_paragraph_separator.h
lib/unictype/pr_pattern_syntax.h
lib/unictype/pr_pattern_white_space.h
lib/unictype/pr_private_use.h
lib/unictype/pr_punctuation.h
lib/unictype/pr_quotation_mark.h
lib/unictype/pr_radical.h
lib/unictype/pr_sentence_terminal.h
lib/unictype/pr_soft_dotted.h
lib/unictype/pr_space.h
lib/unictype/pr_terminal_punctuation.h
lib/unictype/pr_titlecase.h
lib/unictype/pr_unassigned_code_value.h
lib/unictype/pr_unified_ideograph.h
lib/unictype/pr_uppercase.h
lib/unictype/pr_variation_selector.h
lib/unictype/pr_white_space.h
lib/unictype/pr_xid_continue.h
lib/unictype/pr_xid_start.h
lib/unictype/pr_zero_width.h
lib/unictype/scripts.h
lib/unictype/scripts_byname.gperf
lib/unictype/sy_c_ident.h
lib/unictype/sy_c_whitespace.h
lib/unictype/sy_java_ident.h
lib/unictype/sy_java_whitespace.h
lib/unigbrk/gbrkprop.h
lib/unilbrk/lbrkprop1.h
lib/unilbrk/lbrkprop2.h
lib/unilbrk/lbrktables.c
lib/unilbrk/lbrktables.h
lib/uniname/uninames.h
lib/uninorm/composition-table.gperf
lib/uninorm/decomposition-table1.h
lib/uninorm/decomposition-table2.h
lib/uniwbrk/wbrkprop.h
lib/uniwidth/width.c
modules/unictype/category-Pd
modules/unictype/category-Sk
modules/unictype/property-bidi-european-digit
modules/unictype/property-dash
tests/unicase/test-cased.c
tests/unicase/test-ignorable.c
tests/unicase/test-uc_tolower.c
tests/unicase/test-uc_totitle.c
tests/unicase/test-uc_toupper.c
tests/unictype/test-categ_C.c
tests/unictype/test-categ_Cn.c
tests/unictype/test-categ_L.c
tests/unictype/test-categ_LC.c
tests/unictype/test-categ_Ll.c
tests/unictype/test-categ_Lm.c
tests/unictype/test-categ_Lo.c
tests/unictype/test-categ_Lu.c
tests/unictype/test-categ_M.c
tests/unictype/test-categ_Mc.c
tests/unictype/test-categ_Mn.c
tests/unictype/test-categ_N.c
tests/unictype/test-categ_Nd.c
tests/unictype/test-categ_No.c
tests/unictype/test-categ_P.c
tests/unictype/test-categ_Pd.c
tests/unictype/test-categ_Po.c
tests/unictype/test-categ_S.c
tests/unictype/test-categ_Sk.c
tests/unictype/test-categ_So.c
tests/unictype/test-ctype_alnum.c
tests/unictype/test-ctype_alpha.c
tests/unictype/test-ctype_graph.c
tests/unictype/test-ctype_lower.c
tests/unictype/test-ctype_print.c
tests/unictype/test-ctype_punct.c
tests/unictype/test-ctype_upper.c
tests/unictype/test-decdigit.h
tests/unictype/test-digit.h
tests/unictype/test-joininggroup_of.h
tests/unictype/test-joiningtype_of.h
tests/unictype/test-numeric.h
tests/unictype/test-pr_alphabetic.c
tests/unictype/test-pr_bidi_arabic_right_to_left.c
tests/unictype/test-pr_bidi_european_digit.c
tests/unictype/test-pr_bidi_hebrew_right_to_left.c
tests/unictype/test-pr_bidi_left_to_right.c
tests/unictype/test-pr_bidi_non_spacing_mark.c
tests/unictype/test-pr_bidi_other_neutral.c
tests/unictype/test-pr_case_ignorable.c
tests/unictype/test-pr_cased.c
tests/unictype/test-pr_changes_when_casefolded.c
tests/unictype/test-pr_changes_when_casemapped.c
tests/unictype/test-pr_changes_when_lowercased.c
tests/unictype/test-pr_changes_when_titlecased.c
tests/unictype/test-pr_changes_when_uppercased.c
tests/unictype/test-pr_combining.c
tests/unictype/test-pr_composite.c
tests/unictype/test-pr_dash.c
tests/unictype/test-pr_decimal_digit.c
tests/unictype/test-pr_diacritic.c
tests/unictype/test-pr_emoji.c
tests/unictype/test-pr_emoji_modifier_base.c
tests/unictype/test-pr_emoji_presentation.c
tests/unictype/test-pr_extended_pictographic.c
tests/unictype/test-pr_extender.c
tests/unictype/test-pr_grapheme_base.c
tests/unictype/test-pr_grapheme_extend.c
tests/unictype/test-pr_grapheme_link.c
tests/unictype/test-pr_id_continue.c
tests/unictype/test-pr_id_start.c
tests/unictype/test-pr_ideographic.c
tests/unictype/test-pr_lowercase.c
tests/unictype/test-pr_numeric.c
tests/unictype/test-pr_other_alphabetic.c
tests/unictype/test-pr_other_grapheme_extend.c
tests/unictype/test-pr_punctuation.c
tests/unictype/test-pr_sentence_terminal.c
tests/unictype/test-pr_terminal_punctuation.c
tests/unictype/test-pr_unassigned_code_value.c
tests/unictype/test-pr_unified_ideograph.c
tests/unictype/test-pr_uppercase.c
tests/unictype/test-pr_xid_continue.c
tests/unictype/test-pr_xid_start.c
tests/unigbrk/GraphemeBreakTest.txt
tests/unigbrk/test-uc-gbrk-prop.h
tests/unilbrk/test-u16-possible-linebreaks.c
tests/unilbrk/test-u32-possible-linebreaks.c
tests/unilbrk/test-u8-possible-linebreaks.c
tests/uniname/NameAliases.txt
tests/uniname/UnicodeData.txt
tests/uninorm/NormalizationTest.txt
tests/uniwbrk/WordBreakTest.txt
tests/uniwidth/test-uc_width2.sh