summaryrefslogtreecommitdiff
path: root/tests/unigbrk
diff options
context:
space:
mode:
authorBruno Haible <bruno@clisp.org>2021-12-31 18:38:12 +0100
committerBruno Haible <bruno@clisp.org>2021-12-31 18:38:12 +0100
commit14db2b71b5bd05b94ec6126617fd32cd5f1016cd (patch)
tree3b05a875542f85aaec8171d063463e99f5cada6c /tests/unigbrk
parent5610f882b056c5cd528989f747561ee69c89045b (diff)
downloadgnulib-14db2b71b5bd05b94ec6126617fd32cd5f1016cd.tar.gz
Update to Unicode 14.0.0.
* lib/gen-uni-tables.c (UC_JOINING_GROUP_THIN_YEH, UC_JOINING_GROUP_VERTICAL_TAIL): New enum values. (fill_arabicshaping, joining_group_as_c_identifier): Recognize these joining groups. * lib/unictype.in.h (UC_JOINING_GROUP_THIN_YEH, UC_JOINING_GROUP_VERTICAL_TAIL): New enum values. * lib/unictype/joininggroup_name.h: Add the THIN_YEH, VERTICAL_TAIL joining groups. * lib/unictype/joininggroup_byname.gperf: Likewise. * lib/gen-uni-tables.c (LBP_ID1, LBP_ID2): New enum values. (LBP_ID): Assign artificial value. (get_lbp): Use the extended_pictographic property to assign LBP_ID1, LBP_ID2 instead of LBP_ID. Update such that unilbrk/lbrkprop.txt comes out as expected. (debug_output_lbp): Print either LBP_ID1 or LBP_ID2 as LBP_ID. (lbp_value_to_string): Handle LBP_ID1, LBP_ID2 instead of LBP_ID. (output_lbrk_rules_as_tables): Treat LBP_ID as macro that maps to two table rows/columns. In rule LB30b, use LBP_ID2 in addition to LBP_EB. Remove redundant part of rule LB27. * lib/unilbrk/lbrktables.h (LBP_ID1, LBP_ID2): New enum values. (LBP_ID): Remove enum value. (unilbrk_table): Update declaration. * lib/unilbrk/u8-possible-linebreaks.c (u8_possible_linebreaks_loop): Use LBP_ID1 instead of LBP_ID. * lib/unilbrk/u16-possible-linebreaks.c (u16_possible_linebreaks_loop): Likewise. * lib/unilbrk/u32-possible-linebreaks.c (u32_possible_linebreaks_loop): Likewise. * tests/unilbrk/test-u8-possible-linebreaks.c (test_function): Add a test of potential future emoji. * tests/unilbrk/test-u16-possible-linebreaks.c (test_function): Likewise. * tests/unilbrk/test-u32-possible-linebreaks.c (test_function): Likewise. * lib/uniwidth/width.c (nonspacing_table_data, nonspacing_table_ind): Update. (uc_width): Assign width 2 to the characters 0x1AFF0..0x1AFF3, 0x1AFF5..0x1AFFB, 0x1AFFD..0x1AFFE, 0x1B120..0x1B122, 0x1F6DD..0x1F6DF, 0x1F7F0, 0x1FA7B..0x1FA7C, 0x1FAA9..0x1FAAC, 0x1FAB7..0x1FABA, 0x1FAC3..0x1FAC5, 0x1FAD7..0x1FAD9, 0x1FAE0..0x1FAE7, 0x1FAF0..0x1FAF6. * tests/uniwidth/test-uc_width2.sh: Expect width 0 for the characters 0x0890..0x0891, 0x0898..0x089F, 0x08CA..0x0902, 0x0C3C, 0x180F, 0x1AC1..0x1ACE, 0x1DFA, 0x10F82..0x10F85, 0x11070, 0x11073..0x11074, 0x110C2, 0x1CF00..0x1CF2D, 0x1CF30..0x1CF46, 0x1E2AE. Expect ambiguous width for the character 0x1734. Expect width 2 for the characters 0x1AFF0..0x1AFF3, 0x1AFF5..0x1AFFB, 0x1AFFD..0x1AFFE, 0x1B120..0x1B122, 0x1F6DD..0x1F6DF, 0x1F7F0, 0x1FA7B..0x1FA7C, 0x1FAA9..0x1FAAC, 0x1FAB7..0x1FABA, 0x1FAC3..0x1FAC5, 0x1FAD7..0x1FAD9, 0x1FAE0..0x1FAE7, 0x1FAF0..0x1FAF6. * 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.
Diffstat (limited to 'tests/unigbrk')
-rw-r--r--tests/unigbrk/GraphemeBreakTest.txt6
-rw-r--r--tests/unigbrk/test-uc-gbrk-prop.h33
2 files changed, 30 insertions, 9 deletions
diff --git a/tests/unigbrk/GraphemeBreakTest.txt b/tests/unigbrk/GraphemeBreakTest.txt
index 5baf292a07..eff2fd33b0 100644
--- a/tests/unigbrk/GraphemeBreakTest.txt
+++ b/tests/unigbrk/GraphemeBreakTest.txt
@@ -1,6 +1,6 @@
-# GraphemeBreakTest-13.0.0.txt
-# Date: 2019-11-15, 19:49:10 GMT
-# © 2019 Unicode®, Inc.
+# GraphemeBreakTest-14.0.0.txt
+# Date: 2021-03-08, 06:22:32 GMT
+# © 2021 Unicode®, Inc.
# Unicode and the Unicode Logo are registered trademarks of Unicode, Inc. in the U.S. and other countries.
# For terms of use, see http://www.unicode.org/terms_of_use.html
#
diff --git a/tests/unigbrk/test-uc-gbrk-prop.h b/tests/unigbrk/test-uc-gbrk-prop.h
index 99bbb55f32..9a766b6a7c 100644
--- a/tests/unigbrk/test-uc-gbrk-prop.h
+++ b/tests/unigbrk/test-uc-gbrk-prop.h
@@ -79,7 +79,11 @@
{ 0x082E, GBP_EXTEND },
{ 0x0859, GBP_OTHER },
{ 0x085C, GBP_EXTEND },
-{ 0x08D3, GBP_OTHER },
+{ 0x0890, GBP_OTHER },
+{ 0x0892, GBP_PREPEND },
+{ 0x0898, GBP_OTHER },
+{ 0x08A0, GBP_EXTEND },
+{ 0x08CA, GBP_OTHER },
{ 0x08E2, GBP_EXTEND },
{ 0x08E3, GBP_PREPEND },
{ 0x0903, GBP_EXTEND },
@@ -190,6 +194,8 @@
{ 0x0C01, GBP_EXTEND },
{ 0x0C04, GBP_SPACINGMARK },
{ 0x0C05, GBP_EXTEND },
+{ 0x0C3C, GBP_OTHER },
+{ 0x0C3D, GBP_EXTEND },
{ 0x0C3E, GBP_OTHER },
{ 0x0C41, GBP_EXTEND },
{ 0x0C45, GBP_SPACINGMARK },
@@ -325,8 +331,10 @@
{ 0x1360, GBP_EXTEND },
{ 0x1712, GBP_OTHER },
{ 0x1715, GBP_EXTEND },
+{ 0x1716, GBP_SPACINGMARK },
{ 0x1732, GBP_OTHER },
-{ 0x1735, GBP_EXTEND },
+{ 0x1734, GBP_EXTEND },
+{ 0x1735, GBP_SPACINGMARK },
{ 0x1752, GBP_OTHER },
{ 0x1754, GBP_EXTEND },
{ 0x1772, GBP_OTHER },
@@ -344,6 +352,7 @@
{ 0x180B, GBP_OTHER },
{ 0x180E, GBP_EXTEND },
{ 0x180F, GBP_CONTROL },
+{ 0x1810, GBP_EXTEND },
{ 0x1885, GBP_OTHER },
{ 0x1887, GBP_EXTEND },
{ 0x18A9, GBP_OTHER },
@@ -378,7 +387,7 @@
{ 0x1A7F, GBP_OTHER },
{ 0x1A80, GBP_EXTEND },
{ 0x1AB0, GBP_OTHER },
-{ 0x1AC1, GBP_EXTEND },
+{ 0x1ACF, GBP_EXTEND },
{ 0x1B00, GBP_OTHER },
{ 0x1B04, GBP_EXTEND },
{ 0x1B05, GBP_SPACINGMARK },
@@ -429,8 +438,6 @@
{ 0x1CF8, GBP_SPACINGMARK },
{ 0x1CFA, GBP_EXTEND },
{ 0x1DC0, GBP_OTHER },
-{ 0x1DFA, GBP_EXTEND },
-{ 0x1DFB, GBP_OTHER },
{ 0x1E00, GBP_EXTEND },
{ 0x200B, GBP_OTHER },
{ 0x200C, GBP_CONTROL },
@@ -1379,12 +1386,18 @@
{ 0x10EAD, GBP_EXTEND },
{ 0x10F46, GBP_OTHER },
{ 0x10F51, GBP_EXTEND },
+{ 0x10F82, GBP_OTHER },
+{ 0x10F86, GBP_EXTEND },
{ 0x11000, GBP_OTHER },
{ 0x11001, GBP_SPACINGMARK },
{ 0x11002, GBP_EXTEND },
{ 0x11003, GBP_SPACINGMARK },
{ 0x11038, GBP_OTHER },
{ 0x11047, GBP_EXTEND },
+{ 0x11070, GBP_OTHER },
+{ 0x11071, GBP_EXTEND },
+{ 0x11073, GBP_OTHER },
+{ 0x11075, GBP_EXTEND },
{ 0x1107F, GBP_OTHER },
{ 0x11082, GBP_EXTEND },
{ 0x11083, GBP_SPACINGMARK },
@@ -1395,6 +1408,8 @@
{ 0x110BB, GBP_EXTEND },
{ 0x110BD, GBP_OTHER },
{ 0x110BE, GBP_PREPEND },
+{ 0x110C2, GBP_OTHER },
+{ 0x110C3, GBP_EXTEND },
{ 0x110CD, GBP_OTHER },
{ 0x110CE, GBP_PREPEND },
{ 0x11100, GBP_OTHER },
@@ -1505,7 +1520,7 @@
{ 0x116B8, GBP_EXTEND },
{ 0x1171D, GBP_OTHER },
{ 0x11720, GBP_EXTEND },
-{ 0x11722, GBP_SPACINGMARK },
+{ 0x11722, GBP_OTHER },
{ 0x11726, GBP_EXTEND },
{ 0x11727, GBP_SPACINGMARK },
{ 0x1172C, GBP_EXTEND },
@@ -1613,6 +1628,10 @@
{ 0x1BC9F, GBP_EXTEND },
{ 0x1BCA0, GBP_OTHER },
{ 0x1BCA4, GBP_CONTROL },
+{ 0x1CF00, GBP_OTHER },
+{ 0x1CF2E, GBP_EXTEND },
+{ 0x1CF30, GBP_OTHER },
+{ 0x1CF47, GBP_EXTEND },
{ 0x1D165, GBP_OTHER },
{ 0x1D166, GBP_EXTEND },
{ 0x1D167, GBP_SPACINGMARK },
@@ -1652,6 +1671,8 @@
{ 0x1E02B, GBP_EXTEND },
{ 0x1E130, GBP_OTHER },
{ 0x1E137, GBP_EXTEND },
+{ 0x1E2AE, GBP_OTHER },
+{ 0x1E2AF, GBP_EXTEND },
{ 0x1E2EC, GBP_OTHER },
{ 0x1E2F0, GBP_EXTEND },
{ 0x1E8D0, GBP_OTHER },