summaryrefslogtreecommitdiff
path: root/lib
diff options
context:
space:
mode:
authorBruno Haible <bruno@clisp.org>2021-12-29 00:06:00 +0100
committerBruno Haible <bruno@clisp.org>2021-12-29 00:06:00 +0100
commitc8d8a8ed6f782efbcbdbe90467050c0eb9fb76b3 (patch)
treeb119dfbd91459d8d1c7f3661af57b20014f5db00 /lib
parentd798516dca5a6a6bccf79806c267f8406b0f0757 (diff)
downloadgnulib-c8d8a8ed6f782efbcbdbe90467050c0eb9fb76b3.tar.gz
unilbrk: Restore deviation for (IS,AL) pair.
* lib/gen-uni-tables.c (output_lbrk_rules_as_tables): Disable rule LB29. * lib/unilbrk/lbrktables.c: Regenerated. * tests/unilbrk/test-u8-possible-linebreaks.c (main): Add test case with HTML markup. * tests/unilbrk/test-u16-possible-linebreaks.c (main): Likewise. * tests/unilbrk/test-u32-possible-linebreaks.c (main): Likewise. * tests/unilbrk/test-ulc-possible-linebreaks.c (main): Likewise.
Diffstat (limited to 'lib')
-rw-r--r--lib/gen-uni-tables.c4
-rw-r--r--lib/unilbrk/lbrktables.c2
2 files changed, 5 insertions, 1 deletions
diff --git a/lib/gen-uni-tables.c b/lib/gen-uni-tables.c
index d9f81943b5..3d1b718067 100644
--- a/lib/gen-uni-tables.c
+++ b/lib/gen-uni-tables.c
@@ -8149,8 +8149,12 @@ output_lbrk_rules_as_tables (const char *filename, const char *version)
/* (LB29) Do not break between numeric punctuation and alphabetics
("e.g."). */
+ /* We don't implement this rule, because we find it desirable to break before
+ the HTML tag "</P>" in strings like "<P>Some sentence.</P>". */
+#if 0
before = LBP_IS; after = LBP_AL; table[before][after].prohibited_no_sp = true;
before = LBP_IS; after = LBP_HL; table[before][after].prohibited_no_sp = true;
+#endif
/* (LB28) Do not break between alphabetics ("at"). */
before = LBP_AL; after = LBP_AL; table[before][after].prohibited_no_sp = true;
diff --git a/lib/unilbrk/lbrktables.c b/lib/unilbrk/lbrktables.c
index dc6b3931cf..fd72a5cd84 100644
--- a/lib/unilbrk/lbrktables.c
+++ b/lib/unilbrk/lbrktables.c
@@ -50,7 +50,7 @@ const unsigned char unilbrk_table[30][30] =
/* 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, 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, 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, I, D, D, D, D, D, D, I, D, I, D, D, },
+/* 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, 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, 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, },