This patch enables Unicode rule (LB29). I had previously disabled it
because I did not like a particular effect of this rule in a special case.
With this patch, only that special case gets exempted.
2024-09-15 Bruno Haible <br...@clisp.org>
unilbrk: Enable most cases of Unicode rule (LB29).
* lib/gen-uni-tables.c (output_lbrk_rules_as_tables): Enable rule LB29.
* lib/unilbrk/lbrktables.c: Regenerated.
* lib/unilbrk/u8-possible-linebreaks.c (u8_possible_linebreaks_loop):
Allow a break between a character with property IS and '<'.
* lib/unilbrk/u16-possible-linebreaks.c (u16_possible_linebreaks_loop):
Likewise.
* lib/unilbrk/u32-possible-linebreaks.c (u32_possible_linebreaks_loop):
Likewise.
diff --git a/lib/gen-uni-tables.c b/lib/gen-uni-tables.c
index 6ac81d0821..f95a78dbf1 100644
--- a/lib/gen-uni-tables.c
+++ b/lib/gen-uni-tables.c
@@ -9273,12 +9273,8 @@ 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; set_table_cell (prohibited_no_sp, true);
before = LBP_IS; after = LBP_HL; set_table_cell (prohibited_no_sp, true);
-#endif
/* (LB28a) Do not break inside the orthographic syllables of Brahmic
scripts. */
diff --git a/lib/unilbrk/lbrktables.c b/lib/unilbrk/lbrktables.c
index 217933a526..c09f5855a7 100644
--- a/lib/unilbrk/lbrktables.c
+++ b/lib/unilbrk/lbrktables.c
@@ -54,7 +54,7 @@ const unsigned char unilbrk_table[41][41] =
/* QU1 */ { P, I, I, I, I, I, P, P, P, P, I, I, I, I, I, I,
P, P, I, I, I, P, I, I, I, I, I, I, I, I, I, I, I, I, I, I,
I, I, I, I, I, },
/* QU2 */ { 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, P, P, P, P, P, P,
P, P, P, P, P, },
/* QU3 */ { P, I, D, I, D, I, P, P, P, P, I, I, D, D, I, D,
P, P, D, D, D, P, D, D, D, D, D, D, D, D, D, D, D, D, D, D,
D, D, D, D, D, },
-/* IS */ { P, I, D, I, D, I, P, P, P, P, I, I, D, D, I, D,
P, P, I, D, D, P, D, D, D, D, D, D, D, D, D, D, D, D, D, D,
D, D, D, D, D, },
+/* IS */ { P, I, D, I, D, I, P, P, P, P, I, I, D, D, I, D,
P, P, I, D, D, P, I, I, D, D, D, D, D, D, D, I, D, D, D, D,
D, D, I, D, D, },
/* NU */ { P, I, D, I, D, I, P, P, P, P, I, I, I, D, I, D,
P, P, D, D, D, P, I, I, D, D, D, D, D, D, D, I, D, D, D, D,
D, D, I, D, D, },
/* PO */ { P, I, D, I, D, I, P, P, P, P, I, I, D, D, I, D,
P, P, I, D, D, P, I, I, D, D, D, D, D, D, D, I, D, D, D, D,
D, D, I, D, D, },
/* PR */ { P, I, D, I, D, I, P, P, P, P, I, I, D, D, I, D,
P, P, I, D, D, P, I, I, I, I, I, I, I, I, I, I, D, D, D, D,
D, D, I, I, I, },
diff --git a/lib/unilbrk/u16-possible-linebreaks.c
b/lib/unilbrk/u16-possible-linebreaks.c
index dde1aa6064..bf0f31057f 100644
--- a/lib/unilbrk/u16-possible-linebreaks.c
+++ b/lib/unilbrk/u16-possible-linebreaks.c
@@ -290,6 +290,14 @@ u16_possible_linebreaks_loop (const uint16_t *s, size_t n,
const char *encoding,
Brahmic scripts, line 4. */
*p = UC_BREAK_PROHIBITED;
}
+ else if (last_prop == LBP_IS && uc == 0x003C)
+ {
+ /* Partially disable (LB29) Do not break between numeric
+ punctuation and alphabetics ("e.g."). We find it
+ desirable to break before the HTML tag "</P>" in
+ strings like "<P>Some sentence.</P>". */
+ *p = UC_BREAK_POSSIBLE;
+ }
else if (last_prop == LBP_RI && prop == LBP_RI)
{
/* (LB30a) Break between two regional indicator symbols
diff --git a/lib/unilbrk/u32-possible-linebreaks.c
b/lib/unilbrk/u32-possible-linebreaks.c
index 9cdda2868d..a7630467a6 100644
--- a/lib/unilbrk/u32-possible-linebreaks.c
+++ b/lib/unilbrk/u32-possible-linebreaks.c
@@ -283,6 +283,14 @@ u32_possible_linebreaks_loop (const uint32_t *s, size_t n,
const char *encoding,
Brahmic scripts, line 4. */
*p = UC_BREAK_PROHIBITED;
}
+ else if (last_prop == LBP_IS && uc == 0x003C)
+ {
+ /* Partially disable (LB29) Do not break between numeric
+ punctuation and alphabetics ("e.g."). We find it
+ desirable to break before the HTML tag "</P>" in
+ strings like "<P>Some sentence.</P>". */
+ *p = UC_BREAK_POSSIBLE;
+ }
else if (last_prop == LBP_RI && prop == LBP_RI)
{
/* (LB30a) Break between two regional indicator symbols
diff --git a/lib/unilbrk/u8-possible-linebreaks.c
b/lib/unilbrk/u8-possible-linebreaks.c
index 6c26a8c26f..7abf20beed 100644
--- a/lib/unilbrk/u8-possible-linebreaks.c
+++ b/lib/unilbrk/u8-possible-linebreaks.c
@@ -290,6 +290,14 @@ u8_possible_linebreaks_loop (const uint8_t *s, size_t n,
const char *encoding,
Brahmic scripts, line 4. */
*p = UC_BREAK_PROHIBITED;
}
+ else if (last_prop == LBP_IS && uc == 0x003C)
+ {
+ /* Partially disable (LB29) Do not break between numeric
+ punctuation and alphabetics ("e.g."). We find it
+ desirable to break before the HTML tag "</P>" in
+ strings like "<P>Some sentence.</P>". */
+ *p = UC_BREAK_POSSIBLE;
+ }
else if (last_prop == LBP_RI && prop == LBP_RI)
{
/* (LB30a) Break between two regional indicator symbols
