From c8d8a8ed6f782efbcbdbe90467050c0eb9fb76b3 Mon Sep 17 00:00:00 2001
From: Bruno Haible <bruno@clisp.org>
Date: Wed, 29 Dec 2021 00:06:00 +0100
Subject: 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.
---
 tests/unilbrk/test-u16-possible-linebreaks.c | 19 +++++++++++++++++++
 tests/unilbrk/test-u32-possible-linebreaks.c | 19 +++++++++++++++++++
 tests/unilbrk/test-u8-possible-linebreaks.c  | 17 ++++++++++++++++-
 tests/unilbrk/test-ulc-possible-linebreaks.c | 15 +++++++++++++++
 4 files changed, 69 insertions(+), 1 deletion(-)

(limited to 'tests')

diff --git a/tests/unilbrk/test-u16-possible-linebreaks.c b/tests/unilbrk/test-u16-possible-linebreaks.c
index b27d75b2bc..c8c5c50a7a 100644
--- a/tests/unilbrk/test-u16-possible-linebreaks.c
+++ b/tests/unilbrk/test-u16-possible-linebreaks.c
@@ -95,5 +95,24 @@ main ()
     free (p);
   }
 
+  /* Test line breaking in a string with HTML markup.  */
+  {
+    static const uint16_t input[21] =
+      {
+        '<', 'P', '>', 'S', 'o', 'm', 'e', ' ', 's', 'e', 'n', 't',
+        'e', 'n', 'c', 'e', '.', '<', '/', 'P', '>'
+      };
+    char *p = (char *) malloc (SIZEOF (input));
+    size_t i;
+
+    u16_possible_linebreaks (input, SIZEOF (input), "UTF-8", p);
+    for (i = 0; i < 21; i++)
+      {
+        ASSERT (p[i] == (i == 8 || i == 17 || i == 19 ? UC_BREAK_POSSIBLE :
+                         UC_BREAK_PROHIBITED));
+      }
+    free (p);
+  }
+
   return 0;
 }
diff --git a/tests/unilbrk/test-u32-possible-linebreaks.c b/tests/unilbrk/test-u32-possible-linebreaks.c
index 1474ae1c27..b41f49cf2d 100644
--- a/tests/unilbrk/test-u32-possible-linebreaks.c
+++ b/tests/unilbrk/test-u32-possible-linebreaks.c
@@ -95,5 +95,24 @@ main ()
     free (p);
   }
 
+  /* Test line breaking in a string with HTML markup.  */
+  {
+    static const uint32_t input[21] =
+      {
+        '<', 'P', '>', 'S', 'o', 'm', 'e', ' ', 's', 'e', 'n', 't',
+        'e', 'n', 'c', 'e', '.', '<', '/', 'P', '>'
+      };
+    char *p = (char *) malloc (SIZEOF (input));
+    size_t i;
+
+    u32_possible_linebreaks (input, SIZEOF (input), "UTF-8", p);
+    for (i = 0; i < 21; i++)
+      {
+        ASSERT (p[i] == (i == 8 || i == 17 || i == 19 ? UC_BREAK_POSSIBLE :
+                         UC_BREAK_PROHIBITED));
+      }
+    free (p);
+  }
+
   return 0;
 }
diff --git a/tests/unilbrk/test-u8-possible-linebreaks.c b/tests/unilbrk/test-u8-possible-linebreaks.c
index c55e900696..b07464c289 100644
--- a/tests/unilbrk/test-u8-possible-linebreaks.c
+++ b/tests/unilbrk/test-u8-possible-linebreaks.c
@@ -82,12 +82,27 @@ main ()
     size_t i;
 
     u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p);
-    for (i = 0; i < 4; i++)
+    for (i = 0; i < 6; i++)
       {
         ASSERT (p[i] == (i == 5 ? UC_BREAK_POSSIBLE : UC_BREAK_PROHIBITED));
       }
     free (p);
   }
 
+  /* Test line breaking in a string with HTML markup.  */
+  {
+    static const uint8_t input[21] = "<P>Some sentence.</P>";
+    char *p = (char *) malloc (SIZEOF (input));
+    size_t i;
+
+    u8_possible_linebreaks (input, SIZEOF (input), "UTF-8", p);
+    for (i = 0; i < 21; i++)
+      {
+        ASSERT (p[i] == (i == 8 || i == 17 || i == 19 ? UC_BREAK_POSSIBLE :
+                         UC_BREAK_PROHIBITED));
+      }
+    free (p);
+  }
+
   return 0;
 }
diff --git a/tests/unilbrk/test-ulc-possible-linebreaks.c b/tests/unilbrk/test-ulc-possible-linebreaks.c
index 24bae4b717..f3ad7f9222 100644
--- a/tests/unilbrk/test-ulc-possible-linebreaks.c
+++ b/tests/unilbrk/test-ulc-possible-linebreaks.c
@@ -48,6 +48,21 @@ main ()
       }
     free (p);
   }
+
+  /* Test line breaking in a string with HTML markup.  */
+  {
+    static const char input[21] = "<P>Some sentence.</P>";
+    char *p = (char *) malloc (SIZEOF (input));
+    size_t i;
+
+    ulc_possible_linebreaks (input, SIZEOF (input), "UTF-8", p);
+    for (i = 0; i < 21; i++)
+      {
+        ASSERT (p[i] == (i == 8 || i == 17 || i == 19 ? UC_BREAK_POSSIBLE :
+                         UC_BREAK_PROHIBITED));
+      }
+    free (p);
+  }
 #endif
 
   return 0;
-- 
cgit v1.2.1