Tailor the linebreaking algorithm.

diff --git a/ChangeLog b/ChangeLog
index fe52409adc6a33947f34aca0f1ea17616449d23e..6b911c2e5609b31549b327eca6fb11fbd97958c2 100644 (file)
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,4 +1,9 @@
-2008-05-11  Bruno Haible  <bruno@clisp.org>
+2008-05-12  Bruno Haible  <bruno@clisp.org>
+
+       Tailor the linebreaking algorithm.
+       * lib/unilbrk/tables.c (unilbrk_table): Change (IS,AL) entry.
+
+2008-05-12  Bruno Haible  <bruno@clisp.org>
 
        Update to Unicode 5.0.0.
        * lib/unilbrk/tables.h (LBP_*): Add LBP_WJ, LBP_H2, LBP_H3, LBP_JL,

diff --git a/lib/unilbrk/tables.c b/lib/unilbrk/tables.c
index 3d3960e9ebc2459286e0c891a24ae66bacec3b1c..e6ee01ffe2b6ea44358389799592e15b0ebfcdf2 100644 (file)
--- a/lib/unilbrk/tables.c
+++ b/lib/unilbrk/tables.c
@@ -39,7 +39,7 @@ const unsigned char unilbrk_table[24][24] =
 /* NS */ { P, I, D, I, D, I, P, P, D, I, D, I, P, D, D, D, P, 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, },
 /* QU */ { P, I, I, I, I, I, P, P, I, I, P, I, P, I, I, I, P, I, I, I, I, I, I, I, },
-/* IS */ { P, I, D, I, D, I, P, P, D, I, D, I, P, I, D, D, P, I, D, D, D, D, D, D, },
+/* IS */ { P, I, D, I, D, I, P, P, D, I, D, I, P, I, D, D, P, D, D, D, D, D, D, D, },
 /* NU */ { P, I, D, I, D, I, P, P, I, I, D, I, P, I, I, I, P, I, D, D, D, D, D, D, },
 /* PO */ { P, I, D, I, D, I, P, P, D, I, I, I, P, I, D, D, P, I, D, D, D, D, D, D, },
 /* PR */ { P, I, D, I, D, I, P, P, D, I, I, I, P, I, D, D, P, I, I, I, I, I, I, I, },
@@ -54,6 +54,10 @@ const unsigned char unilbrk_table[24][24] =
 /* "" */
 /* before */
 };
+/* Note: The (IS,AL) entry has been changed from I to D. In other words, the
+   rule "Do not break between numeric punctuation and alphabetics" is not
+   implemented here. We want to break before the HTML tag in strings like
+   "<P>Some sentence.</P>"  */
 /* Note: The (B2,B2) entry should probably be D instead of P.  */
 /* Note: The (PR,ID) entry should probably be D instead of I.  */
 /* Note: The (WJ,*) and (GL,*) entries should probably be P instead of I.  */