From: Bruno Haible Date: Mon, 12 May 2008 17:22:07 +0000 (+0200) Subject: Tailor the linebreaking algorithm. X-Git-Url: https://pintos-os.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=6ea7ea7d376e3112b946577431830294a67760d4;p=pspp Tailor the linebreaking algorithm. --- diff --git a/ChangeLog b/ChangeLog index fe52409adc..6b911c2e56 100644 --- a/ChangeLog +++ b/ChangeLog @@ -1,4 +1,9 @@ -2008-05-11 Bruno Haible +2008-05-12 Bruno Haible + + Tailor the linebreaking algorithm. + * lib/unilbrk/tables.c (unilbrk_table): Change (IS,AL) entry. + +2008-05-12 Bruno Haible 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 3d3960e9eb..e6ee01ffe2 100644 --- 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 + "

Some sentence.

" */ /* 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. */