Add grapheme cluster break functions.

12 files changed, 106 insertions, 20 deletions

diff --git a/AUTHORS b/AUTHORS
index 8bedd79..c690b65 100644
--- a/AUTHORS
+++ b/AUTHORS
@@ -1 +1,9 @@
-Bruno Haible <bruno@clisp.org>
+Authors of GNU libunistring
+
+The following contributions warranted legal paper exchanges with the
+Free Software Foundation.  See also the ChangeLog and THANKS files in this
+package and the ChangeLog file in gnulib (where most of the code is imported
+from).
+
+Bruno Haible        <bruno@clisp.org>           all files
+Ben Pfaff           <blp@cs.stanford.edu>       unigbrk
diff --git a/ChangeLog b/ChangeLog
index e5a7edd..4d69c82 100644
--- a/ChangeLog
+++ b/ChangeLog
@@ -1,3 +1,24 @@
+2011-03-29  Bruno Haible  <bruno@clisp.org>
+
+	Add grapheme cluster break functions.
+	* autogen.sh (GNULIB_MODULES): Add unigbrk/*.
+	* gnulib-local/lib/unigbrk.in.h.diff: New file.
+	* gnulib-local/Makefile.am (EXTRA_DIST): Add lib/unigbrk.in.h.diff.
+	* lib/Makefile.am (nobase_include_HEADERS, HEADERS_WITH_EXTERNS): Add
+	unigbrk.h.
+	* doc/Makefile.am (libunistring_TEXINFOS): Move unigbrk.texi before
+	uniwbrk.texi.
+	* doc/libunistring.texi: Move chapter unigbrk.h before chapter
+	uniwbrk.h.
+	* doc/unigbrk.texi (unigbrk.h): Add more index entries. Enhance the
+	explanation of what a grapheme cluster is.
+	(Grapheme cluster break property): Add missing quotes. Avoid imperative
+	form.
+	* doc/uniwbrk.texi (uniwbrk.h): Add more index entries.
+	* AUTHORS: List Ben Pfaff.
+	* README: Mention the new include file unigbrk.h.
+	* NEWS: Likewise.
+
 2011-03-28  Ben Pfaff  <blp@cs.stanford.edu>
 
 	Document grapheme cluster break functions.
diff --git a/NEWS b/NEWS
index d5aa25a..fbcc453 100644
--- a/NEWS
+++ b/NEWS
@@ -1,6 +1,10 @@
 New in 0.9.4:
 * The data tables and line breaking algorithm have been updated to Unicode
   version 6.0.0.
+* A new include file unigbrk.h is provided. It declares functions for
+  grapheme cluster breaking, that is, determining the boundaries between
+  graphemes. See the documentation chapter "Grapheme cluster breaks in strings"
+  for details.
 * In the include file unictype.h, constants are defined for the group of
   general categories LC ("Cased Letter").
 * In the include file unictype.h, functions for associating canonical
diff --git a/README b/README
index c52e56d..e4bc981 100644
--- a/README
+++ b/README
@@ -11,6 +11,7 @@ It consists of the following parts:
   uniname.h    character names
   unictype.h   character classification and properties
   uniwidth.h   string width when using nonproportional fonts
+  unigbrk.h    grapheme cluster breaks
   uniwbrk.h    word breaks
   unilbrk.h    line breaking algorithm
   uninorm.h    normalization (composition and decomposition)
diff --git a/autogen.sh b/autogen.sh
index bde7758..9be9365 100755
--- a/autogen.sh
+++ b/autogen.sh
@@ -314,6 +314,19 @@ if test $skip_gnulib = false; then
       uniwidth/u32-strwidth
       uniwidth/u32-width
       uniwidth/width
+      unigbrk/base
+      unigbrk/u8-grapheme-breaks
+      unigbrk/u8-grapheme-next
+      unigbrk/u8-grapheme-prev
+      unigbrk/u16-grapheme-breaks
+      unigbrk/u16-grapheme-next
+      unigbrk/u16-grapheme-prev
+      unigbrk/u32-grapheme-breaks
+      unigbrk/u32-grapheme-next
+      unigbrk/u32-grapheme-prev
+      unigbrk/uc-gbrk-prop
+      unigbrk/uc-is-grapheme-break
+      unigbrk/ulc-grapheme-breaks
       uniwbrk/base
       uniwbrk/u8-wordbreaks
       uniwbrk/u16-wordbreaks
diff --git a/doc/Makefile.am b/doc/Makefile.am
index cd5c514..c470f6c 100644
--- a/doc/Makefile.am
+++ b/doc/Makefile.am
@@ -33,7 +33,7 @@ info_TEXINFOS = libunistring.texi
 # List of texinfo sources @included by libunistring.texi, excluding version.texi.
 libunistring_TEXINFOS = \
   unitypes.texi unistr.texi uniconv.texi unistdio.texi uniname.texi \
-  unictype.texi uniwidth.texi uniwbrk.texi unilbrk.texi unigbrk.texi \
+  unictype.texi uniwidth.texi unigbrk.texi uniwbrk.texi unilbrk.texi \
   uninorm.texi unicase.texi uniregex.texi \
   gpl.texi lgpl.texi fdl.texi
 
diff --git a/doc/libunistring.texi b/doc/libunistring.texi
index 32209ab..a6f9c8f 100644
--- a/doc/libunistring.texi
+++ b/doc/libunistring.texi
@@ -158,9 +158,9 @@ A copy of the license is included in @ref{GNU GPL}.
 * uniname.h::                   Names of Unicode characters
 * unictype.h::                  Unicode character classification and properties
 * uniwidth.h::                  Display width
+* unigbrk.h::                   Grapheme cluster breaking
 * uniwbrk.h::                   Word breaks in strings
 * unilbrk.h::                   Line breaking
-* unigbrk.h::                   Grapheme cluster breaking
 * uninorm.h::                   Normalization forms
 * unicase.h::                   Case mappings
 * uniregex.h::                  Regular expressions
@@ -217,16 +217,16 @@ Properties
 * Properties as objects::
 * Properties as functions::
 
-uniwbrk.h
-
-* Word breaks in a string::
-* Word break property::
-
 unigbrk.h
 
 * Grapheme cluster breaks in a string::
 * Grapheme cluster break property::
 
+uniwbrk.h
+
+* Word breaks in a string::
+* Word break property::
+
 uninorm.h
 
 * Decomposition of characters::
@@ -281,12 +281,12 @@ character names
 character classification and properties
 @item <uniwidth.h>
 string width when using nonproportional fonts
+@item <unigbrk.h>
+grapheme cluster breaks
 @item <uniwbrk.h>
 word breaks
 @item <unilbrk.h>
 line breaking algorithm
-@item <unigbrk.h>
-grapheme cluster breaks
 @item <uninorm.h>
 normalization (composition and decomposition)
 @item <unicase.h>
@@ -763,9 +763,9 @@ NULL is returned and @code{errno} is set.
 @include uniname.texi
 @include unictype.texi
 @include uniwidth.texi
+@include unigbrk.texi
 @include uniwbrk.texi
 @include unilbrk.texi
-@include unigbrk.texi
 @include uninorm.texi
 @include unicase.texi
 @include uniregex.texi
diff --git a/doc/unigbrk.texi b/doc/unigbrk.texi
index db4df6a..196bd9f 100644
--- a/doc/unigbrk.texi
+++ b/doc/unigbrk.texi
@@ -2,11 +2,18 @@
 @chapter Grapheme cluster breaks in strings @code{<unigbrk.h>}
 
 @cindex grapheme cluster breaks
+@cindex grapheme cluster boundaries
 @cindex breaks, grapheme cluster
+@cindex boundaries, between grapheme clusters
 This include file declares functions for determining where in a string
 ``grapheme clusters'' start and end.  A ``grapheme cluster'' is an
 approximation to a user-perceived character, which sometimes
-corresponds to multiple Unicode characters.  The letter @samp{@'e},
+corresponds to multiple Unicode characters.  Editing operations such as
+mouse selection, cursor movement, and backspacing often operate on
+grapheme clusters as units, not on individual characters.
+
+Some grapheme clusters are built from a base character and a combining
+character.  The letter @samp{@'e},
 for example, is most commonly represented in Unicode as a single
 character U+00E8 @sc{LATIN SMALL LETTER E WITH ACUTE}.  It is,
 however, equally valid to use the pair of characters U+0065 @sc{LATIN
@@ -14,6 +21,12 @@ SMALL LETTER E} followed by U+0301 @sc{COMBINING ACUTE ACCENT}.  Since
 the user would perceive this pair of characters as a single character,
 they would be grouped into a single grapheme cluster.
 
+But there are also grapheme clusters that consist of several base characters.
+For example, a Devanagari letter and a Devanagari vowel sign that follows it
+may form a grapheme cluster.  Similarly, some pairs of Thai characters and
+Hangul syllables (formed by two or three Hangul characters) are grapheme
+clusters.
+
 @menu
 * Grapheme cluster breaks in a string::
 * Grapheme cluster break property::
@@ -65,10 +78,11 @@ grapheme cluster break at start of text.
 @node Grapheme cluster break property
 @section Grapheme cluster break property
 
-This is a more low-level API.  The grapheme cluster break property is a property defined
-in Unicode Standard Annex #29, section ``Grapheme Cluster Boundaries, see
-@url{http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries}.@texnl{}  It is
-used for determining the grapheme cluster breaks in a string.
+This is a more low-level API.  The grapheme cluster break property is a
+property defined in Unicode Standard Annex #29, section ``Grapheme Cluster
+Boundaries'', see
+@url{http://www.unicode.org/reports/tr29/#Grapheme_Cluster_Boundaries}.@texnl{}
+It is used for determining the grapheme cluster breaks in a string.
 
 The following are the possible values of the grapheme cluster break
 property.  More values may be added in the future.
@@ -87,7 +101,8 @@ property.  More values may be added in the future.
 @deftypevrx Constant int GBP_LVT
 @end deftypevr
 
-The following function looks up the grapheme cluster break property of a character.
+The following function looks up the grapheme cluster break property of a
+character.
 
 @deftypefun int uc_graphemeclusterbreak_property (ucs4_t @var{uc})
 Returns the Grapheme_Cluster_Break property of a Unicode character.
@@ -102,7 +117,7 @@ Returns true if there is an grapheme cluster boundary between Unicode
 characters @var{a} and @var{b}.
 
 There is always a grapheme cluster break at the start or end of text.
-Specify zero for @var{a} or @var{b} to indicate start of text or end
+You can specify zero for @var{a} or @var{b} to indicate start of text or end
 of text, respectively.
 
 This implements the extended (not legacy) grapheme cluster rules
diff --git a/doc/uniwbrk.texi b/doc/uniwbrk.texi
index 6f06b92..08c273c 100644
--- a/doc/uniwbrk.texi
+++ b/doc/uniwbrk.texi
@@ -2,7 +2,9 @@
 @chapter Word breaks in strings @code{<uniwbrk.h>}
 
 @cindex word breaks
+@cindex word boundaries
 @cindex breaks, word
+@cindex boundaries, between words
 This include file declares functions for determining where in a string
 ``words'' start and end.  Here ``words'' are not necessarily the same as
 entities that can be looked up in dictionaries, but rather groups of
diff --git a/gnulib-local/Makefile.am b/gnulib-local/Makefile.am
index d011b8d..3758f6d 100644
--- a/gnulib-local/Makefile.am
+++ b/gnulib-local/Makefile.am
@@ -1,5 +1,5 @@
 ## Makefile for the gnulib-local directory of GNU libunistring
-## Copyright (C) 2006-2010 Free Software Foundation, Inc.
+## Copyright (C) 2006-2011 Free Software Foundation, Inc.
 ##
 ## This program is free software: you can redistribute it and/or modify
 ## it under the terms of the GNU General Public License as published by
@@ -22,6 +22,7 @@ EXTRA_DIST = \
 lib/unicase.in.h.diff \
 lib/uniconv.in.h.diff \
 lib/unictype.in.h.diff \
+lib/unigbrk.in.h.diff \
 lib/unilbrk.in.h.diff \
 lib/uninorm.in.h.diff \
 lib/unistr.in.h.diff \
diff --git a/gnulib-local/lib/unigbrk.in.h.diff b/gnulib-local/lib/unigbrk.in.h.diff
new file mode 100644
index 0000000..ed6c7e3
--- /dev/null
+++ b/gnulib-local/lib/unigbrk.in.h.diff
@@ -0,0 +1,19 @@
+*** unigbrk.in.h.orig	2011-01-07 17:40:15.000000000 +0100
+--- unigbrk.in.h	2011-03-29 23:36:45.000000000 +0200
+***************
+*** 19,25 ****
+  #define _UNIGBRK_H
+  
+  /* Get bool.  */
+! #include <stdbool.h>
+  
+  /* Get size_t. */
+  #include <stddef.h>
+--- 19,25 ----
+  #define _UNIGBRK_H
+  
+  /* Get bool.  */
+! #include <unistring/stdbool.h>
+  
+  /* Get size_t. */
+  #include <stddef.h>
diff --git a/lib/Makefile.am b/lib/Makefile.am
index 495b134..917ace1 100644
--- a/lib/Makefile.am
+++ b/lib/Makefile.am
@@ -1,5 +1,5 @@
 ## Makefile for the lib subdirectory of GNU libunistring.
-## Copyright (C) 2009-2010 Free Software Foundation, Inc.
+## Copyright (C) 2009-2011 Free Software Foundation, Inc.
 ##
 ## This program is free software: you can redistribute it and/or modify
 ## it under the terms of the GNU General Public License as published by
@@ -36,6 +36,7 @@ nobase_include_HEADERS = \
   uniname.h \
   unictype.h \
   uniwidth.h \
+  unigbrk.h \
   uniwbrk.h \
   unilbrk.h \
   uninorm.h \
@@ -200,6 +201,7 @@ HEADERS_WITH_EXTERNS = \
   uniname.h \
   unictype.h \
   uniwidth.h \
+  unigbrk.h \
   uniwbrk.h \
   unilbrk.h \
   uninorm.h \