X-Git-Url: http://review.tizen.org/git/?a=blobdiff_plain;f=glib%2Fgunidecomp.c;h=44943c84fe7179bbcb284d1a6fe8892c266c35c7;hb=0a4ee12c7a9dfc82443133dfb2b18fb411d79f48;hp=a6397870c1a406cc819e364b84940b1f00896ab5;hpb=615977d337c7ba776ac2eda6c688bf6f69316c4d;p=platform%2Fupstream%2Fglib.git

diff --git a/glib/gunidecomp.c b/glib/gunidecomp.c
index a639787..44943c8 100644
--- a/glib/gunidecomp.c
+++ b/glib/gunidecomp.c
@@ -15,8 +15,30 @@
  *
  * You should have received a copy of the GNU Lesser General Public
  * License along with the Gnome Library; see the file COPYING.LIB.  If not,
- * write to the Free Software Foundation, Inc., 59 Temple Place - Suite 330,
- *   Boston, MA 02111-1307, USA.
+ * see <http://www.gnu.org/licenses/>.
+ */
+
+/**
+ * SECTION:unicode
+ * @Title: Unicode Manipulation
+ * @Short_description: functions operating on Unicode characters and
+ *     UTF-8 strings
+ * @See_also: g_locale_to_utf8(), g_locale_from_utf8()
+ *
+ * This section describes a number of functions for dealing with
+ * Unicode characters and strings. There are analogues of the
+ * traditional `ctype.h` character classification and case conversion
+ * functions, UTF-8 analogues of some string utility functions,
+ * functions to perform normalization, case conversion and collation
+ * on UTF-8 strings and finally functions to convert between the UTF-8,
+ * UTF-16 and UCS-4 encodings of Unicode.
+ *
+ * The implementations of the Unicode functions in GLib are based
+ * on the Unicode Character Data tables, which are available from
+ * [www.unicode.org](http://www.unicode.org/).
+ * GLib 2.8 supports Unicode 4.0, GLib 2.10 supports Unicode 4.1,
+ * GLib 2.12 supports Unicode 5.0, GLib 2.16.3 supports Unicode 5.1,
+ * GLib 2.30 supports Unicode 6.0.
  */
 
 #include "config.h"
@@ -53,7 +75,7 @@
  * 
  * Determines the canonical combining class of a Unicode character.
  * 
- * Return value: the combining class of the character
+ * Returns: the combining class of the character
  *
  * Since: 2.14
  **/
@@ -202,7 +224,7 @@ find_decomposition (gunichar ch,
  *
  * Computes the canonical decomposition of a Unicode character.  
  * 
- * Return value: a newly allocated string of Unicode characters.
+ * Returns: a newly allocated string of Unicode characters.
  *   @result_len is set to the resulting length of the string.
  *
  * Deprecated: 2.30: Use the more flexible g_unichar_fully_decompose()
@@ -500,7 +522,7 @@ _g_utf8_normalize_wc (const gchar    *str,
  * a legacy encoding or pass it to a system with
  * less capable Unicode handling.
  *
- * Return value: a newly allocated string, that is the
+ * Returns: a newly allocated string, that is the
  *   normalized form of @str, or %NULL if @str is not
  *   valid UTF-8.
  **/
@@ -573,7 +595,8 @@ decompose_hangul_step (gunichar  ch,
  * recursively call this function on @a.  Or use
  * g_unichar_fully_decompose().
  *
- * See <ulink url="http://unicode.org/reports/tr15/">UAX#15</ulink>
+ * See
+ * [UAX#15](http://unicode.org/reports/tr15/)
  * for details.
  *
  * Returns: %TRUE if the character could be decomposed
@@ -629,17 +652,18 @@ g_unichar_decompose (gunichar  ch,
  * Performs a single composition step of the
  * Unicode canonical composition algorithm.
  *
- * This function does not perform algorithmic composition
- * for Hangul characters, and does not include compatibility
- * compositions. It does, however, include 'singleton'
- * compositions which replace a character by a single
- * other character. To obtain these, pass zero for @b.
- *
- * This function includes algorithmic Hangul Jamo composition.
+ * This function includes algorithmic Hangul Jamo composition,
+ * but it is not exactly the inverse of g_unichar_decompose().
+ * No composition can have either of @a or @b equal to zero.
+ * To be precise, this function composes if and only if
+ * there exists a Primary Composite P which is canonically
+ * equivalent to the sequence <@a,@b>.  See the Unicode
+ * Standard for the definition of Primary Composite.
  *
  * If @a and @b do not compose a new character, @ch is set to zero.
  *
- * See <ulink url="http://unicode.org/reports/tr15/">UAX#15</ulink>
+ * See
+ * [UAX#15](http://unicode.org/reports/tr15/)
  * for details.
  *
  * Returns: %TRUE if the characters could be composed
@@ -662,7 +686,7 @@ g_unichar_compose (gunichar  a,
  * g_unichar_fully_decompose:
  * @ch: a Unicode character.
  * @compat: whether perform canonical or compatibility decomposition
- * @result: location to store decomposed result, or %NULL
+ * @result: (allow-none): location to store decomposed result, or %NULL
  * @result_len: length of @result
  *
  * Computes the canonical or compatibility decomposition of a
@@ -673,14 +697,19 @@ g_unichar_compose (gunichar  a,
  * The decomposed sequence is placed in @result.  Only up to
  * @result_len characters are written into @result.  The length
  * of the full decomposition (irrespective of @result_len) is
- * returned by the function.  For canonical decomposition, a
- * result buffer of length 4 is always enough, whereas for
- * compatibility decomposition, a buffer of 18 is enough.
+ * returned by the function.  For canonical decomposition,
+ * currently all decompositions are of length at most 4, but
+ * this may change in the future (very unlikely though).
+ * At any rate, Unicode does guarantee that a buffer of length
+ * 18 is always enough for both compatibility and canonical
+ * decompositions, so that is the size recommended. This is provided
+ * as %G_UNICHAR_MAX_DECOMPOSITION_LENGTH.
  *
- * See <ulink url="http://unicode.org/reports/tr15/">UAX#15</ulink>
+ * See
+ * [UAX#15](http://unicode.org/reports/tr15/)
  * for details.
  *
- * Return value: the length of the full decomposition.
+ * Returns: the length of the full decomposition.
  *
  * Since: 2.30
  **/