X-Git-Url: http://www.chiark.greenend.org.uk/ucgi/~mdw/git/disorder/blobdiff_plain/caecd4f412422d8130d616da33325e03557218e7..a89e0ecf7c67ef6af6678985060a0d8e7bae5fba:/lib/unicode.h

diff --git a/lib/unicode.h b/lib/unicode.h
index 47b39f0..b6d6813 100644
--- a/lib/unicode.h
+++ b/lib/unicode.h
@@ -2,20 +2,18 @@
  * This file is part of DisOrde
  * Copyright (C) 2007 Richard Kettlewell
  *
- * This program is free software; you can redistribute it and/or modify
+ * 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
- * the Free Software Foundation; either version 2 of the License, or
+ * the Free Software Foundation, either version 3 of the License, or
  * (at your option) any later version.
- *
- * This program is distributed in the hope that it will be useful, but
- * WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
- * General Public License for more details.
- *
+ * 
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ * 
  * You should have received a copy of the GNU General Public License
- * along with this program; if not, write to the Free Software
- * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307
- * USA
+ * along with this program.  If not, see <http://www.gnu.org/licenses/>.
  */
 /** @file lib/unicode.h
  * @brief Unicode support functions
@@ -36,10 +34,20 @@
  */
 typedef struct utf32_iterator_data *utf32_iterator;
 
+/** @brief Property tailor function
+ * @param c Code point
+ * @return Tailored property or -1 to use standard value
+ *
+ * See also utf32_iterator_tailor_word_break().
+ */
+typedef int unicode_property_tailor(uint32_t c);
+
 char *utf32_to_utf8(const uint32_t *s, size_t ns, size_t *nd);
 uint32_t *utf8_to_utf32(const char *s, size_t ns, size_t *nd);
 int utf8_valid(const char *s, size_t ns);
 
+int utf32_combining_class(uint32_t c);
+
 size_t utf32_len(const uint32_t *s);
 int utf32_cmp(const uint32_t *a, const uint32_t *b);
 
@@ -49,6 +57,12 @@ char *utf8_decompose_canon(const char *s, size_t ns, size_t *ndp);
 uint32_t *utf32_decompose_compat(const uint32_t *s, size_t ns, size_t *ndp);
 char *utf8_decompose_compat(const char *s, size_t ns, size_t *ndp);
 
+uint32_t *utf32_compose_canon(const uint32_t *s, size_t ns, size_t *ndp);
+char *utf8_compose_canon(const char *s, size_t ns, size_t *ndp);
+
+uint32_t *utf32_compose_compat(const uint32_t *s, size_t ns, size_t *ndp);
+char *utf8_compose_compat(const char *s, size_t ns, size_t *ndp);
+
 uint32_t *utf32_casefold_canon(const uint32_t *s, size_t ns, size_t *ndp);
 char *utf8_casefold_canon(const char *s, size_t ns, size_t *ndp);
 
@@ -67,6 +81,13 @@ int utf32_iterator_advance(utf32_iterator it, size_t n);
 uint32_t utf32_iterator_code(utf32_iterator it);
 int utf32_iterator_grapheme_boundary(utf32_iterator it);
 int utf32_iterator_word_boundary(utf32_iterator it);
+void utf32_iterator_tailor_word_break(utf32_iterator it,
+                                      unicode_property_tailor *pt);
+
+uint32_t **utf32_word_split(const uint32_t *s, size_t ns, size_t *nwp,
+                            unicode_property_tailor *wbreak);
+char **utf8_word_split(const char *s, size_t ns, size_t *nwp,
+                            unicode_property_tailor *wbreak);
 
 /** @brief Convert 0-terminated UTF-32 to UTF-8
  * @param s 0-terminated UTF-32 string