X-Git-Url: http://www.chiark.greenend.org.uk/ucgi/~mdw/git/disorder/blobdiff_plain/7e3178245205a63f6922bda8bb51cd1ebdc34fa4..16b0fea8ae1a581d568dbee2efa2932aa4e6fcce:/lib/unicode.h

diff --git a/lib/unicode.h b/lib/unicode.h
index a996844..34d4d4d 100644
--- a/lib/unicode.h
+++ b/lib/unicode.h
@@ -1,21 +1,19 @@
 /*
  * This file is part of DisOrde
- * Copyright (C) 2007 Richard Kettlewell
+ * Copyright (C) 2007, 2008, 2013 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
@@ -36,11 +34,24 @@
  */
 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);
+char *utf16_to_utf8(const uint16_t *s, size_t ns, size_t *nd);
+uint16_t *utf8_to_utf16(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);
+size_t utf16_len(const uint16_t *s);
 int utf32_cmp(const uint32_t *a, const uint32_t *b);
 
 uint32_t *utf32_decompose_canon(const uint32_t *s, size_t ns, size_t *ndp);
@@ -73,6 +84,13 @@ 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
@@ -84,6 +102,16 @@ static inline char *utf32nt_to_utf8(const uint32_t *s) {
   return utf32_to_utf8(s, utf32_len(s), 0);
 }
 
+/** @brief Convert 0-terminated UTF-16 to UTF-8
+ * @param s 0-terminated UTF-16 string
+ * @return 0-terminated UTF-8 string or 0 on error
+ *
+ * See utf16_to_utf8() for possible causes of errors.
+ */
+static inline char *utf16nt_to_utf8(const uint16_t *s) {
+  return utf16_to_utf8(s, utf16_len(s), 0);
+}
+
 /** @brief Convert 0-terminated UTF-8 to UTF-32
  * @param s 0-terminated UTF-8 string
  * @return 0-terminated UTF-32 string or 0 on error
@@ -94,6 +122,34 @@ static inline uint32_t *utf8nt_to_utf32(const char *s) {
   return utf8_to_utf32(s, strlen(s), 0);
 }
 
+/** @brief Convert 0-terminated UTF-8 to UTF-16
+ * @param s 0-terminated UTF-8 string
+ * @return 0-terminated UTF-16 string or 0 on error
+ *
+ * See utf8_to_utf16() for possible causes of errors.
+ */
+static inline uint16_t *utf8nt_to_utf16(const char *s) {
+  return utf8_to_utf16(s, strlen(s), 0);
+}
+
+#if _WIN32
+static inline wchar_t *utf8nt_to_wchar(const char *s) {
+  return (wchar_t *)utf8nt_to_utf16(s);
+}
+
+static inline char *wcharnt_to_utf8(const wchar_t *s) {
+  return utf16nt_to_utf8((const uint16_t *)s);
+}
+#else
+static inline wchar_t *utf8nt_to_wchar(const char *s) {
+  return (wchar_t *)utf8nt_to_utf32(s);
+}
+
+static inline char *wcharnt_to_utf8(const wchar_t *s) {
+  return utf32nt_to_utf8((const uint32_t *)s);
+}
+#endif
+
 #endif /* UNICODE_H */
 
 /*