X-Git-Url: http://www.chiark.greenend.org.uk/ucgi/~mdw/git/disorder/blobdiff_plain/1452363583a176aafcb00a17bf76c223e3a1f31c..4942ee7d61bf22ba38bf026c7d05028cb7db0d54:/lib/unidata.h

diff --git a/lib/unidata.h b/lib/unidata.h
index 3688a76..1d89322 100644
--- a/lib/unidata.h
+++ b/lib/unidata.h
@@ -1,4 +1,10 @@
-/* Automatically generated file, see scripts/make-unidata */
+/** @file lib/unidata.h
+ * @brief Unicode tables
+ *
+ * Automatically generated file, see scripts/make-unidata
+ *
+ * DO NOT EDIT.
+ */
 #ifndef UNIDATA_H
 #define UNIDATA_H
 enum unicode_General_Category {
@@ -42,31 +48,40 @@ enum unicode_Grapheme_Break {
   unicode_Grapheme_Break_LV,
   unicode_Grapheme_Break_LVT,
   unicode_Grapheme_Break_Other,
+  unicode_Grapheme_Break_Prepend,
+  unicode_Grapheme_Break_SpacingMark,
   unicode_Grapheme_Break_T,
   unicode_Grapheme_Break_V
 };
 extern const char *const unicode_Grapheme_Break_names[];
 enum unicode_Word_Break {
   unicode_Word_Break_ALetter,
+  unicode_Word_Break_CR,
   unicode_Word_Break_Extend,
   unicode_Word_Break_ExtendNumLet,
   unicode_Word_Break_Format,
   unicode_Word_Break_Katakana,
+  unicode_Word_Break_LF,
   unicode_Word_Break_MidLetter,
   unicode_Word_Break_MidNum,
+  unicode_Word_Break_MidNumLet,
+  unicode_Word_Break_Newline,
   unicode_Word_Break_Numeric,
   unicode_Word_Break_Other
 };
 extern const char *const unicode_Word_Break_names[];
 enum unicode_Sentence_Break {
   unicode_Sentence_Break_ATerm,
+  unicode_Sentence_Break_CR,
   unicode_Sentence_Break_Close,
   unicode_Sentence_Break_Extend,
   unicode_Sentence_Break_Format,
+  unicode_Sentence_Break_LF,
   unicode_Sentence_Break_Lower,
   unicode_Sentence_Break_Numeric,
   unicode_Sentence_Break_OLetter,
   unicode_Sentence_Break_Other,
+  unicode_Sentence_Break_SContinue,
   unicode_Sentence_Break_STerm,
   unicode_Sentence_Break_Sep,
   unicode_Sentence_Break_Sp,
@@ -74,15 +89,14 @@ enum unicode_Sentence_Break {
 };
 extern const char *const unicode_Sentence_Break_names[];
 enum unicode_flags {
-  unicode_normalize_before_casefold = 1
+  unicode_normalize_before_casefold = 1,
+  unicode_compatibility_decomposition = 2
 };
 
 struct unidata {
-  const uint32_t *compat;
-  const uint32_t *canon;
+  const uint32_t *decomp;
   const uint32_t *casefold;
-  int16_t upper_offset;
-  int16_t lower_offset;
+  const uint32_t *composed;
   unsigned char ccc;
   char general_category;
   uint8_t flags;
@@ -91,6 +105,13 @@ struct unidata {
   char sentence_break;
 };
 extern const struct unidata *const unidata[];
-#define UNICODE_NCHARS 195200
-#define UNICODE_MODULUS 128
+extern const struct unicode_utf8_row {
+  uint8_t count;
+  uint8_t min2, max2;
+} unicode_utf8_valid[];
+#define UNICODE_NCHARS 1114112
+#define UNICODE_MODULUS 16
+#define UNICODE_BREAK_START 196608
+#define UNICODE_BREAK_END 917504
+#define UNICODE_BREAK_TOP 918016
 #endif