X-Git-Url: http://www.chiark.greenend.org.uk/ucgi/~mdw/git/disorder/blobdiff_plain/35b651f0cc0999deae42c92f2cbca3ecf88fe157..4265e5d362914f3732b4035dcf67162e525e0142:/lib/unidata.h

diff --git a/lib/unidata.h b/lib/unidata.h
index 16ff5fa..1d89322 100644
--- a/lib/unidata.h
+++ b/lib/unidata.h
@@ -1,54 +1,117 @@
-/* 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_gc_cat {
-  unicode_gc_Cc,
-  unicode_gc_Cf,
-  unicode_gc_Cn,
-  unicode_gc_Co,
-  unicode_gc_Cs,
-  unicode_gc_Ll,
-  unicode_gc_Lm,
-  unicode_gc_Lo,
-  unicode_gc_Lt,
-  unicode_gc_Lu,
-  unicode_gc_Mc,
-  unicode_gc_Me,
-  unicode_gc_Mn,
-  unicode_gc_Nd,
-  unicode_gc_Nl,
-  unicode_gc_No,
-  unicode_gc_Pc,
-  unicode_gc_Pd,
-  unicode_gc_Pe,
-  unicode_gc_Pf,
-  unicode_gc_Pi,
-  unicode_gc_Po,
-  unicode_gc_Ps,
-  unicode_gc_Sc,
-  unicode_gc_Sk,
-  unicode_gc_Sm,
-  unicode_gc_So,
-  unicode_gc_Zl,
-  unicode_gc_Zp,
-  unicode_gc_Zs
+enum unicode_General_Category {
+  unicode_General_Category_Cc,
+  unicode_General_Category_Cf,
+  unicode_General_Category_Cn,
+  unicode_General_Category_Co,
+  unicode_General_Category_Cs,
+  unicode_General_Category_Ll,
+  unicode_General_Category_Lm,
+  unicode_General_Category_Lo,
+  unicode_General_Category_Lt,
+  unicode_General_Category_Lu,
+  unicode_General_Category_Mc,
+  unicode_General_Category_Me,
+  unicode_General_Category_Mn,
+  unicode_General_Category_Nd,
+  unicode_General_Category_Nl,
+  unicode_General_Category_No,
+  unicode_General_Category_Pc,
+  unicode_General_Category_Pd,
+  unicode_General_Category_Pe,
+  unicode_General_Category_Pf,
+  unicode_General_Category_Pi,
+  unicode_General_Category_Po,
+  unicode_General_Category_Ps,
+  unicode_General_Category_Sc,
+  unicode_General_Category_Sk,
+  unicode_General_Category_Sm,
+  unicode_General_Category_So,
+  unicode_General_Category_Zl,
+  unicode_General_Category_Zp,
+  unicode_General_Category_Zs
 };
+enum unicode_Grapheme_Break {
+  unicode_Grapheme_Break_CR,
+  unicode_Grapheme_Break_Control,
+  unicode_Grapheme_Break_Extend,
+  unicode_Grapheme_Break_L,
+  unicode_Grapheme_Break_LF,
+  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,
+  unicode_Sentence_Break_Upper
+};
+extern const char *const unicode_Sentence_Break_names[];
 enum unicode_flags {
   unicode_normalize_before_casefold = 1,
-  unicode_grapheme_break_extend = 2
+  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 gc;
+  char general_category;
   uint8_t flags;
+  char grapheme_break;
+  char word_break;
+  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