/*
* This file is part of DisOrder
- * Copyright (C) 2004 Richard Kettlewell
+ * Copyright (C) 2004, 2007 Richard Kettlewell
*
* 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
#include "table.h"
#include "words.h"
#include "utf8.h"
+#include "log.h"
+#include "charset.h"
-#include "casefold.h"
-#include "unicodegc.h"
+#include "unidata.h"
+#include "unicode.h"
const char *casefold(const char *ptr) {
- struct dynstr d;
- int l, r, m;
- uint32_t c;
- const struct cm *t;
- const char *start, *s = ptr;
-
- dynstr_init(&d);
- while(*s) {
- start = s;
- PARSE_UTF8(s, c, return ptr);
- /* seek the folded equivalent */
- t = cm[c & CM_MASK];
- l = 0;
- r = cmn[c & CM_MASK] - 1;
- while(l <= r && c != t[m = (l + r) / 2].ch)
- if(c < t[m].ch)
- r = m - 1;
- else
- l = m + 1;
- if(l <= r)
- dynstr_append_string(&d, t[m].tr);
- else
- dynstr_append_bytes(&d, start, s - start);
- }
- dynstr_terminate(&d);
- return d.vec;
+ return utf8_casefold_canon(ptr, strlen(ptr), 0);
}
-static enum unicode_gc_cat cat(uint32_t c) {
- int l, r, m;
-
- l = 0;
- r = sizeof gcs / sizeof *gcs;
- while(l <= r) {
- m = (l + r) / 2;
- if(c < gcs[m].l)
- r = m - 1;
- else if(c > gcs[m].h)
- l = m + 1;
- else
- return gcs[m].cat;
- }
- return unicode_gc_none;
+static enum unicode_General_Category cat(uint32_t c) {
+ if(c < UNICODE_NCHARS) {
+ const struct unidata *const ud = &unidata[c / UNICODE_MODULUS][c % UNICODE_MODULUS];
+ return ud->general_category;
+ } else
+ return unicode_General_Category_Cn;
}
/* XXX this is a bit kludgy */
}
/* do the rest on category */
switch(cat(c)) {
- case unicode_gc_Ll:
- case unicode_gc_Lm:
- case unicode_gc_Lo:
- case unicode_gc_Lt:
- case unicode_gc_Lu:
- case unicode_gc_Nd:
- case unicode_gc_Nl:
- case unicode_gc_No:
- case unicode_gc_Sc:
- case unicode_gc_Sk:
- case unicode_gc_Sm:
- case unicode_gc_So:
+ case unicode_General_Category_Ll:
+ case unicode_General_Category_Lm:
+ case unicode_General_Category_Lo:
+ case unicode_General_Category_Lt:
+ case unicode_General_Category_Lu:
+ case unicode_General_Category_Nd:
+ case unicode_General_Category_Nl:
+ case unicode_General_Category_No:
+ case unicode_General_Category_Sc:
+ case unicode_General_Category_Sk:
+ case unicode_General_Category_Sm:
+ case unicode_General_Category_So:
/* letters, digits and symbols are considered to be part of
* words */
if(!in_word) {
dynstr_append_bytes(&d, start, s - start);
break;
- case unicode_gc_Cc:
- case unicode_gc_Cf:
- case unicode_gc_Co:
- case unicode_gc_Cs:
- case unicode_gc_Zl:
- case unicode_gc_Zp:
- case unicode_gc_Zs:
- case unicode_gc_Pe:
- case unicode_gc_Ps:
+ case unicode_General_Category_Cc:
+ case unicode_General_Category_Cf:
+ case unicode_General_Category_Co:
+ case unicode_General_Category_Cs:
+ case unicode_General_Category_Zl:
+ case unicode_General_Category_Zp:
+ case unicode_General_Category_Zs:
+ case unicode_General_Category_Pe:
+ case unicode_General_Category_Ps:
separator:
if(in_word) {
dynstr_terminate(&d);
}
break;
- case unicode_gc_Mc:
- case unicode_gc_Me:
- case unicode_gc_Mn:
- case unicode_gc_Pc:
- case unicode_gc_Pd:
- case unicode_gc_Pf:
- case unicode_gc_Pi:
- case unicode_gc_Po:
- case unicode_gc_none:
+ case unicode_General_Category_Mc:
+ case unicode_General_Category_Me:
+ case unicode_General_Category_Mn:
+ case unicode_General_Category_Pc:
+ case unicode_General_Category_Pd:
+ case unicode_General_Category_Pf:
+ case unicode_General_Category_Pi:
+ case unicode_General_Category_Po:
+ case unicode_General_Category_Cn:
/* control and punctuation is completely ignored */
break;
comment-column:40
End:
*/
-/* arch-tag:0ea1f1700f14cd031b7f1fbbcca765fa */