Unicode-capable srfi-14 charsets

* libguile/Makefile.am: distribute new files srfi-14.i.c and
  unidata_to_charset.pl

* chars.c (scm_c_upcase, scm_c_downcase): use unicode-enable toupper
  and tolower

* libguile/srfi-14.h (scm_t_char_range, scm_t_char_set): new structures
  to describe char-sets
  (scm_t_char_set_cursor): new structure to describe char-set-cursors
  (SCM_BITS_PER_LONG): removed
  (SCM_CHARSET_GET): calls function
  New declarations for scm_i_charset_get, scm_i_charset_set,
  scm_i_charset_unset, and scm_debug_char_set.

* test-suite/tests/srfi-14.test: new tests

* libguile/srfi-14.c (SCM_CHARSET_DATA): new macro
  (SCM_CHARSET_SET, SCM_CHARSET_UNSET): call function
  (BYTES_PER_CHARSET, LONGS_PER_CHARSET): removed
  (scm_i_charset_get, scm_i_charset_set, scm_i_charset_unset)
  (charsets_equal, charsets_leq, charsets_union)
  (charsets_intersection, charsets_complement, charsets_xor): new
  functions that are low-level charset operators
  (charset_print, charset_free): modified for new charset struct
  (charset_cursor_print, charset_cursor_free): new function
  (make_char_set, scm_char_set_p, scm_char_set_eq, scm_car_set_leq)
  (scm_char_set_hash, scm_char_set_cursor, scm_char_set_ref)
  (scm_char_set_cursor_next, scm_end_of_char_set_p, scm_char_set_fold)
  (scm_char_set_unfold, scm_char_set_unfold_x, scm_char_set_for_each)
  (scm_char_set_map, scm_char_set_copy, scm_char_set, scm_list_to_char_set)
  (scm_list_to_char_set_x, scm_string_to_char_set, scm_string_to_char_set_x)
  (scm_char_set_filter, scm_char_set_filter_x, scm_ucs_range_to_char_set)
  (scm_ucs_range_to_char_set_x, scm_to_char_set, scm_char_set_size)
  (scm_char_set_count, scm_char_set_to_list, scm_char_set_to_string)
  (scm_char_set_contains_p, scm_char_set_every, scm_char_set_any)
  (scm_char_set_adjoin, scm_char_set_delete, scm_char_set_adjoin_x)
  (scm_char_set_delete_x, scm_char_set_complement, scm_char_set_union)
  (scm_char_set_intersection, scm_char_set_difference, scm_char_set_xor)
  (scm_char_set_diff_plus_intersection, scm_char_set_complement_x)
  (scm_char_set_union_x, scm_char_set_intersection_x, scm_char_set_difference_x)
  (scm_char_set_xor_x, scm_char_set_diff_plus_intersection_x): modified
  to use new charset and charset-cursor data structures
  (CSET_BLANK_PRED, CSET_SYMBOL_PRED, CSET_PUNCT_PRED, CSET_LOWER_PRED)
  (CSET_UPPER_PRED, CSET_LETTER_PRED, CSET_DIGIT_PRED, CSET_WHITESPACE_PRED)
  (CSET_CONTROL_PRED, CSET_HEX_DIGIT_PRED, CSET_ASCII_PRED, CSET_LETTER_PRED)
  (CSET_LETTER_AND_DIGIT_PRED, CSET_PRINTING_PRED, CSET_TRUE_PRED)
  (CSET_FALSE_PRED): removed
  (scm_srfi_14_compute_char_sets): removed - too slow to iterate
  over all of unicode at startup
  (scm_debug_char_set) [SCM_CHARSET_DEBUG]: new function

1 files changed, 2 insertions, 8 deletions

diff --git a/libguile/chars.c b/libguile/chars.c
index 552a2d9c1..c7cb09c47 100644
--- a/libguile/chars.c
+++ b/libguile/chars.c
@@ -296,20 +296,14 @@ TODO: change name  to scm_i_.. ? --hwn
 scm_t_wchar
 scm_c_upcase (scm_t_wchar c)
 {
-  if (c > 255)
-    return c;
-
-  return toupper ((int) c);
+  return uc_toupper ((int) c);
 }
 
 
 scm_t_wchar
 scm_c_downcase (scm_t_wchar c)
 {
-  if (c > 255)
-    return c;
-
-  return tolower ((int) c);
+  return uc_tolower ((int) c);
 }