guile/libguile/srfi-14.h

127 lines
4.8 KiB
C
Raw Normal View History

#ifndef SCM_SRFI_14_H
#define SCM_SRFI_14_H
/* srfi-14.c --- SRFI-14 procedures for Guile
xxg
Copyright 2001,2004,2006,2008,2011,2018
Free Software Foundation, Inc.
This file is part of Guile.
Guile is free software: you can redistribute it and/or modify it
under the terms of the GNU Lesser General Public License as published
by the Free Software Foundation, either version 3 of the License, or
(at your option) any later version.
Guile 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 Lesser General Public
License for more details.
You should have received a copy of the GNU Lesser General Public
License along with Guile. If not, see
<https://www.gnu.org/licenses/>. */
#include "libguile/chars.h"
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
2009-08-27 07:32:50 -07:00
typedef struct
{
scm_t_wchar lo;
scm_t_wchar hi;
} scm_t_char_range;
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
2009-08-27 07:32:50 -07:00
typedef struct
{
size_t len;
scm_t_char_range *ranges;
} scm_t_char_set;
typedef struct
{
size_t range;
scm_t_wchar n;
} scm_t_char_set_cursor;
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
2009-08-27 07:32:50 -07:00
#define SCM_CHARSET_GET(cs,idx) \
scm_i_charset_get((scm_t_char_set *)SCM_SMOB_DATA(cs),idx)
#define SCM_CHARSETP(x) (SCM_HAS_TYP16 (x, scm_tc16_charset))
/* Smob type code for character sets. */
SCM_API int scm_tc16_charset;
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
2009-08-27 07:32:50 -07:00
SCM_INTERNAL int scm_i_charset_get (scm_t_char_set *cs, scm_t_wchar n);
SCM_INTERNAL void scm_i_charset_set (scm_t_char_set *cs, scm_t_wchar n);
SCM_INTERNAL void scm_i_charset_unset (scm_t_char_set *cs, scm_t_wchar n);
SCM_API SCM scm_char_set_p (SCM obj);
SCM_API SCM scm_char_set_eq (SCM char_sets);
SCM_API SCM scm_char_set_leq (SCM char_sets);
SCM_API SCM scm_char_set_hash (SCM cs, SCM bound);
SCM_API SCM scm_char_set_cursor (SCM cs);
SCM_API SCM scm_char_set_ref (SCM cs, SCM cursor);
SCM_API SCM scm_char_set_cursor_next (SCM cs, SCM cursor);
SCM_API SCM scm_end_of_char_set_p (SCM cursor);
SCM_API SCM scm_char_set_fold (SCM kons, SCM knil, SCM cs);
SCM_API SCM scm_char_set_unfold (SCM p, SCM f, SCM g, SCM seed, SCM base_cs);
SCM_API SCM scm_char_set_unfold_x (SCM p, SCM f, SCM g, SCM seed, SCM base_cs);
SCM_API SCM scm_char_set_for_each (SCM proc, SCM cs);
SCM_API SCM scm_char_set_map (SCM proc, SCM cs);
SCM_API SCM scm_char_set_copy (SCM cs);
SCM_API SCM scm_char_set (SCM rest);
SCM_API SCM scm_list_to_char_set (SCM list, SCM base_cs);
SCM_API SCM scm_list_to_char_set_x (SCM list, SCM base_cs);
SCM_API SCM scm_string_to_char_set (SCM str, SCM base_cs);
SCM_API SCM scm_string_to_char_set_x (SCM str, SCM base_cs);
SCM_API SCM scm_char_set_filter (SCM pred, SCM cs, SCM base_cs);
SCM_API SCM scm_char_set_filter_x (SCM pred, SCM cs, SCM base_cs);
SCM_API SCM scm_ucs_range_to_char_set (SCM lower, SCM upper, SCM error, SCM base_cs);
SCM_API SCM scm_ucs_range_to_char_set_x (SCM lower, SCM upper, SCM error, SCM base_cs);
SCM_API SCM scm_to_char_set (SCM x);
SCM_API SCM scm_char_set_size (SCM cs);
SCM_API SCM scm_char_set_count (SCM pred, SCM cs);
SCM_API SCM scm_char_set_to_list (SCM cs);
SCM_API SCM scm_char_set_to_string (SCM cs);
SCM_API SCM scm_char_set_contains_p (SCM cs, SCM ch);
SCM_API SCM scm_char_set_every (SCM pred, SCM cs);
SCM_API SCM scm_char_set_any (SCM pred, SCM cs);
SCM_API SCM scm_char_set_adjoin (SCM cs, SCM rest);
SCM_API SCM scm_char_set_delete (SCM cs, SCM rest);
SCM_API SCM scm_char_set_adjoin_x (SCM cs, SCM rest);
SCM_API SCM scm_char_set_delete_x (SCM cs, SCM rest);
SCM_API SCM scm_char_set_complement (SCM cs);
SCM_API SCM scm_char_set_union (SCM rest);
SCM_API SCM scm_char_set_intersection (SCM rest);
SCM_API SCM scm_char_set_difference (SCM cs1, SCM rest);
SCM_API SCM scm_char_set_xor (SCM rest);
SCM_API SCM scm_char_set_diff_plus_intersection (SCM cs1, SCM rest);
SCM_API SCM scm_char_set_complement_x (SCM cs);
SCM_API SCM scm_char_set_union_x (SCM cs1, SCM rest);
SCM_API SCM scm_char_set_intersection_x (SCM cs1, SCM rest);
SCM_API SCM scm_char_set_difference_x (SCM cs1, SCM rest);
SCM_API SCM scm_char_set_xor_x (SCM cs1, SCM rest);
SCM_API SCM scm_char_set_diff_plus_intersection_x (SCM cs1, SCM cs2, SCM rest);
SCM_API SCM scm_sys_char_set_dump (SCM charset);
SCM_API SCM scm_char_set_lower_case;
SCM_API SCM scm_char_set_upper_case;
SCM_API SCM scm_char_set_title_case;
SCM_API SCM scm_char_set_letter;
SCM_API SCM scm_char_set_digit;
SCM_API SCM scm_char_set_letter_and_digit;
SCM_API SCM scm_char_set_graphic;
SCM_API SCM scm_char_set_printing;
SCM_API SCM scm_char_set_whitespace;
SCM_API SCM scm_char_set_iso_control;
SCM_API SCM scm_char_set_punctuation;
SCM_API SCM scm_char_set_symbol;
SCM_API SCM scm_char_set_hex_digit;
SCM_API SCM scm_char_set_blank;
SCM_API SCM scm_char_set_ascii;
SCM_API SCM scm_char_set_empty;
SCM_API SCM scm_char_set_full;
2008-05-14 05:20:47 +02:00
SCM_INTERNAL void scm_init_srfi_14 (void);
#endif /* SCM_SRFI_14_H */