diff options
Diffstat (limited to 'unicode/courier-unicode.h')
| -rw-r--r-- | unicode/courier-unicode.h | 224 |
1 files changed, 83 insertions, 141 deletions
diff --git a/unicode/courier-unicode.h b/unicode/courier-unicode.h index 42ef9a1..a84e230 100644 --- a/unicode/courier-unicode.h +++ b/unicode/courier-unicode.h @@ -67,12 +67,7 @@ unicode_char unicode_html40ent_lookup(const char *n); extern int unicode_wcwidth(unicode_char c); extern size_t unicode_wcwidth_str(const unicode_char *c); -/* -** The unicode-ish isspace() -*/ -extern int unicode_isspace(unicode_char ch); - -/* Internal unicode table lookup function */ +/* Internal unicode table lookup functions */ extern uint8_t unicode_tab_lookup(unicode_char ch, const size_t *unicode_indextab, @@ -81,6 +76,85 @@ extern uint8_t unicode_tab_lookup(unicode_char ch, const uint8_t *unicode_classtab, uint8_t uclass); +extern uint32_t unicode_tab32_lookup(unicode_char ch, + const size_t *unicode_indextab, + size_t unicode_indextab_sizeof, + const uint8_t (*unicode_rangetab)[2], + const uint32_t *unicode_classtab, + uint32_t uclass); + +/* +** Look up unicode categorization, see http://unicode.org/notes/tn36/ +** +** Returns a 32 bit value with four unicode categories encoded in the +** bits defined by UNICODE_CATEGORY_1..4 +*/ + +#define UNICODE_CATEGORY_1 0xFF000000 +#define UNICODE_CATEGORY_2 0x00FF0000 +#define UNICODE_CATEGORY_3 0x0000FF00 +#define UNICODE_CATEGORY_4 0x000000FF + +#include <courier-unicode-categories-tab.h> + +uint32_t unicode_category_lookup(unicode_char); + +/* +** Return non-0 for TAB, and all UNICODE_CATEGORY_2_SPACE. +*/ + +extern int unicode_isblank(unicode_char ch); + +/* +** The unicode-ish isspace(). In addition to return non-0 for +** unicode_isblank(), this also returns non-0 for unicode characters +** with linebreaking properties of BK, CR, LF, NL, and SP. +*/ +extern int unicode_isspace(unicode_char ch); + +/* +** Return non-0 for all UNICODE_CATEGORY_1_LETTER +*/ + +extern int unicode_isalpha(unicode_char ch); + +/* +** Return non-0 for all UNICODE_CATEGORY_1_NUMBER | UNICODE_CATEGORY_2_DIGIT, +** only (no third categories). +*/ +extern int unicode_isdigit(unicode_char ch); + +/* +** Return non-0 for all unicode_isalpha() or unicode_isdigit(). +*/ + +extern int unicode_isalnum(unicode_char ch); + +/* +** Returns non-0 for all codepoints above SPACE which are not +** unicode_isspace(). +*/ + +extern int unicode_isgraph(unicode_char ch); + +/* +** Return non-0 for all UNICODE_CATEGORY_1_PUNCTUATION. +*/ + +extern int unicode_ispunct(unicode_char ch); + +/* +** Return non-0 for all unicode_isalpha() for which the character is +** equal to unicode_lc() of itself. +*/ +extern int unicode_islower(unicode_char ch); + +/* +** Return non-0 for all unicode_isalpha() for which the character is +** equal to unicode_uc() of itself. +*/ +extern int unicode_isupper(unicode_char ch); + /* ** Implementation of grapheme cluster boundary rules, as per ** http://www.unicode.org/reports/tr29/tr29-27.html @@ -93,141 +167,9 @@ extern uint8_t unicode_tab_lookup(unicode_char ch, int unicode_grapheme_break(unicode_char a, unicode_char b); typedef enum { - /* UNICODE_SCRIPT_T */ - unicode_script_unknown, - unicode_script_common, - unicode_script_latin, - unicode_script_greek, - unicode_script_cyrillic, - unicode_script_armenian, - unicode_script_hebrew, - unicode_script_arabic, - unicode_script_syriac, - unicode_script_thaana, - unicode_script_devanagari, - unicode_script_bengali, - unicode_script_gurmukhi, - unicode_script_gujarati, - unicode_script_oriya, - unicode_script_tamil, - unicode_script_telugu, - unicode_script_kannada, - unicode_script_malayalam, - unicode_script_sinhala, - unicode_script_thai, - unicode_script_lao, - unicode_script_tibetan, - unicode_script_myanmar, - unicode_script_georgian, - unicode_script_hangul, - unicode_script_ethiopic, - unicode_script_cherokee, - unicode_script_canadian_aboriginal, - unicode_script_ogham, - unicode_script_runic, - unicode_script_khmer, - unicode_script_mongolian, - unicode_script_hiragana, - unicode_script_katakana, - unicode_script_bopomofo, - unicode_script_han, - unicode_script_yi, - unicode_script_old_italic, - unicode_script_gothic, - unicode_script_deseret, - unicode_script_inherited, - unicode_script_tagalog, - unicode_script_hanunoo, - unicode_script_buhid, - unicode_script_tagbanwa, - unicode_script_limbu, - unicode_script_tai_le, - unicode_script_linear_b, - unicode_script_ugaritic, - unicode_script_shavian, - unicode_script_osmanya, - unicode_script_cypriot, - unicode_script_braille, - unicode_script_buginese, - unicode_script_coptic, - unicode_script_new_tai_lue, - unicode_script_glagolitic, - unicode_script_tifinagh, - unicode_script_syloti_nagri, - unicode_script_old_persian, - unicode_script_kharoshthi, - unicode_script_balinese, - unicode_script_cuneiform, - unicode_script_phoenician, - unicode_script_phags_pa, - unicode_script_nko, - unicode_script_sundanese, - unicode_script_lepcha, - unicode_script_ol_chiki, - unicode_script_vai, - unicode_script_saurashtra, - unicode_script_kayah_li, - unicode_script_rejang, - unicode_script_lycian, - unicode_script_carian, - unicode_script_lydian, - unicode_script_cham, - unicode_script_tai_tham, - unicode_script_tai_viet, - unicode_script_avestan, - unicode_script_egyptian_hieroglyphs, - unicode_script_samaritan, - unicode_script_lisu, - unicode_script_bamum, - unicode_script_javanese, - unicode_script_meetei_mayek, - unicode_script_imperial_aramaic, - unicode_script_old_south_arabian, - unicode_script_inscriptional_parthian, - unicode_script_inscriptional_pahlavi, - unicode_script_old_turkic, - unicode_script_kaithi, - unicode_script_batak, - unicode_script_brahmi, - unicode_script_mandaic, - unicode_script_chakma, - unicode_script_meroitic_cursive, - unicode_script_meroitic_hieroglyphs, - unicode_script_miao, - unicode_script_sharada, - unicode_script_sora_sompeng, - unicode_script_takri, - unicode_script_caucasian_albanian, - unicode_script_bassa_vah, - unicode_script_duployan, - unicode_script_elbasan, - unicode_script_grantha, - unicode_script_pahawh_hmong, - unicode_script_khojki, - unicode_script_linear_a, - unicode_script_mahajani, - unicode_script_manichaean, - unicode_script_mende_kikakui, - unicode_script_modi, - unicode_script_mro, - unicode_script_old_north_arabian, - unicode_script_nabataean, - unicode_script_palmyrene, - unicode_script_pau_cin_hau, - unicode_script_old_permic, - unicode_script_psalter_pahlavi, - unicode_script_siddham, - unicode_script_khudawadi, - unicode_script_tirhuta, - unicode_script_warang_citi, - unicode_script_ahom, - unicode_script_anatolian_hieroglyphs, - unicode_script_hatran, - unicode_script_multani, - unicode_script_old_hungarian, - unicode_script_signwriting - - /* UNICODE_SCRIPT_T */ + +#include <courier-unicode-script-tab.h> + } unicode_script_t; /* |