/* guniprop.c - Unicode character properties. * * Copyright (C) 1999 Tom Tromey * Copyright (C) 2000 Red Hat, Inc. * * This library 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 2 of the License, or (at your option) any later version. * * This library 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 this library; if not, write to the * Free Software Foundation, Inc., 59 Temple Place - Suite 330, * Boston, MA 02111-1307, USA. */ #include "config.h" #include #include #include #include #include "glib.h" #include "gunichartables.h" #include "gmirroringtable.h" #include "gscripttable.h" #include "gunicodeprivate.h" #include "galias.h" #define ATTR_TABLE(Page) (((Page) <= G_UNICODE_LAST_PAGE_PART1) \ ? attr_table_part1[Page] \ : attr_table_part2[(Page) - 0xe00]) #define ATTTABLE(Page, Char) \ ((ATTR_TABLE(Page) == G_UNICODE_MAX_TABLE_INDEX) ? 0 : (attr_data[ATTR_TABLE(Page)][Char])) #define TTYPE_PART1(Page, Char) \ ((type_table_part1[Page] >= G_UNICODE_MAX_TABLE_INDEX) \ ? (type_table_part1[Page] - G_UNICODE_MAX_TABLE_INDEX) \ : (type_data[type_table_part1[Page]][Char])) #define TTYPE_PART2(Page, Char) \ ((type_table_part2[Page] >= G_UNICODE_MAX_TABLE_INDEX) \ ? (type_table_part2[Page] - G_UNICODE_MAX_TABLE_INDEX) \ : (type_data[type_table_part2[Page]][Char])) #define TYPE(Char) \ (((Char) <= G_UNICODE_LAST_CHAR_PART1) \ ? TTYPE_PART1 ((Char) >> 8, (Char) & 0xff) \ : (((Char) >= 0xe0000 && (Char) <= G_UNICODE_LAST_CHAR) \ ? TTYPE_PART2 (((Char) - 0xe0000) >> 8, (Char) & 0xff) \ : G_UNICODE_UNASSIGNED)) #define IS(Type, Class) (((guint)1 << (Type)) & (Class)) #define OR(Type, Rest) (((guint)1 << (Type)) | (Rest)) #define ISALPHA(Type) IS ((Type), \ OR (G_UNICODE_LOWERCASE_LETTER, \ OR (G_UNICODE_UPPERCASE_LETTER, \ OR (G_UNICODE_TITLECASE_LETTER, \ OR (G_UNICODE_MODIFIER_LETTER, \ OR (G_UNICODE_OTHER_LETTER, 0)))))) #define ISALDIGIT(Type) IS ((Type), \ OR (G_UNICODE_DECIMAL_NUMBER, \ OR (G_UNICODE_LETTER_NUMBER, \ OR (G_UNICODE_OTHER_NUMBER, \ OR (G_UNICODE_LOWERCASE_LETTER, \ OR (G_UNICODE_UPPERCASE_LETTER, \ OR (G_UNICODE_TITLECASE_LETTER, \ OR (G_UNICODE_MODIFIER_LETTER, \ OR (G_UNICODE_OTHER_LETTER, 0))))))))) #define ISMARK(Type) IS ((Type), \ OR (G_UNICODE_NON_SPACING_MARK, \ OR (G_UNICODE_COMBINING_MARK, \ OR (G_UNICODE_ENCLOSING_MARK, 0)))) #define ISZEROWIDTHTYPE(Type) IS ((Type), \ OR (G_UNICODE_NON_SPACING_MARK, \ OR (G_UNICODE_ENCLOSING_MARK, \ OR (G_UNICODE_FORMAT, 0)))) /** * g_unichar_isalnum: * @c: a Unicode character * * Determines whether a character is alphanumeric. * Given some UTF-8 text, obtain a character value * with g_utf8_get_char(). * * Return value: %TRUE if @c is an alphanumeric character **/ gboolean g_unichar_isalnum (gunichar c) { return ISALDIGIT (TYPE (c)) ? TRUE : FALSE; } /** * g_unichar_isalpha: * @c: a Unicode character * * Determines whether a character is alphabetic (i.e. a letter). * Given some UTF-8 text, obtain a character value with * g_utf8_get_char(). * * Return value: %TRUE if @c is an alphabetic character **/ gboolean g_unichar_isalpha (gunichar c) { return ISALPHA (TYPE (c)) ? TRUE : FALSE; } /** * g_unichar_iscntrl: * @c: a Unicode character * * Determines whether a character is a control character. * Given some UTF-8 text, obtain a character value with * g_utf8_get_char(). * * Return value: %TRUE if @c is a control character **/ gboolean g_unichar_iscntrl (gunichar c) { return TYPE (c) == G_UNICODE_CONTROL; } /** * g_unichar_isdigit: * @c: a Unicode character * * Determines whether a character is numeric (i.e. a digit). This * covers ASCII 0-9 and also digits in other languages/scripts. Given * some UTF-8 text, obtain a character value with g_utf8_get_char(). * * Return value: %TRUE if @c is a digit **/ gboolean g_unichar_isdigit (gunichar c) { return TYPE (c) == G_UNICODE_DECIMAL_NUMBER; } /** * g_unichar_isgraph: * @c: a Unicode character * * Determines whether a character is printable and not a space * (returns %FALSE for control characters, format characters, and * spaces). g_unichar_isprint() is similar, but returns %TRUE for * spaces. Given some UTF-8 text, obtain a character value with * g_utf8_get_char(). * * Return value: %TRUE if @c is printable unless it's a space **/ gboolean g_unichar_isgraph (gunichar c) { return !IS (TYPE(c), OR (G_UNICODE_CONTROL, OR (G_UNICODE_FORMAT, OR (G_UNICODE_UNASSIGNED, OR (G_UNICODE_PRIVATE_USE, OR (G_UNICODE_SURROGATE, OR (G_UNICODE_SPACE_SEPARATOR, 0))))))); } /** * g_unichar_islower: * @c: a Unicode character * * Determines whether a character is a lowercase letter. * Given some UTF-8 text, obtain a character value with * g_utf8_get_char(). * * Return value: %TRUE if @c is a lowercase letter **/ gboolean g_unichar_islower (gunichar c) { return TYPE (c) == G_UNICODE_LOWERCASE_LETTER; } /** * g_unichar_isprint: * @c: a Unicode character * * Determines whether a character is printable. * Unlike g_unichar_isgraph(), returns %TRUE for spaces. * Given some UTF-8 text, obtain a character value with * g_utf8_get_char(). * * Return value: %TRUE if @c is printable **/ gboolean g_unichar_isprint (gunichar c) { return !IS (TYPE(c), OR (G_UNICODE_CONTROL, OR (G_UNICODE_FORMAT, OR (G_UNICODE_UNASSIGNED, OR (G_UNICODE_PRIVATE_USE, OR (G_UNICODE_SURROGATE, 0)))))); } /** * g_unichar_ispunct: * @c: a Unicode character * * Determines whether a character is punctuation or a symbol. * Given some UTF-8 text, obtain a character value with * g_utf8_get_char(). * * Return value: %TRUE if @c is a punctuation or symbol character **/ gboolean g_unichar_ispunct (gunichar c) { return IS (TYPE(c), OR (G_UNICODE_CONNECT_PUNCTUATION, OR (G_UNICODE_DASH_PUNCTUATION, OR (G_UNICODE_CLOSE_PUNCTUATION, OR (G_UNICODE_FINAL_PUNCTUATION, OR (G_UNICODE_INITIAL_PUNCTUATION, OR (G_UNICODE_OTHER_PUNCTUATION, OR (G_UNICODE_OPEN_PUNCTUATION, OR (G_UNICODE_CURRENCY_SYMBOL, OR (G_UNICODE_MODIFIER_SYMBOL, OR (G_UNICODE_MATH_SYMBOL, OR (G_UNICODE_OTHER_SYMBOL, 0)))))))))))) ? TRUE : FALSE; } /** * g_unichar_isspace: * @c: a Unicode character * * Determines whether a character is a space, tab, or line separator * (newline, carriage return, etc.). Given some UTF-8 text, obtain a * character value with g_utf8_get_char(). * * (Note: don't use this to do word breaking; you have to use * Pango or equivalent to get word breaking right, the algorithm * is fairly complex.) * * Return value: %TRUE if @c is a space character **/ gboolean g_unichar_isspace (gunichar c) { switch (c) { /* special-case these since Unicode thinks they are not spaces */ case '\t': case '\n': case '\r': case '\f': return TRUE; break; default: { return IS (TYPE(c), OR (G_UNICODE_SPACE_SEPARATOR, OR (G_UNICODE_LINE_SEPARATOR, OR (G_UNICODE_PARAGRAPH_SEPARATOR, 0)))) ? TRUE : FALSE; } break; } } /** * g_unichar_ismark: * @c: a Unicode character * * Determines whether a character is a mark (non-spacing mark, * combining mark, or enclosing mark in Unicode speak). * Given some UTF-8 text, obtain a character value * with g_utf8_get_char(). * * Note: in most cases where isalpha characters are allowed, * ismark characters should be allowed to as they are essential * for writing most European languages as well as many non-Latin * scripts. * * Return value: %TRUE if @c is a mark character * * Since: 2.14 **/ gboolean g_unichar_ismark (gunichar c) { return ISMARK (TYPE (c)); } /** * g_unichar_isupper: * @c: a Unicode character * * Determines if a character is uppercase. * * Return value: %TRUE if @c is an uppercase character **/ gboolean g_unichar_isupper (gunichar c) { return TYPE (c) == G_UNICODE_UPPERCASE_LETTER; } /** * g_unichar_istitle: * @c: a Unicode character * * Determines if a character is titlecase. Some characters in * Unicode which are composites, such as the DZ digraph * have three case variants instead of just two. The titlecase * form is used at the beginning of a word where only the * first letter is capitalized. The titlecase form of the DZ * digraph is U+01F2 LATIN CAPITAL LETTTER D WITH SMALL LETTER Z. * * Return value: %TRUE if the character is titlecase **/ gboolean g_unichar_istitle (gunichar c) { unsigned int i; for (i = 0; i < G_N_ELEMENTS (title_table); ++i) if (title_table[i][0] == c) return TRUE; return FALSE; } /** * g_unichar_isxdigit: * @c: a Unicode character. * * Determines if a character is a hexidecimal digit. * * Return value: %TRUE if the character is a hexadecimal digit **/ gboolean g_unichar_isxdigit (gunichar c) { return ((c >= 'a' && c <= 'f') || (c >= 'A' && c <= 'F') || (TYPE (c) == G_UNICODE_DECIMAL_NUMBER)); } /** * g_unichar_isdefined: * @c: a Unicode character * * Determines if a given character is assigned in the Unicode * standard. * * Return value: %TRUE if the character has an assigned value **/ gboolean g_unichar_isdefined (gunichar c) { return TYPE (c) != G_UNICODE_UNASSIGNED; } /** * g_unichar_iszerowidth: * @c: a Unicode character * * Determines if a given character typically takes zero width when rendered. * The return value is %TRUE for all non-spacing and enclosing marks * (e.g., combining accents), format characters, zero-width * space, but not U+00AD SOFT HYPHEN. * * A typical use of this function is with one of g_unichar_iswide() or * g_unichar_iswide_cjk() to determine the number of cells a string occupies * when displayed on a grid display (terminals). However, note that not all * terminals support zero-width rendering of zero-width marks. * * Return value: %TRUE if the character has zero width * * Since: 2.14 **/ gboolean g_unichar_iszerowidth (gunichar c) { if (G_UNLIKELY (c == 0x00AD)) return FALSE; if (G_UNLIKELY (ISZEROWIDTHTYPE (TYPE (c)))) return TRUE; if (G_UNLIKELY ((c >= 0x1160 && c < 0x1200) || c == 0x200B)) return TRUE; return FALSE; } /** * g_unichar_iswide: * @c: a Unicode character * * Determines if a character is typically rendered in a double-width * cell. * * Return value: %TRUE if the character is wide **/ gboolean g_unichar_iswide (gunichar c) { gunichar ucs = c; /* The following block is stolen from Markus Kuhn 's * wcwidth implementation. */ return (ucs >= 0x1100 && (ucs <= 0x115f || /* Hangul Jamo init. consonants */ ucs == 0x2329 || ucs == 0x232a || (ucs >= 0x2e80 && ucs <= 0xa4cf && ucs != 0x303f) || /* CJK ... Yi */ (ucs >= 0xac00 && ucs <= 0xd7a3) || /* Hangul Syllables */ (ucs >= 0xf900 && ucs <= 0xfaff) || /* CJK Compatibility Ideographs */ (ucs >= 0xfe10 && ucs <= 0xfe19) || /* Vertical forms */ (ucs >= 0xfe30 && ucs <= 0xfe6f) || /* CJK Compatibility Forms */ (ucs >= 0xff00 && ucs <= 0xff60) || /* Fullwidth Forms */ (ucs >= 0xffe0 && ucs <= 0xffe6) || (ucs >= 0x20000 && ucs <= 0x2fffd) || (ucs >= 0x30000 && ucs <= 0x3fffd))); } /* The following block is stolen from Markus Kuhn 's * wcwidth implementation. */ struct Interval { gunichar start, end; }; /* The following block is stolen from Markus Kuhn 's * wcwidth implementation. */ static int interval_compare (const void *key, const void *elt) { gunichar c = GPOINTER_TO_UINT (key); struct Interval *interval = (struct Interval *)elt; if (c < interval->start) return -1; if (c > interval->end) return +1; return 0; } /** * g_unichar_iswide_cjk: * @c: a Unicode character * * Determines if a character is typically rendered in a double-width * cell under legacy East Asian locales. If a character is wide according to * g_unichar_iswide(), then it is also reported wide with this function, but * the converse is not necessarily true. See the * Unicode Standard * Annex #11 for details. * * Return value: %TRUE if the character is wide in legacy East Asian locales * * Since: 2.12 */ gboolean g_unichar_iswide_cjk (gunichar c) { /* The following block is stolen from Markus Kuhn 's * wcwidth implementation. */ /* sorted list of non-overlapping intervals of East Asian Ambiguous * characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */ static const struct Interval ambiguous[] = { { 0x0300, 0x036F }, { 0x0483, 0x0486 }, { 0x0488, 0x0489 }, { 0x0591, 0x05BD }, { 0x05BF, 0x05BF }, { 0x05C1, 0x05C2 }, { 0x05C4, 0x05C5 }, { 0x05C7, 0x05C7 }, { 0x0600, 0x0603 }, { 0x0610, 0x0615 }, { 0x064B, 0x065E }, { 0x0670, 0x0670 }, { 0x06D6, 0x06E4 }, { 0x06E7, 0x06E8 }, { 0x06EA, 0x06ED }, { 0x070F, 0x070F }, { 0x0711, 0x0711 }, { 0x0730, 0x074A }, { 0x07A6, 0x07B0 }, { 0x07EB, 0x07F3 }, { 0x0901, 0x0902 }, { 0x093C, 0x093C }, { 0x0941, 0x0948 }, { 0x094D, 0x094D }, { 0x0951, 0x0954 }, { 0x0962, 0x0963 }, { 0x0981, 0x0981 }, { 0x09BC, 0x09BC }, { 0x09C1, 0x09C4 }, { 0x09CD, 0x09CD }, { 0x09E2, 0x09E3 }, { 0x0A01, 0x0A02 }, { 0x0A3C, 0x0A3C }, { 0x0A41, 0x0A42 }, { 0x0A47, 0x0A48 }, { 0x0A4B, 0x0A4D }, { 0x0A70, 0x0A71 }, { 0x0A81, 0x0A82 }, { 0x0ABC, 0x0ABC }, { 0x0AC1, 0x0AC5 }, { 0x0AC7, 0x0AC8 }, { 0x0ACD, 0x0ACD }, { 0x0AE2, 0x0AE3 }, { 0x0B01, 0x0B01 }, { 0x0B3C, 0x0B3C }, { 0x0B3F, 0x0B3F }, { 0x0B41, 0x0B43 }, { 0x0B4D, 0x0B4D }, { 0x0B56, 0x0B56 }, { 0x0B82, 0x0B82 }, { 0x0BC0, 0x0BC0 }, { 0x0BCD, 0x0BCD }, { 0x0C3E, 0x0C40 }, { 0x0C46, 0x0C48 }, { 0x0C4A, 0x0C4D }, { 0x0C55, 0x0C56 }, { 0x0CBC, 0x0CBC }, { 0x0CBF, 0x0CBF }, { 0x0CC6, 0x0CC6 }, { 0x0CCC, 0x0CCD }, { 0x0CE2, 0x0CE3 }, { 0x0D41, 0x0D43 }, { 0x0D4D, 0x0D4D }, { 0x0DCA, 0x0DCA }, { 0x0DD2, 0x0DD4 }, { 0x0DD6, 0x0DD6 }, { 0x0E31, 0x0E31 }, { 0x0E34, 0x0E3A }, { 0x0E47, 0x0E4E }, { 0x0EB1, 0x0EB1 }, { 0x0EB4, 0x0EB9 }, { 0x0EBB, 0x0EBC }, { 0x0EC8, 0x0ECD }, { 0x0F18, 0x0F19 }, { 0x0F35, 0x0F35 }, { 0x0F37, 0x0F37 }, { 0x0F39, 0x0F39 }, { 0x0F71, 0x0F7E }, { 0x0F80, 0x0F84 }, { 0x0F86, 0x0F87 }, { 0x0F90, 0x0F97 }, { 0x0F99, 0x0FBC }, { 0x0FC6, 0x0FC6 }, { 0x102D, 0x1030 }, { 0x1032, 0x1032 }, { 0x1036, 0x1037 }, { 0x1039, 0x1039 }, { 0x1058, 0x1059 }, { 0x1160, 0x11FF }, { 0x135F, 0x135F }, { 0x1712, 0x1714 }, { 0x1732, 0x1734 }, { 0x1752, 0x1753 }, { 0x1772, 0x1773 }, { 0x17B4, 0x17B5 }, { 0x17B7, 0x17BD }, { 0x17C6, 0x17C6 }, { 0x17C9, 0x17D3 }, { 0x17DD, 0x17DD }, { 0x180B, 0x180D }, { 0x18A9, 0x18A9 }, { 0x1920, 0x1922 }, { 0x1927, 0x1928 }, { 0x1932, 0x1932 }, { 0x1939, 0x193B }, { 0x1A17, 0x1A18 }, { 0x1B00, 0x1B03 }, { 0x1B34, 0x1B34 }, { 0x1B36, 0x1B3A }, { 0x1B3C, 0x1B3C }, { 0x1B42, 0x1B42 }, { 0x1B6B, 0x1B73 }, { 0x1DC0, 0x1DCA }, { 0x1DFE, 0x1DFF }, { 0x200B, 0x200F }, { 0x202A, 0x202E }, { 0x2060, 0x2063 }, { 0x206A, 0x206F }, { 0x20D0, 0x20EF }, { 0x302A, 0x302F }, { 0x3099, 0x309A }, { 0xA806, 0xA806 }, { 0xA80B, 0xA80B }, { 0xA825, 0xA826 }, { 0xFB1E, 0xFB1E }, { 0xFE00, 0xFE0F }, { 0xFE20, 0xFE23 }, { 0xFEFF, 0xFEFF }, { 0xFFF9, 0xFFFB }, { 0x10A01, 0x10A03 }, { 0x10A05, 0x10A06 }, { 0x10A0C, 0x10A0F }, { 0x10A38, 0x10A3A }, { 0x10A3F, 0x10A3F }, { 0x1D167, 0x1D169 }, { 0x1D173, 0x1D182 }, { 0x1D185, 0x1D18B }, { 0x1D1AA, 0x1D1AD }, { 0x1D242, 0x1D244 }, { 0xE0001, 0xE0001 }, { 0xE0020, 0xE007F }, { 0xE0100, 0xE01EF } }; if (g_unichar_iswide (c)) return TRUE; if (bsearch (GUINT_TO_POINTER (c), ambiguous, G_N_ELEMENTS (ambiguous), sizeof ambiguous[0], interval_compare)) return TRUE; return FALSE; } /** * g_unichar_toupper: * @c: a Unicode character * * Converts a character to uppercase. * * Return value: the result of converting @c to uppercase. * If @c is not an lowercase or titlecase character, * or has no upper case equivalent @c is returned unchanged. **/ gunichar g_unichar_toupper (gunichar c) { int t = TYPE (c); if (t == G_UNICODE_LOWERCASE_LETTER) { gunichar val = ATTTABLE (c >> 8, c & 0xff); if (val >= 0x1000000) { const gchar *p = special_case_table + val - 0x1000000; val = g_utf8_get_char (p); } /* Some lowercase letters, e.g., U+000AA, FEMININE ORDINAL INDICATOR, * do not have an uppercase equivalent, in which case val will be * zero. */ return val ? val : c; } else if (t == G_UNICODE_TITLECASE_LETTER) { unsigned int i; for (i = 0; i < G_N_ELEMENTS (title_table); ++i) { if (title_table[i][0] == c) return title_table[i][1]; } } return c; } /** * g_unichar_tolower: * @c: a Unicode character. * * Converts a character to lower case. * * Return value: the result of converting @c to lower case. * If @c is not an upperlower or titlecase character, * or has no lowercase equivalent @c is returned unchanged. **/ gunichar g_unichar_tolower (gunichar c) { int t = TYPE (c); if (t == G_UNICODE_UPPERCASE_LETTER) { gunichar val = ATTTABLE (c >> 8, c & 0xff); if (val >= 0x1000000) { const gchar *p = special_case_table + val - 0x1000000; return g_utf8_get_char (p); } else { /* Not all uppercase letters are guaranteed to have a lowercase * equivalent. If this is the case, val will be zero. */ return val ? val : c; } } else if (t == G_UNICODE_TITLECASE_LETTER) { unsigned int i; for (i = 0; i < G_N_ELEMENTS (title_table); ++i) { if (title_table[i][0] == c) return title_table[i][2]; } } return c; } /** * g_unichar_totitle: * @c: a Unicode character * * Converts a character to the titlecase. * * Return value: the result of converting @c to titlecase. * If @c is not an uppercase or lowercase character, * @c is returned unchanged. **/ gunichar g_unichar_totitle (gunichar c) { unsigned int i; for (i = 0; i < G_N_ELEMENTS (title_table); ++i) { if (title_table[i][0] == c || title_table[i][1] == c || title_table[i][2] == c) return title_table[i][0]; } if (TYPE (c) == G_UNICODE_LOWERCASE_LETTER) return g_unichar_toupper (c); return c; } /** * g_unichar_digit_value: * @c: a Unicode character * * Determines the numeric value of a character as a decimal * digit. * * Return value: If @c is a decimal digit (according to * g_unichar_isdigit()), its numeric value. Otherwise, -1. **/ int g_unichar_digit_value (gunichar c) { if (TYPE (c) == G_UNICODE_DECIMAL_NUMBER) return ATTTABLE (c >> 8, c & 0xff); return -1; } /** * g_unichar_xdigit_value: * @c: a Unicode character * * Determines the numeric value of a character as a hexidecimal * digit. * * Return value: If @c is a hex digit (according to * g_unichar_isxdigit()), its numeric value. Otherwise, -1. **/ int g_unichar_xdigit_value (gunichar c) { if (c >= 'A' && c <= 'F') return c - 'A' + 10; if (c >= 'a' && c <= 'f') return c - 'a' + 10; if (TYPE (c) == G_UNICODE_DECIMAL_NUMBER) return ATTTABLE (c >> 8, c & 0xff); return -1; } /** * g_unichar_type: * @c: a Unicode character * * Classifies a Unicode character by type. * * Return value: the type of the character. **/ GUnicodeType g_unichar_type (gunichar c) { return TYPE (c); } /* * Case mapping functions */ typedef enum { LOCALE_NORMAL, LOCALE_TURKIC, LOCALE_LITHUANIAN } LocaleType; static LocaleType get_locale_type (void) { #ifdef G_OS_WIN32 char *tem = g_win32_getlocale (); char locale[2]; locale[0] = tem[0]; locale[1] = tem[1]; g_free (tem); #else const char *locale = setlocale (LC_CTYPE, NULL); #endif switch (locale[0]) { case 'a': if (locale[1] == 'z') return LOCALE_TURKIC; break; case 'l': if (locale[1] == 't') return LOCALE_LITHUANIAN; break; case 't': if (locale[1] == 'r') return LOCALE_TURKIC; break; } return LOCALE_NORMAL; } static gint output_marks (const char **p_inout, char *out_buffer, gboolean remove_dot) { const char *p = *p_inout; gint len = 0; while (*p) { gunichar c = g_utf8_get_char (p); if (ISMARK (TYPE (c))) { if (!remove_dot || c != 0x307 /* COMBINING DOT ABOVE */) len += g_unichar_to_utf8 (c, out_buffer ? out_buffer + len : NULL); p = g_utf8_next_char (p); } else break; } *p_inout = p; return len; } static gint output_special_case (gchar *out_buffer, int offset, int type, int which) { const gchar *p = special_case_table + offset; gint len; if (type != G_UNICODE_TITLECASE_LETTER) p = g_utf8_next_char (p); if (which == 1) p += strlen (p) + 1; len = strlen (p); if (out_buffer) memcpy (out_buffer, p, len); return len; } static gsize real_toupper (const gchar *str, gssize max_len, gchar *out_buffer, LocaleType locale_type) { const gchar *p = str; const char *last = NULL; gsize len = 0; gboolean last_was_i = FALSE; while ((max_len < 0 || p < str + max_len) && *p) { gunichar c = g_utf8_get_char (p); int t = TYPE (c); gunichar val; last = p; p = g_utf8_next_char (p); if (locale_type == LOCALE_LITHUANIAN) { if (c == 'i') last_was_i = TRUE; else { if (last_was_i) { /* Nasty, need to remove any dot above. Though * I think only E WITH DOT ABOVE occurs in practice * which could simplify this considerably. */ gsize decomp_len, i; gunichar *decomp; decomp = g_unicode_canonical_decomposition (c, &decomp_len); for (i=0; i < decomp_len; i++) { if (decomp[i] != 0x307 /* COMBINING DOT ABOVE */) len += g_unichar_to_utf8 (g_unichar_toupper (decomp[i]), out_buffer ? out_buffer + len : NULL); } g_free (decomp); len += output_marks (&p, out_buffer ? out_buffer + len : NULL, TRUE); continue; } if (!ISMARK (t)) last_was_i = FALSE; } } if (locale_type == LOCALE_TURKIC && c == 'i') { /* i => LATIN CAPITAL LETTER I WITH DOT ABOVE */ len += g_unichar_to_utf8 (0x130, out_buffer ? out_buffer + len : NULL); } else if (c == 0x0345) /* COMBINING GREEK YPOGEGRAMMENI */ { /* Nasty, need to move it after other combining marks .. this would go away if * we normalized first. */ len += output_marks (&p, out_buffer ? out_buffer + len : NULL, FALSE); /* And output as GREEK CAPITAL LETTER IOTA */ len += g_unichar_to_utf8 (0x399, out_buffer ? out_buffer + len : NULL); } else if (IS (t, OR (G_UNICODE_LOWERCASE_LETTER, OR (G_UNICODE_TITLECASE_LETTER, 0)))) { val = ATTTABLE (c >> 8, c & 0xff); if (val >= 0x1000000) { len += output_special_case (out_buffer ? out_buffer + len : NULL, val - 0x1000000, t, t == G_UNICODE_LOWERCASE_LETTER ? 0 : 1); } else { if (t == G_UNICODE_TITLECASE_LETTER) { unsigned int i; for (i = 0; i < G_N_ELEMENTS (title_table); ++i) { if (title_table[i][0] == c) { val = title_table[i][1]; break; } } } /* Some lowercase letters, e.g., U+000AA, FEMININE ORDINAL INDICATOR, * do not have an uppercase equivalent, in which case val will be * zero. */ len += g_unichar_to_utf8 (val ? val : c, out_buffer ? out_buffer + len : NULL); } } else { gsize char_len = g_utf8_skip[*(guchar *)last]; if (out_buffer) memcpy (out_buffer + len, last, char_len); len += char_len; } } return len; } /** * g_utf8_strup: * @str: a UTF-8 encoded string * @len: length of @str, in bytes, or -1 if @str is nul-terminated. * * Converts all Unicode characters in the string that have a case * to uppercase. The exact manner that this is done depends * on the current locale, and may result in the number of * characters in the string increasing. (For instance, the * German ess-zet will be changed to SS.) * * Return value: a newly allocated string, with all characters * converted to uppercase. **/ gchar * g_utf8_strup (const gchar *str, gssize len) { gsize result_len; LocaleType locale_type; gchar *result; g_return_val_if_fail (str != NULL, NULL); locale_type = get_locale_type (); /* * We use a two pass approach to keep memory management simple */ result_len = real_toupper (str, len, NULL, locale_type); result = g_malloc (result_len + 1); real_toupper (str, len, result, locale_type); result[result_len] = '\0'; return result; } /* traverses the string checking for characters with combining class == 230 * until a base character is found */ static gboolean has_more_above (const gchar *str) { const gchar *p = str; gint combining_class; while (*p) { combining_class = g_unichar_combining_class (g_utf8_get_char (p)); if (combining_class == 230) return TRUE; else if (combining_class == 0) break; p = g_utf8_next_char (p); } return FALSE; } static gsize real_tolower (const gchar *str, gssize max_len, gchar *out_buffer, LocaleType locale_type) { const gchar *p = str; const char *last = NULL; gsize len = 0; while ((max_len < 0 || p < str + max_len) && *p) { gunichar c = g_utf8_get_char (p); int t = TYPE (c); gunichar val; last = p; p = g_utf8_next_char (p); if (locale_type == LOCALE_TURKIC && c == 'I') { if (g_utf8_get_char (p) == 0x0307) { /* I + COMBINING DOT ABOVE => i (U+0069) */ len += g_unichar_to_utf8 (0x0069, out_buffer ? out_buffer + len : NULL); p = g_utf8_next_char (p); } else { /* I => LATIN SMALL LETTER DOTLESS I */ len += g_unichar_to_utf8 (0x131, out_buffer ? out_buffer + len : NULL); } } /* Introduce an explicit dot above when lowercasing capital I's and J's * whenever there are more accents above. [SpecialCasing.txt] */ else if (locale_type == LOCALE_LITHUANIAN && (c == 0x00cc || c == 0x00cd || c == 0x0128)) { len += g_unichar_to_utf8 (0x0069, out_buffer ? out_buffer + len : NULL); len += g_unichar_to_utf8 (0x0307, out_buffer ? out_buffer + len : NULL); switch (c) { case 0x00cc: len += g_unichar_to_utf8 (0x0300, out_buffer ? out_buffer + len : NULL); break; case 0x00cd: len += g_unichar_to_utf8 (0x0301, out_buffer ? out_buffer + len : NULL); break; case 0x0128: len += g_unichar_to_utf8 (0x0303, out_buffer ? out_buffer + len : NULL); break; } } else if (locale_type == LOCALE_LITHUANIAN && (c == 'I' || c == 'J' || c == 0x012e) && has_more_above (p)) { len += g_unichar_to_utf8 (g_unichar_tolower (c), out_buffer ? out_buffer + len : NULL); len += g_unichar_to_utf8 (0x0307, out_buffer ? out_buffer + len : NULL); } else if (c == 0x03A3) /* GREEK CAPITAL LETTER SIGMA */ { if ((max_len < 0 || p < str + max_len) && *p) { gunichar next_c = g_utf8_get_char (p); int next_type = TYPE(next_c); /* SIGMA mapps differently depending on whether it is * final or not. The following simplified test would * fail in the case of combining marks following the * sigma, but I don't think that occurs in real text. * The test here matches that in ICU. */ if (ISALPHA (next_type)) /* Lu,Ll,Lt,Lm,Lo */ val = 0x3c3; /* GREEK SMALL SIGMA */ else val = 0x3c2; /* GREEK SMALL FINAL SIGMA */ } else val = 0x3c2; /* GREEK SMALL FINAL SIGMA */ len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL); } else if (IS (t, OR (G_UNICODE_UPPERCASE_LETTER, OR (G_UNICODE_TITLECASE_LETTER, 0)))) { val = ATTTABLE (c >> 8, c & 0xff); if (val >= 0x1000000) { len += output_special_case (out_buffer ? out_buffer + len : NULL, val - 0x1000000, t, 0); } else { if (t == G_UNICODE_TITLECASE_LETTER) { unsigned int i; for (i = 0; i < G_N_ELEMENTS (title_table); ++i) { if (title_table[i][0] == c) { val = title_table[i][2]; break; } } } /* Not all uppercase letters are guaranteed to have a lowercase * equivalent. If this is the case, val will be zero. */ len += g_unichar_to_utf8 (val ? val : c, out_buffer ? out_buffer + len : NULL); } } else { gsize char_len = g_utf8_skip[*(guchar *)last]; if (out_buffer) memcpy (out_buffer + len, last, char_len); len += char_len; } } return len; } /** * g_utf8_strdown: * @str: a UTF-8 encoded string * @len: length of @str, in bytes, or -1 if @str is nul-terminated. * * Converts all Unicode characters in the string that have a case * to lowercase. The exact manner that this is done depends * on the current locale, and may result in the number of * characters in the string changing. * * Return value: a newly allocated string, with all characters * converted to lowercase. **/ gchar * g_utf8_strdown (const gchar *str, gssize len) { gsize result_len; LocaleType locale_type; gchar *result; g_return_val_if_fail (str != NULL, NULL); locale_type = get_locale_type (); /* * We use a two pass approach to keep memory management simple */ result_len = real_tolower (str, len, NULL, locale_type); result = g_malloc (result_len + 1); real_tolower (str, len, result, locale_type); result[result_len] = '\0'; return result; } /** * g_utf8_casefold: * @str: a UTF-8 encoded string * @len: length of @str, in bytes, or -1 if @str is nul-terminated. * * Converts a string into a form that is independent of case. The * result will not correspond to any particular case, but can be * compared for equality or ordered with the results of calling * g_utf8_casefold() on other strings. * * Note that calling g_utf8_casefold() followed by g_utf8_collate() is * only an approximation to the correct linguistic case insensitive * ordering, though it is a fairly good one. Getting this exactly * right would require a more sophisticated collation function that * takes case sensitivity into account. GLib does not currently * provide such a function. * * Return value: a newly allocated string, that is a * case independent form of @str. **/ gchar * g_utf8_casefold (const gchar *str, gssize len) { GString *result; const char *p; g_return_val_if_fail (str != NULL, NULL); result = g_string_new (NULL); p = str; while ((len < 0 || p < str + len) && *p) { gunichar ch = g_utf8_get_char (p); int start = 0; int end = G_N_ELEMENTS (casefold_table); if (ch >= casefold_table[start].ch && ch <= casefold_table[end - 1].ch) { while (TRUE) { int half = (start + end) / 2; if (ch == casefold_table[half].ch) { g_string_append (result, casefold_table[half].data); goto next; } else if (half == start) break; else if (ch > casefold_table[half].ch) start = half; else end = half; } } g_string_append_unichar (result, g_unichar_tolower (ch)); next: p = g_utf8_next_char (p); } return g_string_free (result, FALSE); } /** * g_unichar_get_mirror_char: * @ch: a Unicode character * @mirrored_ch: location to store the mirrored character * * In Unicode, some characters are mirrored. This * means that their images are mirrored horizontally in text that is laid * out from right to left. For instance, "(" would become its mirror image, * ")", in right-to-left text. * * If @ch has the Unicode mirrored property and there is another unicode * character that typically has a glyph that is the mirror image of @ch's * glyph and @mirrored_ch is set, it puts that character in the address * pointed to by @mirrored_ch. Otherwise the original character is put. * * Return value: %TRUE if @ch has a mirrored character, %FALSE otherwise * * Since: 2.4 **/ gboolean g_unichar_get_mirror_char (gunichar ch, gunichar *mirrored_ch) { gboolean found; gunichar mirrored; mirrored = GLIB_GET_MIRRORING(ch); found = ch != mirrored; if (mirrored_ch) *mirrored_ch = mirrored; return found; } #define G_SCRIPT_TABLE_MIDPOINT (G_N_ELEMENTS (g_script_table) / 2) static inline GUnicodeScript g_unichar_get_script_bsearch (gunichar ch) { int lower = 0; int upper = G_N_ELEMENTS (g_script_table) - 1; static int saved_mid = G_SCRIPT_TABLE_MIDPOINT; int mid = saved_mid; do { if (ch < g_script_table[mid].start) upper = mid - 1; else if (ch >= g_script_table[mid].start + g_script_table[mid].chars) lower = mid + 1; else return g_script_table[saved_mid = mid].script; mid = (lower + upper) / 2; } while (lower <= upper); return G_UNICODE_SCRIPT_UNKNOWN; } /** * g_unichar_get_script: * @ch: a Unicode character * * Looks up the #GUnicodeScript for a particular character (as defined * by Unicode Standard Annex #24). No check is made for @ch being a * valid Unicode character; if you pass in invalid character, the * result is undefined. * * This function is equivalent to pango_script_for_unichar() and the * two are interchangeable. * * Return value: the #GUnicodeScript for the character. * * Since: 2.14 */ GUnicodeScript g_unichar_get_script (gunichar ch) { if (ch < G_EASY_SCRIPTS_RANGE) return g_script_easy_table[ch]; else return g_unichar_get_script_bsearch (ch); } #define __G_UNIPROP_C__ #include "galiasdef.c"