+
+/**
+ * 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.
+ *
+ * Returns: %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.
+ *
+ * Returns: 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);
+}
+
+
+/* http://unicode.org/iso15924/ */
+static const guint32 iso15924_tags[] =
+{
+#define PACK(a,b,c,d) ((guint32)((((guint8)(a))<<24)|(((guint8)(b))<<16)|(((guint8)(c))<<8)|((guint8)(d))))
+
+ PACK ('Z','y','y','y'), /* G_UNICODE_SCRIPT_COMMON */
+ PACK ('Z','i','n','h'), /* G_UNICODE_SCRIPT_INHERITED */
+ PACK ('A','r','a','b'), /* G_UNICODE_SCRIPT_ARABIC */
+ PACK ('A','r','m','n'), /* G_UNICODE_SCRIPT_ARMENIAN */
+ PACK ('B','e','n','g'), /* G_UNICODE_SCRIPT_BENGALI */
+ PACK ('B','o','p','o'), /* G_UNICODE_SCRIPT_BOPOMOFO */
+ PACK ('C','h','e','r'), /* G_UNICODE_SCRIPT_CHEROKEE */
+ PACK ('C','o','p','t'), /* G_UNICODE_SCRIPT_COPTIC */
+ PACK ('C','y','r','l'), /* G_UNICODE_SCRIPT_CYRILLIC */
+ PACK ('D','s','r','t'), /* G_UNICODE_SCRIPT_DESERET */
+ PACK ('D','e','v','a'), /* G_UNICODE_SCRIPT_DEVANAGARI */
+ PACK ('E','t','h','i'), /* G_UNICODE_SCRIPT_ETHIOPIC */
+ PACK ('G','e','o','r'), /* G_UNICODE_SCRIPT_GEORGIAN */
+ PACK ('G','o','t','h'), /* G_UNICODE_SCRIPT_GOTHIC */
+ PACK ('G','r','e','k'), /* G_UNICODE_SCRIPT_GREEK */
+ PACK ('G','u','j','r'), /* G_UNICODE_SCRIPT_GUJARATI */
+ PACK ('G','u','r','u'), /* G_UNICODE_SCRIPT_GURMUKHI */
+ PACK ('H','a','n','i'), /* G_UNICODE_SCRIPT_HAN */
+ PACK ('H','a','n','g'), /* G_UNICODE_SCRIPT_HANGUL */
+ PACK ('H','e','b','r'), /* G_UNICODE_SCRIPT_HEBREW */
+ PACK ('H','i','r','a'), /* G_UNICODE_SCRIPT_HIRAGANA */
+ PACK ('K','n','d','a'), /* G_UNICODE_SCRIPT_KANNADA */
+ PACK ('K','a','n','a'), /* G_UNICODE_SCRIPT_KATAKANA */
+ PACK ('K','h','m','r'), /* G_UNICODE_SCRIPT_KHMER */
+ PACK ('L','a','o','o'), /* G_UNICODE_SCRIPT_LAO */
+ PACK ('L','a','t','n'), /* G_UNICODE_SCRIPT_LATIN */
+ PACK ('M','l','y','m'), /* G_UNICODE_SCRIPT_MALAYALAM */
+ PACK ('M','o','n','g'), /* G_UNICODE_SCRIPT_MONGOLIAN */
+ PACK ('M','y','m','r'), /* G_UNICODE_SCRIPT_MYANMAR */
+ PACK ('O','g','a','m'), /* G_UNICODE_SCRIPT_OGHAM */
+ PACK ('I','t','a','l'), /* G_UNICODE_SCRIPT_OLD_ITALIC */
+ PACK ('O','r','y','a'), /* G_UNICODE_SCRIPT_ORIYA */
+ PACK ('R','u','n','r'), /* G_UNICODE_SCRIPT_RUNIC */
+ PACK ('S','i','n','h'), /* G_UNICODE_SCRIPT_SINHALA */
+ PACK ('S','y','r','c'), /* G_UNICODE_SCRIPT_SYRIAC */
+ PACK ('T','a','m','l'), /* G_UNICODE_SCRIPT_TAMIL */
+ PACK ('T','e','l','u'), /* G_UNICODE_SCRIPT_TELUGU */
+ PACK ('T','h','a','a'), /* G_UNICODE_SCRIPT_THAANA */
+ PACK ('T','h','a','i'), /* G_UNICODE_SCRIPT_THAI */
+ PACK ('T','i','b','t'), /* G_UNICODE_SCRIPT_TIBETAN */
+ PACK ('C','a','n','s'), /* G_UNICODE_SCRIPT_CANADIAN_ABORIGINAL */
+ PACK ('Y','i','i','i'), /* G_UNICODE_SCRIPT_YI */
+ PACK ('T','g','l','g'), /* G_UNICODE_SCRIPT_TAGALOG */
+ PACK ('H','a','n','o'), /* G_UNICODE_SCRIPT_HANUNOO */
+ PACK ('B','u','h','d'), /* G_UNICODE_SCRIPT_BUHID */
+ PACK ('T','a','g','b'), /* G_UNICODE_SCRIPT_TAGBANWA */
+
+ /* Unicode-4.0 additions */
+ PACK ('B','r','a','i'), /* G_UNICODE_SCRIPT_BRAILLE */
+ PACK ('C','p','r','t'), /* G_UNICODE_SCRIPT_CYPRIOT */
+ PACK ('L','i','m','b'), /* G_UNICODE_SCRIPT_LIMBU */
+ PACK ('O','s','m','a'), /* G_UNICODE_SCRIPT_OSMANYA */
+ PACK ('S','h','a','w'), /* G_UNICODE_SCRIPT_SHAVIAN */
+ PACK ('L','i','n','b'), /* G_UNICODE_SCRIPT_LINEAR_B */
+ PACK ('T','a','l','e'), /* G_UNICODE_SCRIPT_TAI_LE */
+ PACK ('U','g','a','r'), /* G_UNICODE_SCRIPT_UGARITIC */
+
+ /* Unicode-4.1 additions */
+ PACK ('T','a','l','u'), /* G_UNICODE_SCRIPT_NEW_TAI_LUE */
+ PACK ('B','u','g','i'), /* G_UNICODE_SCRIPT_BUGINESE */
+ PACK ('G','l','a','g'), /* G_UNICODE_SCRIPT_GLAGOLITIC */
+ PACK ('T','f','n','g'), /* G_UNICODE_SCRIPT_TIFINAGH */
+ PACK ('S','y','l','o'), /* G_UNICODE_SCRIPT_SYLOTI_NAGRI */
+ PACK ('X','p','e','o'), /* G_UNICODE_SCRIPT_OLD_PERSIAN */
+ PACK ('K','h','a','r'), /* G_UNICODE_SCRIPT_KHAROSHTHI */
+
+ /* Unicode-5.0 additions */
+ PACK ('Z','z','z','z'), /* G_UNICODE_SCRIPT_UNKNOWN */
+ PACK ('B','a','l','i'), /* G_UNICODE_SCRIPT_BALINESE */
+ PACK ('X','s','u','x'), /* G_UNICODE_SCRIPT_CUNEIFORM */
+ PACK ('P','h','n','x'), /* G_UNICODE_SCRIPT_PHOENICIAN */
+ PACK ('P','h','a','g'), /* G_UNICODE_SCRIPT_PHAGS_PA */
+ PACK ('N','k','o','o'), /* G_UNICODE_SCRIPT_NKO */
+
+ /* Unicode-5.1 additions */
+ PACK ('K','a','l','i'), /* G_UNICODE_SCRIPT_KAYAH_LI */
+ PACK ('L','e','p','c'), /* G_UNICODE_SCRIPT_LEPCHA */
+ PACK ('R','j','n','g'), /* G_UNICODE_SCRIPT_REJANG */
+ PACK ('S','u','n','d'), /* G_UNICODE_SCRIPT_SUNDANESE */
+ PACK ('S','a','u','r'), /* G_UNICODE_SCRIPT_SAURASHTRA */
+ PACK ('C','h','a','m'), /* G_UNICODE_SCRIPT_CHAM */
+ PACK ('O','l','c','k'), /* G_UNICODE_SCRIPT_OL_CHIKI */
+ PACK ('V','a','i','i'), /* G_UNICODE_SCRIPT_VAI */
+ PACK ('C','a','r','i'), /* G_UNICODE_SCRIPT_CARIAN */
+ PACK ('L','y','c','i'), /* G_UNICODE_SCRIPT_LYCIAN */
+ PACK ('L','y','d','i'), /* G_UNICODE_SCRIPT_LYDIAN */
+
+ /* Unicode-5.2 additions */
+ PACK ('A','v','s','t'), /* G_UNICODE_SCRIPT_AVESTAN */
+ PACK ('B','a','m','u'), /* G_UNICODE_SCRIPT_BAMUM */
+ PACK ('E','g','y','p'), /* G_UNICODE_SCRIPT_EGYPTIAN_HIEROGLYPHS */
+ PACK ('A','r','m','i'), /* G_UNICODE_SCRIPT_IMPERIAL_ARAMAIC */
+ PACK ('P','h','l','i'), /* G_UNICODE_SCRIPT_INSCRIPTIONAL_PAHLAVI */
+ PACK ('P','r','t','i'), /* G_UNICODE_SCRIPT_INSCRIPTIONAL_PARTHIAN */
+ PACK ('J','a','v','a'), /* G_UNICODE_SCRIPT_JAVANESE */
+ PACK ('K','t','h','i'), /* G_UNICODE_SCRIPT_KAITHI */
+ PACK ('L','i','s','u'), /* G_UNICODE_SCRIPT_LISU */
+ PACK ('M','t','e','i'), /* G_UNICODE_SCRIPT_MEETEI_MAYEK */
+ PACK ('S','a','r','b'), /* G_UNICODE_SCRIPT_OLD_SOUTH_ARABIAN */
+ PACK ('O','r','k','h'), /* G_UNICODE_SCRIPT_OLD_TURKIC */
+ PACK ('S','a','m','r'), /* G_UNICODE_SCRIPT_SAMARITAN */
+ PACK ('L','a','n','a'), /* G_UNICODE_SCRIPT_TAI_THAM */
+ PACK ('T','a','v','t'), /* G_UNICODE_SCRIPT_TAI_VIET */
+
+ /* Unicode-6.0 additions */
+ PACK ('B','a','t','k'), /* G_UNICODE_SCRIPT_BATAK */
+ PACK ('B','r','a','h'), /* G_UNICODE_SCRIPT_BRAHMI */
+ PACK ('M','a','n','d'), /* G_UNICODE_SCRIPT_MANDAIC */
+
+ /* Unicode-6.1 additions */
+ PACK ('C','a','k','m'), /* G_UNICODE_SCRIPT_CHAKMA */
+ PACK ('M','e','r','c'), /* G_UNICODE_SCRIPT_MEROITIC_CURSIVE */
+ PACK ('M','e','r','o'), /* G_UNICODE_SCRIPT_MEROITIC_HIEROGLYPHS */
+ PACK ('P','l','r','d'), /* G_UNICODE_SCRIPT_MIAO */
+ PACK ('S','h','r','d'), /* G_UNICODE_SCRIPT_SHARADA */
+ PACK ('S','o','r','a'), /* G_UNICODE_SCRIPT_SORA_SOMPENG */
+ PACK ('T','a','k','r'), /* G_UNICODE_SCRIPT_TAKRI */
+
+ /* Unicode 7.0 additions */
+ PACK ('B','a','s','s'), /* G_UNICODE_SCRIPT_BASSA_VAH */
+ PACK ('A','g','h','b'), /* G_UNICODE_SCRIPT_CAUCASIAN_ALBANIAN */
+ PACK ('D','u','p','l'), /* G_UNICODE_SCRIPT_DUPLOYAN */
+ PACK ('E','l','b','a'), /* G_UNICODE_SCRIPT_ELBASAN */
+ PACK ('G','r','a','n'), /* G_UNICODE_SCRIPT_GRANTHA */
+ PACK ('K','h','o','j'), /* G_UNICODE_SCRIPT_KHOJKI*/
+ PACK ('S','i','n','d'), /* G_UNICODE_SCRIPT_KHUDAWADI */
+ PACK ('L','i','n','a'), /* G_UNICODE_SCRIPT_LINEAR_A */
+ PACK ('M','a','h','j'), /* G_UNICODE_SCRIPT_MAHAJANI */
+ PACK ('M','a','n','u'), /* G_UNICODE_SCRIPT_MANICHAEAN */
+ PACK ('M','e','n','d'), /* G_UNICODE_SCRIPT_MENDE_KIKAKUI */
+ PACK ('M','o','d','i'), /* G_UNICODE_SCRIPT_MODI */
+ PACK ('M','r','o','o'), /* G_UNICODE_SCRIPT_MRO */
+ PACK ('N','b','a','t'), /* G_UNICODE_SCRIPT_NABATAEAN */
+ PACK ('N','a','r','b'), /* G_UNICODE_SCRIPT_OLD_NORTH_ARABIAN */
+ PACK ('P','e','r','m'), /* G_UNICODE_SCRIPT_OLD_PERMIC */
+ PACK ('H','m','n','g'), /* G_UNICODE_SCRIPT_PAHAWH_HMONG */
+ PACK ('P','a','l','m'), /* G_UNICODE_SCRIPT_PALMYRENE */
+ PACK ('P','a','u','c'), /* G_UNICODE_SCRIPT_PAU_CIN_HAU */
+ PACK ('P','h','l','p'), /* G_UNICODE_SCRIPT_PSALTER_PAHLAVI */
+ PACK ('S','i','d','d'), /* G_UNICODE_SCRIPT_SIDDHAM */
+ PACK ('T','i','r','h'), /* G_UNICODE_SCRIPT_TIRHUTA */
+ PACK ('W','a','r','a'), /* G_UNICODE_SCRIPT_WARANG_CITI */
+
+#undef PACK
+};
+
+/**
+ * g_unicode_script_to_iso15924:
+ * @script: a Unicode script
+ *
+ * Looks up the ISO 15924 code for @script. ISO 15924 assigns four-letter
+ * codes to scripts. For example, the code for Arabic is 'Arab'. The
+ * four letter codes are encoded as a @guint32 by this function in a
+ * big-endian fashion. That is, the code returned for Arabic is
+ * 0x41726162 (0x41 is ASCII code for 'A', 0x72 is ASCII code for 'r', etc).
+ *
+ * See
+ * [Codes for the representation of names of scripts](http://unicode.org/iso15924/codelists.html)
+ * for details.
+ *
+ * Returns: the ISO 15924 code for @script, encoded as an integer,
+ * of zero if @script is %G_UNICODE_SCRIPT_INVALID_CODE or
+ * ISO 15924 code 'Zzzz' (script code for UNKNOWN) if @script is not understood.
+ *
+ * Since: 2.30
+ */
+guint32
+g_unicode_script_to_iso15924 (GUnicodeScript script)
+{
+ if (G_UNLIKELY (script == G_UNICODE_SCRIPT_INVALID_CODE))
+ return 0;
+
+ if (G_UNLIKELY (script < 0 || script >= (int) G_N_ELEMENTS (iso15924_tags)))
+ return 0x5A7A7A7A;
+
+ return iso15924_tags[script];
+}
+
+/**
+ * g_unicode_script_from_iso15924:
+ * @iso15924: a Unicode script
+ *
+ * Looks up the Unicode script for @iso15924. ISO 15924 assigns four-letter
+ * codes to scripts. For example, the code for Arabic is 'Arab'.
+ * This function accepts four letter codes encoded as a @guint32 in a
+ * big-endian fashion. That is, the code expected for Arabic is
+ * 0x41726162 (0x41 is ASCII code for 'A', 0x72 is ASCII code for 'r', etc).
+ *
+ * See
+ * [Codes for the representation of names of scripts](http://unicode.org/iso15924/codelists.html)
+ * for details.
+ *
+ * Returns: the Unicode script for @iso15924, or
+ * of %G_UNICODE_SCRIPT_INVALID_CODE if @iso15924 is zero and
+ * %G_UNICODE_SCRIPT_UNKNOWN if @iso15924 is unknown.
+ *
+ * Since: 2.30
+ */
+GUnicodeScript
+g_unicode_script_from_iso15924 (guint32 iso15924)
+{
+ unsigned int i;
+
+ if (!iso15924)
+ return G_UNICODE_SCRIPT_INVALID_CODE;
+
+ for (i = 0; i < G_N_ELEMENTS (iso15924_tags); i++)
+ if (iso15924_tags[i] == iso15924)
+ return (GUnicodeScript) i;
+
+ return G_UNICODE_SCRIPT_UNKNOWN;
+}