From 4460fa7eadc7b0ee9ed35fe84fd18547147e4a49 Mon Sep 17 00:00:00 2001 From: Konstantin Ritt Date: Mon, 24 Dec 2012 16:20:17 +0200 Subject: [PATCH] Implement hb_language_get_default_for_script() with a fallbacks to hb_language_get_default() if language can not be determined for a given script. Use it in hb_buffer_guess_segment_properties() instead of hb_language_get_default() when the language is not set. --- src/hb-buffer.cc | 5 +- src/hb-common.cc | 149 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ src/hb-common.h | 37 +++++++------- 3 files changed, 171 insertions(+), 20 deletions(-) diff --git a/src/hb-buffer.cc b/src/hb-buffer.cc index 4b644e4..bcf427a 100644 --- a/src/hb-buffer.cc +++ b/src/hb-buffer.cc @@ -514,10 +514,9 @@ hb_buffer_t::guess_segment_properties (void) props.direction = hb_script_get_horizontal_direction (props.script); } - /* If language is not set, use default language from locale */ + /* If language is not set, use guess language from script */ if (props.language == HB_LANGUAGE_INVALID) { - /* TODO get_default_for_script? using $LANGUAGE */ - props.language = hb_language_get_default (); + props.language = hb_language_get_default_for_script (props.script); } } diff --git a/src/hb-common.cc b/src/hb-common.cc index 9422555..1046db5 100644 --- a/src/hb-common.cc +++ b/src/hb-common.cc @@ -258,6 +258,155 @@ hb_language_get_default (void) return default_language; } +typedef struct { + char language[6]; + hb_script_t script; +} ScriptLang; + +/* + * Extracted from CLDR 22.1, and adjusted manually. + */ + +static const ScriptLang default_languages[] = { +/*{ "", HB_SCRIPT_COMMON }, */ + { "ar", HB_SCRIPT_ARABIC }, + { "hy", HB_SCRIPT_ARMENIAN }, + { "bn", HB_SCRIPT_BENGALI }, + { "zh-tw", HB_SCRIPT_BOPOMOFO }, + { "iu", HB_SCRIPT_CANADIAN_ABORIGINAL }, + { "chr", HB_SCRIPT_CHEROKEE }, + { "cop", HB_SCRIPT_COPTIC }, + { "ru", HB_SCRIPT_CYRILLIC }, + { "hi", HB_SCRIPT_DEVANAGARI }, + { "ka", HB_SCRIPT_GEORGIAN }, + { "el", HB_SCRIPT_GREEK }, + { "gu", HB_SCRIPT_GUJARATI }, + { "pa", HB_SCRIPT_GURMUKHI }, + { "ko", HB_SCRIPT_HANGUL }, + { "zh-cn", HB_SCRIPT_HAN }, + { "he", HB_SCRIPT_HEBREW }, + { "ja", HB_SCRIPT_HIRAGANA }, +/*{ "", HB_SCRIPT_INHERITED }, */ + { "kn", HB_SCRIPT_KANNADA }, + { "ja", HB_SCRIPT_KATAKANA }, + { "lo", HB_SCRIPT_LAO }, + { "en", HB_SCRIPT_LATIN }, + { "ml", HB_SCRIPT_MALAYALAM }, + { "mn", HB_SCRIPT_MONGOLIAN }, + { "sga", HB_SCRIPT_OGHAM }, + { "or", HB_SCRIPT_ORIYA }, + { "non", HB_SCRIPT_RUNIC }, + { "syr", HB_SCRIPT_SYRIAC }, + { "ta", HB_SCRIPT_TAMIL }, + { "te", HB_SCRIPT_TELUGU }, + { "th", HB_SCRIPT_THAI }, + { "ii", HB_SCRIPT_YI }, + + /* Unicode-2.0 additions */ + { "bo", HB_SCRIPT_TIBETAN }, + + /* Unicode-3.0 additions */ + { "am", HB_SCRIPT_ETHIOPIC }, + { "km", HB_SCRIPT_KHMER }, + { "my", HB_SCRIPT_MYANMAR }, + { "si", HB_SCRIPT_SINHALA }, + { "dv", HB_SCRIPT_THAANA }, + + /* Unicode-3.1 additions */ + { "en", HB_SCRIPT_DESERET }, + { "got", HB_SCRIPT_GOTHIC }, + { "ett", HB_SCRIPT_OLD_ITALIC }, + + /* Unicode-3.2 additions */ + { "bku", HB_SCRIPT_BUHID }, + { "hnn", HB_SCRIPT_HANUNOO }, + { "fil", HB_SCRIPT_TAGALOG }, + { "tbw", HB_SCRIPT_TAGBANWA }, + + /* Unicode-4.0 additions */ +/*{ "", HB_SCRIPT_BRAILLE }, */ + { "grc", HB_SCRIPT_CYPRIOT }, + { "lif", HB_SCRIPT_LIMBU }, + { "grc", HB_SCRIPT_LINEAR_B }, + { "so", HB_SCRIPT_OSMANYA }, + { "en", HB_SCRIPT_SHAVIAN }, + { "tdd", HB_SCRIPT_TAI_LE }, + { "uga", HB_SCRIPT_UGARITIC }, + + /* Unicode-4.1 additions */ + { "bug", HB_SCRIPT_BUGINESE }, + { "cu", HB_SCRIPT_GLAGOLITIC }, + { "pra", HB_SCRIPT_KHAROSHTHI }, + { "khb", HB_SCRIPT_NEW_TAI_LUE }, + { "peo", HB_SCRIPT_OLD_PERSIAN }, + { "syl", HB_SCRIPT_SYLOTI_NAGRI }, + { "shi", HB_SCRIPT_TIFINAGH }, + + /* Unicode-5.0 additions */ + { "ban", HB_SCRIPT_BALINESE }, + { "akk", HB_SCRIPT_CUNEIFORM }, + { "man", HB_SCRIPT_NKO }, + { "lzh", HB_SCRIPT_PHAGS_PA }, + { "phn", HB_SCRIPT_PHOENICIAN }, +/*{ "", HB_SCRIPT_UNKNOWN }, */ + + /* Unicode-5.1 additions */ + { "xcr", HB_SCRIPT_CARIAN }, + { "cjm", HB_SCRIPT_CHAM }, + { "eky", HB_SCRIPT_KAYAH_LI }, + { "lep", HB_SCRIPT_LEPCHA }, + { "xlc", HB_SCRIPT_LYCIAN }, + { "xld", HB_SCRIPT_LYDIAN }, + { "sat", HB_SCRIPT_OL_CHIKI }, + { "rej", HB_SCRIPT_REJANG }, + { "saz", HB_SCRIPT_SAURASHTRA }, + { "su", HB_SCRIPT_SUNDANESE }, + { "vai", HB_SCRIPT_VAI }, + + /* Unicode-5.2 additions */ + { "ae", HB_SCRIPT_AVESTAN }, + { "bax", HB_SCRIPT_BAMUM }, + { "egy", HB_SCRIPT_EGYPTIAN_HIEROGLYPHS }, + { "arc", HB_SCRIPT_IMPERIAL_ARAMAIC }, + { "pal", HB_SCRIPT_INSCRIPTIONAL_PAHLAVI }, + { "xpr", HB_SCRIPT_INSCRIPTIONAL_PARTHIAN }, + { "jv", HB_SCRIPT_JAVANESE }, + { "bh", HB_SCRIPT_KAITHI }, + { "lis", HB_SCRIPT_LISU }, + { "mni", HB_SCRIPT_MEETEI_MAYEK }, + { "xsa", HB_SCRIPT_OLD_SOUTH_ARABIAN }, + { "otk", HB_SCRIPT_OLD_TURKIC }, + { "smp", HB_SCRIPT_SAMARITAN }, + { "nod", HB_SCRIPT_TAI_THAM }, + { "blt", HB_SCRIPT_TAI_VIET }, + + /* Unicode-6.0 additions */ + { "bbc", HB_SCRIPT_BATAK }, + { "pra", HB_SCRIPT_BRAHMI }, + { "myz", HB_SCRIPT_MANDAIC }, + + /* Unicode-6.1 additions */ + { "ccp", HB_SCRIPT_CHAKMA }, + { "xmr", HB_SCRIPT_MEROITIC_CURSIVE }, + { "xmr", HB_SCRIPT_MEROITIC_HIEROGLYPHS }, + { "hmd", HB_SCRIPT_MIAO }, + { "sa", HB_SCRIPT_SHARADA }, + { "srb", HB_SCRIPT_SORA_SOMPENG }, + { "doi", HB_SCRIPT_TAKRI } +}; + +hb_language_t +hb_language_get_default_for_script (hb_script_t script) +{ + unsigned int i; + + for (i = 0; i < ARRAY_LENGTH (default_languages); i++) + if (default_languages[i].script == script) + return hb_language_from_string (default_languages[i].language, -1); + + return hb_language_get_default (); +} + /* hb_script_t */ diff --git a/src/hb-common.h b/src/hb-common.h index cc221d3..eb29e08 100644 --- a/src/hb-common.h +++ b/src/hb-common.h @@ -129,23 +129,6 @@ hb_direction_to_string (hb_direction_t direction); #define HB_DIRECTION_REVERSE(dir) ((hb_direction_t) (((unsigned int) (dir)) ^ 1)) /* Direction must be valid */ -/* hb_language_t */ - -typedef struct hb_language_impl_t *hb_language_t; - -/* len=-1 means str is NUL-terminated */ -hb_language_t -hb_language_from_string (const char *str, int len); - -const char * -hb_language_to_string (hb_language_t language); - -#define HB_LANGUAGE_INVALID ((hb_language_t) NULL) - -hb_language_t -hb_language_get_default (void); - - /* hb_script_t */ /* http://unicode.org/iso15924/ */ @@ -302,6 +285,26 @@ hb_direction_t hb_script_get_horizontal_direction (hb_script_t script); +/* hb_language_t */ + +typedef struct hb_language_impl_t *hb_language_t; + +/* len=-1 means str is NUL-terminated */ +hb_language_t +hb_language_from_string (const char *str, int len); + +const char * +hb_language_to_string (hb_language_t language); + +#define HB_LANGUAGE_INVALID ((hb_language_t) NULL) + +hb_language_t +hb_language_get_default (void); + +hb_language_t +hb_language_get_default_for_script (hb_script_t script); + + /* User data */ typedef struct hb_user_data_key_t { -- 1.8.0.msysgit.0