diff options
Diffstat (limited to 'java/src')
5 files changed, 449 insertions, 362 deletions
diff --git a/java/src/com/android/inputmethod/keyboard/ProximityInfo.java b/java/src/com/android/inputmethod/keyboard/ProximityInfo.java index 6b59a8dae..90394ce5e 100644 --- a/java/src/com/android/inputmethod/keyboard/ProximityInfo.java +++ b/java/src/com/android/inputmethod/keyboard/ProximityInfo.java @@ -21,7 +21,6 @@ import android.text.TextUtils; import com.android.inputmethod.keyboard.Keyboard.Params.TouchPositionCorrection; import com.android.inputmethod.latin.JniUtils; -import com.android.inputmethod.latin.spellcheck.SpellCheckerProximityInfo; import java.util.Arrays; import java.util.HashMap; @@ -75,15 +74,12 @@ public class ProximityInfo { return new ProximityInfo("", 1, 1, 1, 1, 1, 1, EMPTY_KEY_ARRAY, null); } - public static ProximityInfo createSpellCheckerProximityInfo(final int[] proximity) { + public static ProximityInfo createSpellCheckerProximityInfo(final int[] proximity, + int rowSize, int gridWidth, int gridHeight) { final ProximityInfo spellCheckerProximityInfo = createDummyProximityInfo(); spellCheckerProximityInfo.mNativeProximityInfo = spellCheckerProximityInfo.setProximityInfoNative("", - SpellCheckerProximityInfo.ROW_SIZE, - SpellCheckerProximityInfo.PROXIMITY_GRID_WIDTH, - SpellCheckerProximityInfo.PROXIMITY_GRID_HEIGHT, - SpellCheckerProximityInfo.PROXIMITY_GRID_WIDTH, - SpellCheckerProximityInfo.PROXIMITY_GRID_HEIGHT, + rowSize, gridWidth, gridHeight, gridWidth, gridHeight, 1, proximity, 0, null, null, null, null, null, null, null, null); return spellCheckerProximityInfo; } diff --git a/java/src/com/android/inputmethod/keyboard/internal/KeyboardTextsSet.java b/java/src/com/android/inputmethod/keyboard/internal/KeyboardTextsSet.java index 1b516755f..425b5e0bf 100644 --- a/java/src/com/android/inputmethod/keyboard/internal/KeyboardTextsSet.java +++ b/java/src/com/android/inputmethod/keyboard/internal/KeyboardTextsSet.java @@ -161,80 +161,79 @@ public final class KeyboardTextsSet { /* 45 */ "more_keys_for_currency_euro", /* 46 */ "more_keys_for_currency_pound", /* 47 */ "more_keys_for_currency_general", - /* 48 */ "more_keys_for_smiley", - /* 49 */ "more_keys_for_punctuation", - /* 50 */ "keyhintlabel_for_punctuation", - /* 51 */ "more_keys_for_star", - /* 52 */ "more_keys_for_plus", - /* 53 */ "more_keys_for_left_parenthesis", - /* 54 */ "more_keys_for_right_parenthesis", - /* 55 */ "more_keys_for_less_than", - /* 56 */ "more_keys_for_greater_than", - /* 57 */ "keylabel_for_popular_domain", - /* 58 */ "more_keys_for_popular_domain", - /* 59 */ "keylabel_for_symbols_1", - /* 60 */ "keylabel_for_symbols_2", - /* 61 */ "keylabel_for_symbols_3", - /* 62 */ "keylabel_for_symbols_4", - /* 63 */ "keylabel_for_symbols_5", - /* 64 */ "keylabel_for_symbols_6", - /* 65 */ "keylabel_for_symbols_7", - /* 66 */ "keylabel_for_symbols_8", - /* 67 */ "keylabel_for_symbols_9", - /* 68 */ "keylabel_for_symbols_0", - /* 69 */ "additional_more_keys_for_symbols_1", - /* 70 */ "additional_more_keys_for_symbols_2", - /* 71 */ "additional_more_keys_for_symbols_3", - /* 72 */ "additional_more_keys_for_symbols_4", - /* 73 */ "additional_more_keys_for_symbols_5", - /* 74 */ "additional_more_keys_for_symbols_6", - /* 75 */ "additional_more_keys_for_symbols_7", - /* 76 */ "additional_more_keys_for_symbols_8", - /* 77 */ "additional_more_keys_for_symbols_9", - /* 78 */ "additional_more_keys_for_symbols_0", - /* 79 */ "more_keys_for_symbols_1", - /* 80 */ "more_keys_for_symbols_2", - /* 81 */ "more_keys_for_symbols_3", - /* 82 */ "more_keys_for_symbols_4", - /* 83 */ "more_keys_for_symbols_5", - /* 84 */ "more_keys_for_symbols_6", - /* 85 */ "more_keys_for_symbols_7", - /* 86 */ "more_keys_for_symbols_8", - /* 87 */ "more_keys_for_symbols_9", - /* 88 */ "more_keys_for_symbols_0", - /* 89 */ "keylabel_for_comma", - /* 90 */ "more_keys_for_comma", - /* 91 */ "keylabel_for_symbols_question", - /* 92 */ "keylabel_for_symbols_semicolon", - /* 93 */ "keylabel_for_symbols_percent", - /* 94 */ "more_keys_for_symbols_question", - /* 95 */ "more_keys_for_symbols_semicolon", - /* 96 */ "more_keys_for_symbols_percent", - /* 97 */ "keylabel_for_tablet_comma", - /* 98 */ "keyhintlabel_for_tablet_comma", - /* 99 */ "more_keys_for_tablet_comma", - /* 100 */ "keyhintlabel_for_tablet_period", - /* 101 */ "more_keys_for_tablet_period", - /* 102 */ "keylabel_for_apostrophe", - /* 103 */ "keylabel_for_dash", - /* 104 */ "keyhintlabel_for_apostrophe", - /* 105 */ "keyhintlabel_for_dash", - /* 106 */ "more_keys_for_apostrophe", - /* 107 */ "more_keys_for_dash", - /* 108 */ "more_keys_for_bullet", - /* 109 */ "more_keys_for_am_pm", - /* 110 */ "settings_as_more_key", - /* 111 */ "shortcut_as_more_key", - /* 112 */ "action_next_as_more_key", - /* 113 */ "action_previous_as_more_key", - /* 114 */ "label_to_more_symbol_key", - /* 115 */ "label_to_more_symbol_for_tablet_key", - /* 116 */ "label_tab_key", - /* 117 */ "label_to_phone_numeric_key", - /* 118 */ "label_to_phone_symbols_key", - /* 119 */ "label_time_am", - /* 120 */ "label_time_pm", - /* 121 */ "label_to_symbol_key_pcqwerty", + /* 48 */ "more_keys_for_punctuation", + /* 49 */ "more_keys_for_star", + /* 50 */ "more_keys_for_bullet", + /* 51 */ "more_keys_for_plus", + /* 52 */ "more_keys_for_left_parenthesis", + /* 53 */ "more_keys_for_right_parenthesis", + /* 54 */ "more_keys_for_less_than", + /* 55 */ "more_keys_for_greater_than", + /* 56 */ "keylabel_for_symbols_1", + /* 57 */ "keylabel_for_symbols_2", + /* 58 */ "keylabel_for_symbols_3", + /* 59 */ "keylabel_for_symbols_4", + /* 60 */ "keylabel_for_symbols_5", + /* 61 */ "keylabel_for_symbols_6", + /* 62 */ "keylabel_for_symbols_7", + /* 63 */ "keylabel_for_symbols_8", + /* 64 */ "keylabel_for_symbols_9", + /* 65 */ "keylabel_for_symbols_0", + /* 66 */ "additional_more_keys_for_symbols_1", + /* 67 */ "additional_more_keys_for_symbols_2", + /* 68 */ "additional_more_keys_for_symbols_3", + /* 69 */ "additional_more_keys_for_symbols_4", + /* 70 */ "additional_more_keys_for_symbols_5", + /* 71 */ "additional_more_keys_for_symbols_6", + /* 72 */ "additional_more_keys_for_symbols_7", + /* 73 */ "additional_more_keys_for_symbols_8", + /* 74 */ "additional_more_keys_for_symbols_9", + /* 75 */ "additional_more_keys_for_symbols_0", + /* 76 */ "more_keys_for_symbols_1", + /* 77 */ "more_keys_for_symbols_2", + /* 78 */ "more_keys_for_symbols_3", + /* 79 */ "more_keys_for_symbols_4", + /* 80 */ "more_keys_for_symbols_5", + /* 81 */ "more_keys_for_symbols_6", + /* 82 */ "more_keys_for_symbols_7", + /* 83 */ "more_keys_for_symbols_8", + /* 84 */ "more_keys_for_symbols_9", + /* 85 */ "more_keys_for_symbols_0", + /* 86 */ "keylabel_for_comma", + /* 87 */ "more_keys_for_comma", + /* 88 */ "keylabel_for_symbols_exclamation", + /* 89 */ "keylabel_for_symbols_question", + /* 90 */ "keylabel_for_symbols_semicolon", + /* 91 */ "keylabel_for_symbols_percent", + /* 92 */ "more_keys_for_symbols_exclamation", + /* 93 */ "more_keys_for_symbols_question", + /* 94 */ "more_keys_for_symbols_semicolon", + /* 95 */ "more_keys_for_symbols_percent", + /* 96 */ "keylabel_for_tablet_comma", + /* 97 */ "keyhintlabel_for_tablet_comma", + /* 98 */ "more_keys_for_tablet_comma", + /* 99 */ "keyhintlabel_for_tablet_period", + /* 100 */ "more_keys_for_tablet_period", + /* 101 */ "keylabel_for_apostrophe", + /* 102 */ "keyhintlabel_for_apostrophe", + /* 103 */ "more_keys_for_apostrophe", + /* 104 */ "more_keys_for_am_pm", + /* 105 */ "settings_as_more_key", + /* 106 */ "shortcut_as_more_key", + /* 107 */ "action_next_as_more_key", + /* 108 */ "action_previous_as_more_key", + /* 109 */ "label_to_more_symbol_key", + /* 110 */ "label_to_more_symbol_for_tablet_key", + /* 111 */ "label_tab_key", + /* 112 */ "label_to_phone_numeric_key", + /* 113 */ "label_to_phone_symbols_key", + /* 114 */ "label_time_am", + /* 115 */ "label_time_pm", + /* 116 */ "label_to_symbol_key_pcqwerty", + /* 117 */ "keylabel_for_popular_domain", + /* 118 */ "more_keys_for_popular_domain", + /* 119 */ "more_keys_for_smiley", + /* 120 */ "more_keys_for_arabic_diacritics", }; private static final String EMPTY = ""; @@ -263,19 +262,23 @@ public final class KeyboardTextsSet { /* 45 */ "\u00A2,\u00A3,$,\u00A5,\u20B1", /* 46 */ "\u00A2,$,\u20AC,\u00A5,\u20B1", /* 47 */ "\u00A2,$,\u20AC,\u00A3,\u00A5,\u20B1", - /* 48 */ "!fixedColumnOrder!5,!hasLabels!,=-O|=-O ,:-P|:-P ,;-)|;-) ,:-(|:-( ,:-)|:-) ,:-!|:-! ,:-$|:-$ ,B-)|B-) ,:O|:O ,:-*|:-* ,:-D|:-D ,:\'(|:\'( ,:-\\\\|:-\\\\ ,O:-)|O:-) ,:-[|:-[ ", - /* 49 */ "!fixedColumnOrder!8,\",\',#,-,:,!,\\,,?,@,&,\\%,+,;,/,(,)", - /* 50 */ EMPTY, + /* 48 */ "!fixedColumnOrder!8,\",\',#,-,:,!,\\,,?,@,&,\\%,+,;,/,(,)", // U+2020: "†" DAGGER // U+2021: "‡" DOUBLE DAGGER // U+2605: "★" BLACK STAR - /* 51 */ "\u2020,\u2021,\u2605", + /* 49 */ "\u2020,\u2021,\u2605", + // U+266A: "♪" EIGHTH NOTE + // U+2665: "♥" BLACK HEART SUIT + // U+2660: "♠" BLACK SPADE SUIT + // U+2666: "♦" BLACK DIAMOND SUIT + // U+2663: "♣" BLACK CLUB SUIT + /* 50 */ "\u266A,\u2665,\u2660,\u2666,\u2663", // U+00B1: "±" PLUS-MINUS SIGN - /* 52 */ "\u00B1", + /* 51 */ "\u00B1", // The all letters need to be mirrored are found at // http://www.unicode.org/Public/6.1.0/ucd/BidiMirroring.txt - /* 53 */ "!fixedColumnOrder!3,<,{,[", - /* 54 */ "!fixedColumnOrder!3,>,},]", + /* 52 */ "!fixedColumnOrder!3,<,{,[", + /* 53 */ "!fixedColumnOrder!3,>,},]", // U+2039: "‹" SINGLE LEFT-POINTING ANGLE QUOTATION MARK // U+203A: "›" SINGLE RIGHT-POINTING ANGLE QUOTATION MARK // U+2264: "≤" LESS-THAN OR EQUAL TO @@ -291,99 +294,110 @@ public final class KeyboardTextsSet { // U+201D: "”" RIGHT DOUBLE QUOTATION MARK // U+201E: "„" DOUBLE LOW-9 QUOTATION MARK // U+201F: "‟" DOUBLE HIGH-REVERSED-9 QUOTATION MARK - /* 55 */ "!fixedColumnOrder!3,\u2039,\u2264,\u00AB", - /* 56 */ "!fixedColumnOrder!3,\u203A,\u2265,\u00BB", - /* 57 */ ".com", - // popular web domains for the locale - most popular, displayed on the keyboard - /* 58 */ "!hasLabels!,.net,.org,.gov,.edu", - /* 59 */ "1", - /* 60 */ "2", - /* 61 */ "3", - /* 62 */ "4", - /* 63 */ "5", - /* 64 */ "6", - /* 65 */ "7", - /* 66 */ "8", - /* 67 */ "9", - /* 68 */ "0", - /* 69~ */ + /* 54 */ "!fixedColumnOrder!3,\u2039,\u2264,\u00AB", + /* 55 */ "!fixedColumnOrder!3,\u203A,\u2265,\u00BB", + /* 56 */ "1", + /* 57 */ "2", + /* 58 */ "3", + /* 59 */ "4", + /* 60 */ "5", + /* 61 */ "6", + /* 62 */ "7", + /* 63 */ "8", + /* 64 */ "9", + /* 65 */ "0", + /* 66~ */ EMPTY, EMPTY, EMPTY, EMPTY, EMPTY, EMPTY, EMPTY, EMPTY, EMPTY, EMPTY, - /* ~78 */ + /* ~75 */ // U+00B9: "¹" SUPERSCRIPT ONE // U+00BD: "½" VULGAR FRACTION ONE HALF // U+2153: "⅓" VULGAR FRACTION ONE THIRD // U+00BC: "¼" VULGAR FRACTION ONE QUARTER // U+215B: "⅛" VULGAR FRACTION ONE EIGHTH - /* 79 */ "\u00B9,\u00BD,\u2153,\u00BC,\u215B", + /* 76 */ "\u00B9,\u00BD,\u2153,\u00BC,\u215B", // U+00B2: "²" SUPERSCRIPT TWO // U+2154: "⅔" VULGAR FRACTION TWO THIRDS - /* 80 */ "\u00B2,\u2154", + /* 77 */ "\u00B2,\u2154", // U+00B3: "³" SUPERSCRIPT THREE // U+00BE: "¾" VULGAR FRACTION THREE QUARTERS // U+215C: "⅜" VULGAR FRACTION THREE EIGHTHS - /* 81 */ "\u00B3,\u00BE,\u215C", + /* 78 */ "\u00B3,\u00BE,\u215C", // U+2074: "⁴" SUPERSCRIPT FOUR - /* 82 */ "\u2074", + /* 79 */ "\u2074", // U+215D: "⅝" VULGAR FRACTION FIVE EIGHTHS - /* 83 */ "\u215D", - /* 84 */ EMPTY, + /* 80 */ "\u215D", + /* 81 */ EMPTY, // U+215E: "⅞" VULGAR FRACTION SEVEN EIGHTHS - /* 85 */ "\u215E", - /* 86 */ EMPTY, - /* 87 */ EMPTY, + /* 82 */ "\u215E", + /* 83 */ EMPTY, + /* 84 */ EMPTY, // U+207F: "ⁿ" SUPERSCRIPT LATIN SMALL LETTER N // U+2205: "∅" EMPTY SET - /* 88 */ "\u207F,\u2205", - /* 89 */ ",", - /* 90 */ EMPTY, - /* 91 */ "?", - /* 92 */ ";", - /* 93 */ "%", + /* 85 */ "\u207F,\u2205", + /* 86 */ ",", + /* 87 */ EMPTY, + /* 88 */ "!", + /* 89 */ "?", + /* 90 */ ";", + /* 91 */ "%", + // U+00A1: "¡" INVERTED EXCLAMATION MARK + /* 92 */ "\u00A1", // U+00BF: "¿" INVERTED QUESTION MARK - /* 94 */ "\u00BF", - /* 95 */ EMPTY, + /* 93 */ "\u00BF", + /* 94 */ EMPTY, // U+2030: "‰" PER MILLE SIGN - /* 96 */ "\u2030", - /* 97 */ ",", + /* 95 */ "\u2030", + /* 96 */ ",", + /* 97 */ "!", /* 98 */ "!", - /* 99 */ "!", + /* 99 */ "?", /* 100 */ "?", - /* 101 */ "?", - /* 102 */ "\'", - /* 103 */ "-", - /* 104 */ "\"", - /* 105 */ "_", - /* 106 */ "\"", - /* 107 */ "_", - // U+266A: "♪" EIGHTH NOTE - // U+2665: "♥" BLACK HEART SUIT - // U+2660: "♠" BLACK SPADE SUIT - // U+2666: "♦" BLACK DIAMOND SUIT - // U+2663: "♣" BLACK CLUB SUIT - /* 108 */ "\u266A,\u2665,\u2660,\u2666,\u2663", - /* 109 */ "!fixedColumnOrder!2,!hasLabels!,!text/label_time_am,!text/label_time_pm", - /* 110 */ "!icon/settings_key|!code/key_settings", - /* 111 */ "!icon/shortcut_key|!code/key_shortcut", - /* 112 */ "!hasLabels!,!text/label_next_key|!code/key_action_next", - /* 113 */ "!hasLabels!,!text/label_previous_key|!code/key_action_previous", + /* 101 */ "\'", + /* 102 */ "\"", + /* 103 */ "\"", + /* 104 */ "!fixedColumnOrder!2,!hasLabels!,!text/label_time_am,!text/label_time_pm", + /* 105 */ "!icon/settings_key|!code/key_settings", + /* 106 */ "!icon/shortcut_key|!code/key_shortcut", + /* 107 */ "!hasLabels!,!text/label_next_key|!code/key_action_next", + /* 108 */ "!hasLabels!,!text/label_previous_key|!code/key_action_previous", // Label for "switch to more symbol" modifier key. Must be short to fit on key! - /* 114 */ "= \\ <", + /* 109 */ "= \\ <", // Label for "switch to more symbol" modifier key on tablets. Must be short to fit on key! - /* 115 */ "~ \\ {", + /* 110 */ "~ \\ {", // Label for "Tab" key. Must be short to fit on key! - /* 116 */ "Tab", + /* 111 */ "Tab", // Label for "switch to phone numeric" key. Must be short to fit on key! - /* 117 */ "123", + /* 112 */ "123", // Label for "switch to phone symbols" key. Must be short to fit on key! // U+FF0A: "＊" FULLWIDTH ASTERISK // U+FF03: "＃" FULLWIDTH NUMBER SIGN - /* 118 */ "\uFF0A\uFF03", + /* 113 */ "\uFF0A\uFF03", // Key label for "ante meridiem" - /* 119 */ "AM", + /* 114 */ "AM", // Key label for "post meridiem" - /* 120 */ "PM", + /* 115 */ "PM", // Label for "switch to symbols" key on PC QWERTY layout - /* 121 */ "Sym", + /* 116 */ "Sym", + /* 117 */ ".com", + // popular web domains for the locale - most popular, displayed on the keyboard + /* 118 */ "!hasLabels!,.net,.org,.gov,.edu", + /* 119 */ "!fixedColumnOrder!5,!hasLabels!,=-O|=-O ,:-P|:-P ,;-)|;-) ,:-(|:-( ,:-)|:-) ,:-!|:-! ,:-$|:-$ ,B-)|B-) ,:O|:O ,:-*|:-* ,:-D|:-D ,:\'(|:\'( ,:-\\\\|:-\\\\ ,O:-)|O:-) ,:-[|:-[ ", + // U+064F: "ُ" ARABIC DAMMA + // U+064C: "ٌ" ARABIC DAMMATAN + // U+0651: "ّ" ARABIC SHADDA + // U+0652: "ْ" ARABIC SUKUN + // U+0653: "ٓ" ARABIC MADDAH ABOVE + // U+064D: "ٍ" ARABIC KASRATAN + // U+064B: "ً" ARABIC FATHATAN + // U+0650: "ِ" ARABIC KASRA + // U+064E: "َ" ARABIC FATHA + // U+0640: "ـ" ARABIC TATWEEL + // U+0656: "ٖ" ARABIC SUBSCRIPT ALEF + // U+0670: "ٰ" ARABIC LETTER SUPERSCRIPT ALEF + // U+0655: "ٕ" ARABIC HAMZA BELOW + // U+0654: "ٔ" ARABIC HAMZA ABOVE + // In order to make Tatweel easily distinguishable from other punctuations, we use consecutive Tatweels only for its displayed label. + /* 120 */ "!fixedColumnOrder!5,\u064F,\u064C,\u0651,\u0652,\u0653,\u064D,\u064B,\u0650,\u064E,\u0640\u0640\u0640|\u0640,\u0656,\u0670,\u0655,\u0654", }; /* Language ar: Arabic */ @@ -400,38 +414,24 @@ public final class KeyboardTextsSet { // <string name="more_keys_for_tablet_double_quote">!fixedColumnOrder!6,“,”,„,‟,«|»,»|«;,‘,’,‚,‛</string> /* 43 */ "!fixedColumnOrder!4,\u201C,\u201D,\u00AB|\u00BB,\u00BB|\u00AB,\u2018,\u2019,\u201A,\u201B", /* 44~ */ - null, null, null, null, null, - /* ~48 */ + null, null, null, null, + /* ~47 */ // U+061F: "؟" ARABIC QUESTION MARK // U+060C: "،" ARABIC COMMA // U+061B: "؛" ARABIC SEMICOLON - // U+0650: "ِ" ARABIC KASRA - // U+064E: "َ" ARABIC FATHA - // U+064D: "ٍ" ARABIC KASRATAN - // U+064B: "ً" ARABIC FATHATAN - // U+0656: "ٖ" ARABIC SUBSCRIPT ALEF - // U+0670: "ٰ" ARABIC LETTER SUPERSCRIPT ALEF - // U+0655: "ٕ" ARABIC HAMZA BELOW - // U+0654: "ٔ" ARABIC HAMZA ABOVE - // U+064F: "ُ" ARABIC DAMMA - // U+064C: "ٌ" ARABIC DAMMATAN - // U+0651: "ّ" ARABIC SHADDA - // U+0652: "ْ" ARABIC SUKUN - // U+0653: "ٓ" ARABIC MADDAH ABOVE - // U+0640: "ـ" ARABIC TATWEEL - // In order to make Tatweel easily distinguishable from other punctuations, we use consecutive Tatweels only for its displayed label. - /* 49 */ "!fixedColumnOrder!8,\",\',-,:,!,\u061F,\u060C,\u061B,\u0650,\u064E,\u064D,\u064B,\u0656,\u0670,\u0655,\u0654,\u064F,\u064C,\u0651,\u0652,\u0653,\u0640\u0640\u0640|\u0640,/", - /* 50 */ "\u064B", + /* 48 */ "!fixedColumnOrder!8,\",\',#,-,:,!,\u060C,\u061F,@,&,\\%,+,\u061B,/,(,)", // U+2605: "★" BLACK STAR // U+066D: "٭" ARABIC FIVE POINTED STAR - /* 51 */ "\u2605,\u066D", - /* 52 */ null, + /* 49 */ "\u2605,\u066D", + // U+266A: "♪" EIGHTH NOTE + /* 50 */ "\u266A", + /* 51 */ null, // The all letters need to be mirrored are found at // http://www.unicode.org/Public/6.1.0/ucd/BidiMirroring.txt // U+FD3E: "﴾" ORNATE LEFT PARENTHESIS // U+FD3F: "﴿" ORNATE RIGHT PARENTHESIS - /* 53 */ "!fixedColumnOrder!4,\uFD3E|\uFD3F,<|>,{|},[|]", - /* 54 */ "!fixedColumnOrder!4,\uFD3F|\uFD3E,>|<,}|{,]|[", + /* 52 */ "!fixedColumnOrder!4,\uFD3E|\uFD3F,<|>,{|},[|]", + /* 53 */ "!fixedColumnOrder!4,\uFD3F|\uFD3E,>|<,}|{,]|[", // U+2264: "≤" LESS-THAN OR EQUAL TO // U+2265: "≥" GREATER-THAN EQUAL TO // U+00AB: "«" LEFT-POINTING DOUBLE ANGLE QUOTATION MARK @@ -447,85 +447,65 @@ public final class KeyboardTextsSet { // U+201D: "”" RIGHT DOUBLE QUOTATION MARK // U+201E: "„" DOUBLE LOW-9 QUOTATION MARK // U+201F: "‟" DOUBLE HIGH-REVERSED-9 QUOTATION MARK - /* 55 */ "!fixedColumnOrder!3,\u2039|\u203A,\u2264|\u2265,\u00AB|\u00BB", - /* 56 */ "!fixedColumnOrder!3,\u203A|\u2039,\u2265|\u2264,\u00BB|\u00AB", - /* 57 */ null, - /* 58 */ null, + /* 54 */ "!fixedColumnOrder!3,\u2039|\u203A,\u2264|\u2265,\u00AB|\u00BB", + /* 55 */ "!fixedColumnOrder!3,\u203A|\u2039,\u2265|\u2264,\u00BB|\u00AB", // U+0661: "١" ARABIC-INDIC DIGIT ONE - /* 59 */ "\u0661", + /* 56 */ "\u0661", // U+0662: "٢" ARABIC-INDIC DIGIT TWO - /* 60 */ "\u0662", + /* 57 */ "\u0662", // U+0663: "٣" ARABIC-INDIC DIGIT THREE - /* 61 */ "\u0663", + /* 58 */ "\u0663", // U+0664: "٤" ARABIC-INDIC DIGIT FOUR - /* 62 */ "\u0664", + /* 59 */ "\u0664", // U+0665: "٥" ARABIC-INDIC DIGIT FIVE - /* 63 */ "\u0665", + /* 60 */ "\u0665", // U+0666: "٦" ARABIC-INDIC DIGIT SIX - /* 64 */ "\u0666", + /* 61 */ "\u0666", // U+0667: "٧" ARABIC-INDIC DIGIT SEVEN - /* 65 */ "\u0667", + /* 62 */ "\u0667", // U+0668: "٨" ARABIC-INDIC DIGIT EIGHT - /* 66 */ "\u0668", + /* 63 */ "\u0668", // U+0669: "٩" ARABIC-INDIC DIGIT NINE - /* 67 */ "\u0669", + /* 64 */ "\u0669", // U+0660: "٠" ARABIC-INDIC DIGIT ZERO - /* 68 */ "\u0660", - /* 69 */ "1", - /* 70 */ "2", - /* 71 */ "3", - /* 72 */ "4", - /* 73 */ "5", - /* 74 */ "6", - /* 75 */ "7", - /* 76 */ "8", - /* 77 */ "9", + /* 65 */ "\u0660", + /* 66 */ "1", + /* 67 */ "2", + /* 68 */ "3", + /* 69 */ "4", + /* 70 */ "5", + /* 71 */ "6", + /* 72 */ "7", + /* 73 */ "8", + /* 74 */ "9", // U+066B: "٫" ARABIC DECIMAL SEPARATOR // U+066C: "٬" ARABIC THOUSANDS SEPARATOR - /* 78 */ "0,\u066B,\u066C", - /* 79~ */ + /* 75 */ "0,\u066B,\u066C", + /* 76~ */ null, null, null, null, null, null, null, null, null, null, - /* ~88 */ + /* ~85 */ // U+060C: "،" ARABIC COMMA - /* 89 */ "\u060C", - /* 90 */ "\\,", - /* 91 */ "\u061F", - /* 92 */ "\u061B", + /* 86 */ "\u060C", + /* 87 */ "\\,", + /* 88 */ null, + /* 89 */ "\u061F", + /* 90 */ "\u061B", // U+066A: "٪" ARABIC PERCENT SIGN - /* 93 */ "\u066A", - /* 94 */ "?", - /* 95 */ ";", + /* 91 */ "\u066A", + /* 92 */ null, + /* 93 */ "?", + /* 94 */ ";", // U+2030: "‰" PER MILLE SIGN - /* 96 */ "\\%,\u2030", - /* 97~ */ + /* 95 */ "\\%,\u2030", + /* 96~ */ null, null, null, null, null, - /* ~101 */ + /* ~100 */ // U+060C: "،" ARABIC COMMA // U+061B: "؛" ARABIC SEMICOLON // U+061F: "؟" ARABIC QUESTION MARK - /* 102 */ "\u060C", - /* 103 */ ".", - /* 104 */ "\u061F", - /* 105 */ "\u064B", - /* 106 */ "\u061F,\u061B,!,:,-,/,\',\"", - // U+0651: "ّ" ARABIC SHADDA - // U+0652: "ْ" ARABIC SUKUN - // U+064C: "ٌ" ARABIC DAMMATAN - // U+0653: "ٓ" ARABIC MADDAH ABOVE - // U+064F: "ُ" ARABIC DAMMA - // U+0650: "ِ" ARABIC KASRA - // U+064E: "َ" ARABIC FATHA - // U+064B: "ً" ARABIC FATHATAN - // U+0640: "ـ" ARABIC TATWEEL - // U+064D: "ٍ" ARABIC KASRATAN - // U+0670: "ٰ" ARABIC LETTER SUPERSCRIPT ALEF - // U+0656: "ٖ" ARABIC SUBSCRIPT ALEF - // U+0654: "ٔ" ARABIC HAMZA ABOVE - // U+0655: "ٕ" ARABIC HAMZA BELOW - // In order to make Tatweel easily distinguishable from other punctuations, we use consecutive Tatweels only for its displayed label. - /* 107 */ "\u0651,\u0652,\u064C,\u0653,\u064F,\u0650,\u064E,\u064B,\u0640\u0640\u0640|\u0640,\u064D,\u0654,\u0656,\u0655,\u0670", - // U+266A: "♪" EIGHTH NOTE - /* 108 */ "\u266A", + /* 101 */ "\u060C", + /* 102 */ "\u061F", + /* 103 */ "\u061F,\u061B,!,:,-,/,\',\"", }; /* Language be: Belarusian */ @@ -881,11 +861,31 @@ public final class KeyboardTextsSet { /* 8~ */ null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, - null, null, null, null, null, null, null, null, null, null, null, - /* ~48 */ + null, null, null, null, null, null, null, null, null, null, + /* ~47 */ + // U+00A1: "¡" INVERTED EXCLAMATION MARK + // U+00BF: "¿" INVERTED QUESTION MARK + /* 48 */ "!fixedColumnOrder!9,\",\',#,-,\u00A1,!,\u00BF,\\,,?,@,&,\\%,+,;,:,/,(,)", + /* 49~ */ + null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, + null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, + null, null, null, null, null, null, null, null, null, + /* ~87 */ // U+00A1: "¡" INVERTED EXCLAMATION MARK + /* 88 */ "\u00A1", // U+00BF: "¿" INVERTED QUESTION MARK - /* 49 */ "!fixedColumnOrder!7,#,-,\u00A1,!,\u00BF,\\,,?,\\%,+,;,:,/,(,),@,&,\",\'", + /* 89 */ "\u00BF", + /* 90 */ null, + /* 91 */ null, + /* 92 */ "!", + /* 93 */ "?", + /* 94~ */ + null, null, null, + /* ~96 */ + /* 97 */ "\u00A1", + /* 98 */ "\u00A1,!", + /* 99 */ "\u00BF", + /* 100 */ "\u00BF,?", }; /* Language et: Estonian */ @@ -1002,38 +1002,24 @@ public final class KeyboardTextsSet { // <string name="more_keys_for_tablet_double_quote">!fixedColumnOrder!6,“,”,„,‟,«|»,»|«;,‘,’,‚,‛</string> /* 43 */ "!fixedColumnOrder!4,\u201C,\u201D,\u00AB|\u00BB,\u00BB|\u00AB,\u2018,\u2019,\u201A,\u201B", /* 44~ */ - null, null, null, null, null, - /* ~48 */ + null, null, null, null, + /* ~47 */ // U+061F: "؟" ARABIC QUESTION MARK // U+060C: "،" ARABIC COMMA // U+061B: "؛" ARABIC SEMICOLON - // U+0650: "ِ" ARABIC KASRA - // U+064E: "َ" ARABIC FATHA - // U+064D: "ٍ" ARABIC KASRATAN - // U+064B: "ً" ARABIC FATHATAN - // U+0656: "ٖ" ARABIC SUBSCRIPT ALEF - // U+0670: "ٰ" ARABIC LETTER SUPERSCRIPT ALEF - // U+0655: "ٕ" ARABIC HAMZA BELOW - // U+0654: "ٔ" ARABIC HAMZA ABOVE - // U+064F: "ُ" ARABIC DAMMA - // U+064C: "ٌ" ARABIC DAMMATAN - // U+0651: "ّ" ARABIC SHADDA - // U+0652: "ْ" ARABIC SUKUN - // U+0653: "ٓ" ARABIC MADDAH ABOVE - // U+0640: "ـ" ARABIC TATWEEL - // In order to make Tatweel easily distinguishable from other punctuations, we use consecutive Tatweels only for its displayed label. - /* 49 */ "!fixedColumnOrder!8,\",\',-,:,!,\u061F,\u060C,\u061B,\u0650,\u064E,\u064D,\u064B,\u0656,\u0670,\u0655,\u0654,\u064F,\u064C,\u0651,\u0652,\u0653,\u0640\u0640\u0640|\u0640,/", - /* 50 */ "\u064B", + /* 48 */ "!fixedColumnOrder!8,\",\',#,-,:,!,\u060C,\u061F,@,&,\\%,+,\u061B,/,(,)", // U+2605: "★" BLACK STAR // U+066D: "٭" ARABIC FIVE POINTED STAR - /* 51 */ "\u2605,\u066D", - /* 52 */ null, + /* 49 */ "\u2605,\u066D", + // U+266A: "♪" EIGHTH NOTE + /* 50 */ "\u266A", + /* 51 */ null, // The all letters need to be mirrored are found at // http://www.unicode.org/Public/6.1.0/ucd/BidiMirroring.txt // U+FD3E: "﴾" ORNATE LEFT PARENTHESIS // U+FD3F: "﴿" ORNATE RIGHT PARENTHESIS - /* 53 */ "!fixedColumnOrder!4,\uFD3E|\uFD3F,<|>,{|},[|]", - /* 54 */ "!fixedColumnOrder!4,\uFD3F|\uFD3E,>|<,}|{,]|[", + /* 52 */ "!fixedColumnOrder!4,\uFD3E|\uFD3F,<|>,{|},[|]", + /* 53 */ "!fixedColumnOrder!4,\uFD3F|\uFD3E,>|<,}|{,]|[", // U+2264: "≤" LESS-THAN OR EQUAL TO // U+2265: "≥" GREATER-THAN EQUAL TO // U+00AB: "«" LEFT-POINTING DOUBLE ANGLE QUOTATION MARK @@ -1049,87 +1035,67 @@ public final class KeyboardTextsSet { // U+201D: "”" RIGHT DOUBLE QUOTATION MARK // U+201E: "„" DOUBLE LOW-9 QUOTATION MARK // U+201F: "‟" DOUBLE HIGH-REVERSED-9 QUOTATION MARK - /* 55 */ "!fixedColumnOrder!3,\u2039|\u203A,\u2264|\u2265,\u00AB|\u00BB", - /* 56 */ "!fixedColumnOrder!3,\u203A|\u2039,\u2265|\u2264,\u00BB|\u00AB", - /* 57 */ null, - /* 58 */ null, + /* 54 */ "!fixedColumnOrder!3,\u2039|\u203A,\u2264|\u2265,\u00AB|\u00BB", + /* 55 */ "!fixedColumnOrder!3,\u203A|\u2039,\u2265|\u2264,\u00BB|\u00AB", // U+06F1: "۱" EXTENDED ARABIC-INDIC DIGIT ONE - /* 59 */ "\u06F1", + /* 56 */ "\u06F1", // U+06F2: "۲" EXTENDED ARABIC-INDIC DIGIT TWO - /* 60 */ "\u06F2", + /* 57 */ "\u06F2", // U+06F3: "۳" EXTENDED ARABIC-INDIC DIGIT THREE - /* 61 */ "\u06F3", + /* 58 */ "\u06F3", // U+06F4: "۴" EXTENDED ARABIC-INDIC DIGIT FOUR - /* 62 */ "\u06F4", + /* 59 */ "\u06F4", // U+06F5: "۵" EXTENDED ARABIC-INDIC DIGIT FIVE - /* 63 */ "\u06F5", + /* 60 */ "\u06F5", // U+06F6: "۶" EXTENDED ARABIC-INDIC DIGIT SIX - /* 64 */ "\u06F6", + /* 61 */ "\u06F6", // U+06F7: "۷" EXTENDED ARABIC-INDIC DIGIT SEVEN - /* 65 */ "\u06F7", + /* 62 */ "\u06F7", // U+06F8: "۸" EXTENDED ARABIC-INDIC DIGIT EIGHT - /* 66 */ "\u06F8", + /* 63 */ "\u06F8", // U+06F9: "۹" EXTENDED ARABIC-INDIC DIGIT NINE - /* 67 */ "\u06F9", + /* 64 */ "\u06F9", // U+06F0: "۰" EXTENDED ARABIC-INDIC DIGIT ZERO - /* 68 */ "\u06F0", - /* 69 */ "1", - /* 70 */ "2", - /* 71 */ "3", - /* 72 */ "4", - /* 73 */ "5", - /* 74 */ "6", - /* 75 */ "7", - /* 76 */ "8", - /* 77 */ "9", + /* 65 */ "\u06F0", + /* 66 */ "1", + /* 67 */ "2", + /* 68 */ "3", + /* 69 */ "4", + /* 70 */ "5", + /* 71 */ "6", + /* 72 */ "7", + /* 73 */ "8", + /* 74 */ "9", // U+066B: "٫" ARABIC DECIMAL SEPARATOR // U+066C: "٬" ARABIC THOUSANDS SEPARATOR - /* 78 */ "0,\u066B,\u066C", - /* 79~ */ + /* 75 */ "0,\u066B,\u066C", + /* 76~ */ null, null, null, null, null, null, null, null, null, null, - /* ~88 */ + /* ~85 */ // U+060C: "،" ARABIC COMMA - /* 89 */ "\u060C", - /* 90 */ "\\,", - /* 91 */ "\u061F", - /* 92 */ "\u061B", + /* 86 */ "\u060C", + /* 87 */ "\\,", + /* 88 */ null, + /* 89 */ "\u061F", + /* 90 */ "\u061B", // U+066A: "٪" ARABIC PERCENT SIGN - /* 93 */ "\u066A", - /* 94 */ "?", - /* 95 */ ";", + /* 91 */ "\u066A", + /* 92 */ null, + /* 93 */ "?", + /* 94 */ ";", // U+2030: "‰" PER MILLE SIGN - /* 96 */ "\\%,\u2030", + /* 95 */ "\\%,\u2030", // U+060C: "،" ARABIC COMMA // U+061B: "؛" ARABIC SEMICOLON // U+061F: "؟" ARABIC QUESTION MARK - /* 97 */ "\u060C", - /* 98 */ "!", - /* 99 */ "!,\\,", - /* 100 */ "\u061F", - /* 101 */ "\u061F,?", - /* 102~ */ - null, null, null, - /* ~104 */ - /* 105 */ "\u064B", - /* 106 */ "\u061F,\u061B,!,:,-,/,\',\"", - // U+0651: "ّ" ARABIC SHADDA - // U+0652: "ْ" ARABIC SUKUN - // U+064C: "ٌ" ARABIC DAMMATAN - // U+0653: "ٓ" ARABIC MADDAH ABOVE - // U+064F: "ُ" ARABIC DAMMA - // U+0650: "ِ" ARABIC KASRA - // U+064E: "َ" ARABIC FATHA - // U+064B: "ً" ARABIC FATHATAN - // U+0640: "ـ" ARABIC TATWEEL - // U+064D: "ٍ" ARABIC KASRATAN - // U+0670: "ٰ" ARABIC LETTER SUPERSCRIPT ALEF - // U+0656: "ٖ" ARABIC SUBSCRIPT ALEF - // U+0654: "ٔ" ARABIC HAMZA ABOVE - // U+0655: "ٕ" ARABIC HAMZA BELOW - // In order to make Tatweel easily distinguishable from other punctuations, we use consecutive Tatweels only for its displayed label. - /* 107 */ "\u0651,\u0652,\u064C,\u0653,\u064F,\u0650,\u064E,\u064B,\u0640\u0640\u0640|\u0640,\u064D,\u0654,\u0656,\u0655,_,\u0670", - // U+266A: "♪" EIGHTH NOTE - /* 108 */ "\u266A", + /* 96 */ "\u060C", + /* 97 */ "!", + /* 98 */ "!,\\,", + /* 99 */ "\u061F", + /* 100 */ "\u061F,?", + /* 101 */ null, + /* 102 */ null, + /* 103 */ "\u061F,\u061B,!,:,-,/,\',\"", }; /* Language fi: Finnish */ @@ -1238,38 +1204,38 @@ public final class KeyboardTextsSet { null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, null, - null, null, null, null, null, null, null, null, null, null, null, null, null, null, - /* ~58 */ + null, null, null, null, null, null, null, null, null, null, null, + /* ~55 */ // U+0967: "१" DEVANAGARI DIGIT ONE - /* 59 */ "\u0967", + /* 56 */ "\u0967", // U+0968: "२" DEVANAGARI DIGIT TWO - /* 60 */ "\u0968", + /* 57 */ "\u0968", // U+0969: "३" DEVANAGARI DIGIT THREE - /* 61 */ "\u0969", + /* 58 */ "\u0969", // U+096A: "४" DEVANAGARI DIGIT FOUR - /* 62 */ "\u096A", + /* 59 */ "\u096A", // U+096B: "५" DEVANAGARI DIGIT FIVE - /* 63 */ "\u096B", + /* 60 */ "\u096B", // U+096C: "६" DEVANAGARI DIGIT SIX - /* 64 */ "\u096C", + /* 61 */ "\u096C", // U+096D: "७" DEVANAGARI DIGIT SEVEN - /* 65 */ "\u096D", + /* 62 */ "\u096D", // U+096E: "८" DEVANAGARI DIGIT EIGHT - /* 66 */ "\u096E", + /* 63 */ "\u096E", // U+096F: "९" DEVANAGARI DIGIT NINE - /* 67 */ "\u096F", + /* 64 */ "\u096F", // U+0966: "०" DEVANAGARI DIGIT ZERO - /* 68 */ "\u0966", - /* 69 */ "1", - /* 70 */ "2", - /* 71 */ "3", - /* 72 */ "4", - /* 73 */ "5", - /* 74 */ "6", - /* 75 */ "7", - /* 76 */ "8", - /* 77 */ "9", - /* 78 */ "0", + /* 65 */ "\u0966", + /* 66 */ "1", + /* 67 */ "2", + /* 68 */ "3", + /* 69 */ "4", + /* 70 */ "5", + /* 71 */ "6", + /* 72 */ "7", + /* 73 */ "8", + /* 74 */ "9", + /* 75 */ "0", }; /* Language hr: Croatian */ @@ -1466,17 +1432,18 @@ public final class KeyboardTextsSet { // <string name="more_keys_for_tablet_double_quote">!fixedColumnOrder!6,“,”,„,‟,«|»,»|«;,‘,’,‚,‛</string> /* 43 */ "!fixedColumnOrder!4,\u201C,\u201D,\u00AB|\u00BB,\u00BB|\u00AB,\u2018,\u2019,\u201A,\u201B", /* 44~ */ - null, null, null, null, null, null, null, - /* ~50 */ + null, null, null, null, null, + /* ~48 */ // U+2605: "★" BLACK STAR - /* 51 */ "\u2605", + /* 49 */ "\u2605", + /* 50 */ null, // U+00B1: "±" PLUS-MINUS SIGN // U+FB29: "﬩" HEBREW LETTER ALTERNATIVE PLUS SIGN - /* 52 */ "\u00B1,\uFB29", + /* 51 */ "\u00B1,\uFB29", // The all letters need to be mirrored are found at // http://www.unicode.org/Public/6.1.0/ucd/BidiMirroring.txt - /* 53 */ "!fixedColumnOrder!3,<|>,{|},[|]", - /* 54 */ "!fixedColumnOrder!3,>|<,}|{,]|[", + /* 52 */ "!fixedColumnOrder!3,<|>,{|},[|]", + /* 53 */ "!fixedColumnOrder!3,>|<,}|{,]|[", // U+2264: "≤" LESS-THAN OR EQUAL TO // U+2265: "≥" GREATER-THAN EQUAL TO // U+00AB: "«" LEFT-POINTING DOUBLE ANGLE QUOTATION MARK @@ -1492,8 +1459,8 @@ public final class KeyboardTextsSet { // U+201D: "”" RIGHT DOUBLE QUOTATION MARK // U+201E: "„" DOUBLE LOW-9 QUOTATION MARK // U+201F: "‟" DOUBLE HIGH-REVERSED-9 QUOTATION MARK - /* 55 */ "!fixedColumnOrder!3,\u2039|\u203A,\u2264|\u2265,\u00AB|\u00BB", - /* 56 */ "!fixedColumnOrder!3,\u203A|\u2039,\u2265|\u2264,\u00BB|\u00AB", + /* 54 */ "!fixedColumnOrder!3,\u2039|\u203A,\u2264|\u2265,\u00AB|\u00BB", + /* 55 */ "!fixedColumnOrder!3,\u203A|\u2039,\u2265|\u2264,\u00BB|\u00AB", }; /* Language ky: Kirghiz */ diff --git a/java/src/com/android/inputmethod/latin/LatinIME.java b/java/src/com/android/inputmethod/latin/LatinIME.java index 213c0ac82..011b512e8 100644 --- a/java/src/com/android/inputmethod/latin/LatinIME.java +++ b/java/src/com/android/inputmethod/latin/LatinIME.java @@ -635,6 +635,12 @@ public class LatinIME extends InputMethodService implements KeyboardActionListen Log.d(TAG, "onStartInputView: editorInfo:" + String.format("inputType=0x%08x imeOptions=0x%08x", editorInfo.inputType, editorInfo.imeOptions)); + Log.d(TAG, "All caps = " + + ((editorInfo.inputType & InputType.TYPE_TEXT_FLAG_CAP_CHARACTERS) != 0) + + ", sentence caps = " + + ((editorInfo.inputType & InputType.TYPE_TEXT_FLAG_CAP_SENTENCES) != 0) + + ", word caps = " + + ((editorInfo.inputType & InputType.TYPE_TEXT_FLAG_CAP_WORDS) != 0)); } if (ProductionFlag.IS_EXPERIMENTAL) { ResearchLogger.latinIME_onStartInputViewInternal(editorInfo, mPrefs); diff --git a/java/src/com/android/inputmethod/latin/makedict/BinaryDictInputOutput.java b/java/src/com/android/inputmethod/latin/makedict/BinaryDictInputOutput.java index d82d503c4..3c818cc56 100644 --- a/java/src/com/android/inputmethod/latin/makedict/BinaryDictInputOutput.java +++ b/java/src/com/android/inputmethod/latin/makedict/BinaryDictInputOutput.java @@ -174,6 +174,7 @@ public class BinaryDictInputOutput { private static final int MAX_CHARGROUPS_IN_A_NODE = 0x7FFF; // 32767 private static final int MAX_TERMINAL_FREQUENCY = 255; + private static final int MAX_BIGRAM_FREQUENCY = 15; // Arbitrary limit to how much passes we consider address size compression should // terminate in. At the time of this writing, our largest dictionary completes @@ -722,15 +723,17 @@ public class BinaryDictInputOutput { } /** - * Makes the flag value for an attribute. + * Makes the flag value for a bigram. * - * @param more whether there are more attributes after this one. - * @param offset the offset of the attribute. - * @param frequency the frequency of the attribute, 0..15 + * @param more whether there are more bigrams after this one. + * @param offset the offset of the bigram. + * @param bigramFrequency the frequency of the bigram, 0..255. + * @param unigramFrequency the unigram frequency of the same word, 0..255. + * @param word the second bigram, for debugging purposes * @return the flags */ - private static final int makeAttributeFlags(final boolean more, final int offset, - final int frequency) { + private static final int makeBigramFlags(final boolean more, final int offset, + int bigramFrequency, final int unigramFrequency, final String word) { int bigramFlags = (more ? FLAG_ATTRIBUTE_HAS_NEXT : 0) + (offset < 0 ? FLAG_ATTRIBUTE_OFFSET_NEGATIVE : 0); switch (getByteSize(offset)) { @@ -746,7 +749,21 @@ public class BinaryDictInputOutput { default: throw new RuntimeException("Strange offset size"); } - bigramFlags += frequency & FLAG_ATTRIBUTE_FREQUENCY; + if (unigramFrequency > bigramFrequency) { + MakedictLog.e("Unigram freq is superior to bigram freq for \"" + word + + "\". Bigram freq is " + bigramFrequency + ", unigram freq for " + + word + " is " + unigramFrequency); + bigramFrequency = unigramFrequency; + } + // We compute the difference between 255 (which means probability = 1) and the + // unigram score. We split this into discrete 16 steps, and this is the value + // we store into the 4 bits of the bigrams frequency. + final float bigramRatio = (float)(bigramFrequency - unigramFrequency) + / (MAX_TERMINAL_FREQUENCY - unigramFrequency); + // TODO: if the bigram freq is very close to the unigram frequency, we don't want + // to include the bigram in the binary dictionary at all. + final int discretizedFrequency = Math.round(bigramRatio * MAX_BIGRAM_FREQUENCY); + bigramFlags += discretizedFrequency & FLAG_ATTRIBUTE_FREQUENCY; return bigramFlags; } @@ -854,11 +871,14 @@ public class BinaryDictInputOutput { final Iterator bigramIterator = group.mBigrams.iterator(); while (bigramIterator.hasNext()) { final WeightedString bigram = (WeightedString)bigramIterator.next(); - final int addressOfBigram = findAddressOfWord(dict, bigram.mWord); + final CharGroup target = + FusionDictionary.findWordInTree(dict.mRoot, bigram.mWord); + final int addressOfBigram = target.mCachedAddress; + final int unigramFrequencyForThisWord = target.mFrequency; ++groupAddress; final int offset = addressOfBigram - groupAddress; - int bigramFlags = makeAttributeFlags(bigramIterator.hasNext(), offset, - bigram.mFrequency); + int bigramFlags = makeBigramFlags(bigramIterator.hasNext(), offset, + bigram.mFrequency, unigramFrequencyForThisWord, bigram.mWord); buffer[index++] = (byte)bigramFlags; final int bigramShift = writeVariableAddress(buffer, index, Math.abs(offset)); index += bigramShift; diff --git a/java/src/com/android/inputmethod/latin/spellcheck/AndroidSpellCheckerService.java b/java/src/com/android/inputmethod/latin/spellcheck/AndroidSpellCheckerService.java index f41645283..6f7f0c333 100644 --- a/java/src/com/android/inputmethod/latin/spellcheck/AndroidSpellCheckerService.java +++ b/java/src/com/android/inputmethod/latin/spellcheck/AndroidSpellCheckerService.java @@ -23,6 +23,7 @@ import android.service.textservice.SpellCheckerService; import android.text.TextUtils; import android.util.Log; import android.util.LruCache; +import android.view.textservice.SentenceSuggestionsInfo; import android.view.textservice.SuggestionsInfo; import android.view.textservice.TextInfo; @@ -392,7 +393,10 @@ public class AndroidSpellCheckerService extends SpellCheckerService public DictAndProximity createDictAndProximity(final Locale locale) { final int script = getScriptFromLocale(locale); final ProximityInfo proximityInfo = ProximityInfo.createSpellCheckerProximityInfo( - SpellCheckerProximityInfo.getProximityForScript(script)); + SpellCheckerProximityInfo.getProximityForScript(script), + SpellCheckerProximityInfo.ROW_SIZE, + SpellCheckerProximityInfo.PROXIMITY_GRID_WIDTH, + SpellCheckerProximityInfo.PROXIMITY_GRID_HEIGHT); final DictionaryCollection dictionaryCollection = DictionaryFactory.createDictionaryFromManager(this, locale, true /* useFullEditDistance */); @@ -484,6 +488,10 @@ public class AndroidSpellCheckerService extends SpellCheckerService } mUnigramSuggestionsInfoCache.put(query, new SuggestionsParams(suggestions, flags)); } + + public void remove(String key) { + mUnigramSuggestionsInfoCache.remove(key); + } } AndroidSpellCheckerSession(final AndroidSpellCheckerService service) { @@ -566,6 +574,96 @@ public class AndroidSpellCheckerService extends SpellCheckerService return (letterCount * 4 < length * 3); } + private SentenceSuggestionsInfo fixWronglyInvalidatedWordWithSingleQuote( + TextInfo ti, SentenceSuggestionsInfo ssi) { + final String typedText = ti.getText(); + if (!typedText.contains(SINGLE_QUOTE)) { + return null; + } + final int N = ssi.getSuggestionsCount(); + final ArrayList<Integer> additionalOffsets = new ArrayList<Integer>(); + final ArrayList<Integer> additionalLengths = new ArrayList<Integer>(); + final ArrayList<SuggestionsInfo> additionalSuggestionsInfos = + new ArrayList<SuggestionsInfo>(); + for (int i = 0; i < N; ++i) { + final SuggestionsInfo si = ssi.getSuggestionsInfoAt(i); + final int flags = si.getSuggestionsAttributes(); + if ((flags & SuggestionsInfo.RESULT_ATTR_IN_THE_DICTIONARY) == 0) { + continue; + } + final int offset = ssi.getOffsetAt(i); + final int length = ssi.getLengthAt(i); + final String subText = typedText.substring(offset, offset + length); + if (!subText.contains(SINGLE_QUOTE)) { + continue; + } + final String[] splitTexts = subText.split(SINGLE_QUOTE, -1); + if (splitTexts == null || splitTexts.length <= 1) { + continue; + } + final int splitNum = splitTexts.length; + for (int j = 0; j < splitNum; ++j) { + final String splitText = splitTexts[j]; + if (TextUtils.isEmpty(splitText)) { + continue; + } + if (mSuggestionsCache.getSuggestionsFromCache(splitText) == null) { + continue; + } + final int newLength = splitText.length(); + // Neither RESULT_ATTR_IN_THE_DICTIONARY nor RESULT_ATTR_LOOKS_LIKE_TYPO + final int newFlags = 0; + final SuggestionsInfo newSi = new SuggestionsInfo(newFlags, EMPTY_STRING_ARRAY); + newSi.setCookieAndSequence(si.getCookie(), si.getSequence()); + if (DBG) { + Log.d(TAG, "Override and remove old span over: " + + splitText + ", " + offset + "," + newLength); + } + additionalOffsets.add(offset); + additionalLengths.add(newLength); + additionalSuggestionsInfos.add(newSi); + } + } + final int additionalSize = additionalOffsets.size(); + if (additionalSize <= 0) { + return null; + } + final int suggestionsSize = N + additionalSize; + final int[] newOffsets = new int[suggestionsSize]; + final int[] newLengths = new int[suggestionsSize]; + final SuggestionsInfo[] newSuggestionsInfos = new SuggestionsInfo[suggestionsSize]; + int i; + for (i = 0; i < N; ++i) { + newOffsets[i] = ssi.getOffsetAt(i); + newLengths[i] = ssi.getLengthAt(i); + newSuggestionsInfos[i] = ssi.getSuggestionsInfoAt(i); + } + for (; i < suggestionsSize; ++i) { + newOffsets[i] = additionalOffsets.get(i - N); + newLengths[i] = additionalLengths.get(i - N); + newSuggestionsInfos[i] = additionalSuggestionsInfos.get(i - N); + } + return new SentenceSuggestionsInfo(newSuggestionsInfos, newOffsets, newLengths); + } + + @Override + public SentenceSuggestionsInfo[] onGetSentenceSuggestionsMultiple( + TextInfo[] textInfos, int suggestionsLimit) { + final SentenceSuggestionsInfo[] retval = super.onGetSentenceSuggestionsMultiple( + textInfos, suggestionsLimit); + if (retval == null || retval.length != textInfos.length) { + return retval; + } + for (int i = 0; i < retval.length; ++i) { + final SentenceSuggestionsInfo tempSsi = + fixWronglyInvalidatedWordWithSingleQuote(textInfos[i], retval[i]); + if (tempSsi != null) { + retval[i] = tempSsi; + } + } + return retval; + } + // Note : this must be reentrant /** * Gets a list of suggestions for a specific string. This returns a list of possible |