aboutsummaryrefslogtreecommitdiffstats
path: root/java
diff options
context:
space:
mode:
Diffstat (limited to 'java')
-rw-r--r--java/res/values/attrs.xml25
-rw-r--r--java/res/xml/keyboard_layout_set_bengali.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_hindi.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_hindi_compact.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_kannada.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_khmer.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_lao.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_malayalam.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_marathi.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_myanmar.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_nepali_romanized.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_nepali_traditional.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_sinhala.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_tamil.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_telugu.xml2
-rw-r--r--java/res/xml/keyboard_layout_set_thai.xml2
-rw-r--r--java/src/com/android/inputmethod/latin/utils/ScriptUtils.java123
17 files changed, 135 insertions, 43 deletions
diff --git a/java/res/values/attrs.xml b/java/res/values/attrs.xml
index 5434106c5..003b011f3 100644
--- a/java/res/values/attrs.xml
+++ b/java/res/values/attrs.xml
@@ -481,13 +481,24 @@
<declare-styleable name="KeyboardLayoutSet_Feature">
<!-- This should be aligned with ScriptUtils.SCRIPT_* -->
<attr name="supportedScript" format="enum">
- <enum name="latin" value="0" />
- <enum name="cyrillic" value="1" />
- <enum name="greek" value="2" />
- <enum name="arabic" value="3" />
- <enum name="hebrew" value="4" />
- <enum name="armenian" value="5" />
- <enum name="georgian" value="6" />
+ <enum name="arabic" value="0" />
+ <enum name="armenian" value="1" />
+ <enum name="bengali" value="2" />
+ <enum name="cyrillic" value="3" />
+ <enum name="devanagari" value="4" />
+ <enum name="georgian" value="5" />
+ <enum name="greek" value="6" />
+ <enum name="hebrew" value="7" />
+ <enum name="kannada" value="8" />
+ <enum name="khmer" value="9" />
+ <enum name="lao" value="10" />
+ <enum name="latin" value="11" />
+ <enum name="malayalam" value="12" />
+ <enum name="myanmar" value="13" />
+ <enum name="sinhala" value="14" />
+ <enum name="tamil" value="15" />
+ <enum name="telugu" value="16" />
+ <enum name="thai" value="17" />
</attr>
</declare-styleable>
diff --git a/java/res/xml/keyboard_layout_set_bengali.xml b/java/res/xml/keyboard_layout_set_bengali.xml
index 6e40e6de4..de48a0ceb 100644
--- a/java/res/xml/keyboard_layout_set_bengali.xml
+++ b/java/res/xml/keyboard_layout_set_bengali.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="bengali" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_bengali"
diff --git a/java/res/xml/keyboard_layout_set_hindi.xml b/java/res/xml/keyboard_layout_set_hindi.xml
index e850c7ebc..ee41b2ae7 100644
--- a/java/res/xml/keyboard_layout_set_hindi.xml
+++ b/java/res/xml/keyboard_layout_set_hindi.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="devanagari" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_hindi"
diff --git a/java/res/xml/keyboard_layout_set_hindi_compact.xml b/java/res/xml/keyboard_layout_set_hindi_compact.xml
index 77d02fbbc..147b2993f 100644
--- a/java/res/xml/keyboard_layout_set_hindi_compact.xml
+++ b/java/res/xml/keyboard_layout_set_hindi_compact.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="devanagari" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_hindi_compact"
diff --git a/java/res/xml/keyboard_layout_set_kannada.xml b/java/res/xml/keyboard_layout_set_kannada.xml
index 8dcf99657..14323e7ef 100644
--- a/java/res/xml/keyboard_layout_set_kannada.xml
+++ b/java/res/xml/keyboard_layout_set_kannada.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="kannada" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_kannada"
diff --git a/java/res/xml/keyboard_layout_set_khmer.xml b/java/res/xml/keyboard_layout_set_khmer.xml
index 181f98b3d..752c8520a 100644
--- a/java/res/xml/keyboard_layout_set_khmer.xml
+++ b/java/res/xml/keyboard_layout_set_khmer.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="khmer" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_khmer"
diff --git a/java/res/xml/keyboard_layout_set_lao.xml b/java/res/xml/keyboard_layout_set_lao.xml
index 2ffde45db..6285f87f9 100644
--- a/java/res/xml/keyboard_layout_set_lao.xml
+++ b/java/res/xml/keyboard_layout_set_lao.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="lao" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_lao"
diff --git a/java/res/xml/keyboard_layout_set_malayalam.xml b/java/res/xml/keyboard_layout_set_malayalam.xml
index 14c76baf0..f6086f6cb 100644
--- a/java/res/xml/keyboard_layout_set_malayalam.xml
+++ b/java/res/xml/keyboard_layout_set_malayalam.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="malayalam" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_malayalam"
diff --git a/java/res/xml/keyboard_layout_set_marathi.xml b/java/res/xml/keyboard_layout_set_marathi.xml
index e5c68e7ce..6aea17546 100644
--- a/java/res/xml/keyboard_layout_set_marathi.xml
+++ b/java/res/xml/keyboard_layout_set_marathi.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="devanagari" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_marathi"
diff --git a/java/res/xml/keyboard_layout_set_myanmar.xml b/java/res/xml/keyboard_layout_set_myanmar.xml
index 5c823b263..5af8c064e 100644
--- a/java/res/xml/keyboard_layout_set_myanmar.xml
+++ b/java/res/xml/keyboard_layout_set_myanmar.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="myanmar" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_myanmar"
diff --git a/java/res/xml/keyboard_layout_set_nepali_romanized.xml b/java/res/xml/keyboard_layout_set_nepali_romanized.xml
index fbbc6a5a0..5bad83537 100644
--- a/java/res/xml/keyboard_layout_set_nepali_romanized.xml
+++ b/java/res/xml/keyboard_layout_set_nepali_romanized.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="devanagari" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_nepali_romanized"
diff --git a/java/res/xml/keyboard_layout_set_nepali_traditional.xml b/java/res/xml/keyboard_layout_set_nepali_traditional.xml
index 4a3b60153..6f11dee58 100644
--- a/java/res/xml/keyboard_layout_set_nepali_traditional.xml
+++ b/java/res/xml/keyboard_layout_set_nepali_traditional.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="devanagari" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_nepali_traditional"
diff --git a/java/res/xml/keyboard_layout_set_sinhala.xml b/java/res/xml/keyboard_layout_set_sinhala.xml
index 8e6e619d2..1955d218f 100644
--- a/java/res/xml/keyboard_layout_set_sinhala.xml
+++ b/java/res/xml/keyboard_layout_set_sinhala.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="sinhala" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_sinhala"
diff --git a/java/res/xml/keyboard_layout_set_tamil.xml b/java/res/xml/keyboard_layout_set_tamil.xml
index 5c0491505..27f4a3266 100644
--- a/java/res/xml/keyboard_layout_set_tamil.xml
+++ b/java/res/xml/keyboard_layout_set_tamil.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="tamil" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_tamil"
diff --git a/java/res/xml/keyboard_layout_set_telugu.xml b/java/res/xml/keyboard_layout_set_telugu.xml
index aca47b9d9..2bf65bcbd 100644
--- a/java/res/xml/keyboard_layout_set_telugu.xml
+++ b/java/res/xml/keyboard_layout_set_telugu.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="telugu" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_telugu"
diff --git a/java/res/xml/keyboard_layout_set_thai.xml b/java/res/xml/keyboard_layout_set_thai.xml
index b8f99971b..f69dfa6bd 100644
--- a/java/res/xml/keyboard_layout_set_thai.xml
+++ b/java/res/xml/keyboard_layout_set_thai.xml
@@ -20,6 +20,8 @@
<KeyboardLayoutSet
xmlns:latin="http://schemas.android.com/apk/res/com.android.inputmethod.latin">
+ <Feature
+ latin:supportedScript="thai" />
<Element
latin:elementName="alphabet"
latin:elementKeyboard="@xml/kbd_thai"
diff --git a/java/src/com/android/inputmethod/latin/utils/ScriptUtils.java b/java/src/com/android/inputmethod/latin/utils/ScriptUtils.java
index a76a6dfd7..0e244666d 100644
--- a/java/src/com/android/inputmethod/latin/utils/ScriptUtils.java
+++ b/java/src/com/android/inputmethod/latin/utils/ScriptUtils.java
@@ -26,13 +26,24 @@ public class ScriptUtils {
// Used for hardware keyboards
public static final int SCRIPT_UNKNOWN = -1;
// TODO: should we use ISO 15924 identifiers instead?
- public static final int SCRIPT_LATIN = 0;
- public static final int SCRIPT_CYRILLIC = 1;
- public static final int SCRIPT_GREEK = 2;
- public static final int SCRIPT_ARABIC = 3;
- public static final int SCRIPT_HEBREW = 4;
- public static final int SCRIPT_ARMENIAN = 5;
- public static final int SCRIPT_GEORGIAN = 6;
+ public static final int SCRIPT_ARABIC = 0;
+ public static final int SCRIPT_ARMENIAN = 1;
+ public static final int SCRIPT_BENGALI = 2;
+ public static final int SCRIPT_CYRILLIC = 3;
+ public static final int SCRIPT_DEVANAGARI = 4;
+ public static final int SCRIPT_GEORGIAN = 5;
+ public static final int SCRIPT_GREEK = 6;
+ public static final int SCRIPT_HEBREW = 7;
+ public static final int SCRIPT_KANNADA = 8;
+ public static final int SCRIPT_KHMER = 9;
+ public static final int SCRIPT_LAO = 10;
+ public static final int SCRIPT_LATIN = 11;
+ public static final int SCRIPT_MALAYALAM = 12;
+ public static final int SCRIPT_MYANMAR = 13;
+ public static final int SCRIPT_SINHALA = 14;
+ public static final int SCRIPT_TAMIL = 15;
+ public static final int SCRIPT_TELUGU = 16;
+ public static final int SCRIPT_THAI = 17;
public static final TreeMap<String, Integer> mSpellCheckerLanguageToScript;
static {
// List of the supported languages and their associated script. We won't check
@@ -72,56 +83,96 @@ public class ScriptUtils {
*/
public static boolean isLetterPartOfScript(final int codePoint, final int scriptId) {
switch (scriptId) {
- case SCRIPT_LATIN:
- // Our supported latin script dictionaries (EFIGS) at the moment only include
- // characters in the C0, C1, Latin Extended A and B, IPA extensions unicode
- // blocks. As it happens, those are back-to-back in the code range 0x40 to 0x2AF,
- // so the below is a very efficient way to test for it. As for the 0-0x3F, it's
- // excluded from isLetter anyway.
- return codePoint <= 0x2AF && Character.isLetter(codePoint);
- case SCRIPT_CYRILLIC:
- // All Cyrillic characters are in the 400~52F block. There are some in the upper
- // Unicode range, but they are archaic characters that are not used in modern
- // Russian and are not used by our dictionary.
- return codePoint >= 0x400 && codePoint <= 0x52F && Character.isLetter(codePoint);
- case SCRIPT_GREEK:
- // Greek letters are either in the 370~3FF range (Greek & Coptic), or in the
- // 1F00~1FFF range (Greek extended). Our dictionary contains both sort of characters.
- // Our dictionary also contains a few words with 0xF2; it would be best to check
- // if that's correct, but a web search does return results for these words so
- // they are probably okay.
- return (codePoint >= 0x370 && codePoint <= 0x3FF)
- || (codePoint >= 0x1F00 && codePoint <= 0x1FFF)
- || codePoint == 0xF2;
case SCRIPT_ARABIC:
// Arabic letters can be in any of the following blocks:
// Arabic U+0600..U+06FF
- // Arabic Supplement U+0750..U+077F
+ // Arabic Supplement, Thaana U+0750..U+077F, U+0780..U+07BF
// Arabic Extended-A U+08A0..U+08FF
// Arabic Presentation Forms-A U+FB50..U+FDFF
// Arabic Presentation Forms-B U+FE70..U+FEFF
return (codePoint >= 0x600 && codePoint <= 0x6FF)
- || (codePoint >= 0x750 && codePoint <= 0x77F)
+ || (codePoint >= 0x750 && codePoint <= 0x7BF)
|| (codePoint >= 0x8A0 && codePoint <= 0x8FF)
|| (codePoint >= 0xFB50 && codePoint <= 0xFDFF)
|| (codePoint >= 0xFE70 && codePoint <= 0xFEFF);
- case SCRIPT_HEBREW:
- // Hebrew letters are in the Hebrew unicode block, which spans from U+0590 to U+05FF,
- // or in the Alphabetic Presentation Forms block, U+FB00..U+FB4F, but only in the
- // Hebrew part of that block, which is U+FB1D..U+FB4F.
- return (codePoint >= 0x590 && codePoint <= 0x5FF
- || codePoint >= 0xFB1D && codePoint <= 0xFB4F);
case SCRIPT_ARMENIAN:
// Armenian letters are in the Armenian unicode block, U+0530..U+058F and
// Alphabetic Presentation Forms block, U+FB00..U+FB4F, but only in the Armenian part
// of that block, which is U+FB13..U+FB17.
return (codePoint >= 0x530 && codePoint <= 0x58F
|| codePoint >= 0xFB13 && codePoint <= 0xFB17);
+ case SCRIPT_BENGALI:
+ // Bengali unicode block is U+0980..U+09FF
+ return (codePoint >= 0x980 && codePoint <= 0x9FF);
+ case SCRIPT_CYRILLIC:
+ // All Cyrillic characters are in the 400~52F block. There are some in the upper
+ // Unicode range, but they are archaic characters that are not used in modern
+ // Russian and are not used by our dictionary.
+ return codePoint >= 0x400 && codePoint <= 0x52F && Character.isLetter(codePoint);
+ case SCRIPT_DEVANAGARI:
+ // Devanagari unicode block is +0900..U+097F
+ return (codePoint >= 0x900 && codePoint <= 0x97F);
case SCRIPT_GEORGIAN:
// Georgian letters are in the Georgian unicode block, U+10A0..U+10FF,
// or Georgian supplement block, U+2D00..U+2D2F
return (codePoint >= 0x10A0 && codePoint <= 0x10FF
|| codePoint >= 0x2D00 && codePoint <= 0x2D2F);
+ case SCRIPT_GREEK:
+ // Greek letters are either in the 370~3FF range (Greek & Coptic), or in the
+ // 1F00~1FFF range (Greek extended). Our dictionary contains both sort of characters.
+ // Our dictionary also contains a few words with 0xF2; it would be best to check
+ // if that's correct, but a web search does return results for these words so
+ // they are probably okay.
+ return (codePoint >= 0x370 && codePoint <= 0x3FF)
+ || (codePoint >= 0x1F00 && codePoint <= 0x1FFF)
+ || codePoint == 0xF2;
+ case SCRIPT_HEBREW:
+ // Hebrew letters are in the Hebrew unicode block, which spans from U+0590 to U+05FF,
+ // or in the Alphabetic Presentation Forms block, U+FB00..U+FB4F, but only in the
+ // Hebrew part of that block, which is U+FB1D..U+FB4F.
+ return (codePoint >= 0x590 && codePoint <= 0x5FF
+ || codePoint >= 0xFB1D && codePoint <= 0xFB4F);
+ case SCRIPT_KANNADA:
+ // Kannada unicode block is U+0C80..U+0CFF
+ return (codePoint >= 0xC80 && codePoint <= 0xCFF);
+ case SCRIPT_KHMER:
+ // Khmer letters are in unicode block U+1780..U+17FF, and the Khmer symbols block
+ // is U+19E0..U+19FF
+ return (codePoint >= 0x1780 && codePoint <= 0x17FF
+ || codePoint >= 0x19E0 && codePoint <= 0x19FF);
+ case SCRIPT_LAO:
+ // The Lao block is U+0E80..U+0EFF
+ return (codePoint >= 0xE80 && codePoint <= 0xEFF);
+ case SCRIPT_LATIN:
+ // Our supported latin script dictionaries (EFIGS) at the moment only include
+ // characters in the C0, C1, Latin Extended A and B, IPA extensions unicode
+ // blocks. As it happens, those are back-to-back in the code range 0x40 to 0x2AF,
+ // so the below is a very efficient way to test for it. As for the 0-0x3F, it's
+ // excluded from isLetter anyway.
+ return codePoint <= 0x2AF && Character.isLetter(codePoint);
+ case SCRIPT_MALAYALAM:
+ // Malayalam unicode block is U+0D00..U+0D7F
+ return (codePoint >= 0xD00 && codePoint <= 0xD7F);
+ case SCRIPT_MYANMAR:
+ // Myanmar has three unicode blocks :
+ // Myanmar U+1000..U+109F
+ // Myanmar extended-A U+AA60..U+AA7F
+ // Myanmar extended-B U+A9E0..U+A9FF
+ return (codePoint >= 0x1000 && codePoint <= 0x109F
+ || codePoint >= 0xAA60 && codePoint <= 0xAA7F
+ || codePoint >= 0xA9E0 && codePoint <= 0xA9FF);
+ case SCRIPT_SINHALA:
+ // Sinhala unicode block is U+0D80..U+0DFF
+ return (codePoint >= 0xD80 && codePoint <= 0xDFF);
+ case SCRIPT_TAMIL:
+ // Tamil unicode block is U+0B80..U+0BFF
+ return (codePoint >= 0xB80 && codePoint <= 0xBFF);
+ case SCRIPT_TELUGU:
+ // Telugu unicode block is U+0C00..U+0C7F
+ return (codePoint >= 0xC00 && codePoint <= 0xC7F);
+ case SCRIPT_THAI:
+ // Thai unicode block is U+0E00..U+0E7F
+ return (codePoint >= 0xE00 && codePoint <= 0xE7F);
case SCRIPT_UNKNOWN:
return true;
default:
generated by cgit v1.2.3-83-g751a (git 2.47.1) at 2025-05-07 11:50:55 +0000