summaryrefslogtreecommitdiffstats
path: root/src/org/madore
diff options
context:
space:
mode:
Diffstat (limited to 'src/org/madore')
-rw-r--r--src/org/madore/android/unicodeMap/UnicodeCharacter.java40
-rw-r--r--src/org/madore/android/unicodeMap/UnicodeDatabase.java2
2 files changed, 34 insertions, 8 deletions
diff --git a/src/org/madore/android/unicodeMap/UnicodeCharacter.java b/src/org/madore/android/unicodeMap/UnicodeCharacter.java
index 0805e8c..6fa8496 100644
--- a/src/org/madore/android/unicodeMap/UnicodeCharacter.java
+++ b/src/org/madore/android/unicodeMap/UnicodeCharacter.java
@@ -14,11 +14,11 @@ import java.io.IOException;
public class UnicodeCharacter implements UnicodeDisplayable {
public static enum Range implements UnicodeDisplayable {
- BASIC_LATIN(0x0000, 0x0080, "Basic Latin"),
- LATIN_1_SUPPLEMENT(0x0080, 0x0100, "Latin-1 Supplement"),
- LATIN_EXTENDED_A(0x0100, 0x0180, "Latin Extended-A"),
- LATIN_EXTENDED_B(0x0180, 0x0250, "Latin Extended-B"),
- IPA_EXTENSIONS(0x0250, 0x02b0, "IPA Extensions"),
+ BASIC_LATIN(0x0000, 0x007F, "Basic Latin"),
+ LATIN_1_SUPPLEMENT(0x0080, 0x00FF, "Latin-1 Supplement"),
+ LATIN_EXTENDED_A(0x0100, 0x017F, "Latin Extended-A"),
+ LATIN_EXTENDED_B(0x0180, 0x024F, "Latin Extended-B"),
+ IPA_EXTENSIONS(0x0250, 0x02AF, "IPA Extensions"),
SPACING_MODIFIER_LETTERS(0x02B0, 0x02FF, "Spacing Modifier Letters"),
COMBINING_DIACRITICAL_MARKS(0x0300, 0x036F, "Combining Diacritical Marks"),
GREEK_AND_COPTIC(0x0370, 0x03FF, "Greek and Coptic"),
@@ -31,6 +31,7 @@ public class UnicodeCharacter implements UnicodeDisplayable {
ARABIC_SUPPLEMENT(0x0750, 0x077F, "Arabic Supplement"),
THAANA(0x0780, 0x07BF, "Thaana"),
NKO(0x07C0, 0x07FF, "NKo"),
+ SAMARITAN(0x0800, 0x083F, "Samaritan"),
DEVANAGARI(0x0900, 0x097F, "Devanagari"),
BENGALI(0x0980, 0x09FF, "Bengali"),
GURMUKHI(0x0A00, 0x0A7F, "Gurmukhi"),
@@ -59,15 +60,18 @@ public class UnicodeCharacter implements UnicodeDisplayable {
TAGBANWA(0x1760, 0x177F, "Tagbanwa"),
KHMER(0x1780, 0x17FF, "Khmer"),
MONGOLIAN(0x1800, 0x18AF, "Mongolian"),
+ UNIFIED_CANADIAN_ABORIGINAL_SYLLABICS_EXTENDED(0x18B0, 0x18FF, "Unified Canadian Aboriginal Syllabics Extended"),
LIMBU(0x1900, 0x194F, "Limbu"),
TAI_LE(0x1950, 0x197F, "Tai Le"),
NEW_TAI_LUE(0x1980, 0x19DF, "New Tai Lue"),
KHMER_SYMBOLS(0x19E0, 0x19FF, "Khmer Symbols"),
BUGINESE(0x1A00, 0x1A1F, "Buginese"),
+ TAI_THAM(0x1A20, 0x1AAF, "Tai Tham"),
BALINESE(0x1B00, 0x1B7F, "Balinese"),
SUNDANESE(0x1B80, 0x1BBF, "Sundanese"),
LEPCHA(0x1C00, 0x1C4F, "Lepcha"),
OL_CHIKI(0x1C50, 0x1C7F, "Ol Chiki"),
+ VEDIC_EXTENSIONS(0x1CD0, 0x1CFF, "Vedic Extensions"),
PHONETIC_EXTENSIONS(0x1D00, 0x1D7F, "Phonetic Extensions"),
PHONETIC_EXTENSIONS_SUPPLEMENT(0x1D80, 0x1DBF, "Phonetic Extensions Supplement"),
COMBINING_DIACRITICAL_MARKS_SUPPLEMENT(0x1DC0, 0x1DFF, "Combining Diacritical Marks Supplement"),
@@ -124,17 +128,27 @@ public class UnicodeCharacter implements UnicodeDisplayable {
CJK_UNIFIED_IDEOGRAPHS(0x4E00, 0x9FFF, "CJK Unified Ideographs"),
YI_SYLLABLES(0xA000, 0xA48F, "Yi Syllables"),
YI_RADICALS(0xA490, 0xA4CF, "Yi Radicals"),
+ LISU(0xA4D0, 0xA4FF, "Lisu"),
VAI(0xA500, 0xA63F, "Vai"),
CYRILLIC_EXTENDED_B(0xA640, 0xA69F, "Cyrillic Extended-B"),
+ BAMUM(0xA6A0, 0xA6FF, "Bamum"),
MODIFIER_TONE_LETTERS(0xA700, 0xA71F, "Modifier Tone Letters"),
LATIN_EXTENDED_D(0xA720, 0xA7FF, "Latin Extended-D"),
SYLOTI_NAGRI(0xA800, 0xA82F, "Syloti Nagri"),
+ COMMON_INDIC_NUMBER_FORMS(0xA830, 0xA83F, "Common Indic Number Forms"),
PHAGS_PA(0xA840, 0xA87F, "Phags-pa"),
SAURASHTRA(0xA880, 0xA8DF, "Saurashtra"),
+ DEVANAGARI_EXTENDED(0xA8E0, 0xA8FF, "Devanagari Extended"),
KAYAH_LI(0xA900, 0xA92F, "Kayah Li"),
REJANG(0xA930, 0xA95F, "Rejang"),
+ HANGUL_JAMO_EXTENDED_A(0xA960, 0xA97F, "Hangul Jamo Extended-A"),
+ JAVANESE(0xA980, 0xA9DF, "Javanese"),
CHAM(0xAA00, 0xAA5F, "Cham"),
+ MYANMAR_EXTENDED_A(0xAA60, 0xAA7F, "Myanmar Extended-A"),
+ TAI_VIET(0xAA80, 0xAADF, "Tai Viet"),
+ MEETEI_MAYEK(0xABC0, 0xABFF, "Meetei Mayek"),
HANGUL_SYLLABLES(0xAC00, 0xD7AF, "Hangul Syllables"),
+ HANGUL_JAMO_EXTENDED_B(0xD7B0, 0xD7FF, "Hangul Jamo Extended-B"),
HIGH_SURROGATES(0xD800, 0xDB7F, "High Surrogates"),
HIGH_PRIVATE_USE_SURROGATES(0xDB80, 0xDBFF, "High Private Use Surrogates"),
LOW_SURROGATES(0xDC00, 0xDFFF, "Low Surrogates"),
@@ -166,11 +180,20 @@ public class UnicodeCharacter implements UnicodeDisplayable {
SHAVIAN(0x10450, 0x1047F, "Shavian"),
OSMANYA(0x10480, 0x104AF, "Osmanya"),
CYPRIOT_SYLLABARY(0x10800, 0x1083F, "Cypriot Syllabary"),
+ IMPERIAL_ARAMAIC(0x10840, 0x1085F, "Imperial Aramaic"),
PHOENICIAN(0x10900, 0x1091F, "Phoenician"),
LYDIAN(0x10920, 0x1093F, "Lydian"),
KHAROSHTHI(0x10A00, 0x10A5F, "Kharoshthi"),
+ OLD_SOUTH_ARABIAN(0x10A60, 0x10A7F, "Old South Arabian"),
+ AVESTAN(0x10B00, 0x10B3F, "Avestan"),
+ INSCRIPTIONAL_PARTHIAN(0x10B40, 0x10B5F, "Inscriptional Parthian"),
+ INSCRIPTIONAL_PAHLAVI(0x10B60, 0x10B7F, "Inscriptional Pahlavi"),
+ OLD_TURKIC(0x10C00, 0x10C4F, "Old Turkic"),
+ RUMI_NUMERAL_SYMBOLS(0x10E60, 0x10E7F, "Rumi Numeral Symbols"),
+ KAITHI(0x11080, 0x110CF, "Kaithi"),
CUNEIFORM(0x12000, 0x123FF, "Cuneiform"),
CUNEIFORM_NUMBERS_AND_PUNCTUATION(0x12400, 0x1247F, "Cuneiform Numbers and Punctuation"),
+ EGYPTIAN_HIEROGLYPHS(0x13000, 0x1342F, "Egyptian Hieroglyphs"),
BYZANTINE_MUSICAL_SYMBOLS(0x1D000, 0x1D0FF, "Byzantine Musical Symbols"),
MUSICAL_SYMBOLS(0x1D100, 0x1D1FF, "Musical Symbols"),
ANCIENT_GREEK_MUSICAL_NOTATION(0x1D200, 0x1D24F, "Ancient Greek Musical Notation"),
@@ -179,7 +202,10 @@ public class UnicodeCharacter implements UnicodeDisplayable {
MATHEMATICAL_ALPHANUMERIC_SYMBOLS(0x1D400, 0x1D7FF, "Mathematical Alphanumeric Symbols"),
MAHJONG_TILES(0x1F000, 0x1F02F, "Mahjong Tiles"),
DOMINO_TILES(0x1F030, 0x1F09F, "Domino Tiles"),
+ ENCLOSED_ALPHANUMERIC_SUPPLEMENT(0x1F100, 0x1F1FF, "Enclosed Alphanumeric Supplement"),
+ ENCLOSED_IDEOGRAPHIC_SUPPLEMENT(0x1F200, 0x1F2FF, "Enclosed Ideographic Supplement"),
CJK_UNIFIED_IDEOGRAPHS_EXTENSION_B(0x20000, 0x2A6DF, "CJK Unified Ideographs Extension B"),
+ CJK_UNIFIED_IDEOGRAPHS_EXTENSION_C(0x2A700, 0x2B73F, "CJK Unified Ideographs Extension C"),
CJK_COMPATIBILITY_IDEOGRAPHS_SUPPLEMENT(0x2F800, 0x2FA1F, "CJK Compatibility Ideographs Supplement"),
TAGS(0xE0000, 0xE007F, "Tags"),
VARIATION_SELECTORS_SUPPLEMENT(0xE0100, 0xE01EF, "Variation Selectors Supplement"),
@@ -187,9 +213,9 @@ public class UnicodeCharacter implements UnicodeDisplayable {
SUPPLEMENTARY_PRIVATE_USE_AREA_B(0x100000, 0x10FFFF, "Supplementary Private Use Area-B");
protected final int from; protected final int to;
protected final String descr;
- Range(int from, int to, String descr) {
+ Range(int from, int last, String descr) {
this.from = from;
- this.to = to;
+ this.to = last+1;
this.descr = descr;
}
public int getFrom() { return this.from; }
diff --git a/src/org/madore/android/unicodeMap/UnicodeDatabase.java b/src/org/madore/android/unicodeMap/UnicodeDatabase.java
index 84efb63..4114e6e 100644
--- a/src/org/madore/android/unicodeMap/UnicodeDatabase.java
+++ b/src/org/madore/android/unicodeMap/UnicodeDatabase.java
@@ -103,7 +103,7 @@ public class UnicodeDatabase {
"UnicodeData-10.txt", "UnicodeData-11.txt",
"UnicodeData-12.txt", "UnicodeData-13.txt",
"UnicodeData-14.txt", "UnicodeData-15.txt",
- "UnicodeData-16.txt", "UnicodeData-17.txt",
+ "UnicodeData-16.txt", "UnicodeData-16b.txt", "UnicodeData-17.txt",
"UnicodeData-18.txt", "UnicodeData-19.txt"
};
try {