Added functions that provide information for block and glyph coverage
CL @ http://codereview.appspot.com/6463047/
git-svn-id: http://sfntly.googlecode.com/svn/trunk@143 672e30a5-4c29-85ac-ac6d-611c735e0a51
diff --git a/java/src/com/google/typography/font/tools/fontinfo/FontInfo.java b/java/src/com/google/typography/font/tools/fontinfo/FontInfo.java
index ce4cece..8324f16 100644
--- a/java/src/com/google/typography/font/tools/fontinfo/FontInfo.java
+++ b/java/src/com/google/typography/font/tools/fontinfo/FontInfo.java
@@ -27,7 +27,10 @@
import com.google.typography.font.sfntly.table.truetype.LocaTable;
import com.google.typography.font.tools.fontinfo.DataDisplayTable.Align;
+import com.ibm.icu.impl.IllegalIcuArgumentException;
import com.ibm.icu.lang.UCharacter;
+import com.ibm.icu.lang.UScript;
+import com.ibm.icu.text.UnicodeSet;
import java.text.DecimalFormat;
import java.util.Arrays;
@@ -279,6 +282,165 @@
// TODO public static DataDisplayTable listChars(Font font, String charString)
/**
+ * Gets a list of Unicode blocks covered by the font and the amount each block
+ * is covered.
+ *
+ * @param font
+ * the source font
+ * @return a list of Unicode blocks covered by the font
+ */
+ // FIXME Find more elegant method of retrieving block data
+ public static DataDisplayTable listCharBlockCoverage(Font font) {
+ String[] header = { "Block", "Coverage" };
+ Align[] displayAlignment = { Align.Left, Align.Right };
+ DataDisplayTable table = new DataDisplayTable(Arrays.asList(header));
+ table.setAlignment(Arrays.asList(displayAlignment));
+
+ // Iterate through each block to check for coverage
+ CMap cmap = getUCSCMap(font);
+ int totalCount = 0;
+ for (int i = 0; i < UnicodeBlockData.numBlocks(); i++) {
+ String block = UnicodeBlockData.getBlockName(i);
+ UnicodeSet set = null;
+ try {
+ set = new UnicodeSet("[[:Block=" + block + ":]-[:gc=Unassigned:]-[:gc=Control:]]");
+ } catch (IllegalIcuArgumentException e) {
+ continue;
+ }
+ int count = 0;
+ for (String charStr : set) {
+ if (cmap.glyphId(UCharacter.codePointAt(charStr, 0)) > 0) {
+ count++;
+ }
+ }
+ if (count > 0) {
+ table.add(Arrays.asList(new String[] { String.format(
+ "%s [%s, %s]", block, UnicodeBlockData.getBlockStartCode(i),
+ UnicodeBlockData.getBlockEndCode(i)), String.format("%d / %d", count, set.size()) }));
+ }
+ totalCount += count;
+ }
+
+ // Add control code points with valid glyphs to find the total number of
+ // unicode characters with valid glyphs
+ UnicodeSet controlSet = new UnicodeSet("[[:gc=Control:]]");
+ for (String charStr : controlSet) {
+ if (cmap.glyphId(UCharacter.codePointAt(charStr, 0)) > 0) {
+ totalCount++;
+ }
+ }
+ int nonUnicodeCount = countChars(font) - totalCount;
+ if (nonUnicodeCount > 0) {
+ table.add(Arrays.asList(new String[] { "Unknown", String.format("%d", nonUnicodeCount) }));
+ }
+
+ return table;
+ }
+
+ /**
+ * Gets a list of scripts covered by the font and the amount each block is covered.
+ *
+ * @param font the source font
+ * @return a list of scripts covered by the font
+ */
+ public static DataDisplayTable listScriptCoverage(Font font) {
+ String[] header = {"Script", "Coverage"};
+ Align[] displayAlignment = {Align.Left, Align.Right};
+ DataDisplayTable table = new DataDisplayTable(Arrays.asList(header));
+ table.setAlignment(Arrays.asList(displayAlignment));
+ HashMap<Integer, Integer> coveredScripts = new HashMap<Integer, Integer>();
+
+ // Add to script count for the script each code point belongs to
+ CMap cmap = getUCSCMap(font);
+ for (int charId : cmap) {
+ if (cmap.glyphId(charId) != CMapTable.NOTDEF) {
+ int scriptCode = UScript.getScript(charId);
+ int scriptCount = 1;
+ if (coveredScripts.containsKey(scriptCode)) {
+ scriptCount += coveredScripts.get(scriptCode);
+ }
+ coveredScripts.put(scriptCode, scriptCount);
+ }
+ }
+
+ // For each covered script, find the total size of the script and add coverage to table
+ Set<Integer> sortedScripts = new TreeSet<Integer>(coveredScripts.keySet());
+ int unknown = 0;
+ for (Integer scriptCode : sortedScripts) {
+ UnicodeSet scriptSet = null;
+ String scriptName = UScript.getName(scriptCode);
+ try {
+ scriptSet = new UnicodeSet("[[:" + scriptName + ":]]");
+ } catch (IllegalIcuArgumentException e) {
+ unknown += coveredScripts.get(scriptCode);
+ continue;
+ }
+
+ table.add(Arrays.asList(new String[] {
+ scriptName, String.format("%d / %d", coveredScripts.get(scriptCode), scriptSet.size())}));
+ }
+ if (unknown > 0) {
+ table.add(Arrays.asList(new String[] {"Unsupported script", String.format("%d", unknown)}));
+ }
+
+ return table;
+ }
+
+ /**
+ * Gets a list of characters needed to fully cover scripts partially covered by the font
+ *
+ * @param font the source font
+ * @return a list of characters needed to fully cover partially-covered scripts
+ */
+ public static DataDisplayTable listCharsNeededToCoverScript(Font font) {
+ String[] header = {"Script", "Code Point", "Name"};
+ Align[] displayAlignment = {Align.Left, Align.Right, Align.Left};
+ DataDisplayTable table = new DataDisplayTable(Arrays.asList(header));
+ table.setAlignment(Arrays.asList(displayAlignment));
+ HashMap<Integer, UnicodeSet> coveredScripts = new HashMap<Integer, UnicodeSet>();
+
+ // Iterate through each set
+ CMap cmap = getUCSCMap(font);
+ for (int charId : cmap) {
+ if (cmap.glyphId(charId) != CMapTable.NOTDEF) {
+ int scriptCode = UScript.getScript(charId);
+ if (scriptCode == UScript.UNKNOWN) {
+ continue;
+ }
+
+ UnicodeSet scriptSet = null;
+ if (!coveredScripts.containsKey(scriptCode)) {
+ // New covered script found, create set
+ try {
+ scriptSet = new UnicodeSet(
+ "[[:" + UScript.getName(scriptCode) + ":]-[:gc=Unassigned:]-[:gc=Control:]]");
+ } catch (IllegalIcuArgumentException e) {
+ continue;
+ }
+ coveredScripts.put(scriptCode, scriptSet);
+ } else {
+ // Set for script already exists, retrieve for character removal
+ scriptSet = coveredScripts.get(scriptCode);
+ }
+ scriptSet.remove(UCharacter.toString(charId));
+ }
+ }
+
+ // Insert into table in order
+ Set<Integer> sortedScripts = new TreeSet<Integer>(coveredScripts.keySet());
+ for (Integer scriptCode : sortedScripts) {
+ UnicodeSet uSet = coveredScripts.get(scriptCode);
+ for (String charStr : uSet) {
+ int codePoint = UCharacter.codePointAt(charStr, 0);
+ table.add(Arrays.asList(new String[] {String.format("%s", UScript.getName(scriptCode)),
+ getFormattedCodePointString(codePoint), UCharacter.getExtendedName(codePoint)}));
+ }
+ }
+
+ return table;
+ }
+
+ /**
* Gets a list of minimum and maximum x and y dimensions for the glyphs in the
* font. This is based on the reported min and max values for each glyph and
* not on the actual outline sizes.
diff --git a/java/src/com/google/typography/font/tools/fontinfo/UnicodeBlockData.java b/java/src/com/google/typography/font/tools/fontinfo/UnicodeBlockData.java
new file mode 100644
index 0000000..614e99c
--- /dev/null
+++ b/java/src/com/google/typography/font/tools/fontinfo/UnicodeBlockData.java
@@ -0,0 +1,689 @@
+package com.google.typography.font.tools.fontinfo;
+
+/**
+ * Class containing functions that return information about Unicode blocks
+ *
+ * Unicode block information listed is for Unicode version 6.1.0 and is
+ * retrieved from ftp://ftp.unicode.org/Public/6.1.0/ucd/Blocks.txt
+ */
+// FIXME Find more elegant method of retrieving this data
+public class UnicodeBlockData {
+ private static String[] blockNames = { "Basic Latin",
+ "Latin-1 Supplement",
+ "Latin Extended-A",
+ "Latin Extended-B",
+ "IPA Extensions",
+ "Spacing Modifier Letters",
+ "Combining Diacritical Marks",
+ "Greek and Coptic",
+ "Cyrillic",
+ "Cyrillic Supplement",
+ "Armenian",
+ "Hebrew",
+ "Arabic",
+ "Syriac",
+ "Arabic Supplement",
+ "Thaana",
+ "NKo",
+ "Samaritan",
+ "Mandaic",
+ "Arabic Extended-A",
+ "Devanagari",
+ "Bengali",
+ "Gurmukhi",
+ "Gujarati",
+ "Oriya",
+ "Tamil",
+ "Telugu",
+ "Kannada",
+ "Malayalam",
+ "Sinhala",
+ "Thai",
+ "Lao",
+ "Tibetan",
+ "Myanmar",
+ "Georgian",
+ "Hangul Jamo",
+ "Ethiopic",
+ "Ethiopic Supplement",
+ "Cherokee",
+ "Unified Canadian Aboriginal Syllabics",
+ "Ogham",
+ "Runic",
+ "Tagalog",
+ "Hanunoo",
+ "Buhid",
+ "Tagbanwa",
+ "Khmer",
+ "Mongolian",
+ "Unified Canadian Aboriginal Syllabics Extended",
+ "Limbu",
+ "Tai Le",
+ "New Tai Lue",
+ "Khmer Symbols",
+ "Buginese",
+ "Tai Tham",
+ "Balinese",
+ "Sundanese",
+ "Batak",
+ "Lepcha",
+ "Ol Chiki",
+ "Sundanese Supplement",
+ "Vedic Extensions",
+ "Phonetic Extensions",
+ "Phonetic Extensions Supplement",
+ "Combining Diacritical Marks Supplement",
+ "Latin Extended Additional",
+ "Greek Extended",
+ "General Punctuation",
+ "Superscripts and Subscripts",
+ "Currency Symbols",
+ "Combining Diacritical Marks for Symbols",
+ "Letterlike Symbols",
+ "Number Forms",
+ "Arrows",
+ "Mathematical Operators",
+ "Miscellaneous Technical",
+ "Control Pictures",
+ "Optical Character Recognition",
+ "Enclosed Alphanumerics",
+ "Box Drawing",
+ "Block Elements",
+ "Geometric Shapes",
+ "Miscellaneous Symbols",
+ "Dingbats",
+ "Miscellaneous Mathematical Symbols-A",
+ "Supplemental Arrows-A",
+ "Braille Patterns",
+ "Supplemental Arrows-B",
+ "Miscellaneous Mathematical Symbols-B",
+ "Supplemental Mathematical Operators",
+ "Miscellaneous Symbols and Arrows",
+ "Glagolitic",
+ "Latin Extended-C",
+ "Coptic",
+ "Georgian Supplement",
+ "Tifinagh",
+ "Ethiopic Extended",
+ "Cyrillic Extended-A",
+ "Supplemental Punctuation",
+ "CJK Radicals Supplement",
+ "Kangxi Radicals",
+ "Ideographic Description Characters",
+ "CJK Symbols and Punctuation",
+ "Hiragana",
+ "Katakana",
+ "Bopomofo",
+ "Hangul Compatibility Jamo",
+ "Kanbun",
+ "Bopomofo Extended",
+ "CJK Strokes",
+ "Katakana Phonetic Extensions",
+ "Enclosed CJK Letters and Months",
+ "CJK Compatibility",
+ "CJK Unified Ideographs Extension A",
+ "Yijing Hexagram Symbols",
+ "CJK Unified Ideographs",
+ "Yi Syllables",
+ "Yi Radicals",
+ "Lisu",
+ "Vai",
+ "Cyrillic Extended-B",
+ "Bamum",
+ "Modifier Tone Letters",
+ "Latin Extended-D",
+ "Syloti Nagri",
+ "Common Indic Number Forms",
+ "Phags-pa",
+ "Saurashtra",
+ "Devanagari Extended",
+ "Kayah Li",
+ "Rejang",
+ "Hangul Jamo Extended-A",
+ "Javanese",
+ "Cham",
+ "Myanmar Extended-A",
+ "Tai Viet",
+ "Meetei Mayek Extensions",
+ "Ethiopic Extended-A",
+ "Meetei Mayek",
+ "Hangul Syllables",
+ "Hangul Jamo Extended-B",
+ "High Surrogates",
+ "High Private Use Surrogates",
+ "Low Surrogates",
+ "Private Use Area",
+ "CJK Compatibility Ideographs",
+ "Alphabetic Presentation Forms",
+ "Arabic Presentation Forms-A",
+ "Variation Selectors",
+ "Vertical Forms",
+ "Combining Half Marks",
+ "CJK Compatibility Forms",
+ "Small Form Variants",
+ "Arabic Presentation Forms-B",
+ "Halfwidth and Fullwidth Forms",
+ "Specials",
+ "Linear B Syllabary",
+ "Linear B Ideograms",
+ "Aegean Numbers",
+ "Ancient Greek Numbers",
+ "Ancient Symbols",
+ "Phaistos Disc",
+ "Lycian",
+ "Carian",
+ "Old Italic",
+ "Gothic",
+ "Ugaritic",
+ "Old Persian",
+ "Deseret",
+ "Shavian",
+ "Osmanya",
+ "Cypriot Syllabary",
+ "Imperial Aramaic",
+ "Phoenician",
+ "Lydian",
+ "Meroitic Hieroglyphs",
+ "Meroitic Cursive",
+ "Kharoshthi",
+ "Old South Arabian",
+ "Avestan",
+ "Inscriptional Parthian",
+ "Inscriptional Pahlavi",
+ "Old Turkic",
+ "Rumi Numeral Symbols",
+ "Brahmi",
+ "Kaithi",
+ "Sora Sompeng",
+ "Chakma",
+ "Sharada",
+ "Takri",
+ "Cuneiform",
+ "Cuneiform Numbers and Punctuation",
+ "Egyptian Hieroglyphs",
+ "Bamum Supplement",
+ "Miao",
+ "Kana Supplement",
+ "Byzantine Musical Symbols",
+ "Musical Symbols",
+ "Ancient Greek Musical Notation",
+ "Tai Xuan Jing Symbols",
+ "Counting Rod Numerals",
+ "Mathematical Alphanumeric Symbols",
+ "Arabic Mathematical Alphabetic Symbols",
+ "Mahjong Tiles",
+ "Domino Tiles",
+ "Playing Cards",
+ "Enclosed Alphanumeric Supplement",
+ "Enclosed Ideographic Supplement",
+ "Miscellaneous Symbols And Pictographs",
+ "Emoticons",
+ "Transport And Map Symbols",
+ "Alchemical Symbols",
+ "CJK Unified Ideographs Extension B",
+ "CJK Unified Ideographs Extension C",
+ "CJK Unified Ideographs Extension D",
+ "CJK Compatibility Ideographs Supplement",
+ "Tags",
+ "Variation Selectors Supplement",
+ "Supplementary Private Use Area-A",
+ "Supplementary Private Use Area-B" };
+
+ private static String[] blockStartCode = { "U+0000",
+ "U+0080",
+ "U+0100",
+ "U+0180",
+ "U+0250",
+ "U+02B0",
+ "U+0300",
+ "U+0370",
+ "U+0400",
+ "U+0500",
+ "U+0530",
+ "U+0590",
+ "U+0600",
+ "U+0700",
+ "U+0750",
+ "U+0780",
+ "U+07C0",
+ "U+0800",
+ "U+0840",
+ "U+08A0",
+ "U+0900",
+ "U+0980",
+ "U+0A00",
+ "U+0A80",
+ "U+0B00",
+ "U+0B80",
+ "U+0C00",
+ "U+0C80",
+ "U+0D00",
+ "U+0D80",
+ "U+0E00",
+ "U+0E80",
+ "U+0F00",
+ "U+1000",
+ "U+10A0",
+ "U+1100",
+ "U+1200",
+ "U+1380",
+ "U+13A0",
+ "U+1400",
+ "U+1680",
+ "U+16A0",
+ "U+1700",
+ "U+1720",
+ "U+1740",
+ "U+1760",
+ "U+1780",
+ "U+1800",
+ "U+18B0",
+ "U+1900",
+ "U+1950",
+ "U+1980",
+ "U+19E0",
+ "U+1A00",
+ "U+1A20",
+ "U+1B00",
+ "U+1B80",
+ "U+1BC0",
+ "U+1C00",
+ "U+1C50",
+ "U+1CC0",
+ "U+1CD0",
+ "U+1D00",
+ "U+1D80",
+ "U+1DC0",
+ "U+1E00",
+ "U+1F00",
+ "U+2000",
+ "U+2070",
+ "U+20A0",
+ "U+20D0",
+ "U+2100",
+ "U+2150",
+ "U+2190",
+ "U+2200",
+ "U+2300",
+ "U+2400",
+ "U+2440",
+ "U+2460",
+ "U+2500",
+ "U+2580",
+ "U+25A0",
+ "U+2600",
+ "U+2700",
+ "U+27C0",
+ "U+27F0",
+ "U+2800",
+ "U+2900",
+ "U+2980",
+ "U+2A00",
+ "U+2B00",
+ "U+2C00",
+ "U+2C60",
+ "U+2C80",
+ "U+2D00",
+ "U+2D30",
+ "U+2D80",
+ "U+2DE0",
+ "U+2E00",
+ "U+2E80",
+ "U+2F00",
+ "U+2FF0",
+ "U+3000",
+ "U+3040",
+ "U+30A0",
+ "U+3100",
+ "U+3130",
+ "U+3190",
+ "U+31A0",
+ "U+31C0",
+ "U+31F0",
+ "U+3200",
+ "U+3300",
+ "U+3400",
+ "U+4DC0",
+ "U+4E00",
+ "U+A000",
+ "U+A490",
+ "U+A4D0",
+ "U+A500",
+ "U+A640",
+ "U+A6A0",
+ "U+A700",
+ "U+A720",
+ "U+A800",
+ "U+A830",
+ "U+A840",
+ "U+A880",
+ "U+A8E0",
+ "U+A900",
+ "U+A930",
+ "U+A960",
+ "U+A980",
+ "U+AA00",
+ "U+AA60",
+ "U+AA80",
+ "U+AAE0",
+ "U+AB00",
+ "U+ABC0",
+ "U+AC00",
+ "U+D7B0",
+ "U+D800",
+ "U+DB80",
+ "U+DC00",
+ "U+E000",
+ "U+F900",
+ "U+FB00",
+ "U+FB50",
+ "U+FE00",
+ "U+FE10",
+ "U+FE20",
+ "U+FE30",
+ "U+FE50",
+ "U+FE70",
+ "U+FF00",
+ "U+FFF0",
+ "U+10000",
+ "U+10080",
+ "U+10100",
+ "U+10140",
+ "U+10190",
+ "U+101D0",
+ "U+10280",
+ "U+102A0",
+ "U+10300",
+ "U+10330",
+ "U+10380",
+ "U+103A0",
+ "U+10400",
+ "U+10450",
+ "U+10480",
+ "U+10800",
+ "U+10840",
+ "U+10900",
+ "U+10920",
+ "U+10980",
+ "U+109A0",
+ "U+10A00",
+ "U+10A60",
+ "U+10B00",
+ "U+10B40",
+ "U+10B60",
+ "U+10C00",
+ "U+10E60",
+ "U+11000",
+ "U+11080",
+ "U+110D0",
+ "U+11100",
+ "U+11180",
+ "U+11680",
+ "U+12000",
+ "U+12400",
+ "U+13000",
+ "U+16800",
+ "U+16F00",
+ "U+1B000",
+ "U+1D000",
+ "U+1D100",
+ "U+1D200",
+ "U+1D300",
+ "U+1D360",
+ "U+1D400",
+ "U+1EE00",
+ "U+1F000",
+ "U+1F030",
+ "U+1F0A0",
+ "U+1F100",
+ "U+1F200",
+ "U+1F300",
+ "U+1F600",
+ "U+1F680",
+ "U+1F700",
+ "U+20000",
+ "U+2A700",
+ "U+2B740",
+ "U+2F800",
+ "U+E0000",
+ "U+E0100",
+ "U+F0000",
+ "U+100000" };
+
+ private static String[] blockEndCode = { "U+007F",
+ "U+00FF",
+ "U+017F",
+ "U+024F",
+ "U+02AF",
+ "U+02FF",
+ "U+036F",
+ "U+03FF",
+ "U+04FF",
+ "U+052F",
+ "U+058F",
+ "U+05FF",
+ "U+06FF",
+ "U+074F",
+ "U+077F",
+ "U+07BF",
+ "U+07FF",
+ "U+083F",
+ "U+085F",
+ "U+08FF",
+ "U+097F",
+ "U+09FF",
+ "U+0A7F",
+ "U+0AFF",
+ "U+0B7F",
+ "U+0BFF",
+ "U+0C7F",
+ "U+0CFF",
+ "U+0D7F",
+ "U+0DFF",
+ "U+0E7F",
+ "U+0EFF",
+ "U+0FFF",
+ "U+109F",
+ "U+10FF",
+ "U+11FF",
+ "U+137F",
+ "U+139F",
+ "U+13FF",
+ "U+167F",
+ "U+169F",
+ "U+16FF",
+ "U+171F",
+ "U+173F",
+ "U+175F",
+ "U+177F",
+ "U+17FF",
+ "U+18AF",
+ "U+18FF",
+ "U+194F",
+ "U+197F",
+ "U+19DF",
+ "U+19FF",
+ "U+1A1F",
+ "U+1AAF",
+ "U+1B7F",
+ "U+1BBF",
+ "U+1BFF",
+ "U+1C4F",
+ "U+1C7F",
+ "U+1CCF",
+ "U+1CFF",
+ "U+1D7F",
+ "U+1DBF",
+ "U+1DFF",
+ "U+1EFF",
+ "U+1FFF",
+ "U+206F",
+ "U+209F",
+ "U+20CF",
+ "U+20FF",
+ "U+214F",
+ "U+218F",
+ "U+21FF",
+ "U+22FF",
+ "U+23FF",
+ "U+243F",
+ "U+245F",
+ "U+24FF",
+ "U+257F",
+ "U+259F",
+ "U+25FF",
+ "U+26FF",
+ "U+27BF",
+ "U+27EF",
+ "U+27FF",
+ "U+28FF",
+ "U+297F",
+ "U+29FF",
+ "U+2AFF",
+ "U+2BFF",
+ "U+2C5F",
+ "U+2C7F",
+ "U+2CFF",
+ "U+2D2F",
+ "U+2D7F",
+ "U+2DDF",
+ "U+2DFF",
+ "U+2E7F",
+ "U+2EFF",
+ "U+2FDF",
+ "U+2FFF",
+ "U+303F",
+ "U+309F",
+ "U+30FF",
+ "U+312F",
+ "U+318F",
+ "U+319F",
+ "U+31BF",
+ "U+31EF",
+ "U+31FF",
+ "U+32FF",
+ "U+33FF",
+ "U+4DBF",
+ "U+4DFF",
+ "U+9FFF",
+ "U+A48F",
+ "U+A4CF",
+ "U+A4FF",
+ "U+A63F",
+ "U+A69F",
+ "U+A6FF",
+ "U+A71F",
+ "U+A7FF",
+ "U+A82F",
+ "U+A83F",
+ "U+A87F",
+ "U+A8DF",
+ "U+A8FF",
+ "U+A92F",
+ "U+A95F",
+ "U+A97F",
+ "U+A9DF",
+ "U+AA5F",
+ "U+AA7F",
+ "U+AADF",
+ "U+AAFF",
+ "U+AB2F",
+ "U+ABFF",
+ "U+D7AF",
+ "U+D7FF",
+ "U+DB7F",
+ "U+DBFF",
+ "U+DFFF",
+ "U+F8FF",
+ "U+FAFF",
+ "U+FB4F",
+ "U+FDFF",
+ "U+FE0F",
+ "U+FE1F",
+ "U+FE2F",
+ "U+FE4F",
+ "U+FE6F",
+ "U+FEFF",
+ "U+FFEF",
+ "U+FFFF",
+ "U+1007F",
+ "U+100FF",
+ "U+1013F",
+ "U+1018F",
+ "U+101CF",
+ "U+101FF",
+ "U+1029F",
+ "U+102DF",
+ "U+1032F",
+ "U+1034F",
+ "U+1039F",
+ "U+103DF",
+ "U+1044F",
+ "U+1047F",
+ "U+104AF",
+ "U+1083F",
+ "U+1085F",
+ "U+1091F",
+ "U+1093F",
+ "U+1099F",
+ "U+109FF",
+ "U+10A5F",
+ "U+10A7F",
+ "U+10B3F",
+ "U+10B5F",
+ "U+10B7F",
+ "U+10C4F",
+ "U+10E7F",
+ "U+1107F",
+ "U+110CF",
+ "U+110FF",
+ "U+1114F",
+ "U+111DF",
+ "U+116CF",
+ "U+123FF",
+ "U+1247F",
+ "U+1342F",
+ "U+16A3F",
+ "U+16F9F",
+ "U+1B0FF",
+ "U+1D0FF",
+ "U+1D1FF",
+ "U+1D24F",
+ "U+1D35F",
+ "U+1D37F",
+ "U+1D7FF",
+ "U+1EEFF",
+ "U+1F02F",
+ "U+1F09F",
+ "U+1F0FF",
+ "U+1F1FF",
+ "U+1F2FF",
+ "U+1F5FF",
+ "U+1F64F",
+ "U+1F6FF",
+ "U+1F77F",
+ "U+2A6DF",
+ "U+2B73F",
+ "U+2B81F",
+ "U+2FA1F",
+ "U+E007F",
+ "U+E01EF",
+ "U+FFFFF",
+ "U+10FFFF", };
+
+ public static String getBlockName(int block) {
+ return blockNames[block];
+ }
+
+ public static String getBlockStartCode(int block) {
+ return blockStartCode[block];
+ }
+
+ public static String getBlockEndCode(int block) {
+ return blockEndCode[block];
+ }
+
+ public static int numBlocks() {
+ return blockNames.length;
+ }
+}
