internal static UnicodeBlock Of(char c)
{
UnicodeBlock block = new UnicodeBlock();
if (c >= '\u4E00' && c <= '\u9FFF')
{
block._block = BlockType.CJKUnifiedIdeographs;
}
else if (c >= '\u3040' && c <= '\u309F')
{
block._block = BlockType.Hiragana;
}
else if (c >= '\u30A0' && c <= '\u30FF')
{
block._block = BlockType.Katakana;
}
else if (c >= '\uFF00' && c <= '\uFFEF')
{
block._block = BlockType.HalfKana;
}
else
{
block._block = BlockType.Unknown;
}
return(block);
}
public void TestUnicodeBlockForName()
{
String[] names = { "Latin-1 Supplement",
"Optical Character Recognition",
"CJK Unified Ideographs Extension A",
"Supplemental Arrows-B",
"Supplemental arrows b",
"supp-lement-al arrowsb",
"Supplementary Private Use Area-B",
"supplementary_Private_Use_Area-b",
"supplementary_PRIVATE_Use_Area_b" };
for (int i = 0; i < names.Length; ++i)
{
try
{
UnicodeBlock b = UnicodeBlock
.ForName(names[i]);
Logln("found: " + b + " for name: " + names[i]);
}
catch (Exception e)
{
Errln("could not find block for name: " + names[i]);
break;
}
}
}
public void TestForName()
{
Assert.AreEqual(UnicodeBlock.BASIC_LATIN, UnicodeBlock.ForName("Basic Latin"));
Assert.AreEqual(UnicodeBlock.HANGUL_SYLLABLES, UnicodeBlock.ForName("HANGUL_SYLLABLES"));
try
{
UnicodeBlock.ForName("Basic___ Latin");
Assert.Fail("exception should be thrown");
}
catch (ArgumentException e)
{
Assert.AreEqual("invalid block name", e.Message);
}
}
public void TestOfMethod()
{
Assert.AreEqual(UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS, UnicodeBlock.Of('中'));
Assert.AreEqual(UnicodeBlock.CJK_UNIFIED_IDEOGRAPHS, UnicodeBlock.Of('語'));
Assert.AreEqual(UnicodeBlock.HANGUL_SYLLABLES, UnicodeBlock.Of('한'));
Assert.AreEqual(UnicodeBlock.BASIC_LATIN, UnicodeBlock.Of('E'));
Assert.AreEqual(UnicodeBlock.BASIC_LATIN, UnicodeBlock.Of('a'));
Assert.AreEqual(UnicodeBlock.BASIC_LATIN, UnicodeBlock.Of('$'));
Assert.AreEqual(UnicodeBlock.BASIC_LATIN, UnicodeBlock.Of('-'));
Assert.AreEqual(UnicodeBlock.LATIN_1_SUPPLEMENT, UnicodeBlock.Of('ç'));
Assert.AreEqual(UnicodeBlock.LATIN_1_SUPPLEMENT, UnicodeBlock.Of('ñ'));
Assert.AreEqual(UnicodeBlock.GREEK, UnicodeBlock.Of('ω'));
Assert.AreEqual(UnicodeBlock.CYRILLIC, UnicodeBlock.Of('Ѧ'));
}
/// <summary>
/// 文を単語ごとに分割します。
/// </summary>
/// <param name="text"></param>
/// <returns></returns>
string[] Split(string text)
{
if (text.Length == 0)
{
return(new string[0]);
}
if (config.UseMecab)
{
return(_tagger.Parse(text).Replace("\r", "").Replace("\n", "").Split(' ').Where(s => !string.IsNullOrEmpty(s) && !string.IsNullOrWhiteSpace(s)).ToArray());
}
var list = new List <string>();
var buf = "";
for (var i = 0; i < text.Length; i++)
{
UnicodeBlock block = text[i].GetBlock();
if (Divider.Contains(text[i].ToString()) ||
char.IsSeparator(text[i]) ||
char.IsSymbol(text[i]))
{
if (!string.IsNullOrEmpty(buf) && !string.IsNullOrWhiteSpace(buf))
{
list.Add(buf);
}
list.Add(text[i].ToString());
buf = "";
continue;
}
if (block != prevBlock)
{
if (!string.IsNullOrEmpty(buf) && !string.IsNullOrWhiteSpace(buf))
{
list.Add(buf);
}
buf = "";
}
buf += text[i];
prevBlock = block;
}
if (!string.IsNullOrEmpty(buf))
{
list.Add(buf);
}
return(list.ToArray());
}
/// <summary>
/// Builds a NFA from a unicode block
/// </summary>
/// <param name="node">An AST node representing a NFA</param>
/// <returns>The equivalent NFA</returns>
private NFA BuildNFAFromUnicodeBlock(ASTNode node)
{
// extract the value
string value = node.Value.Substring(3, node.Value.Length - 4);
UnicodeBlock block = UnicodeBlocks.GetBlock(value);
if (block == null)
{
OnError(node.Position, "Unknown unicode block {0}", value);
return(BuildEpsilonNFA());
}
// build the result
NFA automata = NFA.NewMinimal();
AddUnicodeSpanToNFA(automata, block.Span);
return(automata);
}
private void blockSelection_SelectedIndexChanged(object sender, EventArgs e)
{
charView.Items.Clear();
UnicodeBlock newB = UnicodeInfo.GetBlocks()[blockSelection.SelectedIndex];
int i = newB.CodePointRange.FirstCodePoint;
int range_upper = newB.CodePointRange.LastCodePoint;
UnicodeCharInfo uc = new UnicodeCharInfo();
int itemind = 0;
string name = "RESERVED CODEPOINT";
while (i <= range_upper)
{
uc = UnicodeInfo.GetCharInfo(i);
charView.Items.Add(UnicodeInfo.GetDisplayText(uc));
if (uc.Name != null)
{
name = uc.Name;
}
charView.Items[itemind].ToolTipText = name + "\r\nCode point: U+" + BitConverter.ToString(BitConverter.GetBytes(uc.CodePoint).Reverse().ToArray()).Replace("-", "");
i++;
itemind++;
}
}
internal ScriptData(UnicodeBlock flag, int @base)
{
this.flag = flag;
this.@base = @base;
}
//public UnicodeInfo ToUnicodeData()
//{
// var finalUnicodeData = new UnicodeCharacterData[ucdEntryCount];
// for (int i = 0; i < finalUnicodeData.Length; ++i)
// finalUnicodeData[i] = ucdEntries[i].ToCharacterData();
// var finalUnihanData = new UnihanCharacterData[unihanEntryCount];
// for (int i = 0; i < finalUnihanData.Length; ++i)
// finalUnihanData[i] = unihanEntries[i].ToCharacterData();
// return new UnicodeInfo(unicodeVersion, finalUnicodeData, finalUnihanData, blockEntries.ToArray());
//}
private void WriteUnicodeBlockToFile(BinaryWriter writer, UnicodeBlock block)
{
writer.WriteCodePoint(block.CodePointRange.FirstCodePoint);
writer.WriteCodePoint(block.CodePointRange.LastCodePoint);
writer.Write(block.Name);
}
public void AddBlockEntry(UnicodeBlock block)
{
blockEntries.Add(block);
}
internal ScriptData(UnicodeBlock flag, int @base)
{
this.flag = flag;
this.@base = @base;
}
internal bool Equals(UnicodeBlock block)
{
return(_block == block._block);
}
