|
|
/*****************************************************************************\
> Copyright 2004 DOL for design studio.
>
> DOLS DHtmlTextEncoder Class
>
> E-mail�G nomad_libra.tw@yahoo.com.tw
> E-mail�G jameshrsp@ms2.url.com.tw
>
\*****************************************************************************/
// DHtmlTextEncoder.cs: implementation of the DHtmlTextEncoder class.
//
///////////////////////////////////////////////////////////////////////////////
using System;
using System.IO;
using System.Xml;
using System.Text;
using System.Collections.Generic;
namespace DOL.DHtml
{
/// <summary>
///
/// </summary>
public sealed class DHtmlTextEncoder
{
/////////////////////////////////////////////////////////////////////////////////
#region XHTML ���Ħr�����ާ@
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
/// �ˬd�r���O�_�� XHTML ���Ħr��
/// </summary>
/// <param name="unicode"></param>
/// <returns></returns>
public static bool IsValidXHtmlUnicode(char unicode)
{
bool result = false;
if(!(('\u0000' <= unicode && unicode <= '\u0008') ||
('\u000B' <= unicode && unicode <= '\u000C') ||
('\u000E' <= unicode && unicode <= '\u001F') ||
('\uD800' <= unicode && unicode <= '\uDFFF') ||
('\uFFFE' <= unicode && unicode <= '\uFFFF')))
result = true;
return result;
}
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
/// �ˬd�r��O�_�� XHTML ���Ħr��
/// </summary>
/// <param name="str"></param>
/// <returns></returns>
public static bool IsValidXHtmlString(string str)
{
System.Diagnostics.Debug.Assert(str != null);
bool result = true;
StringReader reader = new StringReader(str);
int read = reader.Read();
while(read != -1)
{
if(!IsValidXHtmlUnicode((char)read))
{
result = false;
break;
}
read = reader.Read();
}
return result;
}
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
/// �ഫ�r��� XHTML ���Ħr��, �L�Ħr���N�ഫ�� XHTML �Ѧ�
/// </summary>
/// <param name="str"></param>
/// <returns></returns>
public static string TransformValidXHtmlString(string str)
{
System.Diagnostics.Debug.Assert(str != null);
StringReader reader = new StringReader(str);
int read = reader.Read();
while(read != -1)
{
if(IsValidXHtmlUnicode((char)read))
m_builder.Append((char)read); // �r��
else m_builder.Append("&#" + ((int)read).ToString() + ";"); // �Ѧ�
read = reader.Read();
}
string result = m_builder.ToString();
if(m_builder.Length > 0) m_builder.Length = 0;
return result;
}
#endregion
/////////////////////////////////////////////////////////////////////////////////
#region HTML �P�¤�r���ഫ
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
///
/// </summary>
/// <param name="str"></param>
/// <returns></returns>
public static string TranHtmlTextToStr(string str)
{
System.Diagnostics.Debug.Assert(str != null);
int length = str.Length;
int index = 0;
while(index < length)
{
int newIndex = str.IndexOf('&', index);
if(newIndex == -1)
{
m_builder.Append(str.Substring(index));
break;
}
else // �ѷ�: �ѷӪ��_�l��ɱ��� "&", �ѷӪ�������ɱ��� ";"
{
m_builder.Append(str.Substring(index, newIndex - index));
index = newIndex;
newIndex = str.IndexOf(';', index); // ��M�ѷӪ�������ɱ��� ";"
if(newIndex == -1) // �䤣�쵲����ɱ���h���������@���r
{
m_builder.Append(str.Substring(index));
break;
}
else
{
string token = str.Substring(index, newIndex - index + 1);
if(token[1] == '#') // �r���ѷ�
{
int intValue = int.Parse(token.Substring(2, token.Length - 3));
m_builder.Append((char)intValue);
}
else // ����ѷ�
{
char referenceValue = TranRefEntityToChar(token);
if(referenceValue != 0) m_builder.Append(referenceValue);
}
index = newIndex;
}
++index;
}
}
string result = m_builder.ToString();
if(m_builder.Length > 0) m_builder.Length = 0;
return result;
}
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
///
/// </summary>
/// <param name="str"></param>
/// <returns></returns>
public static string TranStrToHtmlText(string str)
{
System.Diagnostics.Debug.Assert(str != null);
bool spaceTransform = false;
for(int index = 0, count = str.Length; index < count; ++index)
{
char character = str[index];
if('\x0009' == character || '\x000A' == character || '\x000D' == character || '\x0020' == character)
{
if(spaceTransform == false)
{
spaceTransform = true;
m_builder.Append(' '); // �O�d�Ĥ@�Ӫť�, �åB�ഫ�� ASCII 32
}
else m_builder.Append(" "); // �ĤG�ӥH�᪺�ť��ഫ��
}
else
{
spaceTransform = false;
m_builder.Append(TranCharToRefEntity(character));
}
}
string result = m_builder.ToString();
if(m_builder.Length > 0) m_builder.Length = 0;
return result;
}
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
///
/// </summary>
/// <param name="buffer"></param>
/// <returns></returns>
public static char TranRefEntityToChar(string refEntity)
{
System.Diagnostics.Debug.Assert(refEntity != null);
char result = ((char)0);
switch(refEntity)
{
case "&":
result = ('&');
break;
case " ":
result = (' ');
break;
case "<":
result = ('<');
break;
case ">":
result = ('>');
break;
case """:
result = ('\"');
break;
case "Á":
result = ((char)193);
break;
case "á":
result = ((char)225);
break;
case "Â":
result = ((char)194);
break;
case "â":
result = ((char)226);
break;
case "´":
result = ((char)180);
break;
case "Æ":
result = ((char)198);
break;
case "æ":
result = ((char)230);
break;
case "À":
result = ((char)192);
break;
case "à":
result = ((char)224);
break;
case "ℵ":
result = ((char)8501);
break;
case "Α":
result = ((char)913);
break;
case "α":
result = ((char)945);
break;
case "∧":
result = ((char)8743);
break;
case "∠":
result = ((char)8736);
break;
case "Å":
result = ((char)197);
break;
case "å":
result = ((char)229);
break;
case "≈":
result = ((char)8776);
break;
case "Ã":
result = ((char)195);
break;
case "ã":
result = ((char)227);
break;
case "Ä":
result = ((char)196);
break;
case "ä":
result = ((char)228);
break;
case "„":
result = ((char)8222);
break;
case "Β":
result = ((char)914);
break;
case "β":
result = ((char)946);
break;
case "¦":
result = ((char)166);
break;
case "•":
result = ((char)8226);
break;
case "∩":
result = ((char)8745);
break;
case "Ç":
result = ((char)199);
break;
case "ç":
result = ((char)231);
break;
case "¸":
result = ((char)184);
break;
case "¢":
result = ((char)162);
break;
case "Χ":
result = ((char)935);
break;
case "χ":
result = ((char)967);
break;
case "ˆ":
result = ((char)710);
break;
case "♣":
result = ((char)9827);
break;
case "≅":
result = ((char)8773);
break;
case "©":
result = ((char)169);
break;
case "↵":
result = ((char)8629);
break;
case "∪":
result = ((char)8746);
break;
case "¤":
result = ((char)164);
break;
case "†":
result = ((char)8224);
break;
case "‡":
result = ((char)8225);
break;
case "↓":
result = ((char)8595);
break;
case "⇓":
result = ((char)8659);
break;
case "°":
result = ((char)176);
break;
case "Δ":
result = ((char)916);
break;
case "δ":
result = ((char)948);
break;
case "♦":
result = ((char)9830);
break;
case "÷":
result = ((char)247);
break;
case "É":
result = ((char)201);
break;
case "é":
result = ((char)233);
break;
case "Ê":
result = ((char)202);
break;
case "ê":
result = ((char)234);
break;
case "È":
result = ((char)200);
break;
case "è":
result = ((char)232);
break;
case "∅":
result = ((char)8709);
break;
case " ":
result = ((char)8195);
break;
case " ":
result = ((char)8194);
break;
case "Ε":
result = ((char)917);
break;
case "ε":
result = ((char)949);
break;
case "≡":
result = ((char)8801);
break;
case "Η":
result = ((char)919);
break;
case "η":
result = ((char)951);
break;
case "Ð":
result = ((char)208);
break;
case "ð":
result = ((char)240);
break;
case "Ë":
result = ((char)203);
break;
case "ë":
result = ((char)235);
break;
case "€":
result = ((char)128);
break;
case "∃":
result = ((char)8707);
break;
case "ƒ":
result = ((char)402);
break;
case "∀":
result = ((char)8704);
break;
case "½":
result = ((char)189);
break;
case "¼":
result = ((char)188);
break;
case "¾":
result = ((char)190);
break;
case "&fras1;":
result = ((char)8260);
break;
case "Γ":
result = ((char)915);
break;
case "γ":
result = ((char)947);
break;
case "≥":
result = ((char)8805);
break;
case "↔":
result = ((char)8596);
break;
case "⇔":
result = ((char)8660);
break;
case "♥":
result = ((char)9829);
break;
case "…":
result = ((char)8230);
break;
case "Í":
result = ((char)205);
break;
case "í":
result = ((char)237);
break;
case "Î":
result = ((char)206);
break;
case "î":
result = ((char)238);
break;
case "¡":
result = ((char)161);
break;
case "Ì":
result = ((char)204);
break;
case "ì":
result = ((char)236);
break;
case "ℑ":
result = ((char)8465);
break;
case "∞":
result = ((char)8734);
break;
case "∫":
result = ((char)8747);
break;
case "Ι":
result = ((char)921);
break;
case "ι":
result = ((char)953);
break;
case "¿":
result = ((char)191);
break;
case "∈":
result = ((char)8712);
break;
case "Ï":
result = ((char)207);
break;
case "ï":
result = ((char)239);
break;
case "Κ":
result = ((char)922);
break;
case "κ":
result = ((char)954);
break;
case "Λ":
result = ((char)923);
break;
case "λ":
result = ((char)955);
break;
case "⟨":
result = ((char)9001);
break;
case "«":
result = ((char)171);
break;
case "←":
result = ((char)8592);
break;
case "⇐":
result = ((char)8656);
break;
case "⌈":
result = ((char)8968);
break;
case "“":
result = ((char)8220);
break;
case "≤":
result = ((char)8804);
break;
case "⌊":
result = ((char)8970);
break;
case "∗":
result = ((char)8727);
break;
case "◊":
result = ((char)9674);
break;
case "‎":
result = ((char)8206);
break;
case "‹":
result = ((char)8249);
break;
case "‘":
result = ((char)8216);
break;
case "¯":
result = ((char)175);
break;
case "—":
result = ((char)8212);
break;
case "µ":
result = ((char)181);
break;
case "·":
result = ((char)183);
break;
case "−":
result = ((char)8722);
break;
case "Μ":
result = ((char)924);
break;
case "μ":
result = ((char)956);
break;
case "∇":
result = ((char)8711);
break;
case "–":
result = ((char)8211);
break;
case "≠":
result = ((char)8800);
break;
case "∋":
result = ((char)8715);
break;
case "¬":
result = ((char)172);
break;
case "∉":
result = ((char)8713);
break;
case "⊄":
result = ((char)8836);
break;
case "Ñ":
result = ((char)209);
break;
case "ñ":
result = ((char)241);
break;
case "Ν":
result = ((char)925);
break;
case "ν":
result = ((char)957);
break;
case "Ó":
result = ((char)211);
break;
case "ó":
result = ((char)243);
break;
case "Ô":
result = ((char)212);
break;
case "ô":
result = ((char)244);
break;
case "Œ":
result = ((char)338);
break;
case "œ":
result = ((char)339);
break;
case "Ò":
result = ((char)210);
break;
case "ò":
result = ((char)242);
break;
case "‾":
result = ((char)8254);
break;
case "Ω":
result = ((char)937);
break;
case "ω":
result = ((char)969);
break;
case "Ο":
result = ((char)927);
break;
case "ο":
result = ((char)959);
break;
case "⊕":
result = ((char)8853);
break;
case "∨":
result = ((char)8744);
break;
case "ª":
result = ((char)170);
break;
case "º":
result = ((char)186);
break;
case "Ø":
result = ((char)216);
break;
case "ø":
result = ((char)248);
break;
case "Õ":
result = ((char)213);
break;
case "õ":
result = ((char)245);
break;
case "⊗":
result = ((char)8855);
break;
case "Ö":
result = ((char)214);
break;
case "ö":
result = ((char)246);
break;
case "¶":
result = ((char)182);
break;
case "∂":
result = ((char)8706);
break;
case "‰":
result = ((char)8240);
break;
case "⊥":
result = ((char)8869);
break;
case "Φ":
result = ((char)934);
break;
case "φ":
result = ((char)966);
break;
case "Π":
result = ((char)928);
break;
case "π":
result = ((char)960);
break;
case "ϖ":
result = ((char)982);
break;
case "±":
result = ((char)177);
break;
case "£":
result = ((char)163);
break;
case "′":
result = ((char)8242);
break;
case "″":
result = ((char)8243);
break;
case "∏":
result = ((char)8719);
break;
case "∝":
result = ((char)8733);
break;
case "Ψ":
result = ((char)936);
break;
case "ψ":
result = ((char)968);
break;
case "√":
result = ((char)8730);
break;
case "⟩":
result = ((char)9002);
break;
case "»":
result = ((char)187);
break;
case "→":
result = ((char)8594);
break;
case "⇒":
result = ((char)8658);
break;
case "⌉":
result = ((char)8969);
break;
case "”":
result = ((char)8221);
break;
case "ℜ":
result = ((char)8476);
break;
case "®":
result = ((char)174);
break;
case "⌋":
result = ((char)8971);
break;
case "Ρ":
result = ((char)929);
break;
case "ρ":
result = ((char)961);
break;
case "‏":
result = ((char)8207);
break;
case "›":
result = ((char)8250);
break;
case "’":
result = ((char)8217);
break;
case "‚":
result = ((char)8218);
break;
case "Š":
result = ((char)352);
break;
case "š":
result = ((char)353);
break;
case "⋅":
result = ((char)8901);
break;
case "§":
result = ((char)167);
break;
case "­":
result = ((char)173);
break;
case "Σ":
result = ((char)931);
break;
case "σ":
result = ((char)963);
break;
case "ς":
result = ((char)962);
break;
case "∼":
result = ((char)8764);
break;
case "♠":
result = ((char)9824);
break;
case "⊂":
result = ((char)8834);
break;
case "⊆":
result = ((char)8838);
break;
case "∑":
result = ((char)8721);
break;
case "⊃":
result = ((char)8835);
break;
case "¹":
result = ((char)185);
break;
case "²":
result = ((char)178);
break;
case "³":
result = ((char)179);
break;
case "⊇":
result = ((char)8839);
break;
case "ß":
result = ((char)223);
break;
case "Τ":
result = ((char)932);
break;
case "τ":
result = ((char)964);
break;
case "∴":
result = ((char)8756);
break;
case "Θ":
result = ((char)920);
break;
case "θ":
result = ((char)952);
break;
case "ϑ":
result = ((char)977);
break;
case " ":
result = ((char)8201);
break;
case "Þ":
result = ((char)222);
break;
case "þ":
result = ((char)254);
break;
case "˜":
result = ((char)732);
break;
case "×":
result = ((char)215);
break;
case "™":
result = ((char)8482);
break;
case "Ú":
result = ((char)218);
break;
case "ú":
result = ((char)250);
break;
case "↑":
result = ((char)8593);
break;
case "⇑":
result = ((char)8657);
break;
case "Û":
result = ((char)219);
break;
case "û":
result = ((char)251);
break;
case "Ù":
result = ((char)217);
break;
case "ù":
result = ((char)249);
break;
case "¨":
result = ((char)168);
break;
case "ϒ":
result = ((char)978);
break;
case "Υ":
result = ((char)933);
break;
case "υ":
result = ((char)965);
break;
case "Ü":
result = ((char)220);
break;
case "ü":
result = ((char)252);
break;
case "℘":
result = ((char)8472);
break;
case "Ξ":
result = ((char)926);
break;
case "ξ":
result = ((char)958);
break;
case "Ý":
result = ((char)221);
break;
case "ý":
result = ((char)253);
break;
case "¥":
result = ((char)165);
break;
case "Ÿ":
result = ((char)376);
break;
case "ÿ":
result = ((char)255);
break;
case "Ζ":
result = ((char)918);
break;
case "ζ":
result = ((char)950);
break;
case "‍":
result = ((char)8205);
break;
case "‌":
result = ((char)8204);
break;
default: break;
}
return result;
}
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
///
/// </summary>
/// <param name="buffer"></param>
/// <returns></returns>
public static string TranCharToRefEntity(char character)
{
string result = character.ToString();
switch((int)character)
{
case '<':
result = ("<");
break;
case '>':
result = (">");
break;
case '&':
result = ("&");
break;
case '\"':
result = (""");
break;
case 193:
result = ("Á");
break;
case 225:
result = ("á");
break;
case 194:
result = ("Â");
break;
case 226:
result = ("â");
break;
case 180:
result = ("´");
break;
case 198:
result = ("Æ");
break;
case 230:
result = ("æ");
break;
case 192:
result = ("À");
break;
case 224:
result = ("à");
break;
case 8501:
result = ("ℵ");
break;
case 913:
result = ("Α");
break;
case 945:
result = ("α");
break;
case 8743:
result = ("∧");
break;
case 8736:
result = ("∠");
break;
case 197:
result = ("Å");
break;
case 229:
result = ("å");
break;
case 8776:
result = ("≈");
break;
case 195:
result = ("Ã");
break;
case 227:
result = ("ã");
break;
case 196:
result = ("Ä");
break;
case 228:
result = ("ä");
break;
case 8222:
result = ("„");
break;
case 914:
result = ("Β");
break;
case 946:
result = ("β");
break;
case 166:
result = ("¦");
break;
case 8226:
result = ("•");
break;
case 8745:
result = ("∩");
break;
case 199:
result = ("Ç");
break;
case 231:
result = ("ç");
break;
case 184:
result = ("¸");
break;
case 162:
result = ("¢");
break;
case 935:
result = ("Χ");
break;
case 967:
result = ("χ");
break;
case 710:
result = ("ˆ");
break;
case 9827:
result = ("♣");
break;
case 8773:
result = ("≅");
break;
case 169:
result = ("©");
break;
case 8629:
result = ("↵");
break;
case 8746:
result = ("∪");
break;
case 164:
result = ("¤");
break;
case 8224:
result = ("†");
break;
case 8225:
result = ("‡");
break;
case 8595:
result = ("↓");
break;
case 8659:
result = ("⇓");
break;
case 176:
result = ("°");
break;
case 916:
result = ("Δ");
break;
case 948:
result = ("δ");
break;
case 9830:
result = ("♦");
break;
case 247:
result = ("÷");
break;
case 201:
result = ("É");
break;
case 233:
result = ("é");
break;
case 202:
result = ("Ê");
break;
case 234:
result = ("ê");
break;
case 200:
result = ("È");
break;
case 232:
result = ("è");
break;
case 8709:
result = ("∅");
break;
case 8195:
result = (" ");
break;
case 8194:
result = (" ");
break;
case 917:
result = ("Ε");
break;
case 949:
result = ("ε");
break;
case 8801:
result = ("≡");
break;
case 919:
result = ("Η");
break;
case 951:
result = ("η");
break;
case 208:
result = ("Ð");
break;
case 240:
result = ("ð");
break;
case 203:
result = ("Ë");
break;
case 235:
result = ("ë");
break;
case 128:
result = ("€");
break;
case 8707:
result = ("∃");
break;
case 402:
result = ("ƒ");
break;
case 8704:
result = ("∀");
break;
case 189:
result = ("½");
break;
case 188:
result = ("¼");
break;
case 190:
result = ("¾");
break;
case 8260:
result = ("&fras1;");
break;
case 915:
result = ("Γ");
break;
case 947:
result = ("γ");
break;
case 8805:
result = ("≥");
break;
case 8596:
result = ("↔");
break;
case 8660:
result = ("⇔");
break;
case 9829:
result = ("♥");
break;
case 8230:
result = ("…");
break;
case 205:
result = ("Í");
break;
case 237:
result = ("í");
break;
case 206:
result = ("Î");
break;
case 238:
result = ("î");
break;
case 161:
result = ("¡");
break;
case 204:
result = ("Ì");
break;
case 236:
result = ("ì");
break;
case 8465:
result = ("ℑ");
break;
case 8734:
result = ("∞");
break;
case 8747:
result = ("∫");
break;
case 921:
result = ("Ι");
break;
case 953:
result = ("ι");
break;
case 191:
result = ("¿");
break;
case 8712:
result = ("∈");
break;
case 207:
result = ("Ï");
break;
case 239:
result = ("ï");
break;
case 922:
result = ("Κ");
break;
case 954:
result = ("κ");
break;
case 923:
result = ("Λ");
break;
case 955:
result = ("λ");
break;
case 9001:
result = ("⟨");
break;
case 171:
result = ("«");
break;
case 8592:
result = ("←");
break;
case 8656:
result = ("⇐");
break;
case 8968:
result = ("⌈");
break;
case 8220:
result = ("“");
break;
case 8804:
result = ("≤");
break;
case 8970:
result = ("⌊");
break;
case 8727:
result = ("∗");
break;
case 9674:
result = ("◊");
break;
case 8206:
result = ("‎");
break;
case 8249:
result = ("‹");
break;
case 8216:
result = ("‘");
break;
case 175:
result = ("¯");
break;
case 8212:
result = ("—");
break;
case 181:
result = ("µ");
break;
case 183:
result = ("·");
break;
case 8722:
result = ("−");
break;
case 924:
result = ("Μ");
break;
case 956:
result = ("μ");
break;
case 8711:
result = ("∇");
break;
case 160:
result = (" ");
break;
case 8211:
result = ("–");
break;
case 8800:
result = ("≠");
break;
case 8715:
result = ("∋");
break;
case 172:
result = ("¬");
break;
case 8713:
result = ("∉");
break;
case 8836:
result = ("⊄");
break;
case 209:
result = ("Ñ");
break;
case 241:
result = ("ñ");
break;
case 925:
result = ("Ν");
break;
case 957:
result = ("ν");
break;
case 211:
result = ("Ó");
break;
case 243:
result = ("ó");
break;
case 212:
result = ("Ô");
break;
case 244:
result = ("ô");
break;
case 338:
result = ("Œ");
break;
case 339:
result = ("œ");
break;
case 210:
result = ("Ò");
break;
case 242:
result = ("ò");
break;
case 8254:
result = ("‾");
break;
case 937:
result = ("Ω");
break;
case 969:
result = ("ω");
break;
case 927:
result = ("Ο");
break;
case 959:
result = ("ο");
break;
case 8853:
result = ("⊕");
break;
case 8744:
result = ("∨");
break;
case 170:
result = ("ª");
break;
case 186:
result = ("º");
break;
case 216:
result = ("Ø");
break;
case 248:
result = ("ø");
break;
case 213:
result = ("Õ");
break;
case 245:
result = ("õ");
break;
case 8855:
result = ("⊗");
break;
case 214:
result = ("Ö");
break;
case 246:
result = ("ö");
break;
case 182:
result = ("¶");
break;
case 8706:
result = ("∂");
break;
case 8240:
result = ("‰");
break;
case 8869:
result = ("⊥");
break;
case 934:
result = ("Φ");
break;
case 966:
result = ("φ");
break;
case 928:
result = ("Π");
break;
case 960:
result = ("π");
break;
case 982:
result = ("ϖ");
break;
case 177:
result = ("±");
break;
case 163:
result = ("£");
break;
case 8242:
result = ("′");
break;
case 8243:
result = ("″");
break;
case 8719:
result = ("∏");
break;
case 8733:
result = ("∝");
break;
case 936:
result = ("Ψ");
break;
case 968:
result = ("ψ");
break;
case 8730:
result = ("√");
break;
case 9002:
result = ("⟩");
break;
case 187:
result = ("»");
break;
case 8594:
result = ("→");
break;
case 8658:
result = ("⇒");
break;
case 8969:
result = ("⌉");
break;
case 8221:
result = ("”");
break;
case 8476:
result = ("ℜ");
break;
case 174:
result = ("®");
break;
case 8971:
result = ("⌋");
break;
case 929:
result = ("Ρ");
break;
case 961:
result = ("ρ");
break;
case 8207:
result = ("‏");
break;
case 8250:
result = ("›");
break;
case 8217:
result = ("’");
break;
case 8218:
result = ("‚");
break;
case 352:
result = ("Š");
break;
case 353:
result = ("š");
break;
case 8901:
result = ("⋅");
break;
case 167:
result = ("§");
break;
case 173:
result = ("­");
break;
case 931:
result = ("Σ");
break;
case 963:
result = ("σ");
break;
case 962:
result = ("ς");
break;
case 8764:
result = ("∼");
break;
case 9824:
result = ("♠");
break;
case 8834:
result = ("⊂");
break;
case 8838:
result = ("⊆");
break;
case 8721:
result = ("∑");
break;
case 8835:
result = ("⊃");
break;
case 185:
result = ("¹");
break;
case 178:
result = ("²");
break;
case 179:
result = ("³");
break;
case 8839:
result = ("⊇");
break;
case 223:
result = ("ß");
break;
case 932:
result = ("Τ");
break;
case 964:
result = ("τ");
break;
case 8756:
result = ("∴");
break;
case 920:
result = ("Θ");
break;
case 952:
result = ("θ");
break;
case 977:
result = ("ϑ");
break;
case 8201:
result = (" ");
break;
case 222:
result = ("Þ");
break;
case 254:
result = ("þ");
break;
case 732:
result = ("˜");
break;
case 215:
result = ("×");
break;
case 8482:
result = ("™");
break;
case 218:
result = ("Ú");
break;
case 250:
result = ("ú");
break;
case 8593:
result = ("↑");
break;
case 8657:
result = ("⇑");
break;
case 219:
result = ("Û");
break;
case 251:
result = ("û");
break;
case 217:
result = ("Ù");
break;
case 249:
result = ("ù");
break;
case 168:
result = ("¨");
break;
case 978:
result = ("ϒ");
break;
case 933:
result = ("Υ");
break;
case 965:
result = ("υ");
break;
case 220:
result = ("Ü");
break;
case 252:
result = ("ü");
break;
case 8472:
result = ("℘");
break;
case 926:
result = ("Ξ");
break;
case 958:
result = ("ξ");
break;
case 221:
result = ("Ý");
break;
case 253:
result = ("ý");
break;
case 165:
result = ("¥");
break;
case 376:
result = ("Ÿ");
break;
case 255:
result = ("ÿ");
break;
case 918:
result = ("Ζ");
break;
case 950:
result = ("ζ");
break;
case 8205:
result = ("‍");
break;
case 8204:
result = ("‌");
break;
default: break;
}
return result;
}
#endregion
/////////////////////////////////////////////////////////////////////////////////
#region HTML �r�����B�z
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
///
/// </summary>
/// <param name="a"></param>
/// <param name="b"></param>
/// <returns></returns>
public static bool EqualesOfAnyChar(char a, string b)
{
System.Diagnostics.Debug.Assert(b != null);
return b.IndexOf(a) != -1;
}
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
/// Comapct WSC in input text
/// </summary>
/// <param name="temp"></param>
/// <returns></returns>
public static string ComapctWSCString(string str)
{
System.Diagnostics.Debug.Assert(str != null);
int index = 0;
int length = str.Length;
while(index < length)
{
int newIndex = str.IndexOfAny(WhiteSpaceCharsArray, index);
if(newIndex != -1)
{
m_builder.Append(str.Substring(index, newIndex - index));
m_builder.Append(' ');
index = newIndex + 1;
while(index < length)
{
char temp = str[index];
if('\x0009' == temp || '\x000A' == temp || '\x000D' == temp || '\x0020' == temp)
++index;
else break;
}
}
else
{
m_builder.Append(str.Substring(index));
break;
}
}
string result = m_builder.ToString();
if(m_builder.Length > 0) m_builder.Length = 0;
return result;
}
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
///
/// </summary>
/// <param name="temp"></param>
/// <returns></returns>
public static string RemoveWSCString(string str)
{
System.Diagnostics.Debug.Assert(str != null);
int index = 0;
int length = str.Length;
while(index < length)
{
int newIndex = str.IndexOfAny(WhiteSpaceCharsArray, index);
if(newIndex != -1)
{
m_builder.Append(str.Substring(index, newIndex - index));
index = newIndex + 1;
while(index < length)
{
char temp = str[index];
if('\x0009' == temp || '\x000A' == temp || '\x000D' == temp || '\x0020' == temp)
++index;
else break;
}
}
else
{
m_builder.Append(str.Substring(index));
break;
}
}
string result = m_builder.ToString();
if(m_builder.Length > 0) m_builder.Length = 0;
return result;
}
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
///
/// </summary>
/// <param name="str"></param>
/// <returns></returns>
public static bool ExistWhiteSpaceChar(string str)
{
System.Diagnostics.Debug.Assert(str != null);
return str.IndexOfAny(WhiteSpaceCharsArray) != -1;
}
/////////////////////////////////////////////////////////////////////////////////
/// <summary>
///
/// </summary>
/// <param name="temp"></param>
/// <returns></returns>
public static bool IsWhiteSpaceChar(char temp)
{
bool result = false;
if('\x0009' == temp || '\x000A' == temp || '\x000D' == temp || '\x0020' == temp)
result = true;
return result;
}
#endregion
/////////////////////////////////////////////////////////////////////////////////
#region �ܼ�
/// <summary>
/// HTML ���ťզr��
/// </summary>
public static readonly string WhiteSpaceChars = "\x0009\x000A\x000D\x0020"; // '\t', '\n', '\r', ' '
/// <summary>
/// HTML ���ťզr��
/// </summary>
public static readonly char[] WhiteSpaceCharsArray = { '\x0009', '\x000A', '\x000D', '\x0020' }; // '\t', '\n', '\r', ' '
/// <summary>
///
/// </summary>
private static StringBuilder m_builder = new StringBuilder(1024);
#endregion
}
}
|
By viewing downloads associated with this article you agree to the Terms of Service and the article's licence.
If a file you wish to view isn't highlighted, and is a text file (not binary), please
let us know and we'll add colourisation support for it.
James S.F. Hsieh(Nomad Libra) Working as engineer for "Corel Intervideo" company situated in Taiwan.
He received his master degree in Graduate Institute of Network Learning Technology, National Central University, Taiwan in 2006.
His research interests are semantic Web services, intelligent software agent, machine learning, algorithm, software
engineering and multimedia programming.
Submit an article or tip