When tokenizing in superpower, how to match a string only if it is the first thing in a line (note: this is a different question than this one) ?
For example, assume I have a language with only the following 4 characters (' ', ':', 'X', 'Y'), each of which is a token. There is also a 'Header' token to capture cases of the following regex pattern /^[XY]+:/ (any number of Xs and Ys followed by a colon, only if they start the line).
Here is a quick class for testing (the 4th test-case fails):
using System;
using Superpower;
using Superpower.Parsers;
using Superpower.Tokenizers;
public enum Tokens { Space, Colon, Header, X, Y }
public class XYTokenizer
{
static void Main(string[] args)
{
Test("X", Tokens.X);
Test("XY", Tokens.X, Tokens.Y);
Test("X Y:", Tokens.X, Tokens.Space, Tokens.Y, Tokens.Colon);
Test("X: X", Tokens.Header, Tokens.Space, Tokens.X);
}
public static readonly Tokenizer<Tokens> tokenizer = new TokenizerBuilder<Tokens>()
.Match(Character.EqualTo('X'), Tokens.X)
.Match(Character.EqualTo('Y'), Tokens.Y)
.Match(Character.EqualTo(':'), Tokens.Colon)
.Match(Character.EqualTo(' '), Tokens.Space)
.Build();
static void Test(string input, params Tokens[] expected)
{
var tokens = tokenizer.Tokenize(input);
var i = 0;
foreach (var t in tokens)
{
if (t.Kind != expected[i])
{
Console.WriteLine("tokens[" + i + "] was Tokens." + t.Kind
+ " not Tokens." + expected[i] + " for '" + input + "'");
return;
}
i++;
}
Console.WriteLine("OK");
}
}
I came up with a custom Tokenizer based on the example found here. I added comments throughout the code so you can follow what's happening.
public class MyTokenizer : Tokenizer<Tokens>
{
protected override IEnumerable<Result<Tokens>> Tokenize(TextSpan input)
{
Result<char> next = input.ConsumeChar();
bool checkForHeader = true;
while (next.HasValue)
{
// need to check for a header when starting a new line
if (checkForHeader)
{
var headerStartLocation = next.Location;
var tokenQueue = new List<Result<Tokens>>();
while (next.HasValue && (next.Value == 'X' || next.Value == 'Y'))
{
tokenQueue.Add(Result.Value(next.Value == 'X' ? Tokens.X : Tokens.Y, next.Location, next.Remainder));
next = next.Remainder.ConsumeChar();
}
// only if we had at least one X or one Y
if (tokenQueue.Any())
{
if (next.HasValue && next.Value == ':')
{
// this is a header token; we have to return a Result of the start location
// along with the remainder at this location
yield return Result.Value(Tokens.Header, headerStartLocation, next.Remainder);
next = next.Remainder.ConsumeChar();
}
else
{
// this isn't a header; we have to return all the tokens we parsed up to this point
foreach (Result<Tokens> tokenResult in tokenQueue)
{
yield return tokenResult;
}
}
}
if (!next.HasValue)
yield break;
}
checkForHeader = false;
if (next.Value == '\r')
{
// skip over the carriage return
next = next.Remainder.ConsumeChar();
continue;
}
if (next.Value == '\n')
{
// line break; check for a header token here
next = next.Remainder.ConsumeChar();
checkForHeader = true;
continue;
}
if (next.Value == 'A')
{
var abcStart = next.Location;
next = next.Remainder.ConsumeChar();
if (next.HasValue && next.Value == 'B')
{
next = next.Remainder.ConsumeChar();
if (next.HasValue && next.Value == 'C')
{
yield return Result.Value(Tokens.ABC, abcStart, next.Remainder);
next = next.Remainder.ConsumeChar();
}
else
{
yield return Result.Empty<Tokens>(next.Location, $"unrecognized `AB{next.Value}`");
}
}
else
{
yield return Result.Empty<Tokens>(next.Location, $"unrecognized `A{next.Value}`");
}
}
else if (next.Value == 'X')
{
yield return Result.Value(Tokens.X, next.Location, next.Remainder);
next = next.Remainder.ConsumeChar();
}
else if (next.Value == 'Y')
{
yield return Result.Value(Tokens.Y, next.Location, next.Remainder);
next = next.Remainder.ConsumeChar();
}
else if (next.Value == ':')
{
yield return Result.Value(Tokens.Colon, next.Location, next.Remainder);
next = next.Remainder.ConsumeChar();
}
else if (next.Value == ' ')
{
yield return Result.Value(Tokens.Space, next.Location, next.Remainder);
next = next.Remainder.ConsumeChar();
}
else
{
yield return Result.Empty<Tokens>(next.Location, $"unrecognized `{next.Value}`");
next = next.Remainder.ConsumeChar(); // Skip the character anyway
}
}
}
}
And you can call it like this:
var tokens = new MyTokenizer().Tokenize(input);
I get this error. Later I searched and found out the reason of illegal characters in my XML and its solution. But I don't have the access to edit any of these files. My job is to read and fetch the tag value, attribute value and similar stuff. SO I can't replace the binary characters with escapes like '\x01' with . Also I tried to include CheckCharacters =false in XMLreader settings. It doesn't take this. Still it is throwing the same error.
Is it not possible to fix in XMLreader? I read about XMLtextReader. It can skip the exception. But already I have coded for all my features using XMLreader. It would be good if I can find a solution for this. Otherwise I would have to change all my code.
My code:
private void button1_Click(object sender, EventArgs e)
{
int i = 0;
var filenames = System.IO.Directory
.EnumerateFiles(textBox1.Text, "*.xml", System.IO.SearchOption.AllDirectories)
.Select(System.IO.Path.GetFullPath);
foreach (var f in filenames)
{
var resolver = new XmlUrlOverrideResolver();
resolver.DtdFileMap[#"X1.DTD"] = #"\\location\X1.DTD";
resolver.DtdFileMap[#"R2.DTD"] = #"\\location\X2.DTD";
resolver.DtdFileMap[#"R5.DTD"] = #"\\location\R5.DTD";
XmlReaderSettings settings = new XmlReaderSettings();
settings.DtdProcessing = DtdProcessing.Parse;
settings.XmlResolver = resolver;
XmlReader doc = XmlReader.Create(f, settings);
while (doc.Read())
{
if ((doc.NodeType == XmlNodeType.Element) && (doc.Name == "ap"))
{
if (doc.HasAttributes)
{
String fin = doc.GetAttribute("ap");
if (fin == "no")
{
String[] array = new String[10000];
array[i] = (f);
File.AppendAllText(#"\\location\NAPP.txt", array[i] + Environment.NewLine);
i++;
}
else
{
String[] abs = new String[10000];
abs[i] = (f);
File.AppendAllText(#"\\location\APP.txt", abs[i] + Environment.NewLine);
i++;
}
}
}
}
}
MessageBox.Show("Done");
}
This is a very simple example of character "filter" that will replae the 0x06 character with a space:
public class MyStreamReader : StreamReader {
public MyStreamReader(string path)
: base(path) {
}
public override int Read(char[] buffer, int index, int count) {
int res = base.Read(buffer, index, count);
for (int i = 0; i < res; i++) {
if (buffer[i] == 0x06) {
buffer[i] = ' ';
}
}
return res;
}
}
You use it this way:
using (var sr = new MyStreamReader(f)) {
var doc = XmlReader.Create(sr, settings);
Note that it's very simple because it's replacing a character (the 0x06) with another character of the same "length" (the space). If you wanted to replace a character with a "sequence" of characters (to escape it), it would get more complex (not impossible, 30 minutes of work difficult)
(I have checked and it seems the XmlTextReader only uses that method and not the Read() method)
As always, when a programmer tells you 30 minutes, it means 0 minutes or 2 hours :-)
This is the "more complex" ReplacingStreamReader:
/// <summary>
/// Only the Read methods are supported!
/// </summary>
public class ReplacingStreamReader : StreamReader
{
public ReplacingStreamReader(string path)
: base(path)
{
}
public Func<char, string> ReplaceWith { get; set; }
protected char[] RemainingChars { get; set; }
protected int RemainingCharsIndex { get; set; }
public override int Read()
{
int ch;
if (RemainingChars != null)
{
ch = RemainingChars[RemainingCharsIndex];
RemainingCharsIndex++;
if (RemainingCharsIndex == RemainingChars.Length)
{
RemainingCharsIndex = 0;
RemainingChars = null;
}
}
else
{
ch = base.Read();
if (ch != -1)
{
string replace = ReplaceWith((char)ch);
if (replace == null)
{
// Do nothing
}
else if (replace.Length == 1)
{
ch = replace[0];
}
else
{
ch = replace[0];
RemainingChars = replace.ToCharArray(1, replace.Length - 1);
RemainingCharsIndex = 0;
}
}
}
return ch;
}
public override int Read(char[] buffer, int index, int count)
{
int res = 0;
// We leave error handling to the StreamReader :-)
// We handle only "working" parameters
if (RemainingChars != null && buffer != null && index >= 0 && count > 0 && index + count <= buffer.Length)
{
int remainingCharsCount = RemainingChars.Length - RemainingCharsIndex;
res = Math.Min(remainingCharsCount, count);
Array.Copy(RemainingChars, RemainingCharsIndex, buffer, index, res);
RemainingCharsIndex += res;
if (RemainingCharsIndex == RemainingChars.Length)
{
RemainingCharsIndex = 0;
RemainingChars = null;
}
if (res == count)
{
return res;
}
index += res;
count -= res;
}
while (true)
{
List<char> sb = null;
int res2 = base.Read(buffer, index, count);
if (res2 == 0 || ReplaceWith == null)
{
return res;
}
int j = 0;
for (int i = 0; i < res2; i++)
{
char ch = buffer[index + i];
string replace = ReplaceWith(ch);
if (sb != null)
{
if (replace == null)
{
sb.Add(ch);
}
else
{
sb.AddRange(replace);
}
}
else if (replace == null)
{
buffer[j] = ch;
j++;
}
else if (replace.Length == 1)
{
buffer[j] = replace[0];
j++;
}
else if (replace.Length == 0)
{
// We do not advance
}
else
{
sb = new List<char>();
sb.AddRange(replace);
}
}
res2 = j;
if (sb != null)
{
int res3 = Math.Min(sb.Count, count - res2);
sb.CopyTo(0, buffer, index + res2, res3);
if (res3 < sb.Count)
{
RemainingChars = new char[sb.Count - res3];
RemainingCharsIndex = 0;
sb.CopyTo(res3, RemainingChars, 0, RemainingChars.Length);
}
res += res3;
}
else
{
res2 = j;
// Can't happen if sb != null (at least a character must
// have been added)
if (res2 == 0)
{
continue;
}
}
res += res2;
return res;
}
}
}
Use it like:
using (var sr = new ReplacingStreamReader(f))
{
sr.ReplaceWith = x =>
{
return x == 0x6 ? " " : null;
// return x == '.' ? " " : null; // Replace all . with
};
var doc = XmlReader.Create(sr, settings);
Be aware that the ReplacingStreamReader doesn't "know" which part of the xml it is modifying, so rarely a "blind" replace is ok :-) Other than this limitation, you can replace any character with any string (null in the ReplaceWith means "keep the current character", equivalent to x.ToString() in the example given. Returning string.Empty is valid, means remove the current character).
The class is quite interesting: it keeps a char[] RemainingChars with the chars that have been read (and filtered by ReplaceWith) but that haven't been returned by a Read() method because the passed buffer was too much small (the ReplaceWith method could "enlarge" the read string, making it too much big for the buffer!). Note that sb is a List<char> instead of a StringBuilder. Probably using one or the other would be nearly equivalent, code-wise.
You could first read the content into a string replace (escape) the content, and then load it into a XmlReader:
foreach (var f in filenames) {
string text;
using (StreamReader s = new StreamReader(f,Encoding.UTF8)) {
text = s.ReadToEnd();
}
text = text.Replace("\x01",#""); //replace the content
//load some settings
var resolver = new XmlUrlOverrideResolver();
resolver.DtdFileMap[#"X1.DTD"] = #"\\location\X1.DTD";
resolver.DtdFileMap[#"R2.DTD"] = #"\\location\X2.DTD";
resolver.DtdFileMap[#"R5.DTD"] = #"\\location\R5.DTD";
XmlReaderSettings settings = new XmlReaderSettings();
settings.DtdProcessing = DtdProcessing.Parse;
settings.XmlResolver = resolver;
XmlReader doc = XmlReader.Create(text, settings);
//perform processing task
//...
}
It's fairly straight-forward to add a TextField using ABCPDF:
public FormField AddTextField(string inRect, string inName, string inText)
{
int fieldId = mDoc.AddObject("<</Type /Annot /Subtype /Widget /F 4 /FT /Tx /Ff 4096 /Q 1>>");
mDoc.SetInfo(fieldId, "/V:Text", inText);
RegisterField(fieldId, inName, inRect);
return new FormField(fieldId, mDoc);
}
With this as the implementation:
FormField text = AddTextField("40 530 300 580", "TextField1", "Hello World!");
text.DefaultAppearance = "/TimesRoman 36 Tf 0 0 1 rg";
text.BorderColor = "0 0 0";
text.FillColor = "220 220 220";
text.TextAlign = "Left";
If I need to add two fields that have the same name, it's a little more complex:
public int AddGroupField(FormField[] inKids, string inName, string inValue)
{
if (inKids.Length == 0)
throw new Exception("Cannot have a group field with no kids");
string ft = null, dv = null;
int fieldId = mDoc.AddObject("<< /Kids [] >>");
foreach (FormField kid in inKids)
{
mDoc.SetInfo(fieldId, "/Kids[]:Ref", kid.Id.ToString());
mDoc.SetInfo(kid.Id, "/Parent:Ref", fieldId);
if (ft == null)
ft = mDoc.GetInfo(kid.Id, "/FT");
if (dv == null)
dv = mDoc.GetInfo(kid.Id, "/DV");
mDoc.SetInfo(kid.Id, "/FT:Del", "");
mDoc.SetInfo(kid.Id, "/V:Del", "");
mDoc.SetInfo(kid.Id, "/DV:Del", "");
}
mDoc.SetInfo(fieldId, "/FT", ft);
mDoc.SetInfo(fieldId, "/T:Text", inName);
mDoc.SetInfo(fieldId, "/V:Text", inValue);
if (dv != null)
mDoc.SetInfo(fieldId, "/DV:Text", dv);
int eid = mDoc.GetInfoInt(mDoc.Root, "/AcroForm:Ref");
mDoc.SetInfo(eid, "/Fields*[]:Ref", fieldId);
return fieldId;
}
With this as the implementation:
FormField[] kids = new FormField[2];
kids[0] = AddTextField("40 230 300 280", null, null);
kids[1] = AddTextField("40 170 300 220", null, null);
int id = AddGroupField(kids, "TextField1", "Hello World!");
However, I'm having issues with adding a TextField to a PDF where a TextField already exists with that same name. So, for example, if my PDF already has a field named "TextField1" and then I want to add another field with that same name, none of the above implementations will work.
I was able to get the answer from ABCPDF support. And as you can see, it's not exactly a simple process. I'm not sure anyone could just figure this out on their own without spending months and months of research on the PDF spec and the ABCPDF product.
public FormField AddTextField(string inRect, string inName, string inText)
{
bool fieldAlreadyExists = mDoc.Form[inName] != null;
int fieldId = mDoc.AddObject("<</Type /Annot /Subtype /Widget /F 4 /FT /Tx /Ff 4096 /Q 1>>");
mDoc.SetInfo(fieldId, "/V:Text", inText);
RegisterField(fieldId, inName, inRect);
var field = new FormField(fieldId, mDoc);
if (fieldAlreadyExists)
{
InteractiveForm form = new InteractiveForm(mDoc);
form.AddFieldIntoExistingGroup(field, true);
}
return field;
}
private bool AddFieldIntoExistingGroup(FormField field, bool refreshForm)
{
bool duplicatesFound = false;
int acroFormID = mDoc.GetInfoInt(mDoc.Root, "/AcroForm:Ref");
int parentID = mDoc.GetInfoInt(field.Id, "/Parent:Ref");
ArrayAtom kids;
if (parentID > 0)
{
kids = mDoc.ObjectSoup.Catalog.Resolve(Atom.GetItem(mDoc.ObjectSoup[parentID].Atom, "Kids")) as ArrayAtom;
}
else
{
kids = mDoc.ObjectSoup.Catalog.Resolve(Atom.GetItem(mDoc.ObjectSoup[acroFormID].Atom, "Fields")) as ArrayAtom;
}
Dictionary<string, List<IndirectObject>> items = new Dictionary<string, List<IndirectObject>>();
for (int i = 0; i < kids.Count; i++)
{
IndirectObject io = mDoc.ObjectSoup.Catalog.ResolveObj(kids[i]);
if (io == null)
{
continue; // shouldn't really happen
}
string name = mDoc.GetInfo(io.ID, "/T:Text");
if (!items.ContainsKey(name))
{
items[name] = new List<IndirectObject>();
}
items[name].Add(io);
}
foreach (KeyValuePair<string, List<IndirectObject>> pair in items)
{
if (pair.Value.Count > 1)
{
duplicatesFound = true;
// shift field down to be a child of a new field node
int id = mDoc.AddObject("<< >>");
if (parentID > 0)
{
mDoc.SetInfo(parentID, "/Kids[]:Ref", id);
mDoc.SetInfo(id, "/Parent:Ref", parentID);
}
else
{
mDoc.SetInfo(acroFormID, "/Fields[]:Ref", id);
}
string[] dictEntries = new[] { "/FT", "/T", "/TU", "/Ff", "/V", "/DV" };
foreach (IndirectObject io in pair.Value)
{
foreach (string dictEntry in dictEntries)
{
string val = mDoc.GetInfo(io.ID, dictEntry);
if (!string.IsNullOrEmpty(val))
{
mDoc.SetInfo(id, dictEntry, val);
mDoc.SetInfo(io.ID, dictEntry + ":Del", "");
}
}
ArrayRemoveOneRefAtom(kids, io.ID);
mDoc.SetInfo(id, "/Kids[]:Ref", io.ID);
mDoc.SetInfo(io.ID, "/Parent:Ref", id);
}
}
}
if ((refreshForm) && (duplicatesFound))
{
mDoc.Form.Refresh();
}
return duplicatesFound;
}
private static bool ArrayRemoveOneRefAtom(ArrayAtom array, int id)
{
if (array != null)
{
for (int i = 0; i < array.Count; i++)
{
RefAtom refAtom = array[i] as RefAtom;
if ((refAtom != null) && (refAtom.ID == id))
{
ArrayRemoveAt(array, i);
return true;
}
}
}
return false;
}
private static void ArrayRemoveAt(ArrayAtom array, int index)
{
if (index == 0)
{ // Workaround for bug in some versions of ABCpdf
Atom[] copy = new Atom[array.Count];
array.CopyTo(copy, 0);
array.Clear();
for (int i = 1; i < copy.Length; i++)
array.Add(copy[i]);
}
else
{
array.RemoveAt(index);
}
}
A project using .NET Compact Framework does not allow use System.Web library.
How can I do to HTMLDecode a string using .NET Compact Framework?
I didn't found any class that do that.
If you decompile the .NET Framework source you can get the methods you need. I did it for you, so you can copy and paste the two classes below:
internal class HtmlEntities
{
// Fields
private static string[] _entitiesList = new string[] {
"\"-quot", "&-amp", "<-lt", ">-gt", "\x00a0-nbsp", "\x00a1-iexcl", "\x00a2-cent", "\x00a3-pound", "\x00a4-curren", "\x00a5-yen", "\x00a6-brvbar", "\x00a7-sect", "\x00a8-uml", "\x00a9-copy", "\x00aa-ordf", "\x00ab-laquo",
"\x00ac-not", "\x00ad-shy", "\x00ae-reg", "\x00af-macr", "\x00b0-deg", "\x00b1-plusmn", "\x00b2-sup2", "\x00b3-sup3", "\x00b4-acute", "\x00b5-micro", "\x00b6-para", "\x00b7-middot", "\x00b8-cedil", "\x00b9-sup1", "\x00ba-ordm", "\x00bb-raquo",
"\x00bc-frac14", "\x00bd-frac12", "\x00be-frac34", "\x00bf-iquest", "\x00c0-Agrave", "\x00c1-Aacute", "\x00c2-Acirc", "\x00c3-Atilde", "\x00c4-Auml", "\x00c5-Aring", "\x00c6-AElig", "\x00c7-Ccedil", "\x00c8-Egrave", "\x00c9-Eacute", "\x00ca-Ecirc", "\x00cb-Euml",
"\x00cc-Igrave", "\x00cd-Iacute", "\x00ce-Icirc", "\x00cf-Iuml", "\x00d0-ETH", "\x00d1-Ntilde", "\x00d2-Ograve", "\x00d3-Oacute", "\x00d4-Ocirc", "\x00d5-Otilde", "\x00d6-Ouml", "\x00d7-times", "\x00d8-Oslash", "\x00d9-Ugrave", "\x00da-Uacute", "\x00db-Ucirc",
"\x00dc-Uuml", "\x00dd-Yacute", "\x00de-THORN", "\x00df-szlig", "\x00e0-agrave", "\x00e1-aacute", "\x00e2-acirc", "\x00e3-atilde", "\x00e4-auml", "\x00e5-aring", "\x00e6-aelig", "\x00e7-ccedil", "\x00e8-egrave", "\x00e9-eacute", "\x00ea-ecirc", "\x00eb-euml",
"\x00ec-igrave", "\x00ed-iacute", "\x00ee-icirc", "\x00ef-iuml", "\x00f0-eth", "\x00f1-ntilde", "\x00f2-ograve", "\x00f3-oacute", "\x00f4-ocirc", "\x00f5-otilde", "\x00f6-ouml", "\x00f7-divide", "\x00f8-oslash", "\x00f9-ugrave", "\x00fa-uacute", "\x00fb-ucirc",
"\x00fc-uuml", "\x00fd-yacute", "\x00fe-thorn", "\x00ff-yuml", "Œ-OElig", "œ-oelig", "Š-Scaron", "š-scaron", "Ÿ-Yuml", "ƒ-fnof", "ˆ-circ", "˜-tilde", "Α-Alpha", "Β-Beta", "Γ-Gamma", "Δ-Delta",
"Ε-Epsilon", "Ζ-Zeta", "Η-Eta", "Θ-Theta", "Ι-Iota", "Κ-Kappa", "Λ-Lambda", "Μ-Mu", "Ν-Nu", "Ξ-Xi", "Ο-Omicron", "Π-Pi", "Ρ-Rho", "Σ-Sigma", "Τ-Tau", "Υ-Upsilon",
"Φ-Phi", "Χ-Chi", "Ψ-Psi", "Ω-Omega", "α-alpha", "β-beta", "γ-gamma", "δ-delta", "ε-epsilon", "ζ-zeta", "η-eta", "θ-theta", "ι-iota", "κ-kappa", "λ-lambda", "μ-mu",
"ν-nu", "ξ-xi", "ο-omicron", "π-pi", "ρ-rho", "ς-sigmaf", "σ-sigma", "τ-tau", "υ-upsilon", "φ-phi", "χ-chi", "ψ-psi", "ω-omega", "ϑ-thetasym", "ϒ-upsih", "ϖ-piv",
" -ensp", " -emsp", " -thinsp", "-zwnj", "-zwj", "-lrm", "-rlm", "–-ndash", "—-mdash", "‘-lsquo", "’-rsquo", "‚-sbquo", "“-ldquo", "”-rdquo", "„-bdquo", "†-dagger",
"‡-Dagger", "•-bull", "…-hellip", "‰-permil", "′-prime", "″-Prime", "‹-lsaquo", "›-rsaquo", "‾-oline", "⁄-frasl", "€-euro", "ℑ-image", "℘-weierp", "ℜ-real", "™-trade", "ℵ-alefsym",
"←-larr", "↑-uarr", "→-rarr", "↓-darr", "↔-harr", "↵-crarr", "⇐-lArr", "⇑-uArr", "⇒-rArr", "⇓-dArr", "⇔-hArr", "∀-forall", "∂-part", "∃-exist", "∅-empty", "∇-nabla",
"∈-isin", "∉-notin", "∋-ni", "∏-prod", "∑-sum", "−-minus", "∗-lowast", "√-radic", "∝-prop", "∞-infin", "∠-ang", "∧-and", "∨-or", "∩-cap", "∪-cup", "∫-int",
"∴-there4", "∼-sim", "≅-cong", "≈-asymp", "≠-ne", "≡-equiv", "≤-le", "≥-ge", "⊂-sub", "⊃-sup", "⊄-nsub", "⊆-sube", "⊇-supe", "⊕-oplus", "⊗-otimes", "⊥-perp",
};
private static Hashtable _entitiesLookupTable;
private static object _lookupLockObject = new object();
internal static char Lookup(string entity)
{
if (_entitiesLookupTable == null)
{
lock (_lookupLockObject)
{
if (_entitiesLookupTable == null)
{
Hashtable hashtable = new Hashtable();
foreach (string str in _entitiesList)
{
hashtable[str.Substring(2)] = str[0];
}
_entitiesLookupTable = hashtable;
}
}
}
object obj2 = _entitiesLookupTable[entity];
if (obj2 != null)
{
return (char)obj2;
}
return '\0';
}
}
public sealed class HttpUtility
{
private static char[] s_entityEndingChars = new char[] { ';', '&' };
public static string HtmlDecode(string s)
{
if (s == null)
{
return null;
}
if (s.IndexOf('&') < 0)
{
return s;
}
StringBuilder sb = new StringBuilder();
StringWriter output = new StringWriter(sb);
HtmlDecode(s, output);
return sb.ToString();
}
public static void HtmlDecode(string s, TextWriter output)
{
if (s != null)
{
if (s.IndexOf('&') < 0)
{
output.Write(s);
}
else
{
int length = s.Length;
for (int i = 0; i < length; i++)
{
char ch = s[i];
if (ch == '&')
{
int num3 = s.IndexOfAny(s_entityEndingChars, i + 1);
if ((num3 > 0) && (s[num3] == ';'))
{
string entity = s.Substring(i + 1, (num3 - i) - 1);
if ((entity.Length > 1) && (entity[0] == '#'))
{
try
{
if ((entity[1] == 'x') || (entity[1] == 'X'))
{
ch = (char)int.Parse(entity.Substring(2), NumberStyles.AllowHexSpecifier);
}
else
{
ch = (char)int.Parse(entity.Substring(1));
}
i = num3;
}
catch (FormatException)
{
i++;
}
catch (ArgumentException)
{
i++;
}
}
else
{
i = num3;
char ch2 = HtmlEntities.Lookup(entity);
if (ch2 != '\0')
{
ch = ch2;
}
else
{
output.Write('&');
output.Write(entity);
output.Write(';');
goto Label_0103;
}
}
}
}
output.Write(ch);
Label_0103: ;
}
}
}
}
}
You could always port the code from Mono, sample VB code or sample Java code found with a simple web search.
I've used reflector in the past to find just the methods I need from the framework that aren't included and compile them directly into my compact.net project.