1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453
|
// HtmlAgilityPack V1.0 - Simon Mourier <simon underscore mourier at hotmail dot com>
using System;
using System.IO;
using System.Text;
namespace HtmlAgilityPack
{
/// <summary>
/// Represents a document with mixed code and text. ASP, ASPX, JSP, are good example of such documents.
/// </summary>
public class MixedCodeDocument
{
#region Fields
private int _c;
internal MixedCodeDocumentFragmentList _codefragments;
private MixedCodeDocumentFragment _currentfragment;
internal MixedCodeDocumentFragmentList _fragments;
private int _index;
private int _line;
private int _lineposition;
private ParseState _state;
private Encoding _streamencoding;
internal string _text;
internal MixedCodeDocumentFragmentList _textfragments;
/// <summary>
/// Gets or sets the token representing code end.
/// </summary>
public string TokenCodeEnd = "%>";
/// <summary>
/// Gets or sets the token representing code start.
/// </summary>
public string TokenCodeStart = "<%";
/// <summary>
/// Gets or sets the token representing code directive.
/// </summary>
public string TokenDirective = "@";
/// <summary>
/// Gets or sets the token representing response write directive.
/// </summary>
public string TokenResponseWrite = "Response.Write ";
private string TokenTextBlock = "TextBlock({0})";
#endregion
#region Constructors
/// <summary>
/// Creates a mixed code document instance.
/// </summary>
public MixedCodeDocument()
{
_codefragments = new MixedCodeDocumentFragmentList(this);
_textfragments = new MixedCodeDocumentFragmentList(this);
_fragments = new MixedCodeDocumentFragmentList(this);
}
#endregion
#region Properties
/// <summary>
/// Gets the code represented by the mixed code document seen as a template.
/// </summary>
public string Code
{
get
{
string s = "";
int i = 0;
foreach (MixedCodeDocumentFragment frag in _fragments)
{
switch (frag._type)
{
case MixedCodeDocumentFragmentType.Text:
s += TokenResponseWrite + string.Format(TokenTextBlock, i) + "\n";
i++;
break;
case MixedCodeDocumentFragmentType.Code:
s += ((MixedCodeDocumentCodeFragment) frag).Code + "\n";
break;
}
}
return s;
}
}
/// <summary>
/// Gets the list of code fragments in the document.
/// </summary>
public MixedCodeDocumentFragmentList CodeFragments
{
get { return _codefragments; }
}
/// <summary>
/// Gets the list of all fragments in the document.
/// </summary>
public MixedCodeDocumentFragmentList Fragments
{
get { return _fragments; }
}
/// <summary>
/// Gets the encoding of the stream used to read the document.
/// </summary>
public Encoding StreamEncoding
{
get { return _streamencoding; }
}
/// <summary>
/// Gets the list of text fragments in the document.
/// </summary>
public MixedCodeDocumentFragmentList TextFragments
{
get { return _textfragments; }
}
#endregion
#region Public Methods
/// <summary>
/// Create a code fragment instances.
/// </summary>
/// <returns>The newly created code fragment instance.</returns>
public MixedCodeDocumentCodeFragment CreateCodeFragment()
{
return (MixedCodeDocumentCodeFragment) CreateFragment(MixedCodeDocumentFragmentType.Code);
}
/// <summary>
/// Create a text fragment instances.
/// </summary>
/// <returns>The newly created text fragment instance.</returns>
public MixedCodeDocumentTextFragment CreateTextFragment()
{
return (MixedCodeDocumentTextFragment) CreateFragment(MixedCodeDocumentFragmentType.Text);
}
/// <summary>
/// Loads a mixed code document from a stream.
/// </summary>
/// <param name="stream">The input stream.</param>
public void Load(Stream stream)
{
Load(new StreamReader(stream));
}
/// <summary>
/// Loads a mixed code document from a stream.
/// </summary>
/// <param name="stream">The input stream.</param>
/// <param name="detectEncodingFromByteOrderMarks">Indicates whether to look for byte order marks at the beginning of the file.</param>
public void Load(Stream stream, bool detectEncodingFromByteOrderMarks)
{
Load(new StreamReader(stream, detectEncodingFromByteOrderMarks));
}
/// <summary>
/// Loads a mixed code document from a stream.
/// </summary>
/// <param name="stream">The input stream.</param>
/// <param name="encoding">The character encoding to use.</param>
public void Load(Stream stream, Encoding encoding)
{
Load(new StreamReader(stream, encoding));
}
/// <summary>
/// Loads a mixed code document from a stream.
/// </summary>
/// <param name="stream">The input stream.</param>
/// <param name="encoding">The character encoding to use.</param>
/// <param name="detectEncodingFromByteOrderMarks">Indicates whether to look for byte order marks at the beginning of the file.</param>
public void Load(Stream stream, Encoding encoding, bool detectEncodingFromByteOrderMarks)
{
Load(new StreamReader(stream, encoding, detectEncodingFromByteOrderMarks));
}
/// <summary>
/// Loads a mixed code document from a stream.
/// </summary>
/// <param name="stream">The input stream.</param>
/// <param name="encoding">The character encoding to use.</param>
/// <param name="detectEncodingFromByteOrderMarks">Indicates whether to look for byte order marks at the beginning of the file.</param>
/// <param name="buffersize">The minimum buffer size.</param>
public void Load(Stream stream, Encoding encoding, bool detectEncodingFromByteOrderMarks, int buffersize)
{
Load(new StreamReader(stream, encoding, detectEncodingFromByteOrderMarks, buffersize));
}
/// <summary>
/// Loads a mixed code document from a file.
/// </summary>
/// <param name="path">The complete file path to be read.</param>
public void Load(string path)
{
Load(new StreamReader(path));
}
/// <summary>
/// Loads a mixed code document from a file.
/// </summary>
/// <param name="path">The complete file path to be read.</param>
/// <param name="detectEncodingFromByteOrderMarks">Indicates whether to look for byte order marks at the beginning of the file.</param>
public void Load(string path, bool detectEncodingFromByteOrderMarks)
{
Load(new StreamReader(path, detectEncodingFromByteOrderMarks));
}
/// <summary>
/// Loads a mixed code document from a file.
/// </summary>
/// <param name="path">The complete file path to be read.</param>
/// <param name="encoding">The character encoding to use.</param>
public void Load(string path, Encoding encoding)
{
Load(new StreamReader(path, encoding));
}
/// <summary>
/// Loads a mixed code document from a file.
/// </summary>
/// <param name="path">The complete file path to be read.</param>
/// <param name="encoding">The character encoding to use.</param>
/// <param name="detectEncodingFromByteOrderMarks">Indicates whether to look for byte order marks at the beginning of the file.</param>
public void Load(string path, Encoding encoding, bool detectEncodingFromByteOrderMarks)
{
Load(new StreamReader(path, encoding, detectEncodingFromByteOrderMarks));
}
/// <summary>
/// Loads a mixed code document from a file.
/// </summary>
/// <param name="path">The complete file path to be read.</param>
/// <param name="encoding">The character encoding to use.</param>
/// <param name="detectEncodingFromByteOrderMarks">Indicates whether to look for byte order marks at the beginning of the file.</param>
/// <param name="buffersize">The minimum buffer size.</param>
public void Load(string path, Encoding encoding, bool detectEncodingFromByteOrderMarks, int buffersize)
{
Load(new StreamReader(path, encoding, detectEncodingFromByteOrderMarks, buffersize));
}
/// <summary>
/// Loads the mixed code document from the specified TextReader.
/// </summary>
/// <param name="reader">The TextReader used to feed the HTML data into the document.</param>
public void Load(TextReader reader)
{
_codefragments.Clear();
_textfragments.Clear();
// all pseudo constructors get down to this one
StreamReader sr = reader as StreamReader;
if (sr != null)
{
_streamencoding = sr.CurrentEncoding;
}
_text = reader.ReadToEnd();
reader.Close();
Parse();
}
/// <summary>
/// Loads a mixed document from a text
/// </summary>
/// <param name="html">The text to load.</param>
public void LoadHtml(string html)
{
Load(new StringReader(html));
}
/// <summary>
/// Saves the mixed document to the specified stream.
/// </summary>
/// <param name="outStream">The stream to which you want to save.</param>
public void Save(Stream outStream)
{
StreamWriter sw = new StreamWriter(outStream, GetOutEncoding());
Save(sw);
}
/// <summary>
/// Saves the mixed document to the specified stream.
/// </summary>
/// <param name="outStream">The stream to which you want to save.</param>
/// <param name="encoding">The character encoding to use.</param>
public void Save(Stream outStream, Encoding encoding)
{
StreamWriter sw = new StreamWriter(outStream, encoding);
Save(sw);
}
/// <summary>
/// Saves the mixed document to the specified file.
/// </summary>
/// <param name="filename">The location of the file where you want to save the document.</param>
public void Save(string filename)
{
StreamWriter sw = new StreamWriter(filename, false, GetOutEncoding());
Save(sw);
}
/// <summary>
/// Saves the mixed document to the specified file.
/// </summary>
/// <param name="filename">The location of the file where you want to save the document.</param>
/// <param name="encoding">The character encoding to use.</param>
public void Save(string filename, Encoding encoding)
{
StreamWriter sw = new StreamWriter(filename, false, encoding);
Save(sw);
}
/// <summary>
/// Saves the mixed document to the specified StreamWriter.
/// </summary>
/// <param name="writer">The StreamWriter to which you want to save.</param>
public void Save(StreamWriter writer)
{
Save((TextWriter) writer);
}
/// <summary>
/// Saves the mixed document to the specified TextWriter.
/// </summary>
/// <param name="writer">The TextWriter to which you want to save.</param>
public void Save(TextWriter writer)
{
writer.Flush();
}
#endregion
#region Internal Methods
internal MixedCodeDocumentFragment CreateFragment(MixedCodeDocumentFragmentType type)
{
switch (type)
{
case MixedCodeDocumentFragmentType.Text:
return new MixedCodeDocumentTextFragment(this);
case MixedCodeDocumentFragmentType.Code:
return new MixedCodeDocumentCodeFragment(this);
default:
throw new NotSupportedException();
}
}
internal Encoding GetOutEncoding()
{
if (_streamencoding != null)
return _streamencoding;
return Encoding.Default;
}
#endregion
#region Private Methods
private void IncrementPosition()
{
_index++;
if (_c == 10)
{
_lineposition = 1;
_line++;
}
else
_lineposition++;
}
private void Parse()
{
_state = ParseState.Text;
_index = 0;
_currentfragment = CreateFragment(MixedCodeDocumentFragmentType.Text);
while (_index < _text.Length)
{
_c = _text[_index];
IncrementPosition();
switch (_state)
{
case ParseState.Text:
if (_index + TokenCodeStart.Length < _text.Length)
{
if (_text.Substring(_index - 1, TokenCodeStart.Length) == TokenCodeStart)
{
_state = ParseState.Code;
_currentfragment.Length = _index - 1 - _currentfragment.Index;
_currentfragment = CreateFragment(MixedCodeDocumentFragmentType.Code);
SetPosition();
continue;
}
}
break;
case ParseState.Code:
if (_index + TokenCodeEnd.Length < _text.Length)
{
if (_text.Substring(_index - 1, TokenCodeEnd.Length) == TokenCodeEnd)
{
_state = ParseState.Text;
_currentfragment.Length = _index + TokenCodeEnd.Length - _currentfragment.Index;
_index += TokenCodeEnd.Length;
_lineposition += TokenCodeEnd.Length;
_currentfragment = CreateFragment(MixedCodeDocumentFragmentType.Text);
SetPosition();
continue;
}
}
break;
}
}
_currentfragment.Length = _index - _currentfragment.Index;
}
private void SetPosition()
{
_currentfragment.Line = _line;
_currentfragment._lineposition = _lineposition;
_currentfragment.Index = _index - 1;
_currentfragment.Length = 0;
}
#endregion
#region Nested type: ParseState
private enum ParseState
{
Text,
Code
}
#endregion
}
}
|