File: LiteralTextParser.cs

package info (click to toggle)
mono 6.14.1%2Bds2-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 1,282,732 kB
  • sloc: cs: 11,182,461; xml: 2,850,281; ansic: 699,123; cpp: 122,919; perl: 58,604; javascript: 30,841; asm: 21,845; makefile: 19,602; sh: 10,973; python: 4,772; pascal: 925; sql: 859; sed: 16; php: 1
file content (735 lines) | stat: -rw-r--r-- 23,637 bytes parent folder | download | duplicates (7)
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
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
//------------------------------------------------------------------------------
// <copyright file="LiteralTextParser.cs" company="Microsoft">
//     Copyright (c) Microsoft Corporation.  All rights reserved.
// </copyright>                                                                
//------------------------------------------------------------------------------

using System;
using System.Collections;
using System.Collections.Specialized;
using System.Globalization;
using System.Text;
using System.Web;

namespace System.Web.UI.MobileControls
{
    /*
     * LiteralTextParser class.
     *
     * The LiteralTextParser class parses a string of literal text, 
     * containing certain recognizable tags, and creates a set of controls
     * from them. Any unrecognized tags are ignored.
     *
     * This is an abstract base class. RuntimeLiteralTextParser and 
     * CompileTimeLiteralTextParser inherit from this class.
     *
     * Copyright (c) 2000 Microsoft Corporation
     */

    [Obsolete("The System.Web.Mobile.dll assembly has been deprecated and should no longer be used. For information about how to develop ASP.NET mobile applications, see http://go.microsoft.com/fwlink/?LinkId=157231.")]
    internal abstract class LiteralTextParser
    {
        // The parsing methods (Parse, ParseTag, ParseTagAttributes, ParseText) 
        // build up LiteralElement objects, which can either be text or tags. 
        // ProcessElementInternal is then called. It combines some other data
        // and calls ProcessElement, a method which is overridable by inherited
        // classes.

        // Literal Element type - includes recognized tags.

        protected enum LiteralElementType
        {
            Unrecognized,
            Text,
            Bold,
            Italic,
            Break,
            Paragraph,
            Anchor,
        }

        // Available formatting options for literal elements. This enum can 
        // be combined with the | operator.

        protected enum LiteralFormat
        {
            None = 0,
            Bold = 1,
            Italic = 2,
        }

        // Literal Element.

        protected class LiteralElement
        {
            public LiteralElementType Type;
            public IDictionary Attributes;
            public String Text;
            public LiteralFormat Format = LiteralFormat.None;
            public bool BreakAfter = false;
            public bool ForceBreakTag = false;

            public LiteralElement(String text)
            {
                Type = LiteralElementType.Text;
                Attributes = null;
                Text = text;
            }

            public LiteralElement(LiteralElementType type, IDictionary attributes)
            {
                Type = type;
                Attributes = attributes;
                Text = String.Empty;
            }

            public bool IsText
            {
                get
                {
                    return Type == LiteralElementType.Text;
                }
            }

            public bool IsEmptyText
            {
                get
                {
                    return IsText && !LiteralTextParser.IsValidText(Text);
                }
            }

            public String GetAttribute(String attributeName)
            {
                Object o = (Attributes != null) ? Attributes[attributeName] : null;
                return (o != null) ? (String)o : String.Empty;
            }
        }

        // Methods overriden by inherited classes.

        protected abstract void ProcessElement(LiteralElement element);
        protected abstract void ProcessTagInnerText(String text);

        private bool           _isBreakingReset   = true;
        private LiteralElement _lastQueuedElement = null;
        private LiteralElement _currentTag        = null;
        private bool           _beginNewParagraph = true;
        private FormatStack    _formatStack       = new FormatStack();
        private bool           _elementsProcessed = false;

        // Static constructor that builds a lookup table of recognized tags.

        private static IDictionary _recognizedTags = new Hashtable();
        static LiteralTextParser()
        {
            // PERF: Add both lowercase and uppercase.

            _recognizedTags.Add("b", LiteralElementType.Bold);
            _recognizedTags.Add("B", LiteralElementType.Bold);

            _recognizedTags.Add("i", LiteralElementType.Italic);
            _recognizedTags.Add("I", LiteralElementType.Italic);

            _recognizedTags.Add("br", LiteralElementType.Break);
            _recognizedTags.Add("BR", LiteralElementType.Break);

            _recognizedTags.Add("p", LiteralElementType.Paragraph);
            _recognizedTags.Add("P", LiteralElementType.Paragraph);

            _recognizedTags.Add("a", LiteralElementType.Anchor);
            _recognizedTags.Add("A", LiteralElementType.Anchor);
        }

        // Convert a tag name to a type.

        private static LiteralElementType TagNameToType(String tagName)
        {
            Object o = _recognizedTags[tagName];
            if (o == null)
            {
                o = _recognizedTags[tagName.ToLower(CultureInfo.InvariantCulture)];
            }
            return (o != null) ? (LiteralElementType)o : LiteralElementType.Unrecognized;
        }

        // Returns true if any valid controls could be generated from the given text.

        internal /*public*/ static bool IsValidText(String validText)
        {
            // 

            if (validText.Length == 0)
            {
                return false;
            }

            foreach (char c in validText)
            {
                if (!Char.IsWhiteSpace(c) &&
                        c != '\t' &&
                        c != '\r' && 
                        c != '\n')
                {
                    return true;
                }
            }

            return false;
        }

        // Main parse routine. Called with a block of text to parse.

        internal /*public*/ void Parse(String literalText)
        {
            int length = literalText.Length;
            int currentPosition = 0;

            while (currentPosition < length)
            {
                // Find start of next tag.

                int nextTag = literalText.IndexOf('<', currentPosition);
                if (nextTag == -1)
                {
                    ParseText(literalText.Substring(currentPosition));
                    break;
                }

                if (nextTag > currentPosition)
                {
                    ParseText(literalText.Substring(currentPosition, nextTag - currentPosition));
                }

                // Find end of tag.

                char quoteChar = '\0';
                int endOfTag;
                for (endOfTag = nextTag + 1; endOfTag < length; endOfTag++)
                {
                    char c = literalText[endOfTag];
                    if (quoteChar == '\0')
                    {
                        if (c == '\'' || c == '\"')
                        {
                            quoteChar = c;
                        }
                        else if (c == '>')
                        {
                            break;
                        }
                    }
                    else
                    {
                        if (c == quoteChar)
                        {
                            quoteChar = '\0';
                        }
                    }
                }

                if (endOfTag == length)
                {
                    // 
                    break;
                }

                ParseTag(literalText, nextTag + 1, endOfTag);
                currentPosition = endOfTag + 1;
            }

            Flush();
        }

        internal /*public*/ void ResetBreaking()
        {
            _isBreakingReset = true;
            ElementsProcessed = false;
        }

        internal /*public*/ void ResetNewParagraph()
        {
            _beginNewParagraph = false;
        }

        internal /*public*/ void UnResetBreaking()
        {
            _isBreakingReset = false;
        }

        protected bool ElementsProcessed
        {
            get
            {
                return _elementsProcessed;
            }

            set
            {
                _elementsProcessed = value;
            }
        }

        protected void OnAfterDataBoundLiteral()
        {
            ElementsProcessed = true;
            UnResetBreaking();
        }

        // Parse a single tag.

        private void ParseTag(String literalText, int tagStart, int tagFinish)
        {
            bool isClosingTag = (literalText[tagStart] == '/');
            if (isClosingTag) 
            {
                tagStart++;
            }

            // Empty tag?

            if (tagStart == tagFinish)
            {
                return;
            }

            // Look for end of tag name.

            int tagNameFinish = tagStart;
            while (tagNameFinish < tagFinish && 
                   !Char.IsWhiteSpace(literalText[tagNameFinish]) && literalText[tagNameFinish] != '/')
            {
                tagNameFinish++;
            }

            // Extract tag name, and compare to recognized tags.

            String tagName = literalText.Substring(tagStart, tagNameFinish - tagStart);
            LiteralElementType tagType = TagNameToType(tagName);
            if (tagType == LiteralElementType.Unrecognized)
            {
                return;
            }

            // Are we already in a complex tag?

            if (_currentTag != null)
            {
                // Ignore any inner tags, except the closing tag.

                if (_currentTag.Type == tagType && isClosingTag)
                {
                    ProcessElementInternal(_currentTag);
                    _currentTag = null;
                }
                else
                {
                    // 
                }
                return;
            }

            switch (tagType)
            {
                case LiteralElementType.Paragraph:
                    
                    // Do not create two breaks for </p><p> pairs.

                    if (!_isBreakingReset)
                    {
                        _isBreakingReset = true;
                        goto case LiteralElementType.Break;
                    }

                    break;

                case LiteralElementType.Break:

                    // If a break is already pending, insert an empty one.

                    if (_beginNewParagraph)
                    {
                        ParseText(String.Empty);
                    }
                    if (_lastQueuedElement != null && 
                        _lastQueuedElement.Text.Length == 0)
                    {
                        _lastQueuedElement.ForceBreakTag = true;
                    }
                    _beginNewParagraph = true;
                    break;

                case LiteralElementType.Bold:

                    if (isClosingTag)
                    {
                        _formatStack.Pop(FormatStack.Bold);
                    }
                    else
                    {
                        _formatStack.Push(FormatStack.Bold);
                    }
                    break;

                case LiteralElementType.Italic:

                    if (isClosingTag)
                    {
                        _formatStack.Pop(FormatStack.Italic);
                    }
                    else
                    {
                        _formatStack.Push(FormatStack.Italic);
                    }
                    break;

                default:
                {
                    if (!isClosingTag)
                    {
                        IDictionary attribs = ParseTagAttributes(literalText, tagNameFinish, tagFinish, tagName);
                        _currentTag = new LiteralElement(tagType, attribs);
                    }
                    break;
                }
            }

            if (_isBreakingReset && tagType != LiteralElementType.Paragraph)
            {
                _isBreakingReset = false;
            }
        }

        protected bool IsInTag
        {
            get
            {
                return _currentTag != null;
            }
        }

        protected LiteralFormat CurrentFormat
        {
            get
            {
                return _formatStack.CurrentFormat;
            }
        }

        // Parse attributes of a tag.

        private enum AttributeParseState
        {
            StartingAttributeName,
            ReadingAttributeName,
            ReadingEqualSign,
            StartingAttributeValue,
            ReadingAttributeValue,
            Error,
        }

        private IDictionary ParseTagAttributes(String literalText, int attrStart, int attrFinish, String tagName)
        {
            if (attrFinish > attrStart && literalText[attrFinish - 1] == '/')
            {
                attrFinish--;
            }

            IDictionary dictionary = null;
            int attrPos = attrStart;
            bool skipWhiteSpaces = true;
            int attrNameStart = 0;
            int attrNameFinish = 0; 
            int attrValueStart = 0;
            char quoteChar = '\0';
            AttributeParseState state = AttributeParseState.StartingAttributeName;

            while (attrPos <= attrFinish && state != AttributeParseState.Error)
            {
                char c = attrPos == attrFinish ? '\0' : literalText[attrPos];

                if (skipWhiteSpaces)
                {
                    if (Char.IsWhiteSpace(c))
                    {
                        attrPos++;
                        continue;
                    }
                    else
                    {
                        skipWhiteSpaces = false;
                    }
                }

                switch (state)
                {
                    case AttributeParseState.StartingAttributeName:
                        if (c == '\0')
                        {
                            attrPos = attrFinish + 1;
                        }
                        else
                        {
                            attrNameStart = attrPos;
                            state = AttributeParseState.ReadingAttributeName;
                        }
                        break;

                    case AttributeParseState.ReadingAttributeName:
                        if (c == '=' || Char.IsWhiteSpace(c))
                        {
                            attrNameFinish = attrPos;
                            skipWhiteSpaces = true;
                            state = AttributeParseState.ReadingEqualSign;
                        }
                        else if (c == '\0')
                        {
                            state = AttributeParseState.Error;
                        }
                        else
                        {
                            attrPos++;
                        }
                        break;

                    case AttributeParseState.ReadingEqualSign:
                        if (c == '=')
                        {
                            skipWhiteSpaces = true;
                            state = AttributeParseState.StartingAttributeValue;
                            attrPos++;
                        }
                        else
                        {
                            state = AttributeParseState.Error;
                        }
                        break;

                    case AttributeParseState.StartingAttributeValue:
                        attrValueStart = attrPos;
                        if (c == '\0')
                        {
                            state = AttributeParseState.Error;
                            break;
                        } 
                        else if (c == '\"' || c == '\'')
                        {
                            quoteChar = c;
                            attrValueStart++;
                            attrPos++;
                        }
                        else
                        {
                            quoteChar = '\0';
                        }
                        state = AttributeParseState.ReadingAttributeValue;
                        break;

                    case AttributeParseState.ReadingAttributeValue:
                        if (c == quoteChar || 
                            ((Char.IsWhiteSpace(c) || c == '\0') && quoteChar == '\0'))
                        {
                            if (attrNameFinish == attrNameStart)
                            {
                                state = AttributeParseState.Error;
                                break;
                            }

                            if (dictionary == null)
                            {
                                dictionary = new HybridDictionary(true);
                            }

                            dictionary.Add(
                                literalText.Substring(attrNameStart, attrNameFinish - attrNameStart),
                                literalText.Substring(attrValueStart, attrPos - attrValueStart));

                            skipWhiteSpaces = true;
                            state = AttributeParseState.StartingAttributeName;
                            if (c == quoteChar)
                            {
                                attrPos++;
                            }
                        }
                        else
                        {
                            attrPos++;
                        }
                        break;
                }
            }

            if (state == AttributeParseState.Error)
            {
                throw new Exception(SR.GetString(SR.LiteralTextParser_InvalidTagFormat));
            }

            return dictionary;
        }

        // Parse a plain text literal.

        private void ParseText(String text)
        {
            if (_currentTag != null)
            {
                // Add to inner text of tag.
                _currentTag.Text += text;
            }
            else
            {
                if (_isBreakingReset && IsValidText(text))
                {
                    _isBreakingReset = false;
                }
                ProcessElementInternal(new LiteralElement(text));
            }
        }

        private void ProcessElementInternal(LiteralElement element)
        {
            // This method needs to fill in an element with formatting and
            // breaking information, and calls ProcessElement. However,
            // each element needs to know whether there will be a break
            // AFTER the element, so elements are processed lazily, keeping
            // the last one in a single-element queue.

            LiteralFormat currentFormat = _formatStack.CurrentFormat;

            if (_lastQueuedElement != null)
            {
                // If both the last and current element are text elements, and 
                // the formatting hasn't changed, then just combine the two into
                // a single element.

                if (_lastQueuedElement.IsText && element.IsText && 
                        (_lastQueuedElement.Format == currentFormat) && 
                        !_beginNewParagraph)
                {
                    _lastQueuedElement.Text += element.Text;
                    return;
                }
                else if (_lastQueuedElement.IsEmptyText && 
                         !_beginNewParagraph &&
                         IgnoreWhiteSpaceElement(_lastQueuedElement))
                {
                    // Empty text element with no breaks - so just ignore.
                }
                else
                {
                    _lastQueuedElement.BreakAfter = _beginNewParagraph;
                    ProcessElement(_lastQueuedElement);
                    ElementsProcessed = true;
                }
            }

            _lastQueuedElement = element;
            _lastQueuedElement.Format = currentFormat;
            _beginNewParagraph = false;
        }

        private void Flush()
        {
            if (_currentTag != null)
            {
                // In the middle of a tag. There may be multiple inner text elements inside
                // a tag, e.g.
                //      <a ...>some text <%# a databinding %> some more text</a>
                // and we're being flushed just at the start of the databinding.

                if (!_currentTag.IsEmptyText)
                {
                    ProcessTagInnerText(_currentTag.Text);
                }
                _currentTag.Text = String.Empty;
                return;
            }

            if (_lastQueuedElement == null)
            {
                return;
            }

            // Ignore orphaned whitespace.
                    
            if (!_lastQueuedElement.ForceBreakTag && _lastQueuedElement.IsEmptyText)
            {
                if (!ElementsProcessed)
                {
                    return;
                }
                if (_lastQueuedElement.Text.Length == 0 || _lastQueuedElement.Text[0] != ' ')
                {
                    return;
                }

                _lastQueuedElement.Text = " ";
            }

            _lastQueuedElement.BreakAfter = _beginNewParagraph;
            ProcessElement(_lastQueuedElement);
            _lastQueuedElement = null;
        }

        protected virtual bool IgnoreWhiteSpaceElement(LiteralElement element)
        {
            return true;
        }

        /*
         * FormatStack private class
         *
         * This class maintains a simple stack of formatting directives. As tags and 
         * closing tags are processed, they are pushed on and popped off this stack.
         * The CurrentFormat property returns the current state.
         */

        private class FormatStack
        {
            internal const char Bold = 'b';
            internal const char Italic = 'i';
            
            private StringBuilder _stringBuilder = new StringBuilder(16);

            public void Push(char option)
            {
                _stringBuilder.Append(option);
            }

            public void Pop(char option)
            {
                // Only pop a matching directive - non-matching directives are ignored!

                int length = _stringBuilder.Length;
                if (length > 0 && _stringBuilder[length - 1] == option)
                {
                    _stringBuilder.Remove(length - 1, 1);
                }
            }

            public LiteralFormat CurrentFormat
            {
                get
                {
                    LiteralFormat format = LiteralFormat.None;
                    for (int i = _stringBuilder.Length - 1; i >= 0; i--)
                    {
                        switch (_stringBuilder[i])
                        {
                            case Bold:
                                format |= LiteralFormat.Bold;
                                break;
                            case Italic:
                                format |= LiteralFormat.Italic;
                                break;
                        }
                    }
                    return format;
                }
            }
        }

    }

}