summaryrefslogtreecommitdiff
path: root/indra/llui/llkeywords.cpp
blob: d830df87723ef6342c7b73b9c5f8167c7d6fd255 (plain)
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
/** 
 * @file llkeywords.cpp
 * @brief Keyword list for LSL
 *
 * $LicenseInfo:firstyear=2000&license=viewerlgpl$
 * Second Life Viewer Source Code
 * Copyright (C) 2010, Linden Research, Inc.
 * 
 * This library is free software; you can redistribute it and/or
 * modify it under the terms of the GNU Lesser General Public
 * License as published by the Free Software Foundation;
 * version 2.1 of the License only.
 * 
 * This library is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * Lesser General Public License for more details.
 * 
 * You should have received a copy of the GNU Lesser General Public
 * License along with this library; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA  02110-1301  USA
 * 
 * Linden Research, Inc., 945 Battery Street, San Francisco, CA  94111  USA
 * $/LicenseInfo$
 */

#include "linden_common.h"

#include <iostream>
#include <fstream>

#include "llkeywords.h"
#include "lltexteditor.h"
#include "llstl.h"
#include <boost/tokenizer.hpp>

const U32 KEYWORD_FILE_CURRENT_VERSION = 2;

inline BOOL LLKeywordToken::isHead(const llwchar* s) const
{
	// strncmp is much faster than string compare
	BOOL res = TRUE;
	const llwchar* t = mToken.c_str();
	S32 len = mToken.size();
	for (S32 i=0; i<len; i++)
	{
		if (s[i] != t[i])
		{
			res = FALSE;
			break;
		}
	}
	return res;
}

LLKeywords::LLKeywords() : mLoaded(FALSE)
{
}

inline BOOL LLKeywordToken::isTail(const llwchar* s) const
{
	BOOL res = TRUE;
	const llwchar* t = mDelimiter.c_str();
	S32 len = mDelimiter.size();
	for (S32 i=0; i<len; i++)
	{
		if (s[i] != t[i])
		{
			res = FALSE;
			break;
		}
	}
	return res;
}

LLKeywords::~LLKeywords()
{
	std::for_each(mWordTokenMap.begin(), mWordTokenMap.end(), DeletePairedPointer());
	std::for_each(mLineTokenList.begin(), mLineTokenList.end(), DeletePointer());
	std::for_each(mDelimiterTokenList.begin(), mDelimiterTokenList.end(), DeletePointer());
}

BOOL LLKeywords::loadFromFile( const std::string& filename )
{
	mLoaded = FALSE;

	////////////////////////////////////////////////////////////
	// File header

	const S32 BUFFER_SIZE = 1024;
	char	buffer[BUFFER_SIZE];	/* Flawfinder: ignore */

	llifstream file;
	file.open(filename);	/* Flawfinder: ignore */
	if( file.fail() )
	{
		LL_INFOS() << "LLKeywords::loadFromFile()  Unable to open file: " << filename << LL_ENDL;
		return mLoaded;
	}

	// Identifying string
	file >> buffer;
	if( strcmp( buffer, "llkeywords" ) )
	{
		LL_INFOS() << filename << " does not appear to be a keyword file" << LL_ENDL;
		return mLoaded;
	}

	// Check file version
	file >> buffer;
	U32	version_num;
	file >> version_num;
	if( strcmp(buffer, "version") || version_num != (U32)KEYWORD_FILE_CURRENT_VERSION )
	{
		LL_INFOS() << filename << " does not appear to be a version " << KEYWORD_FILE_CURRENT_VERSION << " keyword file" << LL_ENDL;
		return mLoaded;
	}

	// start of line (SOL)
	std::string SOL_COMMENT("#");
	std::string SOL_WORD("[word ");
	std::string SOL_LINE("[line ");
	std::string SOL_ONE_SIDED_DELIMITER("[one_sided_delimiter ");
	std::string SOL_TWO_SIDED_DELIMITER("[two_sided_delimiter ");
	std::string SOL_DOUBLE_QUOTATION_MARKS("[double_quotation_marks ");

	LLColor3 cur_color( 1, 0, 0 );
	LLKeywordToken::TOKEN_TYPE cur_type = LLKeywordToken::WORD;

	while (!file.eof())
	{
		buffer[0] = 0;
		file.getline( buffer, BUFFER_SIZE );
		std::string line(buffer);
		if( line.find(SOL_COMMENT) == 0 )
		{
			continue;
		}
		else if( line.find(SOL_WORD) == 0 )
		{
			cur_color = readColor( line.substr(SOL_WORD.size()) );
			cur_type = LLKeywordToken::WORD;
			continue;
		}
		else if( line.find(SOL_LINE) == 0 )
		{
			cur_color = readColor( line.substr(SOL_LINE.size()) );
			cur_type = LLKeywordToken::LINE;
			continue;
		}
		else if( line.find(SOL_TWO_SIDED_DELIMITER) == 0 )
		{
			cur_color = readColor( line.substr(SOL_TWO_SIDED_DELIMITER.size()) );
			cur_type = LLKeywordToken::TWO_SIDED_DELIMITER;
			continue;
		}
		else if( line.find(SOL_DOUBLE_QUOTATION_MARKS) == 0 )
		{
			cur_color = readColor( line.substr(SOL_DOUBLE_QUOTATION_MARKS.size()) );
			cur_type = LLKeywordToken::DOUBLE_QUOTATION_MARKS;
			continue;
		}
		else if( line.find(SOL_ONE_SIDED_DELIMITER) == 0 )	
		{
			cur_color = readColor( line.substr(SOL_ONE_SIDED_DELIMITER.size()) );
			cur_type = LLKeywordToken::ONE_SIDED_DELIMITER;
			continue;
		}

		std::string token_buffer( line );
		LLStringUtil::trim(token_buffer);
		
		typedef boost::tokenizer<boost::char_separator<char> > tokenizer;
		boost::char_separator<char> sep_word("", " \t");
		tokenizer word_tokens(token_buffer, sep_word);
		tokenizer::iterator token_word_iter = word_tokens.begin();

		if( !token_buffer.empty() && token_word_iter != word_tokens.end() )
		{
			// first word is the keyword or a left delimiter
			std::string keyword = (*token_word_iter);
			LLStringUtil::trim(keyword);

			// second word may be a right delimiter
			std::string delimiter;
			if (cur_type == LLKeywordToken::TWO_SIDED_DELIMITER)
			{
				while (delimiter.length() == 0 && ++token_word_iter != word_tokens.end())
				{
					delimiter = *token_word_iter;
					LLStringUtil::trim(delimiter);
				}
			}
			else if (cur_type == LLKeywordToken::DOUBLE_QUOTATION_MARKS)
			{
				// Closing delimiter is identical to the opening one.
				delimiter = keyword;
			}

			// following words are tooltip
			std::string tool_tip;
			while (++token_word_iter != word_tokens.end())
			{
				tool_tip += (*token_word_iter);
			}
			LLStringUtil::trim(tool_tip);
			
			if( !tool_tip.empty() )
			{
				// Replace : with \n for multi-line tool tips.
				LLStringUtil::replaceChar( tool_tip, ':', '\n' );
				addToken(cur_type, keyword, cur_color, tool_tip, delimiter );
			}
			else
			{
				addToken(cur_type, keyword, cur_color, LLStringUtil::null, delimiter );
			}
		}
	}

	file.close();

	mLoaded = TRUE;
	return mLoaded;
}

// Add the token as described
void LLKeywords::addToken(LLKeywordToken::TOKEN_TYPE type,
						  const std::string& key_in,
						  const LLColor3& color,
						  const std::string& tool_tip_in,
						  const std::string& delimiter_in)
{
	LLWString key = utf8str_to_wstring(key_in);
	LLWString tool_tip = utf8str_to_wstring(tool_tip_in);
	LLWString delimiter = utf8str_to_wstring(delimiter_in);
	switch(type)
	{
	case LLKeywordToken::WORD:
		mWordTokenMap[key] = new LLKeywordToken(type, color, key, tool_tip, LLWStringUtil::null);
		break;

	case LLKeywordToken::LINE:
		mLineTokenList.push_front(new LLKeywordToken(type, color, key, tool_tip, LLWStringUtil::null));
		break;

	case LLKeywordToken::TWO_SIDED_DELIMITER:
	case LLKeywordToken::DOUBLE_QUOTATION_MARKS:
	case LLKeywordToken::ONE_SIDED_DELIMITER:
		mDelimiterTokenList.push_front(new LLKeywordToken(type, color, key, tool_tip, delimiter));
		break;

	default:
		llassert(0);
	}
}
LLKeywords::WStringMapIndex::WStringMapIndex(const WStringMapIndex& other)
{
	if(other.mOwner)
	{
		copyData(other.mData, other.mLength);
	}
	else
	{
		mOwner = false;
		mLength = other.mLength;
		mData = other.mData;
	}
}

LLKeywords::WStringMapIndex::WStringMapIndex(const LLWString& str)
{
	copyData(str.data(), str.size());
}

LLKeywords::WStringMapIndex::WStringMapIndex(const llwchar *start, size_t length):
mData(start), mLength(length), mOwner(false)
{
}

LLKeywords::WStringMapIndex::~WStringMapIndex()
{
	if(mOwner)
		delete[] mData;
}

void LLKeywords::WStringMapIndex::copyData(const llwchar *start, size_t length)
{
	llwchar *data = new llwchar[length];
	memcpy((void*)data, (const void*)start, length * sizeof(llwchar));

	mOwner = true;
	mLength = length;
	mData = data;
}

bool LLKeywords::WStringMapIndex::operator<(const LLKeywords::WStringMapIndex &other) const
{
	// NOTE: Since this is only used to organize a std::map, it doesn't matter if it uses correct collate order or not.
	// The comparison only needs to strictly order all possible strings, and be stable.
	
	bool result = false;
	const llwchar* self_iter = mData;
	const llwchar* self_end = mData + mLength;
	const llwchar* other_iter = other.mData;
	const llwchar* other_end = other.mData + other.mLength;
	
	while(true)
	{
		if(other_iter >= other_end)
		{
			// We've hit the end of other.
			// This covers two cases: other being shorter than self, or the strings being equal.
			// In either case, we want to return false.
			result = false;
			break;
		}
		else if(self_iter >= self_end)
		{
			// self is shorter than other.
			result = true;
			break; 
		}
		else if(*self_iter != *other_iter)
		{
			// The current character differs.  The strings are not equal.
			result = *self_iter < *other_iter;
			break;
		}

		self_iter++;
		other_iter++;
	}
	
	return result;
}

LLColor3 LLKeywords::readColor( const std::string& s )
{
	F32 r, g, b;
	r = g = b = 0.0f;
	S32 values_read = sscanf(s.c_str(), "%f, %f, %f]", &r, &g, &b );
	if( values_read != 3 )
	{
		LL_INFOS() << " poorly formed color in keyword file" << LL_ENDL;
	}
	return LLColor3( r, g, b );
}

LLTrace::BlockTimerStatHandle FTM_SYNTAX_COLORING("Syntax Coloring");

// Walk through a string, applying the rules specified by the keyword token list and
// create a list of color segments.
void LLKeywords::findSegments(std::vector<LLTextSegmentPtr>* seg_list, const LLWString& wtext, const LLColor4 &defaultColor, LLTextEditor& editor)
{
	LL_RECORD_BLOCK_TIME(FTM_SYNTAX_COLORING);
	seg_list->clear();

	if( wtext.empty() )
	{
		return;
	}
	
	S32 text_len = wtext.size() + 1;

	seg_list->push_back( new LLNormalTextSegment( defaultColor, 0, text_len, editor ) ); 

	const llwchar* base = wtext.c_str();
	const llwchar* cur = base;
	while( *cur )
	{
		if( *cur == '\n' || cur == base )
		{
			if( *cur == '\n' )
			{
				LLTextSegmentPtr text_segment = new LLLineBreakTextSegment(cur-base);
				text_segment->setToken( 0 );
				insertSegment( *seg_list, text_segment, text_len, defaultColor, editor);
				cur++;
				if( !*cur || *cur == '\n' )
				{
					continue;
				}
			}

			// Skip white space
			while( *cur && isspace(*cur) && (*cur != '\n')  )
			{
				cur++;
			}
			if( !*cur || *cur == '\n' )
			{
				continue;
			}

			// cur is now at the first non-whitespace character of a new line	

			// Line start tokens
			{
				BOOL line_done = FALSE;
				for (token_list_t::iterator iter = mLineTokenList.begin();
					 iter != mLineTokenList.end(); ++iter)
				{
					LLKeywordToken* cur_token = *iter;
					if( cur_token->isHead( cur ) )
					{
						S32 seg_start = cur - base;
						while( *cur && *cur != '\n' )
						{
							// skip the rest of the line
							cur++;
						}
						S32 seg_end = cur - base;
						
						//create segments from seg_start to seg_end
						insertSegments(wtext, *seg_list,cur_token, text_len, seg_start, seg_end, defaultColor, editor);
						line_done = TRUE; // to break out of second loop.
						break;
					}
				}

				if( line_done )
				{
					continue;
				}
			}
		}

		// Skip white space
		while( *cur && isspace(*cur) && (*cur != '\n')  )
		{
			cur++;
		}

		while( *cur && *cur != '\n' )
		{
			// Check against delimiters
			{
				S32 seg_start = 0;
				LLKeywordToken* cur_delimiter = NULL;
				for (token_list_t::iterator iter = mDelimiterTokenList.begin();
					 iter != mDelimiterTokenList.end(); ++iter)
				{
					LLKeywordToken* delimiter = *iter;
					if( delimiter->isHead( cur ) )
					{
						cur_delimiter = delimiter;
						break;
					}
				}

				if( cur_delimiter )
				{
					S32 between_delimiters = 0;
					S32 seg_end = 0;

					seg_start = cur - base;
					cur += cur_delimiter->getLengthHead();
					
					LLKeywordToken::TOKEN_TYPE type = cur_delimiter->getType();
					if( type == LLKeywordToken::TWO_SIDED_DELIMITER || type == LLKeywordToken::DOUBLE_QUOTATION_MARKS )
					{
						while( *cur && !cur_delimiter->isTail(cur))
						{
							// Check for an escape sequence.
							if (type == LLKeywordToken::DOUBLE_QUOTATION_MARKS && *cur == '\\')
							{
								// Count the number of backslashes.
								S32 num_backslashes = 0;
								while (*cur == '\\')
								{
									num_backslashes++;
									between_delimiters++;
									cur++;
								}
								// If the next character is the end delimiter?
								if (cur_delimiter->isTail(cur))
								{
									// If there was an odd number of backslashes, then this delimiter
									// does not end the sequence.
									if (num_backslashes % 2 == 1)
									{
										between_delimiters++;
										cur++;
									}
									else
									{
										// This is an end delimiter.
										break;
									}
								}
							}
							else
							{
								between_delimiters++;
								cur++;
							}
						}

						if( *cur )
						{
							cur += cur_delimiter->getLengthHead();
							seg_end = seg_start + between_delimiters + cur_delimiter->getLengthHead() + cur_delimiter->getLengthTail();
						}
						else
						{
							// eof
							seg_end = seg_start + between_delimiters + cur_delimiter->getLengthHead();
						}
					}
					else
					{
						llassert( cur_delimiter->getType() == LLKeywordToken::ONE_SIDED_DELIMITER );
						// Left side is the delimiter.  Right side is eol or eof.
						while( *cur && ('\n' != *cur) )
						{
							between_delimiters++;
							cur++;
						}
						seg_end = seg_start + between_delimiters + cur_delimiter->getLengthHead();
					}

					insertSegments(wtext, *seg_list,cur_delimiter, text_len, seg_start, seg_end, defaultColor, editor);
					/*
					LLTextSegmentPtr text_segment = new LLNormalTextSegment( cur_delimiter->getColor(), seg_start, seg_end, editor );
					text_segment->setToken( cur_delimiter );
					insertSegment( seg_list, text_segment, text_len, defaultColor, editor);
					*/
					// Note: we don't increment cur, since the end of one delimited seg may be immediately
					// followed by the start of another one.
					continue;
				}
			}

			// check against words
			llwchar prev = cur > base ? *(cur-1) : 0;
			if( !isalnum( prev ) && (prev != '_') )
			{
				const llwchar* p = cur;
				while( isalnum( *p ) || (*p == '_') )
				{
					p++;
				}
				S32 seg_len = p - cur;
				if( seg_len > 0 )
				{
					WStringMapIndex word( cur, seg_len );
					word_token_map_t::iterator map_iter = mWordTokenMap.find(word);
					if( map_iter != mWordTokenMap.end() )
					{
						LLKeywordToken* cur_token = map_iter->second;
						S32 seg_start = cur - base;
						S32 seg_end = seg_start + seg_len;

						// LL_INFOS() << "Seg: [" << word.c_str() << "]" << LL_ENDL;

						insertSegments(wtext, *seg_list,cur_token, text_len, seg_start, seg_end, defaultColor, editor);
					}
					cur += seg_len; 
					continue;
				}
			}

			if( *cur && *cur != '\n' )
			{
				cur++;
			}
		}
	}
}

void LLKeywords::insertSegments(const LLWString& wtext, std::vector<LLTextSegmentPtr>& seg_list, LLKeywordToken* cur_token, S32 text_len, S32 seg_start, S32 seg_end, const LLColor4 &defaultColor, LLTextEditor& editor )
{
	std::string::size_type pos = wtext.find('\n',seg_start);
	
	while (pos!=-1 && pos < (std::string::size_type)seg_end)
	{
		if (pos!=seg_start)
		{
			LLTextSegmentPtr text_segment = new LLNormalTextSegment( cur_token->getColor(), seg_start, pos, editor );
			text_segment->setToken( cur_token );
			insertSegment( seg_list, text_segment, text_len, defaultColor, editor);
		}

		LLTextSegmentPtr text_segment = new LLLineBreakTextSegment(pos);
		text_segment->setToken( cur_token );
		insertSegment( seg_list, text_segment, text_len, defaultColor, editor);

		seg_start = pos+1;
		pos = wtext.find('\n',seg_start);
	}

	LLTextSegmentPtr text_segment = new LLNormalTextSegment( cur_token->getColor(), seg_start, seg_end, editor );
	text_segment->setToken( cur_token );
	insertSegment( seg_list, text_segment, text_len, defaultColor, editor);
}

void LLKeywords::insertSegment(std::vector<LLTextSegmentPtr>& seg_list, LLTextSegmentPtr new_segment, S32 text_len, const LLColor4 &defaultColor, LLTextEditor& editor )
{
	LLTextSegmentPtr last = seg_list.back();
	S32 new_seg_end = new_segment->getEnd();

	if( new_segment->getStart() == last->getStart() )
	{
		seg_list.pop_back();
	}
	else
	{
		last->setEnd( new_segment->getStart() );
	}
	seg_list.push_back( new_segment );

	if( new_seg_end < text_len )
	{
		seg_list.push_back( new LLNormalTextSegment( defaultColor, new_seg_end, text_len, editor ) );
	}
}

#ifdef _DEBUG
void LLKeywords::dump()
{
	LL_INFOS() << "LLKeywords" << LL_ENDL;


	LL_INFOS() << "LLKeywords::sWordTokenMap" << LL_ENDL;
	word_token_map_t::iterator word_token_iter = mWordTokenMap.begin();
	while( word_token_iter != mWordTokenMap.end() )
	{
		LLKeywordToken* word_token = word_token_iter->second;
		word_token->dump();
		++word_token_iter;
	}

	LL_INFOS() << "LLKeywords::sLineTokenList" << LL_ENDL;
	for (token_list_t::iterator iter = mLineTokenList.begin();
		 iter != mLineTokenList.end(); ++iter)
	{
		LLKeywordToken* line_token = *iter;
		line_token->dump();
	}


	LL_INFOS() << "LLKeywords::sDelimiterTokenList" << LL_ENDL;
	for (token_list_t::iterator iter = mDelimiterTokenList.begin();
		 iter != mDelimiterTokenList.end(); ++iter)
	{
		LLKeywordToken* delimiter_token = *iter;
		delimiter_token->dump();
	}
}

void LLKeywordToken::dump()
{
	LL_INFOS() << "[" << 
		mColor.mV[VX] << ", " <<
		mColor.mV[VY] << ", " <<
		mColor.mV[VZ] << "] [" <<
		wstring_to_utf8str(mToken) << "]" <<
		LL_ENDL;
}

#endif  // DEBUG