File: LexX12.cxx

package info (click to toggle)
codequery 1.0.1%2Bdfsg-1
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 17,860 kB
  • sloc: cpp: 151,420; xml: 16,576; python: 5,602; ansic: 5,487; makefile: 559; perl: 496; ruby: 209; sql: 194; sh: 106; php: 53; vhdl: 51; erlang: 47; objc: 22; lisp: 18; cobol: 18; modula3: 17; asm: 14; fortran: 12; ml: 11; tcl: 6
file content (400 lines) | stat: -rw-r--r-- 12,313 bytes parent folder | download | duplicates (3)
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
// Scintilla Lexer for X12
// @file LexX12.cxx
// Written by Iain Clarke, IMCSoft & Inobiz AB.
// X12 official documentation is behind a paywall, but there's a description of the syntax here:
// http://www.rawlinsecconsulting.com/x12tutorial/x12syn.html
// This code is subject to the same license terms as the rest of the scintilla project:
// The License.txt file describes the conditions under which this software may be distributed.
//

// Header order must match order in scripts/HeaderOrder.txt
#include <cstdlib>
#include <cassert>
#include <cstring>
#include <cctype>

#include <string>
#include <string_view>

#include <vector>
#include <algorithm>

#include "ILexer.h"
#include "Scintilla.h"
#include "SciLexer.h"
#include "LexerModule.h"
#include "DefaultLexer.h"

using namespace Scintilla;
using namespace Lexilla;

class LexerX12 : public DefaultLexer
{
public:
	LexerX12();
	virtual ~LexerX12() {} // virtual destructor, as we inherit from ILexer

	static ILexer5 *Factory() {
		return new LexerX12;
	}

	int SCI_METHOD Version() const override
	{
		return lvRelease5;
	}
	void SCI_METHOD Release() override
	{
		delete this;
	}

	const char * SCI_METHOD PropertyNames() override
	{
		return "fold";
	}
	int SCI_METHOD PropertyType(const char *) override
	{
		return SC_TYPE_BOOLEAN; // Only one property!
	}
	const char * SCI_METHOD DescribeProperty(const char *name) override
	{
		if (!strcmp(name, "fold"))
			return "Whether to apply folding to document or not";
		return "";
	}

	Sci_Position SCI_METHOD PropertySet(const char *key, const char *val) override
	{
		if (!strcmp(key, "fold"))
		{
			m_bFold = strcmp(val, "0") ? true : false;
			return 0;
		}
		return -1;
	}
	const char * SCI_METHOD PropertyGet(const char *) override {
		return "";
	}
	const char * SCI_METHOD DescribeWordListSets() override
	{
		return "";
	}
	Sci_Position SCI_METHOD WordListSet(int, const char *) override
	{
		return -1;
	}
	void SCI_METHOD Lex(Sci_PositionU startPos, Sci_Position length, int initStyle, IDocument *pAccess) override;
	void SCI_METHOD Fold(Sci_PositionU startPos, Sci_Position length, int initStyle, IDocument *pAccess) override;
	void * SCI_METHOD PrivateCall(int, void *) override
	{
		return NULL;
	}

protected:
	struct Terminator
	{
		int Style = SCE_X12_BAD;
		Sci_PositionU pos = 0;
		Sci_PositionU length = 0;
		int FoldChange = 0;
	};
	Terminator InitialiseFromISA(IDocument *pAccess);
	Sci_PositionU FindPreviousSegmentStart(IDocument *pAccess, Sci_Position startPos) const;
	Terminator DetectSegmentHeader(IDocument *pAccess, Sci_PositionU pos) const;
	Terminator FindNextTerminator(IDocument *pAccess, Sci_PositionU pos, bool bJustSegmentTerminator = false) const;

	bool m_bFold = false;
	char m_SeparatorSubElement = 0;
	char m_SeparatorElement = 0;
	std::string m_SeparatorSegment; // might be multiple characters
	std::string m_LineFeed;
};

LexerModule lmX12(SCLEX_X12, LexerX12::Factory, "x12");

///////////////////////////////////////////////////////////////////////////////



///////////////////////////////////////////////////////////////////////////////

LexerX12::LexerX12() : DefaultLexer("x12", SCLEX_X12)
{
}

void LexerX12::Lex(Sci_PositionU startPos, Sci_Position length, int, IDocument *pAccess)
{
	Sci_PositionU posFinish = startPos + length;

	Terminator T = InitialiseFromISA(pAccess);

	if (T.Style == SCE_X12_BAD)
	{
		if (T.pos < startPos)
			T.pos = startPos; // we may be colouring in batches.
		pAccess->StartStyling(startPos);
		pAccess->SetStyleFor(T.pos - startPos, SCE_X12_ENVELOPE);
		pAccess->SetStyleFor(posFinish - T.pos, SCE_X12_BAD);
		return;
	}

	// Look backwards for a segment start or a document beginning
	Sci_PositionU posCurrent = FindPreviousSegmentStart (pAccess, startPos);

	// Style buffer, so we're not issuing loads of notifications
	pAccess->StartStyling(posCurrent);

	while (posCurrent < posFinish)
	{
		// Look for first element marker, so we can denote segment
		T = DetectSegmentHeader(pAccess, posCurrent);
		if (T.Style == SCE_X12_BAD)
			break;

		pAccess->SetStyleFor(T.pos - posCurrent, T.Style);
		pAccess->SetStyleFor(T.length, SCE_X12_SEP_ELEMENT);
		posCurrent = T.pos + T.length;

		while (T.Style != SCE_X12_BAD && T.Style != SCE_X12_SEGMENTEND) // Break on bad or segment ending
		{
			T = FindNextTerminator(pAccess, posCurrent, false);
			if (T.Style == SCE_X12_BAD)
				break;

			int Style = T.Style;

			pAccess->SetStyleFor(T.pos - posCurrent, SCE_X12_DEFAULT);
			pAccess->SetStyleFor(T.length, Style);
			posCurrent = T.pos + T.length;
		}
		if (T.Style == SCE_X12_BAD)
			break;
	}

	pAccess->SetStyleFor(posFinish - posCurrent, SCE_X12_BAD);
}

void LexerX12::Fold(Sci_PositionU startPos, Sci_Position length, int, IDocument *pAccess)
{
	if (!m_bFold)
		return;

	// Are we even foldable?
	// check for cr,lf,cr+lf.
	if (m_LineFeed.empty())
		return;

	Sci_PositionU posFinish = startPos + length;

	// Look backwards for a segment start or a document beginning
	startPos = FindPreviousSegmentStart(pAccess, startPos);
	Terminator T;

	Sci_PositionU currLine = pAccess->LineFromPosition(startPos);
	int levelCurrentStyle = SC_FOLDLEVELBASE;
	int indentCurrent = 0;
	if (currLine > 0)
	{
		levelCurrentStyle = pAccess->GetLevel(currLine - 1); // bottom 12 bits are level
		indentCurrent = levelCurrentStyle & (SC_FOLDLEVELBASE - 1); // indent from previous line
		Sci_PositionU posLine = pAccess->LineStart(currLine - 1);
		T = DetectSegmentHeader(pAccess, posLine);
		indentCurrent += T.FoldChange;
	}

	while (startPos < posFinish)
	{
		T = DetectSegmentHeader(pAccess, startPos);
		int indentNext = indentCurrent + T.FoldChange;
		if (indentNext < 0)
			indentNext = 0;

		levelCurrentStyle = (T.FoldChange > 0) ? (SC_FOLDLEVELBASE | SC_FOLDLEVELHEADERFLAG) : SC_FOLDLEVELBASE;

		currLine = pAccess->LineFromPosition(startPos);
		pAccess->SetLevel(currLine, levelCurrentStyle | indentCurrent);

		T = FindNextTerminator(pAccess, startPos, true);

		if (T.Style == SCE_X12_BAD)
			break;

		startPos = T.pos + T.length;
		indentCurrent = indentNext;
	}
}

LexerX12::Terminator LexerX12::InitialiseFromISA(IDocument *pAccess)
{
	Sci_Position length = pAccess->Length();
	if (length <= 108)
		return { SCE_X12_BAD, 0 };

	pAccess->GetCharRange(&m_SeparatorElement, 3, 1);
	pAccess->GetCharRange(&m_SeparatorSubElement, 104, 1);

	// Look for GS, as that's the next segment. Anything between 105 and GS/IEA is our segment separator.
	Sci_Position posNextSegment;
	char bufSegment[3] = { 0 };
	for (posNextSegment = 105; posNextSegment < length - 3; posNextSegment++)
	{
		pAccess->GetCharRange(bufSegment, posNextSegment, 3);
		if (!memcmp (bufSegment, "GS", 2) || !memcmp(bufSegment, "IEA", 3))
		{
			m_SeparatorSegment.resize(posNextSegment - 105);
			pAccess->GetCharRange(&m_SeparatorSegment.at(0), 105, posNextSegment - 105);

			// Is some of that CR+LF?
			size_t nPos = m_SeparatorSegment.find_last_not_of("\r\n");
			m_LineFeed = m_SeparatorSegment.substr(nPos + 1);
			m_SeparatorSegment = m_SeparatorSegment.substr(0, nPos + 1);
			break;
		}
	}
	if (m_SeparatorSegment.empty() && m_LineFeed.empty())
	{
		return { SCE_X12_BAD, 105 };
	}

	// Validate we have an element separator, and it's not silly!
	if (m_SeparatorElement == '\0' || m_SeparatorElement == '\n' || m_SeparatorElement == '\r')
		return { SCE_X12_BAD, 3 };

	// Validate we have an element separator, and it's not silly!
	if (m_SeparatorSubElement == '\0' || m_SeparatorSubElement == '\n' || m_SeparatorSubElement == '\r')
		return { SCE_X12_BAD, 103 };
	if (m_SeparatorElement == m_SeparatorSubElement)
		return { SCE_X12_BAD, 104 };
	for (auto& c : m_SeparatorSegment)
	{
		if (m_SeparatorElement == c)
			return { SCE_X12_BAD, 105 };
		if (m_SeparatorSubElement == c)
			return { SCE_X12_BAD, 105 };
	}

	// Check we have element markers at all the right places! ISA element has fixed entries.
	std::vector<Sci_PositionU> ElementMarkers = { 3, 6, 17, 20, 31, 34, 50, 53, 69, 76, 81, 83, 89, 99, 101, 103 };
	for (auto i : ElementMarkers)
	{
		char c;
		pAccess->GetCharRange(&c, i, 1);
		if (c != m_SeparatorElement)
			return { SCE_X12_BAD, i };
	}
	// Check we have no element markers anywhere else!
	for (Sci_PositionU i = 0; i < 105; i++)
	{
		if (std::find(ElementMarkers.begin(), ElementMarkers.end(), i) != ElementMarkers.end())
			continue;

		char c;
		pAccess->GetCharRange(&c, i, 1);
		if (c == m_SeparatorElement)
			return { SCE_X12_BAD, i };
	}

	return { SCE_X12_ENVELOPE };
}

Sci_PositionU LexerX12::FindPreviousSegmentStart(IDocument *pAccess, Sci_Position startPos) const
{
	Sci_PositionU length = pAccess->Length();
	std::string bufTest = m_SeparatorSegment + m_LineFeed; // quick way of making the lengths the same
	std::string bufCompare = bufTest;

	for (; startPos > 0; startPos--)
	{
		if (startPos + bufTest.size() > length)
			continue;

		pAccess->GetCharRange(&bufTest.at(0), startPos, bufTest.size());
		if (bufTest == bufCompare)
		{
			return startPos + bufTest.size();
		}
	}
	// We didn't find a ', so just go with the beginning
	return 0;
}

LexerX12::Terminator LexerX12::DetectSegmentHeader(IDocument *pAccess, Sci_PositionU pos) const
{
	Sci_PositionU Length = pAccess->Length();
	Length -= pos;
	char c, Buf[4] = { 0 }; // max 3 + separator
	for (Sci_PositionU posOffset = 0; posOffset < std::size(Buf) && posOffset < Length; posOffset++)
	{
		pAccess->GetCharRange(&c, pos + posOffset, 1);
		if (c != m_SeparatorElement)
		{
			Buf[posOffset] = c;
			continue;
		}

		// check for special segments, involved in folding start/stop.
		if (memcmp(Buf, "ISA", 3) == 0)
			return { SCE_X12_ENVELOPE, pos + posOffset, 1, +1 };
		if (memcmp(Buf, "IEA", 3) == 0)
			return { SCE_X12_ENVELOPE, pos + posOffset, 1, -1 };
		if (memcmp(Buf, "GS", 2) == 0)
			return { SCE_X12_FUNCTIONGROUP, pos + posOffset, 1, +1 };
		if (memcmp(Buf, "GE", 2) == 0)
			return { SCE_X12_FUNCTIONGROUP, pos + posOffset, 1, -1 };
		if (memcmp(Buf, "ST", 2) == 0)
			return { SCE_X12_TRANSACTIONSET, pos + posOffset, 1, +1 };
		if (memcmp(Buf, "SE", 2) == 0)
			return { SCE_X12_TRANSACTIONSET, pos + posOffset, 1, -1 };
		return { SCE_X12_SEGMENTHEADER, pos + posOffset, 1, 0 };
	}
	return { SCE_X12_BAD, pos, 0, 0 };
}

LexerX12::Terminator LexerX12::FindNextTerminator(IDocument *pAccess, Sci_PositionU pos, bool bJustSegmentTerminator) const
{
	char c;
	Sci_PositionU length = pAccess->Length();
	std::string bufTestSegment = m_SeparatorSegment; // quick way of making the lengths the same
	std::string bufTestLineFeed = m_LineFeed; // quick way of making the lengths the same


	while (pos < (Sci_PositionU)length)
	{
		pAccess->GetCharRange(&c, pos, 1);
		if (pos + m_SeparatorSegment.size() > length)
			bufTestSegment.clear(); // going up - so once we can't get this, we're done with the buffer.
		else if (!bufTestSegment.empty())
			pAccess->GetCharRange(&bufTestSegment.at(0), pos, bufTestSegment.size());
		if (pos + m_LineFeed.size() > length)
			bufTestLineFeed.clear(); // going up - so once we can't get this, we're done with the buffer.
		else if (!bufTestLineFeed.empty())
			pAccess->GetCharRange(&bufTestLineFeed.at(0), pos, bufTestLineFeed.size());

		if (!bJustSegmentTerminator && c == m_SeparatorElement)
			return { SCE_X12_SEP_ELEMENT, pos, 1 };
		else if (!bJustSegmentTerminator && c == m_SeparatorSubElement)
			return { SCE_X12_SEP_SUBELEMENT, pos, 1 };
		else if (!m_SeparatorSegment.empty() && bufTestSegment == m_SeparatorSegment)
		{
			if (m_LineFeed.empty())
				return { SCE_X12_SEGMENTEND, pos, m_SeparatorSegment.size() };
			// is this the end?
			if (pos + m_SeparatorSegment.size() == length)
				return { SCE_X12_SEGMENTEND, pos, m_SeparatorSegment.size() };
			// Check if we're followed by a linefeed.
			if (pos + m_SeparatorSegment.size() + m_LineFeed.size() > length)
				return { SCE_X12_BAD, pos };
			bufTestSegment = m_LineFeed;
			pAccess->GetCharRange(&bufTestSegment.at(0), pos + m_SeparatorSegment.size(), bufTestSegment.size());
			if (bufTestSegment == m_LineFeed)
				return { SCE_X12_SEGMENTEND, pos, m_SeparatorSegment.size() + m_LineFeed.size() };
			break;
		}
		else if (m_SeparatorSegment.empty() && bufTestLineFeed == m_LineFeed)
		{
			return { SCE_X12_SEGMENTEND, pos, m_LineFeed.size() };
		}
		pos++;
	}

	return { SCE_X12_BAD, pos };
}