cariboujs 2.0.6 → 2.0.8
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +5 -3
- package/abnf/AbnfLexer.js +51 -50
- package/asm/asm8080/asm8080Lexer.js +253 -152
- package/asm/asm8080/asm8080Listener.js +72 -0
- package/asm/asm8080/asm8080Parser.js +1307 -289
- package/asm/asm8080/asm8080Visitor.js +48 -0
- package/asm/asmZ80/asmZ80Lexer.js +152 -128
- package/asm/asmZ80/asmZ80Listener.js +9 -0
- package/asm/asmZ80/asmZ80Parser.js +316 -170
- package/asm/asmZ80/asmZ80Visitor.js +6 -0
- package/c/CParser.js +1352 -1344
- package/cypher/CypherLexer.js +208 -205
- package/cypher/CypherParser.js +1180 -984
- package/cypher/CypherParserListener.js +18 -0
- package/cypher/CypherParserVisitor.js +12 -0
- package/miniscript/MiniscriptLexer.js +199 -0
- package/miniscript/MiniscriptListener.js +180 -0
- package/miniscript/MiniscriptParser.js +2620 -0
- package/miniscript/MiniscriptVisitor.js +124 -0
- package/package.json +1 -1
- package/python/python3_14/PythonLexer.js +1238 -0
- package/python/python3_14/PythonLexerBase.js +819 -0
- package/python/{python3_13 → python3_14}/PythonParser.js +4141 -3347
- package/python/{python3_13 → python3_14}/PythonParserListener.js +81 -0
- package/python/{python3_13 → python3_14}/PythonParserVisitor.js +54 -0
- package/sql/plsql/PlSqlLexer.js +4114 -4113
- package/sql/plsql/PlSqlParser.js +37114 -31650
- package/sql/plsql/PlSqlParserBase.js +31 -0
- package/sql/plsql/PlSqlParserListener.js +58 -4
- package/sql/plsql/PlSqlParserVisitor.js +38 -2
- package/sysml-v2/SysMLv2Lexer.js +617 -605
- package/sysml-v2/SysMLv2Parser.js +7135 -10083
- package/sysml-v2/SysMLv2ParserListener.js +45 -423
- package/sysml-v2/SysMLv2ParserVisitor.js +30 -282
- package/xpath/xpath4/XPath4Lexer.js +667 -0
- package/xpath/xpath4/XPath4Parser.js +17424 -0
- package/xpath/xpath4/XPath4ParserBase.js +34 -0
- package/xpath/xpath4/XPath4ParserListener.js +1521 -0
- package/xpath/xpath4/XPath4ParserVisitor.js +1018 -0
- package/xquery/xquery4/XQuery4Lexer.js +1396 -0
- package/xquery/xquery4/XQuery4LexerBase.js +42 -0
- package/xquery/xquery4/XQuery4Parser.js +27899 -0
- package/xquery/xquery4/XQuery4ParserBase.js +38 -0
- package/xquery/xquery4/XQuery4ParserListener.js +2322 -0
- package/xquery/xquery4/XQuery4ParserVisitor.js +1552 -0
- package/awk/awkLexer.js +0 -317
- package/awk/awkListener.js +0 -378
- package/awk/awkParser.js +0 -5859
- package/awk/awkVisitor.js +0 -256
- package/python/python3_13/PythonLexer.js +0 -974
- package/python/python3_13/PythonLexerBase.js +0 -676
|
@@ -1,676 +0,0 @@
|
|
|
1
|
-
/*
|
|
2
|
-
The MIT License (MIT)
|
|
3
|
-
Copyright (c) 2021 Robert Einhorn
|
|
4
|
-
|
|
5
|
-
Permission is hereby granted, free of charge, to any person obtaining a copy
|
|
6
|
-
of this software and associated documentation files (the "Software"), to deal
|
|
7
|
-
in the Software without restriction, including without limitation the rights
|
|
8
|
-
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
|
9
|
-
copies of the Software, and to permit persons to whom the Software is
|
|
10
|
-
furnished to do so, subject to the following conditions:
|
|
11
|
-
The above copyright notice and this permission notice shall be included in
|
|
12
|
-
all copies or substantial portions of the Software.
|
|
13
|
-
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
|
14
|
-
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
|
15
|
-
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
|
16
|
-
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
|
17
|
-
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
|
18
|
-
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
|
19
|
-
THE SOFTWARE.
|
|
20
|
-
*/
|
|
21
|
-
|
|
22
|
-
/*
|
|
23
|
-
*
|
|
24
|
-
* Project : Python Indent/Dedent handler for ANTLR4 grammars
|
|
25
|
-
*
|
|
26
|
-
* Developed by : Robert Einhorn, robert.einhorn.hu@gmail.com
|
|
27
|
-
*
|
|
28
|
-
*/
|
|
29
|
-
|
|
30
|
-
import { CharStreams, CommonTokenStream, Token, CommonToken, Lexer } from "antlr4";
|
|
31
|
-
import PythonLexer from "./PythonLexer.js";
|
|
32
|
-
import PythonParser from "./PythonParser.js";
|
|
33
|
-
|
|
34
|
-
export default class PythonLexerBase extends Lexer {
|
|
35
|
-
constructor(input) {
|
|
36
|
-
super(input);
|
|
37
|
-
|
|
38
|
-
// A stack that keeps track of the indentation lengths
|
|
39
|
-
this.indentLengthStack;
|
|
40
|
-
// A list where tokens are waiting to be loaded into the token stream
|
|
41
|
-
this.pendingTokens;
|
|
42
|
-
|
|
43
|
-
// last pending token types
|
|
44
|
-
this.previousPendingTokenType;
|
|
45
|
-
this.lastPendingTokenTypeFromDefaultChannel;
|
|
46
|
-
|
|
47
|
-
// The amount of opened parentheses, square brackets or curly braces
|
|
48
|
-
this.opened;
|
|
49
|
-
// The amount of opened parentheses and square brackets in the current lexer mode
|
|
50
|
-
this.paren_or_bracket_openedStack;
|
|
51
|
-
// A stack that stores expression(s) between braces in fstring
|
|
52
|
-
this.braceExpressionStack;
|
|
53
|
-
this.prevBraceExpression;
|
|
54
|
-
|
|
55
|
-
// Instead of this._mode (_mode is not implemented in each ANTLR4 runtime)
|
|
56
|
-
this.curLexerMode;
|
|
57
|
-
// Instead of this._modeStack (_modeStack is not implemented in each ANTLR4 runtime)
|
|
58
|
-
this.lexerModeStack;
|
|
59
|
-
|
|
60
|
-
this.wasSpaceIndentation;
|
|
61
|
-
this.wasTabIndentation;
|
|
62
|
-
this.wasIndentationMixedWithSpacesAndTabs;
|
|
63
|
-
|
|
64
|
-
this.curToken; // current (under processing) token
|
|
65
|
-
this.ffgToken; // following (look ahead) token
|
|
66
|
-
|
|
67
|
-
this.#init();
|
|
68
|
-
}
|
|
69
|
-
|
|
70
|
-
get #INVALID_LENGTH() { return -1; }
|
|
71
|
-
get #ERR_TXT() { return " ERROR: "; }
|
|
72
|
-
|
|
73
|
-
nextToken() { // reading the input stream until a return EOF
|
|
74
|
-
this.#checkNextToken();
|
|
75
|
-
return this.pendingTokens.shift() /* stack pollFirst() */; // add the queued token to the token stream
|
|
76
|
-
}
|
|
77
|
-
|
|
78
|
-
reset() {
|
|
79
|
-
this.#init();
|
|
80
|
-
super.reset();
|
|
81
|
-
}
|
|
82
|
-
|
|
83
|
-
#init() {
|
|
84
|
-
this.indentLengthStack = [];
|
|
85
|
-
this.pendingTokens = [];
|
|
86
|
-
this.previousPendingTokenType = 0;
|
|
87
|
-
this.lastPendingTokenTypeFromDefaultChannel = 0;
|
|
88
|
-
this.opened = 0;
|
|
89
|
-
this.paren_or_bracket_openedStack = [];
|
|
90
|
-
this.braceExpressionStack = [];
|
|
91
|
-
this.prevBraceExpression = "";
|
|
92
|
-
this.curLexerMode = 0;
|
|
93
|
-
this.lexerModeStack = [];
|
|
94
|
-
this.wasSpaceIndentation = false;
|
|
95
|
-
this.wasTabIndentation = false;
|
|
96
|
-
this.wasIndentationMixedWithSpacesAndTabs = false;
|
|
97
|
-
this.curToken = null;
|
|
98
|
-
this.ffgToken = null;
|
|
99
|
-
}
|
|
100
|
-
|
|
101
|
-
#checkNextToken() {
|
|
102
|
-
if (this.previousPendingTokenType === Token.EOF)
|
|
103
|
-
return;
|
|
104
|
-
|
|
105
|
-
if (this.indentLengthStack.length === 0) { // We're at the first token
|
|
106
|
-
this.#insertENCODINGtoken();
|
|
107
|
-
this.#setCurrentAndFollowingTokens();
|
|
108
|
-
this.#handleStartOfInput();
|
|
109
|
-
} else {
|
|
110
|
-
this.#setCurrentAndFollowingTokens();
|
|
111
|
-
}
|
|
112
|
-
|
|
113
|
-
switch (this.curToken.type) {
|
|
114
|
-
case PythonLexer.NEWLINE:
|
|
115
|
-
this.#handleNEWLINEtoken();
|
|
116
|
-
break;
|
|
117
|
-
case PythonLexer.LPAR:
|
|
118
|
-
case PythonLexer.LSQB:
|
|
119
|
-
case PythonLexer.LBRACE:
|
|
120
|
-
this.opened++;
|
|
121
|
-
this.#addPendingToken(this.curToken);
|
|
122
|
-
break;
|
|
123
|
-
case PythonLexer.RPAR:
|
|
124
|
-
case PythonLexer.RSQB:
|
|
125
|
-
case PythonLexer.RBRACE:
|
|
126
|
-
this.opened--;
|
|
127
|
-
this.#addPendingToken(this.curToken);
|
|
128
|
-
break;
|
|
129
|
-
case PythonLexer.FSTRING_MIDDLE:
|
|
130
|
-
this.#handleFSTRING_MIDDLEtokenWithDoubleBrace(); // does not affect the opened field
|
|
131
|
-
this.#addPendingToken(this.curToken);
|
|
132
|
-
break;
|
|
133
|
-
case PythonLexer.COLONEQUAL:
|
|
134
|
-
this.#handleCOLONEQUALtokenInFString();
|
|
135
|
-
break;
|
|
136
|
-
case PythonLexer.ERRORTOKEN:
|
|
137
|
-
this.#reportLexerError(`token recognition error at: '${this.curToken.text}'`);
|
|
138
|
-
this.#addPendingToken(this.curToken);
|
|
139
|
-
break;
|
|
140
|
-
case Token.EOF:
|
|
141
|
-
this.#handleEOFtoken();
|
|
142
|
-
break;
|
|
143
|
-
default:
|
|
144
|
-
this.#addPendingToken(this.curToken);
|
|
145
|
-
}
|
|
146
|
-
this.#handleFORMAT_SPECIFICATION_MODE();
|
|
147
|
-
}
|
|
148
|
-
|
|
149
|
-
#setCurrentAndFollowingTokens() {
|
|
150
|
-
this.curToken = this.ffgToken == undefined ?
|
|
151
|
-
super.nextToken() :
|
|
152
|
-
this.ffgToken;
|
|
153
|
-
|
|
154
|
-
this.#checkCurToken(); // ffgToken cannot be used in this method and its sub methods (ffgToken is not yet set)!
|
|
155
|
-
|
|
156
|
-
this.ffgToken = this.curToken.type === Token.EOF ?
|
|
157
|
-
this.curToken :
|
|
158
|
-
super.nextToken();
|
|
159
|
-
}
|
|
160
|
-
|
|
161
|
-
#insertENCODINGtoken() {
|
|
162
|
-
let lineBuilder = [];
|
|
163
|
-
let encodingName = "";
|
|
164
|
-
let lineCount = 0;
|
|
165
|
-
const ws_commentPattern = /^[ \t\f]*(#.*)?$/;
|
|
166
|
-
const inputStream = this.inputStream;
|
|
167
|
-
const size = inputStream.size;
|
|
168
|
-
|
|
169
|
-
inputStream.seek(0);
|
|
170
|
-
for (let i = 0; i < size; i++) {
|
|
171
|
-
let c = String.fromCharCode(inputStream.LA(i + 1));
|
|
172
|
-
lineBuilder.push(c);
|
|
173
|
-
|
|
174
|
-
if (c == '\n' || i == size - 1) {
|
|
175
|
-
let line = lineBuilder.join("").replace("\r", "").replace("\n", "");
|
|
176
|
-
if (ws_commentPattern.test(line)) { // WS* + COMMENT? found
|
|
177
|
-
encodingName = this.#getEncodingName(line);
|
|
178
|
-
if (encodingName !== "") {
|
|
179
|
-
break; // encoding found
|
|
180
|
-
}
|
|
181
|
-
} else {
|
|
182
|
-
break; // statement or backslash found (line is not empty, not whitespace, not comment)
|
|
183
|
-
}
|
|
184
|
-
|
|
185
|
-
lineCount++;
|
|
186
|
-
if (lineCount >= 2) {
|
|
187
|
-
break; // check only the first two lines
|
|
188
|
-
}
|
|
189
|
-
lineBuilder = [];
|
|
190
|
-
}
|
|
191
|
-
}
|
|
192
|
-
|
|
193
|
-
if (encodingName === "") {
|
|
194
|
-
encodingName = "utf-8"; // default Python source code encoding
|
|
195
|
-
}
|
|
196
|
-
|
|
197
|
-
const encodingToken = new CommonToken([null, null], PythonLexer.ENCODING, Token.HIDDEN_CHANNEL, 0, 0);
|
|
198
|
-
encodingToken.text = encodingName;
|
|
199
|
-
encodingToken.line = 0;
|
|
200
|
-
encodingToken.column = -1;
|
|
201
|
-
this.#addPendingToken(encodingToken);
|
|
202
|
-
}
|
|
203
|
-
|
|
204
|
-
#getEncodingName(commentText) { // https://peps.python.org/pep-0263/#defining-the-encoding
|
|
205
|
-
const encodingCommentPattern = /^[ \t\f]*#.*?coding[:=][ \t]*([-_.a-zA-Z0-9]+)/;
|
|
206
|
-
const match = commentText.match(encodingCommentPattern);
|
|
207
|
-
return match ? match[1] : "";
|
|
208
|
-
}
|
|
209
|
-
|
|
210
|
-
// initialize the _indentLengthStack
|
|
211
|
-
// hide the leading NEWLINE token(s)
|
|
212
|
-
// if exists, find the first statement (not NEWLINE, not EOF token) that comes from the default channel
|
|
213
|
-
// insert a leading INDENT token if necessary
|
|
214
|
-
#handleStartOfInput() {
|
|
215
|
-
// initialize the stack with a default 0 indentation length
|
|
216
|
-
this.indentLengthStack.push(0); // this will never be popped off
|
|
217
|
-
while (this.curToken.type !== Token.EOF) {
|
|
218
|
-
if (this.curToken.channel === Token.DEFAULT_CHANNEL) {
|
|
219
|
-
if (this.curToken.type === PythonLexer.NEWLINE) {
|
|
220
|
-
// all the NEWLINE tokens must be ignored before the first statement
|
|
221
|
-
this.#hideAndAddPendingToken(this.curToken);
|
|
222
|
-
} else { // We're at the first statement
|
|
223
|
-
this.#insertLeadingIndentToken();
|
|
224
|
-
return; // continue the processing of the current token with #checkNextToken()
|
|
225
|
-
}
|
|
226
|
-
} else {
|
|
227
|
-
this.#addPendingToken(this.curToken); // it can be WS, EXPLICIT_LINE_JOINING or COMMENT token
|
|
228
|
-
}
|
|
229
|
-
this.#setCurrentAndFollowingTokens();
|
|
230
|
-
} // continue the processing of the EOF token with #checkNextToken()
|
|
231
|
-
}
|
|
232
|
-
|
|
233
|
-
#insertLeadingIndentToken() {
|
|
234
|
-
if (this.previousPendingTokenType === PythonLexer.WS) {
|
|
235
|
-
const prevToken = this.pendingTokens.at(- 1); /* stack peekLast() */ // WS token
|
|
236
|
-
if (this.#getIndentationLength(prevToken.text) !== 0) { // there is an "indentation" before the first statement
|
|
237
|
-
const errMsg = "first statement indented";
|
|
238
|
-
this.#reportLexerError(errMsg);
|
|
239
|
-
// insert an INDENT token before the first statement to raise an 'unexpected indent' error later by the parser
|
|
240
|
-
this.#createAndAddPendingToken(PythonLexer.INDENT, Token.DEFAULT_CHANNEL, this.#ERR_TXT + errMsg, this.curToken);
|
|
241
|
-
}
|
|
242
|
-
}
|
|
243
|
-
}
|
|
244
|
-
|
|
245
|
-
#handleNEWLINEtoken() {
|
|
246
|
-
if (this.lexerModeStack.length > 0) {
|
|
247
|
-
this.#addPendingToken(this.curToken);
|
|
248
|
-
} else if (this.opened > 0) { // We're in an implicit line joining, ignore the current NEWLINE token
|
|
249
|
-
this.#hideAndAddPendingToken(this.curToken);
|
|
250
|
-
} else {
|
|
251
|
-
const nlToken = this.curToken.clone(); // save the current NEWLINE token
|
|
252
|
-
const isLookingAhead = this.ffgToken.type === PythonLexer.WS;
|
|
253
|
-
if (isLookingAhead) {
|
|
254
|
-
this.#setCurrentAndFollowingTokens(); // set the next two tokens
|
|
255
|
-
}
|
|
256
|
-
|
|
257
|
-
switch (this.ffgToken.type) {
|
|
258
|
-
case PythonLexer.NEWLINE: // We're before a blank line
|
|
259
|
-
case PythonLexer.COMMENT: // We're before a comment
|
|
260
|
-
this.#hideAndAddPendingToken(nlToken);
|
|
261
|
-
if (isLookingAhead) {
|
|
262
|
-
this.#addPendingToken(this.curToken); // WS token
|
|
263
|
-
}
|
|
264
|
-
break;
|
|
265
|
-
default:
|
|
266
|
-
this.#addPendingToken(nlToken);
|
|
267
|
-
if (isLookingAhead) { // We're on a whitespace(s) followed by a statement
|
|
268
|
-
const indentationLength = this.ffgToken.type === Token.EOF ?
|
|
269
|
-
0 :
|
|
270
|
-
this.#getIndentationLength(this.curToken.text);
|
|
271
|
-
|
|
272
|
-
if (indentationLength !== this.#INVALID_LENGTH) {
|
|
273
|
-
this.#addPendingToken(this.curToken); // WS token
|
|
274
|
-
this.#insertIndentOrDedentToken(indentationLength); // may insert INDENT token or DEDENT token(s)
|
|
275
|
-
} else {
|
|
276
|
-
this.#reportError("inconsistent use of tabs and spaces in indentation");
|
|
277
|
-
}
|
|
278
|
-
} else { // We're at a newline followed by a statement (there is no whitespace before the statement)
|
|
279
|
-
this.#insertIndentOrDedentToken(0); // may insert DEDENT token(s)
|
|
280
|
-
}
|
|
281
|
-
}
|
|
282
|
-
}
|
|
283
|
-
}
|
|
284
|
-
|
|
285
|
-
#insertIndentOrDedentToken(curIndentLength) {
|
|
286
|
-
let prevIndentLength = this.indentLengthStack.at(-1) /* peek() */;
|
|
287
|
-
if (curIndentLength > prevIndentLength) {
|
|
288
|
-
this.#createAndAddPendingToken(PythonLexer.INDENT, Token.DEFAULT_CHANNEL, null, this.ffgToken);
|
|
289
|
-
this.indentLengthStack.push(curIndentLength);
|
|
290
|
-
} else {
|
|
291
|
-
while (curIndentLength < prevIndentLength) { // more than 1 DEDENT token may be inserted to the token stream
|
|
292
|
-
this.indentLengthStack.pop();
|
|
293
|
-
prevIndentLength = this.indentLengthStack.at(-1) /* peek() */;
|
|
294
|
-
if (curIndentLength <= prevIndentLength) {
|
|
295
|
-
this.#createAndAddPendingToken(PythonLexer.DEDENT, Token.DEFAULT_CHANNEL, null, this.ffgToken);
|
|
296
|
-
} else {
|
|
297
|
-
this.#reportError("inconsistent dedent");
|
|
298
|
-
}
|
|
299
|
-
}
|
|
300
|
-
}
|
|
301
|
-
}
|
|
302
|
-
|
|
303
|
-
#checkCurToken() {
|
|
304
|
-
switch (this.curToken.type) {
|
|
305
|
-
case PythonLexer.FSTRING_START:
|
|
306
|
-
this.#setLexerModeByFSTRING_STARTtoken();
|
|
307
|
-
return;
|
|
308
|
-
case PythonLexer.FSTRING_MIDDLE:
|
|
309
|
-
this.#handleFSTRING_MIDDLEtokenWithQuoteAndLBrace(); // affect the opened field
|
|
310
|
-
if (this.curToken.type === PythonLexer.FSTRING_MIDDLE) {
|
|
311
|
-
return; // No curToken exchange happened
|
|
312
|
-
}
|
|
313
|
-
break;
|
|
314
|
-
case PythonLexer.FSTRING_END:
|
|
315
|
-
this.#popLexerMode();
|
|
316
|
-
return;
|
|
317
|
-
default:
|
|
318
|
-
if (this.lexerModeStack.length === 0) {
|
|
319
|
-
return; // Not in fstring mode
|
|
320
|
-
}
|
|
321
|
-
}
|
|
322
|
-
|
|
323
|
-
switch (this.curToken.type) { // the following tokens can only come from default mode (after an LBRACE in fstring)
|
|
324
|
-
case PythonLexer.NEWLINE:
|
|
325
|
-
// append the current brace expression with the current newline
|
|
326
|
-
this.#appendToBraceExpression(this.curToken.text)
|
|
327
|
-
this.curToken.channel = Token.HIDDEN_CHANNEL;
|
|
328
|
-
break;
|
|
329
|
-
case PythonLexer.LBRACE:
|
|
330
|
-
// the outermost brace expression cannot be a dictionary comprehension or a set comprehension
|
|
331
|
-
this.braceExpressionStack.push("{");
|
|
332
|
-
this.paren_or_bracket_openedStack.push(0);
|
|
333
|
-
this.#pushLexerMode(Lexer.DEFAULT_MODE);
|
|
334
|
-
break;
|
|
335
|
-
case PythonLexer.LPAR:
|
|
336
|
-
case PythonLexer.LSQB:
|
|
337
|
-
// append the current brace expression with a "(" or a "["
|
|
338
|
-
this.#appendToBraceExpression(this.curToken.text)
|
|
339
|
-
// https://peps.python.org/pep-0498/#lambdas-inside-expressions
|
|
340
|
-
this.#incrementBraceStack();
|
|
341
|
-
break;
|
|
342
|
-
case PythonLexer.RPAR:
|
|
343
|
-
case PythonLexer.RSQB:
|
|
344
|
-
// append the current brace expression with a ")" or a "]"
|
|
345
|
-
this.#appendToBraceExpression(this.curToken.text)
|
|
346
|
-
this.#decrementBraceStack();
|
|
347
|
-
break;
|
|
348
|
-
case PythonLexer.COLON:
|
|
349
|
-
case PythonLexer.COLONEQUAL:
|
|
350
|
-
// append the current brace expression with a ":" or a ":="
|
|
351
|
-
this.#appendToBraceExpression(this.curToken.text)
|
|
352
|
-
this.#setLexerModeByCOLONorCOLONEQUALtoken();
|
|
353
|
-
break;
|
|
354
|
-
case PythonLexer.RBRACE:
|
|
355
|
-
this.#setLexerModeAfterRBRACEtoken();
|
|
356
|
-
break;
|
|
357
|
-
default:
|
|
358
|
-
// append the current brace expression with the current token text
|
|
359
|
-
this.#appendToBraceExpression(this.curToken.text)
|
|
360
|
-
}
|
|
361
|
-
}
|
|
362
|
-
|
|
363
|
-
#appendToBraceExpression(text) {
|
|
364
|
-
this.braceExpressionStack[this.braceExpressionStack.length - 1] += text;
|
|
365
|
-
}
|
|
366
|
-
|
|
367
|
-
#incrementBraceStack() { // increment the last element (peek() + 1)
|
|
368
|
-
this.paren_or_bracket_openedStack[this.paren_or_bracket_openedStack.length - 1]++;
|
|
369
|
-
}
|
|
370
|
-
|
|
371
|
-
#decrementBraceStack() { // decrement the last element (peek() - 1)
|
|
372
|
-
this.paren_or_bracket_openedStack[this.paren_or_bracket_openedStack.length - 1]--;
|
|
373
|
-
}
|
|
374
|
-
|
|
375
|
-
#setLexerModeAfterRBRACEtoken() {
|
|
376
|
-
switch (this.curLexerMode) {
|
|
377
|
-
case Lexer.DEFAULT_MODE:
|
|
378
|
-
this.#popLexerMode();
|
|
379
|
-
this.#popByBRACE();
|
|
380
|
-
break;
|
|
381
|
-
case PythonLexer.SQ1__FORMAT_SPECIFICATION_MODE:
|
|
382
|
-
case PythonLexer.SQ1R_FORMAT_SPECIFICATION_MODE:
|
|
383
|
-
case PythonLexer.DQ1__FORMAT_SPECIFICATION_MODE:
|
|
384
|
-
case PythonLexer.DQ1R_FORMAT_SPECIFICATION_MODE:
|
|
385
|
-
case PythonLexer.SQ3__FORMAT_SPECIFICATION_MODE:
|
|
386
|
-
case PythonLexer.SQ3R_FORMAT_SPECIFICATION_MODE:
|
|
387
|
-
case PythonLexer.DQ3__FORMAT_SPECIFICATION_MODE:
|
|
388
|
-
case PythonLexer.DQ3R_FORMAT_SPECIFICATION_MODE:
|
|
389
|
-
this.#popLexerMode();
|
|
390
|
-
this.#popLexerMode();
|
|
391
|
-
this.#popByBRACE();
|
|
392
|
-
break;
|
|
393
|
-
default:
|
|
394
|
-
this.#reportLexerError("f-string: single '}' is not allowed");
|
|
395
|
-
}
|
|
396
|
-
}
|
|
397
|
-
|
|
398
|
-
#setLexerModeByFSTRING_STARTtoken() {
|
|
399
|
-
const text = this.curToken.text.toLowerCase();
|
|
400
|
-
const modeMap = {
|
|
401
|
-
"f'": PythonLexer.SQ1__FSTRING_MODE,
|
|
402
|
-
"rf'": PythonLexer.SQ1R_FSTRING_MODE,
|
|
403
|
-
"fr'": PythonLexer.SQ1R_FSTRING_MODE,
|
|
404
|
-
'f"': PythonLexer.DQ1__FSTRING_MODE,
|
|
405
|
-
'rf"': PythonLexer.DQ1R_FSTRING_MODE,
|
|
406
|
-
'fr"': PythonLexer.DQ1R_FSTRING_MODE,
|
|
407
|
-
"f'''": PythonLexer.SQ3__FSTRING_MODE,
|
|
408
|
-
"rf'''": PythonLexer.SQ3R_FSTRING_MODE,
|
|
409
|
-
"fr'''": PythonLexer.SQ3R_FSTRING_MODE,
|
|
410
|
-
'f"""': PythonLexer.DQ3__FSTRING_MODE,
|
|
411
|
-
'rf"""': PythonLexer.DQ3R_FSTRING_MODE,
|
|
412
|
-
'fr"""': PythonLexer.DQ3R_FSTRING_MODE,
|
|
413
|
-
};
|
|
414
|
-
const mode = modeMap[text];
|
|
415
|
-
if (mode !== undefined) {
|
|
416
|
-
this.#pushLexerMode(mode);
|
|
417
|
-
}
|
|
418
|
-
}
|
|
419
|
-
|
|
420
|
-
#setLexerModeByCOLONorCOLONEQUALtoken() {
|
|
421
|
-
if (this.paren_or_bracket_openedStack[this.paren_or_bracket_openedStack.length - 1] === 0) { // stack peek == 0
|
|
422
|
-
const previousMode = this.lexerModeStack[this.lexerModeStack.length - 1]; // stack peek
|
|
423
|
-
switch (previousMode) { // check the previous lexer mode (the current is DEFAULT_MODE)
|
|
424
|
-
case PythonLexer.SQ1__FSTRING_MODE:
|
|
425
|
-
case PythonLexer.SQ1__FORMAT_SPECIFICATION_MODE:
|
|
426
|
-
this.#pushLexerMode(PythonLexer.SQ1__FORMAT_SPECIFICATION_MODE); // continue in format spec. mode
|
|
427
|
-
break;
|
|
428
|
-
case PythonLexer.SQ1R_FSTRING_MODE:
|
|
429
|
-
case PythonLexer.SQ1R_FORMAT_SPECIFICATION_MODE:
|
|
430
|
-
this.#pushLexerMode(PythonLexer.SQ1R_FORMAT_SPECIFICATION_MODE); // continue in format spec. mode
|
|
431
|
-
break;
|
|
432
|
-
case PythonLexer.DQ1__FSTRING_MODE:
|
|
433
|
-
case PythonLexer.DQ1__FORMAT_SPECIFICATION_MODE:
|
|
434
|
-
this.#pushLexerMode(PythonLexer.DQ1__FORMAT_SPECIFICATION_MODE); // continue in format spec. mode
|
|
435
|
-
break;
|
|
436
|
-
case PythonLexer.DQ1R_FSTRING_MODE:
|
|
437
|
-
case PythonLexer.DQ1R_FORMAT_SPECIFICATION_MODE:
|
|
438
|
-
this.#pushLexerMode(PythonLexer.DQ1R_FORMAT_SPECIFICATION_MODE); // continue in format spec. mode
|
|
439
|
-
break;
|
|
440
|
-
case PythonLexer.SQ3__FSTRING_MODE:
|
|
441
|
-
case PythonLexer.SQ3__FORMAT_SPECIFICATION_MODE:
|
|
442
|
-
this.#pushLexerMode(PythonLexer.SQ3__FORMAT_SPECIFICATION_MODE); // continue in format spec. mode
|
|
443
|
-
break;
|
|
444
|
-
case PythonLexer.SQ3R_FSTRING_MODE:
|
|
445
|
-
case PythonLexer.SQ3R_FORMAT_SPECIFICATION_MODE:
|
|
446
|
-
this.#pushLexerMode(PythonLexer.SQ3R_FORMAT_SPECIFICATION_MODE); // continue in format spec. mode
|
|
447
|
-
break;
|
|
448
|
-
case PythonLexer.DQ3__FSTRING_MODE:
|
|
449
|
-
case PythonLexer.DQ3__FORMAT_SPECIFICATION_MODE:
|
|
450
|
-
this.#pushLexerMode(PythonLexer.DQ3__FORMAT_SPECIFICATION_MODE); // continue in format spec. mode
|
|
451
|
-
break;
|
|
452
|
-
case PythonLexer.DQ3R_FSTRING_MODE:
|
|
453
|
-
case PythonLexer.DQ3R_FORMAT_SPECIFICATION_MODE:
|
|
454
|
-
this.#pushLexerMode(PythonLexer.DQ3R_FORMAT_SPECIFICATION_MODE); // continue in format spec. mode
|
|
455
|
-
break;
|
|
456
|
-
}
|
|
457
|
-
}
|
|
458
|
-
}
|
|
459
|
-
|
|
460
|
-
#popByBRACE() {
|
|
461
|
-
this.paren_or_bracket_openedStack.pop();
|
|
462
|
-
this.prevBraceExpression = this.braceExpressionStack.pop() + "}";
|
|
463
|
-
if (this.braceExpressionStack.length > 0) {
|
|
464
|
-
// append the current brace expression with the previous brace expression
|
|
465
|
-
this.braceExpressionStack[this.braceExpressionStack.length - 1] += this.prevBraceExpression;
|
|
466
|
-
}
|
|
467
|
-
}
|
|
468
|
-
|
|
469
|
-
#handleFSTRING_MIDDLEtokenWithDoubleBrace() {
|
|
470
|
-
// replace the trailing double brace with a single brace and insert a hidden brace token
|
|
471
|
-
switch (this.#getLastTwoCharsOfTheCurTokenText()) {
|
|
472
|
-
case "{{":
|
|
473
|
-
this.#trimLastCharAddPendingTokenSetCurToken(PythonLexer.LBRACE, "{", Token.HIDDEN_CHANNEL);
|
|
474
|
-
break;
|
|
475
|
-
case "}}":
|
|
476
|
-
this.#trimLastCharAddPendingTokenSetCurToken(PythonLexer.RBRACE, "}", Token.HIDDEN_CHANNEL);
|
|
477
|
-
break;
|
|
478
|
-
}
|
|
479
|
-
}
|
|
480
|
-
|
|
481
|
-
#handleFSTRING_MIDDLEtokenWithQuoteAndLBrace() {
|
|
482
|
-
// replace the trailing quote + left_brace with a quote and insert an LBRACE token
|
|
483
|
-
// replace the trailing backslash + left_brace with a backslash and insert an LBRACE token
|
|
484
|
-
switch (this.#getLastTwoCharsOfTheCurTokenText()) {
|
|
485
|
-
case "\"{":
|
|
486
|
-
case "'{":
|
|
487
|
-
case "\\{":
|
|
488
|
-
this.#trimLastCharAddPendingTokenSetCurToken(PythonLexer.LBRACE, "{", Token.DEFAULT_CHANNEL);
|
|
489
|
-
break;
|
|
490
|
-
}
|
|
491
|
-
}
|
|
492
|
-
|
|
493
|
-
#getLastTwoCharsOfTheCurTokenText() {
|
|
494
|
-
return this.curToken.text.slice(-2);
|
|
495
|
-
}
|
|
496
|
-
|
|
497
|
-
#trimLastCharAddPendingTokenSetCurToken(type, text, channel) {
|
|
498
|
-
// trim the last char and add the modified curToken to the pendingTokens stack
|
|
499
|
-
const tokenTextWithoutLastChar = this.curToken.text.slice(0, -1);
|
|
500
|
-
this.curToken.text = tokenTextWithoutLastChar;
|
|
501
|
-
this.curToken.stop -= 1;
|
|
502
|
-
this.#addPendingToken(this.curToken);
|
|
503
|
-
|
|
504
|
-
this.#createNewCurToken(type, text, channel); // set curToken
|
|
505
|
-
}
|
|
506
|
-
|
|
507
|
-
#handleCOLONEQUALtokenInFString() {
|
|
508
|
-
if (this.lexerModeStack.length > 0 &&
|
|
509
|
-
this.paren_or_bracket_openedStack[this.paren_or_bracket_openedStack.length - 1] === 0) { // stack peek == 0
|
|
510
|
-
|
|
511
|
-
// In fstring a colonequal (walrus operator) can only be used in parentheses
|
|
512
|
-
// Not in parentheses, replace COLONEQUAL token with COLON as format specifier
|
|
513
|
-
// and insert the equal symbol to the following FSTRING_MIDDLE token
|
|
514
|
-
this.curToken.type = PythonLexer.COLON;
|
|
515
|
-
this.curToken.text = ":";
|
|
516
|
-
this.curToken.stop = this.curToken.start;
|
|
517
|
-
|
|
518
|
-
if (this.ffgToken.type === PythonLexer.FSTRING_MIDDLE) {
|
|
519
|
-
this.ffgToken.text = "=" + this.ffgToken.text;
|
|
520
|
-
this.ffgToken.start -= 1;
|
|
521
|
-
this.ffgToken.column -= 1;
|
|
522
|
-
} else {
|
|
523
|
-
this.#addPendingToken(this.curToken);
|
|
524
|
-
this.#createNewCurToken(PythonLexer.FSTRING_MIDDLE, "=", Token.DEFAULT_CHANNEL);
|
|
525
|
-
}
|
|
526
|
-
}
|
|
527
|
-
this.#addPendingToken(this.curToken);
|
|
528
|
-
}
|
|
529
|
-
|
|
530
|
-
#createNewCurToken(type, text, channel) {
|
|
531
|
-
const ctkn = this.curToken.clone();
|
|
532
|
-
ctkn.type = type;
|
|
533
|
-
ctkn.text = text;
|
|
534
|
-
ctkn.channel = channel;
|
|
535
|
-
ctkn.column += 1;
|
|
536
|
-
ctkn.start += 1;
|
|
537
|
-
ctkn.stop = ctkn.start;
|
|
538
|
-
this.curToken = ctkn;
|
|
539
|
-
}
|
|
540
|
-
|
|
541
|
-
#pushLexerMode(mode) {
|
|
542
|
-
this.pushMode(mode);
|
|
543
|
-
this.lexerModeStack.push(this.curLexerMode);
|
|
544
|
-
this.curLexerMode = mode;
|
|
545
|
-
}
|
|
546
|
-
|
|
547
|
-
#popLexerMode() {
|
|
548
|
-
this.popMode();
|
|
549
|
-
this.curLexerMode = this.lexerModeStack.pop();
|
|
550
|
-
}
|
|
551
|
-
|
|
552
|
-
#handleFORMAT_SPECIFICATION_MODE() {
|
|
553
|
-
if (this.lexerModeStack.length > 0 &&
|
|
554
|
-
this.ffgToken.type === PythonLexer.RBRACE) {
|
|
555
|
-
|
|
556
|
-
// insert an empty FSTRING_MIDDLE token instead of the missing format specification
|
|
557
|
-
switch (this.curToken.type) {
|
|
558
|
-
case PythonLexer.COLON:
|
|
559
|
-
this.#createAndAddPendingToken(PythonLexer.FSTRING_MIDDLE, Token.DEFAULT_CHANNEL, "", this.ffgToken);
|
|
560
|
-
break;
|
|
561
|
-
case PythonLexer.RBRACE:
|
|
562
|
-
// only if the previous brace expression is not a dictionary comprehension or set comprehension
|
|
563
|
-
if (!this.#isDictionaryComprehensionOrSetComprehension(this.prevBraceExpression)) {
|
|
564
|
-
this.#createAndAddPendingToken(PythonLexer.FSTRING_MIDDLE, Token.DEFAULT_CHANNEL, "", this.ffgToken);
|
|
565
|
-
}
|
|
566
|
-
break;
|
|
567
|
-
}
|
|
568
|
-
}
|
|
569
|
-
}
|
|
570
|
-
|
|
571
|
-
#isDictionaryComprehensionOrSetComprehension(code) {
|
|
572
|
-
const inputStream = CharStreams.fromString(code);
|
|
573
|
-
const lexer = new PythonLexer(inputStream);
|
|
574
|
-
const tokenStream = new CommonTokenStream(lexer);
|
|
575
|
-
let parser = new PythonParser(tokenStream);
|
|
576
|
-
|
|
577
|
-
// Disable error listeners to suppress console output
|
|
578
|
-
lexer.removeErrorListeners();
|
|
579
|
-
parser.removeErrorListeners();
|
|
580
|
-
|
|
581
|
-
parser.dictcomp(); // Try parsing as dictionary comprehension
|
|
582
|
-
if (parser.syntaxErrorsCount === 0)
|
|
583
|
-
return true;
|
|
584
|
-
|
|
585
|
-
parser = new PythonParser(tokenStream);
|
|
586
|
-
tokenStream.seek(0);
|
|
587
|
-
parser.removeErrorListeners();
|
|
588
|
-
parser.setcomp(); // Try parsing as set comprehension
|
|
589
|
-
return parser.syntaxErrorsCount === 0;
|
|
590
|
-
}
|
|
591
|
-
|
|
592
|
-
#insertTrailingTokens() {
|
|
593
|
-
switch (this.lastPendingTokenTypeFromDefaultChannel) {
|
|
594
|
-
case PythonLexer.NEWLINE:
|
|
595
|
-
case PythonLexer.DEDENT:
|
|
596
|
-
break; // no trailing NEWLINE token is needed
|
|
597
|
-
default:
|
|
598
|
-
// insert an extra trailing NEWLINE token that serves as the end of the last statement
|
|
599
|
-
this.#createAndAddPendingToken(PythonLexer.NEWLINE, Token.DEFAULT_CHANNEL, null, this.ffgToken); // _ffgToken is EOF
|
|
600
|
-
}
|
|
601
|
-
this.#insertIndentOrDedentToken(0); // Now insert as much trailing DEDENT tokens as needed
|
|
602
|
-
}
|
|
603
|
-
|
|
604
|
-
#handleEOFtoken() {
|
|
605
|
-
if (this.lastPendingTokenTypeFromDefaultChannel > 0) {
|
|
606
|
-
// there was a statement in the input (leading NEWLINE tokens are hidden)
|
|
607
|
-
this.#insertTrailingTokens();
|
|
608
|
-
}
|
|
609
|
-
this.#addPendingToken(this.curToken);
|
|
610
|
-
}
|
|
611
|
-
|
|
612
|
-
#hideAndAddPendingToken(ctkn) {
|
|
613
|
-
ctkn.channel = Token.HIDDEN_CHANNEL;
|
|
614
|
-
this.#addPendingToken(ctkn);
|
|
615
|
-
}
|
|
616
|
-
|
|
617
|
-
#createAndAddPendingToken(type, channel, text, sampleToken) {
|
|
618
|
-
const ctkn = sampleToken.clone();
|
|
619
|
-
ctkn.type = type;
|
|
620
|
-
ctkn.channel = channel;
|
|
621
|
-
ctkn.stop = sampleToken.start - 1;
|
|
622
|
-
ctkn.text = text == null ?
|
|
623
|
-
`<${this.getSymbolicNames()[type]}>` :
|
|
624
|
-
text;
|
|
625
|
-
|
|
626
|
-
this.#addPendingToken(ctkn);
|
|
627
|
-
}
|
|
628
|
-
|
|
629
|
-
#addPendingToken(tkn) {
|
|
630
|
-
// save the last pending token type because the _pendingTokens linked list can be empty by the nextToken()
|
|
631
|
-
this.previousPendingTokenType = tkn.type;
|
|
632
|
-
if (tkn.channel === Token.DEFAULT_CHANNEL) {
|
|
633
|
-
this.lastPendingTokenTypeFromDefaultChannel = this.previousPendingTokenType;
|
|
634
|
-
}
|
|
635
|
-
this.pendingTokens.push(tkn) /* .addLast(token) */;
|
|
636
|
-
}
|
|
637
|
-
|
|
638
|
-
#getIndentationLength(indentText) { // the indentText may contain spaces, tabs or form feeds
|
|
639
|
-
const TAB_LENGTH = 8; // the standard number of spaces to replace a tab to spaces
|
|
640
|
-
let length = 0;
|
|
641
|
-
for (let ch of indentText) {
|
|
642
|
-
switch (ch) {
|
|
643
|
-
case " ":
|
|
644
|
-
this.wasSpaceIndentation = true;
|
|
645
|
-
length += 1;
|
|
646
|
-
break;
|
|
647
|
-
case "\t":
|
|
648
|
-
this.wasTabIndentation = true;
|
|
649
|
-
length += TAB_LENGTH - (length % TAB_LENGTH);
|
|
650
|
-
break;
|
|
651
|
-
case "\f": // form feed
|
|
652
|
-
length = 0;
|
|
653
|
-
break;
|
|
654
|
-
}
|
|
655
|
-
}
|
|
656
|
-
|
|
657
|
-
if (this.wasTabIndentation && this.wasSpaceIndentation) {
|
|
658
|
-
if (!this.wasIndentationMixedWithSpacesAndTabs) {
|
|
659
|
-
this.wasIndentationMixedWithSpacesAndTabs = true;
|
|
660
|
-
length = this.#INVALID_LENGTH; // only for the first inconsistent indent
|
|
661
|
-
}
|
|
662
|
-
}
|
|
663
|
-
return length;
|
|
664
|
-
}
|
|
665
|
-
|
|
666
|
-
#reportLexerError(errMsg) {
|
|
667
|
-
this.getErrorListener().syntaxError(this, this.curToken, this.curToken.line, this.curToken.column, " LEXER" + this.#ERR_TXT + errMsg, null);
|
|
668
|
-
}
|
|
669
|
-
|
|
670
|
-
#reportError(errMsg) {
|
|
671
|
-
this.#reportLexerError(errMsg);
|
|
672
|
-
|
|
673
|
-
// the ERRORTOKEN will raise an error in the parser
|
|
674
|
-
this.#createAndAddPendingToken(PythonLexer.ERRORTOKEN, Token.DEFAULT_CHANNEL, this.#ERR_TXT + errMsg, this.ffgToken);
|
|
675
|
-
}
|
|
676
|
-
}
|