File: regexp-lexer.js

package info (click to toggle)
node-jison-lex 0.3.4-3
  • links: PTS, VCS
  • area: main
  • in suites: buster, sid
  • size: 192 kB
  • sloc: makefile: 9; sh: 2
file content (603 lines) | stat: -rw-r--r-- 20,169 bytes parent folder | download | duplicates (2)
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
// Basic Lexer implemented using JavaScript regular expressions
// MIT Licensed

"use strict";

var lexParser = require('lex-parser');
var version = require('./package.json').version;

// expand macros and convert matchers to RegExp's
function prepareRules(rules, macros, actions, tokens, startConditions, caseless) {
    var m,i,k,action,conditions,
        newRules = [];

    if (macros) {
        macros = prepareMacros(macros);
    }

    function tokenNumberReplacement (str, token) {
        return "return " + (tokens[token] || "'" + token + "'");
    }

    actions.push('switch($avoiding_name_collisions) {');

    for (i=0;i < rules.length; i++) {
        if (Object.prototype.toString.apply(rules[i][0]) !== '[object Array]') {
            // implicit add to all inclusive start conditions
            for (k in startConditions) {
                if (startConditions[k].inclusive) {
                    startConditions[k].rules.push(i);
                }
            }
        } else if (rules[i][0][0] === '*') {
            // Add to ALL start conditions
            for (k in startConditions) {
                startConditions[k].rules.push(i);
            }
            rules[i].shift();
        } else {
            // Add to explicit start conditions
            conditions = rules[i].shift();
            for (k=0;k<conditions.length;k++) {
                startConditions[conditions[k]].rules.push(i);
            }
        }

        m = rules[i][0];
        if (typeof m === 'string') {
            for (k in macros) {
                if (macros.hasOwnProperty(k)) {
                    m = m.split("{" + k + "}").join('(' + macros[k] + ')');
                }
            }
            m = new RegExp("^(?:" + m + ")", caseless ? 'i':'');
        }
        newRules.push(m);
        if (typeof rules[i][1] === 'function') {
            rules[i][1] = String(rules[i][1]).replace(/^\s*function \(\)\s?\{/, '').replace(/\}\s*$/, '');
        }
        action = rules[i][1];
        if (tokens && action.match(/return '[^']+'/)) {
            action = action.replace(/return '([^']+)'/g, tokenNumberReplacement);
        }
        actions.push('case ' + i + ':' + action + '\nbreak;');
    }
    actions.push("}");

    return newRules;
}

// expand macros within macros
function prepareMacros (macros) {
    var cont = true,
        m,i,k,mnew;
    while (cont) {
        cont = false;
        for (i in macros) if (macros.hasOwnProperty(i)) {
            m = macros[i];
            for (k in macros) if (macros.hasOwnProperty(k) && i !== k) {
                mnew = m.split("{" + k + "}").join('(' + macros[k] + ')');
                if (mnew !== m) {
                    cont = true;
                    macros[i] = mnew;
                }
            }
        }
    }
    return macros;
}

function prepareStartConditions (conditions) {
    var sc,
        hash = {};
    for (sc in conditions) if (conditions.hasOwnProperty(sc)) {
        hash[sc] = {rules:[],inclusive:!!!conditions[sc]};
    }
    return hash;
}

function buildActions (dict, tokens) {
    var actions = [dict.actionInclude || '', "var YYSTATE=YY_START;"];
    var tok;
    var toks = {};

    for (tok in tokens) {
        toks[tokens[tok]] = tok;
    }

    if (dict.options && dict.options.flex) {
        dict.rules.push([".", "console.log(yytext);"]);
    }

    this.rules = prepareRules(dict.rules, dict.macros, actions, tokens && toks, this.conditions, this.options["case-insensitive"]);
    var fun = actions.join("\n");
    "yytext yyleng yylineno yylloc".split(' ').forEach(function (yy) {
        fun = fun.replace(new RegExp("\\b(" + yy + ")\\b", "g"), "yy_.$1");
    });

    return "function anonymous(yy,yy_,$avoiding_name_collisions,YY_START) {" + fun + "\n}";
}

function RegExpLexer (dict, input, tokens) {
    var opts = processGrammar(dict, tokens);
    var source = generateModuleBody(opts);
    var lexer = eval(source);

    lexer.yy = {};
    if (input) {
        lexer.setInput(input);
    }

    lexer.generate = function () { return generateFromOpts(opts); };
    lexer.generateModule = function () { return generateModule(opts); };
    lexer.generateCommonJSModule = function () { return generateCommonJSModule(opts); };
    lexer.generateAMDModule = function () { return generateAMDModule(opts); };

    return lexer;
}

RegExpLexer.prototype = {
    EOF: 1,
    parseError: function parseError(str, hash) {
        if (this.yy.parser) {
            this.yy.parser.parseError(str, hash);
        } else {
            throw new Error(str);
        }
    },

    // resets the lexer, sets new input
    setInput: function (input, yy) {
        this.yy = yy || this.yy || {};
        this._input = input;
        this._more = this._backtrack = this.done = false;
        this.yylineno = this.yyleng = 0;
        this.yytext = this.matched = this.match = '';
        this.conditionStack = ['INITIAL'];
        this.yylloc = {
            first_line: 1,
            first_column: 0,
            last_line: 1,
            last_column: 0
        };
        if (this.options.ranges) {
            this.yylloc.range = [0,0];
        }
        this.offset = 0;
        return this;
    },

    // consumes and returns one char from the input
    input: function () {
        var ch = this._input[0];
        this.yytext += ch;
        this.yyleng++;
        this.offset++;
        this.match += ch;
        this.matched += ch;
        var lines = ch.match(/(?:\r\n?|\n).*/g);
        if (lines) {
            this.yylineno++;
            this.yylloc.last_line++;
        } else {
            this.yylloc.last_column++;
        }
        if (this.options.ranges) {
            this.yylloc.range[1]++;
        }

        this._input = this._input.slice(1);
        return ch;
    },

    // unshifts one char (or a string) into the input
    unput: function (ch) {
        var len = ch.length;
        var lines = ch.split(/(?:\r\n?|\n)/g);

        this._input = ch + this._input;
        this.yytext = this.yytext.substr(0, this.yytext.length - len);
        //this.yyleng -= len;
        this.offset -= len;
        var oldLines = this.match.split(/(?:\r\n?|\n)/g);
        this.match = this.match.substr(0, this.match.length - 1);
        this.matched = this.matched.substr(0, this.matched.length - 1);

        if (lines.length - 1) {
            this.yylineno -= lines.length - 1;
        }
        var r = this.yylloc.range;

        this.yylloc = {
            first_line: this.yylloc.first_line,
            last_line: this.yylineno + 1,
            first_column: this.yylloc.first_column,
            last_column: lines ?
                (lines.length === oldLines.length ? this.yylloc.first_column : 0)
                 + oldLines[oldLines.length - lines.length].length - lines[0].length :
              this.yylloc.first_column - len
        };

        if (this.options.ranges) {
            this.yylloc.range = [r[0], r[0] + this.yyleng - len];
        }
        this.yyleng = this.yytext.length;
        return this;
    },

    // When called from action, caches matched text and appends it on next action
    more: function () {
        this._more = true;
        return this;
    },

    // When called from action, signals the lexer that this rule fails to match the input, so the next matching rule (regex) should be tested instead.
    reject: function () {
        if (this.options.backtrack_lexer) {
            this._backtrack = true;
        } else {
            return this.parseError('Lexical error on line ' + (this.yylineno + 1) + '. You can only invoke reject() in the lexer when the lexer is of the backtracking persuasion (options.backtrack_lexer = true).\n' + this.showPosition(), {
                text: "",
                token: null,
                line: this.yylineno
            });

        }
        return this;
    },

    // retain first n characters of the match
    less: function (n) {
        this.unput(this.match.slice(n));
    },

    // displays already matched input, i.e. for error messages
    pastInput: function () {
        var past = this.matched.substr(0, this.matched.length - this.match.length);
        return (past.length > 20 ? '...':'') + past.substr(-20).replace(/\n/g, "");
    },

    // displays upcoming input, i.e. for error messages
    upcomingInput: function () {
        var next = this.match;
        if (next.length < 20) {
            next += this._input.substr(0, 20-next.length);
        }
        return (next.substr(0,20) + (next.length > 20 ? '...' : '')).replace(/\n/g, "");
    },

    // displays the character position where the lexing error occurred, i.e. for error messages
    showPosition: function () {
        var pre = this.pastInput();
        var c = new Array(pre.length + 1).join("-");
        return pre + this.upcomingInput() + "\n" + c + "^";
    },

    // test the lexed token: return FALSE when not a match, otherwise return token
    test_match: function(match, indexed_rule) {
        var token,
            lines,
            backup;

        if (this.options.backtrack_lexer) {
            // save context
            backup = {
                yylineno: this.yylineno,
                yylloc: {
                    first_line: this.yylloc.first_line,
                    last_line: this.last_line,
                    first_column: this.yylloc.first_column,
                    last_column: this.yylloc.last_column
                },
                yytext: this.yytext,
                match: this.match,
                matches: this.matches,
                matched: this.matched,
                yyleng: this.yyleng,
                offset: this.offset,
                _more: this._more,
                _input: this._input,
                yy: this.yy,
                conditionStack: this.conditionStack.slice(0),
                done: this.done
            };
            if (this.options.ranges) {
                backup.yylloc.range = this.yylloc.range.slice(0);
            }
        }

        lines = match[0].match(/(?:\r\n?|\n).*/g);
        if (lines) {
            this.yylineno += lines.length;
        }
        this.yylloc = {
            first_line: this.yylloc.last_line,
            last_line: this.yylineno + 1,
            first_column: this.yylloc.last_column,
            last_column: lines ?
                         lines[lines.length - 1].length - lines[lines.length - 1].match(/\r?\n?/)[0].length :
                         this.yylloc.last_column + match[0].length
        };
        this.yytext += match[0];
        this.match += match[0];
        this.matches = match;
        this.yyleng = this.yytext.length;
        if (this.options.ranges) {
            this.yylloc.range = [this.offset, this.offset += this.yyleng];
        }
        this._more = false;
        this._backtrack = false;
        this._input = this._input.slice(match[0].length);
        this.matched += match[0];
        token = this.performAction.call(this, this.yy, this, indexed_rule, this.conditionStack[this.conditionStack.length - 1]);
        if (this.done && this._input) {
            this.done = false;
        }
        if (token) {
            return token;
        } else if (this._backtrack) {
            // recover context
            for (var k in backup) {
                this[k] = backup[k];
            }
            return false; // rule action called reject() implying the next rule should be tested instead.
        }
        return false;
    },

    // return next match in input
    next: function () {
        if (this.done) {
            return this.EOF;
        }
        if (!this._input) {
            this.done = true;
        }

        var token,
            match,
            tempMatch,
            index;
        if (!this._more) {
            this.yytext = '';
            this.match = '';
        }
        var rules = this._currentRules();
        for (var i = 0; i < rules.length; i++) {
            tempMatch = this._input.match(this.rules[rules[i]]);
            if (tempMatch && (!match || tempMatch[0].length > match[0].length)) {
                match = tempMatch;
                index = i;
                if (this.options.backtrack_lexer) {
                    token = this.test_match(tempMatch, rules[i]);
                    if (token !== false) {
                        return token;
                    } else if (this._backtrack) {
                        match = false;
                        continue; // rule action called reject() implying a rule MISmatch.
                    } else {
                        // else: this is a lexer rule which consumes input without producing a token (e.g. whitespace)
                        return false;
                    }
                } else if (!this.options.flex) {
                    break;
                }
            }
        }
        if (match) {
            token = this.test_match(match, rules[index]);
            if (token !== false) {
                return token;
            }
            // else: this is a lexer rule which consumes input without producing a token (e.g. whitespace)
            return false;
        }
        if (this._input === "") {
            return this.EOF;
        } else {
            return this.parseError('Lexical error on line ' + (this.yylineno + 1) + '. Unrecognized text.\n' + this.showPosition(), {
                text: "",
                token: null,
                line: this.yylineno
            });
        }
    },

    // return next match that has a token
    lex: function lex () {
        var r = this.next();
        if (r) {
            return r;
        } else {
            return this.lex();
        }
    },

    // activates a new lexer condition state (pushes the new lexer condition state onto the condition stack)
    begin: function begin (condition) {
        this.conditionStack.push(condition);
    },

    // pop the previously active lexer condition state off the condition stack
    popState: function popState () {
        var n = this.conditionStack.length - 1;
        if (n > 0) {
            return this.conditionStack.pop();
        } else {
            return this.conditionStack[0];
        }
    },

    // produce the lexer rule set which is active for the currently active lexer condition state
    _currentRules: function _currentRules () {
        if (this.conditionStack.length && this.conditionStack[this.conditionStack.length - 1]) {
            return this.conditions[this.conditionStack[this.conditionStack.length - 1]].rules;
        } else {
            return this.conditions["INITIAL"].rules;
        }
    },

    // return the currently active lexer condition state; when an index argument is provided it produces the N-th previous condition state, if available
    topState: function topState (n) {
        n = this.conditionStack.length - 1 - Math.abs(n || 0);
        if (n >= 0) {
            return this.conditionStack[n];
        } else {
            return "INITIAL";
        }
    },

    // alias for begin(condition)
    pushState: function pushState (condition) {
        this.begin(condition);
    },

    // return the number of states pushed
    stateStackSize: function stateStackSize() {
        return this.conditionStack.length;
    }
};


// generate lexer source from a grammar
function generate (dict, tokens) {
    var opt = processGrammar(dict, tokens);

    return generateFromOpts(opt);
}

// process the grammar and build final data structures and functions
function processGrammar(dict, tokens) {
    var opts = {};
    if (typeof dict === 'string') {
        dict = lexParser.parse(dict);
    }
    dict = dict || {};

    opts.options = dict.options || {};
    opts.moduleType = opts.options.moduleType;
    opts.moduleName = opts.options.moduleName;

    opts.conditions = prepareStartConditions(dict.startConditions);
    opts.conditions.INITIAL = {rules:[],inclusive:true};

    opts.performAction = buildActions.call(opts, dict, tokens);
    opts.conditionStack = ['INITIAL'];

    opts.moduleInclude = (dict.moduleInclude || '').trim();
    return opts;
}

// Assemble the final source from the processed grammar
function generateFromOpts (opt) {
    var code = "";

    if (opt.moduleType === 'commonjs') {
        code = generateCommonJSModule(opt);
    } else if (opt.moduleType === 'amd') {
        code = generateAMDModule(opt);
    } else {
        code = generateModule(opt);
    }

    return code;
}

function generateModuleBody (opt) {
    var functionDescriptions = {
        setInput: "resets the lexer, sets new input",
        input: "consumes and returns one char from the input",
        unput: "unshifts one char (or a string) into the input",
        more: "When called from action, caches matched text and appends it on next action",
        reject: "When called from action, signals the lexer that this rule fails to match the input, so the next matching rule (regex) should be tested instead.",
        less: "retain first n characters of the match",
        pastInput: "displays already matched input, i.e. for error messages",
        upcomingInput: "displays upcoming input, i.e. for error messages",
        showPosition: "displays the character position where the lexing error occurred, i.e. for error messages",
        test_match: "test the lexed token: return FALSE when not a match, otherwise return token",
        next: "return next match in input",
        lex: "return next match that has a token",
        begin: "activates a new lexer condition state (pushes the new lexer condition state onto the condition stack)",
        popState: "pop the previously active lexer condition state off the condition stack",
        _currentRules: "produce the lexer rule set which is active for the currently active lexer condition state",
        topState: "return the currently active lexer condition state; when an index argument is provided it produces the N-th previous condition state, if available",
        pushState: "alias for begin(condition)",
        stateStackSize: "return the number of states currently on the stack"
    };
    var out = "({\n";
    var p = [];
    var descr;
    for (var k in RegExpLexer.prototype) {
        if (RegExpLexer.prototype.hasOwnProperty(k) && k.indexOf("generate") === -1) {
            // copy the function description as a comment before the implementation; supports multi-line descriptions
            descr = "\n";
            if (functionDescriptions[k]) {
                descr += "// " + functionDescriptions[k].replace(/\n/g, "\n\/\/ ") + "\n";
            }
            p.push(descr + k + ":" + (RegExpLexer.prototype[k].toString() || '""'));
        }
    }
    out += p.join(",\n");

    if (opt.options) {
        out += ",\noptions: " + JSON.stringify(opt.options);
    }

    out += ",\nperformAction: " + String(opt.performAction);
    out += ",\nrules: [" + opt.rules + "]";
    out += ",\nconditions: " + JSON.stringify(opt.conditions);
    out += "\n})";

    return out;
}

function generateModule(opt) {
    opt = opt || {};

    var out = "/* generated by jison-lex " + version + " */";
    var moduleName = opt.moduleName || "lexer";

    out += "\nvar " + moduleName + " = (function(){\nvar lexer = "
          + generateModuleBody(opt);

    if (opt.moduleInclude) {
        out += ";\n" + opt.moduleInclude;
    }

    out += ";\nreturn lexer;\n})();";

    return out;
}

function generateAMDModule(opt) {
    var out = "/* generated by jison-lex " + version + " */";

    out += "define([], function(){\nvar lexer = "
          + generateModuleBody(opt);

    if (opt.moduleInclude) {
        out += ";\n" + opt.moduleInclude;
    }

    out += ";\nreturn lexer;"
         + "\n});";

    return out;
}

function generateCommonJSModule(opt) {
    opt = opt || {};

    var out = "";
    var moduleName = opt.moduleName || "lexer";

    out += generateModule(opt);
    out += "\nexports.lexer = " + moduleName;
    out += ";\nexports.lex = function () { return " + moduleName + ".lex.apply(lexer, arguments); };";
    return out;
}

RegExpLexer.generate = generate;

module.exports = RegExpLexer;