tokenize.js
12.2 KB
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
"use strict";
module.exports = tokenize;
var delimRe = /[\s{}=;:[\],'"()<>]/g,
stringDoubleRe = /(?:"([^"\\]*(?:\\.[^"\\]*)*)")/g,
stringSingleRe = /(?:'([^'\\]*(?:\\.[^'\\]*)*)')/g;
var setCommentRe = /^ *[*/]+ */,
setCommentAltRe = /^\s*\*?\/*/,
setCommentSplitRe = /\n/g,
whitespaceRe = /\s/,
unescapeRe = /\\(.?)/g;
var unescapeMap = {
"0": "\0",
"r": "\r",
"n": "\n",
"t": "\t"
};
/**
* Unescapes a string.
* @param {string} str String to unescape
* @returns {string} Unescaped string
* @property {Object.<string,string>} map Special characters map
* @memberof tokenize
*/
function unescape(str) {
return str.replace(unescapeRe, function($0, $1) {
switch ($1) {
case "\\":
case "":
return $1;
default:
return unescapeMap[$1] || "";
}
});
}
tokenize.unescape = unescape;
/**
* Gets the next token and advances.
* @typedef TokenizerHandleNext
* @type {function}
* @returns {string|null} Next token or `null` on eof
*/
/**
* Peeks for the next token.
* @typedef TokenizerHandlePeek
* @type {function}
* @returns {string|null} Next token or `null` on eof
*/
/**
* Pushes a token back to the stack.
* @typedef TokenizerHandlePush
* @type {function}
* @param {string} token Token
* @returns {undefined}
*/
/**
* Skips the next token.
* @typedef TokenizerHandleSkip
* @type {function}
* @param {string} expected Expected token
* @param {boolean} [optional=false] If optional
* @returns {boolean} Whether the token matched
* @throws {Error} If the token didn't match and is not optional
*/
/**
* Gets the comment on the previous line or, alternatively, the line comment on the specified line.
* @typedef TokenizerHandleCmnt
* @type {function}
* @param {number} [line] Line number
* @returns {string|null} Comment text or `null` if none
*/
/**
* Handle object returned from {@link tokenize}.
* @interface ITokenizerHandle
* @property {TokenizerHandleNext} next Gets the next token and advances (`null` on eof)
* @property {TokenizerHandlePeek} peek Peeks for the next token (`null` on eof)
* @property {TokenizerHandlePush} push Pushes a token back to the stack
* @property {TokenizerHandleSkip} skip Skips a token, returns its presence and advances or, if non-optional and not present, throws
* @property {TokenizerHandleCmnt} cmnt Gets the comment on the previous line or the line comment on the specified line, if any
* @property {number} line Current line number
*/
/**
* Tokenizes the given .proto source and returns an object with useful utility functions.
* @param {string} source Source contents
* @param {boolean} alternateCommentMode Whether we should activate alternate comment parsing mode.
* @returns {ITokenizerHandle} Tokenizer handle
*/
function tokenize(source, alternateCommentMode) {
/* eslint-disable callback-return */
source = source.toString();
var offset = 0,
length = source.length,
line = 1,
commentType = null,
commentText = null,
commentLine = 0,
commentLineEmpty = false,
commentIsLeading = false;
var stack = [];
var stringDelim = null;
/* istanbul ignore next */
/**
* Creates an error for illegal syntax.
* @param {string} subject Subject
* @returns {Error} Error created
* @inner
*/
function illegal(subject) {
return Error("illegal " + subject + " (line " + line + ")");
}
/**
* Reads a string till its end.
* @returns {string} String read
* @inner
*/
function readString() {
var re = stringDelim === "'" ? stringSingleRe : stringDoubleRe;
re.lastIndex = offset - 1;
var match = re.exec(source);
if (!match)
throw illegal("string");
offset = re.lastIndex;
push(stringDelim);
stringDelim = null;
return unescape(match[1]);
}
/**
* Gets the character at `pos` within the source.
* @param {number} pos Position
* @returns {string} Character
* @inner
*/
function charAt(pos) {
return source.charAt(pos);
}
/**
* Sets the current comment text.
* @param {number} start Start offset
* @param {number} end End offset
* @param {boolean} isLeading set if a leading comment
* @returns {undefined}
* @inner
*/
function setComment(start, end, isLeading) {
commentType = source.charAt(start++);
commentLine = line;
commentLineEmpty = false;
commentIsLeading = isLeading;
var lookback;
if (alternateCommentMode) {
lookback = 2; // alternate comment parsing: "//" or "/*"
} else {
lookback = 3; // "///" or "/**"
}
var commentOffset = start - lookback,
c;
do {
if (--commentOffset < 0 ||
(c = source.charAt(commentOffset)) === "\n") {
commentLineEmpty = true;
break;
}
} while (c === " " || c === "\t");
var lines = source
.substring(start, end)
.split(setCommentSplitRe);
for (var i = 0; i < lines.length; ++i)
lines[i] = lines[i]
.replace(alternateCommentMode ? setCommentAltRe : setCommentRe, "")
.trim();
commentText = lines
.join("\n")
.trim();
}
function isDoubleSlashCommentLine(startOffset) {
var endOffset = findEndOfLine(startOffset);
// see if remaining line matches comment pattern
var lineText = source.substring(startOffset, endOffset);
// look for 1 or 2 slashes since startOffset would already point past
// the first slash that started the comment.
var isComment = /^\s*\/{1,2}/.test(lineText);
return isComment;
}
function findEndOfLine(cursor) {
// find end of cursor's line
var endOffset = cursor;
while (endOffset < length && charAt(endOffset) !== "\n") {
endOffset++;
}
return endOffset;
}
/**
* Obtains the next token.
* @returns {string|null} Next token or `null` on eof
* @inner
*/
function next() {
if (stack.length > 0)
return stack.shift();
if (stringDelim)
return readString();
var repeat,
prev,
curr,
start,
isDoc,
isLeadingComment = offset === 0;
do {
if (offset === length)
return null;
repeat = false;
while (whitespaceRe.test(curr = charAt(offset))) {
if (curr === "\n") {
isLeadingComment = true;
++line;
}
if (++offset === length)
return null;
}
if (charAt(offset) === "/") {
if (++offset === length) {
throw illegal("comment");
}
if (charAt(offset) === "/") { // Line
if (!alternateCommentMode) {
// check for triple-slash comment
isDoc = charAt(start = offset + 1) === "/";
while (charAt(++offset) !== "\n") {
if (offset === length) {
return null;
}
}
++offset;
if (isDoc) {
setComment(start, offset - 1, isLeadingComment);
}
++line;
repeat = true;
} else {
// check for double-slash comments, consolidating consecutive lines
start = offset;
isDoc = false;
if (isDoubleSlashCommentLine(offset)) {
isDoc = true;
do {
offset = findEndOfLine(offset);
if (offset === length) {
break;
}
offset++;
} while (isDoubleSlashCommentLine(offset));
} else {
offset = Math.min(length, findEndOfLine(offset) + 1);
}
if (isDoc) {
setComment(start, offset, isLeadingComment);
}
line++;
repeat = true;
}
} else if ((curr = charAt(offset)) === "*") { /* Block */
// check for /** (regular comment mode) or /* (alternate comment mode)
start = offset + 1;
isDoc = alternateCommentMode || charAt(start) === "*";
do {
if (curr === "\n") {
++line;
}
if (++offset === length) {
throw illegal("comment");
}
prev = curr;
curr = charAt(offset);
} while (prev !== "*" || curr !== "/");
++offset;
if (isDoc) {
setComment(start, offset - 2, isLeadingComment);
}
repeat = true;
} else {
return "/";
}
}
} while (repeat);
// offset !== length if we got here
var end = offset;
delimRe.lastIndex = 0;
var delim = delimRe.test(charAt(end++));
if (!delim)
while (end < length && !delimRe.test(charAt(end)))
++end;
var token = source.substring(offset, offset = end);
if (token === "\"" || token === "'")
stringDelim = token;
return token;
}
/**
* Pushes a token back to the stack.
* @param {string} token Token
* @returns {undefined}
* @inner
*/
function push(token) {
stack.push(token);
}
/**
* Peeks for the next token.
* @returns {string|null} Token or `null` on eof
* @inner
*/
function peek() {
if (!stack.length) {
var token = next();
if (token === null)
return null;
push(token);
}
return stack[0];
}
/**
* Skips a token.
* @param {string} expected Expected token
* @param {boolean} [optional=false] Whether the token is optional
* @returns {boolean} `true` when skipped, `false` if not
* @throws {Error} When a required token is not present
* @inner
*/
function skip(expected, optional) {
var actual = peek(),
equals = actual === expected;
if (equals) {
next();
return true;
}
if (!optional)
throw illegal("token '" + actual + "', '" + expected + "' expected");
return false;
}
/**
* Gets a comment.
* @param {number} [trailingLine] Line number if looking for a trailing comment
* @returns {string|null} Comment text
* @inner
*/
function cmnt(trailingLine) {
var ret = null;
if (trailingLine === undefined) {
if (commentLine === line - 1 && (alternateCommentMode || commentType === "*" || commentLineEmpty)) {
ret = commentIsLeading ? commentText : null;
}
} else {
/* istanbul ignore else */
if (commentLine < trailingLine) {
peek();
}
if (commentLine === trailingLine && !commentLineEmpty && (alternateCommentMode || commentType === "/")) {
ret = commentIsLeading ? null : commentText;
}
}
return ret;
}
return Object.defineProperty({
next: next,
peek: peek,
push: push,
skip: skip,
cmnt: cmnt
}, "line", {
get: function() { return line; }
});
/* eslint-enable callback-return */
}