Tokenizer.js
4.7 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
/*?
// --- Scope -----------------
// Lang : Language expressions
*/
/**
* Constructs a new Tokenizer.
* @exports ProtoBuf.DotProto.Tokenizer
* @class prototype tokenizer
* @param {string} proto Proto to tokenize
* @constructor
*/
var Tokenizer = function(proto) {
/**
* Source to parse.
* @type {string}
* @expose
*/
this.source = proto+"";
/**
* Current index.
* @type {number}
* @expose
*/
this.index = 0;
/**
* Current line.
* @type {number}
* @expose
*/
this.line = 1;
/**
* Token stack.
* @type {!Array.<string>}
* @expose
*/
this.stack = [];
/**
* Opening character of the current string read, if any.
* @type {?string}
* @private
*/
this._stringOpen = null;
};
/**
* @alias ProtoBuf.DotProto.Tokenizer.prototype
* @inner
*/
var TokenizerPrototype = Tokenizer.prototype;
/**
* Reads a string beginning at the current index.
* @return {string}
* @private
*/
TokenizerPrototype._readString = function() {
var re = this._stringOpen === '"'
? Lang.STRING_DQ
: Lang.STRING_SQ;
re.lastIndex = this.index - 1; // Include the open quote
var match = re.exec(this.source);
if (!match)
throw Error("unterminated string");
this.index = re.lastIndex;
this.stack.push(this._stringOpen);
this._stringOpen = null;
return match[1];
};
/**
* Gets the next token and advances by one.
* @return {?string} Token or `null` on EOF
* @expose
*/
TokenizerPrototype.next = function() {
if (this.stack.length > 0)
return this.stack.shift();
if (this.index >= this.source.length)
return null;
if (this._stringOpen !== null)
return this._readString();
var repeat,
prev,
next;
do {
repeat = false;
// Strip white spaces
while (Lang.WHITESPACE.test(next = this.source.charAt(this.index))) {
if (next === '\n')
++this.line;
if (++this.index === this.source.length)
return null;
}
// Strip comments
if (this.source.charAt(this.index) === '/') {
++this.index;
if (this.source.charAt(this.index) === '/') { // Line
while (this.source.charAt(++this.index) !== '\n')
if (this.index == this.source.length)
return null;
++this.index;
++this.line;
repeat = true;
} else if ((next = this.source.charAt(this.index)) === '*') { /* Block */
do {
if (next === '\n')
++this.line;
if (++this.index === this.source.length)
return null;
prev = next;
next = this.source.charAt(this.index);
} while (prev !== '*' || next !== '/');
++this.index;
repeat = true;
} else
return '/';
}
} while (repeat);
if (this.index === this.source.length)
return null;
// Read the next token
var end = this.index;
Lang.DELIM.lastIndex = 0;
var delim = Lang.DELIM.test(this.source.charAt(end++));
if (!delim)
while(end < this.source.length && !Lang.DELIM.test(this.source.charAt(end)))
++end;
var token = this.source.substring(this.index, this.index = end);
if (token === '"' || token === "'")
this._stringOpen = token;
return token;
};
/**
* Peeks for the next token.
* @return {?string} Token or `null` on EOF
* @expose
*/
TokenizerPrototype.peek = function() {
if (this.stack.length === 0) {
var token = this.next();
if (token === null)
return null;
this.stack.push(token);
}
return this.stack[0];
};
/**
* Skips a specific token and throws if it differs.
* @param {string} expected Expected token
* @throws {Error} If the actual token differs
*/
TokenizerPrototype.skip = function(expected) {
var actual = this.next();
if (actual !== expected)
throw Error("illegal '"+actual+"', '"+expected+"' expected");
};
/**
* Omits an optional token.
* @param {string} expected Expected optional token
* @returns {boolean} `true` if the token exists
*/
TokenizerPrototype.omit = function(expected) {
if (this.peek() === expected) {
this.next();
return true;
}
return false;
};
/**
* Returns a string representation of this object.
* @return {string} String representation as of "Tokenizer(index/length)"
* @expose
*/
TokenizerPrototype.toString = function() {
return "Tokenizer ("+this.index+"/"+this.source.length+" at line "+this.line+")";
};