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
|
lunr.QueryLexer = function (str) {
this.lexemes = []
this.str = str
this.length = str.length
this.pos = 0
this.start = 0
this.escapeCharPositions = []
}
lunr.QueryLexer.prototype.run = function () {
var state = lunr.QueryLexer.lexText
while (state) {
state = state(this)
}
}
lunr.QueryLexer.prototype.sliceString = function () {
var subSlices = [],
sliceStart = this.start,
sliceEnd = this.pos
for (var i = 0; i < this.escapeCharPositions.length; i++) {
sliceEnd = this.escapeCharPositions[i]
subSlices.push(this.str.slice(sliceStart, sliceEnd))
sliceStart = sliceEnd + 1
}
subSlices.push(this.str.slice(sliceStart, this.pos))
this.escapeCharPositions.length = 0
return subSlices.join('')
}
lunr.QueryLexer.prototype.emit = function (type) {
this.lexemes.push({
type: type,
str: this.sliceString(),
start: this.start,
end: this.pos
})
this.start = this.pos
}
lunr.QueryLexer.prototype.escapeCharacter = function () {
this.escapeCharPositions.push(this.pos - 1)
this.pos += 1
}
lunr.QueryLexer.prototype.next = function () {
if (this.pos >= this.length) {
return lunr.QueryLexer.EOS
}
var char = this.str.charAt(this.pos)
this.pos += 1
return char
}
lunr.QueryLexer.prototype.width = function () {
return this.pos - this.start
}
lunr.QueryLexer.prototype.ignore = function () {
if (this.start == this.pos) {
this.pos += 1
}
this.start = this.pos
}
lunr.QueryLexer.prototype.backup = function () {
this.pos -= 1
}
lunr.QueryLexer.prototype.acceptDigitRun = function () {
var char, charCode
do {
char = this.next()
charCode = char.charCodeAt(0)
} while (charCode > 47 && charCode < 58)
if (char != lunr.QueryLexer.EOS) {
this.backup()
}
}
lunr.QueryLexer.prototype.more = function () {
return this.pos < this.length
}
lunr.QueryLexer.EOS = 'EOS'
lunr.QueryLexer.FIELD = 'FIELD'
lunr.QueryLexer.TERM = 'TERM'
lunr.QueryLexer.EDIT_DISTANCE = 'EDIT_DISTANCE'
lunr.QueryLexer.BOOST = 'BOOST'
lunr.QueryLexer.PRESENCE = 'PRESENCE'
lunr.QueryLexer.lexField = function (lexer) {
lexer.backup()
lexer.emit(lunr.QueryLexer.FIELD)
lexer.ignore()
return lunr.QueryLexer.lexText
}
lunr.QueryLexer.lexTerm = function (lexer) {
if (lexer.width() > 1) {
lexer.backup()
lexer.emit(lunr.QueryLexer.TERM)
}
lexer.ignore()
if (lexer.more()) {
return lunr.QueryLexer.lexText
}
}
lunr.QueryLexer.lexEditDistance = function (lexer) {
lexer.ignore()
lexer.acceptDigitRun()
lexer.emit(lunr.QueryLexer.EDIT_DISTANCE)
return lunr.QueryLexer.lexText
}
lunr.QueryLexer.lexBoost = function (lexer) {
lexer.ignore()
lexer.acceptDigitRun()
lexer.emit(lunr.QueryLexer.BOOST)
return lunr.QueryLexer.lexText
}
lunr.QueryLexer.lexEOS = function (lexer) {
if (lexer.width() > 0) {
lexer.emit(lunr.QueryLexer.TERM)
}
}
// This matches the separator used when tokenising fields
// within a document. These should match otherwise it is
// not possible to search for some tokens within a document.
//
// It is possible for the user to change the separator on the
// tokenizer so it _might_ clash with any other of the special
// characters already used within the search string, e.g. :.
//
// This means that it is possible to change the separator in
// such a way that makes some words unsearchable using a search
// string.
lunr.QueryLexer.termSeparator = lunr.tokenizer.separator
lunr.QueryLexer.lexText = function (lexer) {
while (true) {
var char = lexer.next()
if (char == lunr.QueryLexer.EOS) {
return lunr.QueryLexer.lexEOS
}
// Escape character is '\'
if (char.charCodeAt(0) == 92) {
lexer.escapeCharacter()
continue
}
if (char == ":") {
return lunr.QueryLexer.lexField
}
if (char == "~") {
lexer.backup()
if (lexer.width() > 0) {
lexer.emit(lunr.QueryLexer.TERM)
}
return lunr.QueryLexer.lexEditDistance
}
if (char == "^") {
lexer.backup()
if (lexer.width() > 0) {
lexer.emit(lunr.QueryLexer.TERM)
}
return lunr.QueryLexer.lexBoost
}
// "+" indicates term presence is required
// checking for length to ensure that only
// leading "+" are considered
if (char == "+" && lexer.width() === 1) {
lexer.emit(lunr.QueryLexer.PRESENCE)
return lunr.QueryLexer.lexText
}
// "-" indicates term presence is prohibited
// checking for length to ensure that only
// leading "-" are considered
if (char == "-" && lexer.width() === 1) {
lexer.emit(lunr.QueryLexer.PRESENCE)
return lunr.QueryLexer.lexText
}
if (char.match(lunr.QueryLexer.termSeparator)) {
return lunr.QueryLexer.lexTerm
}
}
}
|
