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
|
// Copyright (c) 2014 Couchbase, Inc.
//
// Licensed under the Apache License, Version 2.0 (the "License");
// you may not use this file except in compliance with the License.
// You may obtain a copy of the License at
//
// http://www.apache.org/licenses/LICENSE-2.0
//
// Unless required by applicable law or agreed to in writing, software
// distributed under the License is distributed on an "AS IS" BASIS,
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
// See the License for the specific language governing permissions and
// limitations under the License.
package analysis
import (
"fmt"
"time"
)
type CharFilter interface {
Filter([]byte) []byte
}
type TokenType int
const (
AlphaNumeric TokenType = iota
Ideographic
Numeric
DateTime
Shingle
Single
Double
Boolean
)
// Token represents one occurrence of a term at a particular location in a
// field.
type Token struct {
// Start specifies the byte offset of the beginning of the term in the
// field.
Start int `json:"start"`
// End specifies the byte offset of the end of the term in the field.
End int `json:"end"`
Term []byte `json:"term"`
// Position specifies the 1-based index of the token in the sequence of
// occurrences of its term in the field.
Position int `json:"position"`
Type TokenType `json:"type"`
KeyWord bool `json:"keyword"`
}
func (t *Token) String() string {
return fmt.Sprintf("Start: %d End: %d Position: %d Token: %s Type: %d", t.Start, t.End, t.Position, string(t.Term), t.Type)
}
type TokenStream []*Token
// A Tokenizer splits an input string into tokens, the usual behaviour being to
// map words to tokens.
type Tokenizer interface {
Tokenize([]byte) TokenStream
}
// A TokenFilter adds, transforms or removes tokens from a token stream.
type TokenFilter interface {
Filter(TokenStream) TokenStream
}
type Analyzer struct {
CharFilters []CharFilter
Tokenizer Tokenizer
TokenFilters []TokenFilter
}
func (a *Analyzer) Analyze(input []byte) TokenStream {
if a.CharFilters != nil {
for _, cf := range a.CharFilters {
input = cf.Filter(input)
}
}
tokens := a.Tokenizer.Tokenize(input)
if a.TokenFilters != nil {
for _, tf := range a.TokenFilters {
tokens = tf.Filter(tokens)
}
}
return tokens
}
var ErrInvalidDateTime = fmt.Errorf("unable to parse datetime with any of the layouts")
type DateTimeParser interface {
ParseDateTime(string) (time.Time, error)
}
type ByteArrayConverter interface {
Convert([]byte) (interface{}, error)
}
|
