forked from dgraph-io/dgraph
/
tokens.go
146 lines (125 loc) · 4.06 KB
/
tokens.go
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
/*
* Copyright (C) 2017 Dgraph Labs, Inc. and Contributors
*
* This program is free software: you can redistribute it and/or modify
* it under the terms of the GNU Affero General Public License as published by
* the Free Software Foundation, either version 3 of the License, or
* (at your option) any later version.
*
* This program is distributed in the hope that it will be useful,
* but WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU Affero General Public License for more details.
*
* You should have received a copy of the GNU Affero General Public License
* along with this program. If not, see <http://www.gnu.org/licenses/>.
*/
package worker
import (
"strings"
"github.com/dgraph-io/badger"
"github.com/dgraph-io/dgraph/schema"
"github.com/dgraph-io/dgraph/tok"
"github.com/dgraph-io/dgraph/types"
"github.com/dgraph-io/dgraph/x"
)
func verifyStringIndex(attr string, funcType FuncType) (string, bool) {
var requiredTokenizer string
switch funcType {
case FullTextSearchFn:
requiredTokenizer = tok.FullTextTokenizer{}.Name()
default:
requiredTokenizer = tok.TermTokenizer{}.Name()
}
if !schema.State().IsIndexed(attr) {
return requiredTokenizer, false
}
tokenizers := schema.State().Tokenizer(attr)
for _, tokenizer := range tokenizers {
// check for prefix, in case of explicit usage of language specific full text tokenizer
if strings.HasPrefix(tokenizer.Name(), requiredTokenizer) {
return requiredTokenizer, true
}
}
return requiredTokenizer, false
}
// Return string tokens from function arguments. It maps function type to correct tokenizer.
// Note: regexp functions require regexp compilation of argument, not tokenization.
func getStringTokens(funcArgs []string, lang string, funcType FuncType) ([]string, error) {
if lang == "." {
lang = "en"
}
switch funcType {
case FullTextSearchFn:
return tok.GetTextTokens(funcArgs, lang)
default:
return tok.GetTokens(funcArgs)
}
}
func pickTokenizer(attr string, f string) (tok.Tokenizer, error) {
// Get the tokenizers and choose the corresponding one.
if !schema.State().IsIndexed(attr) {
return nil, x.Errorf("Attribute %s is not indexed.", attr)
}
tokenizers := schema.State().Tokenizer(attr)
var tokenizer tok.Tokenizer
for _, t := range tokenizers {
if !t.IsLossy() {
tokenizer = t
break
}
}
// If function is eq and we found a tokenizer thats !Lossy(), lets return
// it to avoid the second lookup.
if f == "eq" && tokenizer != nil {
return tokenizer, nil
}
// Lets try to find a sortable tokenizer.
for _, t := range tokenizers {
if t.IsSortable() {
return t, nil
}
}
// rest of the cases, ge, gt , le , lt require a sortable tokenizer.
if f != "eq" {
return nil, x.Errorf("Attribute:%s does not have proper index for comparison",
attr)
}
// We didn't find a sortable or !isLossy() tokenizer, lets return the first one.
return tokenizers[0], nil
}
// getInequalityTokens gets tokens ge / le compared to given token using the first sortable
// index that is found for the predicate.
func getInequalityTokens(attr, f string, ineqValue types.Val) ([]string, string, error) {
tokenizer, err := pickTokenizer(attr, f)
if err != nil {
return nil, "", err
}
// Get the token for the value passed in function.
ineqTokens, err := tokenizer.Tokens(ineqValue)
if err != nil {
return nil, "", err
}
if len(ineqTokens) != 1 {
return nil, "", x.Errorf("Attribute %s does not have a valid tokenizer.", attr)
}
ineqToken := ineqTokens[0]
if f == "eq" {
return []string{ineqToken}, ineqToken, nil
}
isgeOrGt := f == "ge" || f == "gt"
itOpt := badger.DefaultIteratorOptions
itOpt.PrefetchValues = false
itOpt.Reverse = !isgeOrGt
it := pstore.NewIterator(itOpt)
defer it.Close()
var out []string
indexPrefix := x.IndexKey(attr, string(tokenizer.Identifier()))
for it.Seek(x.IndexKey(attr, ineqToken)); it.ValidForPrefix(indexPrefix); it.Next() {
key := it.Item().Key()
k := x.Parse(key)
x.AssertTrue(k != nil)
out = append(out, k.Term)
}
return out, ineqToken, nil
}