aboutsummaryrefslogtreecommitdiffstats
path: root/query/lexer.go
blob: 5ca700c75189e54aa963a67dee47dc1bd153a43c (plain) (blame)
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
package query

import (
	"fmt"
	"strings"
	"unicode"
)

type tokenKind int

const (
	_ tokenKind = iota
	tokenKindKV
	tokenKindSearch
)

type token struct {
	kind tokenKind

	// KV
	qualifier string
	value     string

	// Search
	term string
}

func newTokenKV(qualifier, value string) token {
	return token{
		kind:      tokenKindKV,
		qualifier: qualifier,
		value:     value,
	}
}

func newTokenSearch(term string) token {
	return token{
		kind: tokenKindSearch,
		term: term,
	}
}

// tokenize parse and break a input into tokens ready to be
// interpreted later by a parser to get the semantic.
func tokenize(query string) ([]token, error) {
	fields, err := splitQuery(query)
	if err != nil {
		return nil, err
	}

	var tokens []token
	for _, field := range fields {
		split := strings.Split(field, ":")

		// full text search
		if len(split) == 1 {
			tokens = append(tokens, newTokenSearch(removeQuote(field)))
			continue
		}

		if len(split) != 2 {
			return nil, fmt.Errorf("can't tokenize \"%s\"", field)
		}

		if len(split[0]) == 0 {
			return nil, fmt.Errorf("can't tokenize \"%s\": empty qualifier", field)
		}
		if len(split[1]) == 0 {
			return nil, fmt.Errorf("empty value for qualifier \"%s\"", split[0])
		}

		tokens = append(tokens, newTokenKV(split[0], removeQuote(split[1])))
	}
	return tokens, nil
}

// split the query into chunks by splitting on whitespaces but respecting
// quotes
func splitQuery(query string) ([]string, error) {
	lastQuote := rune(0)
	inQuote := false

	isToken := func(r rune) bool {
		switch {
		case !inQuote && isQuote(r):
			lastQuote = r
			inQuote = true
			return true
		case inQuote && r == lastQuote:
			lastQuote = rune(0)
			inQuote = false
			return true
		case inQuote:
			return true
		default:
			return !unicode.IsSpace(r)
		}
	}

	var result []string
	var token strings.Builder
	for _, r := range query {
		if isToken(r) {
			token.WriteRune(r)
		} else {
			if token.Len() > 0 {
				result = append(result, token.String())
				token.Reset()
			}
		}
	}

	if inQuote {
		return nil, fmt.Errorf("unmatched quote")
	}

	if token.Len() > 0 {
		result = append(result, token.String())
	}

	return result, nil
}

func isQuote(r rune) bool {
	return r == '"' || r == '\''
}

func removeQuote(field string) string {
	runes := []rune(field)
	if len(runes) >= 2 {
		r1 := runes[0]
		r2 := runes[len(runes)-1]

		if r1 == r2 && isQuote(r1) {
			return string(runes[1 : len(runes)-1])
		}
	}
	return field
}