-
Notifications
You must be signed in to change notification settings - Fork 0
/
scanner.go
167 lines (143 loc) · 4.01 KB
/
scanner.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
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
package main
import (
"bufio"
"bytes"
"io"
"regexp"
"strings"
)
// Scanner represents a lexical scanner.
type Scanner struct {
r *bufio.Reader
}
// NewScanner returns a new instance of Scanner.
func NewScanner(r io.Reader) *Scanner {
return &Scanner{r: bufio.NewReader(r)}
}
// Scan returns the next token and literal value.
func (s *Scanner) Scan() (tok Token, lit string) {
// Read the next rune.
ch := s.read()
// If we see whitespace then consume all contiguous whitespace.
// If we see a letter then consume as an ident or reserved word.
// If we see a digit then consume as a number.
if isWhitespace(ch) {
s.unread()
return s.scanWhitespace()
} else if ch == eof {
return EOF, ""
} else if ch == ',' {
return COMMA, string(ch)
} else if isValidCh(ch) {
s.unread()
return s.scanToken()
}
return ILLEGAL, string(ch)
}
// scanWhitespace consumes the current rune and all contiguous whitespace.
func (s *Scanner) scanWhitespace() (tok Token, lit string) {
// Create a buffer and read the current character into it.
var buf bytes.Buffer
buf.WriteRune(s.read())
// Read every subsequent whitespace character into the buffer.
// Non-whitespace characters and EOF will cause the loop to exit.
for {
if ch := s.read(); ch == eof {
break
} else if !isWhitespace(ch) {
s.unread()
break
} else {
buf.WriteRune(ch)
}
}
return WS, buf.String()
}
// scanToken consumes the current rune and all contiguous ident runes.
func (s *Scanner) scanToken() (tok Token, lit string) {
// Create a buffer and read the current character into it.
var buf bytes.Buffer
buf.WriteRune(s.read())
// Read every subsequent ident character into the buffer.
// Non-ident characters and EOF will cause the loop to exit.
for {
if ch := s.read(); ch == eof {
break
} else if isWhitespace(ch) || !isValidCh(ch) {
s.unread()
break
} else {
_, _ = buf.WriteRune(ch)
}
}
// If the string matches a keyword then return that keyword.
switch strings.ToUpper(buf.String()) {
case "MAP":
return MAP, buf.String()
case "REDUCE":
return REDUCE, buf.String()
case "ON":
return ON, buf.String()
case "WHERE":
return WHERE, buf.String()
case "AND":
return AND, buf.String()
case "IN":
return IN, buf.String()
case "SUM":
return SUM, buf.String()
case "COUNT":
return COUNT, buf.String()
}
// Match operators
switch buf.String() {
case "<":
return LT, buf.String()
case "<=":
return LTE, buf.String()
case ">":
return GT, buf.String()
case ">=":
return GTE, buf.String()
case "=":
return EQ, buf.String()
case "!=":
return NOT_EQ, buf.String()
}
// Check for string literal or ident
var str string = buf.String()
if str[0] == '"' && str[len(str)-1] == '"' {
str = str[1 : len(str)-1]
return STRING, str
}
// Check for number
if match, _ := regexp.MatchString("([0-9.]+)", buf.String()); match {
return NUMBER, buf.String()
}
return IDENT, buf.String()
}
// read reads the next rune from the bufferred reader.
// Returns the rune(0) if an error occurs (or io.EOF is returned).
func (s *Scanner) read() rune {
ch, _, err := s.r.ReadRune()
if err != nil {
return eof
}
return ch
}
// unread places the previously read rune back on the reader.
func (s *Scanner) unread() { _ = s.r.UnreadRune() }
// isWhitespace returns true if the rune is a space, tab, or newline.
func isWhitespace(ch rune) bool { return ch == ' ' || ch == '\t' || ch == '\n' }
// isLetter returns true if the rune is a letter.
func isLetter(ch rune) bool { return (ch >= 'a' && ch <= 'z') || (ch >= 'A' && ch <= 'Z') }
// isDigit returns true if the rune is a digit.
func isDigit(ch rune) bool { return (ch >= '0' && ch <= '9') }
func isOperator(ch rune) bool {
return (ch == '<' || ch == '>' || ch == '=' || ch == '+' || ch == '-' || ch == '/' || ch == '*')
}
func isValidCh(ch rune) bool {
return isWhitespace(ch) || isLetter(ch) || isDigit(ch) || isOperator(ch) || ch == '_' || ch == '"' || ch == '.' || ch == '@' || ch == '!'
}
// eof represents a marker rune for the end of the reader.
var eof = rune(0)