File: api.go

package info (click to toggle)
golang-github-alecthomas-participle-v2 2.1.4-2
  • links: PTS, VCS
  • area: main
  • in suites: forky, sid
  • size: 920 kB
  • sloc: javascript: 1,164; sh: 41; makefile: 7
file content (185 lines) | stat: -rw-r--r-- 4,589 bytes parent folder | download
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
package lexer

import (
	"fmt"
	"io"
	"strings"
	"unicode/utf8"
)

type TokenType int

const (
	// EOF represents an end of file.
	EOF TokenType = -(iota + 1)
)

// EOFToken creates a new EOF token at the given position.
func EOFToken(pos Position) Token {
	return Token{Type: EOF, Pos: pos}
}

// Definition is the main entry point for lexing.
type Definition interface {
	// Symbols returns a map of symbolic names to the corresponding pseudo-runes for those symbols.
	// This is the same approach as used by text/scanner. For example, "EOF" might have the rune
	// value of -1, "Ident" might be -2, and so on.
	Symbols() map[string]TokenType
	// Lex an io.Reader.
	Lex(filename string, r io.Reader) (Lexer, error)
}

// StringDefinition is an optional interface lexer Definition's can implement
// to offer a fast path for lexing strings.
type StringDefinition interface {
	LexString(filename string, input string) (Lexer, error)
}

// BytesDefinition is an optional interface lexer Definition's can implement
// to offer a fast path for lexing byte slices.
type BytesDefinition interface {
	LexBytes(filename string, input []byte) (Lexer, error)
}

// A Lexer returns tokens from a source.
type Lexer interface {
	// Next consumes and returns the next token.
	Next() (Token, error)
}

// SymbolsByRune returns a map of lexer symbol names keyed by rune.
func SymbolsByRune(def Definition) map[TokenType]string {
	symbols := def.Symbols()
	out := make(map[TokenType]string, len(symbols))
	for s, r := range symbols {
		out[r] = s
	}
	return out
}

// NameOfReader attempts to retrieve the filename of a reader.
func NameOfReader(r interface{}) string {
	if nr, ok := r.(interface{ Name() string }); ok {
		return nr.Name()
	}
	return ""
}

// Must takes the result of a Definition constructor call and returns the definition, but panics if
// it errors
//
// eg.
//
//	lex = lexer.Must(lexer.Build(`Symbol = "symbol" .`))
func Must(def Definition, err error) Definition {
	if err != nil {
		panic(err)
	}
	return def
}

// ConsumeAll reads all tokens from a Lexer.
func ConsumeAll(lexer Lexer) ([]Token, error) {
	tokens := make([]Token, 0, 1024)
	for {
		token, err := lexer.Next()
		if err != nil {
			return nil, err
		}
		tokens = append(tokens, token)
		if token.Type == EOF {
			return tokens, nil
		}
	}
}

// Position of a token.
type Position struct {
	Filename string
	Offset   int
	Line     int
	Column   int
}

// Advance the Position based on the number of characters and newlines in "span".
func (p *Position) Advance(span string) {
	p.Offset += len(span)
	lines := strings.Count(span, "\n")
	p.Line += lines
	// Update column.
	if lines == 0 {
		p.Column += utf8.RuneCountInString(span)
	} else {
		p.Column = utf8.RuneCountInString(span[strings.LastIndex(span, "\n"):])
	}
}

// Add returns a new Position that is the sum of this position and "pos".
//
// This is useful when parsing values from a parent grammar.
func (p Position) Add(pos Position) Position {
	p.Line += pos.Line - 1
	if pos.Line > 1 {
		p.Column = pos.Column
	} else {
		p.Column += pos.Column - 1
	}
	p.Offset += pos.Offset
	return p
}

func (p Position) GoString() string {
	return fmt.Sprintf("Position{Filename: %q, Offset: %d, Line: %d, Column: %d}",
		p.Filename, p.Offset, p.Line, p.Column)
}

func (p Position) String() string {
	filename := p.Filename
	if filename == "" {
		return fmt.Sprintf("%d:%d", p.Line, p.Column)
	}
	return fmt.Sprintf("%s:%d:%d", filename, p.Line, p.Column)
}

// A Token returned by a Lexer.
type Token struct {
	// Type of token. This is the value keyed by symbol as returned by Definition.Symbols().
	Type  TokenType
	Value string
	Pos   Position
}

// EOF returns true if this Token is an EOF token.
func (t Token) EOF() bool {
	return t.Type == EOF
}

func (t Token) String() string {
	if t.EOF() {
		return "<EOF>"
	}
	return t.Value
}

func (t Token) GoString() string {
	if t.Pos == (Position{}) {
		return fmt.Sprintf("Token{%d, %q}", t.Type, t.Value)
	}
	return fmt.Sprintf("Token@%s{%d, %q}", t.Pos.String(), t.Type, t.Value)
}

// MakeSymbolTable builds a lookup table for checking token ID existence.
//
// For each symbolic name in "types", the returned map will contain the corresponding token ID as a key.
func MakeSymbolTable(def Definition, types ...string) (map[TokenType]bool, error) {
	symbols := def.Symbols()
	table := make(map[TokenType]bool, len(types))
	for _, symbol := range types {
		rn, ok := symbols[symbol]
		if !ok {
			return nil, fmt.Errorf("lexer does not support symbol %q", symbol)
		}
		table[rn] = true
	}
	return table, nil
}