summaryrefslogtreecommitdiff
path: root/caddyconfig/caddyfile/lexer.go
blob: 188ef06492ce00d74aa789b7f18072aec96c0dd2 (plain)
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
186
187
188
189
// Copyright 2015 Light Code Labs, LLC
//
// 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 caddyfile

import (
	"bufio"
	"bytes"
	"io"
	"unicode"
)

type (
	// lexer is a utility which can get values, token by
	// token, from a Reader. A token is a word, and tokens
	// are separated by whitespace. A word can be enclosed
	// in quotes if it contains whitespace.
	lexer struct {
		reader       *bufio.Reader
		token        Token
		line         int
		skippedLines int
	}

	// Token represents a single parsable unit.
	Token struct {
		File string
		Line int
		Text string
	}
)

// load prepares the lexer to scan an input for tokens.
// It discards any leading byte order mark.
func (l *lexer) load(input io.Reader) error {
	l.reader = bufio.NewReader(input)
	l.line = 1

	// discard byte order mark, if present
	firstCh, _, err := l.reader.ReadRune()
	if err != nil {
		return err
	}
	if firstCh != 0xFEFF {
		err := l.reader.UnreadRune()
		if err != nil {
			return err
		}
	}

	return nil
}

// next loads the next token into the lexer.
// A token is delimited by whitespace, unless
// the token starts with a quotes character (")
// in which case the token goes until the closing
// quotes (the enclosing quotes are not included).
// Inside quoted strings, quotes may be escaped
// with a preceding \ character. No other chars
// may be escaped. The rest of the line is skipped
// if a "#" character is read in. Returns true if
// a token was loaded; false otherwise.
func (l *lexer) next() bool {
	var val []rune
	var comment, quoted, btQuoted, escaped bool

	makeToken := func() bool {
		l.token.Text = string(val)
		return true
	}

	for {
		ch, _, err := l.reader.ReadRune()
		if err != nil {
			if len(val) > 0 {
				return makeToken()
			}
			if err == io.EOF {
				return false
			}
			panic(err)
		}

		if !escaped && !btQuoted && ch == '\\' {
			escaped = true
			continue
		}

		if quoted || btQuoted {
			if quoted && escaped {
				// all is literal in quoted area,
				// so only escape quotes
				if ch != '"' {
					val = append(val, '\\')
				}
				escaped = false
			} else {
				if quoted && ch == '"' {
					return makeToken()
				}
				if btQuoted && ch == '`' {
					return makeToken()
				}
			}
			if ch == '\n' {
				l.line += 1 + l.skippedLines
				l.skippedLines = 0
			}
			val = append(val, ch)
			continue
		}

		if unicode.IsSpace(ch) {
			if ch == '\r' {
				continue
			}
			if ch == '\n' {
				if escaped {
					l.skippedLines++
					escaped = false
				} else {
					l.line += 1 + l.skippedLines
					l.skippedLines = 0
				}
				comment = false
			}
			if len(val) > 0 {
				return makeToken()
			}
			continue
		}

		if ch == '#' && len(val) == 0 {
			comment = true
		}
		if comment {
			continue
		}

		if len(val) == 0 {
			l.token = Token{Line: l.line}
			if ch == '"' {
				quoted = true
				continue
			}
			if ch == '`' {
				btQuoted = true
				continue
			}
		}

		if escaped {
			val = append(val, '\\')
			escaped = false
		}

		val = append(val, ch)
	}
}

// Tokenize takes bytes as input and lexes it into
// a list of tokens that can be parsed as a Caddyfile.
// Also takes a filename to fill the token's File as
// the source of the tokens, which is important to
// determine relative paths for `import` directives.
func Tokenize(input []byte, filename string) ([]Token, error) {
	l := lexer{}
	if err := l.load(bytes.NewReader(input)); err != nil {
		return nil, err
	}
	var tokens []Token
	for l.next() {
		l.token.File = filename
		tokens = append(tokens, l.token)
	}
	return tokens, nil
}