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
|
// Copyright 2018 The Hugo Authors. All rights reserved.
//
// 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 pageparser provides a parser for Hugo content files (Markdown, HTML etc.) in Hugo.
// This implementation is highly inspired by the great talk given by Rob Pike called "Lexical Scanning in Go"
// It's on YouTube, Google it!.
// See slides here: http://cuddle.googlecode.com/hg/talk/lex.html
package pageparser
import (
"bytes"
"io"
"io/ioutil"
"github.com/pkg/errors"
)
// Result holds the parse result.
type Result interface {
// Iterator returns a new Iterator positioned at the benning of the parse tree.
Iterator() *Iterator
// Input returns the input to Parse.
Input() []byte
}
var _ Result = (*pageLexer)(nil)
// Parse parses the page in the given reader.
func Parse(r io.Reader) (Result, error) {
b, err := ioutil.ReadAll(r)
if err != nil {
return nil, errors.Wrap(err, "failed to read page content")
}
return parseBytes(b)
}
func parseBytes(b []byte) (Result, error) {
lexer := newPageLexer(b, 0, lexIntroSection)
lexer.run()
return lexer, nil
}
func parseMainSection(input []byte, from int) Result {
lexer := newPageLexer(input, from, lexMainSection)
lexer.run()
return lexer
}
// An Iterator has methods to iterate a parsed page with support going back
// if needed.
type Iterator struct {
l *pageLexer
lastPos int // position of the last item returned by nextItem
}
// consumes and returns the next item
func (t *Iterator) Next() Item {
t.lastPos++
return t.current()
}
// Input returns the input source.
func (t *Iterator) Input() []byte {
return t.l.Input()
}
var errIndexOutOfBounds = Item{tError, 0, []byte("no more tokens")}
func (t *Iterator) current() Item {
if t.lastPos >= len(t.l.items) {
return errIndexOutOfBounds
}
return t.l.items[t.lastPos]
}
// backs up one token.
func (t *Iterator) Backup() {
if t.lastPos < 0 {
panic("need to go forward before going back")
}
t.lastPos--
}
// check for non-error and non-EOF types coming next
func (t *Iterator) IsValueNext() bool {
i := t.Peek()
return i.Type != tError && i.Type != tEOF
}
// look at, but do not consume, the next item
// repeated, sequential calls will return the same item
func (t *Iterator) Peek() Item {
return t.l.items[t.lastPos+1]
}
// PeekWalk will feed the next items in the iterator to walkFn
// until it returns false.
func (t *Iterator) PeekWalk(walkFn func(item Item) bool) {
for i := t.lastPos + 1; i < len(t.l.items); i++ {
item := t.l.items[i]
if !walkFn(item) {
break
}
}
}
// Consume is a convencience method to consume the next n tokens,
// but back off Errors and EOF.
func (t *Iterator) Consume(cnt int) {
for i := 0; i < cnt; i++ {
token := t.Next()
if token.Type == tError || token.Type == tEOF {
t.Backup()
break
}
}
}
// LineNumber returns the current line number. Used for logging.
func (t *Iterator) LineNumber() int {
return bytes.Count(t.l.input[:t.current().Pos], lf) + 1
}
|
