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
190
191
|
// Copyright 2019 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
import (
"bytes"
"io"
"io/ioutil"
"github.com/gohugoio/hugo/parser/metadecoders"
"github.com/pkg/errors"
)
// Result holds the parse result.
type Result interface {
// Iterator returns a new Iterator positioned at the beginning 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 according to the given Config.
// TODO(bep) now that we have improved the "lazy order" init, it *may* be
// some potential saving in doing a buffered approach where the first pass does
// the frontmatter only.
func Parse(r io.Reader, cfg Config) (Result, error) {
return parseSection(r, cfg, lexIntroSection)
}
type ContentFrontMatter struct {
Content []byte
FrontMatter map[string]interface{}
FrontMatterFormat metadecoders.Format
}
// ParseFrontMatterAndContent is a convenience method to extract front matter
// and content from a content page.
func ParseFrontMatterAndContent(r io.Reader) (ContentFrontMatter, error) {
var cf ContentFrontMatter
psr, err := Parse(r, Config{})
if err != nil {
return cf, err
}
var frontMatterSource []byte
iter := psr.Iterator()
walkFn := func(item Item) bool {
if frontMatterSource != nil {
// The rest is content.
cf.Content = psr.Input()[item.Pos:]
// Done
return false
} else if item.IsFrontMatter() {
cf.FrontMatterFormat = FormatFromFrontMatterType(item.Type)
frontMatterSource = item.Val
}
return true
}
iter.PeekWalk(walkFn)
cf.FrontMatter, err = metadecoders.Default.UnmarshalToMap(frontMatterSource, cf.FrontMatterFormat)
return cf, err
}
func FormatFromFrontMatterType(typ ItemType) metadecoders.Format {
switch typ {
case TypeFrontMatterJSON:
return metadecoders.JSON
case TypeFrontMatterORG:
return metadecoders.ORG
case TypeFrontMatterTOML:
return metadecoders.TOML
case TypeFrontMatterYAML:
return metadecoders.YAML
default:
return ""
}
}
// ParseMain parses starting with the main section. Used in tests.
func ParseMain(r io.Reader, cfg Config) (Result, error) {
return parseSection(r, cfg, lexMainSection)
}
func parseSection(r io.Reader, cfg Config, start stateFunc) (Result, error) {
b, err := ioutil.ReadAll(r)
if err != nil {
return nil, errors.Wrap(err, "failed to read page content")
}
return parseBytes(b, cfg, start)
}
func parseBytes(b []byte, cfg Config, start stateFunc) (Result, error) {
lexer := newPageLexer(b, start, cfg)
lexer.run()
return lexer, nil
}
// 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"), true}
// Current will repeatably return the current item.
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
}
|
