summaryrefslogtreecommitdiffstats
path: root/hugofs/files/classifier.go
blob: bdac2d68698f6681d0c5aa2f440e51e8dbad03d8 (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
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
// 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 files

import (
	"bufio"
	"fmt"
	"io"
	"os"
	"path/filepath"
	"sort"
	"strings"
	"unicode"

	"github.com/spf13/afero"
)

const (
	// The NPM package.json "template" file.
	FilenamePackageHugoJSON = "package.hugo.json"
	// The NPM package file.
	FilenamePackageJSON = "package.json"

	FilenameHugoStatsJSON = "hugo_stats.json"
)

var (
	// This should be the only list of valid extensions for content files.
	contentFileExtensions = []string{
		"html", "htm",
		"mdown", "markdown", "md",
		"asciidoc", "adoc", "ad",
		"rest", "rst",
		"org",
		"pandoc", "pdc",
	}

	contentFileExtensionsSet map[string]bool

	htmlFileExtensions = []string{
		"html", "htm",
	}

	htmlFileExtensionsSet map[string]bool
)

func init() {
	contentFileExtensionsSet = make(map[string]bool)
	for _, ext := range contentFileExtensions {
		contentFileExtensionsSet[ext] = true
	}
	htmlFileExtensionsSet = make(map[string]bool)
	for _, ext := range htmlFileExtensions {
		htmlFileExtensionsSet[ext] = true
	}
}

func IsContentFile(filename string) bool {
	return contentFileExtensionsSet[strings.TrimPrefix(filepath.Ext(filename), ".")]
}

func IsIndexContentFile(filename string) bool {
	if !IsContentFile(filename) {
		return false
	}

	base := filepath.Base(filename)

	return strings.HasPrefix(base, "index.") || strings.HasPrefix(base, "_index.")
}

func IsHTMLFile(filename string) bool {
	return htmlFileExtensionsSet[strings.TrimPrefix(filepath.Ext(filename), ".")]
}

func IsContentExt(ext string) bool {
	return contentFileExtensionsSet[ext]
}

type ContentClass string

const (
	ContentClassLeaf    ContentClass = "leaf"
	ContentClassBranch  ContentClass = "branch"
	ContentClassFile    ContentClass = "zfile" // Sort below
	ContentClassContent ContentClass = "zcontent"
)

func (c ContentClass) IsBundle() bool {
	return c == ContentClassLeaf || c == ContentClassBranch
}

func ClassifyContentFile(filename string, open func() (afero.File, error)) ContentClass {
	if !IsContentFile(filename) {
		return ContentClassFile
	}

	if IsHTMLFile(filename) {
		// We need to look inside the file. If the first non-whitespace
		// character is a "<", then we treat it as a regular file.
		// Eearlier we created pages for these files, but that had all sorts
		// of troubles, and isn't what it says in the documentation.
		// See https://github.com/gohugoio/hugo/issues/7030
		if open == nil {
			panic(fmt.Sprintf("no file opener provided for %q", filename))
		}

		f, err := open()
		if err != nil {
			return ContentClassFile
		}
		ishtml := isHTMLContent(f)
		f.Close()
		if ishtml {
			return ContentClassFile
		}

	}

	if strings.HasPrefix(filename, "_index.") {
		return ContentClassBranch
	}

	if strings.HasPrefix(filename, "index.") {
		return ContentClassLeaf
	}

	return ContentClassContent
}

var htmlComment = []rune{'<', '!', '-', '-'}

func isHTMLContent(r io.Reader) bool {
	br := bufio.NewReader(r)
	i := 0
	for {
		c, _, err := br.ReadRune()
		if err != nil {
			break
		}

		if i > 0 {
			if i >= len(htmlComment) {
				return false
			}

			if c != htmlComment[i] {
				return true
			}

			i++
			continue
		}

		if !unicode.IsSpace(c) {
			if i == 0 && c != '<' {
				return false
			}
			i++
		}
	}
	return true
}

const (
	ComponentFolderArchetypes = "archetypes"
	ComponentFolderStatic     = "static"
	ComponentFolderLayouts    = "layouts"
	ComponentFolderContent    = "content"
	ComponentFolderData       = "data"
	ComponentFolderAssets     = "assets"
	ComponentFolderI18n       = "i18n"

	FolderResources = "resources"
	FolderJSConfig  = "_jsconfig" // Mounted below /assets with postcss.config.js etc.
)

var (
	JsConfigFolderMountPrefix = filepath.Join(ComponentFolderAssets, FolderJSConfig)

	ComponentFolders = []string{
		ComponentFolderArchetypes,
		ComponentFolderStatic,
		ComponentFolderLayouts,
		ComponentFolderContent,
		ComponentFolderData,
		ComponentFolderAssets,
		ComponentFolderI18n,
	}

	componentFoldersSet = make(map[string]bool)
)

func init() {
	sort.Strings(ComponentFolders)
	for _, f := range ComponentFolders {
		componentFoldersSet[f] = true
	}
}

// ResolveComponentFolder returns "content" from "content/blog/foo.md" etc.
func ResolveComponentFolder(filename string) string {
	filename = strings.TrimPrefix(filename, string(os.PathSeparator))
	for _, cf := range ComponentFolders {
		if strings.HasPrefix(filename, cf) {
			return cf
		}
	}

	return ""
}

func IsComponentFolder(name string) bool {
	return componentFoldersSet[name]
}