aboutsummaryrefslogtreecommitdiff
path: root/hswg/main.go
blob: 595bb4a7a1f03df5788fb10d6e4a922892dec75f (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
// Program hswg is a static website generator employing libasciidoc with added
// support for two-line/underlined titles, and postprocessing "wiki" InterLinks.
package main

import (
	"bytes"
	"fmt"
	"io"
	"io/ioutil"
	"log"
	"os"
	"path/filepath"
	"regexp"
	"sort"
	"strings"
	"time"
	"unicode"
	"unicode/utf8"

	"github.com/bytesparadise/libasciidoc"
	"github.com/bytesparadise/libasciidoc/pkg/configuration"
	"github.com/bytesparadise/libasciidoc/pkg/types"
)

// isTitle returns the title level if the lines seem to form a title,
// zero otherwise. Input lines may inclide trailing newlines.
func isTitle(line1, line2 []byte) int {
	// This is a very naïve method, we should target graphemes (thus at least
	// NFC normalize the lines first) and account for wide characters.
	diff := utf8.RuneCount(line1) - utf8.RuneCount(line2)
	if len(line2) < 2 || diff < -1 || diff > 1 {
		return 0
	}

	// "Don't be fooled by back-to-back delimited blocks."
	// Still gets fooled by other things, though.
	if bytes.IndexFunc(line1, func(r rune) bool {
		return unicode.IsLetter(r) || unicode.IsNumber(r)
	}) < 0 {
		return 0
	}

	// The underline must be homogenous.
	for _, r := range bytes.TrimRight(line2, "\r\n") {
		if r != line2[0] {
			return 0
		}
	}
	return 1 + strings.IndexByte("=-~^+", line2[0])
}

func writeLine(w *io.PipeWriter, cur, next []byte) []byte {
	if level := isTitle(cur, next); level > 0 {
		w.Write(append(bytes.Repeat([]byte{'='}, level), ' '))
		next = nil
	}
	w.Write(cur)
	return next
}

// ConvertTitles converts AsciiDoc two-line (underlined) titles to single-line.
func ConvertTitles(w *io.PipeWriter, input []byte) {
	var last []byte
	for _, cur := range bytes.SplitAfter(input, []byte{'\n'}) {
		last = writeLine(w, last, cur)
	}
	writeLine(w, last, nil)
}

// entry contains all context information about a single page.
type entry struct {
	path      string         // path
	mtime     time.Time      // modification time
	metadata  types.Metadata // metadata
	document  []byte         // inner document with expanded LinkWords
	backlinks []string       // what documents link back here
}

var extRE = regexp.MustCompile(`\.[^/.]*$`)

func stripExtension(path string) string {
	return extRE.ReplaceAllString(path, "")
}

func resultPath(path string) string {
	if m := extRE.FindStringIndex(path); m != nil {
		return path[:m[0]] + ".html"
	}
	return path + ".html"
}

func makeLink(m *map[string]*entry, name string) string {
	e := (*m)[name]
	return fmt.Sprintf("<a href='%s'>%s</a>", resultPath(e.path), name)
}

var linkWordRE = regexp.MustCompile(`\b\p{Lu}\p{L}*\b`)

func expand(m *map[string]*entry, name string, chunk []byte) []byte {
	return linkWordRE.ReplaceAllFunc(chunk, func(match []byte) []byte {
		if link, ok := (*m)[string(match)]; ok {
			link.backlinks = append(link.backlinks, name)
			return []byte(makeLink(m, string(match)))
		}
		return match
	})
}

func main() {
	if len(os.Args) < 3 {
		log.Fatalf("usage: %s TEMPLATE GLOB...\n", os.Args[0])
	}

	// Read the common page header.
	header, err := ioutil.ReadFile(os.Args[1])
	if err != nil {
		log.Fatalln(err)
	}

	// Create a map from document names to their page entries.
	entries := map[string]*entry{}
	for _, glob := range os.Args[2:] {
		matches, err := filepath.Glob(glob)
		if err != nil {
			log.Fatalf("%s: %s\n", glob, err)
		}
		for _, path := range matches {
			name := stripExtension(filepath.Base(path))
			if conflict, ok := entries[name]; ok {
				log.Fatalf("%s: conflicts with %s\n", name, conflict.path)
			}
			entries[name] = &entry{path: path}
		}
	}

	tagRE := regexp.MustCompile(`<[^<>]+>`)
	for name, e := range entries {
		f, err := os.Open(e.path)
		if err != nil {
			log.Fatalln(err)
		}

		if i, err := f.Stat(); err != nil {
			log.Fatalln(err)
		} else {
			e.mtime = i.ModTime()
		}

		input, err := ioutil.ReadAll(f)
		if err != nil {
			log.Fatalln(err)
		}

		pr, pw := io.Pipe()
		go func() {
			defer pw.Close()
			ConvertTitles(pw, input)
		}()

		config := configuration.NewConfiguration(
			configuration.WithHeaderFooter(false),
			configuration.WithFilename(e.path),
			configuration.WithLastUpdated(e.mtime),
		)

		buf := bytes.NewBuffer(nil)
		e.metadata, err = libasciidoc.ConvertToHTML(pr, buf, config)
		if err != nil {
			log.Fatalln(err)
		}

		// Expand LinkWords anywhere between <tags>.
		// We want something like the inverse of Regexp.ReplaceAllStringFunc.
		raw, last, expanded := buf.Bytes(), 0, bytes.NewBuffer(nil)
		for _, where := range tagRE.FindAllIndex(raw, -1) {
			_, _ = expanded.Write(expand(&entries, name, raw[last:where[0]]))
			_, _ = expanded.Write(raw[where[0]:where[1]])
			last = where[1]
		}
		_, _ = expanded.Write(expand(&entries, name, raw[last:]))
		e.document = expanded.Bytes()
	}

	for name, e := range entries {
		f, err := os.Create(resultPath(e.path))
		if err != nil {
			log.Fatalln(err)
		}

		_, _ = f.Write(header)

		title := e.metadata.Title
		if title == "" {
			title = name
		}

		_, _ = f.WriteString(fmt.Sprintf("<title>%s</title>\n", title))
		_, _ = f.WriteString(fmt.Sprintf("<h1>%s</h1>\n", title))

		sort.Strings(e.backlinks)

		backlinks := []string{}
		for _, name := range e.backlinks {
			backlinks = append(backlinks, makeLink(&entries, name))
		}

		if len(backlinks) > 0 {
			_, _ = f.WriteString(fmt.Sprintf("<p id=links>Links here: %s</p>\n",
				strings.Join(backlinks, ", ")))
		}

		_, _ = f.Write(e.document)
		_, _ = f.WriteString(fmt.Sprintf("<p id=footer>Last updated: %s"+
			" &mdash; <a href='%s'>Source</p>\n",
			e.metadata.LastUpdated, e.path))
	}
}