markitzero.go (view raw)
1//
2// Copyright (c) 2019 Ted Unangst <tedu@tedunangst.com>
3//
4// Permission to use, copy, modify, and distribute this software for any
5// purpose with or without fee is hereby granted, provided that the above
6// copyright notice and this permission notice appear in all copies.
7//
8// THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
9// WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
10// MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
11// ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
12// WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
13// ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
14// OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
15
16package main
17
18import (
19 "fmt"
20 "regexp"
21 "strings"
22
23 "golang.org/x/net/html"
24 "humungus.tedunangst.com/r/webs/synlight"
25)
26
27var re_bolder = regexp.MustCompile(`(^|\W)\*\*((?s:.*?))\*\*($|\W)`)
28var re_italicer = regexp.MustCompile(`(^|\W)\*((?s:.*?))\*($|\W)`)
29var re_bigcoder = regexp.MustCompile("```(.*)\n?((?s:.*?))\n?```\n?")
30var re_coder = regexp.MustCompile("`([^`]*)`")
31var re_quoter = regexp.MustCompile(`(?m:^> (.*)(\n- ?(.*))?\n?)`)
32var re_reciter = regexp.MustCompile(`(<cite><a href=".*?">)https://twitter.com/([^/]+)/.*?(</a></cite>)`)
33var re_link = regexp.MustCompile(`.?.?https?://[^\s"]+[\w/)!]`)
34var re_zerolink = regexp.MustCompile(`\[([^]]*)\]\(([^)]*\)?)\)`)
35var re_imgfix = regexp.MustCompile(`<img ([^>]*)>`)
36var re_lister = regexp.MustCompile(`((^|\n)(\+|-).*)+\n?`)
37var re_tabler = regexp.MustCompile(`((^|\n)\|.*)+\n?`)
38
39var lighter = synlight.New(synlight.Options{Format: synlight.HTML})
40
41func markitzero(s string) string {
42 // prepare the string
43 s = strings.TrimSpace(s)
44 s = strings.Replace(s, "\r", "", -1)
45
46 // save away the code blocks so we don't mess them up further
47 var bigcodes, lilcodes, images []string
48 s = re_bigcoder.ReplaceAllStringFunc(s, func(code string) string {
49 bigcodes = append(bigcodes, code)
50 return "``````"
51 })
52 s = re_coder.ReplaceAllStringFunc(s, func(code string) string {
53 lilcodes = append(lilcodes, code)
54 return "`x`"
55 })
56 s = re_imgfix.ReplaceAllStringFunc(s, func(img string) string {
57 images = append(images, img)
58 return "<img x>"
59 })
60
61 // fewer side effects than html.EscapeString
62 buf := make([]byte, 0, len(s))
63 for _, c := range []byte(s) {
64 switch c {
65 case '&':
66 buf = append(buf, []byte("&")...)
67 case '<':
68 buf = append(buf, []byte("<")...)
69 case '>':
70 buf = append(buf, []byte(">")...)
71 default:
72 buf = append(buf, c)
73 }
74 }
75 s = string(buf)
76
77 // mark it zero
78 if strings.Contains(s, "http") {
79 s = re_link.ReplaceAllStringFunc(s, linkreplacer)
80 }
81 s = re_zerolink.ReplaceAllString(s, `<a href="$2">$1</a>`)
82 if strings.Contains(s, "*") {
83 s = re_bolder.ReplaceAllString(s, "$1<b>$2</b>$3")
84 s = re_italicer.ReplaceAllString(s, "$1<i>$2</i>$3")
85 }
86 s = re_quoter.ReplaceAllString(s, "<blockquote>$1<br><cite>$3</cite></blockquote><p>")
87 s = re_reciter.ReplaceAllString(s, "$1$2$3")
88 s = strings.Replace(s, "\n---\n", "<hr><p>", -1)
89
90 s = re_lister.ReplaceAllStringFunc(s, func(m string) string {
91 m = strings.Trim(m, "\n")
92 items := strings.Split(m, "\n")
93 r := "<ul>"
94 for _, item := range items {
95 r += "<li>" + strings.Trim(item[1:], " ")
96 }
97 r += "</ul><p>"
98 return r
99 })
100 s = re_tabler.ReplaceAllStringFunc(s, func(m string) string {
101 m = strings.Trim(m, "\n")
102 rows := strings.Split(m, "\n")
103 var r strings.Builder
104 r.WriteString("<table>")
105 alignments := make(map[int]string)
106 for _, row := range rows {
107 hastr := false
108 cells := strings.Split(row, "|")
109 for i, cell := range cells {
110 cell = strings.TrimSpace(cell)
111 if cell == "" && (i == 0 || i == len(cells)-1) {
112 continue
113 }
114 switch cell {
115 case ":---":
116 alignments[i] = ` style="text-align: left"`
117 continue
118 case ":---:":
119 alignments[i] = ` style="text-align: center"`
120 continue
121 case "---:":
122 alignments[i] = ` style="text-align: right"`
123 continue
124 }
125 if !hastr {
126 r.WriteString("<tr>")
127 hastr = true
128 }
129 fmt.Fprintf(&r, "<td%s>", alignments[i])
130 r.WriteString(cell)
131 }
132 }
133 r.WriteString("</table><p>")
134 return r.String()
135 })
136
137 // restore images
138 s = strings.Replace(s, "<img x>", "<img x>", -1)
139 s = re_imgfix.ReplaceAllStringFunc(s, func(string) string {
140 img := images[0]
141 images = images[1:]
142 return img
143 })
144
145 // now restore the code blocks
146 s = re_coder.ReplaceAllStringFunc(s, func(string) string {
147 code := lilcodes[0]
148 lilcodes = lilcodes[1:]
149 code = html.EscapeString(code)
150 return code
151 })
152 s = re_bigcoder.ReplaceAllStringFunc(s, func(string) string {
153 code := bigcodes[0]
154 bigcodes = bigcodes[1:]
155 m := re_bigcoder.FindStringSubmatch(code)
156 return "<pre><code>" + lighter.HighlightString(m[2], m[1]) + "</code></pre><p>"
157 })
158 s = re_coder.ReplaceAllString(s, "<code>$1</code>")
159
160 // some final fixups
161 s = strings.Replace(s, "\n", "<br>", -1)
162 s = strings.Replace(s, "<br><blockquote>", "<blockquote>", -1)
163 s = strings.Replace(s, "<br><cite></cite>", "", -1)
164 s = strings.Replace(s, "<br><pre>", "<pre>", -1)
165 s = strings.Replace(s, "<br><ul>", "<ul>", -1)
166 s = strings.Replace(s, "<br><table>", "<table>", -1)
167 s = strings.Replace(s, "<p><br>", "<p>", -1)
168 return s
169}
170
171func linkreplacer(url string) string {
172 if url[0:2] == "](" {
173 return url
174 }
175 prefix := ""
176 for !strings.HasPrefix(url, "http") {
177 prefix += url[0:1]
178 url = url[1:]
179 }
180 addparen := false
181 adddot := false
182 if strings.HasSuffix(url, ")") && strings.IndexByte(url, '(') == -1 {
183 url = url[:len(url)-1]
184 addparen = true
185 }
186 if strings.HasSuffix(url, ".") {
187 url = url[:len(url)-1]
188 adddot = true
189 }
190 url = fmt.Sprintf(`<a href="%s">%s</a>`, url, url)
191 if adddot {
192 url += "."
193 }
194 if addparen {
195 url += ")"
196 }
197 return prefix + url
198}