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?)`)
32var re_link = regexp.MustCompile(`.?.?https?://[^\s"]+[\w/)!]`)
33var re_zerolink = regexp.MustCompile(`\[([^]]*)\]\(([^)]*\)?)\)`)
34var re_imgfix = regexp.MustCompile(`<img ([^>]*)>`)
35
36var lighter = synlight.New(synlight.Options{Format: synlight.HTML})
37
38func markitzero(s string) string {
39 // prepare the string
40 s = strings.TrimSpace(s)
41 s = strings.Replace(s, "\r", "", -1)
42
43 // save away the code blocks so we don't mess them up further
44 var bigcodes, lilcodes, images []string
45 s = re_bigcoder.ReplaceAllStringFunc(s, func(code string) string {
46 bigcodes = append(bigcodes, code)
47 return "``````"
48 })
49 s = re_coder.ReplaceAllStringFunc(s, func(code string) string {
50 lilcodes = append(lilcodes, code)
51 return "`x`"
52 })
53 s = re_imgfix.ReplaceAllStringFunc(s, func(img string) string {
54 images = append(images, img)
55 return "<img x>"
56 })
57
58 // fewer side effects than html.EscapeString
59 buf := make([]byte, 0, len(s))
60 for _, c := range []byte(s) {
61 switch c {
62 case '&':
63 buf = append(buf, []byte("&")...)
64 case '<':
65 buf = append(buf, []byte("<")...)
66 case '>':
67 buf = append(buf, []byte(">")...)
68 default:
69 buf = append(buf, c)
70 }
71 }
72 s = string(buf)
73
74 // mark it zero
75 s = re_link.ReplaceAllStringFunc(s, linkreplacer)
76 s = re_zerolink.ReplaceAllString(s, `<a href="$2">$1</a>`)
77 s = re_bolder.ReplaceAllString(s, "$1<b>$2</b>$3")
78 s = re_italicer.ReplaceAllString(s, "$1<i>$2</i>$3")
79 s = re_quoter.ReplaceAllString(s, "<blockquote>$1</blockquote><p>")
80
81 // restore images
82 s = strings.Replace(s, "<img x>", "<img x>", -1)
83 s = re_imgfix.ReplaceAllStringFunc(s, func(string) string {
84 img := images[0]
85 images = images[1:]
86 return img
87 })
88
89 // now restore the code blocks
90 s = re_coder.ReplaceAllStringFunc(s, func(string) string {
91 code := lilcodes[0]
92 lilcodes = lilcodes[1:]
93 code = html.EscapeString(code)
94 return code
95 })
96 s = re_bigcoder.ReplaceAllStringFunc(s, func(string) string {
97 code := bigcodes[0]
98 bigcodes = bigcodes[1:]
99 m := re_bigcoder.FindStringSubmatch(code)
100 return "<pre><code>" + lighter.HighlightString(m[2], m[1]) + "</code></pre><p>"
101 })
102 s = re_coder.ReplaceAllString(s, "<code>$1</code>")
103
104 // some final fixups
105 s = strings.Replace(s, "\n", "<br>", -1)
106 s = strings.Replace(s, "<br><blockquote>", "<blockquote>", -1)
107 s = strings.Replace(s, "<br><pre>", "<pre>", -1)
108 s = strings.Replace(s, "<p><br>", "<p>", -1)
109 return s
110}
111
112func linkreplacer(url string) string {
113 if url[0:2] == "](" {
114 return url
115 }
116 prefix := ""
117 for !strings.HasPrefix(url, "http") {
118 prefix += url[0:1]
119 url = url[1:]
120 }
121 addparen := false
122 adddot := false
123 if strings.HasSuffix(url, ")") && strings.IndexByte(url, '(') == -1 {
124 url = url[:len(url)-1]
125 addparen = true
126 }
127 if strings.HasSuffix(url, ".") {
128 url = url[:len(url)-1]
129 adddot = true
130 }
131 url = fmt.Sprintf(`<a href="%s">%s</a>`, url, url)
132 if adddot {
133 url += "."
134 }
135 if addparen {
136 url += ")"
137 }
138 return prefix + url
139}