summaryrefslogtreecommitdiff
path: root/utils/format/html.go
blob: 60e2e852a007bc761845173d95d1c46d942a6fb7 (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
package format

import (
	"html"
	"regexp"
	"strings"
)

func SanitizeHTML(htmlContent string) string {
	htmlContent = removeDangerousTags(htmlContent)
	htmlContent = removeEventHandlers(htmlContent)
	htmlContent = removeJavascriptProtocol(htmlContent)
	htmlContent = sanitizeStyles(htmlContent)
	return htmlContent
}

func removeDangerousTags(html string) string {
	dangerousTags := []string{
		"script", "iframe", "object", "embed", "applet",
		"meta", "link", "base", "form", "input", "button",
	}

	for _, tag := range dangerousTags {
		regex := regexp.MustCompile(`(?i)<` + tag + `[^>]*>[\s\S]*?</` + tag + `>`)
		html = regex.ReplaceAllString(html, "")
		regex = regexp.MustCompile(`(?i)<` + tag + `[^>]*>`)
		html = regex.ReplaceAllString(html, "")
	}

	return html
}

func removeEventHandlers(html string) string {
	eventHandlers := regexp.MustCompile(`(?i)\s*on\w+\s*=\s*["'][^"']*["']`)
	return eventHandlers.ReplaceAllString(html, "")
}

func removeJavascriptProtocol(html string) string {
	jsProtocol := regexp.MustCompile(`(?i)javascript:`)
	return jsProtocol.ReplaceAllString(html, "")
}

func sanitizeStyles(html string) string {
	dangerousStyles := []string{"behavior", "expression", "binding", "import", "moz-binding"}

	for _, style := range dangerousStyles {
		regex := regexp.MustCompile(`(?i)` + style + `\s*:\s*[^;]+;?`)
		html = regex.ReplaceAllString(html, "")
	}

	return html
}

func GenerateSnippet(bodyText, bodyHTML string) string {
	text := bodyText
	if text == "" && bodyHTML != "" {
		text = StripHTML(bodyHTML)
	}

	text = strings.TrimSpace(text)
	if len(text) > 150 {
		text = text[:150] + "..."
	}

	return text
}

func StripHTML(html string) string {
	text := html

	styleRegex := regexp.MustCompile(`(?i)<style[^>]*>[\s\S]*?</style>`)
	text = styleRegex.ReplaceAllString(text, "")

	scriptRegex := regexp.MustCompile(`(?i)<script[^>]*>[\s\S]*?</script>`)
	text = scriptRegex.ReplaceAllString(text, "")

	headRegex := regexp.MustCompile(`(?i)<head[^>]*>[\s\S]*?</head>`)
	text = headRegex.ReplaceAllString(text, "")

	text = strings.ReplaceAll(text, "<br>", "\n")
	text = strings.ReplaceAll(text, "<br/>", "\n")
	text = strings.ReplaceAll(text, "<br />", "\n")
	text = strings.ReplaceAll(text, "</p>", "\n\n")
	text = strings.ReplaceAll(text, "</div>", "\n")
	text = strings.ReplaceAll(text, "</tr>", "\n")
	text = strings.ReplaceAll(text, "</h1>", "\n")
	text = strings.ReplaceAll(text, "</h2>", "\n")
	text = strings.ReplaceAll(text, "</h3>", "\n")
	text = strings.ReplaceAll(text, "</li>", "\n")

	inTag := false
	var result strings.Builder
	for _, char := range text {
		if char == '<' {
			inTag = true
			continue
		}
		if char == '>' {
			inTag = false
			continue
		}
		if !inTag {
			result.WriteRune(char)
		}
	}

	cleanText := result.String()

	lines := strings.Split(cleanText, "\n")
	var cleanLines []string
	for _, line := range lines {
		line = strings.TrimSpace(line)
		if line != "" {
			cleanLines = append(cleanLines, line)
		}
	}

	return strings.TrimSpace(strings.Join(cleanLines, " "))
}

func HTMLToPlainText(htmlContent string) string {
	text := htmlContent

	text = regexp.MustCompile(`(?i)<style[^>]*>[\s\S]*?</style>`).ReplaceAllString(text, "")
	text = regexp.MustCompile(`(?i)<script[^>]*>[\s\S]*?</script>`).ReplaceAllString(text, "")
	text = regexp.MustCompile(`(?i)<head[^>]*>[\s\S]*?</head>`).ReplaceAllString(text, "")
	text = regexp.MustCompile(`(?i)<title[^>]*>[\s\S]*?</title>`).ReplaceAllString(text, "")

	text = regexp.MustCompile(`(?i)<br\s*/?>`).ReplaceAllString(text, "\n")
	text = regexp.MustCompile(`(?i)</p>`).ReplaceAllString(text, "\n\n")
	text = regexp.MustCompile(`(?i)</div>`).ReplaceAllString(text, "\n")
	text = regexp.MustCompile(`(?i)</tr>`).ReplaceAllString(text, "\n")
	text = regexp.MustCompile(`(?i)</h[1-6]>`).ReplaceAllString(text, "\n\n")
	text = regexp.MustCompile(`(?i)</li>`).ReplaceAllString(text, "\n")

	text = regexp.MustCompile(`<[^>]+>`).ReplaceAllString(text, "")

	text = strings.ReplaceAll(text, "&nbsp;", " ")
	text = strings.ReplaceAll(text, "&lt;", "<")
	text = strings.ReplaceAll(text, "&gt;", ">")
	text = strings.ReplaceAll(text, "&amp;", "&")
	text = strings.ReplaceAll(text, "&quot;", "\"")
	text = strings.ReplaceAll(text, "&#39;", "'")
	text = strings.ReplaceAll(text, "&#x27;", "'")

	text = regexp.MustCompile(`\n\s*\n\s*\n+`).ReplaceAllString(text, "\n\n")
	text = regexp.MustCompile(`[ \t]+`).ReplaceAllString(text, " ")

	lines := strings.Split(text, "\n")
	var cleanLines []string
	for _, line := range lines {
		trimmed := strings.TrimSpace(line)
		if trimmed != "" {
			cleanLines = append(cleanLines, trimmed)
		}
	}

	return strings.TrimSpace(strings.Join(cleanLines, "\n"))
}

func DecodeHTML(text string) string {
	return html.UnescapeString(text)
}