Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: Clean head and body from html document #719

Merged
merged 2 commits into from
May 1, 2023
Merged

feat: Clean head and body from html document #719

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
33c559a
feat: Clean head and body from html document
valentinperignon Apr 27, 2023
f2669d0
feat: Add "hr" and "dir"
valentinperignon May 1, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions .package.resolved
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -236,10 +236,10 @@
{
"identity" : "swiftsoup",
"kind" : "remoteSourceControl",
"location" : "https://github.com/scinfu/SwiftSoup",
"location" : "https://github.com/valentinperignon/SwiftSoup",
"state" : {
"revision" : "f707b8680cddb96dc1855632340a572ef37bbb98",
"version" : "2.5.3"
"branch" : "try-headcleaner",
"revision" : "05c6c880a5056421de271012faa8bd0a42c2e0a8"
}
},
{
Expand Down
1 change: 0 additions & 1 deletion MailCore/Utils/Constants.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -65,7 +65,6 @@ public enum Constants {
try! NSRegularExpression(pattern: ">\\s*<|>?\\s+<?")
}()

public static let extendedWhitelist = Whitelist.extendedWhitelist
public static let customCss = (try? String(contentsOfFile: Bundle.main.path(forResource: "style", ofType: "css") ?? "",
encoding: .utf8).replacingOccurrences(of: "\n", with: "")) ?? ""

Expand Down
19 changes: 17 additions & 2 deletions MailCore/Utils/MessageBodyUtils.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,10 +66,25 @@ public enum MessageBodyUtils {
}
return nil
}

public static func cleanHtmlContent(rawHtml: String) -> String? {
do {
return try SwiftSoup.clean(rawHtml, Constants.extendedWhitelist)
let dirtyDocument = try SwiftSoup.parse(rawHtml)
let cleanedDocument = try SwiftSoup.Cleaner(headWhitelist: .headWhitelist, bodyWhitelist: .extendedBodyWhitelist)
.clean(dirtyDocument)

// We need to remove the tag <meta http-equiv="refresh" content="x">
let metaRefreshTags = try cleanedDocument.select("meta[http-equiv='refresh']")
for metaRefreshTag in metaRefreshTags {
try metaRefreshTag.parent()?.removeChild(metaRefreshTag)
}

// If `<body>` has a style attribute, keep it
if let bodyStyleAttribute = try dirtyDocument.body()?.attr("style") {
try cleanedDocument.body()?.attr("style", bodyStyleAttribute)
}

return try cleanedDocument.outerHtml()
} catch {
DDLogError("An error occurred while parsing body \(error)")
return nil
Expand Down
93 changes: 20 additions & 73 deletions MailCore/Utils/Whitelist+Extension.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,87 +20,34 @@ import Foundation
import SwiftSoup

extension Whitelist {
static var extendedWhitelist: Whitelist {
static var headWhitelist: Whitelist {
do {
let customWhitelist = Whitelist.none()
let allowedTags = [
"a",
"b",
"blockquote",
"body",
"br",
"caption",
"center",
"cite",
"code",
"col",
"colgroup",
"dd",
"div",
"dl",
"dt",
"em",
"h1",
"h2",
"h3",
"h4",
"h5",
"h6",
"head",
"hr",
"html",
"i",
"img",
"li",
"meta",
"ol",
"p",
"pre",
"q",
"small",
"span",
"strike",
"strong",
"style",
"sub",
"sup",
"table",
"tbody",
"td",
"tfoot",
"th",
"thead",
"title",
"tr",
"u",
"ul",
]
try customWhitelist
.addTags("base", "meta", "style", "title")
.addAttributes("style", "media", "type")
.addAttributes("meta", "charset", "content", "http-equiv", "name")
.addAttributes("base", "href", "target")
.addProtocols("base", "href", "http", "https")

for tag in allowedTags {
try customWhitelist.addTags(tag)
try customWhitelist.addAttributes(tag, "style", "width", "height", "class", "align")
}
return customWhitelist
} catch {
fatalError("Couldn't init head whitelist")
}
}

static var extendedBodyWhitelist: Whitelist {
do {
let customWhitelist = try Whitelist.relaxed()
try customWhitelist
.addAttributes("a", "href", "title")
.addAttributes("blockquote", "cite")
.addAttributes("col", "span")
.addAttributes("colgroup", "span")
.addAttributes("img", "align", "alt", "src", "title")
.addAttributes("ol", "start", "type")
.addAttributes("q", "cite")
.addAttributes("table", "summary")
.addAttributes("td", "abbr", "axis", "colspan", "rowspan")
.addAttributes("th", "abbr", "axis", "colspan", "rowspan", "scope")
.addAttributes("ul", "type")
.addTags("center", "hr", "style")
.addAttributes(":all", "align", "bgcolor", "border", "class", "dir", "height", "id", "style", "width")
.addAttributes("td", "valign")
.addProtocols("img", "src", "cid", "data")

.addProtocols("a", "href", "http", "https", "mailto")
.addProtocols("blockquote", "cite", "http", "https")
.addProtocols("cite", "cite", "http", "https")
.addProtocols("q", "cite", "http", "https")
return customWhitelist
} catch {
fatalError("Couldn't init html whitelist")
fatalError("Couldn't init body whitelist")
}
}
}
2 changes: 1 addition & 1 deletion Project.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -47,7 +47,7 @@ let project = Project(name: "Mail",
.package(url: "https://github.com/SCENEE/FloatingPanel", .upToNextMajor(from: "2.0.0")),
.package(url: "https://github.com/kean/Nuke", .upToNextMajor(from: "12.0.0")),
.package(url: "https://github.com/airbnb/lottie-ios", .exact("3.5.0")),
.package(url: "https://github.com/scinfu/SwiftSoup", .upToNextMajor(from: "2.5.3")),
.package(url: "https://github.com/valentinperignon/SwiftSoup", .branch("try-headcleaner")),
.package(url: "https://github.com/johnpatrickmorgan/NavigationBackport", .upToNextMajor(from: "0.7.2")),
.package(url: "https://github.com/aheze/Popovers", .upToNextMajor(from: "1.3.2"))
],
Expand Down