diff --git a/Package.swift b/Package.swift
index cc00745..f2a52e9 100644
--- a/Package.swift
+++ b/Package.swift
@@ -1,4 +1,4 @@
-// swift-tools-version:5.7
+// swift-tools-version:5.0
import PackageDescription
@@ -8,12 +8,7 @@ let package = Package(
.library(name: "SwiftSoup", targets: ["SwiftSoup"])
],
targets: [
- .target(name: "SwiftSoup",
- path: "Sources",
- exclude: [],
- resources: [.copy("PrivacyInfo.xcprivacy")]),
+ .target(name: "SwiftSoup", path: "Sources"),
.testTarget(name: "SwiftSoupTests", dependencies: ["SwiftSoup"])
]
)
-
-
diff --git a/README.md b/README.md
index 5a0eb88..8de2990 100644
--- a/README.md
+++ b/README.md
@@ -2,7 +2,7 @@
-[](https://bdsmovement.net/)
+
[](https://github.com/apple/swift-package-manager)
@@ -12,9 +12,6 @@
[](http://cocoapods.org/pods/SwiftSoup)
[](http://twitter.com/scinfu)
-[](https://bdsmovement.net/)
-
-
`SwiftSoup` is a pure Swift library, cross-platform (macOS, iOS, tvOS, watchOS and Linux!), for working with real-world HTML. It provides a very convenient API for extracting and manipulating data, using the best of DOM, CSS, and jQuery-like methods.
`SwiftSoup` implements the WHATWG HTML5 specification, and parses HTML to the same DOM as modern browsers do.
* Scrape and parse HTML from a URL, file, or string
@@ -214,46 +211,6 @@ do {
}
```
-If you supply a whole HTML document, with a `` tag, the `clean(_: String, _: String, _: Whitelist)` method will just return the cleaned body HTML.
-You can clean both `` and `` by providing a `Whitelist` for each tags.
-
-```swift
-do {
- let unsafe: String = """
-
-
- Hey
-
-
-
- Hello, world!
-
-
- """
-
- var headWhitelist: Whitelist = {
- do {
- let customWhitelist = Whitelist.none()
- try customWhitelist
- .addTags("meta", "style", "title")
- return customWhitelist
- } catch {
- fatalError("Couldn't init head whitelist")
- }
- }()
-
- let unsafeDocument: Document = try SwiftSoup.parse(unsafe)
- let safe: String = try SwiftSoup.Cleaner(headWhitelist: headWhitelist, bodyWhitelist: .relaxed())
- .clean(unsafeDocument)
- .html()
- // now: HeyHello, world!
-} catch Exception.Error(let type, let message) {
- print(message)
-} catch {
- print("error")
-}
-```
-
### Discussion
A cross-site scripting attack against your site can really ruin your day, not to mention your users'. Many sites avoid XSS attacks by not allowing HTML in user submitted content: they enforce plain text only, or use an alternative markup syntax like wiki-text or Markdown. These are seldom optimal solutions for the user, as they lower expressiveness, and force the user to learn a new syntax.
diff --git a/Sources/Element.swift b/Sources/Element.swift
index 2566d1a..630b991 100644
--- a/Sources/Element.swift
+++ b/Sources/Element.swift
@@ -1226,9 +1226,9 @@ open class Element: Node {
// selfclosing includes unknown tags, isEmpty defines tags that are always empty
if (childNodes.isEmpty && _tag.isSelfClosing()) {
if (out.syntax() == OutputSettings.Syntax.html && _tag.isEmpty()) {
- accum.append(" />") // ![]()
for "always empty" tags. selfclosing is ignored but retained for xml/xhtml compatibility
+ accum.append(">")
} else {
- accum.append(" />") // ![]()
in xml
+ accum.append(" />") // ![]()
in html, ![]()
in xml
}
} else {
accum.append(">")
diff --git a/Sources/HtmlTreeBuilderState.swift b/Sources/HtmlTreeBuilderState.swift
index 2811c02..30bf24a 100644
--- a/Sources/HtmlTreeBuilderState.swift
+++ b/Sources/HtmlTreeBuilderState.swift
@@ -1530,17 +1530,17 @@ enum HtmlTreeBuilderState: String, HtmlTreeBuilderStateProtocol {
}
private static func handleRcData(_ startTag: Token.StartTag, _ tb: HtmlTreeBuilder)throws {
+ try tb.insert(startTag)
tb.tokeniser.transition(TokeniserState.Rcdata)
tb.markInsertionMode()
tb.transition(.Text)
- try tb.insert(startTag)
}
private static func handleRawtext(_ startTag: Token.StartTag, _ tb: HtmlTreeBuilder)throws {
+ try tb.insert(startTag)
tb.tokeniser.transition(TokeniserState.Rawtext)
tb.markInsertionMode()
tb.transition(.Text)
- try tb.insert(startTag)
}
// lists of tags to search through. A little harder to read here, but causes less GC than dynamic varargs.
diff --git a/Sources/NodeTraversor.swift b/Sources/NodeTraversor.swift
index 9a037d7..02d3a02 100644
--- a/Sources/NodeTraversor.swift
+++ b/Sources/NodeTraversor.swift
@@ -23,29 +23,28 @@ class NodeTraversor {
* Start a depth-first traverse of the root and all of its descendants.
* @param root the root node point to traverse.
*/
- open func traverse(_ root: Node?) throws {
+ open func traverse(_ root: Node?)throws {
var node: Node? = root
var depth: Int = 0
while (node != nil) {
- try visitor.head(node!, depth)
- if (node!.childNodeSize() > 0) {
- node = node!.childNode(0)
- depth+=1
- } else {
- while (node!.nextSibling() == nil && depth > 0) {
- let parent = node!.getParentNode()
- try visitor.tail(node!, depth)
- node = parent
- depth-=1
- }
- let nextSib = node!.nextSibling()
- try visitor.tail(node!, depth)
- if (node === root) {
- break
- }
- node = nextSib
- }
+ try visitor.head(node!, depth)
+ if (node!.childNodeSize() > 0) {
+ node = node!.childNode(0)
+ depth+=1
+ } else {
+ while (node!.nextSibling() == nil && depth > 0) {
+ try visitor.tail(node!, depth)
+ node = node!.getParentNode()
+ depth-=1
+ }
+ try visitor.tail(node!, depth)
+ if (node === root) {
+ break
+ }
+ node = node!.nextSibling()
+ }
}
}
+
}
diff --git a/Sources/NodeVisitor.swift b/Sources/NodeVisitor.swift
index 3f20e43..4d6d7c2 100644
--- a/Sources/NodeVisitor.swift
+++ b/Sources/NodeVisitor.swift
@@ -18,7 +18,7 @@ import Foundation
*/
public protocol NodeVisitor {
/**
- * Callback for when a node is first visited. {@code head} cannot safely call {@code node.remove()}.
+ * Callback for when a node is first visited.
*
* @param node the node being visited.
* @param depth the depth of the node, relative to the root node. E.g., the root node has depth 0, and a child node
@@ -27,7 +27,7 @@ public protocol NodeVisitor {
func head(_ node: Node, _ depth: Int)throws
/**
- * Callback for when a node is last visited, after all of its descendants have been visited. {@code tail} can safely call {@code node.remove()}.
+ * Callback for when a node is last visited, after all of its descendants have been visited.
*
* @param node the node being visited.
* @param depth the depth of the node, relative to the root node. E.g., the root node has depth 0, and a child node
diff --git a/Sources/PrivacyInfo.xcprivacy b/Sources/PrivacyInfo.xcprivacy
deleted file mode 100644
index 393cde2..0000000
--- a/Sources/PrivacyInfo.xcprivacy
+++ /dev/null
@@ -1,16 +0,0 @@
-
-
-
-
- NSPrivacyTracking
-
- NSPrivacyTrackingDomains
-
- NSPrivacyCollectedDataTypes
-
-
- NSPrivacyAccessedAPITypes
-
-
-
-
diff --git a/Sources/TokeniserState.swift b/Sources/TokeniserState.swift
index e55d79b..707248a 100644
--- a/Sources/TokeniserState.swift
+++ b/Sources/TokeniserState.swift
@@ -1097,8 +1097,7 @@ enum TokeniserState: TokeniserStateProtocol {
break
case TokeniserStateVars.eof:
t.eofError(self)
- // note: fall through to > case
- fallthrough
+ // note: fall through to > case
case ">": // catch invalid
t.error(self)
t.createDoctypePending()
diff --git a/SwiftSoup.podspec b/SwiftSoup.podspec
index 602db0f..85715da 100644
--- a/SwiftSoup.podspec
+++ b/SwiftSoup.podspec
@@ -8,7 +8,7 @@
Pod::Spec.new do |s|
s.name = 'SwiftSoup'
- s.version = '2.7.2'
+ s.version = '2.6.0'
s.summary = 'Swift HTML Parser / Reader, XML , with best of DOM, CSS, and jquery'
s.description = <<-DESC
SwiftSoup is a Swift library for working with real-world HTML. It provides a very convenient API for extracting and manipulating data, using the best of DOM, CSS, and jquery-like methods.
@@ -31,8 +31,4 @@ SwiftSoup is a Swift library for working with real-world HTML. It provides a ver
#s.resource_bundles = {
# 'SwiftSoup' => ['Assets/*.properties']
#}
- s.ios.resource_bundles = {'SwiftSoup' => ['Sources/PrivacyInfo.xcprivacy']}
- s.osx.resource_bundles = {'SwiftSoup' => ['Sources/PrivacyInfo.xcprivacy']}
- s.watchos.resource_bundles = {'SwiftSoup' => ['Sources/PrivacyInfo.xcprivacy']}
- s.tvos.resource_bundles = {'SwiftSoup' => ['Sources/PrivacyInfo.xcprivacy']}
end
diff --git a/SwiftSoup.xcodeproj/project.pbxproj b/SwiftSoup.xcodeproj/project.pbxproj
index b8e6549..e64b3cc 100644
--- a/SwiftSoup.xcodeproj/project.pbxproj
+++ b/SwiftSoup.xcodeproj/project.pbxproj
@@ -15,10 +15,6 @@
6710743227F580530048E7C1 /* Mutex.swift in Sources */ = {isa = PBXBuildFile; fileRef = 6710743027F580530048E7C1 /* Mutex.swift */; };
6710743327F580530048E7C1 /* Mutex.swift in Sources */ = {isa = PBXBuildFile; fileRef = 6710743027F580530048E7C1 /* Mutex.swift */; };
6710743427F580530048E7C1 /* Mutex.swift in Sources */ = {isa = PBXBuildFile; fileRef = 6710743027F580530048E7C1 /* Mutex.swift */; };
- 722E96332B7DF76400936F48 /* PrivacyInfo.xcprivacy in Resources */ = {isa = PBXBuildFile; fileRef = 722E96322B7DF76400936F48 /* PrivacyInfo.xcprivacy */; };
- 722E96342B7DF76400936F48 /* PrivacyInfo.xcprivacy in Resources */ = {isa = PBXBuildFile; fileRef = 722E96322B7DF76400936F48 /* PrivacyInfo.xcprivacy */; };
- 722E96352B7DF76400936F48 /* PrivacyInfo.xcprivacy in Resources */ = {isa = PBXBuildFile; fileRef = 722E96322B7DF76400936F48 /* PrivacyInfo.xcprivacy */; };
- 722E96362B7DF76400936F48 /* PrivacyInfo.xcprivacy in Resources */ = {isa = PBXBuildFile; fileRef = 722E96322B7DF76400936F48 /* PrivacyInfo.xcprivacy */; };
8C19C82F1DB7E5D200B8FC22 /* Tokeniser.swift in Sources */ = {isa = PBXBuildFile; fileRef = 8C19C82E1DB7E5D200B8FC22 /* Tokeniser.swift */; };
8C19C8311DB7E8CD00B8FC22 /* ParseError.swift in Sources */ = {isa = PBXBuildFile; fileRef = 8C19C8301DB7E8CD00B8FC22 /* ParseError.swift */; };
8C19C8331DB7ECB700B8FC22 /* ParseErrorList.swift in Sources */ = {isa = PBXBuildFile; fileRef = 8C19C8321DB7ECB700B8FC22 /* ParseErrorList.swift */; };
@@ -302,7 +298,6 @@
/* Begin PBXFileReference section */
6710742B27F57FA60048E7C1 /* UnfairLock.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = UnfairLock.swift; sourceTree = ""; };
6710743027F580530048E7C1 /* Mutex.swift */ = {isa = PBXFileReference; lastKnownFileType = sourcecode.swift; path = Mutex.swift; sourceTree = ""; };
- 722E96322B7DF76400936F48 /* PrivacyInfo.xcprivacy */ = {isa = PBXFileReference; lastKnownFileType = text.xml; path = PrivacyInfo.xcprivacy; sourceTree = ""; };
8C19C82E1DB7E5D200B8FC22 /* Tokeniser.swift */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.swift; path = Tokeniser.swift; sourceTree = ""; };
8C19C8301DB7E8CD00B8FC22 /* ParseError.swift */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.swift; path = ParseError.swift; sourceTree = ""; };
8C19C8321DB7ECB700B8FC22 /* ParseErrorList.swift */ = {isa = PBXFileReference; fileEncoding = 4; lastKnownFileType = sourcecode.swift; path = ParseErrorList.swift; sourceTree = ""; };
@@ -615,7 +610,6 @@
BD3B5BAA1FBED934001FDB3B /* InfoMac.plist */,
BD3B5BED1FC063BD001FDB3B /* InfotvOS.plist */,
BD3B5C301FC06424001FDB3B /* InfoWatchOS.plist */,
- 722E96322B7DF76400936F48 /* PrivacyInfo.xcprivacy */,
);
path = Sources;
sourceTree = "";
@@ -909,7 +903,6 @@
isa = PBXResourcesBuildPhase;
buildActionMask = 2147483647;
files = (
- 722E96332B7DF76400936F48 /* PrivacyInfo.xcprivacy in Resources */,
);
runOnlyForDeploymentPostprocessing = 0;
};
@@ -937,7 +930,6 @@
isa = PBXResourcesBuildPhase;
buildActionMask = 2147483647;
files = (
- 722E96342B7DF76400936F48 /* PrivacyInfo.xcprivacy in Resources */,
);
runOnlyForDeploymentPostprocessing = 0;
};
@@ -945,7 +937,6 @@
isa = PBXResourcesBuildPhase;
buildActionMask = 2147483647;
files = (
- 722E96352B7DF76400936F48 /* PrivacyInfo.xcprivacy in Resources */,
);
runOnlyForDeploymentPostprocessing = 0;
};
@@ -953,7 +944,6 @@
isa = PBXResourcesBuildPhase;
buildActionMask = 2147483647;
files = (
- 722E96362B7DF76400936F48 /* PrivacyInfo.xcprivacy in Resources */,
);
runOnlyForDeploymentPostprocessing = 0;
};