Skip to content

JSONSerialization: fix a crash when an escape sequence contains low-surrogate code point without the corresponding high-surrogate code point #1803

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

Merged
merged 1 commit into from
Dec 16, 2018
+53 −8
Merged

JSONSerialization: fix a crash when an escape sequence contains low-surrogate code point without the corresponding high-surrogate code point #1803

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
37 changes: 29 additions & 8 deletions Foundation/JSONSerialization.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -738,19 +738,40 @@ private struct JSONReader {
return nil
}

if !UTF16.isLeadSurrogate(codeUnit) {
let isLeadSurrogate = UTF16.isLeadSurrogate(codeUnit)
let isTrailSurrogate = UTF16.isTrailSurrogate(codeUnit)

guard isLeadSurrogate || isTrailSurrogate else {
// The code units that are neither lead surrogates nor trail surrogates
// form valid unicode scalars.
return (String(UnicodeScalar(codeUnit)!), index)
}

guard let (trailCodeUnit, finalIndex) = try consumeASCIISequence("\\u", input: index).flatMap(parseCodeUnit) , UTF16.isTrailSurrogate(trailCodeUnit) else {
throw NSError(domain: NSCocoaErrorDomain, code: CocoaError.propertyListReadCorrupt.rawValue, userInfo: [
"NSDebugDescription" : "Unable to convert unicode escape sequence (no low-surrogate code point) to UTF8-encoded character at position \(source.distanceFromStart(input))"
])
// Surrogates must always come in pairs.

guard isLeadSurrogate else {
// Trail surrogate must come after lead surrogate
throw CocoaError.error(.propertyListReadCorrupt,
userInfo: [
"NSDebugDescription" : """
Unable to convert unicode escape sequence (no high-surrogate code point) \
to UTF8-encoded character at position \(source.distanceFromStart(input))
"""
])
}

guard let (trailCodeUnit, finalIndex) = try consumeASCIISequence("\\u", input: index).flatMap(parseCodeUnit),
UTF16.isTrailSurrogate(trailCodeUnit) else {
throw CocoaError.error(.propertyListReadCorrupt,
userInfo: [
"NSDebugDescription" : """
Unable to convert unicode escape sequence (no low-surrogate code point) \
to UTF8-encoded character at position \(source.distanceFromStart(input))
"""
])
}

let highValue = (UInt32(codeUnit - 0xD800) << 10)
let lowValue = UInt32(trailCodeUnit - 0xDC00)
return (String(UnicodeScalar(highValue + lowValue + 0x10000)!), finalIndex)
return (String(UTF16.decode(UTF16.EncodedScalar([codeUnit, trailCodeUnit]))), finalIndex)
}

func isHexChr(_ byte: UInt8) -> Bool {
Expand Down
24 changes: 24 additions & 0 deletions TestFoundation/TestJSONSerialization.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -115,6 +115,7 @@ extension TestJSONSerialization {
("test_deserialize_invalidValueInArray_withData", test_deserialize_invalidValueInArray_withData),
("test_deserialize_badlyFormedArray_withData", test_deserialize_badlyFormedArray_withData),
("test_deserialize_invalidEscapeSequence_withData", test_deserialize_invalidEscapeSequence_withData),
("test_deserialize_unicodeMissingLeadingSurrogate_withData", test_deserialize_unicodeMissingLeadingSurrogate_withData),
("test_deserialize_unicodeMissingTrailingSurrogate_withData", test_deserialize_unicodeMissingTrailingSurrogate_withData),

//Deserialization with Stream
Expand Down Expand Up @@ -146,6 +147,7 @@ extension TestJSONSerialization {
("test_deserialize_invalidValueInArray_withStream", test_deserialize_invalidValueInArray_withStream),
("test_deserialize_badlyFormedArray_withStream", test_deserialize_badlyFormedArray_withStream),
("test_deserialize_invalidEscapeSequence_withStream", test_deserialize_invalidEscapeSequence_withStream),
("test_deserialize_unicodeMissingLeadingSurrogate_withStream", test_deserialize_unicodeMissingLeadingSurrogate_withStream),
("test_deserialize_unicodeMissingTrailingSurrogate_withStream", test_deserialize_unicodeMissingTrailingSurrogate_withStream),
("test_JSONObjectWithStream_withFile", test_JSONObjectWithStream_withFile),
("test_JSONObjectWithStream_withURL", test_JSONObjectWithStream_withURL),
Expand Down Expand Up @@ -242,6 +244,10 @@ extension TestJSONSerialization {
deserialize_invalidEscapeSequence(objectType: .data)
}

func test_deserialize_unicodeMissingLeadingSurrogate_withData() {
deserialize_unicodeMissingLeadingSurrogate(objectType: .data)
}

func test_deserialize_unicodeMissingTrailingSurrogate_withData() {
deserialize_unicodeMissingTrailingSurrogate(objectType: .data)
}
Expand Down Expand Up @@ -336,6 +342,10 @@ extension TestJSONSerialization {
deserialize_invalidEscapeSequence(objectType: .stream)
}

func test_deserialize_unicodeMissingLeadingSurrogate_withStream() {
deserialize_unicodeMissingLeadingSurrogate(objectType: .stream)
}

func test_deserialize_unicodeMissingTrailingSurrogate_withStream() {
deserialize_unicodeMissingTrailingSurrogate(objectType: .stream)
}
Expand Down Expand Up @@ -738,6 +748,20 @@ extension TestJSONSerialization {
}
}

func deserialize_unicodeMissingLeadingSurrogate(objectType: ObjectType) {
let subject = "[\"\\uDFF3\"]"
do {
guard let data = subject.data(using: .utf8) else {
XCTFail("Unable to convert string to data")
return
}
let _ = try getjsonObjectResult(data, objectType) as? [String]
XCTFail("Expected error: Missing Leading Surrogate")
} catch {
// Passing case; the unicode character is malformed
}
}

func deserialize_unicodeMissingTrailingSurrogate(objectType: ObjectType) {
let subject = "[\"\\uD834\"]"
do {
Expand Down