Skip to content

Validate UTF8String contents when decoding #129

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

Open
d-date wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Validate UTF8String contents when decoding #129

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
23 changes: 23 additions & 0 deletions Sources/SwiftASN1/Basic ASN1 Types/ASN1Strings.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -27,11 +27,17 @@ public struct ASN1UTF8String: DERImplicitlyTaggable, BERImplicitlyTaggable, Hash
@inlinable
public init(derEncoded node: ASN1Node, withIdentifier identifier: ASN1Identifier) throws {
self.bytes = try ASN1OctetString(derEncoded: node, withIdentifier: identifier).bytes
guard Self._isValid(self.bytes) else {
throw ASN1Error.invalidStringRepresentation(reason: "Invalid bytes for ASN1UTF8String")
}
}

@inlinable
public init(berEncoded node: ASN1Node, withIdentifier identifier: ASN1Identifier) throws {
self.bytes = try ASN1OctetString(berEncoded: node, withIdentifier: identifier).bytes
guard Self._isValid(self.bytes) else {
throw ASN1Error.invalidStringRepresentation(reason: "Invalid bytes for ASN1UTF8String")
}
}

/// Construct a UTF8STRING from raw bytes.
Expand Down Expand Up @@ -61,6 +67,23 @@ public struct ASN1UTF8String: DERImplicitlyTaggable, BERImplicitlyTaggable, Hash
public func withUnsafeBytes<R>(_ body: (UnsafeRawBufferPointer) throws -> R) rethrows -> R {
return try self.bytes.withUnsafeBytes(body)
}

@inlinable
static func _isValid(_ bytes: ArraySlice<UInt8>) -> Bool {
var iterator = bytes.makeIterator()
var decoder = UTF8()

while true {
switch decoder.decode(&iterator) {
case .scalarValue:
continue
case .emptyInput:
return true
case .error:
return false
}
}
}
}

/// TeletexString is an uncommon ASN.1 string type.
Expand Down
24 changes: 24 additions & 0 deletions Tests/SwiftASN1Tests/ASN1StringTests.swift
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,30 @@ final class ASN1StringTests: XCTestCase {
string.withUnsafeBytes { XCTAssertTrue($0.elementsEqual([1, 2, 3, 4])) }
}

func testUTF8StringRejectsInvalidUTF8() throws {
// A lead byte that must be followed by one continuation byte, and 0x28 is not one.
XCTAssertThrowsError(try ASN1UTF8String(derEncoded: [0x0c, 0x02, 0xc3, 0x28]))
// An overlong encoding of U+002F.
XCTAssertThrowsError(try ASN1UTF8String(derEncoded: [0x0c, 0x02, 0xc0, 0xaf]))
// U+D800, the high half of a surrogate pair, encoded as three bytes.
XCTAssertThrowsError(try ASN1UTF8String(derEncoded: [0x0c, 0x03, 0xed, 0xa0, 0x80]))
// A scalar above U+10FFFF.
XCTAssertThrowsError(try ASN1UTF8String(derEncoded: [0x0c, 0x04, 0xf5, 0x80, 0x80, 0x80]))
// A sequence cut short by the end of the contents.
XCTAssertThrowsError(try ASN1UTF8String(derEncoded: [0x0c, 0x02, 0xe2, 0x82]))
// A continuation byte with nothing leading it.
XCTAssertThrowsError(try ASN1UTF8String(derEncoded: [0x0c, 0x01, 0x80]))
}

func testUTF8StringAcceptsValidUTF8() throws {
// Empty, ASCII, two-, three- and four-byte scalars.
XCTAssertEqual(try ASN1UTF8String(derEncoded: [0x0c, 0x00]).bytes, [])
XCTAssertEqual(try ASN1UTF8String(derEncoded: [0x0c, 0x01, 0x41]).bytes, [0x41])
XCTAssertNoThrow(try ASN1UTF8String(derEncoded: [0x0c, 0x02, 0xc2, 0xa9]))
XCTAssertNoThrow(try ASN1UTF8String(derEncoded: [0x0c, 0x03, 0xe6, 0x97, 0xa5]))
XCTAssertNoThrow(try ASN1UTF8String(derEncoded: [0x0c, 0x04, 0xf0, 0x9f, 0x94, 0x92]))
}

func testTeletexStringEncoding() throws {
var serializer = DER.Serializer()
let originalString = ASN1TeletexString(contentBytes: [1, 2, 3, 4])
Expand Down