From 348a325d2ae91faea4885fa82b5110d3101ef1af Mon Sep 17 00:00:00 2001
From: Alastair Houghton <ahoughton@apple.com>
Date: Thu, 14 Nov 2024 14:43:24 +0000
Subject: [PATCH] [Backtracing] Also try `CFStringGetCharactersPtr` when
 converting `CFString`s.

We already try using `CFStringGetCStringPtr` to see if we can get ASCII;
we should also try `CFStringGetCharactersPtr` as the native encoding of
`CFNSString` is very often UTF-16.  While we're at it, try asking explicitly
for UTF-8 as well.  That won't work for `CFNSString` because AFAIK it's
currently never encoded that way, but it might work if something hands us
a Swift-backed string or if some future implementation of `CFString`
happens to support UTF-8 encoded data.

rdar://124913332
---
 .../RuntimeModule/CoreSymbolication.swift     | 22 +++++++++++++++++--
 1 file changed, 20 insertions(+), 2 deletions(-)

diff --git a/stdlib/public/RuntimeModule/CoreSymbolication.swift b/stdlib/public/RuntimeModule/CoreSymbolication.swift
index a9ec307f7b9..94634b6fedb 100644
--- a/stdlib/public/RuntimeModule/CoreSymbolication.swift
+++ b/stdlib/public/RuntimeModule/CoreSymbolication.swift
@@ -46,6 +46,9 @@ private func symbol<T>(_ handle: UnsafeMutableRawPointer, _ name: String) -> T {
   return unsafeBitCast(result, to: T.self)
 }
 
+// Define UniChar
+typealias UniChar = UInt16
+
 private enum Sym {
   // CRCopySanitizedPath
   static let CRCopySanitizedPath: @convention(c) (CFString, CFIndex) -> CFString =
@@ -130,6 +133,9 @@ private enum Sym {
                     UnsafeMutableRawPointer?, CFIndex,
                     UnsafeMutablePointer<CFIndex>?) -> CFIndex =
     symbol(coreFoundationHandle, "CFStringGetBytes")
+  static let CFStringGetCharactersPtr:
+    @convention(c) (CFString) -> UnsafePointer<UniChar>? =
+    symbol(coreFoundationHandle, "CFStringGetCharactersPtr")
 }
 
 // .. Core Foundation miscellany ...............................................
@@ -161,6 +167,11 @@ internal func CFStringGetCStringPtr(_ s: CFString,
   return Sym.CFStringGetCStringPtr(s, encoding)
 }
 
+internal func CFStringGetCharactersPtr(_ s: CFString)
+  -> UnsafePointer<UniChar>? {
+  return Sym.CFStringGetCharactersPtr(s);
+}
+
 internal func CFStringGetBytes(_ s: CFString,
                                _ range: CFRange,
                                _ encoding: CFStringEncoding,
@@ -199,8 +210,15 @@ private func fromCFString(_ cf: CFString) -> String {
 
   if let ptr = CFStringGetCStringPtr(cf,
                                      CFStringBuiltInEncodings.ASCII.rawValue) {
-    return String(decoding: UnsafeRawBufferPointer(start: ptr, count: length),
-                  as: UTF8.self)
+    let buffer = UnsafeRawBufferPointer(start: ptr, count: length)
+    return String(decoding: buffer, as: UTF8.self)
+  } else if let ptr = CFStringGetCharactersPtr(cf) {
+    let buffer = UnsafeBufferPointer(start: ptr, count: length)
+    return String(decoding: buffer, as: UTF16.self)
+  } else if let ptr = CFStringGetCStringPtr(cf,
+                                            CFStringBuiltInEncodings.UTF8.rawValue) {
+    let buffer = UnsafeRawBufferPointer(start: ptr, count: length)
+    return String(decoding: buffer, as: UTF8.self)
   } else {
     var byteLen = CFIndex(0)