From a4e7c4e9b7fbefdc1bf00a75e68dc0262c622bd3 Mon Sep 17 00:00:00 2001
From: Raven Kopelman <raven.kopelman@safe.com>
Date: Tue, 27 Oct 2020 13:39:32 -0700
Subject: [PATCH] Prevent files from being partially read from the cache

---
 SCons/CacheDir.py   | 17 +++++++++++++++--
 SCons/Taskmaster.py |  7 +++++--
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/SCons/CacheDir.py b/SCons/CacheDir.py
index 879c21bd73..cf8156319f 100644
--- a/SCons/CacheDir.py
+++ b/SCons/CacheDir.py
@@ -55,7 +55,20 @@ def CacheRetrieveFunc(target, source, env):
         if fs.islink(cachefile):
             fs.symlink(fs.readlink(cachefile), t.get_internal_path())
         else:
-            env.copy_from_cache(cachefile, t.get_internal_path())
+            try:
+                env.copy_from_cache(cachefile, t.get_internal_path())
+            except:
+                try:
+                    # In case file was partially retrieved (and now corrupt)
+                    # delete it to avoid poisoning commands like 'ar' that
+                    # read from the initial state of the file they are writing
+                    # to.
+                    t.fs.unlink(t.get_internal_path())
+                except:
+                    pass
+
+                raise
+
             try:
                 os.utime(cachefile, None)
             except OSError:
@@ -70,7 +83,7 @@ def CacheRetrieveString(target, source, env):
     cd = env.get_CacheDir()
     cachedir, cachefile = cd.cachepath(t)
     if t.fs.exists(cachefile):
-        return "Retrieved `%s' from cache" % t.get_internal_path()
+        return "Retrieving `%s' from cache" % t.get_internal_path()
     return None
 
 CacheRetrieve = SCons.Action.Action(CacheRetrieveFunc, CacheRetrieveString)
diff --git a/SCons/Taskmaster.py b/SCons/Taskmaster.py
index a1358e0476..59b15141e9 100644
--- a/SCons/Taskmaster.py
+++ b/SCons/Taskmaster.py
@@ -223,10 +223,13 @@ def execute(self):
                 cached_targets.append(t)
             if len(cached_targets) < len(self.targets):
                 # Remove targets before building. It's possible that we
-                # partially retrieved targets from the cache, leaving
-                # them in read-only mode. That might cause the command
+                # retrieved a subset of targets from the cache, leaving
+                # them in an inconsistent state. That might cause the command
                 # to fail.
                 #
+                # Note that retrieve_from_cache() ensures no single target can
+                # be partially retrieved (file left in corrupt state).
+                #
                 for t in cached_targets:
                     try:
                         t.fs.unlink(t.get_internal_path())