Fix combine_phase_logs text encoding issues (#34657)

Avoid text decoding and encoding when combining log files, instead
combine in binary mode.

Also do a buffered copy which is sometimes faster for large log files.

2 files changed, 20 insertions, 5 deletions

diff --git a/lib/spack/spack/installer.py b/lib/spack/spack/installer.py
index 08d4db6ab7..eaf734a816 100644
--- a/lib/spack/spack/installer.py
+++ b/lib/spack/spack/installer.py
@@ -460,11 +460,10 @@ def combine_phase_logs(phase_log_files, log_path):
         phase_log_files (list): a list or iterator of logs to combine
         log_path (str): the path to combine them to
     """
-
-    with open(log_path, "w") as log_file:
+    with open(log_path, "bw") as log_file:
         for phase_log_file in phase_log_files:
-            with open(phase_log_file, "r") as phase_log:
-                log_file.write(phase_log.read())
+            with open(phase_log_file, "br") as phase_log:
+                shutil.copyfileobj(phase_log, log_file)
 
 
 def dump_packages(spec, path):
diff --git a/lib/spack/spack/test/installer.py b/lib/spack/spack/test/installer.py
index 8a446c650e..3b45646c6b 100644
--- a/lib/spack/spack/test/installer.py
+++ b/lib/spack/spack/test/installer.py
@@ -622,7 +622,7 @@ def test_combine_phase_logs(tmpdir):
 
     # This is the output log we will combine them into
     combined_log = os.path.join(str(tmpdir), "combined-out.txt")
-    spack.installer.combine_phase_logs(phase_log_files, combined_log)
+    inst.combine_phase_logs(phase_log_files, combined_log)
     with open(combined_log, "r") as log_file:
         out = log_file.read()
 
@@ -631,6 +631,22 @@ def test_combine_phase_logs(tmpdir):
         assert "Output from %s\n" % log_file in out
 
 
+def test_combine_phase_logs_does_not_care_about_encoding(tmpdir):
+    # this is invalid utf-8 at a minimum
+    data = b"\x00\xF4\xBF\x00\xBF\xBF"
+    input = [str(tmpdir.join("a")), str(tmpdir.join("b"))]
+    output = str(tmpdir.join("c"))
+
+    for path in input:
+        with open(path, "wb") as f:
+            f.write(data)
+
+    inst.combine_phase_logs(input, output)
+
+    with open(output, "rb") as f:
+        assert f.read() == data * 2
+
+
 def test_check_deps_status_install_failure(install_mockery, monkeypatch):
     const_arg = installer_args(["a"], {})
     installer = create_installer(const_arg)