From e9d2732e0072d992736403f61d1f3fc8a09905f8 Mon Sep 17 00:00:00 2001
From: Harmen Stoppels <me@harmenstoppels.nl>
Date: Wed, 11 Dec 2024 10:54:17 +0100
Subject: [PATCH] log.py: improve utf-8 handling, and non-utf-8 output (#48005)

---
 lib/spack/llnl/util/tty/log.py            | 22 ++++++++++++++--------
 lib/spack/spack/test/llnl/util/tty/log.py | 18 ++++++++----------
 2 files changed, 22 insertions(+), 18 deletions(-)

diff --git a/lib/spack/llnl/util/tty/log.py b/lib/spack/llnl/util/tty/log.py
index 534472dbecd..612d9ff380e 100644
--- a/lib/spack/llnl/util/tty/log.py
+++ b/lib/spack/llnl/util/tty/log.py
@@ -879,10 +879,13 @@ def _writer_daemon(
     write_fd.close()
 
     # 1. Use line buffering (3rd param = 1) since Python 3 has a bug
-    # that prevents unbuffered text I/O.
-    # 2. Python 3.x before 3.7 does not open with UTF-8 encoding by default
+    #    that prevents unbuffered text I/O. [needs citation]
+    # 2. Enforce a UTF-8 interpretation of build process output with errors replaced by '?'.
+    #    The downside is that the log file will not contain the exact output of the build process.
     # 3. closefd=False because Connection has "ownership"
-    read_file = os.fdopen(read_fd.fileno(), "r", 1, encoding="utf-8", closefd=False)
+    read_file = os.fdopen(
+        read_fd.fileno(), "r", 1, encoding="utf-8", errors="replace", closefd=False
+    )
 
     if stdin_fd:
         stdin_file = os.fdopen(stdin_fd.fileno(), closefd=False)
@@ -928,11 +931,7 @@ def _writer_daemon(
                     try:
                         while line_count < 100:
                             # Handle output from the calling process.
-                            try:
-                                line = _retry(read_file.readline)()
-                            except UnicodeDecodeError:
-                                # installs like --test=root gpgme produce non-UTF8 logs
-                                line = "<line lost: output was not encoded as UTF-8>\n"
+                            line = _retry(read_file.readline)()
 
                             if not line:
                                 return
@@ -946,6 +945,13 @@ def _writer_daemon(
                                 output_line = clean_line
                                 if filter_fn:
                                     output_line = filter_fn(clean_line)
+                                enc = sys.stdout.encoding
+                                if enc != "utf-8":
+                                    # On Python 3.6 and 3.7-3.14 with non-{utf-8,C} locale stdout
+                                    # may not be able to handle utf-8 output. We do an inefficient
+                                    # dance of re-encoding with errors replaced, so stdout.write
+                                    # does not raise.
+                                    output_line = output_line.encode(enc, "replace").decode(enc)
                                 sys.stdout.write(output_line)
 
                             # Stripped output to log file.
diff --git a/lib/spack/spack/test/llnl/util/tty/log.py b/lib/spack/spack/test/llnl/util/tty/log.py
index 61879fc4108..1ffcf22453f 100644
--- a/lib/spack/spack/test/llnl/util/tty/log.py
+++ b/lib/spack/spack/test/llnl/util/tty/log.py
@@ -57,18 +57,16 @@ def test_log_python_output_without_echo(capfd, tmpdir):
         assert capfd.readouterr()[0] == ""
 
 
-def test_log_python_output_with_invalid_utf8(capfd, tmpdir):
-    with tmpdir.as_cwd():
-        with log.log_output("foo.txt"):
-            sys.stdout.buffer.write(b"\xc3\x28\n")
+def test_log_python_output_with_invalid_utf8(capfd, tmp_path):
+    tmp_file = str(tmp_path / "foo.txt")
+    with log.log_output(tmp_file, echo=True):
+        sys.stdout.buffer.write(b"\xc3helloworld\n")
 
-        expected = b"<line lost: output was not encoded as UTF-8>\n"
-        with open("foo.txt", "rb") as f:
-            written = f.read()
-            assert written == expected
+    # we should be able to read this as valid utf-8
+    with open(tmp_file, "r", encoding="utf-8") as f:
+        assert f.read() == "�helloworld\n"
 
-        # nothing on stdout or stderr
-        assert capfd.readouterr()[0] == ""
+    assert capfd.readouterr().out == "�helloworld\n"
 
 
 def test_log_python_output_and_echo_output(capfd, tmpdir):