bpo-37111: Add 'encoding' and 'errors' parameters to logging.basicCon… (GH-14008)

3 files changed, 140 insertions, 18 deletions

diff --git a/Lib/logging/__init__.py b/Lib/logging/__init__.py
index 16812ec..645e0b3 100644
--- a/Lib/logging/__init__.py
+++ b/Lib/logging/__init__.py
@@ -1,4 +1,4 @@
-# Copyright 2001-2017 by Vinay Sajip. All Rights Reserved.
+# Copyright 2001-2019 by Vinay Sajip. All Rights Reserved.
 #
 # Permission to use, copy, modify, and distribute this software and its
 # documentation for any purpose and without fee is hereby granted,
@@ -18,7 +18,7 @@
 Logging package for Python. Based on PEP 282 and comments thereto in
 comp.lang.python.
 
-Copyright (C) 2001-2017 Vinay Sajip. All Rights Reserved.
+Copyright (C) 2001-2019 Vinay Sajip. All Rights Reserved.
 
 To use, simply 'import logging' and log away!
 """
@@ -1122,7 +1122,7 @@ class FileHandler(StreamHandler):
     """
     A handler class which writes formatted logging records to disk files.
     """
-    def __init__(self, filename, mode='a', encoding=None, delay=False):
+    def __init__(self, filename, mode='a', encoding=None, delay=False, errors=None):
         """
         Open the specified file and use it as the stream for logging.
         """
@@ -1133,6 +1133,7 @@ class FileHandler(StreamHandler):
         self.baseFilename = os.path.abspath(filename)
         self.mode = mode
         self.encoding = encoding
+        self.errors = errors
         self.delay = delay
         if delay:
             #We don't open the stream, but we still need to call the
@@ -1169,7 +1170,8 @@ class FileHandler(StreamHandler):
         Open the current base file with the (original) mode and encoding.
         Return the resulting stream.
         """
-        return open(self.baseFilename, self.mode, encoding=self.encoding)
+        return open(self.baseFilename, self.mode, encoding=self.encoding,
+                    errors=self.errors)
 
     def emit(self, record):
         """
@@ -1928,15 +1930,20 @@ def basicConfig(**kwargs):
               attached to the root logger are removed and closed, before
               carrying out the configuration as specified by the other
               arguments.
+    encoding  If specified together with a filename, this encoding is passed to
+              the created FileHandler, causing it to be used when the file is
+              opened.
+    errors    If specified together with a filename, this value is passed to the
+              created FileHandler, causing it to be used when the file is
+              opened in text mode. If not specified, the default value is
+              `backslashreplace`.
+
     Note that you could specify a stream created using open(filename, mode)
     rather than passing the filename and mode in. However, it should be
     remembered that StreamHandler does not close its stream (since it may be
     using sys.stdout or sys.stderr), whereas FileHandler closes its stream
     when the handler is closed.
 
-    .. versionchanged:: 3.8
-       Added the ``force`` parameter.
-
     .. versionchanged:: 3.2
        Added the ``style`` parameter.
 
@@ -1946,12 +1953,20 @@ def basicConfig(**kwargs):
        ``filename``/``filemode``, or ``filename``/``filemode`` specified
        together with ``stream``, or ``handlers`` specified together with
        ``stream``.
+
+    .. versionchanged:: 3.8
+       Added the ``force`` parameter.
+
+    .. versionchanged:: 3.9
+       Added the ``encoding`` and ``errors`` parameters.
     """
     # Add thread safety in case someone mistakenly calls
     # basicConfig() from multiple threads
     _acquireLock()
     try:
         force = kwargs.pop('force', False)
+        encoding = kwargs.pop('encoding', None)
+        errors = kwargs.pop('errors', 'backslashreplace')
         if force:
             for h in root.handlers[:]:
                 root.removeHandler(h)
@@ -1970,7 +1985,10 @@ def basicConfig(**kwargs):
                 filename = kwargs.pop("filename", None)
                 mode = kwargs.pop("filemode", 'a')
                 if filename:
-                    h = FileHandler(filename, mode)
+                    if 'b'in mode:
+                        errors = None
+                    h = FileHandler(filename, mode,
+                                    encoding=encoding, errors=errors)
                 else:
                     stream = kwargs.pop("stream", None)
                     h = StreamHandler(stream)
diff --git a/Lib/logging/handlers.py b/Lib/logging/handlers.py
index 34ff7a0..5641fee 100644
--- a/Lib/logging/handlers.py
+++ b/Lib/logging/handlers.py
@@ -48,13 +48,16 @@ class BaseRotatingHandler(logging.FileHandler):
     Not meant to be instantiated directly.  Instead, use RotatingFileHandler
     or TimedRotatingFileHandler.
     """
-    def __init__(self, filename, mode, encoding=None, delay=False):
+    def __init__(self, filename, mode, encoding=None, delay=False, errors=None):
         """
         Use the specified filename for streamed logging
         """
-        logging.FileHandler.__init__(self, filename, mode, encoding, delay)
+        logging.FileHandler.__init__(self, filename, mode=mode,
+                                     encoding=encoding, delay=delay,
+                                     errors=errors)
         self.mode = mode
         self.encoding = encoding
+        self.errors = errors
         self.namer = None
         self.rotator = None
 
@@ -117,7 +120,8 @@ class RotatingFileHandler(BaseRotatingHandler):
     Handler for logging to a set of files, which switches from one file
     to the next when the current file reaches a certain size.
     """
-    def __init__(self, filename, mode='a', maxBytes=0, backupCount=0, encoding=None, delay=False):
+    def __init__(self, filename, mode='a', maxBytes=0, backupCount=0,
+                 encoding=None, delay=False, errors=None):
         """
         Open the specified file and use it as the stream for logging.
 
@@ -145,7 +149,8 @@ class RotatingFileHandler(BaseRotatingHandler):
         # on each run.
         if maxBytes > 0:
             mode = 'a'
-        BaseRotatingHandler.__init__(self, filename, mode, encoding, delay)
+        BaseRotatingHandler.__init__(self, filename, mode, encoding=encoding,
+                                     delay=delay, errors=errors)
         self.maxBytes = maxBytes
         self.backupCount = backupCount
 
@@ -196,8 +201,11 @@ class TimedRotatingFileHandler(BaseRotatingHandler):
     If backupCount is > 0, when rollover is done, no more than backupCount
     files are kept - the oldest ones are deleted.
     """
-    def __init__(self, filename, when='h', interval=1, backupCount=0, encoding=None, delay=False, utc=False, atTime=None):
-        BaseRotatingHandler.__init__(self, filename, 'a', encoding, delay)
+    def __init__(self, filename, when='h', interval=1, backupCount=0,
+                 encoding=None, delay=False, utc=False, atTime=None,
+                 errors=None):
+        BaseRotatingHandler.__init__(self, filename, 'a', encoding=encoding,
+                                     delay=delay, errors=errors)
         self.when = when.upper()
         self.backupCount = backupCount
         self.utc = utc
@@ -431,8 +439,11 @@ class WatchedFileHandler(logging.FileHandler):
     This handler is based on a suggestion and patch by Chad J.
     Schroeder.
     """
-    def __init__(self, filename, mode='a', encoding=None, delay=False):
-        logging.FileHandler.__init__(self, filename, mode, encoding, delay)
+    def __init__(self, filename, mode='a', encoding=None, delay=False,
+                 errors=None):
+        logging.FileHandler.__init__(self, filename, mode=mode,
+                                     encoding=encoding, delay=delay,
+                                     errors=errors)
         self.dev, self.ino = -1, -1
         self._statstream()
 
diff --git a/Lib/test/test_logging.py b/Lib/test/test_logging.py
index 50148dc..ac8919d 100644
--- a/Lib/test/test_logging.py
+++ b/Lib/test/test_logging.py
@@ -1,4 +1,4 @@
-# Copyright 2001-2017 by Vinay Sajip. All Rights Reserved.
+# Copyright 2001-2019 by Vinay Sajip. All Rights Reserved.
 #
 # Permission to use, copy, modify, and distribute this software and its
 # documentation for any purpose and without fee is hereby granted,
@@ -16,7 +16,7 @@
 
 """Test harness for the logging module. Run all tests.
 
-Copyright (C) 2001-2017 Vinay Sajip. All Rights Reserved.
+Copyright (C) 2001-2019 Vinay Sajip. All Rights Reserved.
 """
 
 import logging
@@ -4445,6 +4445,99 @@ class BasicConfigTest(unittest.TestCase):
         self.assertEqual(new_string_io.getvalue().strip(),
                          'WARNING:root:warn\nINFO:root:info')
 
+    def test_encoding(self):
+        try:
+            encoding = 'utf-8'
+            logging.basicConfig(filename='test.log', encoding=encoding,
+                                errors='strict',
+                                format='%(message)s', level=logging.DEBUG)
+
+            self.assertEqual(len(logging.root.handlers), 1)
+            handler = logging.root.handlers[0]
+            self.assertIsInstance(handler, logging.FileHandler)
+            self.assertEqual(handler.encoding, encoding)
+            logging.debug('The Øresund Bridge joins Copenhagen to Malmö')
+        finally:
+            handler.close()
+            with open('test.log', encoding='utf-8') as f:
+                data = f.read().strip()
+            os.remove('test.log')
+            self.assertEqual(data,
+                             'The Øresund Bridge joins Copenhagen to Malmö')
+
+    def test_encoding_errors(self):
+        try:
+            encoding = 'ascii'
+            logging.basicConfig(filename='test.log', encoding=encoding,
+                                errors='ignore',
+                                format='%(message)s', level=logging.DEBUG)
+
+            self.assertEqual(len(logging.root.handlers), 1)
+            handler = logging.root.handlers[0]
+            self.assertIsInstance(handler, logging.FileHandler)
+            self.assertEqual(handler.encoding, encoding)
+            logging.debug('The Øresund Bridge joins Copenhagen to Malmö')
+        finally:
+            handler.close()
+            with open('test.log', encoding='utf-8') as f:
+                data = f.read().strip()
+            os.remove('test.log')
+            self.assertEqual(data, 'The resund Bridge joins Copenhagen to Malm')
+
+    def test_encoding_errors_default(self):
+        try:
+            encoding = 'ascii'
+            logging.basicConfig(filename='test.log', encoding=encoding,
+                                format='%(message)s', level=logging.DEBUG)
+
+            self.assertEqual(len(logging.root.handlers), 1)
+            handler = logging.root.handlers[0]
+            self.assertIsInstance(handler, logging.FileHandler)
+            self.assertEqual(handler.encoding, encoding)
+            self.assertEqual(handler.errors, 'backslashreplace')
+            logging.debug('😂: ☃️: The Øresund Bridge joins Copenhagen to Malmö')
+        finally:
+            handler.close()
+            with open('test.log', encoding='utf-8') as f:
+                data = f.read().strip()
+            os.remove('test.log')
+            self.assertEqual(data, r'\U0001f602: \u2603\ufe0f: The \xd8resund '
+                                   r'Bridge joins Copenhagen to Malm\xf6')
+
+    def test_encoding_errors_none(self):
+        # Specifying None should behave as 'strict'
+        try:
+            encoding = 'ascii'
+            logging.basicConfig(filename='test.log', encoding=encoding,
+                                errors=None,
+                                format='%(message)s', level=logging.DEBUG)
+
+            self.assertEqual(len(logging.root.handlers), 1)
+            handler = logging.root.handlers[0]
+            self.assertIsInstance(handler, logging.FileHandler)
+            self.assertEqual(handler.encoding, encoding)
+            self.assertIsNone(handler.errors)
+
+            message = []
+
+            def dummy_handle_error(record):
+                _, v, _ = sys.exc_info()
+                message.append(str(v))
+
+            handler.handleError = dummy_handle_error
+            logging.debug('The Øresund Bridge joins Copenhagen to Malmö')
+            self.assertTrue(message)
+            self.assertIn("'ascii' codec can't encode "
+                          "character '\\xd8' in position 4:", message[0])
+        finally:
+            handler.close()
+            with open('test.log', encoding='utf-8') as f:
+                data = f.read().strip()
+            os.remove('test.log')
+            # didn't write anything due to the encoding error
+            self.assertEqual(data, r'')
+
+
     def _test_log(self, method, level=None):
         # logging.root has no handlers so basicConfig should be called
         called = []