From 05010706697ce9c18e7f8a8e571753b0bcfd6548 Mon Sep 17 00:00:00 2001 From: Victor Stinner Date: Fri, 27 May 2011 16:50:40 +0200 Subject: Revert my commit 3555cf6f9c98: "Issue #8796: codecs.open() calls the builtin open() function instead of using StreamReaderWriter. Deprecate StreamReader, StreamWriter, StreamReaderWriter, StreamRecoder and EncodedFile() of the codec module. Use the builtin open() function or io.TextIOWrapper instead." "It has not been approved !" wrote Marc-Andre Lemburg. --- Doc/library/codecs.rst | 25 -------- Lib/codecs.py | 25 ++++---- Lib/test/test_codecs.py | 152 +++++++++++++++--------------------------------- Misc/NEWS | 5 -- 4 files changed, 59 insertions(+), 148 deletions(-) diff --git a/Doc/library/codecs.rst b/Doc/library/codecs.rst index b58e410..4d5058e 100644 --- a/Doc/library/codecs.rst +++ b/Doc/library/codecs.rst @@ -85,9 +85,6 @@ It defines the following functions: In case a search function cannot find a given encoding, it should return ``None``. - .. deprecated:: 3.3 - *streamreader* and *streamwriter* attributes are now deprecated. - .. function:: lookup(encoding) @@ -142,8 +139,6 @@ functions which use :func:`lookup` for the codec lookup: Raises a :exc:`LookupError` in case the encoding cannot be found. - .. deprecated:: 3.3 - .. function:: getwriter(encoding) @@ -152,8 +147,6 @@ functions which use :func:`lookup` for the codec lookup: Raises a :exc:`LookupError` in case the encoding cannot be found. - .. deprecated:: 3.3 - .. function:: register_error(name, error_handler) @@ -224,11 +217,6 @@ utility functions: .. note:: - This function is kept for backward compatibility with Python 2, the - builtin :func:`open` function should be used instead. - - .. note:: - The wrapped version's methods will accept and return strings only. Bytes arguments will be rejected. @@ -263,8 +251,6 @@ utility functions: ``'strict'``, which causes :exc:`ValueError` to be raised in case an encoding error occurs. - .. deprecated:: 3.3 - .. function:: iterencode(iterator, encoding, errors='strict', **kwargs) @@ -577,9 +563,6 @@ The :class:`StreamWriter` class is a subclass of :class:`Codec` and defines the following methods which every stream writer must define in order to be compatible with the Python codec registry. -.. deprecated:: 3.3 - Use the builtin the :class:`io.TextIOWrapper` class. - .. class:: StreamWriter(stream[, errors]) @@ -645,9 +628,6 @@ The :class:`StreamReader` class is a subclass of :class:`Codec` and defines the following methods which every stream reader must define in order to be compatible with the Python codec registry. -.. deprecated:: 3.3 - Use the builtin the :class:`io.TextIOWrapper` class. - .. class:: StreamReader(stream[, errors]) @@ -748,9 +728,6 @@ and write modes. The design is such that one can use the factory functions returned by the :func:`lookup` function to construct the instance. -.. deprecated:: 3.3 - Use the :class:`io.TextIOWrapper` class. - .. class:: StreamReaderWriter(stream, Reader, Writer, errors) @@ -775,8 +752,6 @@ which is sometimes useful when dealing with different encoding environments. The design is such that one can use the factory functions returned by the :func:`lookup` function to construct the instance. -.. deprecated:: 3.3 - .. class:: StreamRecoder(stream, encode, decode, Reader, Writer, errors) diff --git a/Lib/codecs.py b/Lib/codecs.py index ec7879f..b150d64 100644 --- a/Lib/codecs.py +++ b/Lib/codecs.py @@ -345,8 +345,6 @@ class StreamWriter(Codec): The set of allowed parameter values can be extended via register_error. """ - import warnings - warnings.warn('use io.TextIOWrapper', DeprecationWarning, stacklevel=2) self.stream = stream self.errors = errors @@ -418,8 +416,6 @@ class StreamReader(Codec): The set of allowed parameter values can be extended via register_error. """ - import warnings - warnings.warn('use io.TextIOWrapper', DeprecationWarning, stacklevel=2) self.stream = stream self.errors = errors self.bytebuffer = b"" @@ -850,7 +846,7 @@ class StreamRecoder: ### Shortcuts -def open(filename, mode='r', encoding=None, errors=None, buffering=1): +def open(filename, mode='rb', encoding=None, errors='strict', buffering=1): """ Open an encoded file using the given mode and return a wrapped version providing transparent encoding/decoding. @@ -881,13 +877,18 @@ def open(filename, mode='r', encoding=None, errors=None, buffering=1): parameter. """ - if encoding is not None: - return builtins.open(filename, mode, buffering, - encoding, errors, newline='') - else: - if 'b' not in mode: - mode = mode + 'b' - return builtins.open(filename, mode, buffering, encoding, errors) + if encoding is not None and \ + 'b' not in mode: + # Force opening of the file in binary mode + mode = mode + 'b' + file = builtins.open(filename, mode, buffering) + if encoding is None: + return file + info = lookup(encoding) + srw = StreamReaderWriter(file, info.streamreader, info.streamwriter, errors) + # Add attributes to simplify introspection + srw.encoding = encoding + return srw def EncodedFile(file, data_encoding, file_encoding=None, errors='strict'): diff --git a/Lib/test/test_codecs.py b/Lib/test/test_codecs.py index 1f46560..c0450e7 100644 --- a/Lib/test/test_codecs.py +++ b/Lib/test/test_codecs.py @@ -1,10 +1,7 @@ from test import support -import _testcapi -import codecs -import io -import sys import unittest -import warnings +import codecs +import sys, _testcapi, io class Queue(object): """ @@ -66,9 +63,7 @@ class ReadTest(unittest.TestCase, MixInCheckStateHandling): # the StreamReader and check that the results equal the appropriate # entries from partialresults. q = Queue(b"") - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - r = codecs.getreader(self.encoding)(q) + r = codecs.getreader(self.encoding)(q) result = "" for (c, partialresult) in zip(input.encode(self.encoding), partialresults): q.write(bytes([c])) @@ -111,9 +106,7 @@ class ReadTest(unittest.TestCase, MixInCheckStateHandling): return codecs.getreader(self.encoding)(stream) def readalllines(input, keepends=True, size=None): - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - reader = getreader(input) + reader = getreader(input) lines = [] while True: line = reader.readline(size=size, keepends=keepends) @@ -222,18 +215,14 @@ class ReadTest(unittest.TestCase, MixInCheckStateHandling): ' \r\n', ] stream = io.BytesIO("".join(s).encode(self.encoding)) - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - reader = codecs.getreader(self.encoding)(stream) + reader = codecs.getreader(self.encoding)(stream) for (i, line) in enumerate(reader): self.assertEqual(line, s[i]) def test_readlinequeue(self): q = Queue(b"") - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - writer = codecs.getwriter(self.encoding)(q) - reader = codecs.getreader(self.encoding)(q) + writer = codecs.getwriter(self.encoding)(q) + reader = codecs.getreader(self.encoding)(q) # No lineends writer.write("foo\r") @@ -264,9 +253,7 @@ class ReadTest(unittest.TestCase, MixInCheckStateHandling): s = (s1+s2+s3).encode(self.encoding) stream = io.BytesIO(s) - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - reader = codecs.getreader(self.encoding)(stream) + reader = codecs.getreader(self.encoding)(stream) self.assertEqual(reader.readline(), s1) self.assertEqual(reader.readline(), s2) self.assertEqual(reader.readline(), s3) @@ -281,9 +268,7 @@ class ReadTest(unittest.TestCase, MixInCheckStateHandling): s = (s1+s2+s3+s4+s5).encode(self.encoding) stream = io.BytesIO(s) - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - reader = codecs.getreader(self.encoding)(stream) + reader = codecs.getreader(self.encoding)(stream) self.assertEqual(reader.readline(), s1) self.assertEqual(reader.readline(), s2) self.assertEqual(reader.readline(), s3) @@ -305,9 +290,7 @@ class UTF32Test(ReadTest): _,_,reader,writer = codecs.lookup(self.encoding) # encode some stream s = io.BytesIO() - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - f = writer(s) + f = writer(s) f.write("spam") f.write("spam") d = s.getvalue() @@ -315,22 +298,16 @@ class UTF32Test(ReadTest): self.assertTrue(d == self.spamle or d == self.spambe) # try to read it back s = io.BytesIO(d) - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - f = reader(s) + f = reader(s) self.assertEqual(f.read(), "spamspam") def test_badbom(self): s = io.BytesIO(4*b"\xff") - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - f = codecs.getreader(self.encoding)(s) + f = codecs.getreader(self.encoding)(s) self.assertRaises(UnicodeError, f.read) s = io.BytesIO(8*b"\xff") - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - f = codecs.getreader(self.encoding)(s) + f = codecs.getreader(self.encoding)(s) self.assertRaises(UnicodeError, f.read) def test_partial(self): @@ -477,9 +454,7 @@ class UTF16Test(ReadTest): _,_,reader,writer = codecs.lookup(self.encoding) # encode some stream s = io.BytesIO() - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - f = writer(s) + f = writer(s) f.write("spam") f.write("spam") d = s.getvalue() @@ -487,22 +462,16 @@ class UTF16Test(ReadTest): self.assertTrue(d == self.spamle or d == self.spambe) # try to read it back s = io.BytesIO(d) - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - f = reader(s) + f = reader(s) self.assertEqual(f.read(), "spamspam") def test_badbom(self): s = io.BytesIO(b"\xff\xff") - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - f = codecs.getreader(self.encoding)(s) + f = codecs.getreader(self.encoding)(s) self.assertRaises(UnicodeError, f.read) s = io.BytesIO(b"\xff\xff\xff\xff") - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - f = codecs.getreader(self.encoding)(s) + f = codecs.getreader(self.encoding)(s) self.assertRaises(UnicodeError, f.read) def test_partial(self): @@ -548,8 +517,7 @@ class UTF16Test(ReadTest): self.addCleanup(support.unlink, support.TESTFN) with open(support.TESTFN, 'wb') as fp: fp.write(s) - with codecs.open(support.TESTFN, 'U', - encoding=self.encoding) as reader: + with codecs.open(support.TESTFN, 'U', encoding=self.encoding) as reader: self.assertEqual(reader.read(), s1) class UTF16LETest(ReadTest): @@ -737,9 +705,7 @@ class UTF8SigTest(ReadTest): reader = codecs.getreader("utf-8-sig") for sizehint in [None] + list(range(1, 11)) + \ [64, 128, 256, 512, 1024]: - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - istream = reader(io.BytesIO(bytestring)) + istream = reader(io.BytesIO(bytestring)) ostream = io.StringIO() while 1: if sizehint is not None: @@ -761,9 +727,7 @@ class UTF8SigTest(ReadTest): reader = codecs.getreader("utf-8-sig") for sizehint in [None] + list(range(1, 11)) + \ [64, 128, 256, 512, 1024]: - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - istream = reader(io.BytesIO(bytestring)) + istream = reader(io.BytesIO(bytestring)) ostream = io.StringIO() while 1: if sizehint is not None: @@ -785,9 +749,7 @@ class EscapeDecodeTest(unittest.TestCase): class RecodingTest(unittest.TestCase): def test_recoding(self): f = io.BytesIO() - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - f2 = codecs.EncodedFile(f, "unicode_internal", "utf-8") + f2 = codecs.EncodedFile(f, "unicode_internal", "utf-8") f2.write("a") f2.close() # Python used to crash on this at exit because of a refcount @@ -1164,9 +1126,7 @@ class IDNACodecTest(unittest.TestCase): self.assertEqual("pyth\xf6n.org.".encode("idna"), b"xn--pythn-mua.org.") def test_stream(self): - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - r = codecs.getreader("idna")(io.BytesIO(b"abc")) + r = codecs.getreader("idna")(io.BytesIO(b"abc")) r.read(3) self.assertEqual(r.read(), "") @@ -1273,24 +1233,18 @@ class CodecsModuleTest(unittest.TestCase): class StreamReaderTest(unittest.TestCase): def setUp(self): - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - self.reader = codecs.getreader('utf-8') + self.reader = codecs.getreader('utf-8') self.stream = io.BytesIO(b'\xed\x95\x9c\n\xea\xb8\x80') def test_readlines(self): - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - f = self.reader(self.stream) + f = self.reader(self.stream) self.assertEqual(f.readlines(), ['\ud55c\n', '\uae00']) class EncodedFileTest(unittest.TestCase): def test_basic(self): f = io.BytesIO(b'\xed\x95\x9c\n\xea\xb8\x80') - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - ef = codecs.EncodedFile(f, 'utf-16-le', 'utf-8') + ef = codecs.EncodedFile(f, 'utf-16-le', 'utf-8') self.assertEqual(ef.read(), b'\\\xd5\n\x00\x00\xae') f = io.BytesIO() @@ -1434,9 +1388,7 @@ class BasicUnicodeTest(unittest.TestCase, MixInCheckStateHandling): if encoding not in broken_unicode_with_streams: # check stream reader/writer q = Queue(b"") - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - writer = codecs.getwriter(encoding)(q) + writer = codecs.getwriter(encoding)(q) encodedresult = b"" for c in s: writer.write(c) @@ -1444,9 +1396,7 @@ class BasicUnicodeTest(unittest.TestCase, MixInCheckStateHandling): self.assertTrue(type(chunk) is bytes, type(chunk)) encodedresult += chunk q = Queue(b"") - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - reader = codecs.getreader(encoding)(q) + reader = codecs.getreader(encoding)(q) decodedresult = "" for c in encodedresult: q.write(bytes([c])) @@ -1520,9 +1470,7 @@ class BasicUnicodeTest(unittest.TestCase, MixInCheckStateHandling): continue if encoding in broken_unicode_with_streams: continue - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - reader = codecs.getreader(encoding)(io.BytesIO(s.encode(encoding))) + reader = codecs.getreader(encoding)(io.BytesIO(s.encode(encoding))) for t in range(5): # Test that calling seek resets the internal codec state and buffers reader.seek(0, 0) @@ -1591,19 +1539,15 @@ class CharmapTest(unittest.TestCase): class WithStmtTest(unittest.TestCase): def test_encodedfile(self): f = io.BytesIO(b"\xc3\xbc") - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - with codecs.EncodedFile(f, "latin-1", "utf-8") as ef: - self.assertEqual(ef.read(), b"\xfc") + with codecs.EncodedFile(f, "latin-1", "utf-8") as ef: + self.assertEqual(ef.read(), b"\xfc") def test_streamreaderwriter(self): f = io.BytesIO(b"\xc3\xbc") info = codecs.lookup("utf-8") - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - with codecs.StreamReaderWriter(f, info.streamreader, - info.streamwriter, 'strict') as srw: - self.assertEqual(srw.read(), "\xfc") + with codecs.StreamReaderWriter(f, info.streamreader, + info.streamwriter, 'strict') as srw: + self.assertEqual(srw.read(), "\xfc") class TypesTest(unittest.TestCase): def test_decode_unicode(self): @@ -1700,15 +1644,15 @@ class BomTest(unittest.TestCase): # (StreamWriter) Check that the BOM is written after a seek(0) with codecs.open(support.TESTFN, 'w+', encoding=encoding) as f: - f.write(data[0]) - self.assertNotEqual(f.tell(), 0) - f.seek(0) - f.write(data) + f.writer.write(data[0]) + self.assertNotEqual(f.writer.tell(), 0) + f.writer.seek(0) + f.writer.write(data) f.seek(0) self.assertEqual(f.read(), data) - # Check that the BOM is not written after a seek() at a - # position different than the start + # Check that the BOM is not written after a seek() at a position + # different than the start with codecs.open(support.TESTFN, 'w+', encoding=encoding) as f: f.write(data) f.seek(f.tell()) @@ -1716,12 +1660,12 @@ class BomTest(unittest.TestCase): f.seek(0) self.assertEqual(f.read(), data * 2) - # (StreamWriter) Check that the BOM is not written after a - # seek() at a position different than the start + # (StreamWriter) Check that the BOM is not written after a seek() + # at a position different than the start with codecs.open(support.TESTFN, 'w+', encoding=encoding) as f: - f.write(data) - f.seek(f.tell()) - f.write(data) + f.writer.write(data) + f.writer.seek(f.writer.tell()) + f.writer.write(data) f.seek(0) self.assertEqual(f.read(), data * 2) @@ -1760,9 +1704,7 @@ class TransformCodecTest(unittest.TestCase): def test_read(self): for encoding in bytes_transform_encodings: sin = codecs.encode(b"\x80", encoding) - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - reader = codecs.getreader(encoding)(io.BytesIO(sin)) + reader = codecs.getreader(encoding)(io.BytesIO(sin)) sout = reader.read() self.assertEqual(sout, b"\x80") @@ -1771,9 +1713,7 @@ class TransformCodecTest(unittest.TestCase): if encoding in ['uu_codec', 'zlib_codec']: continue sin = codecs.encode(b"\x80", encoding) - with warnings.catch_warnings(): - warnings.simplefilter("ignore", DeprecationWarning) - reader = codecs.getreader(encoding)(io.BytesIO(sin)) + reader = codecs.getreader(encoding)(io.BytesIO(sin)) sout = reader.readline() self.assertEqual(sout, b"\x80") diff --git a/Misc/NEWS b/Misc/NEWS index df8bca8..2a916fd 100644 --- a/Misc/NEWS +++ b/Misc/NEWS @@ -167,11 +167,6 @@ Library - Issue #1625: BZ2File and bz2.decompress() now support multi-stream files. Initial patch by Nir Aides. -- Issue #8796: codecs.open() calls the builtin open() function instead of using - StreamReaderWriter. Deprecate StreamReader, StreamWriter, StreamReaderWriter, - StreamRecoder and EncodedFile() of the codec module. Use the builtin open() - function or io.TextIOWrapper instead. - - Issue #12175: BufferedReader.read(-1) now calls raw.readall() if available. - Issue #12175: FileIO.readall() now only reads the file position and size -- cgit v0.12