diff options
Diffstat (limited to 'Lib')
| -rw-r--r-- | Lib/bz2.py | 81 | ||||
| -rw-r--r-- | Lib/test/test_subprocess.py | 123 |
2 files changed, 149 insertions, 55 deletions
@@ -79,7 +79,8 @@ class BZ2File(io.BufferedIOBase): mode = "rb" mode_code = _MODE_READ self._decompressor = BZ2Decompressor() - self._buffer = None + self._buffer = b"" + self._buffer_offset = 0 elif mode in ("w", "wb"): mode = "wb" mode_code = _MODE_WRITE @@ -124,7 +125,8 @@ class BZ2File(io.BufferedIOBase): self._fp = None self._closefp = False self._mode = _MODE_CLOSED - self._buffer = None + self._buffer = b"" + self._buffer_offset = 0 @property def closed(self): @@ -174,16 +176,13 @@ class BZ2File(io.BufferedIOBase): # Fill the readahead buffer if it is empty. Returns False on EOF. def _fill_buffer(self): + if self._mode == _MODE_READ_EOF: + return False # Depending on the input data, our call to the decompressor may not # return any data. In this case, try again after reading another block. - while True: - if self._buffer: - return True - - if self._decompressor.unused_data: - rawblock = self._decompressor.unused_data - else: - rawblock = self._fp.read(_BUFFER_SIZE) + while self._buffer_offset == len(self._buffer): + rawblock = (self._decompressor.unused_data or + self._fp.read(_BUFFER_SIZE)) if not rawblock: if self._decompressor.eof: @@ -199,30 +198,48 @@ class BZ2File(io.BufferedIOBase): self._decompressor = BZ2Decompressor() self._buffer = self._decompressor.decompress(rawblock) + self._buffer_offset = 0 + return True # Read data until EOF. # If return_data is false, consume the data without returning it. def _read_all(self, return_data=True): + # The loop assumes that _buffer_offset is 0. Ensure that this is true. + self._buffer = self._buffer[self._buffer_offset:] + self._buffer_offset = 0 + blocks = [] while self._fill_buffer(): if return_data: blocks.append(self._buffer) self._pos += len(self._buffer) - self._buffer = None + self._buffer = b"" if return_data: return b"".join(blocks) # Read a block of up to n bytes. # If return_data is false, consume the data without returning it. def _read_block(self, n, return_data=True): + # If we have enough data buffered, return immediately. + end = self._buffer_offset + n + if end <= len(self._buffer): + data = self._buffer[self._buffer_offset : end] + self._buffer_offset = end + self._pos += len(data) + return data if return_data else None + + # The loop assumes that _buffer_offset is 0. Ensure that this is true. + self._buffer = self._buffer[self._buffer_offset:] + self._buffer_offset = 0 + blocks = [] while n > 0 and self._fill_buffer(): if n < len(self._buffer): data = self._buffer[:n] - self._buffer = self._buffer[n:] + self._buffer_offset = n else: data = self._buffer - self._buffer = None + self._buffer = b"" if return_data: blocks.append(data) self._pos += len(data) @@ -238,9 +255,9 @@ class BZ2File(io.BufferedIOBase): """ with self._lock: self._check_can_read() - if self._mode == _MODE_READ_EOF or not self._fill_buffer(): + if not self._fill_buffer(): return b"" - return self._buffer + return self._buffer[self._buffer_offset:] def read(self, size=-1): """Read up to size uncompressed bytes from the file. @@ -250,7 +267,7 @@ class BZ2File(io.BufferedIOBase): """ with self._lock: self._check_can_read() - if self._mode == _MODE_READ_EOF or size == 0: + if size == 0: return b"" elif size < 0: return self._read_all() @@ -268,15 +285,19 @@ class BZ2File(io.BufferedIOBase): # In this case we make multiple reads, to avoid returning b"". with self._lock: self._check_can_read() - if (size == 0 or self._mode == _MODE_READ_EOF or - not self._fill_buffer()): + if (size == 0 or + # Only call _fill_buffer() if the buffer is actually empty. + # This gives a significant speedup if *size* is small. + (self._buffer_offset == len(self._buffer) and not self._fill_buffer())): return b"" - if 0 < size < len(self._buffer): - data = self._buffer[:size] - self._buffer = self._buffer[size:] + if size > 0: + data = self._buffer[self._buffer_offset : + self._buffer_offset + size] + self._buffer_offset += len(data) else: - data = self._buffer - self._buffer = None + data = self._buffer[self._buffer_offset:] + self._buffer = b"" + self._buffer_offset = 0 self._pos += len(data) return data @@ -299,6 +320,14 @@ class BZ2File(io.BufferedIOBase): raise TypeError("Integer argument expected") size = size.__index__() with self._lock: + # Shortcut for the common case - the whole line is in the buffer. + if size < 0: + end = self._buffer.find(b"\n", self._buffer_offset) + 1 + if end > 0: + line = self._buffer[self._buffer_offset : end] + self._buffer_offset = end + self._pos += len(line) + return line return io.BufferedIOBase.readline(self, size) def readlines(self, size=-1): @@ -345,7 +374,8 @@ class BZ2File(io.BufferedIOBase): self._mode = _MODE_READ self._pos = 0 self._decompressor = BZ2Decompressor() - self._buffer = None + self._buffer = b"" + self._buffer_offset = 0 def seek(self, offset, whence=0): """Change the file position. @@ -385,8 +415,7 @@ class BZ2File(io.BufferedIOBase): offset -= self._pos # Read and discard data until we reach the desired position. - if self._mode != _MODE_READ_EOF: - self._read_block(offset, return_data=False) + self._read_block(offset, return_data=False) return self._pos diff --git a/Lib/test/test_subprocess.py b/Lib/test/test_subprocess.py index 2420772..24924f6 100644 --- a/Lib/test/test_subprocess.py +++ b/Lib/test/test_subprocess.py @@ -1,4 +1,5 @@ import unittest +from test import script_helper from test import support import subprocess import sys @@ -191,15 +192,101 @@ class ProcessTestCase(BaseTestCase): p.wait() self.assertEqual(p.stderr, None) + # For use in the test_cwd* tests below. + def _normalize_cwd(self, cwd): + # Normalize an expected cwd (for Tru64 support). + # We can't use os.path.realpath since it doesn't expand Tru64 {memb} + # strings. See bug #1063571. + original_cwd = os.getcwd() + os.chdir(cwd) + cwd = os.getcwd() + os.chdir(original_cwd) + return cwd + + # For use in the test_cwd* tests below. + def _split_python_path(self): + # Return normalized (python_dir, python_base). + python_path = os.path.realpath(sys.executable) + return os.path.split(python_path) + + # For use in the test_cwd* tests below. + def _assert_cwd(self, expected_cwd, python_arg, **kwargs): + # Invoke Python via Popen, and assert that (1) the call succeeds, + # and that (2) the current working directory of the child process + # matches *expected_cwd*. + p = subprocess.Popen([python_arg, "-c", + "import os, sys; " + "sys.stdout.write(os.getcwd()); " + "sys.exit(47)"], + stdout=subprocess.PIPE, + **kwargs) + self.addCleanup(p.stdout.close) + p.wait() + self.assertEqual(47, p.returncode) + normcase = os.path.normcase + self.assertEqual(normcase(expected_cwd), + normcase(p.stdout.read().decode("utf-8"))) + + def test_cwd(self): + # Check that cwd changes the cwd for the child process. + temp_dir = tempfile.gettempdir() + temp_dir = self._normalize_cwd(temp_dir) + self._assert_cwd(temp_dir, sys.executable, cwd=temp_dir) + + def test_cwd_with_relative_arg(self): + # Check that Popen looks for args[0] relative to cwd if args[0] + # is relative. + python_dir, python_base = self._split_python_path() + rel_python = os.path.join(os.curdir, python_base) + with support.temp_cwd() as wrong_dir: + # Before calling with the correct cwd, confirm that the call fails + # without cwd and with the wrong cwd. + self.assertRaises(FileNotFoundError, subprocess.Popen, + [rel_python]) + self.assertRaises(FileNotFoundError, subprocess.Popen, + [rel_python], cwd=wrong_dir) + python_dir = self._normalize_cwd(python_dir) + self._assert_cwd(python_dir, rel_python, cwd=python_dir) + + def test_cwd_with_relative_executable(self): + # Check that Popen looks for executable relative to cwd if executable + # is relative (and that executable takes precedence over args[0]). + python_dir, python_base = self._split_python_path() + rel_python = os.path.join(os.curdir, python_base) + doesntexist = "somethingyoudonthave" + with support.temp_cwd() as wrong_dir: + # Before calling with the correct cwd, confirm that the call fails + # without cwd and with the wrong cwd. + self.assertRaises(FileNotFoundError, subprocess.Popen, + [doesntexist], executable=rel_python) + self.assertRaises(FileNotFoundError, subprocess.Popen, + [doesntexist], executable=rel_python, + cwd=wrong_dir) + python_dir = self._normalize_cwd(python_dir) + self._assert_cwd(python_dir, doesntexist, executable=rel_python, + cwd=python_dir) + + def test_cwd_with_absolute_arg(self): + # Check that Popen can find the executable when the cwd is wrong + # if args[0] is an absolute path. + python_dir, python_base = self._split_python_path() + abs_python = os.path.join(python_dir, python_base) + rel_python = os.path.join(os.curdir, python_base) + with script_helper.temp_dir() as wrong_dir: + # Before calling with an absolute path, confirm that using a + # relative path fails. + self.assertRaises(FileNotFoundError, subprocess.Popen, + [rel_python], cwd=wrong_dir) + wrong_dir = self._normalize_cwd(wrong_dir) + self._assert_cwd(wrong_dir, abs_python, cwd=wrong_dir) + @unittest.skipIf(sys.base_prefix != sys.prefix, 'Test is not venv-compatible') def test_executable_with_cwd(self): - python_dir = os.path.dirname(os.path.realpath(sys.executable)) - p = subprocess.Popen(["somethingyoudonthave", "-c", - "import sys; sys.exit(47)"], - executable=sys.executable, cwd=python_dir) - p.wait() - self.assertEqual(p.returncode, 47) + python_dir, python_base = self._split_python_path() + python_dir = self._normalize_cwd(python_dir) + self._assert_cwd(python_dir, "somethingyoudonthave", + executable=sys.executable, cwd=python_dir) @unittest.skipIf(sys.base_prefix != sys.prefix, 'Test is not venv-compatible') @@ -208,11 +295,7 @@ class ProcessTestCase(BaseTestCase): def test_executable_without_cwd(self): # For a normal installation, it should work without 'cwd' # argument. For test runs in the build directory, see #7774. - p = subprocess.Popen(["somethingyoudonthave", "-c", - "import sys; sys.exit(47)"], - executable=sys.executable) - p.wait() - self.assertEqual(p.returncode, 47) + self._assert_cwd('', "somethingyoudonthave", executable=sys.executable) def test_stdin_pipe(self): # stdin redirection @@ -369,24 +452,6 @@ class ProcessTestCase(BaseTestCase): p.wait() self.assertEqual(p.stdin, None) - def test_cwd(self): - tmpdir = tempfile.gettempdir() - # We cannot use os.path.realpath to canonicalize the path, - # since it doesn't expand Tru64 {memb} strings. See bug 1063571. - cwd = os.getcwd() - os.chdir(tmpdir) - tmpdir = os.getcwd() - os.chdir(cwd) - p = subprocess.Popen([sys.executable, "-c", - 'import sys,os;' - 'sys.stdout.write(os.getcwd())'], - stdout=subprocess.PIPE, - cwd=tmpdir) - self.addCleanup(p.stdout.close) - normcase = os.path.normcase - self.assertEqual(normcase(p.stdout.read().decode("utf-8")), - normcase(tmpdir)) - def test_env(self): newenv = os.environ.copy() newenv["FRUIT"] = "orange" |