procutil: make stream detection in make_line_buffered more correct and strict
In make_line_buffered(), we don’t want to wrap the stream if we know that lines
get flushed to the underlying raw stream already.
Previously, the heuristic was too optimistic. It assumed that any stream which
is not an instance of io.BufferedIOBase doesn’t need wrapping. However, there
are buffered streams that aren’t instances of io.BufferedIOBase, like
Mercurial’s own winstdout.
The new logic is different in two ways:
First, only for the check, if unwraps any combination of WriteAllWrapper and
winstdout.
Second, it skips wrapping the stream only if it is an instance of io.RawIOBase
(or already wrapped). If it is an instance of io.BufferedIOBase, it gets
wrapped. In any other case, the function raises an exception. This ensures
that, if an unknown stream is passed or we add another wrapper in the future,
we don’t wrap the stream if it’s already line buffered or not wrap the stream
if it’s not line buffered. In fact, this was already helpful during development
of this change. Without it, I possibly would have forgot that WriteAllWrapper
needs to be ignored for the check, leading to unnecessary wrapping if stdout is
unbuffered.
The alternative would have been to always wrap unknown streams. However, I
don’t think that anyone would benefit from being less strict. We can expect
streams from the standard library to be subclassing either io.RawIOBase or
io.BufferedIOBase, so running Mercurial in the standard way should not regress
by this change. Py2exe might replace sys.stdout and sys.stderr, but that
currently breaks Mercurial anyway and also these streams don’t claim to be
interactive, so this function is not called for them.
# Copyright (c) 2016-present, Gregory Szorc
# All rights reserved.
#
# This software may be modified and distributed under the terms
# of the BSD license. See the LICENSE file for details.
import cffi
import distutils.ccompiler
import os
import re
import subprocess
import tempfile
HERE = os.path.abspath(os.path.dirname(__file__))
SOURCES = [
"zstd/%s" % p
for p in (
"common/debug.c",
"common/entropy_common.c",
"common/error_private.c",
"common/fse_decompress.c",
"common/pool.c",
"common/threading.c",
"common/xxhash.c",
"common/zstd_common.c",
"compress/fse_compress.c",
"compress/hist.c",
"compress/huf_compress.c",
"compress/zstd_compress.c",
"compress/zstd_compress_literals.c",
"compress/zstd_compress_sequences.c",
"compress/zstd_double_fast.c",
"compress/zstd_fast.c",
"compress/zstd_lazy.c",
"compress/zstd_ldm.c",
"compress/zstd_opt.c",
"compress/zstdmt_compress.c",
"decompress/huf_decompress.c",
"decompress/zstd_ddict.c",
"decompress/zstd_decompress.c",
"decompress/zstd_decompress_block.c",
"dictBuilder/cover.c",
"dictBuilder/fastcover.c",
"dictBuilder/divsufsort.c",
"dictBuilder/zdict.c",
)
]
# Headers whose preprocessed output will be fed into cdef().
HEADERS = [
os.path.join(HERE, "zstd", *p)
for p in (
("zstd.h",),
("dictBuilder", "zdict.h"),
)
]
INCLUDE_DIRS = [
os.path.join(HERE, d)
for d in (
"zstd",
"zstd/common",
"zstd/compress",
"zstd/decompress",
"zstd/dictBuilder",
)
]
# cffi can't parse some of the primitives in zstd.h. So we invoke the
# preprocessor and feed its output into cffi.
compiler = distutils.ccompiler.new_compiler()
# Needed for MSVC.
if hasattr(compiler, "initialize"):
compiler.initialize()
# Distutils doesn't set compiler.preprocessor, so invoke the preprocessor
# manually.
if compiler.compiler_type == "unix":
args = list(compiler.executables["compiler"])
args.extend(
[
"-E",
"-DZSTD_STATIC_LINKING_ONLY",
"-DZDICT_STATIC_LINKING_ONLY",
]
)
elif compiler.compiler_type == "msvc":
args = [compiler.cc]
args.extend(
[
"/EP",
"/DZSTD_STATIC_LINKING_ONLY",
"/DZDICT_STATIC_LINKING_ONLY",
]
)
else:
raise Exception("unsupported compiler type: %s" % compiler.compiler_type)
def preprocess(path):
with open(path, "rb") as fh:
lines = []
it = iter(fh)
for l in it:
# zstd.h includes <stddef.h>, which is also included by cffi's
# boilerplate. This can lead to duplicate declarations. So we strip
# this include from the preprocessor invocation.
#
# The same things happens for including zstd.h, so give it the same
# treatment.
#
# We define ZSTD_STATIC_LINKING_ONLY, which is redundant with the inline
# #define in zstdmt_compress.h and results in a compiler warning. So drop
# the inline #define.
if l.startswith(
(
b"#include <stddef.h>",
b'#include "zstd.h"',
b"#define ZSTD_STATIC_LINKING_ONLY",
)
):
continue
# The preprocessor environment on Windows doesn't define include
# paths, so the #include of limits.h fails. We work around this
# by removing that import and defining INT_MAX ourselves. This is
# a bit hacky. But it gets the job done.
# TODO make limits.h work on Windows so we ensure INT_MAX is
# correct.
if l.startswith(b"#include <limits.h>"):
l = b"#define INT_MAX 2147483647\n"
# ZSTDLIB_API may not be defined if we dropped zstd.h. It isn't
# important so just filter it out.
if l.startswith(b"ZSTDLIB_API"):
l = l[len(b"ZSTDLIB_API ") :]
lines.append(l)
fd, input_file = tempfile.mkstemp(suffix=".h")
os.write(fd, b"".join(lines))
os.close(fd)
try:
env = dict(os.environ)
if getattr(compiler, "_paths", None):
env["PATH"] = compiler._paths
process = subprocess.Popen(
args + [input_file], stdout=subprocess.PIPE, env=env
)
output = process.communicate()[0]
ret = process.poll()
if ret:
raise Exception("preprocessor exited with error")
return output
finally:
os.unlink(input_file)
def normalize_output(output):
lines = []
for line in output.splitlines():
# CFFI's parser doesn't like __attribute__ on UNIX compilers.
if line.startswith(b'__attribute__ ((visibility ("default"))) '):
line = line[len(b'__attribute__ ((visibility ("default"))) ') :]
if line.startswith(b"__attribute__((deprecated("):
continue
elif b"__declspec(deprecated(" in line:
continue
lines.append(line)
return b"\n".join(lines)
ffi = cffi.FFI()
# zstd.h uses a possible undefined MIN(). Define it until
# https://github.com/facebook/zstd/issues/976 is fixed.
# *_DISABLE_DEPRECATE_WARNINGS prevents the compiler from emitting a warning
# when cffi uses the function. Since we statically link against zstd, even
# if we use the deprecated functions it shouldn't be a huge problem.
ffi.set_source(
"_zstd_cffi",
"""
#define MIN(a,b) ((a)<(b) ? (a) : (b))
#define ZSTD_STATIC_LINKING_ONLY
#include <zstd.h>
#define ZDICT_STATIC_LINKING_ONLY
#define ZDICT_DISABLE_DEPRECATE_WARNINGS
#include <zdict.h>
""",
sources=SOURCES,
include_dirs=INCLUDE_DIRS,
extra_compile_args=["-DZSTD_MULTITHREAD"],
)
DEFINE = re.compile(b"^\\#define ([a-zA-Z0-9_]+) ")
sources = []
# Feed normalized preprocessor output for headers into the cdef parser.
for header in HEADERS:
preprocessed = preprocess(header)
sources.append(normalize_output(preprocessed))
# #define's are effectively erased as part of going through preprocessor.
# So perform a manual pass to re-add those to the cdef source.
with open(header, "rb") as fh:
for line in fh:
line = line.strip()
m = DEFINE.match(line)
if not m:
continue
if m.group(1) == b"ZSTD_STATIC_LINKING_ONLY":
continue
# The parser doesn't like some constants with complex values.
if m.group(1) in (b"ZSTD_LIB_VERSION", b"ZSTD_VERSION_STRING"):
continue
# The ... is magic syntax by the cdef parser to resolve the
# value at compile time.
sources.append(m.group(0) + b" ...")
cdeflines = b"\n".join(sources).splitlines()
cdeflines = [l for l in cdeflines if l.strip()]
ffi.cdef(b"\n".join(cdeflines).decode("latin1"))
if __name__ == "__main__":
ffi.compile()