##// END OF EJS Templates
posix: always seek to EOF when opening a file in append mode...
posix: always seek to EOF when opening a file in append mode Python 3 already does this, so skip it there. Consider the program: #include <stdio.h> int main() { FILE *f = fopen("narf", "w"); fprintf(f, "narf\n"); fclose(f); f = fopen("narf", "a"); printf("%ld\n", ftell(f)); fprintf(f, "troz\n"); printf("%ld\n", ftell(f)); return 0; } on macOS, FreeBSD, and Linux with glibc, this program prints 5 10 but on musl libc (Alpine Linux and probably others) this prints 0 10 By my reading of https://pubs.opengroup.org/onlinepubs/009695399/functions/fopen.html this is technically correct, specifically: > Opening a file with append mode (a as the first character in the > mode argument) shall cause all subsequent writes to the file to be > forced to the then current end-of-file, regardless of intervening > calls to fseek(). in other words, the file position doesn't really matter in append-mode files, and we can't depend on it being at all meaningful unless we perform a seek() before tell() after open(..., 'a'). Experimentally after a .write() we can do a .tell() and it'll always be reasonable, but I'm unclear from reading the specification if that's a smart thing to rely on. This matches what we do on Windows and what Python 3 does for free, so let's just be consistent. Thanks to Yuya for the idea.

File last commit:

r40157:73fef626 default
r42778:97ada9b8 5.0.2 stable
Show More
test_train_dictionary.py
88 lines | 2.8 KiB | text/x-python | PythonLexer
import struct
import sys
import unittest
import zstandard as zstd
from . common import (
generate_samples,
make_cffi,
)
if sys.version_info[0] >= 3:
int_type = int
else:
int_type = long
@make_cffi
class TestTrainDictionary(unittest.TestCase):
def test_no_args(self):
with self.assertRaises(TypeError):
zstd.train_dictionary()
def test_bad_args(self):
with self.assertRaises(TypeError):
zstd.train_dictionary(8192, u'foo')
with self.assertRaises(ValueError):
zstd.train_dictionary(8192, [u'foo'])
def test_no_params(self):
d = zstd.train_dictionary(8192, generate_samples())
self.assertIsInstance(d.dict_id(), int_type)
# The dictionary ID may be different across platforms.
expected = b'\x37\xa4\x30\xec' + struct.pack('<I', d.dict_id())
data = d.as_bytes()
self.assertEqual(data[0:8], expected)
def test_basic(self):
d = zstd.train_dictionary(8192, generate_samples(), k=64, d=16)
self.assertIsInstance(d.dict_id(), int_type)
data = d.as_bytes()
self.assertEqual(data[0:4], b'\x37\xa4\x30\xec')
self.assertEqual(d.k, 64)
self.assertEqual(d.d, 16)
def test_set_dict_id(self):
d = zstd.train_dictionary(8192, generate_samples(), k=64, d=16,
dict_id=42)
self.assertEqual(d.dict_id(), 42)
def test_optimize(self):
d = zstd.train_dictionary(8192, generate_samples(), threads=-1, steps=1,
d=16)
# This varies by platform.
self.assertIn(d.k, (50, 2000))
self.assertEqual(d.d, 16)
@make_cffi
class TestCompressionDict(unittest.TestCase):
def test_bad_mode(self):
with self.assertRaisesRegexp(ValueError, 'invalid dictionary load mode'):
zstd.ZstdCompressionDict(b'foo', dict_type=42)
def test_bad_precompute_compress(self):
d = zstd.train_dictionary(8192, generate_samples(), k=64, d=16)
with self.assertRaisesRegexp(ValueError, 'must specify one of level or '):
d.precompute_compress()
with self.assertRaisesRegexp(ValueError, 'must only specify one of level or '):
d.precompute_compress(level=3,
compression_params=zstd.CompressionParameters())
def test_precompute_compress_rawcontent(self):
d = zstd.ZstdCompressionDict(b'dictcontent' * 64,
dict_type=zstd.DICT_TYPE_RAWCONTENT)
d.precompute_compress(level=1)
d = zstd.ZstdCompressionDict(b'dictcontent' * 64,
dict_type=zstd.DICT_TYPE_FULLDICT)
with self.assertRaisesRegexp(zstd.ZstdError, 'unable to precompute dictionary'):
d.precompute_compress(level=1)