##// 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:

r37966:3ea3c96a default
r43163:97ada9b8 5.0.2 stable
Show More
test-encoding-func.py
80 lines | 2.3 KiB | text/x-python | PythonLexer
/ tests / test-encoding-func.py
from __future__ import absolute_import
import unittest
from mercurial import (
encoding,
)
class IsasciistrTest(unittest.TestCase):
asciistrs = [
b'a',
b'ab',
b'abc',
b'abcd',
b'abcde',
b'abcdefghi',
b'abcd\0fghi',
]
def testascii(self):
for s in self.asciistrs:
self.assertTrue(encoding.isasciistr(s))
def testnonasciichar(self):
for s in self.asciistrs:
for i in range(len(s)):
t = bytearray(s)
t[i] |= 0x80
self.assertFalse(encoding.isasciistr(bytes(t)))
class LocalEncodingTest(unittest.TestCase):
def testasciifastpath(self):
s = b'\0' * 100
self.assertTrue(s is encoding.tolocal(s))
self.assertTrue(s is encoding.fromlocal(s))
class Utf8bEncodingTest(unittest.TestCase):
def setUp(self):
self.origencoding = encoding.encoding
def tearDown(self):
encoding.encoding = self.origencoding
def testasciifastpath(self):
s = b'\0' * 100
self.assertTrue(s is encoding.toutf8b(s))
self.assertTrue(s is encoding.fromutf8b(s))
def testlossylatin(self):
encoding.encoding = b'ascii'
s = u'\xc0'.encode('utf-8')
l = encoding.tolocal(s)
self.assertEqual(l, b'?') # lossy
self.assertEqual(s, encoding.toutf8b(l)) # utf8 sequence preserved
def testlosslesslatin(self):
encoding.encoding = b'latin-1'
s = u'\xc0'.encode('utf-8')
l = encoding.tolocal(s)
self.assertEqual(l, b'\xc0') # lossless
self.assertEqual(s, encoding.toutf8b(l)) # convert back to utf-8
def testlossy0xed(self):
encoding.encoding = b'euc-kr' # U+Dxxx Hangul
s = u'\ud1bc\xc0'.encode('utf-8')
l = encoding.tolocal(s)
self.assertIn(b'\xed', l)
self.assertTrue(l.endswith(b'?')) # lossy
self.assertEqual(s, encoding.toutf8b(l)) # utf8 sequence preserved
def testlossless0xed(self):
encoding.encoding = b'euc-kr' # U+Dxxx Hangul
s = u'\ud1bc'.encode('utf-8')
l = encoding.tolocal(s)
self.assertEqual(l, b'\xc5\xed') # lossless
self.assertEqual(s, encoding.toutf8b(l)) # convert back to utf-8
if __name__ == '__main__':
import silenttestrunner
silenttestrunner.main(__name__)