def check_reader(unicode_string, encoding, n=1000):
bytestr = unicode_string.encode(encoding)
strlen = len(unicode_string)
stream = BytesIO(bytestr)
reader = SeekableUnicodeStreamReader(stream, encoding)
# Find all character positions
chars = []
while True:
pos = reader.tell()
chars.append((pos, reader.read(1)))
if chars[-1][1] == '':
break
# Find all strings
strings = dict((pos, '') for (pos, c) in chars)
for pos1, char in chars:
for pos2, _ in chars:
if pos2 <= pos1:
strings[pos2] += char
while True:
op = random.choice('tsrr')
# Check our position?
if op == 't': # tell
reader.tell()
# Perform a seek?
if op == 's': # seek
new_pos = random.choice([p for (p, c) in chars])
reader.seek(new_pos)
# Perform a read?
if op == 'r': # read
if random.random() < 0.3:
pos = reader.tell()
else:
pos = None
if random.random() < 0.2:
size = None
elif random.random() < 0.8:
size = random.randint(0, int(strlen / 6))
else:
size = random.randint(0, strlen + 20)
if random.random() < 0.8:
s = reader.read(size)
else:
s = reader.readline(size)
# check that everything's consistent
if pos is not None:
assert pos in strings
assert strings[pos].startswith(s)
n -= 1
if n == 0:
return 'passed'
def check_reader(unicode_string, encoding, n=1000):
bytestr = unicode_string.encode(encoding)
strlen = len(unicode_string)
stream = BytesIO(bytestr)
reader = SeekableUnicodeStreamReader(stream, encoding)
# Find all character positions
chars = []
while True:
pos = reader.tell()
chars.append( (pos, reader.read(1)) )
if chars[-1][1] == '': break
# Find all strings
strings = dict( (pos,'') for (pos,c) in chars )
for pos1, char in chars:
for pos2, _ in chars:
if pos2 <= pos1:
strings[pos2] += char
while True:
op = random.choice('tsrr')
# Check our position?
if op == 't': # tell
reader.tell()
# Perform a seek?
if op == 's': # seek
new_pos = random.choice([p for (p,c) in chars])
reader.seek(new_pos)
# Perform a read?
if op == 'r': # read
if random.random() < .3: pos = reader.tell()
else: pos = None
if random.random() < .2: size = None
elif random.random() < .8:
size = random.randint(0, int(strlen/6))
else: size = random.randint(0, strlen+20)
if random.random() < .8:
s = reader.read(size)
else:
s = reader.readline(size)
# check that everything's consistent
if pos is not None:
assert pos in strings
assert strings[pos].startswith(s)
n -= 1
if n == 0:
return 'passed'
def check_reader(unicode_string, encoding):
bytestr = unicode_string.encode(encoding)
stream = BytesIO(bytestr)
reader = SeekableUnicodeStreamReader(stream, encoding)
# Should open at the start of the file
assert reader.tell() == 0
# Compare original string to contents from `.readlines()`
assert unicode_string == "".join(reader.readlines())
# Should be at the end of the file now
stream.seek(0, os.SEEK_END)
assert reader.tell() == stream.tell()
reader.seek(0) # go back to start
# Compare original string to contents from `.read()`
contents = ""
char = None
while char != "":
char = reader.read(1)
contents += char
assert unicode_string == contents