mirror of https://github.com/python/cpython
(This fix is really by Jeremy)
Here's my suggested replacement for gzip.py for 1.5.1. I've re-implemeted methods readline and readlines, added an _unread, and tweaked read and _read. I tried a more complicated buffer scheme for unread (using a list of strings and string.join), but it was more complicated and slower. This version is a lot faster than the current version and is still pretty simple.
This commit is contained in:
parent
7570669a08
commit
b16a3b8450
49
Lib/gzip.py
49
Lib/gzip.py
|
@ -81,7 +81,6 @@ class GzipFile:
|
|||
elif self.mode == READ:
|
||||
self._read_gzip_header()
|
||||
|
||||
|
||||
def __repr__(self):
|
||||
s = repr(self.fileobj)
|
||||
return '<gzip ' + s[1:-1] + ' ' + hex(id(self)) + '>'
|
||||
|
@ -162,18 +161,19 @@ class GzipFile:
|
|||
if self.extrasize <= 0 and self.fileobj is None:
|
||||
return ''
|
||||
|
||||
if not size:
|
||||
# get the whole thing
|
||||
readsize = 1024
|
||||
if not size: # get the whole thing
|
||||
try:
|
||||
while 1:
|
||||
self._read()
|
||||
self._read(readsize)
|
||||
readsize = readsize * 2
|
||||
except EOFError:
|
||||
size = self.extrasize
|
||||
else:
|
||||
# just get some more of it
|
||||
else: # just get some more of it
|
||||
try:
|
||||
while size > self.extrasize:
|
||||
self._read()
|
||||
self._read(readsize)
|
||||
readsize = readsize * 2
|
||||
except EOFError:
|
||||
pass
|
||||
|
||||
|
@ -183,8 +183,15 @@ class GzipFile:
|
|||
|
||||
return chunk
|
||||
|
||||
def _read(self):
|
||||
buf = self.fileobj.read(1024)
|
||||
def _unread(self, buf):
|
||||
self.extrabuf = buf + self.extrabuf
|
||||
self.extrasize = len(buf) + self.extrasize
|
||||
|
||||
def _read(self, size=1024):
|
||||
try:
|
||||
buf = self.fileobj.read(size)
|
||||
except AttributeError:
|
||||
raise EOFError, "Reached EOF"
|
||||
if buf == "":
|
||||
uncompress = self.decompress.flush()
|
||||
if uncompress == "":
|
||||
|
@ -237,21 +244,21 @@ class GzipFile:
|
|||
return 0
|
||||
|
||||
def readline(self):
|
||||
# XXX This function isn't implemented in a very efficient way
|
||||
line=""
|
||||
bufs = []
|
||||
readsize = 100
|
||||
while 1:
|
||||
c = self.read(1)
|
||||
line = line + c
|
||||
if c=='\n' or c=="": break
|
||||
return line
|
||||
c = self.read(readsize)
|
||||
i = string.find(c, '\n')
|
||||
if i >= 0 or c == '':
|
||||
bufs.append(c[:i])
|
||||
self._unread(c[i+1:])
|
||||
return string.join(bufs, '')
|
||||
bufs.append(c)
|
||||
readsize = readsize * 2
|
||||
|
||||
def readlines(self):
|
||||
L=[]
|
||||
line = self.readline()
|
||||
while line!="":
|
||||
L.append(line)
|
||||
line = self.readline()
|
||||
return L
|
||||
buf = self.read()
|
||||
return string.split(buf, '\n')
|
||||
|
||||
def writelines(self, L):
|
||||
for line in L:
|
||||
|
|
Loading…
Reference in New Issue