def __download_range(self, k, dst):
try:
_, ext = os.path.splitext(dst)
ds = []
parts = []
logging.info("Download %s start", k.name)
for startByte in range(0, k.size, self.splitMB):
output_part = self.new_temp_file(suffix=ext)
parts.append(output_part)
endByte = min(startByte + self.splitMB - 1, k.size)
logging.debug(
"deferToThreadPool %s start=%d end=%d size=%d cnt=%d",
k.name,
startByte,
endByte,
endByte - startByte,
len(ds),
)
d = twisted.internet.threads.deferToThreadPool(
reactor,
reactor.getThreadPool(), # @UndefinedVariable
self.__downloadOne,
k,
startByte,
endByte,
output_part,
len(ds),
)
ds.append(d)
if os.path.exists(dst):
os.remove(dst)
fout = file(dst, "wb")
start = timeit.default_timer()
for cnt, p in enumerate(parts):
yield ds[cnt]
shutil.copyfileobj(file(p, "rb"), fout)
size = min(k.size, (cnt + 1) * self.splitMB)
elapsed = timeit.default_timer() - start
speedstr = formatFileSize(size / elapsed)
sizestr = formatFileSize(size)
percent = (float(cnt) / len(parts)) * 100.0
logging.info(
"%03d/%03d (%.2f%%) speed=%s/s, elapsed=%.2f, size=%s",
cnt,
len(parts),
percent,
speedstr,
elapsed,
sizestr,
)
except Exception:
logging.error("download error", exc_info=True)
raise
def getFilesAndDirectories(self, directory):
files = []
dirs = []
for path in directory:
url = urllib.quote(path.encode('utf8'), "/")
escapedPath = cgi.escape(path)
if os.path.isdir(os.path.join(self.path, path)):
url = url + '/'
dirs.append({
'text': escapedPath + "/",
'href': url,
'size': '',
'type': '[Directory]',
'encoding': ''
})
else:
mimetype, encoding = static.getTypeAndEncoding(
path, self.contentTypes, self.contentEncodings,
self.defaultType)
try:
size = os.stat(os.path.join(self.path, path)).st_size
except OSError:
continue
files.append({
'text': escapedPath,
"href": url,
'type': '[%s]' % mimetype,
'encoding': (encoding and '[%s]' % encoding or ''),
'size': static.formatFileSize(size)
})
return dirs, files
def getFilesAndDirectories(self, directory):
files = []
dirs = []
for path in directory:
url = urllib.quote(path.encode('utf8'), "/")
escapedPath = cgi.escape(path)
if os.path.isdir(os.path.join(self.path, path)):
url = url + '/'
dirs.append({'text': escapedPath + "/", 'href': url,
'size': '', 'type': '[Directory]',
'encoding': ''})
else:
mimetype, encoding = static.getTypeAndEncoding(path, self.contentTypes,
self.contentEncodings,
self.defaultType)
try:
size = os.stat(os.path.join(self.path, path)).st_size
except OSError:
continue
files.append({
'text': escapedPath, "href": url,
'type': '[%s]' % mimetype,
'encoding': (encoding and '[%s]' % encoding or ''),
'size': static.formatFileSize(size)})
return dirs, files
def download(self, key, dst):
start = timeit.default_timer()
if key.size < self.splitMB:
key.get_contents_to_filename(dst)
else:
try:
yield self.__download_range(key, dst)
finally:
for f in self.tempfiles:
try:
os.unlink(f)
except Exception:
pass
elapsed = timeit.default_timer() - start
speedstr = formatFileSize(key.size / elapsed)
sizestr = formatFileSize(key.size)
logging.info("Done=%s dst=%s speed=%s/s, elapsed=%.2f, size=%s", key.name, dst, speedstr, elapsed, sizestr)
def __uploadOne(self, mp, src, dst, seek, cnt):
size = os.path.getsize(src)
sizestr = formatFileSize(size)
logging.debug("upload start src=%s, dst=%s, size=%s, seek=%d, cnt=%d", src, dst, sizestr, seek, cnt)
start = timeit.default_timer()
fd = file(src, "rb")
sd = cStringIO.StringIO()
fd.seek(seek)
content = fd.read(self.splitMB)
size = len(content)
sd.write(content)
sd.seek(0)
mp.upload_part_from_file(sd, cnt + 1, policy=self.grant)
elapsed = timeit.default_timer() - start
speedstr = formatFileSize(size / elapsed)
logging.info(
"upload end src=%s, dst=%s, size=%s, speed=%s/s, seek=%d, cnt=%d", src, dst, sizestr, speedstr, seek, cnt
)
def _getFilesAndDirectories(self, directory):
"""
Helper returning files and directories in given directory listing, with
attributes to be used to build a table content with
C{self.linePattern}.
@return: tuple of (directories, files)
@rtype: C{tuple} of C{list}
"""
files = []
dirs = []
for path in directory:
if _PY3:
if isinstance(path, bytes):
path = path.decode("utf8")
url = quote(path, "/")
escapedPath = escape(path)
childPath = filepath.FilePath(self.path).child(path)
if childPath.isdir():
dirs.append({
'text': escapedPath + "/",
'href': url + "/",
'size_int': -1,
'size': '',
'type': '[Directory]',
'encoding': '',
'ctime': ''
})
else:
mimetype, encoding = getTypeAndEncoding(
path, self.contentTypes, self.contentEncodings,
self.defaultType)
try:
size = childPath.getsize()
except OSError:
continue
files.append({
'text': escapedPath,
"href": url,
'type': '[%s]' % mimetype,
'encoding': (encoding and '[%s]' % encoding or ''),
'size_int': size,
'size': formatFileSize(size),
'ctime': self.getCreateTime(childPath.path)
})
return dirs, files
def test_formatFileSize(self):
"""
L{static.formatFileSize} format an amount of bytes into a more readable
format.
"""
self.assertEquals(static.formatFileSize(0), "0B")
self.assertEquals(static.formatFileSize(123), "123B")
self.assertEquals(static.formatFileSize(4567), "4K")
self.assertEquals(static.formatFileSize(8900000), "8M")
self.assertEquals(static.formatFileSize(1234000000), "1G")
self.assertEquals(static.formatFileSize(1234567890000), "1149G")
def test_formatFileSize(self):
"""
L{static.formatFileSize} format an amount of bytes into a more readable
format.
"""
self.assertEquals(static.formatFileSize(0), "0B")
self.assertEquals(static.formatFileSize(123), "123B")
self.assertEquals(static.formatFileSize(4567), "4K")
self.assertEquals(static.formatFileSize(8900000), "8M")
self.assertEquals(static.formatFileSize(1234000000), "1G")
self.assertEquals(static.formatFileSize(1234567890000), "1149G")
def targzip_package(tarpath, basedir, src_paths, src_excludes, checksum=False):
from twisted.web.static import formatFileSize
start = timeit.default_timer()
files = []
for src_path in src_paths:
try:
src_path.index("/")
except ValueError:
files.append(src_path)
continue
exp = re.compile(src_path)
# look for the deeper possible sub_path to search (e.g. faster)
exp_subpath = re.compile(r'^([\w\/]+)')
sub_path = exp_subpath.match(src_path).group(1)
sub_path = sub_path[:sub_path.rfind('/')]
logging.info("searching %s for '%s'", sub_path, src_path)
for dirpath, dirnames, filenames in os.walk(
os.path.join(basedir, sub_path)):
for filename in filenames:
path = os.path.join(dirpath, filename)
path = path[len(basedir) + 1:]
path = path.replace('\\', "/")
if exp.match(path):
files.append(path)
for dirname in dirnames:
path = os.path.join(dirpath, dirname)
if not os.path.islink(path):
continue
path = path[len(basedir) + 1:]
path = path.replace('\\', "/")
if exp.match(path):
files.append(path)
newfiles = []
src_excludes_exp = map(lambda x: re.compile(x), src_excludes)
for f in files:
add = True
for cnt, e in enumerate(src_excludes_exp):
if e.match(f):
add = False
logging.debug("excluding %s (based on %s)", f,
src_excludes[cnt])
break
if add:
newfiles.append(f)
files = newfiles
files.sort()
if not files:
logging.warning("skipping targzip_package, no files")
return None
logging.info("targzip_package: search elapsed=%.2f",
timeit.default_timer() - start)
# checksum
image_size = 0
if checksum:
start = timeit.default_timer()
sha_image = sha()
for f in files:
logging.debug("checksum %s", f)
path = os.path.join(basedir, f)
if os.path.islink(path):
sha_image.update(os.readlink(path)) # @UndefinedVariable
continue
fd = open(path, "rb")
while 1:
buf = fd.read(IMAGE_IO_CHUNK)
if not buf:
break
sha_image.update(buf)
image_size += os.path.getsize(path)
image_digest = hexlify(sha_image.digest())
logging.info("targzip_package: sha=%s, size=%d, elapsed=%.2f",
image_digest, image_size, timeit.default_timer() - start)
else:
image_digest = None
for f in files:
path = os.path.join(basedir, f)
if not os.path.islink(path):
image_size += os.path.getsize(path)
# tar/gzip
start = timeit.default_timer()
tar_file = targzip_files(tarpath, files, basedir)
tar_size = os.path.getsize(tar_file)
logging.info(
"targzip_package: size=%s, compressed=%s, ratio=%.2f%%, elapsed=%.2f",
formatFileSize(image_size), formatFileSize(tar_size),
(float(tar_size) / image_size) * 100,
timeit.default_timer() - start)
return tar_file, image_digest
def _getFilesAndDirectories(self, directory):
"""
Helper returning files and directories in given directory listing, with
attributes to be used to build a table content with
C{self.linePattern}.
@return: tuple of (directories, files)
@rtype: C{tuple} of C{list}
"""
files = []
dirs = []
dirs.append({'text':"<i>Parent Directory</i>", 'href': "..",
'size': '', 'type': '',
# 'encoding': '',
'mtime': "",
'commstr': ""
})
for path in directory:
if path[0] == ".": # ignore filenames that begin with "."
continue
mtime = time.asctime(time.localtime(os.path.getmtime(os.path.join(self.path, path))))
url = urllib.quote(path, "/")
escapedPath = cgi.escape(path)
# print "path %s url %s escapedPath %s" %(path, url, escapedPath)
if os.path.isdir(os.path.join(self.path, path)):
url = url + '/'
dirs.append({'text': escapedPath + "/", 'href': url,
'size': '', 'type': '[Directory]',
# 'encoding': '',
'mtime': mtime,
'commstr': ''
})
else:
mimetype, encoding = getTypeAndEncoding(path, self.contentTypes,
self.contentEncodings,
self.defaultType)
try:
size = os.stat(os.path.join(self.path, path)).st_size
except OSError:
continue
extension = os.path.splitext(path)[1]
if extension == ".dbm": # ignore .dbm files
continue
if extension == ".db": # if it's ".db"
str = path[:-3]
extension = os.path.splitext(str)[1]
if extension == ".dbm": # and if there's also a ".dbm"
continue # just ignore it - MacOSX (esp. Mountain Lion) likes to
# add .dbm.db (see comment in snmpsimd.py) - so don't show it
theCommStr = ""
if (extension == ".snmprec") or (extension == ".sapwalk") or (extension == ".snmpwalk"):
bdLen = len(myBaseDir) + len("/data/")
theCommStr = self.path[bdLen:] # get the path up to .../data
if theCommStr != "": # if it's non-empty
theCommStr += "/" # append the "/"
theCommStr += path[:-len(extension)] # append the file name, less the extension
## ** Comment **
## Add attributes the the "elements" displayed in each line
files.append({
'text': escapedPath, "href": url,
'type': '[%s]' % mimetype,
# 'encoding': (encoding and '[%s]' % encoding or ''),
'size': formatFileSize(size),
'mtime': mtime,
'commstr': theCommStr,
}
)
return dirs, files
