Python gzip.decompress方法代码示例

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def patch_id(repo):
        url = repo + 'repodata/repomd.xml'
        repomd = requests.get(url)
        if not repomd.ok:
            return None
        root = ET.fromstring(repomd.text)

        cs = root.find(
            './/{http://linux.duke.edu/metadata/repo}data[@type="updateinfo"]/{http://linux.duke.edu/metadata/repo}location')
        try:
            url = repo + cs.attrib['href']
        except AttributeError:
            return None

        repomd = requests.get(url).content
        root = ET.fromstring(decompress(repomd))
        return root.find('.//id').text

    # take the first package name we find - often enough correct 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def testRequest(self):
        runner.run(
            self._func, 'p', ('foo', 'bar'), host=_HOST, port=_PORT)
        response = urllib.request.urlopen(
            'http://%s:%s/profile' % (_HOST, _PORT))
        response_data = gzip.decompress(response.read())
        stats = json.loads(response_data.decode('utf-8'))
        curr_filename = inspect.getabsfile(inspect.currentframe())
        self.assertEqual(stats['p']['objectName'],
                         '_func @ %s (function)' % curr_filename)
        self.assertTrue(len(stats['p']['callStats']) > 0)
        self.assertTrue(stats['p']['totalTime'] > 0)
        self.assertTrue(stats['p']['primitiveCalls'] > 0)
        self.assertTrue(stats['p']['totalCalls'] > 0)


# pylint: enable=missing-docstring, blacklisted-name 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def testRequest(self):
        runner.run(
            self._func, 'h', ('foo', 'bar'), host=_HOST, port=_PORT)
        response = urllib.request.urlopen(
            'http://%s:%s/profile' % (_HOST, _PORT))
        response_data = gzip.decompress(response.read())
        stats = json.loads(response_data.decode('utf-8'))
        self.assertTrue(stats['h']['runTime'] > 0)
        heatmaps = stats['h']['heatmaps']
        curr_filename = inspect.getabsfile(inspect.currentframe())
        self.assertEqual(stats['h']['objectName'],
                         '_func @ %s (function)' % curr_filename)
        self.assertEqual(len(heatmaps), 1)
        self.assertDictEqual(
            heatmaps[0]['executionCount'], {'101': 1, '102': 1})
        self.assertListEqual(
            heatmaps[0]['srcCode'],
            [['line', 100, u'        def _func(foo, bar):\n'],
             ['line', 101, u'            baz = foo + bar\n'],
             ['line', 102, u'            return baz\n']])

# pylint: enable=missing-docstring, blacklisted-name 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def testRequest(self):
        runner.run(
            self._func, 'c', ('foo', 'bar'), host=_HOST, port=_PORT)
        response = urllib.request.urlopen(
            'http://%s:%s/profile' % (_HOST, _PORT))
        response_data = gzip.decompress(response.read())
        stats = json.loads(response_data.decode('utf-8'))
        curr_filename = inspect.getabsfile(inspect.currentframe())
        self.assertEqual(stats['c']['objectName'],
                         '_func @ %s (function)' % curr_filename)
        self.assertEqual(
            stats['c']['sampleInterval'], flame_graph._SAMPLE_INTERVAL)
        self.assertTrue(stats['c']['runTime'] > 0)
        self.assertTrue(len(stats['c']['callStats']) >= 0)
        self.assertTrue(stats['c']['totalSamples'] >= 0)

# pylint: enable=missing-docstring, blacklisted-name, protected-access 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def testRequest(self):
        runner.run(
            self._func, 'm', ('foo', 'bar'), host=_HOST, port=_PORT)
        response = urllib.request.urlopen(
            'http://%s:%s/profile' % (_HOST, _PORT))
        response_data = gzip.decompress(response.read())
        stats = json.loads(response_data.decode('utf-8'))
        curr_filename = inspect.getabsfile(inspect.currentframe())
        self.assertEqual(stats['m']['objectName'],
                         '_func @ %s (function)' % curr_filename)
        self.assertEqual(stats['m']['totalEvents'], 2)
        self.assertEqual(stats['m']['codeEvents'][0][0], 1)
        self.assertEqual(stats['m']['codeEvents'][0][1], 91)
        self.assertEqual(stats['m']['codeEvents'][0][3], '_func')
        self.assertEqual(stats['m']['codeEvents'][1][0], 2)
        self.assertEqual(stats['m']['codeEvents'][1][1], 92)
        self.assertEqual(stats['m']['codeEvents'][1][3], '_func')

# pylint: enable=missing-docstring, blacklisted-name 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def read_data(self, f):
        """Retrieve (uncompressed) data from WAD file object"""

        f.seek(self.offset)
        # assume files are small enough to fit in memory
        data = f.read(self.compressed_size)
        if self.type == 0:
            return data
        elif self.type == 1:
            return gzip.decompress(data)
        elif self.type == 2:
            n, = struct.unpack('<L', data[:4])
            target = data[4:4+n].rstrip(b'\0').decode('utf-8')
            logger.debug(f"file redirection: {target}")
            return None
        elif self.type == 3:
            return zstd_decompress(data)
        raise ValueError(f"unsupported file type: {self.type}") 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def get_items_from_gzip(binary: bytes) -> Tuple[str, Dict[str, bytes]]:
    """
    Return decompressed gzip contents.

    Parameters
    ----------
    binary : bytes
        byte array of gz file

    Returns
    -------
    Tuple[str, bytes]
        File type + decompressed file

    """
    archive_file = gzip.decompress(binary)
    return "gz", {"gzip_file": archive_file} 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def main():
    # Install the library.
    os.makedirs(os.path.join(INSTALL_PATH, 'lib'), exist_ok=True)

    with open(LIBRARY_PATH, 'wb') as fd:
        fd.write(gzip.decompress(base64.b85decode(ENCODED_LIB_CONTENTS)))
        os.fchmod(fd.fileno(), 0o755)

    # Install the wrapper script.
    os.makedirs(os.path.join(INSTALL_PATH, 'bin'), exist_ok=True)

    with open(SCRIPT_PATH, 'w') as fd:
        fd.write(DROPBOX_WRAPPER_CONTENTS)
        os.fchmod(fd.fileno(), 0o755)

    print("Installed the library and the wrapper script at:\n  %s\n  %s" % (LIBRARY_PATH, SCRIPT_PATH))
    print("(To uninstall, simply delete them.)")

    # Check that the correct 'dropbox' is in the $PATH.
    result = subprocess.check_output(['which', 'dropbox']).decode().rstrip()
    if result != SCRIPT_PATH:
        print()
        print("You will need to fix your $PATH! Currently, %r takes precedence." % result) 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def getstream(file):

    # TODO -- gcs

    if file.startswith('http://') or file.startswith('https://'):
        response = requests.get(file)
        status_code = response.status_code    #TODO Do something with this

        if file.endswith('.gz'):
            content = response.content
            text = gzip.decompress(content).decode('utf-8')
        else:
            text = response.text
        f = io.StringIO(text)
        return text

    elif file.endswith('.gz'):
        f = gzip.open(file, mode='rt')

    else:
        f = open(file, encoding='UTF-8')

    return f 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def download_sifts_xml(pdb_id, outdir='', force_rerun=False):
    """Download the SIFTS file for a PDB ID.

    Args:
        pdb_id (str): PDB ID
        outdir (str): Output directory, current working directory if not specified.
        force_rerun (bool): If the file should be downloaded again even if it exists

    Returns:
        str: Path to downloaded file

    """
    baseURL = 'ftp://ftp.ebi.ac.uk/pub/databases/msd/sifts/xml/'
    filename = '{}.xml.gz'.format(pdb_id.lower())

    outfile = op.join(outdir, filename.split('.')[0] + '.sifts.xml')

    if ssbio.utils.force_rerun(flag=force_rerun, outfile=outfile):
        response = urlopen(baseURL + filename)
        with open(outfile, 'wb') as f:
            f.write(gzip.decompress(response.read()))

    return outfile 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def __iter__(self):
        keys = self._get_keys()
        if self.shuffle:
            random.shuffle(keys)
        for key in keys:
            chunk = json.loads(gzip.decompress(self.db[key]).decode('utf-8'))
            # discard long examples
            trunc_chunk = []
            lens = []
            for feat in chunk:
                if feat['input_len'] > self.max_len:
                    continue
                trunc_chunk.append(feat)
                lens.append(feat['input_len'])

            dataset = GPT2FeatureDataset(trunc_chunk, self.max_len)
            sampler = BucketSampler(lens, self.bucket_size, self.batch_size,
                                    droplast=True, shuffle=self.shuffle)
            loader = DataLoader(dataset, batch_sampler=sampler,
                                num_workers=0,  # can test multi-worker
                                collate_fn=GPT2FeatureDataset.collate)
            yield from loader 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def download(self, mirror, meta):
        """Fetches compressed JSON data from NIST.

        Nothing is done if we have already seen the same version of
        the feed before.

        Returns True if anything has been loaded successfully.
        """
        url = mirror + self.download_uri
        _log.info('Loading %s', url)
        r = requests.get(url, headers=meta.headers_for(url))
        r.raise_for_status()
        if r.status_code == 200:
            _log.debug('Loading JSON feed "%s"', self.name)
            self.parse(gzip.decompress(r.content))
            meta.update_headers_for(url, r.headers)
            return True
        else:
            _log.debug('Skipping JSON feed "%s" (%s)', self.name, r.reason)
            return False 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def raw_decode(cls, data, content_encoding=None):
        content_encoding = ContentEncoding.of(content_encoding)
        if content_encoding.is_gzip:
            try:
                data = gzip.decompress(data)
            except (ValueError, TypeError):
                raise ActorMessageDecodeError('gzip decompress failed')
        try:
            if content_encoding.is_json:
                data = json.loads(data.decode('utf-8'))
            else:
                data = msgpack.unpackb(data, raw=False)
        except json.JSONDecodeError:
            raise ActorMessageDecodeError('json decode failed')
        except msgpack.UnpackException:
            raise ActorMessageDecodeError('msgpack decode failed')
        return data 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def get_feed_content_divided_to_lines(self, url, raw_response):
        """Fetch feed data and divides its content to lines

        Args:
            url: Current feed's url.
            raw_response: The raw response from the feed's url.

        Returns:
            List. List of lines from the feed content.
        """
        if self.feed_url_to_config and self.feed_url_to_config.get(url).get('is_zipped_file'):  # type: ignore
            response_content = gzip.decompress(raw_response.content)
        else:
            response_content = raw_response.content

        return response_content.decode(self.encoding).split('\n') 

# 需要导入模块: import gzip [as 别名]
# 或者: from gzip import decompress [as 别名]
def content(self):
        if self._content:
            return self._content
        encode = self.rep.msg.get('content-encoding', None)
        try:
            body = self.rep.read()
        except socket.timeout:
            body = b''
        if encode == 'gzip':
            body = gzip.decompress(body)
        elif encode == 'deflate':
            try:
                body = zlib.decompress(body, -zlib.MAX_WBITS)
            except:
                body = zlib.decompress(body)
        # redirect = self.rep.msg.get('location', None)   # handle 301/302
        self._content = body
        return body