Python future.builtins.range() Examples

def test_escape_path(self):
        cases = [
            # quoted safe
            ("/foo%2f/bar", "/foo%2F/bar"),
            ("/foo%2F/bar", "/foo%2F/bar"),
            # quoted %
            ("/foo%%/bar", "/foo%%/bar"),
            # quoted unsafe
            ("/fo%19o/bar", "/fo%19o/bar"),
            ("/fo%7do/bar", "/fo%7Do/bar"),
            # unquoted safe
            ("/foo/bar&", "/foo/bar&"),
            ("/foo//bar", "/foo//bar"),
            ("\176/foo/bar", "\176/foo/bar"),
            # unquoted unsafe
            ("/foo\031/bar", "/foo%19/bar"),
            ("/\175foo/bar", "/%7Dfoo/bar"),
            # unicode, latin-1 range
            ("/foo/bar\u00fc", "/foo/bar%C3%BC"),     # UTF-8 encoded
            # unicode
            ("/foo/bar\uabcd", "/foo/bar%EA%AF%8D"),  # UTF-8 encoded
            ]
        for arg, result in cases:
            self.assertEqual(escape_path(arg), result) 

def body_encode(s, maxlinelen=76, eol=NL):
    r"""Encode a string with base64.

    Each line will be wrapped at, at most, maxlinelen characters (defaults to
    76 characters).

    Each line of encoded text will end with eol, which defaults to "\n".  Set
    this to "\r\n" if you will be using the result of this function directly
    in an email.
    """
    if not s:
        return s

    encvec = []
    max_unencoded = maxlinelen * 3 // 4
    for i in range(0, len(s), max_unencoded):
        # BAW: should encode() inherit b2a_base64()'s dubious behavior in
        # adding a newline to the encoded string?
        enc = b2a_base64(s[i:i + max_unencoded]).decode("ascii")
        if enc.endswith(NL) and eol != NL:
            enc = enc[:-1] + eol
        encvec.append(enc)
    return EMPTYSTRING.join(encvec) 

def unquote(string, encoding='utf-8', errors='replace'):
    """Replace %xx escapes by their single-character equivalent. The optional
    encoding and errors parameters specify how to decode percent-encoded
    sequences into Unicode characters, as accepted by the bytes.decode()
    method.
    By default, percent-encoded sequences are decoded with UTF-8, and invalid
    sequences are replaced by a placeholder character.

    unquote('abc%20def') -> 'abc def'.
    """
    if '%' not in string:
        string.split
        return string
    if encoding is None:
        encoding = 'utf-8'
    if errors is None:
        errors = 'replace'
    bits = _asciire.split(string)
    res = [bits[0]]
    append = res.append
    for i in range(1, len(bits), 2):
        append(unquote_to_bytes(bits[i]).decode(encoding, errors))
        append(bits[i + 1])
    return ''.join(res) 

def push(self, data):
        """Push some new data into this object."""
        # Handle any previous leftovers
        data, self._partial = self._partial + data, ''
        # Crack into lines, but preserve the newlines on the end of each
        parts = NLCRE_crack.split(data)
        # The *ahem* interesting behaviour of re.split when supplied grouping
        # parentheses is that the last element of the resulting list is the
        # data after the final RE.  In the case of a NL/CR terminated string,
        # this is the empty string.
        self._partial = parts.pop()
        #GAN 29Mar09  bugs 1555570, 1721862  Confusion at 8K boundary ending with \r:
        # is there a \n to follow later?
        if not self._partial and parts and parts[-1].endswith('\r'):
            self._partial = parts.pop(-2)+parts.pop()
        # parts is a list of strings, alternating between the line contents
        # and the eol character(s).  Gather up a list of lines after
        # re-attaching the newlines.
        lines = []
        for i in range(len(parts) // 2):
            lines.append(parts[i*2] + parts[i*2+1])
        self.pushlines(lines) 

def body_encode(s, maxlinelen=76, eol=NL):
    r"""Encode a string with base64.

    Each line will be wrapped at, at most, maxlinelen characters (defaults to
    76 characters).

    Each line of encoded text will end with eol, which defaults to "\n".  Set
    this to "\r\n" if you will be using the result of this function directly
    in an email.
    """
    if not s:
        return s

    encvec = []
    max_unencoded = maxlinelen * 3 // 4
    for i in range(0, len(s), max_unencoded):
        # BAW: should encode() inherit b2a_base64()'s dubious behavior in
        # adding a newline to the encoded string?
        enc = b2a_base64(s[i:i + max_unencoded]).decode("ascii")
        if enc.endswith(NL) and eol != NL:
            enc = enc[:-1] + eol
        encvec.append(enc)
    return EMPTYSTRING.join(encvec) 

def push(self, data):
        """Push some new data into this object."""
        # Handle any previous leftovers
        data, self._partial = self._partial + data, ''
        # Crack into lines, but preserve the newlines on the end of each
        parts = NLCRE_crack.split(data)
        # The *ahem* interesting behaviour of re.split when supplied grouping
        # parentheses is that the last element of the resulting list is the
        # data after the final RE.  In the case of a NL/CR terminated string,
        # this is the empty string.
        self._partial = parts.pop()
        #GAN 29Mar09  bugs 1555570, 1721862  Confusion at 8K boundary ending with \r:
        # is there a \n to follow later?
        if not self._partial and parts and parts[-1].endswith('\r'):
            self._partial = parts.pop(-2)+parts.pop()
        # parts is a list of strings, alternating between the line contents
        # and the eol character(s).  Gather up a list of lines after
        # re-attaching the newlines.
        lines = []
        for i in range(len(parts) // 2):
            lines.append(parts[i*2] + parts[i*2+1])
        self.pushlines(lines) 

def unquote(string, encoding='utf-8', errors='replace'):
    """Replace %xx escapes by their single-character equivalent. The optional
    encoding and errors parameters specify how to decode percent-encoded
    sequences into Unicode characters, as accepted by the bytes.decode()
    method.
    By default, percent-encoded sequences are decoded with UTF-8, and invalid
    sequences are replaced by a placeholder character.

    unquote('abc%20def') -> 'abc def'.
    """
    if '%' not in string:
        string.split
        return string
    if encoding is None:
        encoding = 'utf-8'
    if errors is None:
        errors = 'replace'
    bits = _asciire.split(string)
    res = [bits[0]]
    append = res.append
    for i in range(1, len(bits), 2):
        append(unquote_to_bytes(bits[i]).decode(encoding, errors))
        append(bits[i + 1])
    return ''.join(res) 

def replace_header(self, _name, _value):
        """Replace a header.

        Replace the first matching header found in the message, retaining
        header order and case.  If no matching header was found, a KeyError is
        raised.
        """
        _name = _name.lower()
        for i, (k, v) in zip(range(len(self._headers)), self._headers):
            if k.lower() == _name:
                self._headers[i] = self.policy.header_store_parse(k, _value)
                break
        else:
            raise KeyError(_name)

    #
    # Use these three methods instead of the three above.
    # 

def replace_header(self, _name, _value):
        """Replace a header.

        Replace the first matching header found in the message, retaining
        header order and case.  If no matching header was found, a KeyError is
        raised.
        """
        _name = _name.lower()
        for i, (k, v) in zip(range(len(self._headers)), self._headers):
            if k.lower() == _name:
                self._headers[i] = self.policy.header_store_parse(k, _value)
                break
        else:
            raise KeyError(_name)

    #
    # Use these three methods instead of the three above.
    # 

def body_encode(s, maxlinelen=76, eol=NL):
    r"""Encode a string with base64.

    Each line will be wrapped at, at most, maxlinelen characters (defaults to
    76 characters).

    Each line of encoded text will end with eol, which defaults to "\n".  Set
    this to "\r\n" if you will be using the result of this function directly
    in an email.
    """
    if not s:
        return s

    encvec = []
    max_unencoded = maxlinelen * 3 // 4
    for i in range(0, len(s), max_unencoded):
        # BAW: should encode() inherit b2a_base64()'s dubious behavior in
        # adding a newline to the encoded string?
        enc = b2a_base64(s[i:i + max_unencoded]).decode("ascii")
        if enc.endswith(NL) and eol != NL:
            enc = enc[:-1] + eol
        encvec.append(enc)
    return EMPTYSTRING.join(encvec) 

def unquote(string, encoding='utf-8', errors='replace'):
    """Replace %xx escapes by their single-character equivalent. The optional
    encoding and errors parameters specify how to decode percent-encoded
    sequences into Unicode characters, as accepted by the bytes.decode()
    method.
    By default, percent-encoded sequences are decoded with UTF-8, and invalid
    sequences are replaced by a placeholder character.

    unquote('abc%20def') -> 'abc def'.
    """
    if '%' not in string:
        string.split
        return string
    if encoding is None:
        encoding = 'utf-8'
    if errors is None:
        errors = 'replace'
    bits = _asciire.split(string)
    res = [bits[0]]
    append = res.append
    for i in range(1, len(bits), 2):
        append(unquote_to_bytes(bits[i]).decode(encoding, errors))
        append(bits[i + 1])
    return ''.join(res) 

def run_pipeline():
    for label, subdir in [(VAL_SPLIT, 'SeqVal'), (TRAIN_SPLIT, 'SeqTrain')]:

        # get list of h5 files to preprocess
        h5_files = get_files(subdir, data_dir=FLAGS.data_dir, num_files=FLAGS.h5_files_per_split)
        random.shuffle(h5_files)

        for index in range(0, len(h5_files), BATCHSIZE):

            output_filename = '{}-{:05d}.tfrecord.gz'.format(label, index / BATCHSIZE)
            output_filepath = os.path.join(FLAGS.preproc_output_dir, output_filename)

            upper_index = min(index + BATCHSIZE, len(h5_files))
            some_h5_files = h5_files[index:upper_index]

            write_tfrecord_file(output_filepath, some_h5_files) 

def _bulker(self, bulk_size):
        """
        Example:
            u = bulker()
            u.send(None)  #for generator initialize
            u.send(json_str)  # input json item
            u.send(another_json_str)  # input json item
            ...
            u.send(None) force finish bulk and post
        """
        while True:
            data = ""
            for i in range(bulk_size):
                item = yield
                if item:
                    data = data + item + "\n"
                else:
                    break
            # print(data)
            print('-'*10)
            if data:
                self._post_to_es(data) 

def body_encode(s, maxlinelen=76, eol=NL):
    r"""Encode a string with base64.

    Each line will be wrapped at, at most, maxlinelen characters (defaults to
    76 characters).

    Each line of encoded text will end with eol, which defaults to "\n".  Set
    this to "\r\n" if you will be using the result of this function directly
    in an email.
    """
    if not s:
        return s

    encvec = []
    max_unencoded = maxlinelen * 3 // 4
    for i in range(0, len(s), max_unencoded):
        # BAW: should encode() inherit b2a_base64()'s dubious behavior in
        # adding a newline to the encoded string?
        enc = b2a_base64(s[i:i + max_unencoded]).decode("ascii")
        if enc.endswith(NL) and eol != NL:
            enc = enc[:-1] + eol
        encvec.append(enc)
    return EMPTYSTRING.join(encvec) 

def push(self, data):
        """Push some new data into this object."""
        # Handle any previous leftovers
        data, self._partial = self._partial + data, ''
        # Crack into lines, but preserve the newlines on the end of each
        parts = NLCRE_crack.split(data)
        # The *ahem* interesting behaviour of re.split when supplied grouping
        # parentheses is that the last element of the resulting list is the
        # data after the final RE.  In the case of a NL/CR terminated string,
        # this is the empty string.
        self._partial = parts.pop()
        #GAN 29Mar09  bugs 1555570, 1721862  Confusion at 8K boundary ending with \r:
        # is there a \n to follow later?
        if not self._partial and parts and parts[-1].endswith('\r'):
            self._partial = parts.pop(-2)+parts.pop()
        # parts is a list of strings, alternating between the line contents
        # and the eol character(s).  Gather up a list of lines after
        # re-attaching the newlines.
        lines = []
        for i in range(len(parts) // 2):
            lines.append(parts[i*2] + parts[i*2+1])
        self.pushlines(lines) 

def replace_header(self, _name, _value):
        """Replace a header.

        Replace the first matching header found in the message, retaining
        header order and case.  If no matching header was found, a KeyError is
        raised.
        """
        _name = _name.lower()
        for i, (k, v) in zip(range(len(self._headers)), self._headers):
            if k.lower() == _name:
                self._headers[i] = self.policy.header_store_parse(k, _value)
                break
        else:
            raise KeyError(_name)

    #
    # Use these three methods instead of the three above.
    # 

def unquote(string, encoding='utf-8', errors='replace'):
    """Replace %xx escapes by their single-character equivalent. The optional
    encoding and errors parameters specify how to decode percent-encoded
    sequences into Unicode characters, as accepted by the bytes.decode()
    method.
    By default, percent-encoded sequences are decoded with UTF-8, and invalid
    sequences are replaced by a placeholder character.

    unquote('abc%20def') -> 'abc def'.
    """
    if '%' not in string:
        string.split
        return string
    if encoding is None:
        encoding = 'utf-8'
    if errors is None:
        errors = 'replace'
    bits = _asciire.split(string)
    res = [bits[0]]
    append = res.append
    for i in range(1, len(bits), 2):
        append(unquote_to_bytes(bits[i]).decode(encoding, errors))
        append(bits[i + 1])
    return ''.join(res) 

def contains(self, other):
        if isinstance(other, self.__class__):
            if self.is_full() or other.is_empty():
                return True
            return (self.angle().radians >=
                    self.axis().angle(other.axis()) + other.angle().radians)
        elif isinstance(other, Point):
            assert is_unit_length(other)
            return (self.axis() - other).norm2() <= 2 * self.height()
        elif isinstance(other, Cell):
            vertices = []
            for k in range(4):
                vertices.append(other.get_vertex(k))
                if not self.contains(vertices[k]):
                    return False
            return not self.complement().intersects(other, vertices)
        else:
            raise NotImplementedError() 

def _init_lookup_cell(level, i, j, orig_orientation, pos, orientation):
    if level == LOOKUP_BITS:
        ij = (i << LOOKUP_BITS) + j
        LOOKUP_POS[(ij << 2) + orig_orientation] = (pos << 2) + orientation
        LOOKUP_IJ[(pos << 2) + orig_orientation] = (ij << 2) + orientation
    else:
        level = level + 1
        i <<= 1
        j <<= 1
        pos <<= 2
        r = POS_TO_IJ[orientation]
        for index in range(4):
            _init_lookup_cell(
                level, i + (r[index] >> 1),
                j + (r[index] & 1), orig_orientation,
                pos + index, orientation ^ POS_TO_ORIENTATION[index],
            ) 

def contains(self, *args):
        if len(args) == 1 and isinstance(args[0], Cell):
            return self.contains(args[0].id())
        elif len(args) == 1 and isinstance(args[0], CellId):
            cell_id = args[0]
            index = bisect.bisect_left(self.__cell_ids, cell_id)
            if index < len(self.__cell_ids) \
                    and self.__cell_ids[index].range_min() <= cell_id:
                return True
            return (index != 0 and
                    self.__cell_ids[index - 1].range_max() >= cell_id)
        elif len(args) == 1 and isinstance(args[0], Point):
            return self.contains(CellId.from_point(args[0]))
        elif len(args) == 1 and isinstance(args[0], self.__class__):
            cell_union = args[0]
            for i in range(cell_union.num_cells()):
                if not self.contains(cell_union.cell_id(i)):
                    return False
            return True
        else:
            raise NotImplementedError() 

def __get_initial_candidates(self):
        if self.__max_cells >= 4:
            cap = self.__region.get_cap_bound()
            level = min(CellId.min_width().get_max_level(
                        2 * cap.angle().radians),
                        min(self.__max_level, CellId.MAX_LEVEL - 1))

            if self.__level_mod > 1 and level > self.__min_level:
                level -= (level - self.__min_level) % self.__level_mod

            if level > 0:
                cell_id = CellId.from_point(cap.axis())
                vertex_neighbors = cell_id.get_vertex_neighbors(level)
                for neighbor in vertex_neighbors:
                    self.__add_candidate(self.__new_candidate(Cell(neighbor)))
                return

        for face in range(6):
            self.__add_candidate(self.__new_candidate(FACE_CELLS[face])) 

def download(self):
        logger.info('Starting to download doujinshi: %s' % self.name)
        if self.downloader:
            download_queue = []

            if len(self.ext) != self.pages:
                logger.warning('Page count and ext count do not equal')

            for i in range(1, min(self.pages, len(self.ext)) + 1):
                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i, self.ext[i-1]))

            self.downloader.download(download_queue, self.filename)

            '''
            for i in range(len(self.ext)):
                download_queue.append('%s/%d/%d.%s' % (IMAGE_URL, int(self.img_id), i+1, EXT_MAP[self.ext[i]]))
            '''

        else:
            logger.critical('Downloader has not been loaded') 

def body_encode(s, maxlinelen=76, eol=NL):
    r"""Encode a string with base64.

    Each line will be wrapped at, at most, maxlinelen characters (defaults to
    76 characters).

    Each line of encoded text will end with eol, which defaults to "\n".  Set
    this to "\r\n" if you will be using the result of this function directly
    in an email.
    """
    if not s:
        return s

    encvec = []
    max_unencoded = maxlinelen * 3 // 4
    for i in range(0, len(s), max_unencoded):
        # BAW: should encode() inherit b2a_base64()'s dubious behavior in
        # adding a newline to the encoded string?
        enc = b2a_base64(s[i:i + max_unencoded]).decode("ascii")
        if enc.endswith(NL) and eol != NL:
            enc = enc[:-1] + eol
        encvec.append(enc)
    return EMPTYSTRING.join(encvec) 

def push(self, data):
        """Push some new data into this object."""
        # Handle any previous leftovers
        data, self._partial = self._partial + data, ''
        # Crack into lines, but preserve the newlines on the end of each
        parts = NLCRE_crack.split(data)
        # The *ahem* interesting behaviour of re.split when supplied grouping
        # parentheses is that the last element of the resulting list is the
        # data after the final RE.  In the case of a NL/CR terminated string,
        # this is the empty string.
        self._partial = parts.pop()
        #GAN 29Mar09  bugs 1555570, 1721862  Confusion at 8K boundary ending with \r:
        # is there a \n to follow later?
        if not self._partial and parts and parts[-1].endswith('\r'):
            self._partial = parts.pop(-2)+parts.pop()
        # parts is a list of strings, alternating between the line contents
        # and the eol character(s).  Gather up a list of lines after
        # re-attaching the newlines.
        lines = []
        for i in range(len(parts) // 2):
            lines.append(parts[i*2] + parts[i*2+1])
        self.pushlines(lines) 

def replace_header(self, _name, _value):
        """Replace a header.

        Replace the first matching header found in the message, retaining
        header order and case.  If no matching header was found, a KeyError is
        raised.
        """
        _name = _name.lower()
        for i, (k, v) in zip(range(len(self._headers)), self._headers):
            if k.lower() == _name:
                self._headers[i] = self.policy.header_store_parse(k, _value)
                break
        else:
            raise KeyError(_name)

    #
    # Use these three methods instead of the three above.
    # 

def unquote(string, encoding='utf-8', errors='replace'):
    """Replace %xx escapes by their single-character equivalent. The optional
    encoding and errors parameters specify how to decode percent-encoded
    sequences into Unicode characters, as accepted by the bytes.decode()
    method.
    By default, percent-encoded sequences are decoded with UTF-8, and invalid
    sequences are replaced by a placeholder character.

    unquote('abc%20def') -> 'abc def'.
    """
    if '%' not in string:
        string.split
        return string
    if encoding is None:
        encoding = 'utf-8'
    if errors is None:
        errors = 'replace'
    bits = _asciire.split(string)
    res = [bits[0]]
    append = res.append
    for i in range(1, len(bits), 2):
        append(unquote_to_bytes(bits[i]).decode(encoding, errors))
        append(bits[i + 1])
    return ''.join(res) 

def test_slice_range(self):
        r = range(8)
        self.assertEqual(r[:], range(8))
        self.assertEqual(r[:2], range(2))
        self.assertEqual(r[:-2], range(6))
        self.assertEqual(r[2:], range(2, 8))
        self.assertEqual(r[-2:], range(6, 8))
        self.assertEqual(r[2:-2], range(2, 6))
        self.assertEqual(r[-2:2:-1], range(6, 2, -1))
        r = r[::-1]
        self.assertEqual(r, range(7, -1, -1))
        self.assertEqual(r[:], range(7, -1, -1))
        self.assertEqual(r[:2], range(7, 5, -1))
        self.assertEqual(r[:-2], range(7, 1, -1))
        self.assertEqual(r[2:], range(5, -1, -1))
        self.assertEqual(r[-2:], range(1, -1, -1))
        self.assertEqual(r[2:-2], range(5, 1, -1))
        self.assertEqual(r[-2:2:-1], range(1, 5)) 

def test_unquoting(self):
        # Make sure unquoting of all ASCII values works
        escape_list = []
        for num in range(128):
            given = hexescape(chr(num))
            expect = chr(num)
            result = urllib_parse.unquote(given)
            self.assertEqual(expect, result,
                             "using unquote(): %r != %r" % (expect, result))
            result = urllib_parse.unquote_plus(given)
            self.assertEqual(expect, result,
                             "using unquote_plus(): %r != %r" %
                             (expect, result))
            escape_list.append(given)
        escape_string = ''.join(escape_list)
        del escape_list
        result = urllib_parse.unquote(escape_string)
        self.assertEqual(result.count('%'), 1,
                         "using unquote(): not all characters escaped: "
                         "%s" % result)
        self.assertRaises((TypeError, AttributeError), urllib_parse.unquote, None)
        self.assertRaises((TypeError, AttributeError), urllib_parse.unquote, ())
        with support.check_warnings(('', BytesWarning), quiet=True):
            self.assertRaises((TypeError, AttributeError), urllib_parse.unquote, bytes(b'')) 

def push(self, data):
        """Push some new data into this object."""
        # Handle any previous leftovers
        data, self._partial = self._partial + data, ''
        # Crack into lines, but preserve the newlines on the end of each
        parts = NLCRE_crack.split(data)
        # The *ahem* interesting behaviour of re.split when supplied grouping
        # parentheses is that the last element of the resulting list is the
        # data after the final RE.  In the case of a NL/CR terminated string,
        # this is the empty string.
        self._partial = parts.pop()
        #GAN 29Mar09  bugs 1555570, 1721862  Confusion at 8K boundary ending with \r:
        # is there a \n to follow later?
        if not self._partial and parts and parts[-1].endswith('\r'):
            self._partial = parts.pop(-2)+parts.pop()
        # parts is a list of strings, alternating between the line contents
        # and the eol character(s).  Gather up a list of lines after
        # re-attaching the newlines.
        lines = []
        for i in range(len(parts) // 2):
            lines.append(parts[i*2] + parts[i*2+1])
        self.pushlines(lines) 

def modules_cleanup(oldmodules):
    # Encoders/decoders are registered permanently within the internal
    # codec cache. If we destroy the corresponding modules their
    # globals will be set to None which will trip up the cached functions.
    encodings = [(k, v) for k, v in sys.modules.items()
                 if k.startswith('encodings.')]
    # Was:
    # sys.modules.clear()
    # Py2-compatible:
    for i in range(len(sys.modules)):
        sys.modules.pop()

    sys.modules.update(encodings)
    # XXX: This kind of problem can affect more than just encodings. In particular
    # extension modules (such as _ssl) don't cope with reloading properly.
    # Really, test modules should be cleaning out the test specific modules they
    # know they added (ala test_runpy) rather than relying on this function (as
    # test_importhooks and test_pkg do currently).
    # Implicitly imported *real* modules should be left alone (see issue 10556).
    sys.modules.update(oldmodules)

#=======================================================================
# Backported versions of threading_setup() and threading_cleanup() which don't refer
# to threading._dangling (not available on Py2.7).

# Threading support to prevent reporting refleaks when running regrtest.py -R

# NOTE: we use thread._count() rather than threading.enumerate() (or the
# moral equivalent thereof) because a threading.Thread object is still alive
# until its __bootstrap() method has returned, even after it has been
# unregistered from the threading module.
# thread._count(), on the other hand, only gets decremented *after* the
# __bootstrap() method has returned, which gives us reliable reference counts
# at the end of a test run.