Python google.appengine.ext.blobstore.BlobKey() Examples

def __init__(self, blob_key, start_position, end_position):
    """Initializes this instance with the given blob key and character range.

    This BlobstoreInputReader will read from the first record starting after
    strictly after start_position until the first record ending at or after
    end_position (exclusive). As an exception, if start_position is 0, then
    this InputReader starts reading at the first record.

    Args:
      blob_key: the BlobKey that this input reader is processing.
      start_position: the position to start reading at.
      end_position: a position in the last record to read.
    """
    self._blob_key = blob_key
    self._blob_reader = blobstore.BlobReader(blob_key,
                                             self._BLOB_BUFFER_SIZE,
                                             start_position)
    self._end_position = end_position
    self._has_iterated = False
    self._read_before_start = bool(start_position) 

def validate(cls, mapper_spec):
    """Validates mapper spec and all mapper parameters.

    Args:
      mapper_spec: The MapperSpec for this InputReader.

    Raises:
      BadReaderParamsError: required parameters are missing or invalid.
    """
    if mapper_spec.input_reader_class() != cls:
      raise BadReaderParamsError("Mapper input reader class mismatch")
    params = _get_params(mapper_spec)
    if cls.BLOB_KEY_PARAM not in params:
      raise BadReaderParamsError("Must specify 'blob_key' for mapper input")
    blob_key = params[cls.BLOB_KEY_PARAM]
    blob_info = blobstore.BlobInfo.get(blobstore.BlobKey(blob_key))
    if not blob_info:
      raise BadReaderParamsError("Could not find blobinfo for key %s" %
                                 blob_key) 

def __init__(self, blob_key, start_file_index, end_file_index, offset,
               _reader=blobstore.BlobReader):
    """Initializes this instance with the given blob key and file range.

    This BlobstoreZipLineInputReader will read from the file with index
    start_file_index up to but not including the file with index end_file_index.
    It will return lines starting at offset within file[start_file_index]

    Args:
      blob_key: the BlobKey that this input reader is processing.
      start_file_index: the index of the first file to read within the zip.
      end_file_index: the index of the first file that will not be read.
      offset: the byte offset within blob_key.zip[start_file_index] to start
        reading. The reader will continue to the end of the file.
      _reader: a callable that returns a file-like object for reading blobs.
          Used for dependency injection.
    """
    self._blob_key = blob_key
    self._start_file_index = start_file_index
    self._end_file_index = end_file_index
    self._initial_offset = offset
    self._reader = _reader
    self._zip = None
    self._entries = None
    self._filestream = None 

def __init__(self, blob_key, start_index, end_index,
               _reader=blobstore.BlobReader):
    """Initializes this instance with the given blob key and file range.

    This BlobstoreZipInputReader will read from the file with index start_index
    up to but not including the file with index end_index.

    Args:
      blob_key: the BlobKey that this input reader is processing.
      start_index: the index of the first file to read.
      end_index: the index of the first file that will not be read.
      _reader: a callable that returns a file-like object for reading blobs.
          Used for dependency injection.
    """
    self._blob_key = blob_key
    self._start_index = start_index
    self._end_index = end_index
    self._reader = _reader
    self._zip = None
    self._entries = None 

def validate(cls, mapper_spec):
    """Validates mapper spec and all mapper parameters.

    Args:
      mapper_spec: The MapperSpec for this InputReader.

    Raises:
      BadReaderParamsError: required parameters are missing or invalid.
    """
    if mapper_spec.input_reader_class() != cls:
      raise BadReaderParamsError("Mapper input reader class mismatch")
    params = _get_params(mapper_spec)
    if cls.BLOB_KEY_PARAM not in params:
      raise BadReaderParamsError("Must specify 'blob_key' for mapper input")
    blob_key = params[cls.BLOB_KEY_PARAM]
    blob_info = blobstore.BlobInfo.get(blobstore.BlobKey(blob_key))
    if not blob_info:
      raise BadReaderParamsError("Could not find blobinfo for key %s" %
                                 blob_key) 

def __init__(self, blob_key, start_file_index, end_file_index, offset,
               _reader=blobstore.BlobReader):
    """Initializes this instance with the given blob key and file range.

    This BlobstoreZipLineInputReader will read from the file with index
    start_file_index up to but not including the file with index end_file_index.
    It will return lines starting at offset within file[start_file_index]

    Args:
      blob_key: the BlobKey that this input reader is processing.
      start_file_index: the index of the first file to read within the zip.
      end_file_index: the index of the first file that will not be read.
      offset: the byte offset within blob_key.zip[start_file_index] to start
        reading. The reader will continue to the end of the file.
      _reader: a callable that returns a file-like object for reading blobs.
          Used for dependency injection.
    """
    self._blob_key = blob_key
    self._start_file_index = start_file_index
    self._end_file_index = end_file_index
    self._initial_offset = offset
    self._reader = _reader
    self._zip = None
    self._entries = None
    self._filestream = None 

def __init__(self, blob_key, start_position, end_position):
    """Initializes this instance with the given blob key and character range.

    This BlobstoreInputReader will read from the first record starting after
    strictly after start_position until the first record ending at or after
    end_position (exclusive). As an exception, if start_position is 0, then
    this InputReader starts reading at the first record.

    Args:
      blob_key: the BlobKey that this input reader is processing.
      start_position: the position to start reading at.
      end_position: a position in the last record to read.
    """
    self._blob_key = blob_key
    self._blob_reader = blobstore.BlobReader(blob_key,
                                             self._BLOB_BUFFER_SIZE,
                                             start_position)
    self._end_position = end_position
    self._has_iterated = False
    self._read_before_start = bool(start_position) 

def __init__(self, blob_key, start_position, end_position):
    """Initializes this instance with the given blob key and character range.

    This BlobstoreInputReader will read from the first record starting after
    strictly after start_position until the first record ending at or after
    end_position (exclusive). As an exception, if start_position is 0, then
    this InputReader starts reading at the first record.

    Args:
      blob_key: the BlobKey that this input reader is processing.
      start_position: the position to start reading at.
      end_position: a position in the last record to read.
    """
    self._blob_key = blob_key
    self._blob_reader = blobstore.BlobReader(blob_key,
                                             self._BLOB_BUFFER_SIZE,
                                             start_position)
    self._end_position = end_position
    self._has_iterated = False
    self._read_before_start = bool(start_position) 

def __init__(self, blob_key, start_index, end_index,
               _reader=blobstore.BlobReader):
    """Initializes this instance with the given blob key and file range.

    This BlobstoreZipInputReader will read from the file with index start_index
    up to but not including the file with index end_index.

    Args:
      blob_key: the BlobKey that this input reader is processing.
      start_index: the index of the first file to read.
      end_index: the index of the first file that will not be read.
      _reader: a callable that returns a file-like object for reading blobs.
          Used for dependency injection.
    """
    self._blob_key = blob_key
    self._start_index = start_index
    self._end_index = end_index
    self._reader = _reader
    self._zip = None
    self._entries = None 

def __init__(self, blob_key, start_index, end_index,
               _reader=blobstore.BlobReader):
    """Initializes this instance with the given blob key and file range.

    This BlobstoreZipInputReader will read from the file with index start_index
    up to but not including the file with index end_index.

    Args:
      blob_key: the BlobKey that this input reader is processing.
      start_index: the index of the first file to read.
      end_index: the index of the first file that will not be read.
      _reader: a callable that returns a file-like object for reading blobs.
          Used for dependency injection.
    """
    self._blob_key = blob_key
    self._start_index = start_index
    self._end_index = end_index
    self._reader = _reader
    self._zip = None
    self._entries = None 

def validate(cls, mapper_spec):
    """Validates mapper spec and all mapper parameters.

    Args:
      mapper_spec: The MapperSpec for this InputReader.

    Raises:
      BadReaderParamsError: required parameters are missing or invalid.
    """
    if mapper_spec.input_reader_class() != cls:
      raise BadReaderParamsError("Mapper input reader class mismatch")
    params = _get_params(mapper_spec)
    if cls.BLOB_KEY_PARAM not in params:
      raise BadReaderParamsError("Must specify 'blob_key' for mapper input")
    blob_key = params[cls.BLOB_KEY_PARAM]
    blob_info = blobstore.BlobInfo.get(blobstore.BlobKey(blob_key))
    if not blob_info:
      raise BadReaderParamsError("Could not find blobinfo for key %s" %
                                 blob_key) 

def __init__(self, blob_key, start_file_index, end_file_index, offset,
               _reader=blobstore.BlobReader):
    """Initializes this instance with the given blob key and file range.

    This BlobstoreZipLineInputReader will read from the file with index
    start_file_index up to but not including the file with index end_file_index.
    It will return lines starting at offset within file[start_file_index]

    Args:
      blob_key: the BlobKey that this input reader is processing.
      start_file_index: the index of the first file to read within the zip.
      end_file_index: the index of the first file that will not be read.
      offset: the byte offset within blob_key.zip[start_file_index] to start
        reading. The reader will continue to the end of the file.
      _reader: a callable that returns a file-like object for reading blobs.
          Used for dependency injection.
    """
    self._blob_key = blob_key
    self._start_file_index = start_file_index
    self._end_file_index = end_file_index
    self._initial_offset = offset
    self._reader = _reader
    self._zip = None
    self._entries = None
    self._filestream = None 

def __init__(self, blob_key, start_file_index, end_file_index, offset,
               _reader=blobstore.BlobReader):
    """Initializes this instance with the given blob key and file range.

    This BlobstoreZipLineInputReader will read from the file with index
    start_file_index up to but not including the file with index end_file_index.
    It will return lines starting at offset within file[start_file_index]

    Args:
      blob_key: the BlobKey that this input reader is processing.
      start_file_index: the index of the first file to read within the zip.
      end_file_index: the index of the first file that will not be read.
      offset: the byte offset within blob_key.zip[start_file_index] to start
        reading. The reader will continue to the end of the file.
      _reader: a callable that returns a file-like object for reading blobs.
          Used for dependency injection.
    """
    self._blob_key = blob_key
    self._start_file_index = start_file_index
    self._end_file_index = end_file_index
    self._initial_offset = offset
    self._reader = _reader
    self._zip = None
    self._entries = None
    self._filestream = None 

def testSplitInputTwoBlobsThreeShards(self):
    """Corner case: Shards don't split nicely so we get too few."""
    readers = self.split_input(2, 3)
    # Note we might be able to make this return 3 with a more clever algorithm.
    self.assertEqual(2, len(readers))
    self.assertEqual("blobstore.BlobKey('blob0'):[0, 3]:0", str(readers[0]))
    self.assertEqual("blobstore.BlobKey('blob1'):[0, 3]:0", str(readers[1])) 

def testSplitInput(self):
    """Test that split_input functions as expected."""
    mapper_spec = model.MapperSpec.from_json({
        "mapper_handler_spec": "FooHandler",
        "mapper_input_reader": self.READER_NAME,
        "mapper_params": {"blob_key": ["foo"]},
        "mapper_shard_count": 2})
    readers = input_readers.BlobstoreZipInputReader.split_input(
        mapper_spec, self.mockZipReader)
    self.assertEqual(len(readers), 2)
    self.assertEqual(str(readers[0]), "blobstore.BlobKey(['foo']):[0, 7]")
    self.assertEqual(str(readers[1]), "blobstore.BlobKey(['foo']):[7, 10]") 

def testSplitInputThreeBlobsTwoShards(self):
    """Corner case: More blobs than requested shards."""
    readers = self.split_input(3, 2)
    self.assertEqual(3, len(readers))
    self.assertEqual("blobstore.BlobKey('blob0'):[0, 3]:0", str(readers[0]))
    self.assertEqual("blobstore.BlobKey('blob1'):[0, 3]:0", str(readers[1]))
    self.assertEqual("blobstore.BlobKey('blob2'):[0, 3]:0", str(readers[2])) 

def split_input(cls, mapper_spec):
    """Returns a list of shard_count input_spec_shards for input_spec.

    Args:
      mapper_spec: The mapper specification to split from. Must contain
          'blob_keys' parameter with one or more blob keys.

    Returns:
      A list of BlobstoreInputReaders corresponding to the specified shards.
    """
    params = _get_params(mapper_spec)
    blob_keys = params[cls.BLOB_KEYS_PARAM]
    if isinstance(blob_keys, basestring):
      # This is a mechanism to allow multiple blob keys (which do not contain
      # commas) in a single string. It may go away.
      blob_keys = blob_keys.split(",")

    blob_sizes = {}
    for blob_key in blob_keys:
      blob_info = blobstore.BlobInfo.get(blobstore.BlobKey(blob_key))
      blob_sizes[blob_key] = blob_info.size

    shard_count = min(cls._MAX_SHARD_COUNT, mapper_spec.shard_count)
    shards_per_blob = shard_count // len(blob_keys)
    if shards_per_blob == 0:
      shards_per_blob = 1

    chunks = []
    for blob_key, blob_size in blob_sizes.items():
      blob_chunk_size = blob_size // shards_per_blob
      for i in xrange(shards_per_blob - 1):
        chunks.append(BlobstoreLineInputReader.from_json(
            {cls.BLOB_KEY_PARAM: blob_key,
             cls.INITIAL_POSITION_PARAM: blob_chunk_size * i,
             cls.END_POSITION_PARAM: blob_chunk_size * (i + 1)}))
      chunks.append(BlobstoreLineInputReader.from_json(
          {cls.BLOB_KEY_PARAM: blob_key,
           cls.INITIAL_POSITION_PARAM: blob_chunk_size * (shards_per_blob - 1),
           cls.END_POSITION_PARAM: blob_size}))
    return chunks 

def testSplitInputTwoBlobsSixShards(self):
    """Corner case: Shards don't split nicely so we get too few."""
    readers = self.split_input(2, 6)
    # Note we might be able to make this return 6 with a more clever algorithm.
    self.assertEqual(4, len(readers))
    self.assertEqual("blobstore.BlobKey('blob0'):[0, 2]:0", str(readers[0]))
    self.assertEqual("blobstore.BlobKey('blob0'):[2, 3]:0", str(readers[1]))
    self.assertEqual("blobstore.BlobKey('blob1'):[0, 2]:0", str(readers[2]))
    self.assertEqual("blobstore.BlobKey('blob1'):[2, 3]:0", str(readers[3])) 

def testSplitInputTwoBlobsTwoShards(self):
    """Simple case: Ask for num shards == num blobs."""
    readers = self.split_input(2, 2)
    self.assertEqual(2, len(readers))
    self.assertEqual("blobstore.BlobKey('blob0'):[0, 3]:0", str(readers[0]))
    self.assertEqual("blobstore.BlobKey('blob1'):[0, 3]:0", str(readers[1])) 

def testSplitInputOneBlobFourShards(self):
    """Corner case: Ask for more shards than we can deliver."""
    readers = self.split_input(1, 4)
    self.assertEqual(2, len(readers))
    self.assertEqual("blobstore.BlobKey('blob0'):[0, 2]:0", str(readers[0]))
    self.assertEqual("blobstore.BlobKey('blob0'):[2, 3]:0", str(readers[1])) 

def testSplitInputOneBlob(self):
    """Simple case: split one blob into two groups."""
    readers = self.split_input(1, 2)
    self.assertEqual(2, len(readers))
    self.assertEqual("blobstore.BlobKey('blob0'):[0, 2]:0", str(readers[0]))
    self.assertEqual("blobstore.BlobKey('blob0'):[2, 3]:0", str(readers[1])) 

def test_store_and_build_forward_message_total_size_exceeded(self):
    """Test upload with all blobs larger than the total allowed size."""
    self.generate_blob_key().AndReturn(blobstore.BlobKey('item1'))

    self.now().AndReturn(datetime.datetime(2008, 11, 12, 10, 40))

    self.mox.ReplayAll()

    form = FakeForm({
        'field1': FakeForm(name='field1',
                           file=StringIO.StringIO('a'),
                           type='image/png',
                           type_options={'a': 'b', 'x': 'y'},
                           filename='stuff.png',
                           headers={'h1': 'v1',
                                    'h2': 'v2',
                                   }),
        'field2': FakeForm(name='field2',
                           file=StringIO.StringIO('longerfile'),
                           type='application/pdf',
                           type_options={},
                           filename='stuff.pdf',
                           headers={}),
        })

    self.assertRaises(webob.exc.HTTPRequestEntityTooLarge,
                      self.handler.store_and_build_forward_message,
                      form, '================1234==', max_bytes_total=3)

    self.mox.VerifyAll()

    blob1 = blobstore.get('item1')
    self.assertIsNone(blob1) 

def __str__(self):
    """Returns the string representation of this reader.

    Returns:
      string blobkey:[start file num, end file num]:current offset.
    """
    return "blobstore.BlobKey(%r):[%d, %d]:%d" % (
        self._blob_key, self._start_file_index, self._end_file_index,
        self._next_offset()) 

def validate(cls, mapper_spec):
    """Validates mapper spec and all mapper parameters.

    Args:
      mapper_spec: The MapperSpec for this InputReader.

    Raises:
      BadReaderParamsError: required parameters are missing or invalid.
    """
    if mapper_spec.input_reader_class() != cls:
      raise BadReaderParamsError("Mapper input reader class mismatch")
    params = _get_params(mapper_spec)
    if cls.BLOB_KEYS_PARAM not in params:
      raise BadReaderParamsError("Must specify 'blob_keys' for mapper input")

    blob_keys = params[cls.BLOB_KEYS_PARAM]
    if isinstance(blob_keys, basestring):


      blob_keys = blob_keys.split(",")
    if len(blob_keys) > cls._MAX_BLOB_KEYS_COUNT:
      raise BadReaderParamsError("Too many 'blob_keys' for mapper input")
    if not blob_keys:
      raise BadReaderParamsError("No 'blob_keys' specified for mapper input")
    for blob_key in blob_keys:
      blob_info = blobstore.BlobInfo.get(blobstore.BlobKey(blob_key))
      if not blob_info:
        raise BadReaderParamsError("Could not find blobinfo for key %s" %
                                   blob_key) 

def __str__(self):
    """Returns the string representation of this BlobstoreZipInputReader."""
    return "blobstore.BlobKey(%r):[%d, %d]" % (
        self._blob_key, self._start_index, self._end_index) 

def split_input(cls, mapper_spec):
    """Returns a list of shard_count input_spec_shards for input_spec.

    Args:
      mapper_spec: The mapper specification to split from. Must contain
          'blob_keys' parameter with one or more blob keys.

    Returns:
      A list of BlobstoreInputReaders corresponding to the specified shards.
    """
    params = _get_params(mapper_spec)
    blob_keys = params[cls.BLOB_KEYS_PARAM]
    if isinstance(blob_keys, basestring):


      blob_keys = blob_keys.split(",")

    blob_sizes = {}
    for blob_key in blob_keys:
      blob_info = blobstore.BlobInfo.get(blobstore.BlobKey(blob_key))
      blob_sizes[blob_key] = blob_info.size

    shard_count = min(cls._MAX_SHARD_COUNT, mapper_spec.shard_count)
    shards_per_blob = shard_count // len(blob_keys)
    if shards_per_blob == 0:
      shards_per_blob = 1

    chunks = []
    for blob_key, blob_size in blob_sizes.items():
      blob_chunk_size = blob_size // shards_per_blob
      for i in xrange(shards_per_blob - 1):
        chunks.append(BlobstoreLineInputReader.from_json(
            {cls.BLOB_KEY_PARAM: blob_key,
             cls.INITIAL_POSITION_PARAM: blob_chunk_size * i,
             cls.END_POSITION_PARAM: blob_chunk_size * (i + 1)}))
      chunks.append(BlobstoreLineInputReader.from_json(
          {cls.BLOB_KEY_PARAM: blob_key,
           cls.INITIAL_POSITION_PARAM: blob_chunk_size * (shards_per_blob - 1),
           cls.END_POSITION_PARAM: blob_size}))
    return chunks 

def validate(cls, mapper_spec):
    """Validates mapper spec and all mapper parameters.

    Args:
      mapper_spec: The MapperSpec for this InputReader.

    Raises:
      BadReaderParamsError: required parameters are missing or invalid.
    """
    if mapper_spec.input_reader_class() != cls:
      raise BadReaderParamsError("Mapper input reader class mismatch")
    params = _get_params(mapper_spec)
    if cls.BLOB_KEYS_PARAM not in params:
      raise BadReaderParamsError("Must specify 'blob_keys' for mapper input")
    blob_keys = params[cls.BLOB_KEYS_PARAM]
    if isinstance(blob_keys, basestring):


      blob_keys = blob_keys.split(",")
    if len(blob_keys) > cls._MAX_BLOB_KEYS_COUNT:
      raise BadReaderParamsError("Too many 'blob_keys' for mapper input")
    if not blob_keys:
      raise BadReaderParamsError("No 'blob_keys' specified for mapper input")
    for blob_key in blob_keys:
      blob_info = blobstore.BlobInfo.get(blobstore.BlobKey(blob_key))
      if not blob_info:
        raise BadReaderParamsError("Could not find blobinfo for key %s" %
                                   blob_key) 

def __str__(self):
    """Returns the string representation of this BlobstoreLineInputReader."""
    return "blobstore.BlobKey(%r):[%d, %d]" % (
        self._blob_key, self._blob_reader.tell(), self._end_position) 

def get_blob_key(fname):
  return blobstore.BlobKey(_MaybeStripBlobstorePrefix(fname)) 

def test_store_and_build_forward_message_utf8_values(self):
    """Test store and build message method with UTF-8 values."""
    self.generate_blob_key().AndReturn(blobstore.BlobKey('item1'))

    self.now().AndReturn(datetime.datetime(2008, 11, 12, 10, 40))

    self.mox.ReplayAll()

    form = FakeForm({
        'field1': FakeForm(name='field1',
                           file=StringIO.StringIO('file1'),
                           type='text/plain',
                           type_options={'a': 'b', 'x': 'y'},
                           filename='chinese_char_name_\xe6\xb1\x89.txt',
                           headers={'h1': 'v1',
                                    'h2': 'v2',
                                   }),
        })

    content_type, content_text = self.handler.store_and_build_forward_message(
        form, '================1234==')

    self.mox.VerifyAll()

    self.assertEqual(EXPECTED_GENERATED_UTF8_CONTENT_TYPE, content_type)
    self.assertMessageEqual(EXPECTED_GENERATED_UTF8_MIME_MESSAGE,
                            content_text)

    blob1 = blobstore.get('item1')
    self.assertEquals(u'chinese_char_name_\u6c49.txt', blob1.filename)