Python string_ops.substr函数代码示例

  def testMismatchPosLenShapes(self, dtype, unit):
    test_string = {
        "BYTE": [[b"ten", b"eleven", b"twelve"],
                 [b"thirteen", b"fourteen", b"fifteen"],
                 [b"sixteen", b"seventeen", b"eighteen"]],
        "UTF8_CHAR": [[x.encode("utf-8") for x in [u"\U0001d229\U0001d227n",
                                                   u"\xc6\u053c\u025bv\u025bn",
                                                   u"tw\u0c1dlv\u025b"]],
                      [x.encode("utf-8") for x in [u"th\xcdrt\xea\xean",
                                                   u"f\U0001f604urt\xea\xean",
                                                   u"f\xcd\ua09ctee\ua0e4"]],
                      [x.encode("utf-8") for x in [u"s\xcdxt\xea\xean",
                                                   u"se\U00010299enteen",
                                                   u"ei\U0001e920h\x86een"]]],
    }[unit]
    position = np.array([[1, 2, 3]], dtype)
    length = np.array([2, 3, 4], dtype)
    # Should fail: position/length have different rank
    with self.assertRaises(ValueError):
      string_ops.substr(test_string, position, length)

    position = np.array([[1, 2, 3], [1, 2, 3], [1, 2, 3]], dtype)
    length = np.array([[2, 3, 4]], dtype)
    # Should fail: position/length have different dimensionality
    with self.assertRaises(ValueError):
      string_ops.substr(test_string, position, length)

  def testOutOfRangeError_MatrixMatrix(self, dtype, unit):
    # Matrix/Matrix
    test_string = {
        "BYTE": [[b"good", b"good", b"good"], [b"good", b"good", b"bad"],
                 [b"good", b"good", b"good"]],
        "UTF8_CHAR": [[x.encode("utf-8") for x in [u"g\xc3\xc3d", u"g\xc3\xc3d",
                                                   u"g\xc3\xc3d"]],
                      [x.encode("utf-8") for x in [u"g\xc3\xc3d", u"g\xc3\xc3d",
                                                   u"b\xc3d"]],
                      [x.encode("utf-8") for x in [u"g\xc3\xc3d", u"g\xc3\xc3d",
                                                   u"g\xc3\xc3d"]]],
    }[unit]
    position = np.array([[1, 2, 3], [1, 2, 4], [1, 2, 3]], dtype)
    length = np.array([[3, 2, 1], [1, 2, 3], [2, 2, 2]], dtype)
    substr_op = string_ops.substr(test_string, position, length, unit=unit)
    with self.cached_session():
      with self.assertRaises(errors_impl.InvalidArgumentError):
        substr_op.eval()

    # Matrix/Matrix (with negative)
    position = np.array([[1, 2, -3], [1, 2, -4], [1, 2, -3]], dtype)
    length = np.array([[3, 2, 1], [1, 2, 3], [2, 2, 2]], dtype)
    substr_op = string_ops.substr(test_string, position, length, unit=unit)
    with self.cached_session():
      with self.assertRaises(errors_impl.InvalidArgumentError):
        substr_op.eval()

  def _testBroadcast(self, dtype):
    # Broadcast pos/len onto input string
    test_string = [[b"ten", b"eleven", b"twelve"],
                   [b"thirteen", b"fourteen", b"fifteen"],
                   [b"sixteen", b"seventeen", b"eighteen"],
                   [b"nineteen", b"twenty", b"twentyone"]]
    position = np.array([1, 2, 3], dtype)
    length = np.array([1, 2, 3], dtype)
    expected_value = [[b"e", b"ev", b"lve"], [b"h", b"ur", b"tee"],
                      [b"i", b"ve", b"hte"], [b"i", b"en", b"nty"]]
    substr_op = string_ops.substr(test_string, position, length)
    with self.test_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, expected_value)

    # Broadcast input string onto pos/len
    test_string = [b"thirteen", b"fourteen", b"fifteen"]
    position = np.array([[1, 2, 3], [3, 2, 1], [5, 5, 5]], dtype)
    length = np.array([[3, 2, 1], [1, 2, 3], [2, 2, 2]], dtype)
    expected_value = [[b"hir", b"ur", b"t"], [b"r", b"ur", b"ift"],
                      [b"ee", b"ee", b"en"]]
    substr_op = string_ops.substr(test_string, position, length)
    with self.test_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, expected_value)

    # Test 1D broadcast
    test_string = b"thirteen"
    position = np.array([1, 5, 7], dtype)
    length = np.array([3, 2, 1], dtype)
    expected_value = [b"hir", b"ee", b"n"]
    substr_op = string_ops.substr(test_string, position, length)
    with self.test_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, expected_value)

 def testBadBroadcast(self, dtype, unit):
   test_string = [[b"ten", b"eleven", b"twelve"],
                  [b"thirteen", b"fourteen", b"fifteen"],
                  [b"sixteen", b"seventeen", b"eighteen"]]
   position = np.array([1, 2, -3, 4], dtype)
   length = np.array([1, 2, 3, 4], dtype)
   with self.assertRaises(ValueError):
     string_ops.substr(test_string, position, length, unit=unit)

  def testScalarString_EdgeCases(self, dtype, unit):
    # Empty string
    test_string = {
        "BYTE": b"",
        "UTF8_CHAR": u"".encode("utf-8"),
    }[unit]
    expected_value = b""
    position = np.array(0, dtype)
    length = np.array(3, dtype)
    substr_op = string_ops.substr(test_string, position, length, unit=unit)
    with self.cached_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, expected_value)

    # Full string
    test_string = {
        "BYTE": b"Hello",
        "UTF8_CHAR": u"H\xc3ll\U0001f604".encode("utf-8"),
    }[unit]
    position = np.array(0, dtype)
    length = np.array(5, dtype)
    substr_op = string_ops.substr(test_string, position, length, unit=unit)
    with self.cached_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, test_string)

    # Full string (Negative)
    test_string = {
        "BYTE": b"Hello",
        "UTF8_CHAR": u"H\xc3ll\U0001f604".encode("utf-8"),
    }[unit]
    position = np.array(-5, dtype)
    length = np.array(5, dtype)
    substr_op = string_ops.substr(test_string, position, length, unit=unit)
    with self.cached_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, test_string)

    # Length is larger in magnitude than a negative position
    test_string = {
        "BYTE": b"Hello",
        "UTF8_CHAR": u"H\xc3ll\U0001f604".encode("utf-8"),
    }[unit]
    expected_string = {
        "BYTE": b"ello",
        "UTF8_CHAR": u"\xc3ll\U0001f604".encode("utf-8"),
    }[unit]
    position = np.array(-4, dtype)
    length = np.array(5, dtype)
    substr_op = string_ops.substr(test_string, position, length, unit=unit)
    with self.cached_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, expected_string)

  def _testMismatchPosLenShapes(self, dtype):
    test_string = [[b"ten", b"eleven", b"twelve"],
                   [b"thirteen", b"fourteen", b"fifteen"],
                   [b"sixteen", b"seventeen", b"eighteen"]]
    position = np.array([[1, 2, 3]], dtype)
    length = np.array([2, 3, 4], dtype)
    # Should fail: position/length have different rank
    with self.assertRaises(ValueError):
      substr_op = string_ops.substr(test_string, position, length)

    position = np.array([[1, 2, 3], [1, 2, 3], [1, 2, 3]], dtype)
    length = np.array([[2, 3, 4]], dtype)
    # Should fail: postion/length have different dimensionality
    with self.assertRaises(ValueError):
      substr_op = string_ops.substr(test_string, position, length)

  def _read_test(self, batch_size, num_epochs, file_index=None,
                 num_parallel_reads=1, drop_final_batch=False, parser_fn=False):
    if file_index is None:
      file_pattern = self.test_filenames
    else:
      file_pattern = self.test_filenames[file_index]

    if parser_fn:
      fn = lambda x: string_ops.substr(x, 1, 999)
    else:
      fn = None

    with ops.Graph().as_default() as g:
      with self.session(graph=g) as sess:
        outputs = readers.make_tf_record_dataset(
            file_pattern=file_pattern,
            num_epochs=num_epochs,
            batch_size=batch_size,
            parser_fn=fn,
            num_parallel_reads=num_parallel_reads,
            drop_final_batch=drop_final_batch,
            shuffle=False).make_one_shot_iterator().get_next()
        self._verify_records(
            sess, outputs, batch_size, file_index, num_epochs=num_epochs,
            interleave_cycle_length=num_parallel_reads,
            drop_final_batch=drop_final_batch, use_parser_fn=parser_fn)
        with self.assertRaises(errors.OutOfRangeError):
          sess.run(outputs)

 def testElementWisePosLen(self, dtype, unit):
   test_string = {
       "BYTE": [[b"ten", b"eleven", b"twelve"],
                [b"thirteen", b"fourteen", b"fifteen"],
                [b"sixteen", b"seventeen", b"eighteen"]],
       "UTF8_CHAR": [[x.encode("utf-8") for x in [u"\U0001d229\U0001d227n",
                                                  u"\xc6\u053c\u025bv\u025bn",
                                                  u"tw\u0c1dlv\u025b"]],
                     [x.encode("utf-8") for x in [u"He\xc3\xc3o",
                                                  u"W\U0001f604rld",
                                                  u"d\xfcd\xea"]],
                     [x.encode("utf-8") for x in [u"sixt\xea\xean",
                                                  u"se\U00010299enteen",
                                                  u"ei\U0001e920h\x86een"]]],
   }[unit]
   position = np.array([[1, -4, 3], [1, 2, -4], [-5, 2, 3]], dtype)
   length = np.array([[2, 2, 4], [4, 3, 2], [5, 5, 5]], dtype)
   expected_value = {
       "BYTE": [[b"en", b"ev", b"lve"], [b"hirt", b"urt", b"te"],
                [b"xteen", b"vente", b"hteen"]],
       "UTF8_CHAR": [[x.encode("utf-8") for x in [u"\U0001d227n",
                                                  u"\u025bv",
                                                  u"lv\u025b"]],
                     [x.encode("utf-8") for x in [u"e\xc3\xc3o",
                                                  u"rld",
                                                  u"d\xfc"]],
                     [x.encode("utf-8") for x in [u"xt\xea\xean",
                                                  u"\U00010299ente",
                                                  u"h\x86een"]]],
   }[unit]
   substr_op = string_ops.substr(test_string, position, length, unit=unit)
   with self.cached_session():
     substr = substr_op.eval()
     self.assertAllEqual(substr, expected_value)

  def _read_test(self, batch_size, num_epochs, file_index=None,
                 num_parallel_reads=1, drop_final_batch=False, parser_fn=False):
    if file_index is None:
      file_pattern = self.test_filenames
    else:
      file_pattern = self.test_filenames[file_index]

    if parser_fn:
      fn = lambda x: string_ops.substr(x, 1, 999)
    else:
      fn = None

    outputs = self.getNext(
        readers.make_tf_record_dataset(
            file_pattern=file_pattern,
            num_epochs=num_epochs,
            batch_size=batch_size,
            parser_fn=fn,
            num_parallel_reads=num_parallel_reads,
            drop_final_batch=drop_final_batch,
            shuffle=False))
    self._verify_records(
        outputs,
        batch_size,
        file_index,
        num_epochs=num_epochs,
        interleave_cycle_length=num_parallel_reads,
        drop_final_batch=drop_final_batch,
        use_parser_fn=parser_fn)
    with self.assertRaises(errors.OutOfRangeError):
      self.evaluate(outputs())

  def _testOutOfRangeError(self, dtype):
    # Scalar/Scalar
    test_string = b"Hello"
    position = np.array(7, dtype)
    length = np.array(3, dtype)
    substr_op = string_ops.substr(test_string, position, length)
    with self.test_session():
      with self.assertRaises(errors_impl.InvalidArgumentError):
        substr = substr_op.eval()

    # Vector/Scalar
    test_string = [b"good", b"good", b"bad", b"good"]
    position = np.array(3, dtype)
    length = np.array(1, dtype)
    substr_op = string_ops.substr(test_string, position, length)
    with self.test_session():
      with self.assertRaises(errors_impl.InvalidArgumentError):
        substr = substr_op.eval()

    # Negative pos
    test_string = b"Hello"
    position = np.array(-1, dtype)
    length = np.array(3, dtype)
    substr_op = string_ops.substr(test_string, position, length)
    with self.test_session():
      with self.assertRaises(errors_impl.InvalidArgumentError):
        substr = substr_op.eval()

    # Matrix/Matrix
    test_string = [[b"good", b"good", b"good"], [b"good", b"good", b"bad"],
                   [b"good", b"good", b"good"]]
    position = np.array([[1, 2, 3], [1, 2, 3], [1, 2, 3]], dtype)
    length = np.array([[3, 2, 1], [1, 2, 3], [2, 2, 2]], dtype)
    substr_op = string_ops.substr(test_string, position, length)
    with self.test_session():
      with self.assertRaises(errors_impl.InvalidArgumentError):
        substr = substr_op.eval()

    # Broadcast
    test_string = [[b"good", b"good", b"good"], [b"good", b"good", b"bad"]]
    position = np.array([1, 2, 3], dtype)
    length = np.array([1, 2, 3], dtype)
    substr_op = string_ops.substr(test_string, position, length)
    with self.test_session():
      with self.assertRaises(errors_impl.InvalidArgumentError):
        substr = substr_op.eval()

  def testMatrixStrings(self, dtype, unit):
    test_string = {
        "BYTE": [[b"ten", b"eleven", b"twelve"],
                 [b"thirteen", b"fourteen", b"fifteen"],
                 [b"sixteen", b"seventeen", b"eighteen"]],
        "UTF8_CHAR": [[x.encode("utf-8") for x in [u"\U0001d229\U0001d227n",
                                                   u"\xc6\u053c\u025bv\u025bn",
                                                   u"tw\u0c1dlv\u025b"]],
                      [x.encode("utf-8") for x in [u"He\xc3\xc3o",
                                                   u"W\U0001f604rld",
                                                   u"d\xfcd\xea"]]],
    }[unit]
    position = np.array(1, dtype)
    length = np.array(4, dtype)
    expected_value = {
        "BYTE": [[b"en", b"leve", b"welv"], [b"hirt", b"ourt", b"ifte"],
                 [b"ixte", b"even", b"ight"]],
        "UTF8_CHAR": [[x.encode("utf-8") for x in [u"\U0001d227n",
                                                   u"\u053c\u025bv\u025b",
                                                   u"w\u0c1dlv"]],
                      [x.encode("utf-8") for x in [u"e\xc3\xc3o",
                                                   u"\U0001f604rld",
                                                   u"\xfcd\xea"]]],
    }[unit]
    substr_op = string_ops.substr(test_string, position, length, unit=unit)
    with self.cached_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, expected_value)

    position = np.array(-3, dtype)
    length = np.array(2, dtype)
    expected_value = {
        "BYTE": [[b"te", b"ve", b"lv"], [b"ee", b"ee", b"ee"],
                 [b"ee", b"ee", b"ee"]],
        "UTF8_CHAR": [[x.encode("utf-8") for x in [u"\U0001d229\U0001d227",
                                                   u"v\u025b", u"lv"]],
                      [x.encode("utf-8") for x in [u"\xc3\xc3", u"rl",
                                                   u"\xfcd"]]],
    }[unit]
    substr_op = string_ops.substr(test_string, position, length, unit=unit)
    with self.cached_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, expected_value)

 def _testBadBroadcast(self, dtype):
   test_string = [[b"ten", b"eleven", b"twelve"],
                  [b"thirteen", b"fourteen", b"fifteen"],
                  [b"sixteen", b"seventeen", b"eighteen"]]
   position = np.array([1, 2, 3, 4], dtype)
   length = np.array([1, 2, 3, 4], dtype)
   expected_value = [[b"e", b"ev", b"lve"], [b"h", b"ur", b"tee"],
                     [b"i", b"ve", b"hte"]]
   with self.assertRaises(ValueError):
     substr_op = string_ops.substr(test_string, position, length)

  def _testVectorStrings(self, dtype):
    test_string = [b"Hello", b"World"]
    position = np.array(1, dtype)
    length = np.array(3, dtype)
    expected_value = [b"ell", b"orl"]

    substr_op = string_ops.substr(test_string, position, length)
    with self.test_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, expected_value)

  def _testScalarString(self, dtype):
    test_string = b"Hello"
    position = np.array(1, dtype)
    length = np.array(3, dtype)
    expected_value = b"ell"

    substr_op = string_ops.substr(test_string, position, length)
    with self.test_session():
      substr = substr_op.eval()
      self.assertAllEqual(substr, expected_value)

 def testOutOfRangeError_Scalar(self, dtype, pos, unit):
   # Scalar/Scalar
   test_string = {
       "BYTE": b"Hello",
       "UTF8_CHAR": u"H\xc3ll\U0001f604".encode("utf-8"),
   }[unit]
   position = np.array(pos, dtype)
   length = np.array(3, dtype)
   substr_op = string_ops.substr(test_string, position, length, unit=unit)
   with self.cached_session():
     with self.assertRaises(errors_impl.InvalidArgumentError):
       substr_op.eval()