本文整理汇总了Python中apache_beam.io.textio._TextSource.read方法的典型用法代码示例。如果您正苦于以下问题：Python _TextSource.read方法的具体用法？Python _TextSource.read怎么用？Python _TextSource.read使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类apache_beam.io.textio._TextSource的用法示例。
在下文中一共展示了_TextSource.read方法的3个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: test_read_single_file_without_striping_eol_crlf
# 需要导入模块: from apache_beam.io.textio import _TextSource [as 别名]
# 或者: from apache_beam.io.textio._TextSource import read [as 别名]
def test_read_single_file_without_striping_eol_crlf(self):
file_name, written_data = write_data(TextSourceTest.DEFAULT_NUM_RECORDS,
eol=EOL.CRLF)
assert len(written_data) == TextSourceTest.DEFAULT_NUM_RECORDS
source = TextSource(file_name, 0, CompressionTypes.UNCOMPRESSED,
False, coders.StrUtf8Coder())
range_tracker = source.get_range_tracker(None, None)
read_data = list(source.read(range_tracker))
self.assertCountEqual([line + '\r\n' for line in written_data], read_data)示例2: _run_read_test
# 需要导入模块: from apache_beam.io.textio import _TextSource [as 别名]
# 或者: from apache_beam.io.textio._TextSource import read [as 别名]
def _run_read_test(self, file_or_pattern, expected_data,
buffer_size=DEFAULT_NUM_RECORDS,
compression=CompressionTypes.UNCOMPRESSED):
# Since each record usually takes more than 1 byte, default buffer size is
# smaller than the total size of the file. This is done to
# increase test coverage for cases that hit the buffer boundary.
source = TextSource(file_or_pattern, 0, compression,
True, coders.StrUtf8Coder(), buffer_size)
range_tracker = source.get_range_tracker(None, None)
read_data = list(source.read(range_tracker))
self.assertCountEqual(expected_data, read_data)示例3: _read_skip_header_lines
# 需要导入模块: from apache_beam.io.textio import _TextSource [as 别名]
# 或者: from apache_beam.io.textio._TextSource import read [as 别名]
def _read_skip_header_lines(self, file_or_pattern, skip_header_lines):
"""Simple wrapper function for instantiating TextSource."""
source = TextSource(
file_or_pattern,
0,
CompressionTypes.UNCOMPRESSED,
True,
coders.StrUtf8Coder(),
skip_header_lines=skip_header_lines)
range_tracker = source.get_range_tracker(None, None)
return list(source.read(range_tracker))