本文整理汇总了Python中LTTL.Segmenter.import_xml方法的典型用法代码示例。如果您正苦于以下问题：Python Segmenter.import_xml方法的具体用法？Python Segmenter.import_xml怎么用？Python Segmenter.import_xml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LTTL.Segmenter的用法示例。
在下文中一共展示了Segmenter.import_xml方法的15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_import_xml_exception_missing_opening
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_exception_missing_opening(self):
"""Does import_xml detect missing opening tag?"""
with self.assertRaises(
ValueError,
msg="import_xml doesn't detect missing opening tag!"
):
Segmenter.import_xml(
self.wrong_xml_seg2,
element='a',
)示例2: test_import_xml_progress
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_progress(self):
"""Does import_xml track progress?"""
def progress_callback():
"""Mock progress callback"""
self.count += 1
Segmenter.import_xml(
self.broken_xml_seg,
element='a',
progress_callback=progress_callback,
)
self.assertEqual(
self.count,
len(self.broken_xml_seg),
msg="import_xml doesn't track progress!"
)示例3: test_import_xml_import_annotations_false
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_import_annotations_false(self):
"""Does import_xml skip importing annotations?"""
segmentation = Segmenter.import_xml(
self.broken_xml_seg,
element='a',
import_annotations=False,
)
self.assertFalse(
'a' in segmentation[0].annotations,
msg="import_xml doesn't skip importing annotations!"
)示例4: test_import_xml_convert_attributes
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_convert_attributes(self):
"""Does import_xml convert attributes?"""
segmentation = Segmenter.import_xml(
self.xml_seg,
element='a',
)
self.assertEqual(
[s.annotations['attr'] for s in segmentation],
['1', '2'],
msg="import_xml doesn't convert attributes!"
)示例5: test_import_xml_segment_elements_broken
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_segment_elements_broken(self):
"""Does import_xml segment xml elements from distinct strings?"""
segmentation = Segmenter.import_xml(
self.broken_xml_seg,
element='a',
)
self.assertEqual(
[s.get_content() for s in segmentation],
['1<a>2<a>3</a>4', '2<a>3</a>4', '3', '</a>5'],
msg="import_xml doesn't segment elements from distinct strings!"
)示例6: test_import_xml_segment_elements
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_segment_elements(self):
"""Does import_xml segment xml elements?"""
segmentation = Segmenter.import_xml(
self.xml_seg,
element='a',
)
self.assertEqual(
[s.get_content() for s in segmentation],
['<a attr="2">c<a/>d</a>', 'c<a/>d'],
msg="import_xml doesn't segment xml elements!"
)示例7: test_import_xml_autonumber
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_autonumber(self):
"""Does import_xml autonumber input segments?"""
segmentation = Segmenter.import_xml(
self.xml_seg,
element='a',
auto_number_as='num'
)
self.assertEqual(
[s.annotations['num'] for s in segmentation],
[1, 2],
msg="import_xml doesn't autonumber input segments!"
)示例8: test_import_xml_import_element_as_annotation
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_import_element_as_annotation(self):
"""Does import_xml import element as annotation?"""
segmentation = Segmenter.import_xml(
self.xml_seg,
element='a',
import_element_as='test',
)
self.assertEqual(
[s.annotations['test'] for s in segmentation],
['a', 'a'],
msg="import_xml doesn't import element as annotation!"
)示例9: test_import_xml_import_annotations
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_import_annotations(self):
"""Does import_xml import annotations?"""
segmentation = Segmenter.import_xml(
self.broken_xml_seg,
element='a',
import_annotations=True,
)
self.assertEqual(
segmentation[0].annotations['a'],
'1',
msg="import_xml doesn't import annotations!"
)示例10: test_import_xml_remove_markup_broken
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_remove_markup_broken(self):
"""Does import_xml remove markup from distinct strings?"""
segmentation = Segmenter.import_xml(
self.broken_xml_seg,
element='a',
remove_markup=True,
)
self.assertEqual(
[s.get_content() for s in segmentation],
['1', '2', '2', '3', '3', '3', '4', '4', '5'],
msg="import_xml doesn't remove markup from distinct strings!"
)示例11: test_import_xml_condition
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_condition(self):
"""Does import_xml respect conditions?"""
segmentation = Segmenter.import_xml(
self.xml_seg,
element='a',
conditions={'attr': re.compile(r'^2$')},
)
self.assertEqual(
[s.annotations['attr'] for s in segmentation],
['2'],
msg="import_xml doesn't respect conditions!"
)示例12: test_import_xml_solve_attribute_conflict
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_solve_attribute_conflict(self):
"""Does import_xml solve attribute conflicts?"""
segmentation = Segmenter.import_xml(
self.xml_seg,
element='a',
merge_duplicates=True,
remove_markup=True,
)
self.assertEqual(
segmentation[0].annotations['attr'],
'1',
msg="import_xml doesn't solve attribute conflicts!"
)示例13: test_import_xml_merge_duplicates
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_merge_duplicates(self):
"""Does import_xml merge duplicates?"""
segmentation = Segmenter.import_xml(
self.xml_seg,
element='a',
merge_duplicates=True,
remove_markup=True,
)
self.assertEqual(
[s.get_content() for s in segmentation],
['c', 'd'],
msg="import_xml doesn't merge duplicates!"
)示例14: test_import_xml_remove_markup
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_remove_markup(self):
"""Does import_xml remove markup?"""
segmentation = Segmenter.import_xml(
self.xml_seg,
element='a',
conditions={'attr': re.compile(r'^2$')},
remove_markup=True,
)
self.assertEqual(
[s.get_content() for s in segmentation],
['c', 'd'],
msg="import_xml doesn't remove markup!"
)示例15: test_import_xml_preserve_leaves
# 需要导入模块: from LTTL import Segmenter [as 别名]
# 或者: from LTTL.Segmenter import import_xml [as 别名]
def test_import_xml_preserve_leaves(self):
"""Does import_xml preserve leaves?"""
segmentation = Segmenter.import_xml(
self.xml_seg,
element='a',
merge_duplicates=True,
remove_markup=True,
preserve_leaves=True,
)
self.assertEqual(
segmentation[0].annotations['attr'],
'2',
msg="import_xml doesn't preserve leaves!"
)