本文整理汇总了Python中document.Document.content方法的典型用法代码示例。如果您正苦于以下问题：Python Document.content方法的具体用法？Python Document.content怎么用？Python Document.content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document.Document的用法示例。
在下文中一共展示了Document.content方法的5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_textWithLineBlocks
# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import content [as 别名]
def test_textWithLineBlocks (self):
sampleDocxFile = os.path.join(os.getcwd(), 'samples', 'docx', '08_line_blocks.docx')
docxProcessor = DocxProcessor(sampleDocxFile)
document = docxProcessor.document()
expectedDocument = Document().initWithFile(os.path.join(os.getcwd(), 'samples', 'expected outcome', 'docx', 'test_08'))
self.assertEquals(expectedDocument.content(), document.content())
self.assertEquals(expectedDocument.formatting(), document.formatting())示例2: test_parseSimplePdf
# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import content [as 别名]
def test_parseSimplePdf (self):
samplePdfFile = os.path.join(os.getcwd(), 'samples', 'pdf', '01_simple_text.pdf')
pdfProcessor = PdfProcessor(samplePdfFile)
document = pdfProcessor.document()
expectedDocument = Document().initWithFile(os.path.join(os.getcwd(), 'samples', 'expected outcome', 'docx', 'test_01'))
self.assertEquals(expectedDocument.content(), document.content())
self.assertEquals(expectedDocument.formatting(), document.formatting())示例3: test_textWithWeirdFormatting
# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import content [as 别名]
def test_textWithWeirdFormatting (self):
sampleDocxFile = os.path.join(os.getcwd(), 'samples', 'docx', '11_weird_formatting.docx')
docxProcessor = DocxProcessor(sampleDocxFile)
document = docxProcessor.document()
expectedDocument = Document().initWithFile(os.path.join(os.getcwd(), 'samples', 'expected outcome', 'docx', 'test_11'))
self.assertEquals(expectedDocument.content(), document.content())
self.assertEquals(expectedDocument.formatting(), document.formatting())示例4: test_sampleDocumentProcessing
# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import content [as 别名]
def test_sampleDocumentProcessing (self):
sampleSubstanceFile = os.path.join(os.getcwd(), 'samples', 'substance', '01_sample.json')
substanceProcessor = SubstanceProcessor().initWithFile(sampleSubstanceFile)
document = substanceProcessor.document()
expectedDocument = Document().initWithFile(os.path.join(os.getcwd(), 'samples', 'expected outcome', 'substance_01'))
print("DOCUMENT METADATA: " + str(document.metadata()))
self.assertEqual(expectedDocument.content(), document.content())
self.assertEqual(expectedDocument.metadata(), document.metadata())示例5: corpus_line
# 需要导入模块: from document import Document [as 别名]
# 或者: from document.Document import content [as 别名]
def corpus_line(file_path: str, encoding='utf-8', zip_type=None):
suffix = '' if not zip_type else '.' + zip_type
# class label
class_label_file = os.path.join(file_path, '.labels' + suffix)
if os.path.isfile(class_label_file):
class_label_iter = parse_file(class_label_file, encoding=encoding, zip_type=zip_type)
else:
class_label_iter = itertools.repeat('[none]')
# document name
doc_name_file = os.path.join(file_path, '.names' + suffix)
if os.path.isfile(doc_name_file):
doc_name_iter = parse_file(doc_name_file, encoding=encoding, zip_type=zip_type)
else:
doc_name_iter = itertools.repeat('[none]')
# doc content
content_iter = parse_file(file_path + suffix, encoding=encoding, zip_type=zip_type)
for doc_id, class_label, name, content in\
zip(itertools.count(0), class_label_iter, doc_name_iter, content_iter):
doc = Document(name, doc_id, class_label)
doc.content = content
yield doc