def setUp(self):
# initiates DOCXDocument
self.doc = DOCXDocument(self.test_file_name)
self.doc.load()
self.d_original = self.soup_doc.find(DOCXDrawing.full_tag_name)
self.d = DOCXDrawing(self.d_original, docx=self.doc)
def setUp(self):
# initiates DOCXDocument
self.doc = DOCXDocument(self.test_file_name)
self.doc.load()
# find first hyperlink
self.h_original = self.soup_doc.find(DOCXHyperlink.full_tag_name)
self.h = DOCXHyperlink(self.h_original, docx=self.doc)
def setUp(self):
# initiates DOCXDocument
self.doc = DOCXDocument(self.test_file_name)
self.doc.load()
# find second paragraph
self.p_original = self.soup_doc.find_all(
DOCXParagraph.full_tag_name)[1]
self.p = DOCXParagraph(self.p_original, docx=self.doc)
# find second paragraph
self.pi_original = self.soup_doc.find_all(
DOCXParagraph.full_tag_name)[0]
self.pi = DOCXParagraph(self.pi_original, docx=self.doc)
class DOCXDrawingTest(DOCXItemTest):
"""DOCXDrawing tests"""
def setUp(self):
# initiates DOCXDocument
self.doc = DOCXDocument(self.test_file_name)
self.doc.load()
self.d_original = self.soup_doc.find(DOCXDrawing.full_tag_name)
self.d = DOCXDrawing(self.d_original, docx=self.doc)
def test_DOCXDrawing_getText_returns_None(self):
"""getText() contents for <w:drawing> return None"""
self.assertEqual(self.d.getText(), None)
def test_DOCXDrawing_getImageName(self):
"""getImageName() contents for <w:drawing>"""
image_name = self.d.getImageName()
self.assertEqual(image_name, 'media/image2.jpg')
class DOCXHyperlinkTest(DOCXItemTest):
"""DOCXHyperlink tests"""
def setUp(self):
# initiates DOCXDocument
self.doc = DOCXDocument(self.test_file_name)
self.doc.load()
# find first hyperlink
self.h_original = self.soup_doc.find(DOCXHyperlink.full_tag_name)
self.h = DOCXHyperlink(self.h_original, docx=self.doc)
def test_DOCXHyperlink_getText(self):
"""<w:hyperlink> getText"""
tgt = '<a href="http://www.duma.gov.ru/structure/factions/er/">ракци</a>'
self.assertEqual(self.h.getText(), tgt)
def test_DOCXHyperlink_getCleanedText(self):
"""<w:hyperlin>k getCleanedText() result equals to bs4.element.Tag.get_text()"""
self.assertEqual(self.h.getCleanedText(), self.h_original.get_text())
def test_DOCXHyperlink_getRelationshipId(self):
"""<w:hyperlink> getRelationshipId returns correct relation identifier"""
self.assertEqual(self.h.getRelationshipId(), 'rId7')
def __init__(self, file_name, *args, **kwargs):
super(ASOZDParser, self).__init__(file_name, *args, **kwargs)
#if kwargs.get('debug'):
# self._debug = (kwargs.get('debug') == True)
self._line_separator = os.linesep
if kwargs.get('linesep'):
self._line_separator = kwargs.get('linesep')
# file name for docx document
self.file_name = file_name
# configuration
from parser_config import config
self.config = config
# list for storing paragraph data
#self.pStorage = []
self._init_config()
self._doc = DOCXDocument(self.file_name)
class DOCXParagraphTest(DOCXItemTest):
"""DOCXParagraph tests"""
def setUp(self):
# initiates DOCXDocument
self.doc = DOCXDocument(self.test_file_name)
self.doc.load()
# find second paragraph
self.p_original = self.soup_doc.find_all(
DOCXParagraph.full_tag_name)[1]
self.p = DOCXParagraph(self.p_original, docx=self.doc)
# find second paragraph
self.pi_original = self.soup_doc.find_all(
DOCXParagraph.full_tag_name)[0]
self.pi = DOCXParagraph(self.pi_original, docx=self.doc)
def test_DOCXParagraph_getText_with_several_children_wr(self):
"""<w:p> getText common test with several children <w:r> elements"""
tgt = 'Депутат Государственной Думы VII созыва, избран от избирательного округа '+\
'0039 (Барнаульский - Алтайский край)'
self.assertEqual(self.p.getText(), tgt)
def test_DOCXParagraph_getId(self):
"""<w:p> getId common test"""
self.assertEqual(self.p.getId(), '00000001')
def test_DOCXParagraph_getChildren_doesnt_contain_excluded_tags(self):
"""<w:p> getChildren doesn't contains excluded elements"""
tmp = [
y for y in [x.name for x in self.p.getChildren()]
if y in self.p.EXCLUDE_LIST
]
self.assertEqual(tmp, [])
def test_DOCXParagraph_getChildren_common(self):
"""<w:p> getChildren returns first level child objects"""
# using pi (paragraph image) which contains two child <w:r> elements
self.assertEqual([x.name for x in self.pi.getChildren()], ['r', 'r'])
def test_DOCXParagraph_getRawText(self):
"""<w:p> getRawText() returns list with <w:r> contents"""
tgt = [
'Депутат Государственной Думы VII созыва, избран от избирательного округа 0039 (Барнаульский ',
'-', ' Алтайский край)'
]
#tgt = []
#for r in self.p._item.findChildren('r', recursive=False):
# t = r.getText()
# if t: tgt.append(t)
self.assertEqual(self.p.getRawText(), tgt)
def test_DOCXParagraph_getImages_with_images_exists(self):
"""<w:p> getImages() return <w:drawings> only"""
self.assertEqual(set([t.name for t in self.pi.getImages()]),
{'drawing'})
def test_DOCXParagraph_getImages_empty_result(self):
"""<w:p> getImages() return empty set if paragraph doesn't contain <w:drawings>"""
self.assertEqual([t.name for t in self.p.getImages()], [])