Page MenuHomec4science
Files F60182076

test_process_words_post_merging.py
No OneTemporary
Actions

File Metadata

Created
Sun, Apr 28, 03:14

test_process_words_post_merging.py
View Options

import unittest
from os import sep, path, remove
from os.path import isdir, isfile, dirname
import shutil
import sys
import lxml.etree as ET
import warnings
import sys
sys.path.append('svgscripts')
import process_words_post_merging
from datatypes.faksimile import FaksimilePage
from datatypes.mark_foreign_hands import MarkForeignHands
from datatypes.page import Page
from datatypes.path import Path
from datatypes.positional_word_part import PositionalWordPart
from datatypes.text_connection_mark import TextConnectionMark
from datatypes.transkriptionField import TranskriptionField
from datatypes.word_position import WordPosition
class TestPostMerge(unittest.TestCase):
def setUp(self):
process_words_post_merging.UNITTESTING = True
DATADIR = path.dirname(__file__) + sep + 'test_data'
self.faksimile_dir = DATADIR + sep + 'faksimile_svg'
self.manuscript = DATADIR + sep + 'N_VII_1.xml'
self.manuscript_copy = self.manuscript.replace('.', '_copy.')
self.faksimile_file = self.faksimile_dir + sep + 'N-VII-1,5et6.svg'
self.xml_file = DATADIR + sep + 'N_VII_1_page005.xml'
self.Mp_XIV_1_mytest_421 = DATADIR + sep + 'Mp_XIV_1_mytest_421.xml'
self.test_tcm_xml = DATADIR + sep + 'N_VII_1_page001.xml'
self.pdf_xml = DATADIR + sep + 'W_I_8_page125.xml'
self.pdf_xml_source = DATADIR + sep + 'W_I_8_neu_125-01.svg'
def test_main(self):
process_words_post_merging.main([self.manuscript])
def test_categorize_paths(self):
page = Page(self.pdf_xml)
page.source = self.pdf_xml_source
tr = TranskriptionField(page.source)
page.words = [ word for word in page.words if word.line_number == 33 ]
path_dict = process_words_post_merging.categorize_paths(page, tr)
self.assertEqual(True in [ word.deleted for word in page.words if word.id == 269 ], False)
self.assertEqual(len(path_dict.get('deletion_or_underline_paths')) > 0, True)
self.assertEqual(len(path_dict.get('box_paths')), 5)
"""
words = [ word for word in page.words if len(word.box_paths) > 0 ]
self.assertEqual(len(words), 1)
self.assertEqual(words[0].word_parts[0].earlier_version is not None, True)
self.assertEqual(words[0].word_parts[0].earlier_version.text, ')')
"""
def test_find_special_words(self):
page = Page(self.xml_file)
process_words_post_merging.find_special_words(page)
self.assertEqual(len(page.mark_foreign_hands), 1)
self.assertEqual(page.mark_foreign_hands[0].foreign_hands_text, 'x')
page.update_and_attach_words2tree()
nodes = page.page_tree.xpath('//' + MarkForeignHands.XML_TAG)
page = Page(self.test_tcm_xml)
process_words_post_merging.find_special_words(page)
self.assertEqual(len(page.text_connection_marks), 1)
self.assertEqual(page.text_connection_marks[0].text_source.first_line, 2)
"""
page.update_and_attach_words2tree()
nodes = page.page_tree.xpath('//' + TextConnectionMark.XML_TAG)
print(ET.dump(nodes[0]))
"""
@unittest.skip('fix word.process_boxes first')
def test_process_word_boxes(self):
page = Page(self.pdf_xml) # W_I_8_page125.xml
page.source = self.pdf_xml_source
for word in page.words:
word.partition_according_to_writing_process_id()
tr = TranskriptionField(page.source)
box_path_d = ['M 598.11,626.565 L 603.557,626.565 L 603.557,632.565 L 598.11,632.565 L 598.11,626.565',\
'M 557.443,683.44 L 574.182,683.44 L 574.182,694.815 L 557.443,694.815 L 557.443,683.44',\
'M 404.193,659.565 L 407.80699999999996,659.565 L 407.80699999999996,668.94 L 404.193,668.94 L 404.193,659.565',\
'M 587.932,634.065 L 598.318,634.065 L 598.318,643.19 L 587.932,643.19 L 587.932,634.065',\
'M 570.443,221.315 L 576.557,221.315 L 576.557,230.065 L 570.443,230.065 L 570.443,221.315']
box_paths = [ Path(d_string=d_string) for d_string in box_path_d ]
process_words_post_merging.process_word_boxes(page, box_paths, tr)
words_with_boxes = [ word for word in page.words if len(word.box_paths) > 0 ]
expected_values = {'Aber': 'aber', 'seiner': ')', 'mit': ',', '(–': ':', 'Um': 'Denn'}
self.assertEqual(len(words_with_boxes), len(expected_values.keys()))
for word in words_with_boxes:
self.assertEqual(word.earlier_version.text, expected_values.get(word.text))
#print(f'{word.id} {word.text} "{word.earlier_version.text}" "{word.box_paths[0].earlier_text}"')
def test_update_writing_process_ids(self):
page = Page(self.pdf_xml)
page.words = [ word for word in page.words if word.text == 'Aber' and word.line_number == 2 ]
process_words_post_merging.update_writing_process_ids(page)
self.assertEqual(len(page.words[0].word_parts), 2)
self.assertEqual(page.words[0].word_parts[0].writing_process_id, 1)
self.assertEqual(page.words[0].word_parts[1].writing_process_id, 0)
@unittest.skip('takes long')
#@unittest.skipUnless(__name__ == "__main__", 'test takes too long, we do not run it with unittest discover')
def test_reset_page(self):
page = Page(self.pdf_xml)
page.source = self.pdf_xml_source
process_words_post_merging.post_merging_processing_and_saving(page=page)
numWordParts = 7
process_words_post_merging.post_merging_processing_and_saving(page=page)
self.assertEqual(len([ word for word in page.words if len(word.word_parts) > 0 ]), numWordParts)
process_words_post_merging.reset_page(page)
self.assertEqual(len([ word for word in page.words if word.earlier_version is not None ]), 0)
self.assertEqual(len([ word for word in page.words if len(word.word_parts) > 0 ]), 0)
if __name__ == "__main__":
unittest.main()

Event Timeline

c4science · Help