Page MenuHomec4science
Files F62569172

test_join_faksimileAndTranskription.py
No OneTemporary
Actions

File Metadata

Created
Tue, May 14, 01:38

test_join_faksimileAndTranskription.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 join_faksimileAndTranskription
from datatypes.faksimile import FaksimilePage
from datatypes.page import Page
from datatypes.positional_word_part import PositionalWordPart
from datatypes.transkriptionField import TranskriptionField
from datatypes.word_position import WordPosition
class TestJoin(unittest.TestCase):
def setUp(self):
join_faksimileAndTranskription.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'
def test_sort_words(self):
page = Page(xml_source_file=self.Mp_XIV_1_mytest_421)
words_line7 = [ word for word in page.words if word.line_number == 7 ]
page.words = words_line7
sorted_words = join_faksimileAndTranskription.sort_words(page)
self.assertEqual(len(sorted_words), len(words_line7))
for index, word in enumerate(words_line7):
self.assertEqual(sorted_words[index], word)
def test_sort_faksimile_positions(self):
faksimile_tree = ET.parse(self.faksimile_file)
namespaces = { k if k is not None else 'ns': v for k, v in faksimile_tree.getroot().nsmap.items() }
faksimile_pages = FaksimilePage.GET_FAKSIMILEPAGES(faksimile_tree, namespaces=namespaces)
self.assertEqual(len(faksimile_pages), 2)
svg_pos_file, manuscript_file = join_faksimileAndTranskription.get_svgPosFile_and_manuscriptFile(faksimile_pages[0], manuscript_file=self.manuscript)
sorted_positions = join_faksimileAndTranskription.sort_faksimile_positions(faksimile_pages[0].word_positions)
page = Page(xml_source_file=svg_pos_file)
for index in range(0, 10):
id = sorted_positions[index].id
if len(faksimile_tree.getroot().xpath('//ns:rect[@id="{0}"]/ns:title/text()|//ns:path[@id="{0}"]/ns:title/text()'\
.format(id), namespaces=namespaces)) > 0:
word_text = faksimile_tree.getroot().xpath('//ns:rect[@id="{0}"]/ns:title/text()|//ns:path[@id="{0}"]/ns:title/text()'\
.format(id), namespaces=namespaces)[0]
#print(sorted_positions[index].left, sorted_positions[index].top, word_text, page.words[index].text)
self.assertEqual(word_text, page.words[index].text)
def test_get_filelist_and_manuscript_file(self):
file_list, manuscript_file = join_faksimileAndTranskription.get_filelist_and_manuscript_file(self.faksimile_dir, self.manuscript)
self.assertEqual(len(file_list), 1)
self.assertEqual(file_list[0], self.faksimile_file)
self.assertEqual(manuscript_file, self.manuscript)
file_list, manuscript_file = join_faksimileAndTranskription.get_filelist_and_manuscript_file(self.manuscript, self.faksimile_file)
self.assertEqual(len(file_list), 1)
self.assertEqual(file_list[0], self.faksimile_file)
self.assertEqual(manuscript_file, self.manuscript)
def test_get_svgPosFile_and_manuscriptFile(self):
faksimile_tree = ET.parse(self.faksimile_file)
faksimile_pages = FaksimilePage.GET_FAKSIMILEPAGES(faksimile_tree)
self.assertEqual(len(faksimile_pages), 2)
svg_pos_file, manuscript_file = join_faksimileAndTranskription.get_svgPosFile_and_manuscriptFile(faksimile_pages[0], manuscript_file=self.manuscript)
#self.assertEqual(svg_pos_file, self.manuscript.replace('.', '_page00{}.'.format(faksimile_pages[0].page_number)))
self.assertEqual(manuscript_file, self.manuscript)
def test_join_faksimileAndTranskription(self):
self.assertEqual(join_faksimileAndTranskription.join_faksimileAndTranskription(self.faksimile_file, self.manuscript), 0)
#self.assertEqual(join_faksimileAndTranskription.join_faksimileAndTranskription(self.faksimile_file, self.manuscript, test_word_text='gar'), 0)
def testupdate_writing_process(self):
page = Page(xml_source_file=self.xml_file)
word = page.words[12]
self.assertEqual(len(word.faksimile_positions), 1)
self.assertEqual(word.faksimile_positions[0].writing_process_id, -1)
join_faksimileAndTranskription.update_writing_process(word)
self.assertEqual(word.faksimile_positions[0].writing_process_id, 0)
#@unittest.skipUnless(__name__ == "__main__", 'test takes too long, we do not run it with unittest discover')
@unittest.skip('test takes too long, has been tested')
def test_fix_errors(self):
page = Page(xml_source_file=self.xml_file)
word_position = WordPosition(id='rect945', text='Lenken')
join_faksimileAndTranskription.fix_errors(self.faksimile_file, [ word_position], [page.words[12]], xml_source_file=self.xml_file, manuscript_file=self.manuscript )
if __name__ == "__main__":
unittest.main()

Event Timeline

c4science · Help