#!/usr/bin/python3
from csvreader import CsvReader
import re
reader = CsvReader(',', '"')
original = reader.parse('latin.gerald.original.csv')
modified = reader.parse('latin.gerald.modified.csv')
if len(original) != len(modified):
print('Both documents don\'t have equal number of rows')
exit(1)
else:
for i in range(0, len(original)):
normalized_original = re.sub(r'[ \n\t\.,;:\(\)]', '', original[i][1].lower())
normalized_modified = re.sub(r'[ \n\t\.,;:\(\)]', '', (modified[i][1] + modified[i][2]).lower())
if original[i][0] != modified[i][0]:
print('row', (i + 1), ': latin column does not match (' + original[i][0] + ' <-> ' + modified[i][0] + ')')
#end if
if normalized_original != normalized_modified:
print('row', (i + 1), ': translation column was altered (' + original[i][1].replace('\n', '\\n') + ' <-> ' + modified[i][1].replace('\n', '\\n') + ' [' + modified[i][2].replace('\n', '\\n') + '])')
#end if
#end for
print('Checked documents')
exit(0)
#end if
#end def
#end def
def fetch_kanji(self, kanji):
encoded_char = urllib.parse.quote(kanji)
image_url = WikicommonsResource.get_imageurl(encoded_char + '-j' + self.imgtype + '.' + self.filetype) # check for japan-specific file
if image_url != None:
print('Found Japan-specific image for kanji ' + kanji + '!')
self._save_image(image_url)
else:
image_url = WikicommonsResource.get_imageurl(encoded_char + '-' + self.imgtype + '.' + self.filetype)
if image_url != None:
self._save_image(image_url)
else:
print('Cannot download image for kanji ' + kanji)
#end if
#end if
#end def
#end class
hiraganas = HiraganaResource('/home/heartdisease/Documents/hiragana_animated/', 'stroke_order_animation', 'gif')
katakanas = KatakanaResource('/home/heartdisease/Documents/katakana_animated/', 'stroke_order_animation', 'gif')
kanjis = KanjiResource('/home/heartdisease/Documents/kanji_red/', 'red', 'png') # 'order', 'red'
#hiraganas.fetch_hiraganas(HiraganaResource.get_hiraganas())
#katakanas.fetch_katakanas(KatakanaResource.get_katakanas())
kanjilist = CsvReader(',', '"')
kanjis.fetch_kanjis([row[0] for row in kanjilist.parse('csv/kanji80.csv')])
