def test_mix_english_with_greek(self):
sentence = u"English is the main language but let me show my GREEK: Καλημέρα σας! 59310"
# English is the main language
output = brl.translate(sentence, main_language="english")
actual_output = [[
'000001', '100010', '101110', '110110', '111000', '010100',
'100101'
], ['010100', '011100'], ['011101'], ['101100', '100000', '001010'],
[
'111000', '100000', '101110', '110110', '101001',
'100000', '110110', '100010'
], ['110000'], ['111000', '100010', '011110'],
['101100', '100010'], ['100101', '010101'],
['101100', '101111'],
[
'000001', '000001', '110110', '111010', '100010',
'100010', '101000'
],
[
'000010', '000001', '101000', '100000', '111000',
'001110', '101100', '000010', '000101', '111010',
'100000'
], ['000010', '011100', '100000'],
[
'001111', '010001', '001010', '010010', '010000',
'001011'
]]
# ⠠⠑⠝⠛⠇⠊⠩ ⠊⠎ ⠮ ⠍⠁⠔ ⠇⠁⠝⠛⠥⠁⠛⠑ ⠃ ⠇⠑⠞ ⠍⠑ ⠩⠪ ⠍⠽ ⠠⠠⠛⠗⠑⠑⠅ ⠐⠠⠅⠁⠇⠜⠍⠐⠨⠗⠁ ⠐⠎⠁ ⠼⠢⠔⠒⠂⠴
self.assertEqual(output, actual_output)
def test_greek_main_translation(self):
sentence = u"Τεστ 3,5 σουβλακι"
# Greek is the main language
output = brl.translate(sentence, main_language="greek")
actual_output = [['000101', '011110', '100010', '011100', '011110'],
['001111', '010010', '010001'],
[
'011100', '101001', '110000', '111000', '100000',
'101000', '010100'
]]
# ⠨⠞⠑⠎⠞ ⠼⠒⠢ ⠎⠥⠃⠇⠁⠅⠊
self.assertEqual(output, actual_output)
def test_english_translation(self):
sentence = "Hello WORLD 123"
output = brl.translate(sentence, main_language="english")
actual_output = [[
'000001', '110010', '100010', '111000', '111000', '101010'
],
[
'000001', '000001', '010111', '101010', '111010',
'111000', '100110'
], ['001111', '010000', '011000', '010010']]
# ⠠⠓⠑⠇⠇⠕ ⠠⠠⠺⠕⠗⠇⠙ ⠼⠂⠆⠒
self.assertEqual(output, actual_output)
def test_greek_foreign_translation(self):
sentence = u"Τεστ 3,5 σουβλακι"
# English is the main language
output = brl.translate(sentence, main_language="english")
actual_output = [[
'000010', '000001', '011110', '100010', '011100', '011110'
], ['001111', '010010', '010001'],
[
'000010', '011100', '101001', '110000', '111000',
'100000', '101000', '010100'
]]
# ⠐⠠⠞⠑⠎⠞ ⠼⠒⠢ ⠐⠎⠥⠃⠇⠁⠅⠊
self.assertEqual(output, actual_output)
def test_mix_english_with_greek(self):
sentence = u"Η κύρια γλώσσα είναι τα Ελληνικά. ΑΓΓΛΙΚΆ: Foo bar 59310"
# Greek is the main language
output = brl.translate(sentence, main_language="greek")
actual_output = [
['000101', '001110'],
['101000', '000010', '000101', '111010', '010100', '100000'],
[
'110110', '111000', '000010', '000100', '011100', '011100',
'100000'
], ['000010', '000101', '101110', '110001'], ['011110', '100000'],
[
'000101', '100010', '111000', '111000', '001110', '101110',
'010100', '101000', '000010', '000101'
],
[
'000101', '000101', '100000', '110110', '110110', '111000',
'010100', '101000', '000010', '000101'
], ['000011', '000001', '110100', '101010', '101010'],
['000011', '110000', '001110'],
['001111', '010001', '001010', '010010', '010000', '001011']
]
# ⠨⠜ ⠅⠐⠨⠗⠊⠁ ⠛⠇⠐⠈⠎⠎⠁ ⠐⠨⠝⠣ ⠞⠁ ⠨⠑⠇⠇⠜⠝⠊⠅⠐⠨ ⠨⠨⠁⠛⠛⠇⠊⠅⠐⠨ ⠰⠠⠋⠕⠕ ⠰⠃⠜ ⠼⠢⠔⠒⠂⠴
self.assertEqual(output, actual_output)
def mytext(self):
cursor = self.textEdit.textCursor()
textSelected = cursor.selectedText()
example=brl.translate(textSelected)
s = brl.toUnicodeSymbols(example, flatten=True)
cursor.insertText(s)
def convert(argv):
def usage():
print(
'usage: %s [-d] [-p pagenos] [-m maxpages] [-P password] [-o output]'
' [-C] [-n] [-A] [-V] [-M char_margin] [-L line_margin] [-W word_margin]'
' [-F boxes_flow] [-Y layout_mode] [-O output_dir] [-R rotation]'
' [-t text|html|xml|tag] [-c codec] [-s scale]'
' file ...' % argv[0])
return 100
try:
(opts, args) = getopt.getopt(argv[1:],
'dp:m:P:o:CnAVM:L:W:F:Y:O:R:t:c:s:')
except getopt.GetoptError:
return usage()
if not args: return usage()
# debug option
debug = 0
# input option
password = ''
pagenos = set()
maxpages = 0
# output option
outfile = 'inputs/' + sys.argv[1].replace(' ', '')[:-4] + '.txt'
outtype = None
imagewriter = None
rotation = 0
layoutmode = 'normal'
codec = 'utf-8'
pageno = 1
scale = 1
caching = True
showpageno = True
laparams = LAParams()
for (k, v) in opts:
if k == '-d': debug += 1
elif k == '-p': pagenos.update(int(x) - 1 for x in v.split(','))
elif k == '-m': maxpages = int(v)
elif k == '-P': password = v
elif k == '-o': outfile = v
elif k == '-C': caching = False
elif k == '-n': laparams = None
elif k == '-A': laparams.all_texts = True
elif k == '-V': laparams.detect_vertical = True
elif k == '-M': laparams.char_margin = float(v)
elif k == '-L': laparams.line_margin = float(v)
elif k == '-W': laparams.word_margin = float(v)
elif k == '-F': laparams.boxes_flow = float(v)
elif k == '-Y': layoutmode = v
elif k == '-O': imagewriter = ImageWriter(v)
elif k == '-R': rotation = int(v)
elif k == '-t': outtype = v
elif k == '-c': codec = v
elif k == '-s': scale = float(v)
#
PDFDocument.debug = debug
PDFParser.debug = debug
CMapDB.debug = debug
PDFResourceManager.debug = debug
PDFPageInterpreter.debug = debug
PDFDevice.debug = debug
#
rsrcmgr = PDFResourceManager(caching=caching)
if not outtype:
outtype = 'text'
if outfile:
if outfile.endswith('.htm') or outfile.endswith('.html'):
outtype = 'html'
elif outfile.endswith('.xml'):
outtype = 'xml'
elif outfile.endswith('.tag'):
outtype = 'tag'
if outfile:
outfp = file(outfile, 'w')
else:
outfp = sys.stdout
if outtype == 'text':
device = TextConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'xml':
device = XMLConverter(rsrcmgr,
outfp,
codec=codec,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'html':
device = HTMLConverter(rsrcmgr,
outfp,
codec=codec,
scale=scale,
layoutmode=layoutmode,
laparams=laparams,
imagewriter=imagewriter)
elif outtype == 'tag':
device = TagExtractor(rsrcmgr, outfp, codec=codec)
else:
return usage()
for fname in args:
fp = file('pdfs/' + fname, 'rb')
interpreter = PDFPageInterpreter(rsrcmgr, device)
for page in PDFPage.get_pages(fp,
pagenos,
maxpages=maxpages,
password=password,
caching=caching,
check_extractable=True):
page.rotate = (page.rotate + rotation) % 360
interpreter.process_page(page)
fp.close()
device.close()
outfp.close()
#read converted file
y = open("inputs/" + sys.argv[1].replace(' ', '')[:-4] + '.txt', "r")
output = brl.translate(y.read())
#convert into Grade 2 Braille unicode
x = brl.toUnicodeSymbols(output, flatten=True)
#save to results folder in .txt format
text_file = open(
"results/" + sys.argv[1].replace(' ', '')[:-4] + "-Braille.txt", "w")
text_file.write(x.encode(codec))
text_file.close()