def text_to_bidi(text):
text = normalize_spaces(text)
configured_reshaper = ArabicReshaper(
configuration={'use_unshaped_instead_of_isolated': True})
reshaped_text = configured_reshaper.reshape(text)
bidi_text = get_display(reshaped_text)
return bidi_text
def _draw_textarea(self, canvas: Canvas, op: OrderPosition, order: Order,
o: dict):
font = o['fontfamily']
if o['bold']:
font += ' B'
if o['italic']:
font += ' I'
align_map = {'left': TA_LEFT, 'center': TA_CENTER, 'right': TA_RIGHT}
style = ParagraphStyle(name=uuid.uuid4().hex,
fontName=font,
fontSize=float(o['fontsize']),
leading=float(o['fontsize']),
autoLeading="max",
textColor=Color(o['color'][0] / 255,
o['color'][1] / 255,
o['color'][2] / 255),
alignment=align_map[o['align']])
text = conditional_escape(
self._get_text_content(op, order, o)
or "", ).replace("\n", "<br/>\n")
# reportlab does not support RTL, ligature-heavy scripts like Arabic. Therefore, we use ArabicReshaper
# to resolve all ligatures and python-bidi to switch RTL texts.
configuration = {
'delete_harakat': True,
'support_ligatures': False,
}
reshaper = ArabicReshaper(configuration=configuration)
try:
text = "<br/>".join(
get_display(reshaper.reshape(l)) for l in text.split("<br/>"))
except:
logger.exception('Reshaping/Bidi fixes failed on string {}'.format(
repr(text)))
p = Paragraph(text, style=style)
w, h = p.wrapOn(canvas, float(o['width']) * mm, 1000 * mm)
# p_size = p.wrap(float(o['width']) * mm, 1000 * mm)
ad = getAscentDescent(font, float(o['fontsize']))
canvas.saveState()
# The ascent/descent offsets here are not really proven to be correct, they're just empirical values to get
# reportlab render similarly to browser canvas.
if o.get('downward', False):
canvas.translate(float(o['left']) * mm, float(o['bottom']) * mm)
canvas.rotate(o.get('rotation', 0) * -1)
p.drawOn(canvas, 0, -h - ad[1] / 2)
else:
canvas.translate(
float(o['left']) * mm,
float(o['bottom']) * mm + h)
canvas.rotate(o.get('rotation', 0) * -1)
p.drawOn(canvas, 0, -h - ad[1])
canvas.restoreState()
def _draw_textarea(self, canvas: Canvas, op: OrderPosition, order: Order,
o: dict):
font = o['fontfamily']
if o['bold']:
font += ' B'
if o['italic']:
font += ' I'
align_map = {'left': TA_LEFT, 'center': TA_CENTER, 'right': TA_RIGHT}
style = ParagraphStyle(name=uuid.uuid4().hex,
fontName=font,
fontSize=float(o['fontsize']),
leading=float(o['fontsize']),
autoLeading="max",
textColor=Color(o['color'][0] / 255,
o['color'][1] / 255,
o['color'][2] / 255),
alignment=align_map[o['align']])
text = re.sub(
"<br[^>]*>", "<br/>",
bleach.clean(self._get_text_content(op, order, o) or "",
tags=["br"],
attributes={},
styles=[],
strip=True))
# reportlab does not support RTL, ligature-heavy scripts like Arabic. Therefore, we use ArabicReshaper
# to resolve all ligatures and python-bidi to switch RTL texts.
configuration = {
'delete_harakat': True,
'support_ligatures': False,
}
reshaper = ArabicReshaper(configuration=configuration)
text = "<br/>".join(
get_display(reshaper.reshape(l)) for l in text.split("<br/>"))
p = Paragraph(text, style=style)
p.wrapOn(canvas, float(o['width']) * mm, 1000 * mm)
# p_size = p.wrap(float(o['width']) * mm, 1000 * mm)
ad = getAscentDescent(font, float(o['fontsize']))
p.drawOn(canvas,
float(o['left']) * mm,
float(o['bottom']) * mm - ad[1])
def main():
"""
Description: Main function
"""
# Argument parsing
args = parse_arguments()
# Create the directory if it does not exist.
try:
os.makedirs(args.output_dir)
except OSError as e:
if e.errno != errno.EEXIST:
raise
# Creating word list
if args.dict:
lang_dict = []
if os.path.isfile(args.dict):
with open(args.dict, "r", encoding="utf8", errors="ignore") as d:
lang_dict = [l for l in d.read().splitlines() if len(l) > 0]
else:
sys.exit("Cannot open dict")
else:
lang_dict = load_dict(args.language)
with open('./trdg/dicts/en.txt', 'r', encoding='utf8',
errors='ignore') as f:
en_dict = [i for i in f.read().splitlines() if len(i) > 0]
# Create font (path) list
if args.font_dir:
fonts = [
os.path.join(args.font_dir, p) for p in os.listdir(args.font_dir)
if os.path.splitext(p)[1] == ".ttf"
]
elif args.font:
if os.path.isfile(args.font):
fonts = [args.font]
else:
sys.exit("Cannot open font")
else:
fonts = load_fonts(args.language)
# Creating synthetic sentences (or word)
strings = []
if args.use_wikipedia:
print('use_wikipedia')
strings = create_strings_from_wikipedia(args.length, args.count,
args.language)
elif args.input_file != "":
print('input_file')
strings = create_strings_from_file(args.input_file, args.count)
elif args.random_sequences:
print('random_sequences')
strings = create_strings_randomly(
args.length,
args.random,
args.count,
args.include_letters,
args.include_numbers,
args.include_symbols,
args.language,
)
# Set a name format compatible with special characters automatically if they are used
if args.include_symbols or True not in (
args.include_letters,
args.include_numbers,
args.include_symbols,
):
args.name_format = 2
# else :
# print('create_strings_from_dict')
# strings = create_strings_from_dict(
# args.length,
# args.random,
# args.count,
# lang_dict
# )
else:
print(make_my_strings)
strings = make_my_strings(
args.count,
lang_dict,
en_dict,
)
if args.language == "ar":
from arabic_reshaper import ArabicReshaper
arabic_reshaper = ArabicReshaper()
strings = [
" ".join([arabic_reshaper.reshape(w) for w in s.split(" ")[::-1]])
for s in strings
]
if args.case == "upper":
strings = [x.upper() for x in strings]
if args.case == "lower":
strings = [x.lower() for x in strings]
string_count = len(strings)
p = Pool(args.thread_count)
for _ in tqdm(
p.imap_unordered(
FakeTextDataGenerator.generate_from_tuple,
zip(
[i for i in range(0, string_count)],
strings,
[
fonts[rnd.randrange(0, len(fonts))]
for _ in range(0, string_count)
],
[args.output_dir] * string_count,
[args.format] * string_count,
[args.extension] * string_count,
[args.skew_angle] * string_count,
[args.random_skew] * string_count,
[args.blur] * string_count,
[args.random_blur] * string_count,
[args.background] * string_count,
[args.distorsion] * string_count,
[args.distorsion_orientation] * string_count,
[args.handwritten] * string_count,
[args.name_format] * string_count,
[args.width] * string_count,
[args.alignment] * string_count,
[args.text_color] * string_count,
[args.orientation] * string_count,
[args.space_width] * string_count,
[args.character_spacing] * string_count,
[args.margins] * string_count,
[args.fit] * string_count,
[args.output_mask] * string_count,
[args.word_split] * string_count,
[args.image_dir] * string_count,
),
),
total=args.count,
):
pass
p.terminate()
if args.name_format == 2:
# Create file with filename-to-label connections
with open(os.path.join(args.output_dir, "labels.txt"),
"w",
encoding="utf8") as f:
for i in range(string_count):
file_name = str(i) + "." + args.extension
f.write("{}\t{}\n".format(file_name, strings[i]))
d = "F:\\Current Semester\\FYP\\OASRU_CLEN\\OASRU\\ResultScripts"
configuration = {
'delete_harakat': False,
'support_ligatures': True,
'RIAL SIGN': True, # Replace ر ي ا ل with ﷼
}
reshaper = ArabicReshaper(configuration=configuration)
text_to_be_reshaped = "ترجمان"
text_to_be_reshaped = normalize(text_to_be_reshaped)
text_to_be_reshaped = normalization.normalize_characters(text_to_be_reshaped)
text_to_be_reshaped = normalization.normalize_combine_characters(text_to_be_reshaped)
text_to_be_reshaped = normalization.punctuations_space(text_to_be_reshaped)
nlp = spacy.blank("ur")
reshaped_text = reshaper.reshape(text_to_be_reshaped)
doc = nlp(text_to_be_reshaped)
text = []
for each in doc:
if str(each) not in str(stop_words.STOP_WORDS):
#(each)
text.append(str(each))
reshaped_text = ""
for each in text:
reshaped_text = reshaped_text+" "+each
reshaped_text = reshaper.reshape(reshaped_text)
from bidi.algorithm import get_display
import arabic_reshaper
text_to_be_reshaped = 'اللغة العربية رائعة'
reshaped_text = arabic_reshaper.reshape(text_to_be_reshaped)
print(reshaped_text)
from arabic_reshaper import ArabicReshaper
configuration = {
'delete_harakat': False,
'support_ligatures': True,
'RIAL SIGN': True, # Replace ر ي ا ل with ﷼
}
reshaper = ArabicReshaper(configuration=configuration)
l1='ل'
l2='ا'
l3='ر'
l4='ي'
text_to_be_reshaped = 'ب ﺭ ﻱ ﺕ' # had to split the string for display
reshaped_text = reshaper.reshape(text_to_be_reshaped.replace(' ',''))
print(reshaped_text)
def MyWordCloudGen(imgpath, scriptpath, os):
# d = "F:\\Current Semester\\FYP\\OASRU_CLEN\\OASRU\\ResultScripts"
configuration = {
'delete_harakat': False,
'support_ligatures': True,
'RIAL SIGN': True, # Replace ر ي ا ل with ﷼
}
reshaper = ArabicReshaper(configuration=configuration)
scripts = os.listdir(scriptpath)
scripts.sort(key=lambda x: os.stat(os.path.join(scriptpath, x)).st_mtime)
print((scripts))
text_to_be_reshaped = open(path.join(scriptpath, scripts[1]),
encoding="UTF-8").read()
print(text_to_be_reshaped)
text_to_be_reshaped = normalize(text_to_be_reshaped)
text_to_be_reshaped = normalization.normalize_characters(
text_to_be_reshaped)
text_to_be_reshaped = normalization.normalize_combine_characters(
text_to_be_reshaped)
text_to_be_reshaped = normalization.punctuations_space(text_to_be_reshaped)
nlp = spacy.blank("ur")
reshaped_text = reshaper.reshape(text_to_be_reshaped)
doc = nlp(text_to_be_reshaped)
text = []
for each in doc:
if str(each) not in str(stop_words.STOP_WORDS):
#(each)
text.append(str(each))
reshaped_text = ""
for each in text:
reshaped_text = reshaped_text + " " + each
reshaped_text = reshaper.reshape(reshaped_text)
from bidi.algorithm import get_display
bidi_text = get_display(reshaped_text)
fontdir = "D:\\tarjumaan-master\\Urdu_fonts\\"
import os
plt.figure(figsize=(20, 15), dpi=200)
wordcloud = WordCloud(os.getcwd() + "\\Urdu_fonts\\" +
"DecoType Thuluth.ttf",
width=2000,
height=1500,
include_numbers=True,
stopwords=stop_words.STOP_WORDS,
min_font_size=30,
background_color="black",
margin=0,
max_words=200).generate(bidi_text)
plt.imshow(wordcloud, interpolation='bilinear')
plt.axis("off")
plt.savefig(imgpath + "\\image.png", format="png")
plt.show()
img = imgpath + "\\" + "image.png"
print(img)
print("Relative Path", os.path.relpath(img))
img = os.path.relpath(img)
return img