Skip to content

english date fixed #21

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
tisbuet wants to merge 2 commits into
base: main
Choose a base branch
from
Open

english date fixed #21

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
a806ef9
english date fixed
tisbuet Nov 24, 2025
d4b5ebe
eval script updated
tisbuet Nov 25, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1,2 @@
*.pyc
*.~lock*
4 changes: 2 additions & 2 deletions pybangla/eval_pybangla_3.0.x.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -69,8 +69,8 @@ def evaluate_normalization(data, output_path):
normalized_text = nrml.text_normalizer(input_text, all_operation=True)

# remove punctuation
# reviewed_text = re.sub(r"[।,!?]", "", str(reviewed_text))
# normalized_text = re.sub(r"[।,!?]", "", normalized_text)
reviewed_text = re.sub(r"[।,!?]", "", str(reviewed_text))
normalized_text = re.sub(r"[।,!?]", "", normalized_text)

print("\nInput Text: ", input_text)
print("Reviewed Text: ", reviewed_text)
Expand Down
19 changes: 8 additions & 11 deletions pybangla/module/parser.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -367,6 +367,10 @@ def number_to_words_converting_process(self, number_string: str, lang="bn"):
return

def number_to_words(self, number: str, chunk_millions=7, language="bn"):
english_status = self.contains_only_english(number)
if english_status:
language = "en"

en_extraction = list(re.finditer(self.en_regex, number, re.UNICODE))
# print("en_extraction : ", en_extraction[1])
# print("number_to_words : ", number, language)
Expand All @@ -391,7 +395,6 @@ def number_to_words(self, number: str, chunk_millions=7, language="bn"):
[self.number_to_words_converting_process(chunk, lang="bn") for chunk in chunks]
)
number = number.replace("শূন্য", "")

return (" ".join(number.split())).replace(" শো", "শো")

def digit_number_to_digit_word(self, number, language="bn"):
Expand Down Expand Up @@ -422,28 +425,22 @@ def year_in_number(self, year_in_number: str, language="bn"):
english_status = self.contains_only_english(year_in_number)
# print("english_status : ", english_status)
if english_status:
year_in_number = "".join(
[cfg._english2bangla2_digits_mapping[i] for i in year_in_number]
)
language = "en"

# print("year_in_number : ", year_in_number)
if language == "bn":
mid_text = "শো "
else:
mid_text = " century "
mid_text = " "

if (len(year_in_number) == 4 and year_in_number[1] != "০") or len(year_in_number) == 3:
# print("year in ")

if year_in_number[1] != "0":
year_str = self.number_to_words(year_in_number)
return (
self.number_to_words(year_in_number[:-2])
+ mid_text
+ self.number_to_words(year_in_number[-2:])
)

else:
# print("+++++++++ else+++++++++++++++")
return self.number_to_words(year_in_number)

def _replace_starting_zero(self, month):
Expand Down Expand Up @@ -1735,7 +1732,7 @@ def replace_date_processing(self, text):
word_date_string = date_string.replace(str(year), word_year)
word_date_string = word_date_string.replace(str(day), day_word)
original_text = original_text.replace(date, word_date_string)
# print(n_status, r_date)
if n_status == False:
continue

Expand Down