Upload clean_inline_tags_file.py with huggingface_hub
Browse files- clean_inline_tags_file.py +16 -0
clean_inline_tags_file.py
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
def clean_inline_tag_file(input_file, output_file):
|
| 2 |
+
with open(input_file, 'r', encoding='utf-8') as infile, open(output_file, 'w', encoding='utf-8') as outfile:
|
| 3 |
+
for line in infile:
|
| 4 |
+
# Split by tabs and ensure at least two elements are present
|
| 5 |
+
parts = line.strip().split('\t')
|
| 6 |
+
if len(parts) >= 2:
|
| 7 |
+
# Extract source and target removing language tags
|
| 8 |
+
source = parts[0].split(': ')[-1]
|
| 9 |
+
target = parts[1].split(': ')[-1]
|
| 10 |
+
# Write the cleaned pair to the output file
|
| 11 |
+
outfile.write(f"{source}\t{target}\n")
|
| 12 |
+
|
| 13 |
+
# Example usage
|
| 14 |
+
input_file = '/home/vikrant-MNMT/myenv/NMT_V2/important_files/date_tags.txt' # Replace with actual input file path
|
| 15 |
+
output_file = '/home/vikrant-MNMT/myenv/BPCC/inline_tages/eng_Latn-hin_Deva/date_tag_cleaned.txt' # Replace with desired output file path
|
| 16 |
+
clean_inline_tag_file(input_file, output_file)
|