Skip to content
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

Jump to bottom

Add pattrens to normalize common errors #26

Merged
merged 2 commits into from
Aug 22, 2024
Merged

Add pattrens to normalize common errors #26

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
06af6b5
Clean up rules and test cases for common errors
kavyamanohar Aug 22, 2024
91716b8
Merge branch 'libindic:master' into master
kavyamanohar Aug 22, 2024
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
6 changes: 3 additions & 3 deletions libindic/normalizer/rules/normalizer.ml.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,9 +33,9 @@ common_mistakes: # For common mistakes
'([^\s]+)‌$': '\1' # Remove ZWNJ at the end of the string
'(ൺ|ൻ|ർ|ൽ|ൾ|ൿ|ൔ|ൕ|ൖ)‌': '\1' # Remove ZWNJ after any of the chillu characters
'\u200D': '' # Remove all ZWJ characters
'ര്(?!$)(?!യ)(?![\s{PUNCTUATION}])': 'ർ' # Replace ര് with ർ when not at word end, string end and not followed by യ
'റ്(?!$)(?!റ)(?![\s{PUNCTUATION}])': 'ർ' # Replace ര് with ർ when not at word end, string end and not followed by യ
'ള്(?!$)(?!ള)(?![\s{PUNCTUATION}])': 'ൾ' # Replace ള് with ൾ when not at word end, string end and not followed by ള
'ര്(?![\s{PUNCTUATION}]|യ|$)': 'ർ' # Replace ര് with ർ when not at word end, string end and not followed by യ
'റ്(?![\s{PUNCTUATION}\u200c]|യ|വ|ല|ര|റ|$)': 'ർ' # Replace റ് with ർ when not at word end, string end and not followed by റ, ര, വ, ല, യ
'ള്(?![\s{PUNCTUATION}]|ള|$)': 'ൾ' # Replace ള് with ൾ when not at word end, string end and not followed by ള
'ദു:ഖ': 'ദുഃഖ' # Common Mistake
'നമ:': 'നമഃ' # Remove all ZWJ characters
'ററ': 'റ്റ' # To correct പൂമ്പാററ. Fails for കണ്ടംപററി
Expand Down
5 changes: 4 additions & 1 deletion libindic/normalizer/tests/test_normalizer.py
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,5 @@
#!/usr/bin/env python
# -*- coding: utf-8 -*-

from testtools import TestCase

from .. import Normalizer
Expand Down Expand Up @@ -46,6 +45,9 @@ def test_normalize(self):
self.assertEqual(normalize('അവൻ‌'), 'അവൻ')
self.assertEqual(normalize('കൺ‌മണി'), 'കൺമണി')
self.assertEqual(normalize('ഹാർഡ്‌വെയർ‌'), 'ഹാർഡ്‌വെയർ')
self.assertEqual(normalize('സോഫ്റ്റ്‍വെയർ'), 'സോഫ്റ്റ്വെയർ') #soft_ware written with an zwj, before ware gets removed.
self.assertEqual(normalize('ആറ്റ്‌ലി'), 'ആറ്റ്‌ലി')
self.assertEqual(normalize('ഇൻസ്റ്റിറ്റ്യൂട്ട്'), 'ഇൻസ്റ്റിറ്റ്യൂട്ട്')
self.assertEqual(normalize('കാല്‍‍പനികം'), 'കാൽപനികം')
self.assertEqual(normalize('അവര്ക്ക്'), 'അവർക്ക്')
self.assertEqual(normalize('അവര്'), 'അവര്')
Expand All @@ -57,6 +59,7 @@ def test_normalize(self):
self.assertEqual(normalize('കാറ്'), 'കാറ്')
self.assertEqual(normalize('കാറ് '), 'കാറ് ')
self.assertEqual(normalize('പൂമ്പാററ'), 'പൂമ്പാറ്റ')
self.assertEqual(normalize('കാറ്റ്'), 'കാറ്റ്')
self.assertEqual(normalize('ദു:ഖത്തിന്റെ'), 'ദുഃഖത്തിന്റെ')
self.assertEqual(normalize('ദു:ഖത്തിന്റെ', keep_punctuations=True),
'ദുഃഖത്തിന്റെ')
Expand Down
Loading