🐛 Fix consecutive period bug

nipunsadvilkar · nipunsadvilkar · commit f0e71a518895 · 2020-09-11T15:49:15.000+05:30
Reference allenai/scholarphi#114
diff --git a/pysbd/lang/common/common.py b/pysbd/lang/common/common.py
@@ -4,8 +4,9 @@
 
 class Common(object):
 
-    # added special case: r"[。．.！!?].*" to handle intermittent dots, exclamation, etc.
-    SENTENCE_BOUNDARY_REGEX = r"（(?:[^）])*）(?=\s?[A-Z])|「(?:[^」])*」(?=\s[A-Z])|\((?:[^\)]){2,}\)(?=\s[A-Z])|\'(?:[^\'])*[^,]\'(?=\s[A-Z])|\"(?:[^\"])*[^,]\"(?=\s[A-Z])|\“(?:[^\”])*[^,]\”(?=\s[A-Z])|[。．.！!?？].*|\S.*?[。．.！!?？ȸȹ☉☈☇☄]"
+    # added special case: r"[。．.！!? ]{2,}" to handle intermittent dots, exclamation, etc.
+    # r"[。．.！!?] at end to handle single instances of these symbol inputs
+    SENTENCE_BOUNDARY_REGEX = r"（(?:[^）])*）(?=\s?[A-Z])|「(?:[^」])*」(?=\s[A-Z])|\((?:[^\)]){2,}\)(?=\s[A-Z])|\'(?:[^\'])*[^,]\'(?=\s[A-Z])|\"(?:[^\"])*[^,]\"(?=\s[A-Z])|\“(?:[^\”])*[^,]\”(?=\s[A-Z])|[。．.！!?？ ]{2,}|\S.*?[。．.！!?？ȸȹ☉☈☇☄]|[。．.！!?？]"
 
     # # Rubular: http://rubular.com/r/NqCqv372Ix
     QUOTATION_AT_END_OF_SENTENCE_REGEX = r'[!?\.-][\"\'“”]\s{1}[A-Z]'
diff --git a/tests/regression/test_issues.py b/tests/regression/test_issues.py
@@ -64,8 +64,9 @@
 you may copy it, give it away or re-use it under the terms of the this license
 """,
 [('This eBook is for the use of anyone anywhere at no cost\n', 0, 56),
- ('you may copy it, give it away or re-use it under the terms of the this license\n', 56, 135)])
-
+ ('you may copy it, give it away or re-use it under the terms of the this license\n', 56, 135)]),
+('#78', 'Sentence. .. Next sentence. Next next sentence.',
+[('Sentence. ', 0, 10), ('.. ', 10, 13), ('Next sentence. ', 13, 28), ('Next next sentence.', 28, 47)])
 ]
 
 @pytest.mark.parametrize('issue_no,text,expected_sents', TEST_ISSUE_DATA)
