🐛 Fix scanlists (#28)

🐛  Fix scanlists

Author: nipunsadvilkar

CHANGELOG.md

@@ -1,4 +1,12 @@
+# v0.1.0
 
+-   Initial Release
 
-# v0.0.1
-* Initial Release
+# v0.1.1
+
+-   English language support only
+-   Support for oother languages - WIP
+
+# v0.1.2
+
+-   🐛BugFix - IndexError of `scanlists` function

pysbd/about.py

@@ -2,7 +2,7 @@
 # https://python-packaging-user-guide.readthedocs.org/en/latest/single_source_version/
 
 __title__ = "pysbd"
-__version__ = "0.1.1"
+__version__ = "0.1.2"
 __summary__ = "pysbd (Python Sentence Boundary Disambiguation) is a rule-based sentence boundary detection that works out-of-the-box across many languages."
 __uri__ = "http://nipunsadvilkar.github.io/"
 __author__ = "Nipun Sadvilkar"

pysbd/lists_item_replacer.py

@@ -122,7 +122,7 @@ def scan_lists(self, regex1, regex2, replacement, strip=False):
             elif ind > 0:
                 if (((item - 1) == list_array[ind - 1]) or
                     ((item == 0) and (list_array[ind - 1] == 9)) or
-                    ((item == 9) and (list_array[ind + 1] == 0))):
+                    ((item == 9) and (list_array[ind - 1] == 0))):
                     self.substitute_found_list_items(regex2, item, strip, replacement)
 
     def substitute_found_list_items(self, regex, each, strip, replacement):

pysbd/segmenter.py

@@ -23,7 +23,7 @@ def segment(self, text):
 
 
 if __name__ == "__main__":
-    text = "Saint Maximus (died 250) is a Christian saint and martyr.[1] The emperor Decius published a decree ordering the veneration of busts of the deified emperors."
+    text = "This new form of generalized PDF in (9) is generic and suitable for all the fading models presented in Table I withbranches MRC reception. In section III, (9) will be used in the derivations of the unified ABER and ACC expression."
     # ["Saint Maximus (died 250) is a Christian saint and martyr.[1]", "The emperor Decius published a decree ordering the veneration of busts of the deified emperors."
     print("Input String:\n{}".format(text))
     seg = Segmenter(language="en", clean=True)