PyRuSH 1.0.9__tar.gz → 1.0.10.dev0__tar.gz

{PyRuSH-1.0.9 → pyrush-1.0.10.dev0}/MANIFEST.in

@@ -1,3 +1,4 @@
+include LICENSE
 include conf/rush_rules.tsv
 include PyRuSH/StaticSentencizerFun.pyx
 include requirements.txt

{PyRuSH-1.0.9 → pyrush-1.0.10.dev0}/PKG-INFO

@@ -1,39 +1,26 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.4
 Name: PyRuSH
-Version: 1.0.9
+Version: 1.0.10.dev0
 Summary: PyRuSH is the python implementation of RuSH (Rule-based sentence Segmenter using Hashing), which is originally developed using Java. RuSH is an efficient, reliable, and easy adaptable rule-based sentence segmentation solution. It is specifically designed to handle the telegraphic written text in clinical note. It leverages a nested hash table to execute simultaneous rule processing, which reduces the impact of the rule-base growth on execution time and eliminates the effect of rule order on accuracy.
 Home-page: https://github.com/jianlins/PyRuSH
 Author: Jianlin
 Author-email: Jianlin <jianlinshi.cn@gmail.com>
-License: MIT License
-        
-        Copyright (c) 2020 Jianlin Shi
-        
-        Permission is hereby granted, free of charge, to any person obtaining a copy
-        of this software and associated documentation files (the "Software"), to deal
-        in the Software without restriction, including without limitation the rights
-        to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-        copies of the Software, and to permit persons to whom the Software is
-        furnished to do so, subject to the following conditions:
-        
-        The above copyright notice and this permission notice shall be included in all
-        copies or substantial portions of the Software.
-        
-        THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-        IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-        FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-        AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-        LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-        OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-        SOFTWARE.
-        
+License-Expression: MIT
 Project-URL: Source, https://github.com/jianlins/PyRuSH
 Keywords: PyRuSH,NLP,sentenczier,sentence segmentation
-Classifier: License :: OSI Approved :: MIT License
 Classifier: Programming Language :: Python :: 3
 Requires-Python: >=3.6
 Description-Content-Type: text/x-rst
 License-File: LICENSE
+Requires-Dist: Cython
+Requires-Dist: setuptools
+Requires-Dist: spacy<3.8; python_version < "3.12"
+Requires-Dist: spacy>=3.8; python_version >= "3.12"
+Requires-Dist: PyFastNER>=1.0.8
+Requires-Dist: quicksectx>=0.3.5
+Dynamic: author
+Dynamic: home-page
+Dynamic: license-file
 
 PyRuSH
 =========

{PyRuSH-1.0.9 → pyrush-1.0.10.dev0}/PyRuSH/PyRuSHSentencizer.py

@@ -19,13 +19,13 @@ from spacy import Language
 from spacy.pipeline import Sentencizer
 
 from .RuSH import RuSH
-from .StaticSentencizerFun import cpredict, cset_annotations
+from .StaticSentencizerFun import cpredict_merge_gaps,cpredict_split_gaps, cset_annotations
 
 
 @Language.factory("medspacy_pyrush")
 class PyRuSHSentencizer(Sentencizer):
     def __init__(self, nlp: Language, name: str = "medspacy_pyrush", rules_path: str = '', max_repeat: int = 50,
-                 auto_fix_gaps: bool = True) -> Sentencizer:
+                 auto_fix_gaps: bool = True, merge_gaps: bool = False) -> Sentencizer:
         """
 
         @param rules_path: The string of the rule file path or rules themselves. By default, it will look for
@@ -33,7 +33,8 @@ class PyRuSHSentencizer(Sentencizer):
         @param max_repeat: Total number of replicates that allows to be handled by "+" wildcard.
         @param auto_fix_gaps: If gaps are caused by malcrafted rules, try to fix them.
             However, this has no control of sentence end,
-             TODO: need to see how the downsteam spacy components make use of doc.c
+        @param merge_gaps: When True, gaps between sentences are merged into the preceding sentence.
+            When False, gaps are split into separate sentences.
         """
         self.nlp = nlp
         self.name = name
@@ -43,6 +44,7 @@ class PyRuSHSentencizer(Sentencizer):
             rules_path = str(os.path.join(root, 'conf', 'rush_rules.tsv'))
         self.rules_path = rules_path
         self.rush = RuSH(rules=rules_path, max_repeat=max_repeat, auto_fix_gaps=auto_fix_gaps)
+        self.merge_gaps = merge_gaps
 
     @classmethod
     def from_nlp(cls, nlp, **cfg):
@@ -57,7 +59,11 @@ class PyRuSHSentencizer(Sentencizer):
         """Apply the pipeline's model to a batch of docs, without
         modifying them.
         """
-        guesses = cpredict(docs, self.rush.segToSentenceSpans)
+        if self.merge_gaps:
+            from .StaticSentencizerFun import cpredict_ww
+            guesses = cpredict_merge_gaps(docs, self.rush.segToSentenceSpans)
+        else:
+            guesses = cpredict_split_gaps(docs, self.rush.segToSentenceSpans)
         return guesses
 
     def set_annotations(self, docs, batch_tag_ids, tensors=None):