From 10c930cc96b731d88f78998248d54dfe2bfd8934 Mon Sep 17 00:00:00 2001
From: Adriane Boyd <adrianeboyd@gmail.com>
Date: Fri, 26 Feb 2021 09:48:14 +0100
Subject: [PATCH] Re-refactor Sentencizer with Pipe API (#7176)

Reapply the refactoring (#4721) so that `Sentencizer` uses the faster
`predict` and `set_annotations` for both `__call__` and `pipe`.
---
 spacy/pipeline/sentencizer.pyx | 18 ++----------------
 1 file changed, 2 insertions(+), 16 deletions(-)

diff --git a/spacy/pipeline/sentencizer.pyx b/spacy/pipeline/sentencizer.pyx
index b10cdd8e8..60102efcb 100644
--- a/spacy/pipeline/sentencizer.pyx
+++ b/spacy/pipeline/sentencizer.pyx
@@ -66,26 +66,12 @@ class Sentencizer(Pipe):
         """
         error_handler = self.get_error_handler()
         try:
-            self._call(doc)
+            tags = self.predict([doc])
+            self.set_annotations([doc], tags)
             return doc
         except Exception as e:
             error_handler(self.name, self, [doc], e)
 
-    def _call(self, doc):
-        start = 0
-        seen_period = False
-        for i, token in enumerate(doc):
-            is_in_punct_chars = token.text in self.punct_chars
-            token.is_sent_start = i == 0
-            if seen_period and not token.is_punct and not is_in_punct_chars:
-                doc[start].is_sent_start = True
-                start = token.i
-                seen_period = False
-            elif is_in_punct_chars:
-                seen_period = True
-        if start < len(doc):
-            doc[start].is_sent_start = True
-
     def predict(self, docs):
         """Apply the pipe to a batch of docs, without modifying them.