From f762d52b2419e1388229d64753f40fc5351ced39 Mon Sep 17 00:00:00 2001
From: Matthew Honnibal <honnibal+gh@gmail.com>
Date: Sun, 5 Aug 2018 13:33:52 +0200
Subject: [PATCH] Add example for Issue #2627

---
 .../pipeline/custom_sentence_segmentation.py  | 48 +++++++++++++++++++
 1 file changed, 48 insertions(+)
 create mode 100644 examples/pipeline/custom_sentence_segmentation.py

diff --git a/examples/pipeline/custom_sentence_segmentation.py b/examples/pipeline/custom_sentence_segmentation.py
new file mode 100644
index 000000000..d4f8aee63
--- /dev/null
+++ b/examples/pipeline/custom_sentence_segmentation.py
@@ -0,0 +1,48 @@
+'''Example of adding a pipeline component to prohibit sentence boundaries
+before certain tokens.
+
+What we do is write to the token.is_sent_start attribute, which
+takes values in {True, False, None}. The default value None allows the parser
+to predict sentence segments. The value False prohibits the parser from inserting
+a sentence boundary before that token. Note that fixing the sentence segmentation
+should also improve the parse quality.
+
+The specific example here is drawn from https://github.com/explosion/spaCy/issues/2627
+Other versions of the model may not make the original mistake, so the specific
+example might not be apt for future versions.
+'''
+import plac
+import spacy
+
+def prevent_sentence_boundaries(doc):
+    for token in doc:
+        if not can_be_sentence_start(token):
+            token.is_sent_start = False
+    return doc
+
+def can_be_sentence_start(token):
+    if token.i == 0:
+        return True
+    elif token.is_title:
+        return True
+    elif token.nbor(-1).is_punct:
+        return True
+    elif token.nbor(-1).is_space:
+        return True
+    else:
+        return False
+
+def main():
+    nlp = spacy.load('en_core_web_lg')
+    raw_text = "Been here and I'm loving it."
+    doc = nlp(raw_text)
+    sentences = [sent.string.strip() for sent in doc.sents]
+    print(sentences)
+    nlp.add_pipe(prevent_sentence_boundaries, before='parser')
+    doc = nlp(raw_text)
+    sentences = [sent.string.strip() for sent in doc.sents]
+    print(sentences)
+ 
+    
+if __name__ == '__main__':
+    plac.call(main)