From 56c38484a1a3ca1625a455985a3272057823abbd Mon Sep 17 00:00:00 2001 From: Adriane Boyd Date: Wed, 28 Aug 2019 09:16:40 +0200 Subject: [PATCH] Single and paired orth variants for English --- spacy/lang/en/__init__.py | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/spacy/lang/en/__init__.py b/spacy/lang/en/__init__.py index 7d00c749c..2f391de0b 100644 --- a/spacy/lang/en/__init__.py +++ b/spacy/lang/en/__init__.py @@ -38,6 +38,10 @@ class EnglishDefaults(Language.Defaults): "lemma_index": "lemmatizer/lemma_index.json", "lemma_exc": "lemmatizer/lemma_exc.json", } + single_orth_variants = [{"tags": ["NFP"], "variants": ["…", "..."]}, + {"tags": [":"], "variants": ["-", "—", "–", "--", "---", "——"]}] + paired_orth_variants = [{"tags": ["``", "''"], "variants": [("'", "'"), ("‘", "’")]}, + {"tags": ["``", "''"], "variants": [('"', '"'), ("“", "”")]}] class English(Language):