From 819e30a26ef65c070676d903e6bcc52fdb04cba1 Mon Sep 17 00:00:00 2001
From: ines <ines@ines.io>
Date: Wed, 1 Nov 2017 23:02:45 +0100
Subject: [PATCH] Tidy up tokenizer exceptions

---
 spacy/lang/bn/tokenizer_exceptions.py | 2 +-
 spacy/lang/da/tokenizer_exceptions.py | 3 +--
 spacy/lang/de/tokenizer_exceptions.py | 2 +-
 spacy/lang/en/tokenizer_exceptions.py | 4 ++--
 spacy/lang/es/tokenizer_exceptions.py | 2 +-
 spacy/lang/fi/tokenizer_exceptions.py | 2 +-
 spacy/lang/fr/tokenizer_exceptions.py | 2 +-
 spacy/lang/nb/tokenizer_exceptions.py | 2 +-
 spacy/lang/pl/tokenizer_exceptions.py | 2 +-
 spacy/lang/sv/tokenizer_exceptions.py | 2 +-
 spacy/lang/tokenizer_exceptions.py    | 2 +-
 11 files changed, 12 insertions(+), 13 deletions(-)

diff --git a/spacy/lang/bn/tokenizer_exceptions.py b/spacy/lang/bn/tokenizer_exceptions.py
index 5c6de139b..dc1181335 100644
--- a/spacy/lang/bn/tokenizer_exceptions.py
+++ b/spacy/lang/bn/tokenizer_exceptions.py
@@ -20,7 +20,7 @@ for exc_data in [
     {ORTH: "সে.মি.", LEMMA: "সেন্টিমিটার"},
     {ORTH: "সে.মি", LEMMA: "সেন্টিমিটার"},
     {ORTH: "মি.লি.", LEMMA: "মিলিলিটার"}]:
-    _exc[exc_data[ORTH]] = [dict(exc_data)]
+    _exc[exc_data[ORTH]] = [exc_data]
 
 
 TOKENIZER_EXCEPTIONS = _exc
diff --git a/spacy/lang/da/tokenizer_exceptions.py b/spacy/lang/da/tokenizer_exceptions.py
index e8edf36b8..c67c038bf 100644
--- a/spacy/lang/da/tokenizer_exceptions.py
+++ b/spacy/lang/da/tokenizer_exceptions.py
@@ -8,7 +8,6 @@ _exc = {}
 
 for exc_data in [
     {ORTH: "Kbh.", LEMMA: "København", NORM: "København"},
-
     {ORTH: "Jan.", LEMMA: "januar", NORM: "januar"},
     {ORTH: "Feb.", LEMMA: "februar", NORM: "februar"},
     {ORTH: "Mar.", LEMMA: "marts", NORM: "marts"},
@@ -21,7 +20,7 @@ for exc_data in [
     {ORTH: "Okt.", LEMMA: "oktober", NORM: "oktober"},
     {ORTH: "Nov.", LEMMA: "november", NORM: "november"},
     {ORTH: "Dec.", LEMMA: "december", NORM: "december"}]:
-    _exc[exc_data[ORTH]] = [dict(exc_data)]
+    _exc[exc_data[ORTH]] = [exc_data]
 
 for orth in [
     "A/S", "beg.", "bl.a.", "ca.", "d.s.s.", "dvs.", "f.eks.", "fr.", "hhv.",
diff --git a/spacy/lang/de/tokenizer_exceptions.py b/spacy/lang/de/tokenizer_exceptions.py
index 0b23a1001..cb16fb06c 100644
--- a/spacy/lang/de/tokenizer_exceptions.py
+++ b/spacy/lang/de/tokenizer_exceptions.py
@@ -164,7 +164,7 @@ for exc_data in [
     {ORTH: "z.b.", LEMMA: "zum Beispiel"},
     {ORTH: "zzgl.", LEMMA: "zuzüglich"},
     {ORTH: "österr.", LEMMA: "österreichisch", NORM: "österreichisch"}]:
-    _exc[exc_data[ORTH]] = [dict(exc_data)]
+    _exc[exc_data[ORTH]] = [exc_data]
 
 
 for orth in [
diff --git a/spacy/lang/en/tokenizer_exceptions.py b/spacy/lang/en/tokenizer_exceptions.py
index 0e5bbc7f6..a76b5fb2b 100644
--- a/spacy/lang/en/tokenizer_exceptions.py
+++ b/spacy/lang/en/tokenizer_exceptions.py
@@ -276,7 +276,7 @@ for exc_data in [
     exc_data_apos = dict(exc_data)
     exc_data_apos[ORTH] = "'" + exc_data_apos[ORTH]
     for data in [exc_data, exc_data_apos]:
-        _exc[data[ORTH]] = [dict(data)]
+        _exc[data[ORTH]] = [data]
 
 
 # Times
@@ -440,7 +440,7 @@ for exc_data in [
     {ORTH: "Va.", LEMMA: "Virginia", NORM: "Virginia"},
     {ORTH: "Wash.", LEMMA: "Washington", NORM: "Washington"},
     {ORTH: "Wis.", LEMMA: "Wisconsin", NORM: "Wisconsin"}]:
-    _exc[exc_data[ORTH]] = [dict(exc_data)]
+    _exc[exc_data[ORTH]] = [exc_data]
 
 
 for orth in [
diff --git a/spacy/lang/es/tokenizer_exceptions.py b/spacy/lang/es/tokenizer_exceptions.py
index cb62f008f..d4131ddf6 100644
--- a/spacy/lang/es/tokenizer_exceptions.py
+++ b/spacy/lang/es/tokenizer_exceptions.py
@@ -26,7 +26,7 @@ for exc_data in [
     {ORTH: "Vd.", LEMMA: PRON_LEMMA, NORM: "usted"},
     {ORTH: "Uds.", LEMMA: PRON_LEMMA, NORM: "ustedes"},
     {ORTH: "Vds.", LEMMA: PRON_LEMMA, NORM: "ustedes"}]:
-    _exc[exc_data[ORTH]] = [dict(exc_data)]
+    _exc[exc_data[ORTH]] = [exc_data]
 
 
 # Times
diff --git a/spacy/lang/fi/tokenizer_exceptions.py b/spacy/lang/fi/tokenizer_exceptions.py
index 33e223575..88859fefb 100644
--- a/spacy/lang/fi/tokenizer_exceptions.py
+++ b/spacy/lang/fi/tokenizer_exceptions.py
@@ -73,7 +73,7 @@ for exc_data in [
     {ORTH: "ts.", LEMMA: "toisin sanoen"},
     {ORTH: "vm.", LEMMA: "viimeksi mainittu"},
     {ORTH: "srk.", LEMMA: "seurakunta"}]:
-    _exc[exc_data[ORTH]] = [dict(exc_data)]
+    _exc[exc_data[ORTH]] = [exc_data]
 
 
 TOKENIZER_EXCEPTIONS = _exc
diff --git a/spacy/lang/fr/tokenizer_exceptions.py b/spacy/lang/fr/tokenizer_exceptions.py
index 442b367dd..9994686ac 100644
--- a/spacy/lang/fr/tokenizer_exceptions.py
+++ b/spacy/lang/fr/tokenizer_exceptions.py
@@ -54,7 +54,7 @@ for exc_data in [
     {LEMMA: "degrés", ORTH: "d°"},
     {LEMMA: "saint", ORTH: "St."},
     {LEMMA: "sainte", ORTH: "Ste."}]:
-    _exc[exc_data[ORTH]] = [dict(exc_data)]
+    _exc[exc_data[ORTH]] = [exc_data]
 
 
 for orth in FR_BASE_EXCEPTIONS + ["etc."]:
diff --git a/spacy/lang/nb/tokenizer_exceptions.py b/spacy/lang/nb/tokenizer_exceptions.py
index 1529315ca..764866732 100644
--- a/spacy/lang/nb/tokenizer_exceptions.py
+++ b/spacy/lang/nb/tokenizer_exceptions.py
@@ -11,7 +11,7 @@ for exc_data in [
     {ORTH: "jan.", LEMMA: "januar"},
     {ORTH: "feb.", LEMMA: "februar"},
     {ORTH: "jul.", LEMMA: "juli"}]:
-    _exc[exc_data[ORTH]] = [dict(exc_data)]
+    _exc[exc_data[ORTH]] = [exc_data]
 
 
 for orth in [
diff --git a/spacy/lang/pl/tokenizer_exceptions.py b/spacy/lang/pl/tokenizer_exceptions.py
index fb87ae8a6..6098c2bb6 100644
--- a/spacy/lang/pl/tokenizer_exceptions.py
+++ b/spacy/lang/pl/tokenizer_exceptions.py
@@ -13,7 +13,7 @@ for exc_data in [
     {ORTH: "tzn.", LEMMA: "to znaczy", POS: ADV},
     {ORTH: "tj.", LEMMA: "to jest", POS: ADV},
     {ORTH: "tzw.", LEMMA: "tak zwany", POS: ADJ}]:
-    _exc[exc_data[ORTH]] = [dict(exc_data)],
+    _exc[exc_data[ORTH]] = [exc_data]
 
 for orth in [
     "w.", "r."]:
diff --git a/spacy/lang/sv/tokenizer_exceptions.py b/spacy/lang/sv/tokenizer_exceptions.py
index 0575c3892..64aedf8af 100644
--- a/spacy/lang/sv/tokenizer_exceptions.py
+++ b/spacy/lang/sv/tokenizer_exceptions.py
@@ -68,7 +68,7 @@ for exc_data in [
     {ORTH: "Sön.", LEMMA: "Söndag"},
     {ORTH: "sthlm", LEMMA: "Stockholm"},
     {ORTH: "gbg", LEMMA: "Göteborg"}]:
-    _exc[exc_data[ORTH]] = [dict(exc_data)]
+    _exc[exc_data[ORTH]] = [exc_data]
 
 
 for orth in [
diff --git a/spacy/lang/tokenizer_exceptions.py b/spacy/lang/tokenizer_exceptions.py
index 73ad88d08..89e1b1476 100644
--- a/spacy/lang/tokenizer_exceptions.py
+++ b/spacy/lang/tokenizer_exceptions.py
@@ -68,7 +68,7 @@ for exc_data in [
     {ORTH: "\\n", POS: SPACE},
     {ORTH: "\u2014", POS: PUNCT, LEMMA: "--"},
     {ORTH: "\u00a0", POS: SPACE, LEMMA: "  "}]:
-    BASE_EXCEPTIONS[exc_data[ORTH]] = [dict(exc_data)]
+    BASE_EXCEPTIONS[exc_data[ORTH]] = [exc_data]
 
 
 for orth in [