Don't copy exception dicts if not necessary and tidy up

spacy/lang/bn/tokenizer_exceptions.py

@@ -23,4 +23,4 @@ for exc_data in [
     _exc[exc_data[ORTH]] = [dict(exc_data)]
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/da/tokenizer_exceptions.py

@@ -30,4 +30,4 @@ for orth in [
     _exc[orth] = [{ORTH: orth}]
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/de/tokenizer_exceptions.py

@@ -181,4 +181,4 @@ for orth in [
     _exc[orth] = [{ORTH: orth}]
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/en/tokenizer_exceptions.py

@@ -456,4 +456,4 @@ for string in _exclude:
         _exc.pop(string)
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/es/tokenizer_exceptions.py

@@ -54,4 +54,4 @@ for orth in [
     _exc[orth] = [{ORTH: orth}]
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/fi/tokenizer_exceptions.py

@@ -76,4 +76,4 @@ for exc_data in [
     _exc[exc_data[ORTH]] = [dict(exc_data)]
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/fr/tokenizer_exceptions.py

@@ -147,5 +147,5 @@ _regular_exp += ["^{prefix}[{elision}][{alpha}][{alpha}{elision}{hyphen}\-]*$".f
 _regular_exp.append(URL_PATTERN)
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc
 TOKEN_MATCH = re.compile('|'.join('(?:{})'.format(m) for m in _regular_exp), re.IGNORECASE).match

spacy/lang/hu/tokenizer_exceptions.py

@@ -95,5 +95,5 @@ _nums = "(({ne})|({t})|({on})|({c}))({s})?".format(
     c=CURRENCY, s=_suffixes)
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc
 TOKEN_MATCH = re.compile("^({u})|({n})$".format(u=URL_PATTERN, n=_nums)).match

spacy/lang/id/tokenizer_exceptions.py

@@ -46,5 +46,4 @@ for orth in [
     ]:
     _exc[orth] = [{ORTH: orth}]
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc
-

spacy/lang/nb/tokenizer_exceptions.py

@@ -35,4 +35,4 @@ for orth in [
     _exc[orth] = [{ORTH: orth}]
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/pl/tokenizer_exceptions.py

@@ -20,4 +20,4 @@ for orth in [
     _exc[orth] = [{ORTH: orth}]
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/pt/tokenizer_exceptions.py

@@ -72,4 +72,4 @@ for orth in [
     _exc[orth] = [{ORTH: orth}]
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/sv/tokenizer_exceptions.py

@@ -80,4 +80,4 @@ for orth in [
     _exc[orth] = [{ORTH: orth}]
 
 
-TOKENIZER_EXCEPTIONS = dict(_exc)
+TOKENIZER_EXCEPTIONS = _exc

spacy/lang/th/tag_map.py

@@ -2,10 +2,10 @@
 # data from Korakot Chaovavanich (https://www.facebook.com/photo.php?fbid=390564854695031&set=p.390564854695031&type=3&permPage=1&ifg=1)
 from __future__ import unicode_literals
 
-from ...symbols import *
+from ...symbols import POS, NOUN, PRON, ADJ, ADV, INTJ, PROPN, DET, NUM, AUX
-
+from ...symbols import ADP, CCONJ, PART, PUNCT, SPACE, SCONJ
 TAG_MAP = {
-    #NOUN
+    # NOUN
     "NOUN":     {POS: NOUN},
     "NCMN":     {POS: NOUN},
     "NTTL":     {POS: NOUN},
@@ -14,7 +14,7 @@ TAG_MAP = {
     "CMTR":     {POS: NOUN},
     "CFQC":     {POS: NOUN},
     "CVBL":     {POS: NOUN},
-    #PRON
+    # PRON
     "PRON":     {POS: PRON},
     "NPRP":     {POS: PRON},
     # ADJ
@@ -28,7 +28,7 @@ TAG_MAP = {
     "ADVI":     {POS: ADV},
     "ADVP":     {POS: ADV},
     "ADVS":     {POS: ADV},
-	# INT
+    # INT
     "INT":      {POS: INTJ},
     # PRON
     "PROPN":    {POS: PROPN},
@@ -50,20 +50,20 @@ TAG_MAP = {
     "NCNM":     {POS: NUM},
     "NLBL":     {POS: NUM},
     "DCNM":     {POS: NUM},
-	# AUX
+    # AUX
     "AUX":      {POS: AUX},
     "XVBM":     {POS: AUX},
     "XVAM":     {POS: AUX},
     "XVMM":     {POS: AUX},
     "XVBB":     {POS: AUX},
     "XVAE":     {POS: AUX},
-	# ADP
+    # ADP
     "ADP":      {POS: ADP},
     "RPRE":     {POS: ADP},
     # CCONJ
     "CCONJ":    {POS: CCONJ},
     "JCRG":     {POS: CCONJ},
-	# SCONJ
+    # SCONJ
     "SCONJ":    {POS: SCONJ},
     "PREL":     {POS: SCONJ},
     "JSBR":     {POS: SCONJ},

spacy/lang/th/tokenizer_exceptions.py

@@ -1,43 +1,23 @@
 # encoding: utf8
 from __future__ import unicode_literals
 
-from ...symbols import *
+from ...symbols import ORTH, LEMMA
 
-TOKENIZER_EXCEPTIONS = {
+
-    "ม.ค.": [
+_exc = {
-        {ORTH: "ม.ค.", LEMMA: "มกราคม"}
+    "ม.ค.": [{ORTH: "ม.ค.", LEMMA: "มกราคม"}],
-    ],
+    "ก.พ.": [{ORTH: "ก.พ.", LEMMA: "กุมภาพันธ์"}],
-    "ก.พ.": [
+    "มี.ค.": [{ORTH: "มี.ค.", LEMMA: "มีนาคม"}],
-        {ORTH: "ก.พ.", LEMMA: "กุมภาพันธ์"}
+    "เม.ย.": [{ORTH: "เม.ย.", LEMMA: "เมษายน"}],
-    ],
+    "พ.ค.": [{ORTH: "พ.ค.", LEMMA: "พฤษภาคม"}],
-    "มี.ค.": [
+    "มิ.ย.": [{ORTH: "มิ.ย.", LEMMA: "มิถุนายน"}],
-        {ORTH: "มี.ค.", LEMMA: "มีนาคม"}
+    "ก.ค.": [{ORTH: "ก.ค.", LEMMA: "กรกฎาคม"}],
-    ],
+    "ส.ค.": [{ORTH: "ส.ค.", LEMMA: "สิงหาคม"}],
-    "เม.ย.": [
+    "ก.ย.": [{ORTH: "ก.ย.", LEMMA: "กันยายน"}],
-        {ORTH: "เม.ย.", LEMMA: "เมษายน"}
+    "ต.ค.": [{ORTH: "ต.ค.", LEMMA: "ตุลาคม"}],
-    ],
+    "พ.ย.": [{ORTH: "พ.ย.", LEMMA: "พฤศจิกายน"}],
-    "พ.ค.": [
+    "ธ.ค.": [{ORTH: "ธ.ค.", LEMMA: "ธันวาคม"}]
-        {ORTH: "พ.ค.", LEMMA: "พฤษภาคม"}
-    ],
-    "มิ.ย.": [
-        {ORTH: "มิ.ย.", LEMMA: "มิถุนายน"}
-    ],
-    "ก.ค.": [
-        {ORTH: "ก.ค.", LEMMA: "กรกฎาคม"}
-    ],
-    "ส.ค.": [
-        {ORTH: "ส.ค.", LEMMA: "สิงหาคม"}
-    ],
-    "ก.ย.": [
-        {ORTH: "ก.ย.", LEMMA: "กันยายน"}
-    ],
-    "ต.ค.": [
-        {ORTH: "ต.ค.", LEMMA: "ตุลาคม"}
-    ],
-    "พ.ย.": [
-        {ORTH: "พ.ย.", LEMMA: "พฤศจิกายน"}
-    ],
-    "ธ.ค.": [
-        {ORTH: "ธ.ค.", LEMMA: "ธันวาคม"}
-    ]
 }
+
+
+TOKENIZER_EXCEPTIONS = _exc