Improved tokenization for UD_Norwegian-Bokmaal

spacy/lang/nb/__init__.py

@@ -2,6 +2,8 @@
 from __future__ import unicode_literals
 
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+from .punctuation import TOKENIZER_PREFIXES, TOKENIZER_INFIXES
+from .punctuation import TOKENIZER_SUFFIXES
 from .stop_words import STOP_WORDS
 from .morph_rules import MORPH_RULES
 from .syntax_iterators import SYNTAX_ITERATORS
@@ -21,6 +23,9 @@ class NorwegianDefaults(Language.Defaults):
         Language.Defaults.lex_attr_getters[NORM], BASE_NORMS
     )
     tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
+    prefixes = TOKENIZER_PREFIXES
+    infixes = TOKENIZER_INFIXES
+    suffixes = TOKENIZER_SUFFIXES
     stop_words = STOP_WORDS
     morph_rules = MORPH_RULES
     tag_map = TAG_MAP

spacy/lang/nb/punctuation.py

@@ -1,16 +1,33 @@
 # coding: utf8
 from __future__ import unicode_literals
 
-from ..char_classes import LIST_ELLIPSES, LIST_ICONS
+from ..char_classes import LIST_ELLIPSES, LIST_ICONS, LIST_PUNCT, LIST_QUOTES
 from ..char_classes import CONCAT_QUOTES, ALPHA, ALPHA_LOWER, ALPHA_UPPER
-from ..punctuation import TOKENIZER_SUFFIXES
+from ..char_classes import CURRENCY, PUNCT, UNITS, LIST_CURRENCY
 
-# Punctuation stolen from Danish
+
+# Punctuation adapted from Danish
 _quotes = CONCAT_QUOTES.replace("'", "")
+_list_punct = [x for x in LIST_PUNCT if x != "#"]
+_list_icons = [x for x in LIST_ICONS if x != "°"]
+_list_icons = [x.replace("\\u00B0", "") for x in _list_icons]
+_list_quotes = [x for x in LIST_QUOTES if x != "\\'"]
+
+
+_prefixes = (
+    ["§", "%", "=", "—", "–", r"\+(?![0-9])"]
+    + _list_punct
+    + LIST_ELLIPSES
+    + LIST_QUOTES
+    + LIST_CURRENCY
+    + LIST_ICONS
+)
+
+
 
 _infixes = (
     LIST_ELLIPSES
-    + LIST_ICONS
+    + _list_icons
     + [
         r"(?<=[{al}])\.(?=[{au}])".format(al=ALPHA_LOWER, au=ALPHA_UPPER),
         r"(?<=[{a}])[,!?](?=[{a}])".format(a=ALPHA),
@@ -21,13 +38,26 @@ _infixes = (
     ]
 )
 
-_suffixes = [
+_suffixes = (
-    suffix
+    LIST_PUNCT
-    for suffix in TOKENIZER_SUFFIXES
+    + LIST_ELLIPSES
-    if suffix not in ["'s", "'S", "’s", "’S", r"\'"]
+    + _list_quotes
+    + _list_icons
+    + ["—", "–"]
+    + [
+        r"(?<=[0-9])\+",
+        r"(?<=°[FfCcKk])\.",
+        r"(?<=[0-9])(?:{c})".format(c=CURRENCY),
+        r"(?<=[0-9])(?:{u})".format(u=UNITS),
+        r"(?<=[{al}{e}{p}(?:{q})])\.".format(
+            al=ALPHA_LOWER, e=r"%²\-\+", q=_quotes, p=PUNCT
+        ),
+        r"(?<=[{au}][{au}])\.".format(au=ALPHA_UPPER),
     ]
-_suffixes += [r"(?<=[^sSxXzZ])\'"]
+    + [r"(?<=[^sSxXzZ])'"]
+)
 
 
+TOKENIZER_PREFIXES = _prefixes
 TOKENIZER_INFIXES = _infixes
 TOKENIZER_SUFFIXES = _suffixes

spacy/lang/nb/tokenizer_exceptions.py

@@ -24,57 +24,80 @@ for exc_data in [
 
 
 for orth in [
-    "adm.dir.",
+    "Ap.",
-    "a.m.",
-    "andelsnr",
     "Aq.",
+    "Ca.",
+    "Chr.",
+    "Co.",
+    "Co.",
+    "Dr.",
+    "F.eks.",
+    "Fr.p.",
+    "Frp.",
+    "Grl.",
+    "Kr.",
+    "Kr.F.",
+    "Kr.F.s",
+    "Mr.",
+    "Mrs.",
+    "Pb.",
+    "Pr.",
+    "Sp.",
+    "Sp.",
+    "St.",
+    "a.m.",
+    "ad.",
+    "adm.dir.",
+    "andelsnr",
     "b.c.",
     "bl.a.",
     "bla.",
     "bm.",
     "bnr.",
     "bto.",
+    "c.c.",
     "ca.",
     "cand.mag.",
-    "c.c.",
     "co.",
     "d.d.",
-    "dept.",
     "d.m.",
-    "dr.philos.",
-    "dvs.",
     "d.y.",
-    "E. coli",
+    "dept.",
+    "dr.",
+    "dr.med.",
+    "dr.philos.",
+    "dr.psychol.",
+    "dvs.",
+    "e.Kr.",
+    "e.l.",
     "eg.",
     "ekskl.",
-    "e.Kr.",
     "el.",
-    "e.l.",
     "et.",
     "etc.",
     "etg.",
     "ev.",
     "evt.",
     "f.",
+    "f.Kr.",
     "f.eks.",
+    "f.o.m.",
     "fhv.",
     "fk.",
-    "f.Kr.",
-    "f.o.m.",
     "foreg.",
     "fork.",
     "fv.",
     "fvt.",
     "g.",
-    "gt.",
     "gl.",
     "gno.",
     "gnr.",
     "grl.",
+    "gt.",
+    "h.r.adv.",
     "hhv.",
     "hoh.",
     "hr.",
-    "h.r.adv.",
     "ifb.",
     "ifm.",
     "iht.",
@@ -83,39 +106,45 @@ for orth in [
     "jf.",
     "jr.",
     "jun.",
+    "juris.",
     "kfr.",
+    "kgl.",
     "kgl.res.",
     "kl.",
     "komm.",
     "kr.",
     "kst.",
+    "lat.",
     "lø.",
+    "m.a.o.",
+    "m.fl.",
+    "m.m.",
+    "m.v.",
     "ma.",
     "mag.art.",
-    "m.a.o.",
     "md.",
     "mfl.",
+    "mht.",
     "mill.",
     "min.",
-    "m.m.",
     "mnd.",
     "moh.",
-    "Mr.",
+    "mrd.",
     "muh.",
     "mv.",
     "mva.",
+    "n.å.",
     "ndf.",
     "no.",
     "nov.",
     "nr.",
     "nto.",
     "nyno.",
-    "n.å.",
     "o.a.",
+    "o.l.",
     "off.",
     "ofl.",
     "okt.",
-    "o.l.",
     "on.",
     "op.",
     "org.",
@@ -123,14 +152,15 @@ for orth in [
     "ovf.",
     "p.",
     "p.a.",
-    "Pb.",
+    "p.g.a.",
+    "p.m.",
+    "p.t.",
     "pga.",
     "ph.d.",
     "pkt.",
-    "p.m.",
     "pr.",
     "pst.",
-    "p.t.",
+    "pt.",
     "red.anm.",
     "ref.",
     "res.",
@@ -139,6 +169,10 @@ for orth in [
     "rv.",
     "s.",
     "s.d.",
+    "s.k.",
+    "s.k.",
+    "s.u.",
+    "s.å.",
     "sen.",
     "sep.",
     "siviling.",
@@ -148,16 +182,17 @@ for orth in [
     "sr.",
     "sst.",
     "st.",
-    "stip.",
-    "stk.",
     "st.meld.",
     "st.prp.",
+    "stip.",
+    "stk.",
     "stud.",
-    "s.u.",
     "sv.",
-    "sø.",
-    "s.å.",
     "såk.",
+    "sø.",
+    "t.h.",
+    "t.o.m.",
+    "t.v.",
     "temp.",
     "ti.",
     "tils.",
@@ -165,7 +200,6 @@ for orth in [
     "tl;dr",
     "tlf.",
     "to.",
-    "t.o.m.",
     "ult.",
     "utg.",
     "v.",
@@ -179,8 +213,10 @@ for orth in [
     "vol.",
     "vs.",
     "vsa.",
+    "©NTB",
     "årg.",
     "årh.",
+    "§§",
 ]:
     _exc[orth] = [{ORTH: orth}]