Merge pull request #688 from nlesc-sherlock/dutch

Support for Dutch in SpaCy

.github/contributors/RvanNieuwpoort.md

@@ -0,0 +1,107 @@
+# spaCy contributor agreement
+
+This spaCy Contributor Agreement (**"SCA"**) is based on the
+[Oracle Contributor Agreement](http://www.oracle.com/technetwork/oca-405177.pdf).
+The SCA applies to any contribution that you make to any product or project
+managed by us (the **"project"**), and sets out the intellectual property rights
+you grant to us in the contributed materials. The term **"us"** shall mean
+[ExplosionAI UG (haftungsbeschränkt)](https://explosion.ai/legal). The term
+**"you"** shall mean the person or entity identified below.
+
+If you agree to be bound by these terms, fill in the information requested
+below and include the filled-in version with your first pull request, under the
+folder [`.github/contributors/`](/.github/contributors/). The name of the file
+should be your GitHub username, with the extension `.md`. For example, the user
+example_user would create the file `.github/contributors/example_user.md`.
+
+Read this agreement carefully before signing. These terms and conditions
+constitute a binding legal agreement.
+
+## Contributor Agreement
+
+1. The term "contribution" or "contributed materials" means any source code,
+object code, patch, tool, sample, graphic, specification, manual,
+documentation, or any other material posted or submitted by you to the project.
+
+2. With respect to any worldwide copyrights, or copyright applications and
+registrations, in your contribution:
+
+    * you hereby assign to us joint ownership, and to the extent that such
+    assignment is or becomes invalid, ineffective or unenforceable, you hereby
+    grant to us a perpetual, irrevocable, non-exclusive, worldwide, no-charge,
+    royalty-free, unrestricted license to exercise all rights under those
+    copyrights. This includes, at our option, the right to sublicense these same
+    rights to third parties through multiple levels of sublicensees or other
+    licensing arrangements;
+
+    * you agree that each of us can do all things in relation to your
+    contribution as if each of us were the sole owners, and if one of us makes
+    a derivative work of your contribution, the one who makes the derivative
+    work (or has it made will be the sole owner of that derivative work;
+
+    * you agree that you will not assert any moral rights in your contribution
+    against us, our licensees or transferees;
+
+    * you agree that we may register a copyright in your contribution and
+    exercise all ownership rights associated with it; and
+
+    * you agree that neither of us has any duty to consult with, obtain the
+    consent of, pay or render an accounting to the other for any use or
+    distribution of your contribution.
+
+3. With respect to any patents you own, or that you can license without payment
+to any third party, you hereby grant to us a perpetual, irrevocable,
+non-exclusive, worldwide, no-charge, royalty-free license to:
+
+    * make, have made, use, sell, offer to sell, import, and otherwise transfer
+    your contribution in whole or in part, alone or in combination with or
+    included in any product, work or materials arising out of the project to
+    which your contribution was submitted, and
+
+    * at our option, to sublicense these same rights to third parties through
+    multiple levels of sublicensees or other licensing arrangements.
+
+4. Except as set out above, you keep all right, title, and interest in your
+contribution. The rights that you grant to us under these terms are effective
+on the date you first submitted a contribution to us, even if your submission
+took place before the date you sign these terms.
+
+5. You covenant, represent, warrant and agree that:
+
+    * Each contribution that you submit is and shall be an original work of
+    authorship and you can legally grant the rights set out in this SCA;
+
+    * to the best of your knowledge, each contribution will not violate any
+    third party's copyrights, trademarks, patents, or other intellectual
+    property rights; and
+
+    * each contribution shall be in compliance with U.S. export control laws and
+    other applicable export and import laws. You agree to notify us if you
+    become aware of any circumstance which would make any of the foregoing
+    representations inaccurate in any respect. We may publicly disclose your 
+    participation in the project, including the fact that you have signed the SCA.
+
+6. This SCA is governed by the laws of the State of California and applicable
+U.S. Federal law. Any choice of law rules will not apply.
+
+7. Please place an “x” on one of the applicable statement below. Please do NOT
+mark both statements:
+
+    * [ ] I am signing on behalf of myself as an individual and no other person
+    or entity, including my employer, has or will have rights with respect my
+    contributions.
+
+    * [x] I am signing on behalf of my employer or a legal entity and I have the
+    actual authority to contractually bind that entity.
+
+## Contributor Details
+
+| Field                          | Entry                            |
+|------------------------------- | -------------------------------- |
+| Name                           |  Rob van Nieuwpoort              |
+| Signing on behalf of             |  Dafne van Kuppevelt, Janneke van der Zwaan, Willem van Hage          |
+| Company name (if applicable)   |  Netherlands eScience center     |
+| Title or role (if applicable)  |  Director of technology          |
+| Date                           |  14-12-2016                      |
+| GitHub username                |  RvanNieuwpoort                  |
+| Website (optional)             |  https://www.esciencecenter.nl/  |

bin/init_model.py

@@ -151,10 +151,10 @@ def _read_senses(loc):
 def setup_vocab(lex_attr_getters, tag_map, src_dir, dst_dir):
     if not dst_dir.exists():
         dst_dir.mkdir()
-
+    print('Reading vocab from ', src_dir)
     vectors_src = src_dir / 'vectors.bz2'
     if vectors_src.exists():
-        write_binary_vectors(vectors_src.as_posix, (dst_dir / 'vec.bin').as_posix())
+        write_binary_vectors(vectors_src.as_posix(), (dst_dir / 'vec.bin').as_posix())
     else:
         print("Warning: Word vectors file not found")
     vocab = Vocab(lex_attr_getters=lex_attr_getters, tag_map=tag_map)

setup.py

@@ -28,6 +28,7 @@ PACKAGES = [
     'spacy.fr',
     'spacy.it',
     'spacy.pt',
+    'spacy.nl',
     'spacy.serialize',
     'spacy.syntax',
     'spacy.munge',

spacy/__init__.py

@@ -10,6 +10,7 @@ from . import es
 from . import it
 from . import fr
 from . import pt
+from . import nl
 
 
 try:
@@ -25,6 +26,7 @@ set_lang_class(pt.Portuguese.lang, pt.Portuguese)
 set_lang_class(fr.French.lang, fr.French)
 set_lang_class(it.Italian.lang, it.Italian)
 set_lang_class(zh.Chinese.lang, zh.Chinese)
+set_lang_class(nl.Dutch.lang, nl.Dutch)
 
 
 def load(name, **overrides):
@@ -33,7 +35,7 @@ def load(name, **overrides):
     if target_name == 'en' and 'add_vectors' not in overrides:
         if 'vectors' in overrides:
             vec_path = util.match_best_version(overrides['vectors'], None, data_path)
-            if vec_path is None: 
+            if vec_path is None:
                 raise IOError(
                     'Could not load data pack %s from %s' % (overrides['vectors'], data_path))
 

spacy/nl/__init__.py

@@ -0,0 +1,26 @@
+from __future__ import unicode_literals, print_function
+
+from os import path
+
+from ..language import Language
+from ..attrs import LANG
+from . import language_data
+
+
+class Dutch(Language):
+    lang = 'nl'
+
+    class Defaults(Language.Defaults):
+        tokenizer_exceptions = dict(language_data.TOKENIZER_EXCEPTIONS)
+        lex_attr_getters = dict(Language.Defaults.lex_attr_getters)
+        lex_attr_getters[LANG] = lambda text: 'nl'
+
+        prefixes = tuple(language_data.TOKENIZER_PREFIXES)
+
+        suffixes = tuple(language_data.TOKENIZER_SUFFIXES)
+
+        infixes = tuple(language_data.TOKENIZER_INFIXES)
+
+        tag_map = dict(language_data.TAG_MAP)
+
+        stop_words = set(language_data.STOP_WORDS)

spacy/nl/language_data.py

@@ -0,0 +1,285 @@
+# encoding: utf8
+from __future__ import unicode_literals
+import re
+
+# Stop words are retrieved from http://www.damienvanholten.com/downloads/dutch-stop-words.txt
+STOP_WORDS = set("""
+aan
+af
+al
+alles
+als
+altijd
+andere
+ben
+bij
+daar
+dan
+dat
+de
+der
+deze
+die
+dit
+doch
+doen
+door
+dus
+een
+eens
+en
+er
+ge
+geen
+geweest
+haar
+had
+heb
+hebben
+heeft
+hem
+het
+hier
+hij
+hoe
+hun
+iemand
+iets
+ik
+in
+is
+ja
+je
+kan
+kon
+kunnen
+maar
+me
+meer
+men
+met
+mij
+mijn
+moet
+na
+naar
+niet
+niets
+nog
+nu
+of
+om
+omdat
+ons
+ook
+op
+over
+reeds
+te
+tegen
+toch
+toen
+tot
+u
+uit
+uw
+van
+veel
+voor
+want
+waren
+was
+wat
+we
+wel
+werd
+wezen
+wie
+wij
+wil
+worden
+zal
+ze
+zei
+zelf
+zich
+zij
+zijn
+zo
+zonder
+zou
+""".split())
+
+
+TOKENIZER_PREFIXES = map(re.escape, r'''
+,
+"
+(
+[
+{
+*
+<
+>
+$
+£
+„
+“
+'
+``
+`
+#
+US$
+C$
+A$
+a-
+‘
+....
+...
+‚
+»
+_
+§
+'''.strip().split('\n'))
+
+
+TOKENIZER_SUFFIXES = r'''
+,
+\"
+\)
+\]
+\}
+\*
+\!
+\?
+%
+\$
+>
+:
+;
+'
+”
+“
+«
+_
+''
+'s
+'S
+’s
+’S
+’
+‘
+°
+€
+\.\.
+\.\.\.
+\.\.\.\.
+(?<=[a-zäöüßÖÄÜ)\]"'´«‘’%\)²“”])\.
+\-\-
+´
+(?<=[0-9])km²
+(?<=[0-9])m²
+(?<=[0-9])cm²
+(?<=[0-9])mm²
+(?<=[0-9])km³
+(?<=[0-9])m³
+(?<=[0-9])cm³
+(?<=[0-9])mm³
+(?<=[0-9])ha
+(?<=[0-9])km
+(?<=[0-9])m
+(?<=[0-9])cm
+(?<=[0-9])mm
+(?<=[0-9])µm
+(?<=[0-9])nm
+(?<=[0-9])yd
+(?<=[0-9])in
+(?<=[0-9])ft
+(?<=[0-9])kg
+(?<=[0-9])g
+(?<=[0-9])mg
+(?<=[0-9])µg
+(?<=[0-9])t
+(?<=[0-9])lb
+(?<=[0-9])oz
+(?<=[0-9])m/s
+(?<=[0-9])km/h
+(?<=[0-9])mph
+(?<=[0-9])°C
+(?<=[0-9])°K
+(?<=[0-9])°F
+(?<=[0-9])hPa
+(?<=[0-9])Pa
+(?<=[0-9])mbar
+(?<=[0-9])mb
+(?<=[0-9])T
+(?<=[0-9])G
+(?<=[0-9])M
+(?<=[0-9])K
+(?<=[0-9])kb
+'''.strip().split('\n')
+
+
+TOKENIZER_INFIXES = r'''
+\.\.\.
+(?<=[a-z])\.(?=[A-Z])
+(?<=[a-zöäüßA-ZÖÄÜ"]):(?=[a-zöäüßA-ZÖÄÜ])
+(?<=[a-zöäüßA-ZÖÄÜ"])>(?=[a-zöäüßA-ZÖÄÜ])
+(?<=[a-zöäüßA-ZÖÄÜ"])<(?=[a-zöäüßA-ZÖÄÜ])
+(?<=[a-zöäüßA-ZÖÄÜ"])=(?=[a-zöäüßA-ZÖÄÜ])
+'''.strip().split('\n')
+
+
+#TODO Make tokenizer excpetions for Dutch
+TOKENIZER_EXCEPTIONS = {}
+
+#TODO insert TAG_MAP for Dutch
+TAG_MAP = {
+  "ADV": {
+    "pos": "ADV"
+  },
+  "NOUN": {
+    "pos": "NOUN"
+  },
+  "ADP": {
+    "pos": "ADP"
+  },
+  "PRON": {
+    "pos": "PRON"
+  },
+  "SCONJ": {
+    "pos": "SCONJ"
+  },
+  "PROPN": {
+    "pos": "PROPN"
+  },
+  "DET": {
+    "pos": "DET"
+  },
+  "SYM": {
+    "pos": "SYM"
+  },
+  "INTJ": {
+    "pos": "INTJ"
+  },
+  "PUNCT": {
+    "pos": "PUNCT"
+  },
+  "NUM": {
+    "pos": "NUM"
+  },
+  "AUX": {
+    "pos": "AUX"
+  },
+  "X": {
+    "pos": "X"
+  },
+  "CONJ": {
+    "pos": "CONJ"
+  },
+  "ADJ": {
+    "pos": "ADJ"
+  },
+  "VERB": {
+    "pos": "VERB"
+  }
+}

spacy/tests/integration/test_load_languages.py

@@ -1,6 +1,7 @@
 # encoding: utf8
 from __future__ import unicode_literals
 from ...fr import French
+from ...nl import Dutch
 
 def test_load_french():
     nlp = French()
@@ -10,3 +11,11 @@ def test_load_french():
     assert doc[2].text == u'vous'
     assert doc[3].text == u'français'
     assert doc[4].text == u'?'
+
+def test_load_dutch():
+    nlp = Dutch()
+    doc = nlp(u'Is dit Nederlands?')
+    assert doc[0].text == u'Is'
+    assert doc[1].text == u'dit'
+    assert doc[2].text == u'Nederlands'
+    assert doc[3].text == u'?'