Merge branch 'master' into da_ud_tokenization

.github/contributors/cbilgili.md

@@ -0,0 +1,106 @@
+# 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:
+
+    * [x] 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 to my
+    contributions.
+
+    * [ ] 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                           | Canbey Bilgili                     |
+| Company name (if applicable)   |                                    |
+| Title or role (if applicable)  |                                    |
+| Date                           | 1 December 2017                    |
+| GitHub username                | cbilgili                           |
+| Website (optional)             |                                    |

.github/contributors/kimfalk.md

@@ -0,0 +1,106 @@
+# 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:
+
+    * [x] 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 to my
+    contributions.
+
+    * [ ] 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                           | Kim Falk             |
+| Company name (if applicable)   |                      |
+| Title or role (if applicable)  |                      |
+| Date                           | 19 December 2017     |
+| GitHub username                | kimfalk              |
+| Website (optional)             |                      |

CONTRIBUTORS.md

@@ -12,6 +12,7 @@ This is a list of everyone who has made significant contributions to spaCy, in a
 * Ben Eyal, [@beneyal](https://github.com/beneyal)
 * Bhargav Srinivasa, [@bhargavvader](https://github.com/bhargavvader)
 * Bruno P. Kinoshita, [@kinow](https://github.com/kinow)
+* Canbey Bilgili, [@cbilgili](https://github.com/cbilgili)
 * Chris DuBois, [@chrisdubois](https://github.com/chrisdubois)
 * Christoph Schwienheer, [@chssch](https://github.com/chssch)
 * Dafne van Kuppevelt, [@dafnevk](https://github.com/dafnevk)

spacy/lang/da/examples.py

@@ -13,6 +13,6 @@ Example sentences to test spaCy and its language models.
 sentences = [
     "Apple overvejer at købe et britisk startup for 1 milliard dollar",
     "Selvkørende biler flytter forsikringsansvaret over på producenterne",
-    "San Francisco overvejer at forbyde leverandørrobotter på fortov",
+    "San Francisco overvejer at forbyde udbringningsrobotter på fortov",
     "London er en stor by i Storbritannien"
 ]

spacy/lang/hi/examples.py

@@ -1,4 +1,4 @@
-  # coding: utf8
+# coding: utf8
 from __future__ import unicode_literals
 
 
@@ -12,11 +12,11 @@ Example sentences to test spaCy and its language models.
 
 sentences = [
     "एप्पल 1 अरब डॉलर के लिए यू.के. स्टार्टअप खरीदने पर विचार कर रहा है",
-     "स्वायत्त कार निर्माताओं की ओर बीमा दायित्व रखती है",
+    "स्वायत्त कार निर्माताओं की ओर बीमा दायित्व रखती है",
-     "सैन फ्रांसिस्को फुटवे डिलीवरी रोबोटों पर प्रतिबंध लगाने का विचार कर रहा है",
+    "सैन फ्रांसिस्को फुटवे डिलीवरी रोबोटों पर प्रतिबंध लगाने का विचार कर रहा है",
-     "लंदन यूनाइटेड किंगडम का बड़ा शहर है।",
+    "लंदन यूनाइटेड किंगडम का बड़ा शहर है।",
-     "आप कहाँ हैं?",
+    "आप कहाँ हैं?",
-     "फ्रांस के राष्ट्रपति कौन हैं?",
+    "फ्रांस के राष्ट्रपति कौन हैं?",
-     "संयुक्त राज्य की राजधानी क्या है?",
+    "संयुक्त राज्य की राजधानी क्या है?",
-     "बराक ओबामा का जन्म हुआ था?"
+    "बराक ओबामा का जन्म हुआ था?",
 ]

spacy/lang/tr/__init__.py

@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 from .tokenizer_exceptions import TOKENIZER_EXCEPTIONS
+from .lemmatizer import LOOKUP
 from .stop_words import STOP_WORDS
 
 from ..tokenizer_exceptions import BASE_EXCEPTIONS
@@ -17,6 +18,7 @@ class TurkishDefaults(Language.Defaults):
     lex_attr_getters[NORM] = add_lookups(Language.Defaults.lex_attr_getters[NORM], BASE_NORMS)
     tokenizer_exceptions = update_exc(BASE_EXCEPTIONS, TOKENIZER_EXCEPTIONS)
     stop_words = STOP_WORDS
+    lemma_lookup = LOOKUP
 
 
 class Turkish(Language):

spacy/tests/conftest.py

@@ -15,7 +15,7 @@ from .. import util
 # here if it's using spaCy's tokenizer (not a different library)
 # TODO: re-implement generic tokenizer tests
 _languages = ['bn', 'da', 'de', 'en', 'es', 'fi', 'fr', 'ga', 'he', 'hu', 'id',
-              'it', 'nb', 'nl', 'pl', 'pt', 'ru', 'sv', 'xx']
+              'it', 'nb', 'nl', 'pl', 'pt', 'ru', 'sv', 'tr', 'xx']
 _models = {'en': ['en_core_web_sm'],
            'de': ['de_core_news_md'],
            'fr': ['fr_core_news_sm'],
@@ -142,6 +142,10 @@ def th_tokenizer():
     pythainlp = pytest.importorskip("pythainlp")
     return util.get_lang_class('th').Defaults.create_tokenizer()
 
+@pytest.fixture
+def tr_tokenizer():
+    return util.get_lang_class('tr').Defaults.create_tokenizer()
+
 
 @pytest.fixture
 def ru_tokenizer():

spacy/tests/lang/tr/test_lemmatization.py

@@ -0,0 +1,15 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import pytest
+
+@pytest.mark.parametrize('string,lemma', [('evlerimizdeki', 'ev'),
+                                          ('işlerimizi', 'iş'),
+                                          ('biran', 'biran'),
+                                          ('bitirmeliyiz', 'bitir'),
+                                          ('isteklerimizi', 'istek'),
+                                          ('karşılaştırmamızın', 'karşılaştır'),
+                                          ('çoğulculuktan', 'çoğulcu')])
+def test_lemmatizer_lookup_assigns(tr_tokenizer, string, lemma):
+    tokens = tr_tokenizer(string)
+    assert tokens[0].lemma_ == lemma