Merge branch 'master' into develop

.github/contributors/tamuhey.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 GmbH](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                           | Yohei Tamura |
+| Company name (if applicable)   | PKSHA |
+| Title or role (if applicable)  |  |
+| Date                           | 2019/9/12 |
+| GitHub username                | tamuhey |
+| Website (optional)             |                      |

spacy/cli/converters/conllu2json.py

@@ -6,7 +6,7 @@ import re
 from ...gold import iob_to_biluo
 
 
-def conllu2json(input_data, n_sents=10, use_morphology=False, lang=None):
+def conllu2json(input_data, n_sents=10, use_morphology=False, lang=None, **_):
     """
     Convert conllu files into JSON format for use with train cli.
     use_morphology parameter enables appending morphology to tags, which is

spacy/language.py

@@ -214,6 +214,7 @@ class Language(object):
             "name": self.vocab.vectors.name,
         }
         self._meta["pipeline"] = self.pipe_names
+        self._meta["labels"] = self.pipe_labels
         return self._meta
 
     @meta.setter
@@ -254,6 +255,18 @@ class Language(object):
         """
         return [pipe_name for pipe_name, _ in self.pipeline]
 
+    @property
+    def pipe_labels(self):
+        """Get the labels set by the pipeline components, if available.
+
+        RETURNS (dict): Labels keyed by component name.
+        """
+        labels = OrderedDict()
+        for name, pipe in self.pipeline:
+            if hasattr(pipe, "labels"):
+                labels[name] = list(pipe.labels)
+        return labels
+
     def get_pipe(self, name):
         """Get a pipeline component for a given component name.
 

spacy/pipeline/pipes.pyx

@@ -67,7 +67,7 @@ class Pipe(object):
         """
         self.require_model()
         predictions = self.predict([doc])
-        if isinstance(predictions, tuple) and len(tuple) == 2:
+        if isinstance(predictions, tuple) and len(predictions) == 2:
             scores, tensors = predictions
             self.set_annotations([doc], scores, tensor=tensors)
         else:
@@ -1067,7 +1067,7 @@ cdef class DependencyParser(Parser):
     @property
     def labels(self):
         # Get the labels from the model by looking at the available moves
-        return tuple(set(move.split("-")[1] for move in self.move_names))
+        return tuple(set(move.split("-")[1] for move in self.move_names if "-" in move))
 
 
 cdef class EntityRecognizer(Parser):

spacy/tests/parser/test_add_label.py

@@ -68,3 +68,20 @@ def test_add_label_deserializes_correctly():
     assert ner1.moves.n_moves == ner2.moves.n_moves
     for i in range(ner1.moves.n_moves):
         assert ner1.moves.get_class_name(i) == ner2.moves.get_class_name(i)
+
+
+@pytest.mark.parametrize(
+    "pipe_cls,n_moves", [(DependencyParser, 5), (EntityRecognizer, 4)]
+)
+def test_add_label_get_label(pipe_cls, n_moves):
+    """Test that added labels are returned correctly. This test was added to
+    test for a bug in DependencyParser.labels that'd cause it to fail when
+    splitting the move names.
+    """
+    labels = ["A", "B", "C"]
+    pipe = pipe_cls(Vocab())
+    for label in labels:
+        pipe.add_label(label)
+    assert len(pipe.move_names) == len(labels) * n_moves
+    pipe_labels = sorted(list(pipe.labels))
+    assert pipe_labels == labels

spacy/tests/pipeline/test_pipe_methods.py

@@ -128,3 +128,19 @@ def test_pipe_base_class_add_label(nlp, component):
         assert label in pipe.labels
     else:
         assert pipe.labels == (label,)
+
+
+def test_pipe_labels(nlp):
+    input_labels = {
+        "ner": ["PERSON", "ORG", "GPE"],
+        "textcat": ["POSITIVE", "NEGATIVE"],
+    }
+    for name, labels in input_labels.items():
+        pipe = nlp.create_pipe(name)
+        for label in labels:
+            pipe.add_label(label)
+        assert len(pipe.labels) == len(labels)
+        nlp.add_pipe(pipe)
+    assert len(nlp.pipe_labels) == len(input_labels)
+    for name, labels in nlp.pipe_labels.items():
+        assert sorted(input_labels[name]) == sorted(labels)

spacy/tests/regression/test_issue4278.py

@@ -0,0 +1,28 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+import pytest
+from spacy.language import Language
+from spacy.pipeline import Pipe
+
+
+class DummyPipe(Pipe):
+    def __init__(self):
+        self.model = "dummy_model"
+
+    def predict(self, docs):
+        return ([1, 2, 3], [4, 5, 6])
+
+    def set_annotations(self, docs, scores, tensor=None):
+        return docs
+
+
+@pytest.fixture
+def nlp():
+    return Language()
+
+
+def test_multiple_predictions(nlp):
+    doc = nlp.make_doc("foo")
+    dummy_pipe = DummyPipe()
+    dummy_pipe(doc)