Merge branch 'develop' of https://github.com/explosion/spaCy into develop

.github/contributors/jarib.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                           | Jari Bakken          |
+| Company name (if applicable)   |                      |
+| Title or role (if applicable)  |                      |
+| Date                           | 2018-12-21           |
+| GitHub username                | jarib                |
+| Website (optional)             |                      |

spacy/cli/convert.py

@@ -69,7 +69,7 @@ def convert(
     # Use converter function to convert data
     func = CONVERTERS[converter]
     input_data = input_path.open("r", encoding="utf-8").read()
-    data = func(input_data, nsents=n_sents, use_morphology=morphology, lang=lang)
+    data = func(input_data, n_sents=n_sents, use_morphology=morphology, lang=lang)
     if output_dir != "-":
         # Export data to a file
         suffix = ".{}".format(file_type)

spacy/cli/evaluate.py

@@ -49,9 +49,9 @@ def evaluate(
     end = timer()
     nwords = sum(len(doc_gold[0]) for doc_gold in dev_docs)
     results = {
-        "Time": "%.2f s" % end - begin,
+        "Time": "%.2f s" % (end - begin),
         "Words": nwords,
-        "Words/s": "%.0f" % nwords / (end - begin),
+        "Words/s": "%.0f" % (nwords / (end - begin)),
         "TOK": "%.2f" % scorer.token_acc,
         "POS": "%.2f" % scorer.tags_acc,
         "UAS": "%.2f" % scorer.uas,

spacy/cli/package.py

@@ -102,6 +102,7 @@ def generate_meta(model_path, existing_meta, msg):
         "width": nlp.vocab.vectors_length,
         "vectors": len(nlp.vocab.vectors),
         "keys": nlp.vocab.vectors.n_keys,
+        "name": nlp.vocab.vectors.name,
     }
     msg.divider("Generating meta.json")
     msg.text(

spacy/cli/train.py

@@ -279,6 +279,7 @@ def train(
                     "width": nlp.vocab.vectors_length,
                     "vectors": len(nlp.vocab.vectors),
                     "keys": nlp.vocab.vectors.n_keys,
+                    "name": nlp.vocab.vectors.name
                 }
                 meta.setdefault("name", "model%d" % i)
                 meta.setdefault("version", version)

spacy/lang/nb/tag_map.py

@@ -76,6 +76,7 @@ TAG_MAP = {
     "ADJ___": {"morph": "_", POS: ADJ},
     "ADP___": {"morph": "_", POS: ADP},
     "ADV___": {"morph": "_", POS: ADV},
+    "ADV__Gender=Masc": {"morph": "Gender=Masc", POS: ADV},
     "AUX__Mood=Imp|VerbForm=Fin": {"morph": "Mood=Imp|VerbForm=Fin", POS: AUX},
     "AUX__Mood=Ind|Tense=Past|VerbForm=Fin": {
         "morph": "Mood=Ind|Tense=Past|VerbForm=Fin",
@@ -90,6 +91,7 @@ TAG_MAP = {
         POS: AUX,
     },
     "AUX__VerbForm=Inf": {"morph": "VerbForm=Inf", POS: AUX},
+    "AUX__VerbForm=Inf|Voice=Pass": {"morph": "VerbForm=Inf|Voice=Pass", POS: AUX},
     "AUX__VerbForm=Part": {"morph": "VerbForm=Part", POS: AUX},
     "CONJ___": {"morph": "_", POS: CONJ},
     "DET__Case=Gen|Definite=Ind|Gender=Masc|Number=Sing|PronType=Dem": {
@@ -310,6 +312,7 @@ TAG_MAP = {
         POS: NOUN,
     },
     "NOUN__Definite=Ind|Number=Plur": {"morph": "Definite=Ind|Number=Plur", POS: NOUN},
+    "NOUN__Definite=Ind|Number=Sing": {"morph": "Definite=Ind|Number=Sing", POS: NOUN},
     "NOUN__Gender=Fem": {"morph": "Gender=Fem", POS: NOUN},
     "NOUN__Gender=Masc": {"morph": "Gender=Masc", POS: NOUN},
     "NOUN__Gender=Masc|Number=Sing": {"morph": "Gender=Masc|Number=Sing", POS: NOUN},
@@ -411,6 +414,10 @@ TAG_MAP = {
         "morph": "Case=Nom|Number=Plur|Person=",
         POS: PRON,
     },
+    "PRON__Case=Gen|Number=Plur|Person=3|PronType=Prs": {
+        "morph": "Case=Gen|Number=Plur|Person=3|PronType=Prs",
+        POS: PRON,
+    },
     "PRON__Gender=Fem,Masc|Number=Sing|Person=3|PronType=Prs": {
         "morph": "Gender=Fem",
         POS: PRON,