3 files changed, 133 insertions, 0 deletions
diff --git a/pkgs/development/python-modules/spacy-transformers/annotation-test/annotate.py b/pkgs/development/python-modules/spacy-transformers/annotation-test/annotate.py
new file mode 100644
index 000000000000..d0be2d1c335a
--- /dev/null
+++ b/pkgs/development/python-modules/spacy-transformers/annotation-test/annotate.py
@@ -0,0 +1,68 @@
+import pytest
+import spacy
+
+en_text = (
+    "When Sebastian Thrun started working on self-driving cars at "
+    "Google in 2007, few people outside of the company took him "
+    "seriously. “I can tell you very senior CEOs of major American "
+    "car companies would shake my hand and turn away because I wasn’t "
+    "worth talking to,” said Thrun, in an interview with Recode earlier "
+    "this week.")
+
+
+@pytest.fixture
+def en_core_web_trf():
+    return spacy.load("en_core_web_trf")
+
+
+@pytest.fixture
+def doc_en_core_web_trf(en_core_web_trf):
+    return en_core_web_trf(en_text)
+
+
+def test_entities(doc_en_core_web_trf):
+    entities = list(map(lambda e: (e.text, e.label_),
+                        doc_en_core_web_trf.ents))
+
+    assert entities == [
+        ('Sebastian Thrun', 'PERSON'),
+        ('Google', 'ORG'),
+        ('2007', 'DATE'),
+        ('American', 'NORP'),
+        ('Thrun', 'PERSON'),
+        ('Recode', 'ORG'),
+        ('earlier this week', 'DATE'),
+    ]
+
+
+def test_nouns(doc_en_core_web_trf):
+    assert [
+        chunk.text for chunk in doc_en_core_web_trf.noun_chunks] == [
+        'Sebastian Thrun',
+        'self-driving cars',
+        'Google',
+        'few people',
+        'the company',
+        'him',
+        'I',
+        'you',
+        'very senior CEOs',
+        'major American car companies',
+        'my hand',
+        'I',
+        'Thrun',
+        'an interview',
+        'Recode']
+
+
+def test_verbs(doc_en_core_web_trf):
+    assert [
+        token.lemma_ for token in doc_en_core_web_trf if token.pos_ == "VERB"] == [
+        'start',
+        'take',
+        'tell',
+        'shake',
+        'turn',
+        'be',
+        'talk',
+        'say']
diff --git a/pkgs/development/python-modules/spacy-transformers/annotation-test/default.nix b/pkgs/development/python-modules/spacy-transformers/annotation-test/default.nix
new file mode 100644
index 000000000000..11a927a0a627
--- /dev/null
+++ b/pkgs/development/python-modules/spacy-transformers/annotation-test/default.nix
@@ -0,0 +1,23 @@
+{ stdenv, pytest, spacy_models }:
+
+stdenv.mkDerivation {
+  name = "spacy-transformers-annotation-test";
+
+  src = ./.;
+
+  dontConfigure = true;
+  dontBuild = true;
+  doCheck = true;
+
+  checkInputs = [ pytest spacy_models.en_core_web_trf ];
+
+  checkPhase = ''
+    pytest annotate.py
+  '';
+
+  installPhase = ''
+    touch $out
+  '';
+
+  meta.timeout = 60;
+}
diff --git a/pkgs/development/python-modules/spacy-transformers/default.nix b/pkgs/development/python-modules/spacy-transformers/default.nix
new file mode 100644
index 000000000000..1d02460167bf
--- /dev/null
+++ b/pkgs/development/python-modules/spacy-transformers/default.nix
@@ -0,0 +1,42 @@
+{ lib
+, callPackage
+, fetchPypi
+, buildPythonPackage
+, pytorch
+, spacy
+, spacy-alignments
+, srsly
+, transformers
+}:
+
+buildPythonPackage rec {
+  pname = "spacy-transformers";
+  version = "1.0.2";
+
+  src = fetchPypi {
+    inherit pname version;
+    hash = "sha256-AYshH2trMTgeSkAPRb6wRWpm4gA5FaKV2NJd+PhzAy4=";
+  };
+
+  propagatedBuildInputs = [
+    pytorch
+    spacy
+    spacy-alignments
+    srsly
+    transformers
+  ];
+
+  # Test fails due to missing arguments for trfs2arrays().
+  doCheck = false;
+
+  pythonImportsCheck = [ "spacy_transformers" ];
+
+  passthru.tests.annotation = callPackage ./annotation-test { };
+
+  meta = with lib; {
+    description = "spaCy pipelines for pretrained BERT, XLNet and GPT-2";
+    homepage = "https://github.com/explosion/spacy-transformers";
+    license = licenses.mit;
+    maintainers = with maintainers; [ danieldk ];
+  };
+}