From fb7acacd42658a59717bb20151ffe2b18efe508e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Dani=C3=ABl=20de=20Kok?= <me@danieldk.eu>
Date: Tue, 18 Aug 2020 19:38:43 +0200
Subject: [PATCH] python3Packages.spacy: add passthru test

I have been using the main example of the spaCy web page for testing
updates of spacy (and its transitive dependencies). Let's convert this
into a proper test to take out manual testing.
---
 .../spacy/annotation-test/annotate.py         | 69 +++++++++++++++++++
 .../spacy/annotation-test/default.nix         | 23 +++++++
 .../python-modules/spacy/default.nix          |  3 +
 3 files changed, 95 insertions(+)
 create mode 100644 pkgs/development/python-modules/spacy/annotation-test/annotate.py
 create mode 100644 pkgs/development/python-modules/spacy/annotation-test/default.nix

diff --git a/pkgs/development/python-modules/spacy/annotation-test/annotate.py b/pkgs/development/python-modules/spacy/annotation-test/annotate.py
new file mode 100644
index 00000000000..822eb8ac074
--- /dev/null
+++ b/pkgs/development/python-modules/spacy/annotation-test/annotate.py
@@ -0,0 +1,69 @@
+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_sm():
+    return spacy.load("en_core_web_sm")
+
+
+@pytest.fixture
+def doc_en_core_web_sm(en_core_web_sm):
+    return en_core_web_sm(en_text)
+
+
+def test_entities(doc_en_core_web_sm):
+    entities = list(map(lambda e: (e.text, e.label_),
+                        doc_en_core_web_sm.ents))
+
+    assert entities == [
+        ('Sebastian Thrun', 'PERSON'),
+        ('Google', 'ORG'), ('2007', 'DATE'),
+        ('American', 'NORP'),
+        ('Thrun', 'ORG'),
+        ('earlier this week', 'DATE')
+    ]
+
+
+def test_nouns(doc_en_core_web_sm):
+    assert [
+        chunk.text for chunk in doc_en_core_web_sm.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_sm):
+    assert [
+        token.lemma_ for token in doc_en_core_web_sm if token.pos_ == "VERB"] == [
+        'start',
+        'work',
+        'drive',
+        'take',
+        'can',
+        'tell',
+        'would',
+        'shake',
+        'turn',
+        'talk',
+        'say']
diff --git a/pkgs/development/python-modules/spacy/annotation-test/default.nix b/pkgs/development/python-modules/spacy/annotation-test/default.nix
new file mode 100644
index 00000000000..1b066ff3c39
--- /dev/null
+++ b/pkgs/development/python-modules/spacy/annotation-test/default.nix
@@ -0,0 +1,23 @@
+{ stdenv, pytest, spacy_models }:
+
+stdenv.mkDerivation {
+  name = "spacy-annotation-test";
+
+  src = ./.;
+
+  dontConfigure = true;
+  dontBuild = true;
+  doCheck = true;
+
+  checkInputs = [ pytest spacy_models.en_core_web_sm ];
+
+  checkPhase = ''
+    pytest annotate.py
+  '';
+
+  installPhase = ''
+    touch $out
+  '';
+
+  meta.timeout = 60;
+}
diff --git a/pkgs/development/python-modules/spacy/default.nix b/pkgs/development/python-modules/spacy/default.nix
index 322f10d00ae..077aea4dc9a 100644
--- a/pkgs/development/python-modules/spacy/default.nix
+++ b/pkgs/development/python-modules/spacy/default.nix
@@ -1,5 +1,6 @@
 { lib
 , buildPythonPackage
+, callPackage
 , fetchPypi
 , pythonOlder
 , pytest
@@ -64,6 +65,8 @@ buildPythonPackage rec {
 
   pythonImportsCheck = [ "spacy" ];
 
+  passthru.tests = callPackage ./annotation-test {};
+
   meta = with lib; {
     description = "Industrial-strength Natural Language Processing (NLP) with Python and Cython";
     homepage = "https://github.com/explosion/spaCy";