From 253ba5ef14a42b42684628204ed358981de104db Mon Sep 17 00:00:00 2001
From: Ines Montani <ines@ines.io>
Date: Tue, 15 Sep 2020 13:25:34 +0200
Subject: [PATCH] Raise for bad Vocab values

---
 spacy/errors.py              |  3 +++
 spacy/language.py            |  2 ++
 spacy/tests/test_language.py | 11 +++++++++++
 3 files changed, 16 insertions(+)

diff --git a/spacy/errors.py b/spacy/errors.py
index f857bea52..84593bede 100644
--- a/spacy/errors.py
+++ b/spacy/errors.py
@@ -480,6 +480,9 @@ class Errors:
     E201 = ("Span index out of range.")
 
     # TODO: fix numbering after merging develop into master
+    E918 = ("Received invalid value for vocab: {vocab} ({vocab_type}). Valid "
+            "values are an instance of spacy.vocab.Vocab or True to create one"
+            " (default).")
     E919 = ("A textcat 'positive_label' '{pos_label}' was provided for training "
             "data that does not appear to be a binary classification problem "
             "with two labels. Labels found: {labels}")
diff --git a/spacy/language.py b/spacy/language.py
index e71f4215f..543bcd8bc 100644
--- a/spacy/language.py
+++ b/spacy/language.py
@@ -144,6 +144,8 @@ class Language:
         self._pipe_meta: Dict[str, "FactoryMeta"] = {}  # meta by component
         self._pipe_configs: Dict[str, Config] = {}  # config by component
 
+        if not isinstance(vocab, Vocab) and vocab is not True:
+            raise ValueError(Errors.E918.format(vocab=vocab, vocab_type=type(Vocab)))
         if vocab is True:
             vectors_name = meta.get("vectors", {}).get("name")
             vocab = create_vocab(
diff --git a/spacy/tests/test_language.py b/spacy/tests/test_language.py
index 1156d26b0..4c689e524 100644
--- a/spacy/tests/test_language.py
+++ b/spacy/tests/test_language.py
@@ -277,3 +277,14 @@ def test_spacy_blank():
     nlp = spacy.blank("en", config=config, meta=meta)
     assert nlp.config["training"]["dropout"] == 0.2
     assert nlp.meta["name"] == "my_custom_model"
+
+
+@pytest.mark.parametrize(
+    "value",
+    [False, None, ["x", "y"], Language, Vocab],
+)
+def test_language_init_invalid_vocab(value):
+    err_fragment = "invalid value"
+    with pytest.raises(ValueError) as e:
+        Language(value)
+    assert err_fragment in str(e)