Quick hack for multiword (#17)

* Add proper support for multiword tokens

spacy_udpipe/language.py

@@ -185,6 +185,12 @@ def __call__(self, text: str) -> Doc:
         lemmas = []
         offset = 0
         is_aligned = self._check_aligned(text=text, tokens=tokens)
+        if not is_aligned:
+            text = ""
+            for token in tokens:
+                text += token.form
+                if "SpaceAfter=No" not in token.misc:
+                    text += " "
         for i, token in enumerate(tokens):
             span = text[offset:]
             if not span:

tests/languages/fr/test_fr_language.py

@@ -0,0 +1,45 @@
+from typing import List
+
+import pytest
+from spacy.lang.fr import FrenchDefaults
+from spacy.language import BaseDefaults
+from spacy_udpipe import download
+from spacy_udpipe.language import load
+from spacy_udpipe.utils import get_defaults
+
+FR = "fr"
+
+
+@pytest.fixture
+def lang() -> str:
+    return FR
+
+
+@pytest.fixture(autouse=True)
+def download_lang(lang: str) -> None:
+    download(lang)
+
+
+def test_get_defaults(lang: str) -> None:
+    assert get_defaults(lang) == FrenchDefaults
+    assert get_defaults("blabla") == BaseDefaults
+
+
+def test_spacy_udpipe(lang: str) -> None:
+    nlp = load(lang=lang)
+    assert nlp._meta["lang"] == f"udpipe_{lang}"
+
+    text = "Attention aux articles contractés!"
+    doc = nlp (text=text)
+
+    assert [t.orth_ for t in doc] == ["Attention", "à", "les", "articles", "contractés", "!"]
+
+    pos = [{"INTJ", "NOUN"}, {"ADP"}, {"DET"}, {"NOUN"}, {"VERB", "ADJ"}, {"PUNCT"}]
+    for i, t in enumerate(doc):
+        assert t.pos_ in pos[i]
+
+    assert [t.head.i for t in doc] == [0, 3, 3, 0, 3, 0]
+
+    dep = [{"ROOT", "root"}, {"case"}, {"det"}, {"nmod", "obl", "obl:arg"}, {"acl", "amod"}, {"punct"}]
+    for i, t in enumerate(doc):
+        assert t.dep_ in dep[i]