Merge branch 'master' into spacy.io

.github/azure-steps.yml

@@ -63,12 +63,12 @@ steps:
     displayName: "Run GPU tests"
     condition: eq(${{ parameters.gpu }}, true)
 
-#  - script: |
+  - script: |
-#      python -m spacy download ca_core_news_sm
+      python -m spacy download ca_core_news_sm
-#      python -m spacy download ca_core_news_md
+      python -m spacy download ca_core_news_md
-#      python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
+      python -c "import spacy; nlp=spacy.load('ca_core_news_sm'); doc=nlp('test')"
-#    displayName: 'Test download CLI'
+    displayName: 'Test download CLI'
-#    condition: eq(variables['python_version'], '3.8')
+    condition: eq(variables['python_version'], '3.8')
 
   - script: |
       python -m spacy convert extra/example_data/ner_example_data/ner-token-per-line-conll2003.json .
@@ -92,17 +92,17 @@ steps:
     displayName: 'Test train CLI'
     condition: eq(variables['python_version'], '3.8')
 
-#  - script: |
+  - script: |
-#      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
+      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_sm'}; config.to_disk('ner_source_sm.cfg')"
-#      PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
+      PYTHONWARNINGS="error,ignore::DeprecationWarning" python -m spacy assemble ner_source_sm.cfg output_dir
-#    displayName: 'Test assemble CLI'
+    displayName: 'Test assemble CLI'
-#    condition: eq(variables['python_version'], '3.8')
+    condition: eq(variables['python_version'], '3.8')
-#
+
-#  - script: |
+  - script: |
-#      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
+      python -c "import spacy; config = spacy.util.load_config('ner.cfg'); config['components']['ner'] = {'source': 'ca_core_news_md'}; config.to_disk('ner_source_md.cfg')"
-#      python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
+      python -m spacy assemble ner_source_md.cfg output_dir 2>&1 | grep -q W113
-#    displayName: 'Test assemble CLI vectors warning'
+    displayName: 'Test assemble CLI vectors warning'
-#    condition: eq(variables['python_version'], '3.8')
+    condition: eq(variables['python_version'], '3.8')
 
   - script: |
       python .github/validate_universe_json.py website/meta/universe.json

CONTRIBUTING.md

@@ -271,7 +271,8 @@ except:  # noqa: E722
 
 ### Python conventions
 
-All Python code must be written **compatible with Python 3.6+**.
+All Python code must be written **compatible with Python 3.6+**. More detailed
+code conventions can be found in the [developer docs](https://github.com/explosion/spaCy/blob/master/extra/DEVELOPER_DOCS/Code%20Conventions.md).
 
 #### I/O and handling paths
 

spacy/about.py

@@ -1,6 +1,6 @@
 # fmt: off
 __title__ = "spacy"
-__version__ = "3.4.0"
+__version__ = "3.4.1"
 __download_url__ = "https://github.com/explosion/spacy-models/releases/download"
 __compatibility__ = "https://raw.githubusercontent.com/explosion/spacy-models/master/compatibility.json"
 __projects__ = "https://github.com/explosion/projects"

spacy/cli/pretrain.py

@@ -61,7 +61,7 @@ def pretrain_cli(
         # TODO: What's the solution here? How do we handle optional blocks?
         msg.fail("The [pretraining] block in your config is empty", exits=1)
     if not output_dir.exists():
-        output_dir.mkdir()
+        output_dir.mkdir(parents=True)
         msg.good(f"Created output directory: {output_dir}")
     # Save non-interpolated config
     raw_config.to_disk(output_dir / "config.cfg")

spacy/ml/_precomputable_affine.py

@@ -26,7 +26,11 @@ def forward(model, X, is_train):
     Yf = model.ops.alloc2f(X.shape[0] + 1, nF * nO * nP, zeros=False)
     model.ops.gemm(X, W.reshape((nF * nO * nP, nI)), trans2=True, out=Yf[1:])
     Yf = Yf.reshape((Yf.shape[0], nF, nO, nP))
-    Yf[0] = model.get_param("pad")
+
+    # Set padding. Padding has shape (1, nF, nO, nP). Unfortunately, we cannot
+    # change its shape to (nF, nO, nP) without breaking existing models. So
+    # we'll squeeze the first dimension here.
+    Yf[0] = model.ops.xp.squeeze(model.get_param("pad"), 0)
 
     def backward(dY_ids):
         # This backprop is particularly tricky, because we get back a different

spacy/tests/test_cli.py

@@ -589,7 +589,6 @@ def test_string_to_list_intify(value):
     assert string_to_list(value, intify=True) == [1, 2, 3]
 
 
-@pytest.mark.skip(reason="Temporarily skip for dev version")
 def test_download_compatibility():
     spec = SpecifierSet("==" + about.__version__)
     spec.prereleases = False
@@ -600,7 +599,6 @@ def test_download_compatibility():
         assert get_minor_version(about.__version__) == get_minor_version(version)
 
 
-@pytest.mark.skip(reason="Temporarily skip for dev version")
 def test_validate_compatibility_table():
     spec = SpecifierSet("==" + about.__version__)
     spec.prereleases = False

spacy/tokens/span.pyi

@@ -120,6 +120,10 @@ class Span:
     ent_id: int
     ent_id_: str
     @property
+    def id(self) -> int: ...
+    @property
+    def id_(self) -> str: ...
+    @property
     def orth_(self) -> str: ...
     @property
     def lemma_(self) -> str: ...