Merge pull request #6168 from explosion/fix/default-corpus-values

spacy/cli/templates/quickstart_training.jinja

@@ -4,8 +4,8 @@ can help generate the best possible configuration, given a user's requirements.
 {%- set use_transformer = (transformer_data and hardware != "cpu") -%}
 {%- set transformer = transformer_data[optimize] if use_transformer else {} -%}
 [paths]
-train = ""
-dev = ""
+train = null
+dev = null
 
 [system]
 {% if use_transformer -%}

spacy/default_config.cfg

@@ -1,6 +1,6 @@
 [paths]
-train = ""
-dev = ""
+train = null
+dev = null
 vectors = null
 vocab_data = null
 init_tok2vec = null

spacy/errors.py

@@ -477,6 +477,8 @@ class Errors:
     E201 = ("Span index out of range.")
 
     # TODO: fix numbering after merging develop into master
+    E913 = ("Corpus path can't be None. Maybe you forgot to define it in your "
+            "config.cfg or override it on the CLI?")
     E914 = ("Executing {name} callback failed. Expected the function to "
             "return the nlp object but got: {value}. Maybe you forgot to return "
             "the modified object in your function?")

spacy/tests/serialize/test_serialize_config.py

@@ -14,8 +14,8 @@ from ..util import make_tempdir
 
 nlp_config_string = """
 [paths]
-train = ""
-dev = ""
+train = null
+dev = null
 
 [corpora]
 
@@ -309,7 +309,7 @@ def test_config_interpolation():
     config = Config().from_str(nlp_config_string, interpolate=False)
     assert config["corpora"]["train"]["path"] == "${paths.train}"
     interpolated = config.interpolate()
-    assert interpolated["corpora"]["train"]["path"] == ""
+    assert interpolated["corpora"]["train"]["path"] is None
     nlp = English.from_config(config)
     assert nlp.config["corpora"]["train"]["path"] == "${paths.train}"
     # Ensure that variables are preserved in nlp config
@@ -317,10 +317,10 @@ def test_config_interpolation():
     assert config["components"]["tagger"]["model"]["tok2vec"]["width"] == width
     assert nlp.config["components"]["tagger"]["model"]["tok2vec"]["width"] == width
     interpolated2 = nlp.config.interpolate()
-    assert interpolated2["corpora"]["train"]["path"] == ""
+    assert interpolated2["corpora"]["train"]["path"] is None
     assert interpolated2["components"]["tagger"]["model"]["tok2vec"]["width"] == 342
     nlp2 = English.from_config(interpolated)
-    assert nlp2.config["corpora"]["train"]["path"] == ""
+    assert nlp2.config["corpora"]["train"]["path"] is None
     assert nlp2.config["components"]["tagger"]["model"]["tok2vec"]["width"] == 342
 
 

spacy/training/corpus.py

@@ -7,7 +7,7 @@ import srsly
 from .. import util
 from .augment import dont_augment
 from .example import Example
-from ..errors import Warnings
+from ..errors import Warnings, Errors
 from ..tokens import DocBin, Doc
 from ..vocab import Vocab
 
@@ -20,12 +20,14 @@ FILE_TYPE = ".spacy"
 
 @util.registry.readers("spacy.Corpus.v1")
 def create_docbin_reader(
-    path: Path,
+    path: Optional[Path],
     gold_preproc: bool,
     max_length: int = 0,
     limit: int = 0,
     augmenter: Optional[Callable] = None,
 ) -> Callable[["Language"], Iterable[Example]]:
+    if path is None:
+        raise ValueError(Errors.E913)
     util.logger.debug(f"Loading corpus from path: {path}")
     return Corpus(
         path,