Custom warning if the doc_bin is too large (#8069)

* custom warning if the doc_bin is too large

* cleanup

* Update spacy/errors.py

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

* fix numbering

* fixing numbering once more

* fixing this seems to be pretty hard

Co-authored-by: Adriane Boyd <adrianeboyd@gmail.com>

spacy/errors.py

@@ -490,6 +490,11 @@ class Errors:
     E202 = ("Unsupported alignment mode '{mode}'. Supported modes: {modes}.")
 
     # New errors added in v3.x
+    E870 = ("Could not serialize the DocBin because it is too large. Consider "
+            "splitting up your documents into several doc bins and serializing "
+            "each separately. spacy.Corpus.v1 will search recursively for all "
+            "*.spacy files if you provide a directory instead of a filename as "
+            "the 'path'.")
     E871 = ("Error encountered in nlp.pipe with multiprocessing:\n\n{error}")
     E872 = ("Unable to copy tokenizer from base model due to different "
             'tokenizer settings: current tokenizer config "{curr_config}" '

spacy/tokens/_serialize.py

@@ -246,7 +246,10 @@ class DocBin:
         """
         path = ensure_path(path)
         with path.open("wb") as file_:
-            file_.write(self.to_bytes())
+            try:
+                file_.write(self.to_bytes())
+            except ValueError:
+                raise ValueError(Errors.E870)
 
     def from_disk(self, path: Union[str, Path]) -> "DocBin":
         """Load the DocBin from a file (typically called .spacy).