explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-02-06 06:30:35 +03:00
Code Issues Packages Projects Releases Wiki Activity

Update converter

Browse Source
This commit is contained in:
Matthew Honnibal 2020-06-20 16:00:14 +02:00
parent f5780cb160
commit 5d89b1840e
1 changed files with 1 additions and 12 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
spacy/cli/convert.py
View File

@ -25,17 +25,6 @@ CONVERTERS = {
} }
ALL_ATTRS = [
"ORTH",
"TAG",
"HEAD",
"DEP",
"SENT_START",
"ENT_IOB",
"ENT_TYPE",
"LEMMA",
"MORPH",
]
# File types # File types
FILE_TYPES = ("json", "jsonl", "msg") FILE_TYPES = ("json", "jsonl", "msg")
FILE_TYPES_STDOUT = ("json", "jsonl") FILE_TYPES_STDOUT = ("json", "jsonl")
@ -91,7 +80,7 @@ def convert(
data = docs2json(docs) data = docs2json(docs)
srsly.write_json(output_file, docs2json(docs)) srsly.write_json(output_file, docs2json(docs))
else: else:
data = DocBin(attrs=ALL_ATTRS, docs=docs).to_bytes() data = DocBin(docs=docs).to_bytes()
with output_file.open("wb") as file_: with output_file.open("wb") as file_:
file_.write(data) file_.write(data)
msg.good(f"Generated output file ({len(docs)} documents): {output_file}") msg.good(f"Generated output file ({len(docs)} documents): {output_file}")