explosion/spaCy
1
1
Fork 0
mirror of https://github.com/explosion/spaCy.git synced 2025-08-06 21:30:22 +03:00
Code Issues Packages Projects Releases Wiki Activity

black

Browse Source
This commit is contained in:
kadarakos 2022-12-08 11:30:19 +00:00
parent a9991abf8f
commit 185293aa78
1 changed files with 21 additions and 17 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

38
spacy/cli/apply.py
View File

@ -14,22 +14,27 @@ from ..vocab import Vocab
from ..util import ensure_path, load_model from ..util import ensure_path, load_model
path_help = ("Location of the documents to predict on. " path_help = (
"Can be a single file in .spacy format or a " "Location of the documents to predict on. "
".jsonl file. Files with other extensions " "Can be a single file in .spacy format or a "
"are treated as single plain text documents. " ".jsonl file. Files with other extensions "
"If a directory is provided " "are treated as single plain text documents. "
"it is traversed recursively to grab all files to " "If a directory is provided "
"be processed. The files can be a mixture of .spacy, " "it is traversed recursively to grab all files to "
".jsonl and text files. If .jsonl is provided the " "be processed. The files can be a mixture of .spacy, "
"specified field is going to be grabbed ('text' " ".jsonl and text files. If .jsonl is provided the "
"by default).") "specified field is going to be grabbed ('text' "
"by default)."
)
out_help = "Path where to save the result .spacy file" out_help = "Path where to save the result .spacy file"
code_help = ("Path to Python file with additional " code_help = (
"code (registered functions) to be imported") "Path to Python file with additional " "code (registered functions) to be imported"
)
gold_help = "Use gold preprocessing provided in the .spacy files" gold_help = "Use gold preprocessing provided in the .spacy files"
force_msg = ("The provided output file already exists. " force_msg = (
"To force overwriting the output file, set the --force or -F flag.") "The provided output file already exists. "
"To force overwriting the output file, set the --force or -F flag."
)
DocOrStrStream = Union[Iterable[str], Iterable[Doc]] DocOrStrStream = Union[Iterable[str], Iterable[Doc]]
@ -52,8 +57,7 @@ def _stream_jsonl(path: Path, field: str) -> Iterable[str]:
for entry in srsly.read_jsonl(path): for entry in srsly.read_jsonl(path):
if field not in entry: if field not in entry:
raise msg.fail( raise msg.fail(
f"{path} does not contain the required '{field}' field.", f"{path} does not contain the required '{field}' field.", exits=1
exits=1
) )
else: else:
yield entry[field] yield entry[field]
@ -64,7 +68,7 @@ def _stream_texts(paths: Iterable[Path]) -> Iterable[str]:
Yields strings from text files in paths. Yields strings from text files in paths.
""" """
for path in paths: for path in paths:
with open(path, 'r') as fin: with open(path, "r") as fin:
text = fin.read() text = fin.read()
yield text yield text