langchain/libs/community/langchain_community/document_loaders/parsers/generic.py
Bagatur a0c2281540
infra: update mypy 1.10, ruff 0.5 (#23721)
```python
"""python scripts/update_mypy_ruff.py"""
import glob
import tomllib
from pathlib import Path

import toml
import subprocess
import re

ROOT_DIR = Path(__file__).parents[1]


def main():
    for path in glob.glob(str(ROOT_DIR / "libs/**/pyproject.toml"), recursive=True):
        print(path)
        with open(path, "rb") as f:
            pyproject = tomllib.load(f)
        try:
            pyproject["tool"]["poetry"]["group"]["typing"]["dependencies"]["mypy"] = (
                "^1.10"
            )
            pyproject["tool"]["poetry"]["group"]["lint"]["dependencies"]["ruff"] = (
                "^0.5"
            )
        except KeyError:
            continue
        with open(path, "w") as f:
            toml.dump(pyproject, f)
        cwd = "/".join(path.split("/")[:-1])
        completed = subprocess.run(
            "poetry lock --no-update; poetry install --with typing; poetry run mypy . --no-color",
            cwd=cwd,
            shell=True,
            capture_output=True,
            text=True,
        )
        logs = completed.stdout.split("\n")

        to_ignore = {}
        for l in logs:
            if re.match("^(.*)\:(\d+)\: error:.*\[(.*)\]", l):
                path, line_no, error_type = re.match(
                    "^(.*)\:(\d+)\: error:.*\[(.*)\]", l
                ).groups()
                if (path, line_no) in to_ignore:
                    to_ignore[(path, line_no)].append(error_type)
                else:
                    to_ignore[(path, line_no)] = [error_type]
        print(len(to_ignore))
        for (error_path, line_no), error_types in to_ignore.items():
            all_errors = ", ".join(error_types)
            full_path = f"{cwd}/{error_path}"
            try:
                with open(full_path, "r") as f:
                    file_lines = f.readlines()
            except FileNotFoundError:
                continue
            file_lines[int(line_no) - 1] = (
                file_lines[int(line_no) - 1][:-1] + f"  # type: ignore[{all_errors}]\n"
            )
            with open(full_path, "w") as f:
                f.write("".join(file_lines))

        subprocess.run(
            "poetry run ruff format .; poetry run ruff --select I --fix .",
            cwd=cwd,
            shell=True,
            capture_output=True,
            text=True,
        )


if __name__ == "__main__":
    main()

```
2024-07-03 10:33:27 -07:00

72 lines
2.4 KiB
Python

"""Code for generic / auxiliary parsers.
This module contains some logic to help assemble more sophisticated parsers.
"""
from typing import Iterator, Mapping, Optional
from langchain_core.documents import Document
from langchain_community.document_loaders.base import BaseBlobParser
from langchain_community.document_loaders.blob_loaders.schema import Blob
class MimeTypeBasedParser(BaseBlobParser):
"""Parser that uses `mime`-types to parse a blob.
This parser is useful for simple pipelines where the mime-type is sufficient
to determine how to parse a blob.
To use, configure handlers based on mime-types and pass them to the initializer.
Example:
.. code-block:: python
from langchain_community.document_loaders.parsers.generic import MimeTypeBasedParser
parser = MimeTypeBasedParser(
handlers={
"application/pdf": ...,
},
fallback_parser=...,
)
""" # noqa: E501
def __init__(
self,
handlers: Mapping[str, BaseBlobParser],
*,
fallback_parser: Optional[BaseBlobParser] = None,
) -> None:
"""Define a parser that uses mime-types to determine how to parse a blob.
Args:
handlers: A mapping from mime-types to functions that take a blob, parse it
and return a document.
fallback_parser: A fallback_parser parser to use if the mime-type is not
found in the handlers. If provided, this parser will be
used to parse blobs with all mime-types not found in
the handlers.
If not provided, a ValueError will be raised if the
mime-type is not found in the handlers.
"""
self.handlers = handlers
self.fallback_parser = fallback_parser
def lazy_parse(self, blob: Blob) -> Iterator[Document]:
"""Load documents from a blob."""
mimetype = blob.mimetype
if mimetype is None:
raise ValueError(f"{blob} does not have a mimetype.")
if mimetype in self.handlers:
handler = self.handlers[mimetype]
yield from handler.lazy_parse(blob)
else:
if self.fallback_parser is not None:
yield from self.fallback_parser.lazy_parse(blob)
else:
raise ValueError(f"Unsupported mime type: {mimetype}")