remove textract references

.github/workflows/tests.yml

@@ -39,9 +39,9 @@ jobs:
           PYTHON_KEYRING_BACKEND: keyring.backends.null.Keyring
         run: |
           python3 -m pip install -U pip setuptools
-          python3 -m pip install poetry==1.7.1 lxml
+          python3 -m pip install poetry==1.7.1
           poetry config virtualenvs.create false
-          poetry install --with=dev --extras=textract
+          poetry install --with=dev
 
       - name: Version info
         run: |

CHANGELOG.md

@@ -3,7 +3,7 @@
 ## [Unreleased]
 
 - Integrated `pdftotext`, `pdfminer` and `docx2txt` interfaces into `filecontent` filter.
-- Removed `textract` and many other dependencies as they are no longer needed.
+- Removed `textract` and ~50 MB of dependencies as they are no longer needed.
 - Python 3.12 support
 
 ## v3.1.1 (2024-02-11)

Dockerfile

@@ -12,7 +12,7 @@ FROM base as pydeps
 RUN pip install "poetry==1.7.1" && \
     python -m venv ${VIRTUAL_ENV}
 COPY pyproject.toml poetry.lock ./
-RUN poetry install --only=main --extras=textract --no-interaction
+RUN poetry install --only=main --no-interaction
 
 
 FROM base as final

README.md

@@ -77,13 +77,6 @@ Installation is done via pip. Note that the package name is `organize-tool`:
 pip install -U organize-tool
 ```
 
-If you want the text extraction capabilities, install with `textract` like this (the
-qoutes are important):
-
-```bash
-pip install "organize-tool[texttract]"
-```
-
 This command can also be used to update to the newest version. Now you can run `organize --help` to check if the installation was successful.
 
 ### Create your first rule

organize/filters/filecontent.py

@@ -3,7 +3,7 @@
 import subprocess
 from functools import lru_cache
 from pathlib import Path
-from typing import Any, ClassVar
+from typing import Any, Callable, ClassVar, Dict
 
 from pydantic.config import ConfigDict
 from pydantic.dataclasses import dataclass
@@ -54,9 +54,9 @@ def _pdftotext_available() -> bool:
 
 def _extract_with_pdftotext(path: Path, keep_layout: bool) -> str:
     if keep_layout:
-        args = ("-layout", str(path), "-")
+        args = ["-layout", str(path), "-"]
     else:
-        args = (str(path), "-")
+        args = [str(path), "-"]
     result = subprocess.check_output(("pdftotext", *args), text=True)
     return clean(result)
 
@@ -74,13 +74,13 @@ def extract_pdf(path: Path, keep_layout: bool = True) -> str:
 
 
 def extract_docx(path: Path) -> str:
-    import docx2txt
+    import docx2txt  # type: ignore
 
     result = docx2txt.process(path)
     return clean(result)
 
 
-EXTRACTORS = {
+EXTRACTORS: Dict[str, Callable[[Path], str]] = {
     ".md": extract_txt,
     ".txt": extract_txt,
     ".log": extract_txt,