Merge pull request #7 from homeylab/clean_up

Clean up

.dockerignore

@@ -0,0 +1,167 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#pdm.lock
+#   pdm stores project-wide configurations in .pdm.toml, but it is recommended to not include it
+#   in version control.
+#   https://pdm.fming.dev/#use-with-ide
+.pdm.toml
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+
+## Local
+local/
+
+## test outputs
+bkps/

Dockerfile

@@ -0,0 +1,31 @@
+
+ARG BASE_IMAGE=python
+ARG BASE_IMAGE_TAG=3.11-slim-python
+
+FROM ${BASE_IMAGE}:${BASE_IMAGE_TAG}
+
+# Get security updates and clean up apt cache for smaller size
+RUN apt update -y && apt upgrade -y && \
+    apt install dumb-init && \
+    rm -rf /var/lib/apt/lists/*
+
+ARG DOCKER_WORK_DIR
+ARG DOCKER_CONFIG_DIR
+ARG DOCKER_EXPORT_DIR
+
+ENV DOCKER_CONFIG_DIR=${DOCKER_CONFIG_DIR}
+ENV DOCKER_EXPORT_DIR=${DOCKER_EXPORT_DIR}
+
+WORKDIR ${DOCKER_WORK_DIR}
+
+COPY . .
+
+RUN pip install .
+
+RUN mkdir -p ${DOCKER_CONFIG_DIR} && \
+    mkdir -p ${DOCKER_EXPORT_DIR}
+
+USER nobody
+
+ENTRYPOINT ["/usr/bin/dumb-init", "--"]
+CMD [ "./entrypoint.sh" ]

Makefile

@@ -1,2 +1,31 @@
+## DOCKER BUILD VARS
+BASE_IMAGE=python
+BASE_IMAGE_TAG=3.11-slim-bookworm
+IMAGE_NAME=homeylab/bookstack-file-exporter
+IMAGE_TAG=test
+DOCKER_WORK_DIR=/export
+DOCKER_CONFIG_DIR=/export/config
+DOCKER_EXPORT_DIR=/export/dump
+
 test_local:
-	pip install -e .
+	pip install -e .
+
+docker_build: 
+	docker buildx build \
+	--build-arg BASE_IMAGE=${BASE_IMAGE} \
+	--build-arg BASE_IMAGE_TAG=${BASE_IMAGE_TAG} \
+	--build-arg DOCKER_WORK_DIR=${DOCKER_WORK_DIR} \
+	--build-arg DOCKER_CONFIG_DIR=${DOCKER_CONFIG_DIR} \
+	--build-arg DOCKER_EXPORT_DIR=${DOCKER_EXPORT_DIR} \
+	-t ${IMAGE_NAME}:${IMAGE_TAG} \
+	--no-cache .
+
+docker_push:
+	docker push ${IMAGE_NAME}:${IMAGE_TAG}
+
+docker_test:
+	docker run \
+	-e LOG_LEVEL='debug' \
+	-v ${CURDIR}/local/config.yml:/export/config/config.yml:ro \
+	-v ${CURDIR}/bkps:/export/dump \
+	${IMAGE_NAME}:${IMAGE_TAG}

bookstack_file_exporter/__init__.py

@@ -0,0 +1 @@
+

bookstack_file_exporter/archiver/__init__.py

@@ -0,0 +1 @@
+

bookstack_file_exporter/archiver/archiver.py

@@ -1,12 +1,15 @@
 from typing import List, Dict, Union
 from time import sleep
 from datetime import datetime
+import logging
 
 from bookstack_file_exporter.exporter.node import Node
 from bookstack_file_exporter.archiver import util
 from bookstack_file_exporter.archiver.minio_archiver import MinioArchiver
 from bookstack_file_exporter.config_helper.remote import StorageProviderConfig
 
+log = logging.getLogger(__name__)
+
 _META_FILE_SUFFIX = "_meta"
 _TAR_GZ_SUFFIX = ".tgz"
 
@@ -36,12 +39,11 @@ class Archiver:
     Returns:
         Archiver instance with attributes that are accessible for use for file level archival and backup.
     """
-    def __init__(self, base_dir: str, add_meta: Union[bool, None], base_page_url: str, headers: Dict[str, str], object_storage_config: Dict[str, StorageProviderConfig]):
+    def __init__(self, base_dir: str, add_meta: Union[bool, None], base_page_url: str, headers: Dict[str, str]):
         self.base_dir = base_dir
         self.add_meta = add_meta
         self.base_page_url = base_page_url
         self._headers = headers
-        self._object_storage_config = object_storage_config
         self._root_dir = self.generate_root_folder(self.base_dir)
         # the tar file will be name of parent export directory, bookstack-<timestamp>, and .tgz extension
         self._tar_file = f"{self._root_dir}{_FILE_EXTENSION_MAP['tar']}"
@@ -58,6 +60,7 @@ def archive(self, page_nodes: Dict[int, Node], export_formats: List[str]):
     # convert to bytes to be agnostic to end destination (future use case?)
     def _gather(self, page_node: Node, export_format: str):
         raw_data = self._get_data_format(page_node.id, export_format)
+        log.debug(f"Output directory for exports set to: {self._root_dir}")
         self._gather_local(page_node.file_path, raw_data, export_format, page_node.meta)
 
     def _gather_local(self, page_path: str, data: bytes, export_format: str, meta_data: Union[bytes, None]):

bookstack_file_exporter/common/__init__.py

@@ -0,0 +1 @@
+

bookstack_file_exporter/config_helper/__init__.py

@@ -0,0 +1 @@
+

bookstack_file_exporter/config_helper/config_helper.py

@@ -50,7 +50,7 @@ class ConfigNode:
     def __init__(self, args: argparse.Namespace):
         self.unassigned_book_dir = _UNASSIGNED_BOOKS_DIR
         self.user_inputs = self._generate_config(args.config_file)
-        self._base_dir_name = self._set_base_dir()
+        self._base_dir_name = self._set_base_dir(args.output_dir)
         self._token_id, self._token_secret = self._generate_credentials()
         self._headers = self._generate_headers()
         self._urls = self._generate_urls()
@@ -136,8 +136,12 @@ def _generate_urls(self) -> Dict[str, str]:
             urls[key] = f"{url_prefix}{self.user_inputs.host}/{value}"
         return urls
 
-    def _set_base_dir(self) -> str:
+    def _set_base_dir(self, cmd_output_dir: str) -> str:
         output_dir = self.user_inputs.output_path
+        # override if command line specified
+        if cmd_output_dir:
+            log.debug("Output directory overwritten by command line option")
+            output_dir = cmd_output_dir
         # check if user provided an output path
         if output_dir:
             # detect trailing slash
@@ -178,6 +182,7 @@ def _check_var(env_key: str, default_val: str) -> str:
         env_value = os.environ.get(env_key, "")
         # env value takes precedence
         if env_value:
+            log.debug(f"env key: {env_key} specified. Will override configuration file value if set.")
             return env_value
         # check for optional inputs, if env and input is missing
         if not env_value and not default_val:

bookstack_file_exporter/exporter/__init__.py

@@ -0,0 +1 @@
+