doms_databasen -> domsdatabasen

.github/workflows/docs.yaml

@@ -29,7 +29,7 @@ jobs:
           pip install -r requirements.txt
 
       - name: Build documentation
-        run: pip install pdoc==7.3.0 && pdoc --docformat google src/doms_databasen -o docs
+        run: pip install pdoc==7.3.0 && pdoc --docformat google src/domsdatabasen -o docs
 
       - name: Compress documentation
         run: tar --directory docs/ -hcf artifact.tar .

.gitignore

@@ -94,8 +94,8 @@ outputs/
 multirun/
 
 # Documentation
-docs/doms_databasen/
-docs/doms_databasen.html
+docs/domsdatabasen/
+docs/domsdatabasen.html
 docs/index.html
 docs/search.js
 

.pre-commit-config.yaml

@@ -7,7 +7,7 @@ repos:
     rev: v0.0.290
     hooks:
       - id: ruff
-        exclude: src/doms_databasen/constants.py
+        exclude: src/domsdatabasen/constants.py
         args: [--fix, --exit-non-zero-on-fix]
         types_or: [python, pyi, jupyter]
 -   repo: https://github.com/kynan/nbstripout

CONTRIBUTING.md

@@ -1,4 +1,4 @@
-# Welcome to doms_databasen contributing guide
+# Welcome to domsdatabasen contributing guide
 
 Thank you for investing your time in contributing to our project! :sparkles:.
 
@@ -29,11 +29,11 @@ resources to help you get started with open source contributions:
 If you spot a problem with the package, [search if an issue already
 exists](https://docs.github.com/en/github/searching-for-information-on-github/searching-on-github/searching-issues-and-pull-requests#search-by-the-title-body-or-comments).
 If a related issue doesn't exist, you can open a new issue using a relevant [issue
-form](https://github.com/alexandrainst/doms_databasen/issues).
+form](https://github.com/alexandrainst/domsdatabasen/issues).
 
 #### Solve an issue
 
-Scan through our [existing issues](https://github.com/alexandrainst/doms_databasen/issues)
+Scan through our [existing issues](https://github.com/alexandrainst/domsdatabasen/issues)
 to find one that interests you. You can narrow down the search using `labels` as
 filters. See [Labels](/contributing/how-to-use-labels.md) for more information. If you
 find an issue to work on, you are welcome to open a PR with a fix.
@@ -87,4 +87,4 @@ questions or request for additional information.
 
 ### Your PR is merged!
 
-Congratulations :tada::tada: The doms_databasen team thanks you :sparkles:.
+Congratulations :tada::tada: The domsdatabasen team thanks you :sparkles:.

Makefile

@@ -35,7 +35,7 @@ help:
 	@grep -E '^[0-9a-zA-Z_-]+:.*?## .*$$' makefile | sort | awk 'BEGIN {FS = ":.*?## "}; {printf "\033[36m%-30s\033[0m %s\n", $$1, $$2}'
 
 install: ## Install dependencies
-	@echo "Installing the 'doms_databasen' project..."
+	@echo "Installing the 'domsdatabasen' project..."
 	@$(MAKE) --quiet install-brew
 	@$(MAKE) --quiet install-gpg
 	@$(MAKE) --quiet generate-gpg-key
@@ -45,7 +45,7 @@ install: ## Install dependencies
 	@$(MAKE) --quiet setup-environment-variables
 	@$(MAKE) --quiet setup-git
 	@$(MAKE) --quiet add-repo-to-git
-	@echo "Installed the 'doms_databasen' project. You can now activate your virtual environment with 'source .venv/bin/activate'."
+	@echo "Installed the 'domsdatabasen' project. You can now activate your virtual environment with 'source .venv/bin/activate'."
 	@echo "Note that this is a Poetry project. Use 'poetry add <package>' to install new dependencies and 'poetry remove <package>' to remove them."
 
 install-brew:
@@ -130,11 +130,11 @@ add-repo-to-git:
 		git commit --quiet -m "Initial commit"; \
 	fi
 	@if [ "$(shell git remote)" = "" ]; then \
-		git remote add origin [email protected]:alexandrainst/doms_databasen.git; \
+		git remote add origin [email protected]:alexandrainst/domsdatabasen.git; \
 	fi
 
 docs:  ## Generate documentation
-	@poetry run pdoc --docformat google src/doms_databasen -o docs
+	@poetry run pdoc --docformat google src/domsdatabasen -o docs
 	@echo "Saved documentation."
 
 view-docs:  ## View documentation
@@ -146,15 +146,15 @@ view-docs:  ## View documentation
 			(*CYGWIN*) openCmd='cygstart'; ;; \
 			(*) echo 'Error: Unsupported platform: $${uname}'; exit 2; ;; \
 		esac; \
-		"$${openCmd}" docs/doms_databasen.html
+		"$${openCmd}" docs/domsdatabasen.html
 
 test:
 	@poetry run pytest tests/scraper ; \
 	poetry run pytest tests/processor ; \
 
 docker:  ## Build Docker image and run container
-	@docker build -t doms_databasen .
-	@docker run -it --rm doms_databasen
+	@docker build -t domsdatabasen .
+	@docker run -it --rm domsdatabasen
 
 tree:  ## Print directory tree
 	@tree -a --gitignore -I .git .

README.md

@@ -1,4 +1,4 @@
-<a href="https://github.com/alexandrainst/doms_databasen"><img src="gfx/alexandra_logo.png" width="239" height="175" align="right" /></a>
+<a href="https://github.com/alexandrainst/domsdatabasen"><img src="gfx/alexandra_logo.png" width="239" height="175" align="right" /></a>
 # Domsdatabasen
 
 Scraping og processering af [domsdatabasen](https://domsdatabasen.dk/#).
@@ -17,11 +17,11 @@ Se `src/scripts/process.py`.
 Se `src/scripts/finalize.py`.
 
 ______________________________________________________________________
-[![Documentation](https://img.shields.io/badge/docs-passing-green)](https://alexandrainst.github.io/doms_databasen/doms_databasen.html)
-[![License](https://img.shields.io/github/license/oliverkinch/doms_databasen)](https://github.com/alexandrainst/doms_databasen/blob/master/LICENSE)
-[![LastCommit](https://img.shields.io/github/last-commit/oliverkinch/doms_databasen)](https://github.com/alexandrainst/doms_databasen/commits/master)
-[![Code Coverage](https://img.shields.io/badge/Coverage-100%25-brightgreen.svg)](https://github.com/alexandrainst/doms_databasen/tree/master/tests)
-[![Contributor Covenant](https://img.shields.io/badge/Contributor%20Covenant-2.0-4baaaa.svg)](https://github.com/alexandrainst/doms_databasen/blob/master/CODE_OF_CONDUCT.md)
+[![Documentation](https://img.shields.io/badge/docs-passing-green)](https://alexandrainst.github.io/domsdatabasen/domsdatabasen.html)
+[![License](https://img.shields.io/github/license/oliverkinch/domsdatabasen)](https://github.com/alexandrainst/domsdatabasen/blob/master/LICENSE)
+[![LastCommit](https://img.shields.io/github/last-commit/oliverkinch/domsdatabasen)](https://github.com/alexandrainst/domsdatabasen/commits/master)
+[![Code Coverage](https://img.shields.io/badge/Coverage-100%25-brightgreen.svg)](https://github.com/alexandrainst/domsdatabasen/tree/master/tests)
+[![Contributor Covenant](https://img.shields.io/badge/Contributor%20Covenant-2.0-4baaaa.svg)](https://github.com/alexandrainst/domsdatabasen/blob/master/CODE_OF_CONDUCT.md)
 
 
 Developers:
@@ -38,11 +38,11 @@ Developers:
 
 
 ## A Word on Modules and Scripts
-In the `src` directory there are two subdirectories, `doms_databasen`
+In the `src` directory there are two subdirectories, `domsdatabasen`
 and `scripts`. This is a brief explanation of the differences between the two.
 
 ### Modules
-All Python files in the `doms_databasen` directory are _modules_
+All Python files in the `domsdatabasen` directory are _modules_
 internal to the project package. Examples here could be a general data loading script,
 a definition of a model, or a training function. Think of modules as all the building
 blocks of a project.
@@ -65,7 +65,7 @@ When importing module functions/classes when you're in a script, you do it like
 would normally import from any other package:
 
 ```
-from doms_databasen import some_function
+from domsdatabasen import some_function
 ```
 
 Note that this is also how we import functions/classes in tests, since each test Python
@@ -90,7 +90,7 @@ for the repository (can be enabled on Github in the repository settings).
 Code Spaces is a new feature on Github, that allows you to develop on a project
 completely in the cloud, without having to do any local setup at all. This repo comes
 included with a configuration file for running code spaces on Github. When hosted on
-`alexandrainst/doms_databasen` then simply press the `<> Code` button
+`alexandrainst/domsdatabasen` then simply press the `<> Code` button
 and add a code space to get started, which will open a VSCode window directly in your
 browser.
 
@@ -130,7 +130,7 @@ browser.
 │   ├── scripts
 │   │   ├── fix_dot_env_file.py
 │   │   └── your_script.py
-│   └── doms_databasen
+│   └── domsdatabasen
 │       ├── __init__.py
 │       └── your_module.py
 └── tests

pyproject.toml

@@ -1,5 +1,5 @@
 [tool.poetry]
-name = "doms_databasen"
+name = "domsdatabasen"
 description = "Scraper and PDF text processor for domsdatabasen.dk"
 version = "0.2.0"
 authors = [
@@ -66,7 +66,7 @@ extend-select = [
     "D",
 ]
 exclude = [
-    "src/doms_databasen/_xpaths.py",
+    "src/domsdatabasen/_xpaths.py",
 ]
 
 [tool.ruff.pydocstyle]
@@ -100,5 +100,5 @@ filterwarnings = [
 log_cli_level = "info"
 testpaths = [
     "tests",
-    "src/doms_databasen",
+    "src/domsdatabasen",
 ]

src/domsdatabasen/__init__.py

@@ -0,0 +1 @@
+"""__init__.py file for the domsdatabasen package."""

src/doms_databasen/_exceptions.py → src/domsdatabasen/_exceptions.py

@@ -1,4 +1,4 @@
-"""Exceptions for the doms_databasen package."""
+"""Exceptions for the domsdatabasen package."""
 
 
 class PDFDownloadException(Exception):

src/doms_databasen/_utils.py → src/domsdatabasen/_utils.py

@@ -1,4 +1,4 @@
-"""Utility function for the doms_databasen package."""
+"""Utility function for the domsdatabasen package."""
 
 import json
 from typing import List

src/doms_databasen/dataset_builder.py → src/domsdatabasen/dataset_builder.py

@@ -8,7 +8,7 @@
 
 from omegaconf import DictConfig
 
-from doms_databasen._utils import append_jsonl, init_jsonl, read_json
+from domsdatabasen._utils import append_jsonl, init_jsonl, read_json
 
 logger = getLogger(__name__)
 

src/doms_databasen/processor.py → src/domsdatabasen/processor.py

@@ -173,7 +173,7 @@ def _raw_data_exists(self, case_dir) -> bool:
         and contains two files: the PDF document and the tabular data.
 
         Same code as the method `_already_scraped` from class `Scraper`
-        (src/doms_databasen/scraper.py).
+        (src/domsdatabasen/scraper.py).
 
         Args:
             case_dir (Path):

src/scripts/finalize.py

@@ -11,7 +11,7 @@
 
 
 import hydra
-from doms_databasen.dataset_builder import DatasetBuilder
+from domsdatabasen.dataset_builder import DatasetBuilder
 from omegaconf import DictConfig
 
 

src/scripts/process.py

@@ -17,7 +17,7 @@
 import logging
 
 import hydra
-from doms_databasen.processor import Processor
+from domsdatabasen.processor import Processor
 from omegaconf import DictConfig
 
 logger = logging.getLogger(__name__)

src/scripts/scrape.py

@@ -17,7 +17,7 @@
 import logging
 
 import hydra
-from doms_databasen.scraper import Scraper
+from domsdatabasen.scraper import Scraper
 from omegaconf import DictConfig
 
 logger = logging.getLogger(__name__)

tests/processor/test_processor.py

@@ -2,7 +2,7 @@
 
 
 import pytest
-from doms_databasen.processor import Processor
+from domsdatabasen.processor import Processor
 
 
 @pytest.fixture(scope="module")

tests/processor/test_text_extraction.py

@@ -3,7 +3,7 @@
 import cv2
 import numpy as np
 import pytest
-from doms_databasen._text_extraction import PDFTextReader
+from domsdatabasen._text_extraction import PDFTextReader
 from PIL import Image
 
 

tests/scraper/conftest.py

@@ -3,7 +3,7 @@
 import shutil
 
 import pytest
-from doms_databasen.scraper import Scraper
+from domsdatabasen.scraper import Scraper
 from hydra import compose, initialize
 
 # Initialise Hydra