Merge branch 'main' into sphinx-docs

.cruft.json

@@ -4,7 +4,7 @@
   "checkout": null,
   "context": {
     "cookiecutter": {
-      "project_name": "dso",
+      "project_name": "dso-core",
       "package_name": "dso",
       "project_description": "data science operations",
       "author_full_name": "Gregor Sturm",

.github/workflows/pre_commit.yml

@@ -1,24 +1,26 @@
-name: "DSO lint"
 on:
   push:
     branches: [main]
   pull_request:
+    branches: [main]
+
+name: pre-commit
 
 jobs:
-  pre_commit:
-    name: "pre-commit"
+  pre-commit:
+    permissions:
+      # Give the default GITHUB_TOKEN write permission to commit and push the
+      # added or changed files to the repository.
+      contents: write
     runs-on: ubuntu-latest
     steps:
       - uses: actions/checkout@v4
         with:
           ref: ${{ github.head_ref }}
 
-      - uses: actions/setup-python@v5
-        with:
-          python-version: "3.12"
-          cache: "pip"
-
       - uses: pre-commit/[email protected]
 
       - uses: stefanzweifel/git-auto-commit-action@v5
         if: '!cancelled()'
+        with:
+          commit_message: pre-commit autofixes

.github/workflows/release.yml

@@ -11,7 +11,7 @@ jobs:
     runs-on: ubuntu-latest
     environment:
       name: pypi
-      url: https://pypi.org/p/dso # TODO update once settled on a name
+      url: https://pypi.org/p/dso-core
     permissions:
       id-token: write # IMPORTANT: this permission is mandatory for trusted publishing
     steps:

.pre-commit-config.yaml

@@ -12,7 +12,7 @@ repos:
 #       - id: prettier
 #         exclude: '^src/dso/templates/.*\.yaml$' # prettier messes with jinja2 templating here
   - repo: https://github.com/astral-sh/ruff-pre-commit
-    rev: v0.4.7
+    rev: v0.6.8
     hooks:
       - id: ruff
         types_or: [python, pyi, jupyter]

CHANGELOG.md

@@ -8,6 +8,12 @@ and this project adheres to [Semantic Versioning][].
 [keep a changelog]: https://keepachangelog.com/en/1.0.0/
 [semantic versioning]: https://semver.org/spec/v2.0.0.html
 
+## [Unreleased]
+
+### New Features
+
+-   `dso watermark` now supports files in PDF format. With this change, quarto reports using the watermark feature can
+    be rendered to PDF, too.
 
 ## v0.8.2
 

CODE_OF_CONDUCT.md

@@ -0,0 +1,127 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the package maintainers via the communication channels listed in their GitHub profiles.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.

README.md

@@ -117,13 +117,17 @@ companion package [`dso-r`](https://github.com/Boehringer-Ingelheim/dso-r) that
 
 DSO requires Python 3.10 or later.
 
-You can install it with pip using
+You can install the latest version with pip using
 
 ```bash
-pip install git+https://github.com/Boehringer-Ingelheim/dso.git@main
+pip install dso-core
 ```
 
-The tool will be made available on PyPI in the near future.
+Alternatively, you can install the development version from GitHub:
+
+```bash
+pip install git+https://github.com/Boehringer-Ingelheim/dso.git@main
+```
 
 ## Release notes
 

pyproject.toml

@@ -1,10 +1,9 @@
 [build-system]
 build-backend = "hatchling.build"
-requires = [ "hatchling" ]
+requires = [ "hatch-vcs", "hatchling" ]
 
 [project]
-name = "dso"
-version = "0.8.2"
+name = "dso-core"
 description = "Data Science Operations on top of dvc"
 readme = "README.md"
 license = { file = "LICENSE" }
@@ -23,13 +22,15 @@ classifiers = [
   "Programming Language :: Python :: 3.11",
   "Programming Language :: Python :: 3.12",
 ]
+dynamic = [ "version" ]
 dependencies = [
   "dvc",
   "jinja2",
   "panflute",
   "pillow",
   "platformdirs",
   "pre-commit",
+  "pypdf",
   "pyyaml",
   "questionary",
   "rich-click",
@@ -68,6 +69,12 @@ urls.Source = "https://github.com/Boehringer-Ingelheim/dso"
 scripts.dso = "dso:cli"
 scripts.dso_pandocfilter = "dso.pandocfilter:main"
 
+[tool.hatch.version]
+source = "vcs"
+
+[tool.hatch.build.targets.wheel]
+packages = [ "src/dso" ]
+
 [tool.ruff]
 line-length = 120
 src = [ "src" ]

src/dso/_metadata.py

@@ -1,3 +1,3 @@
 from importlib.metadata import version
 
-__version__ = version("dso")
+__version__ = version("dso-core")

src/dso/templates/init/default/.ruff.toml

@@ -1,43 +1,45 @@
 line-length = 120
 extend-include = ["*.ipynb"]
-unfixable = ["F841"]
-select = [
-    "F",  # Errors detected by Pyflakes
-    "E",  # Error detected by Pycodestyle
-    "W",  # Warning detected by Pycodestyle
-    "I",  # isort
-    "D",  # pydocstyle
-    "B",  # flake8-bugbear
-    "TID",  # flake8-tidy-imports
-    "C4",  # flake8-comprehensions
-    "BLE",  # flake8-blind-except
-    "UP",  # pyupgrade
-    "RUF100",  # Report unused noqa directives
-]
-ignore = [
-    # line too long -> we accept long comment lines; black gets rid of long code lines
-    "E501",
-    # Do not assign a lambda expression, use a def -> lambda expression assignments are convenient
-    "E731",
-    # allow I, O, l as variable names -> I is the identity matrix
-    "E741",
-    # Missing docstring in public package
-    "D104",
-    # Missing docstring in public module
-    "D100",
-    # Missing docstring in __init__
-    "D107",
-    # Errors from function calls in argument defaults. These are fine when the result is immutable.
-    "B008",
-    # __magic__ methods are are often self-explanatory, allow missing docstrings
-    "D105",
-    # first line should end with a period [Bug: doesn't work with single-line docstrings]
-    "D400",
-    # First line should be in imperative mood; try rephrasing
-    "D401",
-    ## Disable one in each pair of mutually incompatible rules
-    # We don’t want a blank line before a class docstring
-    "D203",
-    # We want docstrings to start immediately after the opening triple quote
-    "D213",
-]
+
+[lint]
+    unfixable = ["F841"]
+    select = [
+        "F",  # Errors detected by Pyflakes
+        "E",  # Error detected by Pycodestyle
+        "W",  # Warning detected by Pycodestyle
+        "I",  # isort
+        "D",  # pydocstyle
+        "B",  # flake8-bugbear
+        "TID",  # flake8-tidy-imports
+        "C4",  # flake8-comprehensions
+        "BLE",  # flake8-blind-except
+        "UP",  # pyupgrade
+        "RUF100",  # Report unused noqa directives
+    ]
+    ignore = [
+        # line too long -> we accept long comment lines; black gets rid of long code lines
+        "E501",
+        # Do not assign a lambda expression, use a def -> lambda expression assignments are convenient
+        "E731",
+        # allow I, O, l as variable names -> I is the identity matrix
+        "E741",
+        # Missing docstring in public package
+        "D104",
+        # Missing docstring in public module
+        "D100",
+        # Missing docstring in __init__
+        "D107",
+        # Errors from function calls in argument defaults. These are fine when the result is immutable.
+        "B008",
+        # __magic__ methods are are often self-explanatory, allow missing docstrings
+        "D105",
+        # first line should end with a period [Bug: doesn't work with single-line docstrings]
+        "D400",
+        # First line should be in imperative mood; try rephrasing
+        "D401",
+        ## Disable one in each pair of mutually incompatible rules
+        # We don’t want a blank line before a class docstring
+        "D203",
+        # We want docstrings to start immediately after the opening triple quote
+        "D213",
+    ]

src/dso/templates/stage/quarto/src/{{ stage_name }}.qmd

@@ -1,14 +1,22 @@
 ```{r}
-library(conflicted)
-library(dso)
+#| label: load_libraries
+
+require(conflicted)
+require(dso)
 ```
 
 ```{r}
-# Set stage dir, compile and load params
+#| label: read_params
+# read_params sets the stage directory, runs 'dso compile-config'
+# and loads params defined in the 'dvc.yaml' 'params' section of the stage
+
 params <- read_params("{{ stage_path }}")
 ```
 
 ```{r}
-# Obtain files relative to stage directory, e.g.
+#| label: obtain_files_relative_to_stage_dir
+
+# stage_here locates your files relative to the stage path set in read_params
+# e.g.
 samplesheet <- readr::read_csv(stage_here(params$samplesheet))
 ```