Initial commit

.github/workflows/ci.yml

@@ -0,0 +1,22 @@
+name: ci 
+on:
+  push:
+    branches:
+      - main
+permissions:
+  contents: write
+jobs:
+  deploy:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+      - name: Configure Git Credentials
+        run: |
+          git config user.name github-actions[bot]
+          git config user.email 41898282+github-actions[bot]@users.noreply.github.com
+      - uses: actions/setup-python@v5
+        with:
+          python-version: 3.x
+      - run: pip install "mkdocs-material[imaging]==9.5.34"
+      - run: pip install mkdocs-glightbox mkdocs-minify-plugin mkdocs-git-revision-date-localized-plugin mkdocs-git-committers-plugin-2
+      - run: mkdocs gh-deploy --force

.gitignore

@@ -0,0 +1,165 @@
+# MacOS stuff 
+.DS_Store
+
+# 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/latest/usage/project/#working-with-version-control
+.pdm.toml
+.pdm-python
+.pdm-build/
+
+# 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/

README copy.md

@@ -0,0 +1,20 @@
+# KCEO Glossary
+
+Test repo for KCEO glossary
+
+## Mac build error
+If error `ERROR   -  "cairosvg" Python module is installed, but it crashed with:` just use:
+
+`export DYLD_FALLBACK_LIBRARY_PATH=/opt/homebrew/lib` before. Or set it once, e.g. for zsh shell: 
+
+`echo 'export DYLD_FALLBACK_LIBRARY_PATH=/opt/homebrew/lib' >> ~/.zshrc && source ~/.zshrc`
+
+## Installation commands 
+See ci.yml.
+
+## Contributions and Feedback
+The KCEO Glossary is freely available for you to use. In addition, your feedback and ideas are welcome to improve the terms and create alternative versions.
+
+If you have questions you can ping us or open an [Issue] (add link).
+
+Feel free to also send us a pull request.

README.md

@@ -1,3 +1,19 @@
 # KCEO Glossary
 
-Currently work in progress.
+## Contributions and Feedback
+The KCEO Glossary is built for the EO community. Your feedback and ideas are fundamental for the further development of this glossary. PR's and contributions of any kind are highly welcomed. 
+
+### Contribution Guide
+coming soon
+
+## Local installation
+See the github actions in .github/workflows/ci.yml.
+
+## FAQ
+### Mac build error
+If error `ERROR   -  "cairosvg" Python module is installed, but it crashed with:` just use:
+
+`export DYLD_FALLBACK_LIBRARY_PATH=/opt/homebrew/lib` before. Or set it once, e.g. for zsh shell: 
+
+`echo 'export DYLD_FALLBACK_LIBRARY_PATH=/opt/homebrew/lib' >> ~/.zshrc && source ~/.zshrc`
+

add_cross_links.py

@@ -0,0 +1,76 @@
+import os
+import re
+
+def extract_titles_from_md(file_path):
+    titles = []
+    with open(file_path, 'r') as file:
+        in_yaml = False
+        for line in file:
+            if line.strip() == '---':
+                in_yaml = not in_yaml
+            if in_yaml:
+                continue
+            if line.startswith('# ') and not line.startswith('##'):
+                # Remove "#" and any potential markdown link syntax
+                title = re.sub(r'\[([^\]]+)\]\(.*?\)', r'\1', line.lstrip('# ').strip())
+                titles.append(title)
+    return titles
+
+def insert_hyperlinks(file_path, terms):
+    with open(file_path, 'r') as file:
+        content = file.readlines()
+
+    new_content = []
+    in_yaml = False
+    current_title = None
+
+    for line in content:
+        if line.strip() == '---':
+            in_yaml = not in_yaml
+            new_content.append(line)
+            continue
+        if in_yaml:
+            new_content.append(line)
+            continue
+        if line.startswith('# ') and not line.startswith('##'):
+            current_title = re.sub(r'\[([^\]]+)\]\(.*?\)', r'\1', line.lstrip('# ').strip())
+            new_content.append(line)
+            continue
+
+        for term in terms:
+            if term == current_title:  # Skip self-references
+                continue
+
+            # Skip terms that already have a hyperlink
+            if re.search(r'\[' + re.escape(term) + r'\]\(.*?\)', line):
+                continue
+
+            # Avoid altering headings by ensuring replacements are only made in non-heading lines
+            pattern = re.compile(r'\b' + re.escape(term) + r'\b', re.IGNORECASE)
+            replacement = f'[{term}](../{" ".join(term.split()).lower()})'
+            line = pattern.sub(lambda match: replacement if not re.search(rf'\[{re.escape(match.group(0))}\]\(.*?\)', match.string) else match.group(0), line)
+
+        new_content.append(line)
+
+    with open(file_path, 'w') as file:
+        file.writelines(new_content)
+
+def main(directory, exclude_files):
+    all_titles = []
+    md_files = [f for f in os.listdir(directory) if f.endswith('.md') and f not in exclude_files]
+
+    # Extract titles from all markdown files
+    for md_file in md_files:
+        file_path = os.path.join(directory, md_file)
+        titles = extract_titles_from_md(file_path)
+        all_titles.extend(titles)
+
+    # Insert hyperlinks based on extracted titles
+    for md_file in md_files:
+        file_path = os.path.join(directory, md_file)
+        insert_hyperlinks(file_path, all_titles)
+
+if __name__ == "__main__":
+    directory = './docs'  # Replace with your directory path
+    exclude_files = ['changelog.md', 'impressum.md', 'index.md', 'glossary.md', 'introduction.md', 'mermaid.md']  # Files to be excluded
+    main(directory, exclude_files)

create_topology.py

@@ -0,0 +1,50 @@
+import re
+from collections import defaultdict
+
+# Helper function to parse the mermaid markdown and extract relationships
+def parse_mermaid_relationships(mermaid_content):
+    # Adjusted regex pattern
+    pattern = re.compile(r'id_([\w-]+)\(\["<a href=\'\.\./([\w-]+)\'>([\w\s-]+)</a>"\]\) --> id_([\w-]+)\(\["<a href=\'\.\./([\w-]+)\'>([\w\s-]+)</a>"\]\)')
+    relationships = defaultdict(lambda: {'parents': set(), 'children': set(), 'link': None})
+
+    for match in pattern.finditer(mermaid_content):
+        parent_id, parent_link, parent_name, child_id, child_link, child_name = match.groups()
+
+        # Add child to parent's children list
+        relationships[parent_name]['children'].add((child_name, f"../{child_link}/"))
+        relationships[parent_name]['link'] = f"../{parent_link}/"  # Add link for parent
+
+        # Add parent to child's parents list
+        relationships[child_name]['parents'].add((parent_name, f"../{parent_link}/"))
+        relationships[child_name]['link'] = f"../{child_link}/"  # Add link for child
+
+    return relationships
+
+# Read the mermaid.md file
+with open('docs/mermaid.md', 'r') as file:
+    mermaid_content = file.read()
+
+# Remove leading and trailing backticks and optional whitespace/newlines
+mermaid_content = mermaid_content.strip('` \n')
+
+# Parse relationships
+relationships = parse_mermaid_relationships(mermaid_content)
+
+# Write the glossary_topology.md file
+with open('docs/glossary_topology.md', 'w') as file:
+    for term, links in sorted(relationships.items()):
+        file.write(f'## [{term}]({links["link"]})\n')  # Make heading a hyperlink
+        if links['parents']:
+            file.write('**Parents**: ')
+            file.write(', '.join(f"[{parent[0]}]({parent[1]})" for parent in sorted(links['parents'])))
+            if links['children']:
+                file.write('<br>\n')
+            else:
+                file.write('\n')
+        if links['children']:
+            file.write('**Children**: ')
+            file.write(', '.join(f"[{child[0]}]({child[1]})" for child in sorted(links['children'])))
+            file.write('\n')
+        file.write('\n')
+
+print('glossary_topology.md has been created/overwritten with the extracted relationships.')