started work on dplace 3

.github/workflows/python-package.yml

@@ -12,24 +12,22 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        python-version: [3.6, 3.7, 3.8, 3.9]
+        python-version: [3.8, 3.9, "3.10", "3.11"]
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v4
     - name: Set up Python ${{ matrix.python-version }}
-      uses: actions/setup-python@v2
+      uses: actions/setup-python@v4
       with:
         python-version: ${{ matrix.python-version }}
     - name: Install dependencies
       run: |
         python -m pip install --upgrade pip
+        sudo apt-add-repository ppa:ubuntugis/ubuntugis-unstable
+        sudo apt-get update
+        sudo apt-get install gdal-bin libgdal-dev
+        pip install GDAL==3.2.3 
         pip install .[test]
     - name: Test with pytest
       run: |
         pytest
-    - name: "Convert coverage"
-      run: "python -m coverage xml"
-    - name: "Upload coverage to Codecov"
-      uses: "codecov/codecov-action@v1"
-      with:
-        fail_ci_if_error: true

README.md

@@ -1,42 +1,91 @@
 # pydplace
 
-A Python library to access [D-PLACE](https://d-place.org) data. 
+A Python library to curate [D-PLACE](https://d-place.org) data.
 
 [![Build Status](https://github.com/D-PLACE/pydplace/workflows/tests/badge.svg)](https://github.com/D-PLACE/pydplace/actions?query=workflow%3Atests)
-[![codecov](https://codecov.io/gh/D-PLACE/pydplace/branch/master/graph/badge.svg)](https://codecov.io/gh/D-PLACE/pydplace)
 [![PyPI](https://img.shields.io/pypi/v/pydplace.svg)](https://pypi.org/project/pydplace)
 
 
-To install `pydplace` you need a python installation on your system, running python 2.7 or >3.4. Run
+To install `pydplace` run
 
 ```
 pip install pydplace
 ```
 
-to install the requirements, `pydplace` and the command line interface `dplace`.
+## Usage
 
-`pydplace` is built to access data in a local clone or export of D-PLACE's data repository https://github.com/D-PLACE/dplace-data
+### Bootstrapping a `pydplace`-curated dataset
 
+`pydplace` provides a `cldfbench` dataset template to create the skeleton of files and directories for a
+D-PLACE dataset, to be run with [cldfbench new](https://github.com/cldf/cldfbench/#creating-a-skeleton-for-a-new-dataset-directory).
 
-## CLI
+Running
 
-Command line functionality is implemented via sub-commands of `dplace`. The list of
-available sub-commands can be inspected running
+```shell
+cldfbench new --template dplace_dataset 
 ```
-$ dplace --help
-usage: deplace [-h] [--verbosity VERBOSITY] [--log-level LOG_LEVEL]
-                 [--repos REPOS]
-                 command ...
-...
 
-Use 'dplace help <cmd>' to get help about individual commands.
+will create a dataset skeleton looking as follows
+```shell
+$ tree testtree/
 ```
 
-## Python API
 
-D-PLACE data can also be accessed programmatically. All functionality is mediated through an instance of `pydplace.api.Repos`, e.g.
+### Implementing CLDF creation
 
-```python
->>> from pydplace.api import Repos
->>> api = Repos('.')
+Implementing CLDF creation means - as for any other `cldfbench`-curated dataset - filling in the
+`cmd_makecldf` method of the `Dataset` subclass in `cldfbench_<id>.py`.
 
+
+### Running CLDF creation
+
+With `cmd_makecldf` implemented, CLDF creation can be triggered running
+```shell
+cldfbench makecldf cldfbench_<id>.py
+```
+
+The resulting CLDF dataset can be validated running
+```shell
+pytest
+```
+
+
+### Release workflow
+
+```shell
+cldfbench makecldf --glottolog-version v4.8 --with-cldfreadme cldfbench_<id>.py
+pytest
+cldfbench zenodo --communities dplace cldfbench_<id>.py
+cldfbench cldfviz.map cldf --pacific-centered --format png --width 20 --output map.png --with-ocean --no-legend
+cldfbench readme cldfbench_<id>.py
+dplace check cldfbench_<id>.py
+git commit -a -m"release vX.Y"
+git push origin
+```
+
+Then create a release on GitHub, thereby pushing the repos to Zenodo.
+
+
+### Using the datasets
+
+```shell
+$ csvgrep -c Var_ID -m AnnualMeanTemperature cldf/data.csv | csvstat -c Value
+  4. "Value"
+
+	Type of data:          Number
+	Contains null values:  False
+	Unique values:         1649
+	Smallest value:        -19,45
+	Largest value:         29,153
+	Sum:                   32.700,717
+	Mean:                  16,449
+	Median:                19,721
+	StDev:                 9,684
+	Most common values:    14,392 (9x)
+	                       21,66 (6x)
+	                       6,96 (6x)
+	                       23,335 (5x)
+	                       21,619 (5x)
+
+Row count: 1988
+```

pyproject.toml

@@ -0,0 +1,3 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"

setup.cfg

@@ -1,10 +1,82 @@
+[metadata]
+name = pydplace
+version = 3.0.0.dev0
+author = Robert Forkel
+author_email = [email protected]
+description = A cldfbench plugin to curate D-PLACE datasets
+long_description = file: README.md
+long_description_content_type = text/markdown
+keywords = linguistics
+license = Apache 2.0
+license_files = LICENSE
+url = https://github.com/D-PLACE/pydplace
+project_urls =
+    Bug Tracker = https://github.com/D-PLACE/pydplace/issues
+platforms = any
+classifiers =
+    Development Status :: 5 - Production/Stable
+    Intended Audience :: Developers
+    Intended Audience :: Science/Research
+    Natural Language :: English
+    Operating System :: OS Independent
+    Programming Language :: Python :: 3
+    Programming Language :: Python :: 3.8
+    Programming Language :: Python :: 3.9
+    Programming Language :: Python :: 3.10
+    Programming Language :: Python :: 3.11
+    Programming Language :: Python :: 3.12
+    Programming Language :: Python :: Implementation :: CPython
+    Programming Language :: Python :: Implementation :: PyPy
+    License :: OSI Approved :: Apache Software License
+
+[options]
+zip_safe = False
+packages = find:
+package_dir =
+    = src
+python_requires = >=3.8
+install_requires =
+    pybtex
+    attrs>=19.1
+    cldfbench
+    clldutils>=3.5.0
+    csvw>=1.6
+    pyglottolog>=3.0
+    pycldf>=1.14
+    fiona
+    shapely
+include_package_data = True
+
+[options.packages.find]
+where = src
+
+[options.package_data]
+pycldf =
+    dataset_template/*
+    *.json
+    *.geojson
+
+[options.entry_points]
+console_scripts =
+    dplace = pydplace.__main__:main
+cldfbench.scaffold =
+    dplace_dataset = pydplace.scaffold:DatasetTemplate
+
+[options.extras_require]
+dev =
+    tox
+    flake8
+    wheel>=0.36
+    twine
+test =
+    pytest>=5
+    pytest-mock
+    pytest-cov
+    coverage>=4.2
+
 [easy_install]
 zip_ok = false
 
-[metadata]
-description-file = README.md
-license_file = LICENSE
-
 [bdist_wheel]
 universal = 1
 
@@ -26,3 +98,12 @@ source =
 [coverage:report]
 show_missing = true
 skip_covered = true
+
+[tox:tox]
+envlist = py38, py39, py310, py311, py312
+isolated_build = true
+skip_missing_interpreter = true
+
+[testenv]
+deps = .[test]
+commands = pytest {posargs}

setup.py

@@ -1,63 +1,4 @@
-from setuptools import setup, find_packages
+from setuptools import setup
 
 
-setup(
-    name='pydplace',
-    version='2.4.1.dev0',
-    license='Apache 2.0',
-    description='programmatic access to D-PLACE/dplace-data',
-    long_description=open('README.md').read(),
-    long_description_content_type='text/markdown',
-    classifiers=[
-        "Programming Language :: Python",
-        "Programming Language :: Python :: 3",
-        "Programming Language :: Python :: 3.6",
-        "Programming Language :: Python :: 3.7",
-        "Programming Language :: Python :: 3.8",
-        "Programming Language :: Python :: 3.9",
-    ],
-    author='Robert Forkel',
-    author_email='[email protected]',
-    url='https://d-place.org',
-    keywords='data',
-    packages=find_packages(where='src'),
-    package_dir={'': 'src'},
-    include_package_data=True,
-    zip_safe=False,
-    platforms='any',
-    python_requires='>=3.6',
-    install_requires=[
-        'pybtex',
-        'attrs>=19.1',
-        'clldutils>=3.5.0',
-        'cldfcatalog',
-        'csvw>=1.6',
-        'pyglottolog>=3.0',
-        'python-nexus>=2.2.0',
-        'pycldf>=1.14',
-        # ete3 doesn't install its dependencies properly, so we have to:
-        'six',
-        'numpy',
-        'ete3>=3.1.2',
-        #'pygdal>=1.11.3.3',
-        #'fiona',
-        #'shapely',
-    ],
-    extras_require={
-        'dev': ['flake8', 'wheel', 'twine'],
-        'test': [
-            'pytest>=5',
-            'pytest-mock',
-            'pytest-cov',
-            'coverage>=4.2',
-        ],
-    },
-    entry_points={
-        'console_scripts': [
-            'dplace=pydplace.__main__:main',
-        ],
-        'cldfbench.commands': [
-            'dplace=pydplace.cldfbench_commands',
-        ],
-    },
-)
+setup()

src/pydplace/__init__.py

@@ -1,5 +1,6 @@
 #
-from pydplace.api import Repos as API
+from .dataset import DatasetWithSocieties, DatasetWithoutSocieties
 
-DPLACE = API  # provide a more specific alias for the API class
 __version__ = "2.4.1.dev0"
+assert DatasetWithSocieties
+assert DatasetWithoutSocieties

src/pydplace/__main__.py

@@ -1,22 +1,15 @@
 import sys
-import pathlib
 import contextlib
 
 from clldutils.loglib import Logging
-from clldutils.clilib import get_parser_and_subparsers, register_subcommands, PathType
+from clldutils.clilib import get_parser_and_subparsers, register_subcommands
 
 import pydplace
-from pydplace.api import Repos
 import pydplace.commands
 
 
 def main(args=None, catch_all=False, parsed_args=None, log=None):
     parser, subparsers = get_parser_and_subparsers('dplace')
-    parser.add_argument(
-        '--repos',
-        type=PathType(type='dir'),
-        default=pathlib.Path('dplace-data'),
-        help='Location of clone of D_PLACE/dplace-data')
     register_subcommands(subparsers, pydplace.commands)
 
     args = parsed_args or parser.parse_args(args=args)
@@ -30,7 +23,6 @@ def main(args=None, catch_all=False, parsed_args=None, log=None):
             stack.enter_context(Logging(args.log, level=args.log_level))
         else:
             args.log = log
-        args.repos = Repos(args.repos)
         try:
             return args.main(args) or 0
         except KeyboardInterrupt:  # pragma: no cover