Merge pull request #8 from cedadev/sparql_test2

Poetry Update and SPARQL Query Removal

.github/workflows/tests.yml

@@ -0,0 +1,25 @@
+name: Automatic Test
+
+on:
+  - push
+  - pull_request
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+
+    steps:
+    - name: Checkout repository
+      uses: actions/checkout@v4
+
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v5
+      with:
+        python-version: 3.11
+    - name: Install Python dependencies
+      run: |
+        python -m pip install --upgrade pip
+        pip3 install .
+        pip3 install -r requirements_fix.txt
+    - name: Run tests
+      run: pytest

docs/triple_store_removal.md

@@ -0,0 +1,44 @@
+# Notes for removing triple store
+
+## SPARQL Query requests:
+
+### get_concepts_in_scheme
+
+From all items, verify in scheme, pull out ID and verify in endpoints list, then get prefLabel.
+
+### get_alt_concepts_in_scheme
+
+From all items, verify in scheme, pull out ID and verify in endpoints list, then get altLabel.
+
+### get_broader
+
+Does something interesting with a request for 'narrower'
+
+### get_alt_label
+
+Links to get nerc or get ceda alt_label. Still just getting alt or pref labels.
+
+## Facet Object Components
+
+### __facets private attribute
+ - `facets[facet]` = dict of concepts arranged by label/concept (@value - prefLabel/@id)
+ - `facets[facet-alt]` = same as above but with (@value - altLabel/@id)
+ - `facets[broader-processing-level]` = get alt level for proc level mappings.
+
+## __proc_level_mappings
+ - `proc_level_mappings[proc_level.uri]` - @id from above facet = single item(concept) from records that contain a 'narrower' option.
+
+## __platform_program_mappings
+ - `platform_program_mappings[platform.uri]` - @id from above facet = single item(label) from records that contain a 'narrower' option.
+
+## __programme_group_mappings
+ - `programme_group_mappings[single item(concept)]` - from above = single item(label) from other records that contain a 'narrower' option.
+
+## __reversible_facet_mappings
+ - Reversed mappings for each facet, makes construction of mappings easier.
+
+## FACET_ENDPOINTS
+ - Defined config values
+
+## LABEL_SOURCE
+ - Defined config values

pyproject.toml

@@ -1,45 +1,46 @@
-[tool.poetry]
+[project]
 name = "tag-scanner"
-
-version = "2.1.9"
+version = "2.2.0"
 description = "This package provides a command line tool moles_esgf_tag to generate dataset tags for both MOLES and ESGF."
-license = "{file='LICENSE'}"
+license = "BSD 3"
 readme = "README.md"
-
-authors = ["Daniel Westwood <[email protected]>", "Antony Wilson <[email protected]>"]
-
+authors = [
+    { name = "Daniel Westwood", email = "[email protected]"},
+    { name = "Antony Wilson", email = "[email protected]"}
+]
 classifiers = [
-    'Intended Audience :: Developers',
-    'License :: OSI Approved :: BSD License',
-    'Operating System :: OS Independent',
-    'Programming Language :: Python',
-    'Programming Language :: Python :: 2.7',
-    'Programming Language :: Python :: 3',
+    "Intended Audience :: Developers",
+    "License :: OSI Approved :: BSD License",
+    "Operating System :: OS Independent",
+    "Programming Language :: Python",
+    "Programming Language :: Python :: 2.7",
+    "Programming Language :: Python :: 3",
 ]
-
 include = [
     { path = "templates/*.html" },
-    { path = "conf/tag_check.conf" }
+    { path = "conf/tag_check.conf" },
+    { path = "tag_scanner/tests/*"}
+]
+dependencies = [
+    "verboselogs>=1.7",
+    "elasticsearch (>=7.6.0,<7.7)",
+    "tqdm (>=4.45.0,<5)",
+    "pytest<8.3.3",
+    "jinja2 (>=3,<4)",
+    "numpy (>=1.25,<2.0)",
+    "netcdf4 (>=1.7.2,<2.0.0)",
+    "six (>=1.16.0,<2.0.0)",
+    "requests (>=2.32.3,<3.0.0)",
+#    "directory-tree @ https://github.com/cedadev/ceda-directory-tree.git"
 ]
 
-[tool.poetry.dependencies]
-python = ">=3.8,<4.0"
-verboselogs = "1.7"
-elasticsearch = "7.6.0"
-tqdm = "^4.45.0"
-pytest = "^8.3.3"
-jinja2 = "^3"
-directory-tree = { git = "https://github.com/cedadev/ceda-directory-tree.git", tag = "v1.1.4"}
-
-sparqlwrapper = "^2.0.0"
-netcdf4 = "^1.7.2"
-six = "^1.16.0"
+requires-python = ">=3.9,<4"
 
 [build-system]
 requires = ["poetry-core"]
 build-backend = "poetry.core.masonry.api"
 
-[tool.poetry.scripts]
+[project.scripts]
 moles_esgf_tag = "tag_scanner.scripts:CCITaggerCommandLineClient.main"
 cci_json_check = "tag_scanner.scripts:TestJSONFile.cmd"
 cci_check_tags = "tag_scanner.scripts.check_tags:main"

requirements_fix.txt

@@ -0,0 +1 @@
+https://github.com/cedadev/ceda-directory-tree/archive/v1.1.5.tar.gz

tag_scanner/dataset/__init__.py

@@ -5,3 +5,5 @@
 __copyright__ = 'Copyright 2024 United Kingdom Research and Innovation'
 __license__ = 'BSD - see LICENSE file in top-level package directory'
 __contact__ = '[email protected]'
+
+from .dataset import Dataset