merge esgvoc in main #286

.github/workflows/check_ld.yml

@@ -9,6 +9,7 @@ on:
 
 jobs:
   check-graph:
+    if: false
     runs-on: ubuntu-latest  # Specify the machine type
 
     steps:

.github/workflows/deploy-docs.yml

@@ -14,6 +14,7 @@ on:
 
 jobs:
   deploy-docs:
+    if: false
     runs-on: ubuntu-latest
 
     steps:

.github/workflows/static.yml

@@ -18,6 +18,7 @@ concurrency:
 
 jobs:
   deploy:
+    if: false
     environment:
       name: github-pages
       url: ${{ steps.deployment.outputs.page_url }}

.github/workflows/update-jsonld.yml

@@ -9,6 +9,7 @@ on:
 
 jobs:
   update-jsonld:
+    if: false
     runs-on: ubuntu-latest  # Specify the machine type
 
     steps:

.gitignore

@@ -168,3 +168,4 @@ cython_debug/
 #  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/
+scripts/WCRP-universe_known_branded_variable/*

.python-version

@@ -0,0 +1 @@
+3.12

README.md

@@ -41,3 +41,71 @@ This work is sponsored by the Regional and Global Model Analysis ([RGMA](https:/
          alt="UK Met Office"
     >
 </p>
+
+
+This repository contains the controlled vocabularies (CVs) for the CMIP7 project. It defines project-specific collections of terms used for organizing
+   and documenting CMIP7 climate simulation data.
+
+  ## Overview
+
+  CMIP7_CVs is a project-specific CV repository that works in conjunction with the https://github.com/WCRP-CMIP/WCRP-universe repository. While the
+  universe contains all possible terms with complete metadata, this repository contains collections that reference those terms by ID, selecting only the
+   terms relevant to CMIP7.
+
+  ## Key Concepts
+
+  - **WCRP-universe**: The canonical repository containing all possible terms with full metadata (experiments, institutions, models, variables, etc.)
+  - **CMIP7_CVs**: Project-specific collections that reference universe terms by ID, with optional project-specific overrides
+  - **Collections**: Folders containing JSON files that list term IDs from a specific data descriptor (e.g., activity/, experiment/, institution/)
+  - **Terms**: Individual JSON files representing a controlled vocabulary entry (e.g., experiment/historical.json)
+
+## Repository Structure
+
+  CMIP7_CVs/  
+  ├── project_specs.json       # DRS (Data Reference Syntax) and global attributes  
+  ├── project_specs.yaml        # Project metadata  
+  ├── activity/                 # Activity IDs (CMIP, ScenarioMIP, etc.)  
+  ├── experiment/               # Experiment definitions  
+  ├── institution/              # Institutions  
+  ├── source/                   # Climate models  
+  ├── brandedVariable/          # Variable names  
+  ├── reportingInterval/        # Temporal frequencies  
+  └── ...                       # Other collections  
+
+  Each collection folder contains:
+  - 000_context.jsonld: JSON-LD context for semantic web compatibility
+  - {term-id}.json: Individual term files that reference universe terms
+
+  ### How Terms Link to the Universe
+
+  Terms in CMIP7_CVs reference the universe using minimal JSON:
+```json
+  Example - CMIP7_CVs/activity/cmip.json:
+  {
+      "@context": "000_context.jsonld",
+      "id": "cmip",
+      "type": "activity"
+  }
+```
+  This references the full definition in WCRP-universe/activity/cmip.json:
+  ```json
+  {
+      "@context": "000_context.jsonld",
+      "type": "activity",
+      "id": "cmip",
+      "name": "CMIP",
+      "cmip_acronym": "CMIP",
+      "long_name": "CMIP DECK: 1pctCO2, abrupt4xCO2, amip, ...",
+      "url": "https://gmd.copernicus.org/articles/9/1937/2016/...",
+      "drs_name": "CMIP"
+  }
+```
+  Projects can override or add properties by including them in their term files.
+
+### Using with esgvoc
+
+  The https://github.com/ESGF/esgf-vocab provides a Python API and CLI to interact with these controlled vocabularies.
+
+ Documentation can be find : https://esgf.github.io/esgf-vocab/
+
+

_scripts/create_activity_id.py

@@ -0,0 +1,47 @@
+import json
+import os
+from pathlib import Path
+
+import esgvoc.api as ev
+import requests
+
+# URLs of the JSON files on GitHub
+json_url = "https://raw.githubusercontent.com/WCRP-CMIP/CMIP7-CVs/refs/heads/main/CMIP7-CVs_activity.json"
+
+# Directory where the JSON files will be saved
+save_dir = "CMIP7_activity"
+
+# Create the directory if it doesn't exist
+os.makedirs(save_dir, exist_ok=True)
+
+
+# Function to fetch and load JSON data from a URL
+def fetch_json(url):
+    response = requests.get(url)
+    response.raise_for_status()  # Check for request errors
+    return response.json()
+
+
+data = fetch_json(json_url)["activity"]
+
+known_sources_in_universe = ev.get_all_terms_in_data_descriptor("activity")
+print(known_sources_in_universe)
+for item in data:
+    found_item = None
+    for activity in known_sources_in_universe:
+        if activity.drs_name == item:
+            found_item = activity
+            break
+
+    if found_item is None:
+        print(item, "not found in universe")
+    else:
+        # Create json file
+        dict_to_save = {
+            "@context": "000_context.jsonld",
+            "id": found_item.id,
+            "type": found_item.type,
+        }
+        # print(dict_to_save)
+        with open(Path(save_dir) / f"{found_item.id}.json", "w") as f:
+            json.dump(dict_to_save, f, indent=4)

_scripts/create_bv_labels.py

@@ -0,0 +1,24 @@
+import esgvoc.api as ev
+from icecream import IceCreamDebugger
+import devtools
+
+ic = IceCreamDebugger(argToStringFunction=devtools.pformat)
+
+
+def main():
+    known_bv_in_universe = ev.get_all_terms_in_data_descriptor("known_branded_variable")
+    i = 0
+    for bv in known_bv_in_universe:
+        i = i + 1
+        if i == 5:
+            break
+        ic(bv)
+        temporal_label = bv.temporal_label
+        vertical_label = bv.vertical_label
+        horizontal_label = bv.horizontal_label
+        area_label = bv.area_label
+        ic([temporal_label, vertical_label, horizontal_label, area_label])
+
+
+if __name__ == "__main__":
+    main()