Merge pull request #3 from caltechlibrary/main

merge

.github/workflows/codemeta2cff.yml

@@ -0,0 +1,26 @@
+name: CodeMeta2CFF
+run-name: Run CodeMeta2CFF after ${{github.event_name}} by ${{github.actor}}
+
+on:
+  push:
+    paths: ['codemeta.json']
+  workflow_dispatch:
+    inputs:
+      reason:
+        description: 'Reason'
+        required: false
+        default: 'Manual trigger'
+
+jobs:
+  CodeMeta2CFF:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+      - name: Convert CFF
+        uses: caltechlibrary/codemeta2cff@main
+      - name: Commit CFF
+        uses: EndBug/add-and-commit@v9
+        with:
+          message: 'Add updated CITATION.cff from codemeta.json file'
+          add: 'CITATION.cff'

.github/workflows/iga.yaml

@@ -1,4 +1,3 @@
-name: InvenioRDM GitHub Archiver and CodeMeta2CFF
 env:
   INVENIO_SERVER: https://data.caltech.edu
 
@@ -10,47 +9,51 @@ env:
   parent_record: "6qhkm-7n074"
   debug:         false
 
-# ~~~~~~~~~~ The rest of this file should be left as-is ~~~~~~~~~~
+  # This variable is a setting for post-archiving CodeMeta file updates.
+  # If you don't have a CodeMeta file, you can remove the add_doi_codemeta
+  # and Coremeta2CFF jobs at the bottom of this file.
+  ref: main
+
+# ╭────────────────────────────────────────────╮
+# │ The rest of this file should be left as-is │
+# ╰────────────────────────────────────────────╯
+
+name: InvenioRDM GitHub Archiver
 on:
   release:
     types: [published]
   workflow_dispatch:
     inputs:
       release_tag:
-        description: "The tag of the release to archive:"
+        description: The release tag (empty = latest)
+      parent_record:
+        description: ID of parent record (for versioning)
+      community:
+        description: Name of InvenioRDM community (if any)
       draft:
-        default: false
-        description: "Mark the record as a draft:"
+        description: Mark the record as a draft
+        type: boolean
       all_assets:
-        default: false
-        description: "Attach all GitHub assets:"
+        description: Attach all GitHub assets
+        type: boolean
       all_metadata:
-        default: false
-        description: "Include additional GitHub metadata:"
-      community:
-        description: "Send record to InvenioRDM community:"
-      parent_record:
-        description: "ID of parent record (for versioning):"
+        description: Include additional GitHub metadata
+        type: boolean
+      debug:
+        description: Print debug info in the GitHub log
+        type: boolean
+
+run-name: Archive ${{inputs.release_tag || 'latest release'}} in InvenioRDM
 jobs:
-  CodeMeta2CFF:
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v4
-      - name: Convert CFF
-        uses: caltechlibrary/codemeta2cff@main
-      - name: Commit CFF
-        uses: EndBug/add-and-commit@v9
-        with:
-          message: 'Add CITATION.cff for release'
-          add: "['CITATION.cff']"
-          push: origin HEAD:main
   run_iga:
-    name: "Send to ${{needs.get_repository.outputs.server}}"
+    name: Send to ${{needs.get_repository.outputs.server}}
     runs-on: ubuntu-latest
-    needs: [get_repository, CodeMeta2CFF]
+    needs: get_repository
+    outputs:
+      record_doi: ${{steps.iga.outputs.record_doi}}
     steps:
-      - uses: caltechlibrary/iga@main
+      - uses: caltechlibrary/iga@v1
+        id: iga
         with:
           INVENIO_SERVER: ${{env.INVENIO_SERVER}}
           INVENIO_TOKEN:  ${{secrets.INVENIO_TOKEN}}
@@ -62,10 +65,44 @@ jobs:
           parent_record:  ${{github.event.inputs.parent_record || env.parent_record}}
           release_tag:    ${{github.event.inputs.release_tag || 'latest'}}
   get_repository:
-    name: "Get repository name"
+    name: Get repository name
     runs-on: ubuntu-latest
     outputs:
       server: ${{steps.parse.outputs.host}}
     steps:
-      - id: parse
+      - name: Extract name from INVENIO_SERVER
+        id: parse
         run: echo "host=$(cut -d'/' -f3 <<< ${{env.INVENIO_SERVER}} | cut -d':' -f1)" >> $GITHUB_OUTPUT
+  add_doi_codemeta:
+    name: "Add ${{needs.run_iga.outputs.record_doi}} to codemeta.json"
+    needs: run_iga
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ env.ref }}
+      - name: Install sde
+        run: pip install sde
+      - name: Add DOI to CodeMeta File
+        run: sde identifier ${{needs.run_iga.outputs.record_doi}} codemeta.json
+      - name: Commit CFF
+        uses: EndBug/add-and-commit@v9
+        with:
+          message: 'Add DOI to codemeta.json file'
+          add: 'codemeta.json'
+  CodeMeta2CFF:
+    runs-on: ubuntu-latest
+    needs: add_doi_codemeta
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ env.ref }}
+      - name: Convert CFF
+        uses: caltechlibrary/codemeta2cff@main
+      - name: Commit CFF
+        uses: EndBug/add-and-commit@v9
+        with:
+          message: 'Add updated CITATION.cff from codemeta.json file'
+          add: 'CITATION.cff'

CITATION.cff

@@ -11,11 +11,11 @@ authors:
 abstract: Python wrapper for CaltechDATA API.
 repository-code: "https://github.com/caltechlibrary/caltechdata_api"
 type: software
-version: 1.8.1
+version: 1.8.2
 license-url: "https://data.caltech.edu/license"
 keywords:
   - GitHub
   - metadata
   - software
   - InvenioRDM
-date-released: 2024-10-18
+date-released: 2024-11-06

README.md

@@ -1,5 +1,7 @@
 # CaltechDATA API Python Library
 
+[![DOI](https://img.shields.io/badge/dynamic/json.svg?label=DOI&query=$.pids.doi.identifier&uri=https://data.caltech.edu/api/records/wfjr5-kw507/versions/latest)](https://data.caltech.edu/records/wfjr5-kw507/latest)
+
 The `caltechdata_api` Python library provides a convenient interface for interacting with the CaltechDATA API. It allows users to write files, create DataCite 4 standard JSON records, edit existing records, and retrieve metadata from the CaltechDATA repository.
 
 ## Features

caltechdata_api/cli.py

@@ -71,6 +71,11 @@ def get_or_set_token(production=True):
         with open(token_file, "rb") as f:
             encrypted_token = f.read()
             token = decrypt_token(encrypted_token, key)
+            print(
+                "Using saved CaltechDATA production token."
+                if production
+                else "Using saved CaltechDATA test token."
+            )
             return token
     except FileNotFoundError:
         while True:
@@ -422,8 +427,6 @@ def main():
 
 def create_record(production):
     token = get_or_set_token(production)
-    # keep_file = input("Do you want to keep your existing files? (yes/no): ").lower() == "yes"
-    print("Using CaltechDATA token:", token)
     while True:
         choice = get_user_input(
             "Do you want to use metadata from an existing file or create new metadata? (existing/create): "

caltechdata_api/customize_schema.py

@@ -1,5 +1,4 @@
-# Convert a DataCite 4 or 4.3 standard schema json record to the customized internal
-# schema used by TIND in CaltechDATA
+# Convert a DataCite 4.3 standard schema json record to the InvenioRDM schema
 import argparse
 import json
 from datetime import date

caltechdata_api/get_metadata.py

@@ -8,26 +8,43 @@
 
 
 def get_metadata(
-    idv, production=True, validate=True, emails=False, schema="43", token=False
+    idv,
+    production=True,
+    validate=True,
+    emails=False,
+    schema="43",
+    token=False,
+    authors=False,
 ):
     # Returns just DataCite metadata or DataCite metadata with emails
 
     if production == True:
-        url = "https://data.caltech.edu/api/records/"
+        if authors:
+            url = "https://authors.library.caltech.edu/api/records/"
+        else:
+            url = "https://data.caltech.edu/api/records/"
         verify = True
     else:
-        url = "https://data.caltechlibrary.dev/api/records/"
+        if authors:
+            url = "https://authors.caltechlibrary.dev/api/records/"
+        else:
+            url = "https://data.caltechlibrary.dev/api/records/"
         verify = True
 
-    headers = {
-        "accept": "application/vnd.datacite.datacite+json",
-    }
+    if authors:
+        headers = {
+            "accept": "application/json",
+        }
+        validate = False
+    else:
+        headers = {
+            "accept": "application/vnd.datacite.datacite+json",
+        }
 
     if token:
         headers["Authorization"] = "Bearer %s" % token
 
     response = requests.get(url + idv, headers=headers, verify=verify)
-    print(response.headers)
     if response.status_code != 200:
         raise Exception(response.text)
     else:
@@ -59,6 +76,7 @@ def get_metadata(
         help="The CaltechDATA ID for each record of interest",
     )
     parser.add_argument("-test", dest="production", action="store_false")
+    parser.add_argument("-authors", dest="authors", action="store_true")
     parser.add_argument("-xml", dest="save_xml", action="store_true")
     parser.add_argument(
         "-skip_validate",
@@ -72,14 +90,17 @@ def get_metadata(
 
     production = args.production
     schema = args.schema
+    authors = args.authors
     skip_validate = args.skip_validate
     if skip_validate:
         validate = False
     else:
         validate = True
 
     for idv in args.ids:
-        metadata = get_metadata(idv, production, validate, schema)
+        metadata = get_metadata(
+            idv, production, validate, schema=schema, authors=authors
+        )
         outfile = open(str(idv) + ".json", "w")
         outfile.write(json.dumps(metadata, indent=4))
         outfile.close()