Merge

.github/workflows/bot.yaml

@@ -1,20 +1,6 @@
 name: Bot validation
 
-on:
-  push:
-    paths:
-      - 'caltechdata_api/cli.py'
-      - 'caltechdata_api/customize_schema.py'
-      - 'caltechdata_api/caltechdata_write.py'
-      - 'caltechdata_api/caltechdata_edit.py' 
-      - 'README.md'
-  pull_request:
-    paths:
-      - 'caltechdata_api/cli.py'
-      - 'caltechdata_api/customize_schema.py'
-      - 'caltechdata_api/caltechdata_write.py'
-      - 'caltechdata_api/caltechdata_edit.py' 
-      - 'README.md'
+on: [push, pull_request]
 
 jobs:
   validate-metadata:
@@ -36,13 +22,17 @@ jobs:
         pip install pytest requests s3fs cryptography 
         pip install .
 
-    - name: Run CaltechDATA Metadata Validation
+    - name: Run against CaltechData Test system
       env:
-        CALTECHDATA_TOKEN: ${{ secrets.CALTECHDATA_TOKEN }}
-      run: |
-        python tests/bot_yaml.py
-    - name: Run Unit Tests
+        RDMTOK: ${{ secrets.CALTECHDATA_TOKEN }}
       run: |
         cd tests
         pytest test_unit.py
         pytest test_rdm.py
+    - name: Run Medata Validation Test and RDM
+      env:
+        RDMTOK: ${{ secrets.CALTECHDATA_TOKEN }}
+      run: |
+        cd tests
+        python bot_yaml.py
+

.github/workflows/codemeta2cff.yml

@@ -19,8 +19,27 @@ jobs:
         uses: actions/checkout@v4
       - name: Convert CFF
         uses: caltechlibrary/codemeta2cff@main
+      - name: Install jq for JSON parsing
+        run: sudo apt-get install -y jq
+      - name: Parse and update setup.cfg
+        run: |
+            # Extract values from codemeta.json
+            NAME=$(jq -r '.name' codemeta.json)
+            VERSION=$(jq -r '.version' codemeta.json)
+            AUTHORS=$(jq -r '[.author[] | .givenName + " " + .familyName] | join(", ")' codemeta.json)
+            AUTHOR_EMAILS=$(jq -r '[.author[] | .email // empty] | join(", ")' codemeta.json)
+            DESCRIPTION=$(jq -r '.description' codemeta.json)
+            URL=$(jq -r '.codeRepository // .url' codemeta.json)
+
+            # Update setup.cfg fields
+            sed -i "s/^name = .*/name = $NAME/" setup.cfg
+            sed -i "s/^version = .*/version = $VERSION/" setup.cfg
+            sed -i "s/^author = .*/author = $AUTHORS/" setup.cfg
+            sed -i "s/^author_email = .*/author_email = $AUTHOR_EMAILS/" setup.cfg
+            sed -i "s/^description = .*/description = $DESCRIPTION/" setup.cfg
+            sed -i "s|^url = .*|url = $URL|" setup.cfg
       - name: Commit CFF
         uses: EndBug/add-and-commit@v9
         with:
-          message: 'Add updated CITATION.cff from codemeta.json file'
-          add: 'CITATION.cff'
+          message: 'Add updated CITATION.cff and setup.cfg from codemeta.json file'
+          add: '["setup.cfg", "CITATION.cff"]'

.github/workflows/pypi-publish.yaml

@@ -22,7 +22,7 @@ jobs:
         run: |
           python setup.py sdist bdist_wheel
       - name: Publish
-        uses: pypa/gh-action-pypi-publish@v1.3.1
+        uses: pypa/gh-action-pypi-publish@v1.13.0
         with:
           user: __token__
           password: ${{ secrets.pypi_token }}

CITATION.cff

@@ -14,15 +14,18 @@ authors:
   - family-names: Abakah
     given-names: Alexander A
     orcid: https://orcid.org/0009-0003-5640-6691
+  - family-names: Nagi
+    given-names: Kshemaahna
+    orcid: https://orcid.org/0009-0002-8113-3763
 abstract: Python wrapper for CaltechDATA API.
 repository-code: "https://github.com/caltechlibrary/caltechdata_api"
 type: software
-doi: 10.22002/bv2pv-2b295
-version: 1.9.1
+doi: 10.22002/2g4c7-zva46
+version: 1.10.6
 license-url: "https://data.caltech.edu/license"
 keywords:
   - GitHub
   - metadata
   - software
   - InvenioRDM
-date-released: 2025-02-06
+date-released: 2025-10-18

README.md

@@ -29,7 +29,7 @@ pip install caltechdata_api
 
 There are some example python scripts in the GitHub repository.
 
-###Create a record:
+### Create a record:
 
 ```shell
 python write.py example.json -fnames logo.gif
@@ -39,7 +39,7 @@ python write.py example.json -fnames logo.gif
 the end of a url to visit the record (e.g.
 https://data.caltechlibrary.dev/records/pbkn6-m9y63)
 
-###Edit a record 
+### Edit a record 
 Make changes to the example.json file to see a change)
 ```
 python edit.py example.json -id pbkn6-m9y63
@@ -77,3 +77,6 @@ This returns the custom DOI of the record if it is successful.
 Only test your application on the test repository (`data.caltechlibrary.dev`).  Testing the API on the public 
 repository will generate junk records that are annoying to delete.
 
+## Using the Command Line Interface
+
+If you would like to interact with the CaltechDATA API using the Command line Interface (CLI), please [see the detailed documentation](https://caltechlibrary.github.io/caltechdata_api/caltechdata_api/cli-documentation-for-users).

add_files_authors.py

@@ -0,0 +1,50 @@
+import requests, os, argparse
+from caltechdata_api import write_files_rdm
+
+parser = argparse.ArgumentParser(
+    description="Add files to an existing CaltechAUTHORS record."
+)
+parser.add_argument(
+    "idv",
+    type=str,
+    help="The CaltechAUTHORS record idv to edit.",
+)
+parser.add_argument(
+    "files",
+    type=str,
+    nargs="+",
+    help="The files to upload to the record.",
+)
+args = parser.parse_args()
+idv = args.idv
+files = args.files
+token = os.environ["RDMTOK"]
+url = "https://authors.library.caltech.edu"
+
+headers = {
+    "Authorization": "Bearer %s" % token,
+    "Content-type": "application/json",
+}
+f_headers = {
+    "Authorization": "Bearer %s" % token,
+    "Content-type": "application/octet-stream",
+}
+
+existing = requests.get(
+    url + "/api/records/" + idv + "/draft",
+    headers=headers,
+)
+if existing.status_code != 200:
+    raise Exception(f"Record {idv} does not exist, cannot edit")
+data = existing.json()
+data["files"] = {"enabled": True}
+# Update metadata
+result = requests.put(
+    url + "/api/records/" + idv + "/draft",
+    headers=headers,
+    json=data,
+)
+if result.status_code != 200:
+    raise Exception(result.text)
+file_link = result.json()["links"]["files"]
+write_files_rdm(files, file_link, headers, f_headers)

caltechdata_api/__init__.py

@@ -8,6 +8,7 @@
     caltechdata_edit,
     caltechdata_unembargo,
     caltechdata_accept,
+    caltechdata_reject,
 )
 from .customize_schema import customize_schema, validate_metadata
 from .get_metadata import get_metadata

caltechdata_api/caltechdata_edit.py

@@ -49,6 +49,48 @@ def caltechdata_accept(ids, token=None, production=False):
             raise Exception(result.text)
 
 
+def caltechdata_reject(ids, token=None, production=False, authors=False):
+    # Reject a record from a community
+
+    # If no token is provided, get from RDMTOK environment variable
+    if not token:
+        token = os.environ["RDMTOK"]
+
+    if production == True:
+        if authors:
+            url = "https://authors.library.caltech.edu"
+        else:
+            url = "https://data.caltech.edu"
+    else:
+        if authors:
+            url = "https://authors.caltechlibrary.dev"
+        else:
+            url = "https://data.caltechlibrary.dev"
+
+    headers = {
+        "Authorization": "Bearer %s" % token,
+        "Content-type": "application/json",
+    }
+
+    for idv in ids:
+        result = requests.get(
+            url + "/api/records/" + idv + "/draft/review", headers=headers
+        )
+        print(url + "/api/records/" + idv + "/draft/review")
+        if result.status_code != 200:
+            raise Exception(result.text)
+        accept_link = result.json()["links"]["actions"]["decline"]
+        data = comment = {
+            "payload": {
+                "content": "This record was declined automatically with the CaltechDATA API",
+                "format": "html",
+            }
+        }
+        result = requests.post(accept_link, json=data, headers=headers)
+        if result.status_code != 200:
+            raise Exception(result.text)
+
+
 def caltechdata_edit(
     idv,
     metadata={},
@@ -66,6 +108,8 @@ def caltechdata_edit(
     default_preview=None,
     authors=False,
     keepfiles=False,
+    return_id=False,
+    local=False,
 ):
     # Make a copy of the metadata to make sure our local changes don't leak
     metadata = copy.deepcopy(metadata)
@@ -81,14 +125,22 @@ def caltechdata_edit(
     # Check if file links were provided in the metadata
     descriptions = []
     ex_file_links = []
+    ex_file_descriptions = []
     if "descriptions" in metadata:
         for d in metadata["descriptions"]:
             if d["description"].startswith("Files available via S3"):
                 file_text = d["description"]
                 file_list = file_text.split('href="')
+                # Check if we have file_descriptions
+                split_comma = file_list[0].split(", ")
+                if len(split_comma) == 3:
+                    ex_file_descriptions.append(split_comma[1])
                 # Loop over links in description, skip header text
                 for file in file_list[1:]:
                     ex_file_links.append(file.split('"\n')[0])
+                    split_comma = file.split(", ")
+                    if len(split_comma) == 3:
+                        ex_file_descriptions.append(split_comma[1])
             else:
                 descriptions.append(d)
         # We remove file link descriptions, and re-add below
@@ -102,17 +154,21 @@ def caltechdata_edit(
     # Otherwise we add file links found in the mtadata file
     elif ex_file_links:
         metadata = add_file_links(
-            metadata, ex_file_links, file_descriptions, s3_link=s3_link
+            metadata, ex_file_links, ex_file_descriptions, s3_link=s3_link
         )
 
     if authors == False:
         if production == True:
             url = "https://data.caltech.edu/"
+        elif local == True:
+            url = "https://127.0.0.1:5000/"
         else:
             url = "https://data.caltechlibrary.dev/"
     else:
         if production == True:
             url = "https://authors.library.caltech.edu/"
+        elif local == True:
+            url = "https://127.0.0.1:5000/"
         else:
             url = "https://authors.caltechlibrary.dev/"
 
@@ -299,10 +355,13 @@ def caltechdata_edit(
         result = requests.post(publish_link, headers=headers)
         if result.status_code != 202:
             raise Exception(result.text)
-        pids = result.json()["pids"]
-        if "doi" in pids:
-            return pids["doi"]["identifier"]
+        if return_id:
+            return result.json()["id"]
         else:
-            return pids["oai"]["identifier"]
+            pids = result.json()["pids"]
+            if "doi" in pids:
+                return pids["doi"]["identifier"]
+            else:
+                return pids["oai"]["identifier"]
     else:
         return idv