caltechdata-api 1.4.5__tar.gz → 1.6.0__tar.gz

caltechdata_api-1.6.0/PKG-INFO

@@ -0,0 +1,100 @@
+Metadata-Version: 2.1
+Name: caltechdata_api
+Version: 1.6.0
+Summary: Python wrapper for CaltechDATA API.
+Home-page: https://github.com/caltechlibrary/caltechdata_api
+Author: Thomas E Morrell
+Author-email: tmorrell@caltech.edu
+License: https://data.caltech.edu/license
+Platform: UNKNOWN
+Classifier: License :: OSI Approved :: BSD License
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.7
+Classifier: Programming Language :: Python :: Implementation :: CPython
+Classifier: Programming Language :: Python :: Implementation :: PyPy
+Requires-Python: >=3.6.0
+Description-Content-Type: text/markdown
+License-File: LICENSE
+
+
+# CaltechDATA API Python Library
+
+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
+
+### Writing and Editing Records
+- `caltechdata_write`: Writes files and a DataCite 4 standard JSON record to the CaltechDATA repository.
+- `caltechdata_edit`: Edits existing records in CaltechDATA.
+
+### Metadata Operations
+- `get_metadata`: Retrieves metadata from CaltechDATA records.
+
+## Requirements
+
+- Python 3 (Anaconda is recommended)
+- `requests` library
+
+## Installation
+
+Install the library via pip:
+
+```shell
+pip install caltechdata_api
+```
+
+## Examples
+
+There are some example python scripts in the GitHub repository.
+
+###Create a record:
+
+```shell
+python write.py example.json -fnames logo.gif
+# Output: pbkn6-m9y63 (unique identifier)
+```
+> The response will be the unique identifier for the record. You can put this at
+the end of a url to visit the record (e.g.
+https://data.caltechlibrary.dev/records/pbkn6-m9y63)
+
+###Edit a record 
+Make changes to the example.json file to see a change)
+```
+python edit.py example.json -id pbkn6-m9y63
+10.33569/pbkn6-m9y63
+```
+> The response is the DOI for the record, which includes the unique identifier
+for the record in the default configuration.
+
+## Using Custom DOIs 
+Some groups have worked with the library to create custom DOIs. These can be
+passed in the metadata like:
+
+```shell
+python write.py example_custom.json -fnames logo.gif
+m6zxz-p4j22
+```
+
+And then you can edit with
+```
+python edit.py example_custom.json -id m6zxz-p4j22
+10.5281/inveniordm.1234
+```
+
+This returns the custom DOI of the record if it is successful.
+
+
+## Setup and Authentication
+
+1. Acquire a personal access token from your CaltechDATA account (found under "Applications" at the top right of your screen).
+2. Copy the token to a file named token.bash.
+3. Load the token in the command line using source token.bash.
+
+## Note on Testing
+
+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.
+
+
+

caltechdata_api-1.6.0/README.md

@@ -0,0 +1,78 @@
+# CaltechDATA API Python Library
+
+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
+
+### Writing and Editing Records
+- `caltechdata_write`: Writes files and a DataCite 4 standard JSON record to the CaltechDATA repository.
+- `caltechdata_edit`: Edits existing records in CaltechDATA.
+
+### Metadata Operations
+- `get_metadata`: Retrieves metadata from CaltechDATA records.
+
+## Requirements
+
+- Python 3 (Anaconda is recommended)
+- `requests` library
+
+## Installation
+
+Install the library via pip:
+
+```shell
+pip install caltechdata_api
+```
+
+## Examples
+
+There are some example python scripts in the GitHub repository.
+
+###Create a record:
+
+```shell
+python write.py example.json -fnames logo.gif
+# Output: pbkn6-m9y63 (unique identifier)
+```
+> The response will be the unique identifier for the record. You can put this at
+the end of a url to visit the record (e.g.
+https://data.caltechlibrary.dev/records/pbkn6-m9y63)
+
+###Edit a record 
+Make changes to the example.json file to see a change)
+```
+python edit.py example.json -id pbkn6-m9y63
+10.33569/pbkn6-m9y63
+```
+> The response is the DOI for the record, which includes the unique identifier
+for the record in the default configuration.
+
+## Using Custom DOIs 
+Some groups have worked with the library to create custom DOIs. These can be
+passed in the metadata like:
+
+```shell
+python write.py example_custom.json -fnames logo.gif
+m6zxz-p4j22
+```
+
+And then you can edit with
+```
+python edit.py example_custom.json -id m6zxz-p4j22
+10.5281/inveniordm.1234
+```
+
+This returns the custom DOI of the record if it is successful.
+
+
+## Setup and Authentication
+
+1. Acquire a personal access token from your CaltechDATA account (found under "Applications" at the top right of your screen).
+2. Copy the token to a file named token.bash.
+3. Load the token in the command line using source token.bash.
+
+## Note on Testing
+
+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.
+

{caltechdata_api-1.4.5 → caltechdata_api-1.6.0}/caltechdata_api/caltechdata_edit.py

@@ -33,7 +33,6 @@ def caltechdata_accept(ids, token=None, production=False):
     }
 
     for idv in ids:
-
         result = requests.get(
             url + "/api/records/" + idv + "/draft/review", headers=headers
         )
@@ -65,6 +64,7 @@ def caltechdata_edit(
     file_descriptions=[],
     s3_link=None,
     default_preview=None,
+    authors=False,
 ):
     # Make a copy of the metadata to make sure our local changes don't leak
     metadata = copy.deepcopy(metadata)
@@ -104,10 +104,16 @@ def caltechdata_edit(
             metadata, ex_file_links, file_descriptions, s3_link=s3_link
         )
 
-    if production == True:
-        url = "https://data.caltech.edu"
+    if authors == False:
+        if production == True:
+            url = "https://data.caltech.edu/"
+        else:
+            url = "https://data.caltechlibrary.dev/"
     else:
-        url = "https://data.caltechlibrary.dev"
+        if production == True:
+            url = "https://authors.library.caltech.edu/"
+        else:
+            url = "https://authors.caltechlibrary.dev/"
 
     headers = {
         "Authorization": "Bearer %s" % token,
@@ -156,8 +162,12 @@ def caltechdata_edit(
 
     print(idv)
     # Pull out pid information
+    # Not currently used for authors
     if production == True:
-        repo_prefix = "10.22002"
+        if authors == True:
+            repo_prefix = "10.7907"
+        else:
+            repo_prefix = "10.22002"
     else:
         repo_prefix = "10.33569"
     pids = {}
@@ -209,8 +219,18 @@ def caltechdata_edit(
             # We want to have the system set new DOIs
             data["pids"] = {}
     else:
-        metadata["pids"] = pids
-        data = customize_schema.customize_schema(metadata, schema=schema)
+        if authors == False:
+            metadata["pids"] = pids
+            data = customize_schema.customize_schema(metadata, schema=schema)
+        else:
+            # Authors, force oai PID
+            if "pids" not in metadata:
+                metadata["pids"] = {}
+            metadata["pids"]["oai"] = {
+                "identifier": f"oai:authors.library.caltech.edu:{idv}",
+                "provider": "oai",
+            }
+            data = metadata
 
     if files:
         if default_preview:
@@ -250,7 +270,7 @@ def caltechdata_edit(
             if result.status_code != 200:
                 raise Exception(result.text)
         # We want files to stay the same as the existing record
-        data["files"] = existing.json()["files"]
+        data["files"] = existing["files"]
         if default_preview:
             data["files"]["default_preview"] = default_preview
         # Update metadata
@@ -267,7 +287,10 @@ def caltechdata_edit(
         result = requests.post(publish_link, headers=headers)
         if result.status_code != 202:
             raise Exception(result.text)
-        doi = result.json()["pids"]["doi"]["identifier"]
-        return doi
+        pids = result.json()["pids"]
+        if "doi" in pids:
+            return pids["doi"]["identifier"]
+        else:
+            return pids["oai"]["identifier"]
     else:
         return idv

{caltechdata_api-1.4.5 → caltechdata_api-1.6.0}/caltechdata_api/caltechdata_write.py

@@ -67,9 +67,9 @@ def write_files_rdm(files, file_link, headers, f_headers, s3=None):
 def add_file_links(
     metadata, file_links, file_descriptions=[], additional_descriptions="", s3_link=None
 ):
-    # Currently configured for OSN S3 links
+    # Currently configured for S3 links, assuming all are at same endpoint
     link_string = ""
-    endpoint = "https://renc.osn.xsede.org/"
+    endpoint = "https://" + file_links[0].split("/")[2]
     s3 = s3fs.S3FileSystem(anon=True, client_kwargs={"endpoint_url": endpoint})
     index = 0
     for link in file_links:
@@ -102,7 +102,6 @@ def add_file_links(
 
 
 def send_to_community(review_link, data, headers, publish, community, message=None):
-
     if not message:
         message = "This record is submitted automatically with the CaltechDATA API"
 
@@ -189,6 +188,7 @@ def caltechdata_write(
     elif "identifiers" in metadata:
         identifiers = metadata["identifiers"]
     for identifier in identifiers:
+        doi = False
         if "identifierType" in identifier:
             if identifier["identifierType"] == "DOI":
                 doi = identifier["identifier"]
@@ -198,17 +198,11 @@ def caltechdata_write(
                     "identifier": identifier["identifier"],
                     "provider": "oai",
                 }
-            else:
-                doi = False
         elif "scheme" in identifier:
             # We have RDM internal metadata
             if identifier["scheme"] == "doi":
                 doi = identifier["identifier"]
                 prefix = doi.split("/")[0]
-            else:
-                doi = False
-        else:
-            doi = False
         if doi != False:
             if prefix == repo_prefix:
                 pids["doi"] = {