Add simple file upload script

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+
+# Idea software family
+.idea/
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+env/
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*,cover
+
+# Translations
+*.mo
+
+# Django stuff:
+*.log
+
+# PyBuilder
+target/
+
+# Vim swapfiles
+.*.sw?
+

README.md

+Invenio Utilities
+=================
+
+Utility scripts and tools for handling Invenio.
+
+
+upload
+------
+
+Record creation & file upload utility for the REST API introduced in the InvenioRDM November 2020 release.
+

upload/test-record.json

+{
+  "metadata": {
+    "resource_type": { "type": "other", "subtype": "" },
+    "title": "Test Record without Files",
+    "description": "A test record following the metadata schema for InvenioRDM November 2020 release (https://inveniordm.docs.cern.ch/reference/metadata/)",
+    "creators": [
+      {
+        "given_name": "Max",
+        "family_name": "Moser",
+        "type": "personal",
+        "affiliations": [
+          { "name": "TU Wien", "identifiers": { "ror": "04d836q62" } }
+        ]
+      },
+      {
+        "given_name": "Tomasz",
+        "family_name": "Miksa",
+        "type": "personal",
+        "identifiers": { "orcid": "0000-0002-4929-7875" },
+        "affiliations": [
+          { "name": "TU Wien", "identifiers": { "ror": "04d836q62" } }
+        ]
+      }
+    ],
+    "publisher": "TU Data",
+    "publication_date": "2020-12-01"
+  },
+  "access": {
+    "metadata": false,
+    "files": false,
+    "owned_by": [1],
+    "access_right": "open"
+  }
+}
+

upload/test-record/metadata.json

+{
+  "metadata": {
+    "resource_type": { "type": "other", "subtype": "" },
+    "title": "Test Record with Files",
+    "description": "A test record following the metadata schema for InvenioRDM November 2020 release (https://inveniordm.docs.cern.ch/reference/metadata/)",
+    "creators": [
+      {
+        "given_name": "Max",
+        "family_name": "Moser",
+        "type": "personal",
+        "affiliations": [
+          { "name": "TU Wien", "identifiers": { "ror": "04d836q62" } }
+        ]
+      },
+      {
+        "given_name": "Tomasz",
+        "family_name": "Miksa",
+        "type": "personal",
+        "identifiers": { "orcid": "0000-0002-4929-7875" },
+        "affiliations": [
+          { "name": "TU Wien", "identifiers": { "ror": "04d836q62" } }
+        ]
+      }
+    ],
+    "publisher": "TU Data",
+    "publication_date": "2020-12-01"
+  },
+  "access": {
+    "metadata": false,
+    "files": false,
+    "owned_by": [1],
+    "access_right": "open"
+  }
+}
+

upload/upload.sh

+#!/bin/bash
+# script for creating records in invenio (november 2020 release)
+#
+# a record should either consist of a single json file containing the metadata
+# in the expected format (record.json), or it should be a directory containing
+# the file 'metadata.json' and a directory 'files/'.
+# in the latter case, all files in this subdirectory will be uploaded as part
+# of the deposit.
+#
+# record/
+#   metadata.json
+#   files/
+#     file1.ext
+#     file2.ext
+#     ...
+
+function usage () {
+	echo "usage: $0 [ RECORD_DIR | RECORD_JSON ] ..." 1>&2
+}
+
+base_url="https://localhost:5000"
+while getopts "u:h" opt; do
+	case "${opt}" in
+		u)
+			base_url=${OPTARG}
+			;;
+		h)
+			usage
+			exit 0
+			;;
+		*)
+			usage
+			exit 1
+			;;
+	esac
+done
+shift $(( OPTIND - 1 ))
+
+if [[ $# -lt 1 ]]; then
+	usage
+	exit 1
+fi
+
+record_dirs=()
+record_files=()
+while [[ $# -gt 0 ]]; do
+	record=$1
+	if [[ -f $record ]]; then
+		jq . $record > /dev/null
+		if [[ $? -eq 0 ]]; then
+			record_files+=( $record )
+		else
+			echo "not a valid json file: $record/metadata.json" 1>&2
+		fi
+	elif [[ -d $record && -f $record/metadata.json ]]; then
+		jq . $record/metadata.json > /dev/null
+		if [[ $? -eq 0 ]]; then
+			record_dirs+=( $record )
+		else
+			echo "not a valid json file: $record/metadata.json" 1>&2
+		fi
+	else
+		echo "unknown entity: $record" 1>&2
+	fi
+
+	shift
+done
+
+if [[ $(( ${#record_dirs[@]} + ${#record_files[@]} )) -le 0 ]]; then
+	echo "no valid record files/directories specified"
+	exit 1
+fi
+
+recids=()
+for record in ${record_dirs[@]}; do
+	recid=$(curl -sk -X POST -H 'Content-Type: application/json' -d @${record}/metadata.json ${base_url}/api/records | jq ".id")
+	recid=${recid%\"}
+	recid=${recid#\"}
+	recids+=( $recid )
+
+	files=()
+	file_objects=""
+	if [[ -d $record/files ]]; then
+		for file in $record/files/*; do
+			if [[ ! -f $file ]]; then
+				echo "not a file: $file" 1>&2
+				continue
+			fi
+			file_name=$(basename $file)
+			files+=( $file_name )
+			file_object="{\"key\":\"${file_name}\"}"
+			file_objects="${file_objects},${file_object}"
+		done
+	fi
+
+	curl -sk -X POST -H 'Content-Type: application/json' -d "[${file_objects:1}]" ${base_url}/api/records/${recid}/draft/files > /dev/null
+
+	for file in ${files[@]}; do
+		curl -sk -X PUT -H 'Content-Type: application/octet-stream' --upload-file ${record}/files/${file} ${base_url}/api/records/${recid}/draft/files/${file}/content > /dev/null
+		curl -sk -X POST ${base_url}/api/records/${recid}/draft/files/${file}/commit > /dev/null
+	done
+
+	curl -sk -X POST ${base_url}/api/records/${recid}/draft/actions/publish > /dev/null
+done
+
+for record in ${record_files[@]}; do
+	recid=$(curl -sk -X POST -H 'Content-Type: application/json' -d @${record} ${base_url}/api/records | jq ".id")
+	recid=${recid%\"}
+	recid=${recid#\"}
+	recids+=( $recid )
+
+	curl -sk -X POST ${base_url}/api/records/${recid}/draft/actions/publish > /dev/null
+done
+
+for recid in ${recids[@]}; do
+	echo ${recid}
+done
+