Feat: Addresses changes to the bagit profiles for UAL preservation workflow (Issue #114)

bagger/README.md

@@ -96,7 +96,7 @@ class Status(IntEnum):
     DRY_RUN = SUCCESS
 ```
 
-Code that imports the `Bagger` module can use the name or value of the `Status` object: 
+Code that imports the `Bagger` module can use the name or value of the `Status` object:
 
 ```python
 if status == Status.INVALID_PATH:
@@ -140,6 +140,8 @@ workflow = "default_workflow.json" # Path to the DART workflow file
 dart_command = "dart-runner" # Command or path to DART executable
 ```
 
+There are currently two workflows `default_workflow.json` and `noupload_workflow.json`. The only difference is that the latter instructs dart-runner to not upload files to any remote storage locations.
+
 ### Logging
 
 ReBACH-Bagger logs errors, debug messages, and DART output to disk.
@@ -152,12 +154,12 @@ logfile_prefix = "ReBACH-Bagger" # Log filename prefix
 
 ### Wasabi
 
-Both DART and ReBACH-Bagger use the credentials in this section to authenticate to Wasabi. 
+Both DART and ReBACH-Bagger use the credentials in this section to authenticate to Wasabi.
 ReBACH-Bagger checks Wasabi for duplicate bags. See [DART Workflow]("#dart-workflow") for details on how
-these variables are used in DART. 
+these variables are used in DART.
 
-If the `dart_workflow_hostbucket_override` variable is set to `true` 
-(default), the values of `host` and `bucket` defined here are used in the DART workflow defined in the 
+If the `dart_workflow_hostbucket_override` variable is set to `true`
+(default), the values of `host` and `bucket` defined here are used in the DART workflow defined in the
 `workflow` variable above. If set to `false`, the values defined in the workflow itself are used instead. This
 option can only be set in the configuration file.
 
@@ -192,7 +194,7 @@ the tag.
 
 ### Metadata from JSON
 
-Users may also use an inline table to define a dot-notation `tag_path` to the tag's corresponding 
+Users may also use an inline table to define a dot-notation `tag_path` to the tag's corresponding
 key in the package's metadata file. Take the following abbreviated example of a metadata JSON file:
 
 ```json
@@ -214,15 +216,35 @@ key in the package's metadata file. Take the following abbreviated example of a
 }
 ```
 
-To define a set of tags based on this metadata named "First-Author", "License", and "DOI" in the 
+To define a set of tags based on this metadata named "First-Author", "License", and "DOI" in the
 "bag-info.txt" tag file, users can define the following relationships in the config file:
 
 ```toml
 [Metadata]
-bag-info.First-Author = { tag_path = "authors.0.full_name" }
-bag-info.License = { tag_path = "license.name" }
-bag-info.DOI = { tag_path = "doi" }
+bag-info.First-Author = { tag_path = ["authors.0.full_name"] }
+bag-info.License = { tag_path = ["license.name"] }
+bag-info.DOI = { tag_path = ["doi"] }
+```
+
+To extract multiple items and concatenate their values into a single tag, include more list items.
+
+```toml
+bag-info.External-Identifier = { tag_path = ["authors.0.full_name", "#hash#"] }
+```
+
+Note the special value `#hash#`. This will not extract values from the JSON but instead from the name of the bag that will be created. Available values:
+
+- `#id#`: the article id
+- `#version#`: the article version (in `vXX` format where XX is a zero-padded number from 1 to 99)
+- `#hash#`: The metadata hash
+
+In the example, the value of External-Identifier will be set to `Brian Avants-<md5>` where `<md5>` is the 32 character MD5 hash computed by bagger for the bag name. To include literal text in the tag, enclose it in `@`. 
+
+```toml
+bag-info.External-Identifier = { tag_path = ["@azu_@", "authors.0.full_name", "#hash#"] }
 ```
+sets External-Identifier to `azu_Brian Avants-<md5>`
+
 
 ### Metadata Utilities
 

bagger/bag.py

@@ -125,7 +125,7 @@ def _init_dart(self, package_path: PathLike) -> Union[Status, tuple[str, list]]:
         if not self.validate_package(metadata_path):
             return Status.INVALID_PACKAGE
 
-        metadata_tags = Metadata(self.config, metadata_path,
+        metadata_tags = Metadata(self.config, metadata_path, article_id, version, metadata_hash,
                                  self.log).parse_metadata()
 
         if not metadata_tags:

bagger/config/default.example.toml

@@ -1,6 +1,6 @@
 [Defaults]
 output_dir = "out"
-workflow = "bagger/config/default_workflow.json"
+workflow = "bagger/config/noupload_workflow.json"
 dart_command = "dart-runner"
 overwrite = false
 delete = true
@@ -26,6 +26,7 @@ aptrust-info.Description = { tag_path = "description", strip_html = true }
 
 bag-info.Contact-Name = "ReDATA Administrator"
 bag-info.Contact-Email = "redata@arizona.edu"
-bag-info.Internal-Sender-Identifier = { tag_path = "doi" }
-bag-info.License-Name = { tag_path = "license.name" }
-bag-info.Published-Date = { tag_path = "published_date" }
+bag-info.Internal-Sender-Identifier = { tag_path = ["doi"] }
+bag-info.License-Name = { tag_path = ["license.name"] }
+bag-info.Published-Date = { tag_path = ["published_date"] }
+bag-info.External-Identifier = { tag_path = ["id", "#version#", "authors.0.first_name", "authors.0.last_name", "#hash#"] }

bagger/config/default_workflow.json

@@ -6,14 +6,14 @@
   "packagePluginId": "BagIt",
   "packagePluginName": null,
   "bagItProfile": {
-    "id": "80dda49d-96c9-46dd-91bf-7f57053854d4",
+    "id": "7f0cd963-4750-4c10-a3de-0c65bb0d0dc5",
     "userCanDelete": true,
     "required": [
       "name",
       "id"
     ],
     "errors": {},
-    "name": "ReDATA BagIt Profile",
+    "name": "ReDATA",
     "description": "BagIt Profile for ReDATA BagIt preservation using ReBACH (based on APTrust BagIt Profile v2.2)",
     "acceptBagItVersion": [
       "0.97",
@@ -24,13 +24,13 @@
     ],
     "allowFetchTxt": false,
     "bagItProfileInfo": {
-      "bagItProfileIdentifier": "https://raw.githubusercontent.com/UAL-RE/ReBACH/main/profiles/redata-bagit-dart-v2.2.json",
+      "bagItProfileIdentifier": "https://raw.githubusercontent.com/UAL-RE/ReBACH/main/bagger/profiles/redata-bagit-dart-v3.0.json",
       "bagItProfileVersion": "",
       "contactEmail": "redata@arizona.edu",
       "contactName": "ReDATA Administrator",
-      "externalDescription": "BagIt profile for creating bags from ReDATA content. Based on APTrust BagIt profile v2.2.",
+      "externalDescription": "Profile for ReDATA content. Based on APTrust BagIt profile v2.2. bagItProfileIdentifier points to a DART settings object which contains this profile.",
       "sourceOrganization": "redata.arizona.edu",
-      "version": "2.2"
+      "version": "3.0"
     },
     "manifestsRequired": [
       "md5"
@@ -106,14 +106,15 @@
         "tagName": "Bag-Count",
         "required": false,
         "values": [],
-        "defaultValue": "",
+        "defaultValue": null,
         "userValue": "",
         "help": "The number of bags that make up this object. Set this only if you are packaging a single object into multiple bags. See https://wiki.aptrust.org/Bagging_specifications for info on naming multi-part APTrust bags.",
         "isBuiltIn": true,
         "isUserAddedFile": false,
         "isUserAddedTag": false,
         "wasAddedForJob": false,
-        "errors": {}
+        "errors": {},
+        "emptyOk": true
       },
       {
         "id": "41b75504-e54d-49a1-aad4-c8a4921d15ce",
@@ -287,7 +288,7 @@
         "errors": {}
       },
       {
-        "id": "16772027-e33b-416b-9eb1-9d50b02224f7",
+        "id": "22f51ea6-de98-494e-a876-dbaeb004cc9f",
         "tagFile": "bag-info.txt",
         "tagName": "License-Name",
         "required": false,
@@ -305,15 +306,30 @@
         ],
         "defaultValue": "",
         "userValue": "",
-        "help": "The name of the license assigned to the record in ReDATA. For items with multiple licenses,",
+        "help": "The name of the license assigned to the record in ReDATA.",
+        "isBuiltIn": false,
+        "isUserAddedFile": false,
+        "isUserAddedTag": true,
+        "wasAddedForJob": false,
+        "errors": {}
+      },
+      {
+        "id": "317ede75-de6f-4bd5-9af0-67c2a24f9174",
+        "tagFile": "bag-info.txt",
+        "tagName": "External-Identifier",
+        "required": true,
+        "values": [],
+        "defaultValue": "",
+        "userValue": "",
+        "help": "Format: {id of item on figshare}-{version}-{first author firstname}-{first author lastname}-{hash}",
         "isBuiltIn": false,
         "isUserAddedFile": false,
         "isUserAddedTag": true,
         "wasAddedForJob": false,
         "errors": {}
       },
       {
-        "id": "d9044d6b-818c-4c3b-b7ff-ab867c525249",
+        "id": "8a264c2d-9a75-4a07-917e-1763e2b57993",
         "tagFile": "bag-info.txt",
         "tagName": "Published-Date",
         "required": false,
@@ -344,8 +360,8 @@
         "id"
       ],
       "errors": {},
-      "name": "Wasabi Main",
-      "description": "Main Wasabi storage endpoint",
+      "name": "Wasabi (ReDATA)",
+      "description": "Wasabi storage for ReDATA. Override necessary settings using ReBACH bagger config.",
       "protocol": "s3",
       "host": "***Override***",
       "port": 0,