From c315c4b1ff5b3b83d2fb298e18ae461369082fc2 Mon Sep 17 00:00:00 2001
From: wshahn <162052406+wshahn@users.noreply.github.com>
Date: Mon, 9 Sep 2024 16:04:09 -0400
Subject: [PATCH 1/2] Update get_collection_storagesize.py

Slight alteration of script to ignore processing the root dataverse collection, and only get the size of sub-collections. Additionally, the instance url has been changed to use 'unc' instead of 'root'.
---
 get_collection_storagesize.py | 22 +++++++++++++---------
 1 file changed, 13 insertions(+), 9 deletions(-)

diff --git a/get_collection_storagesize.py b/get_collection_storagesize.py
index cd0b6bc..353a99c 100755
--- a/get_collection_storagesize.py
+++ b/get_collection_storagesize.py
@@ -30,7 +30,7 @@ def get_size(dataverse,collection,token):
     # throws I/O errors in TRSA case
     #dvurl = dataverse + '/api/dataverses/' + collection + '/storagesize?includeCached=true&key=' + token
     dvurl = dataverse + '/api/dataverses/' + collection + '/storagesize?key=' + token
-    r = requests.get(dvurl)
+    r = requests.get(dvurl)   
     j = r.json()
     # strip out "size of this ... bytes"
     error = "Couldn't get storagesize for collection: " + collection
@@ -77,15 +77,16 @@ def format_size(byte_size):
    readablesize = format_size(size)
    dvfilecount = get_filecount(dataverse,collection,token)
    print(collection + ': ' + str(size) + ' bytes' + ' (' + readablesize + '), ' + str(dvfilecount) + ' files.')
-   
+     
 else:
-   # start with the root dataverse
-   collection = 'root'
-   size = get_size(dataverse,collection,token)
-   dvfilecount = get_filecount(dataverse,collection,token)
-   print(collection + ': ' + str(size) + ' bytes, ' + str(dvfilecount) + ' files.')
-   # now iterate through sub-collections
-   instanceurl = dataverse + '/api/dataverses/root/contents'
+   # don't process root for performance reasons
+   #collection = 'root'
+   #size = get_size(dataverse,collection,token)
+   #dvfilecount = get_filecount(dataverse,collection,token)
+   #print(collection + ': ' + str(size) + ' bytes, ' + str(dvfilecount) + ' files.')
+   
+   # iterate through sub-collections
+   instanceurl = dataverse + '/api/dataverses/unc/contents'
    r = requests.get(instanceurl)
    j = r.json()
    for i in range(len(j["data"])):
@@ -97,6 +98,9 @@ def format_size(byte_size):
           ar = requests.get(aliasurl)
           aj = ar.json()
           collection = aj["data"]["alias"]
+          # get size
           size = get_size(dataverse,collection,token)
+          readablesize = format_size(size)
           dvfilecount = get_filecount(dataverse,collection,token)
           print(collection + ': ' + str(size) + ' bytes' + ' (' + readablesize + '), ' + str(dvfilecount) + ' files.')
+          

From cb84245e681a63872f220ff679aeb28fd5792687 Mon Sep 17 00:00:00 2001
From: wshahn <162052406+wshahn@users.noreply.github.com>
Date: Mon, 23 Jun 2025 13:59:12 -0400
Subject: [PATCH 2/2] Add files via upload

---
 get_collection_storagesize.py | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/get_collection_storagesize.py b/get_collection_storagesize.py
index 353a99c..610cf40 100755
--- a/get_collection_storagesize.py
+++ b/get_collection_storagesize.py
@@ -10,6 +10,7 @@
 parser.add_argument('-c', '--collection', help='Sum the size of datasets in the given Dataverse collection.')
 parser.add_argument('-a', '--all_collections', help='Report the sizes of all collections in the given Dataverse.', action='store_true')
 parser.add_argument('-t', '--api_token', help='API token of an admin user.')
+parser.add_argument('-r', '--root_collection', default='root', help='Specify the name of the root collection.')
 
 args = parser.parse_args()
 if (args.collection is None) and (args.all_collections is False):
@@ -25,6 +26,7 @@
 collection = args.collection
 all = args.all_collections
 token = args.api_token
+root_coll = args.root_collection
 
 def get_size(dataverse,collection,token):
     # throws I/O errors in TRSA case
@@ -86,7 +88,7 @@ def format_size(byte_size):
    #print(collection + ': ' + str(size) + ' bytes, ' + str(dvfilecount) + ' files.')
    
    # iterate through sub-collections
-   instanceurl = dataverse + '/api/dataverses/unc/contents'
+   instanceurl = dataverse + f"/api/dataverses/{root_coll}/contents"
    r = requests.get(instanceurl)
    j = r.json()
    for i in range(len(j["data"])):
@@ -103,4 +105,3 @@ def format_size(byte_size):
           readablesize = format_size(size)
           dvfilecount = get_filecount(dataverse,collection,token)
           print(collection + ': ' + str(size) + ' bytes' + ' (' + readablesize + '), ' + str(dvfilecount) + ' files.')
-