From 9af49de3c9751acaf0eb15bb44dd32ed1531e099 Mon Sep 17 00:00:00 2001
From: Miguel Caballer <micafer1@upv.es>
Date: Wed, 25 Sep 2024 10:42:44 +0200
Subject: [PATCH 1/3] Revert changes in OSF

---
 datahugger/services.py       | 23 ++---------------------
 tests/test_repositories.toml |  4 ----
 2 files changed, 2 insertions(+), 25 deletions(-)

diff --git a/datahugger/services.py b/datahugger/services.py
index 9c4baa1..022adf5 100644
--- a/datahugger/services.py
+++ b/datahugger/services.py
@@ -320,13 +320,13 @@ class MendeleyDataset(DatasetDownloader):
 class OSFDataset(DatasetDownloader):
     """Downloader for OSF repository."""
 
-    REGEXP_ID = r"osf\.io\/(?P<record_id>[^\/]*)\/{0,1}"
+    REGEXP_ID = r"osf\.io\/(?P<record_id>.*)/"
 
     # the base entry point of the REST API
     API_URL = "https://api.osf.io/v2/nodes/"
 
     # the files and metadata about the dataset
-    API_URL_META = "{api_url}{record_id}/files/"
+    API_URL_META = "{api_url}{record_id}/files/osfstorage/?format=jsonapi"
     META_FILES_JSONPATH = "data[*]"
 
     PAGINATION_JSONPATH = "links.next"
@@ -342,25 +342,6 @@ class OSFDataset(DatasetDownloader):
     ATTR_HASH_JSONPATH = "attributes.extra.hashes.sha256"
     ATTR_HASH_TYPE_VALUE = "sha256"
 
-    def _get_node_providers(self):
-        """Get the providers of a node."""
-        record_id = self._params["record_id"]
-        res = requests.get(f"{self.API_URL}/{record_id}/files/")
-        return set([prov["attributes"]["provider"] for prov in res.json()["data"]])
-
-    def _get_files_recursive(self, url, folder_name=None, base_url=None):
-        files = []
-        # In case of the top-level folder, we need to get first the providers
-        if folder_name is None:
-            for provider in self._get_node_providers():
-                # and then the files of each provider
-                files.extend(
-                    super()._get_files_recursive(f"{url}{provider}/", None, base_url)
-                )
-        else:
-            files = super()._get_files_recursive(url, folder_name, base_url)
-        return files
-
 
 class ZenodoDataset(DatasetDownloader):
     """Downloader for Zenodo repository.
diff --git a/tests/test_repositories.toml b/tests/test_repositories.toml
index 04dc97b..bf81923 100644
--- a/tests/test_repositories.toml
+++ b/tests/test_repositories.toml
@@ -62,10 +62,6 @@ files = "ReadmeFile.txt"
 location = "https://doi.org/10.5061/dryad.31zcrjdm5"
 files = "ReadmeFile.txt"
 
-[[osf]]
-location = "https://osf.io/ews27/"
-files = "Cross-comparison/amarlt1"
-
 [[osf]]
 location = "https://osf.io/kq573/"
 files = "nest_area_data.xlsx"

From 5d3c3d3f5ba4878bacbb6bbd67605f40eea518c6 Mon Sep 17 00:00:00 2001
From: Miguel Caballer <micafer1@upv.es>
Date: Wed, 25 Sep 2024 10:49:25 +0200
Subject: [PATCH 2/3] Enable to miss the last /

---
 datahugger/services.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/datahugger/services.py b/datahugger/services.py
index 022adf5..2941464 100644
--- a/datahugger/services.py
+++ b/datahugger/services.py
@@ -320,7 +320,7 @@ class MendeleyDataset(DatasetDownloader):
 class OSFDataset(DatasetDownloader):
     """Downloader for OSF repository."""
 
-    REGEXP_ID = r"osf\.io\/(?P<record_id>.*)/"
+    REGEXP_ID = r"osf\.io\/(?P<record_id>[^\/]*)\/{0,1}"
 
     # the base entry point of the REST API
     API_URL = "https://api.osf.io/v2/nodes/"

From b28d4c1d537e8553d94b8d8fa425de68fa6dd782 Mon Sep 17 00:00:00 2001
From: Miguel Caballer <micafer1@upv.es>
Date: Wed, 25 Sep 2024 11:00:55 +0200
Subject: [PATCH 3/3] Fix figshare test

---
 tests/test_repositories.toml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tests/test_repositories.toml b/tests/test_repositories.toml
index bf81923..9254425 100644
--- a/tests/test_repositories.toml
+++ b/tests/test_repositories.toml
@@ -47,8 +47,8 @@ location = "https://figshare.com/articles/dataset/Long-term_behavioral_repeatabi
 files = "cross_year_data2.csv"
 
 [[figshare]]
-location = "https://doi.org/10.15131/shef.data.22010159.v2"
-files = "ScHARR QUIT evaluation statistical and health economic analysis plan.pdf"
+location = "https://doi.org/10.15131/shef.data.26977237.v1"
+files = "README.txt"
 
 [[djehuty]]
 location = "https://doi.org/10.4121/21989216.v1"