Merge branch 'main' into original-format

.appveyor.yml

@@ -74,7 +74,7 @@ environment:
       APPVEYOR_BUILD_WORKER_IMAGE: Visual Studio 2019
       # Python version specification is non-standard on windows
       PY: 39-x64
-      INSTALL_GITANNEX: git-annex -m datalad/git-annex:release
+      INSTALL_GITANNEX: git-annex -m datalad/packages
     # MacOS core tests
     - ID: MacP38core
       DTS: datalad_dataverse
@@ -89,20 +89,13 @@ matrix:
     - KNOWN2FAIL: 1
 
 
-# do not run the CI if only documentation changes were made
+# only run the CI for code changes.
 # documentation builds are tested elsewhere and cheaper
-skip_commits:
+only_commits:
   files:
-    - docs/
-    - changelog.d/
-    - .github/
-    - CHANGELOG.md
-    - CITATION.cff
-    - CONTRIBUTORS
-    - LICENSE
-    - Makefile
-    - README.md
-    - readthedocs.yml
+    - .appveyor.yml
+    - datalad_dataverse/
+    - tools/
 
 
 # it is OK to specify paths that may not exist for a particular test run

CODE_OF_CONDUCT.md

@@ -6,7 +6,7 @@
 We as members, contributors, and leaders pledge to make participation in our
 community a harassment-free experience for everyone, regardless of age, body
 size, visible or invisible disability, ethnicity, sex characteristics, gender
-identity and expression, level of experience, education, socio-economic status,
+identity and expression, level of experience, education, socioeconomic status,
 nationality, personal appearance, race, caste, color, religion, or sexual
 identity and orientation.
 

README.md

@@ -38,6 +38,9 @@ Doing so will enable the extension to also alter the behavior the core DataLad
 package and its commands, from example to be able to directly clone from
 a Dataverse dataset landing page.
 
+Full-compatibility with Windows requires a git-annex installation of version
+10.20230321 (or later).
+
 
 ## Summary of functionality provided by this extension
 

datalad_dataverse/dataset.py

@@ -94,7 +94,7 @@ def __init__(self, api, dsid: str, root_path: str | None = None):
         # check if project with specified doi exists
         # TODO ask for ':latest' and cache?
         dv_ds = api.get_dataset(identifier=dsid)
-        if not dv_ds.ok:
+        if not dv_ds.status_code < 400:
             raise RuntimeError("Cannot find dataset")
 
     def get_fileid_from_path(
@@ -171,13 +171,18 @@ def download_file(self, fid: int, path: Path):
         # https://github.com/gdcc/pyDataverse/issues/49
         # the code below is nevertheless readied for such a
         # scenario
-        response = self.data_access_api.get_datafile(fid, data_format="original")
+        response = self.data_access_api.get_datafile(fid, is_pid=False, data_format="original")
         # http error handling
         response.raise_for_status()
         with path.open("wb") as f:
+            # accommodate old and newer pydataverse version
+            try:
+                it = response.iter_content
+            except AttributeError:
+                it = response.iter_bytes
             # `chunk_size=None` means
             # "read data in whatever size the chunks are received"
-            for chunk in response.iter_content(chunk_size=None):
+            for chunk in it(chunk_size=None):
                 f.write(chunk)
 
     def remove_file(self, fid: int):

datalad_dataverse/tests/test_pydataverse.py

@@ -54,14 +54,21 @@ def test_file_handling(
 def check_download(api, fileid, dsid, fpath, src_md5):
     # TODO there is no standalone implementation of the following
     # reimplementing DataverseRemote._download_file
-    response = api.get_datafile(fileid)
+
+    # recent pydataverse requires saying `is_pid=False` for a file-id
+    response = api.get_datafile(fileid, is_pid=False)
     # TODO this could also just be a download via HttpUrlOperations
     # avoiding any custom code
     assert response.status_code == 200
     with fpath.open("wb") as f:
-        # use a stupdly small chunksize to actual get chunking on
+        # accommodate old and newer pydataverse version
+        try:
+            it = response.iter_content
+        except AttributeError:
+            it = response.iter_bytes
+        # use a stupdily small chunksize to actual get chunking on
         # our tiny test file
-        for chunk in response.iter_content(chunk_size=1):
+        for chunk in it(chunk_size=1):
             f.write(chunk)
 
     # confirm identity