caltechdata-api 2.2.2__py3-none-any.whl → 2.2.4__py3-none-any.whl

caltechdata_api/caltechdata_edit.py

@@ -14,7 +14,7 @@ def caltechdata_unembargo(token, ids, production=False):
     print("caltechdaua_unembargo is not yet re-implemented")
 
 
-def caltechdata_accept(ids, token=None, production=False):
+def caltechdata_accept(ids, token=None, production=False, verify=True):
     # Accept a record into a community. Only accepts the first community
     # request
 
@@ -34,11 +34,15 @@ def caltechdata_accept(ids, token=None, production=False):
 
     for idv in ids:
         result = requests.get(
-            url + "/api/records/" + idv + "/draft/review", headers=headers
+            url + "/api/records/" + idv + "/draft/review",
+            headers=headers,
+            verify=verify,
         )
         if result.status_code != 200:
             result = requests.get(
-                url + "/api/records/" + idv + "/requests", headers=headers
+                url + "/api/records/" + idv + "/requests",
+                headers=headers,
+                verify=verify,
             )
             if result.status_code != 200:
                 raise Exception(result.text)
@@ -51,7 +55,7 @@ def caltechdata_accept(ids, token=None, production=False):
                 "format": "html",
             }
         }
-        result = requests.post(accept_link, json=data, headers=headers)
+        result = requests.post(accept_link, json=data, headers=headers, verify=verify)
         if result.status_code != 200:
             raise Exception(result.text)
 
@@ -117,6 +121,7 @@ def caltechdata_edit(
     keepfiles=False,
     return_id=False,
     local=False,
+    verify=True,
 ):
     # Make a copy of the metadata to make sure our local changes don't leak
     metadata = copy.deepcopy(metadata)
@@ -159,28 +164,32 @@ def caltechdata_edit(
             url + "/api/records/" + idv + "/communities",
             headers=headers,
             data=json.dumps({"communities": [{"id": community}]}),
+            verify=verify,
         )
         if result.status_code != 200:
             print(result.url)
             raise Exception(result.text)
-        caltechdata_accept([idv], token, production)
+        caltechdata_accept([idv], token, production, verify=verify)
 
     # Check status
     existing = requests.get(
         url + "/api/records/" + idv,
         headers=headers,
+        verify=verify,
     )
     if existing.status_code != 200:
         # Might have a draft
         existing = requests.get(
             url + "/api/records/" + idv + "/draft",
             headers=headers,
+            verify=verify,
         )
         if existing.status_code != 200:
             # Try back again to the record
             existing = requests.get(
                 url + "/api/records/" + idv,
                 headers=headers,
+                verify=verify,
             )
 
             if existing.status_code != 200:
@@ -202,6 +211,7 @@ def caltechdata_edit(
         result = requests.post(
             url + "/api/records/" + idv + "/versions",
             headers=headers,
+            verify=verify,
         )
         if result.status_code != 201:
             raise Exception(result.text)
@@ -304,12 +314,14 @@ def caltechdata_edit(
     result = requests.get(
         url + "/api/records/" + idv + "/draft",
         headers=headers,
+        verify=verify,
     )
     if result.status_code != 200:
         # We make a draft
         result = requests.post(
             url + "/api/records/" + idv + "/draft",
             headers=headers,
+            verify=verify,
         )
         if result.status_code != 201:
             raise Exception(result.text)
@@ -324,16 +336,28 @@ def caltechdata_edit(
             url + "/api/records/" + idv + "/draft",
             headers=headers,
             json=data,
+            verify=verify,
         )
         if result.status_code != 200:
             raise Exception(result.text)
         file_upload_link = result.json()["links"]["files"]
         if files:
             write_files_rdm(
-                files, file_upload_link, headers, f_headers, keepfiles=keepfiles
+                files,
+                file_upload_link,
+                headers,
+                f_headers,
+                keepfiles=keepfiles,
+                verify=verify,
             )
         if file_links:
-            add_file_links(file_upload_link, file_links, headers, keepfiles=keepfiles)
+            add_file_links(
+                file_upload_link,
+                file_links,
+                headers,
+                keepfiles=keepfiles,
+                verify=verify,
+            )
 
     else:
         # We want files to stay the same as the existing record
@@ -345,6 +369,7 @@ def caltechdata_edit(
             url + "/api/records/" + idv + "/draft",
             headers=headers,
             json=data,
+            verify=verify,
         )
         if result.status_code != 200:
             time.sleep(3)
@@ -352,16 +377,17 @@ def caltechdata_edit(
                 url + "/api/records/" + idv + "/draft",
                 headers=headers,
                 json=data,
+                verify=verify,
             )
             if result.status_code != 200:
                 raise Exception(result.text)
 
     if publish:
         publish_link = f"{url}/api/records/{idv}/draft/actions/publish"
-        result = requests.post(publish_link, headers=headers)
+        result = requests.post(publish_link, headers=headers, verify=verify)
         if result.status_code != 202:
             time.sleep(3)
-            result = requests.post(publish_link, headers=headers)
+            result = requests.post(publish_link, headers=headers, verify=verify)
             if result.status_code != 202:
                 raise Exception(result.text)
         if return_id:

caltechdata_api/caltechdata_write.py

@@ -67,16 +67,21 @@ def write_files_rdm(
                     raise Exception(result.text)
 
 
-def add_file_links(file_upload_link, file_links, headers, keepfiles=False):
+def add_file_links(file_upload_link, file_links, headers, keepfiles=False, verify=True):
     # Currently configured for S3 links, assuming all are at the same endpoint
+    # Links are urls, or (file name, url) pairs when the url file names are not
+    # unique across the bucket
     link_string = ""
-    endpoint = "https://" + file_links[0].split("/")[2]
+    file_links = [
+        link if isinstance(link, (list, tuple)) else (link.split("/")[-1], link)
+        for link in file_links
+    ]
+    endpoint = "https://" + file_links[0][1].split("/")[2]
     s3 = s3fs.S3FileSystem(anon=True, client_kwargs={"endpoint_url": endpoint})
     index = 0
     file_json = []
     f_list = []
-    for link in file_links:
-        file = link.split("/")[-1]
+    for file, link in file_links:
         f_list.append(file)
         path = link.split(endpoint)[1]
         size = s3.info(path)["size"]
@@ -85,20 +90,27 @@ def add_file_links(file_upload_link, file_links, headers, keepfiles=False):
             {"key": file, "size": size, "transfer": {"type": "R", "url": link}}
         )
     # Now we see if any existing files need to be replaced
-    result = requests.get(file_upload_link, headers=headers)
+    result = requests.get(file_upload_link, headers=headers, verify=verify)
     if result.status_code == 200:
         ex_files = result.json()["entries"]
         for ex in ex_files:
             if ex["key"] in f_list:
-                result = requests.delete(ex["links"]["self"], headers=headers)
+                result = requests.delete(
+                    ex["links"]["self"], headers=headers, verify=verify
+                )
                 if result.status_code != 204:
                     raise Exception(result.text)
             else:
                 if keepfiles == False:
-                    result = requests.delete(ex["links"]["self"], headers=headers)
+                    result = requests.delete(
+                        ex["links"]["self"], headers=headers, verify=verify
+                    )
                     if result.status_code != 204:
                         raise Exception(result.text)
-    result = requests.post(file_upload_link, headers=headers, json=file_json)
+
+    result = requests.post(
+        file_upload_link, headers=headers, json=file_json, verify=verify
+    )
     if result.status_code != 201:
         raise Exception(result.text)
 

caltechdata_api/download_from_record.py

@@ -19,7 +19,9 @@ from urllib.parse import urlsplit
 from typing import Any, Dict, Optional, Sequence
 
 
-def get_base_url(production: bool = True, authors: bool = False) -> str:
+def get_base_url(
+    production: bool = True, authors: bool = False, local: bool = False
+) -> str:
     """Get the base URL of the repository to download from.
 
     Parameters
@@ -31,6 +33,11 @@ def get_base_url(production: bool = True, authors: bool = False) -> str:
     authors
         Whether to use CaltechAUTHORS instead of CaltechDATA.
 
+    local
+        Whether to use a local instance, at ``https://127.0.0.1:5000``,
+        instead of the test (development) instance. Ignored when
+        ``production`` is ``True``, as in :func:`caltechdata_write`.
+
     Returns
     -------
     str
@@ -40,6 +47,8 @@ def get_base_url(production: bool = True, authors: bool = False) -> str:
         if authors:
             return "https://authors.library.caltech.edu"
         return "https://data.caltech.edu"
+    elif local:
+        return "https://127.0.0.1:5000"
     else:
         if authors:
             return "https://authors.caltechlibrary.dev"
@@ -51,6 +60,8 @@ def get_files_from_record(
     production: bool = True,
     authors: bool = False,
     token: Optional[str] = None,
+    local: bool = False,
+    verify: bool = True,
 ) -> Dict[str, Any]:
     """Get a dictionary of files associated with a record.
 
@@ -74,25 +85,37 @@ def get_files_from_record(
         token is given and the published record is not found, the
         record's draft is tried as well.
 
+    local
+        Whether to query a local instance, at ``https://127.0.0.1:5000``,
+        instead of the test (development) instance.
+
+    verify
+        Whether to verify the server's TLS certificate. Use ``False``
+        for a local instance with a self-signed certificate.
+
     Returns
     -------
     dict
         A dictionary with the file names as keys and the metadata
         associated with those files as values.
     """
-    base_url = get_base_url(production=production, authors=authors)
+    base_url = get_base_url(production=production, authors=authors, local=local)
     headers = {}
     if token is not None:
         headers["Authorization"] = "Bearer %s" % token
 
-    r = requests.get(f"{base_url}/api/records/{record_id}/files", headers=headers)
+    r = requests.get(
+        f"{base_url}/api/records/{record_id}/files", headers=headers, verify=verify
+    )
     try:
         if r.status_code == 404 and token is not None:
             # An unpublished record has no published version to return,
             # so fall back to its draft, which requires authentication.
             r.close()
             r = requests.get(
-                f"{base_url}/api/records/{record_id}/draft/files", headers=headers
+                f"{base_url}/api/records/{record_id}/draft/files",
+                headers=headers,
+                verify=verify,
             )
 
         r.raise_for_status()
@@ -114,6 +137,8 @@ def download_files_from_record(
     production: bool = True,
     authors: bool = False,
     token: Optional[str] = None,
+    local: bool = False,
+    verify: bool = True,
 ):
     """Download one or more files from a record.
 
@@ -157,12 +182,28 @@ def download_files_from_record(
         files from restricted records. If omitted, the requests are
         made without authentication and only public records are
         available.
+
+    local
+        Whether to download from a local instance, at
+        ``https://127.0.0.1:5000``, instead of the test (development)
+        instance.
+
+    verify
+        Whether to verify the server's TLS certificate, for requests to
+        the instance itself. Use ``False`` for a local instance with a
+        self-signed certificate. Redirects to other hosts are always
+        verified.
     """
     if not os.path.isdir(output_path):
         raise IOError(f"{output_path} is not an extant directory")
 
     files = get_files_from_record(
-        record_id, production=production, authors=authors, token=token
+        record_id,
+        production=production,
+        authors=authors,
+        token=token,
+        local=local,
+        verify=verify,
     )
     if filenames is None:
         filenames = sorted(files.keys())
@@ -181,7 +222,11 @@ def download_files_from_record(
 
         content_url = entry["links"]["content"]
         download_content(
-            content_url, output_file, max_redirects=max_redirects, token=token
+            content_url,
+            output_file,
+            max_redirects=max_redirects,
+            token=token,
+            verify=verify,
         )
 
 
@@ -190,6 +235,7 @@ def download_content(
     fname: os.PathLike,
     max_redirects=5,
     token: Optional[str] = None,
+    verify: bool = True,
 ):
     """Download the contents of a file.
 
@@ -216,6 +262,11 @@ def download_content(
         content from restricted records. If omitted, the request is
         made without authentication. The token is only sent to the
         host of ``content_url``, not to hosts we are redirected to.
+
+    verify
+        Whether to verify the server's TLS certificate. Like the token,
+        it applies only to the host of ``content_url``: a redirect to
+        another host is always verified.
     """
     url = content_url
     host = urlsplit(content_url).netloc
@@ -228,7 +279,9 @@ def download_content(
         if token is not None and urlsplit(url).netloc == host:
             headers["Authorization"] = "Bearer %s" % token
 
-        with requests.get(url, stream=True, headers=headers) as r:
+        # A redirect to another host (the file store) is always verified
+        verify_url = verify if urlsplit(url).netloc == host else True
+        with requests.get(url, stream=True, headers=headers, verify=verify_url) as r:
             r.raise_for_status()
             if "Location" in r.headers:
                 # Redirection - follow to the next URL

{caltechdata_api-2.2.2.dist-info → caltechdata_api-2.2.4.dist-info}/METADATA

@@ -1,9 +1,9 @@
 Metadata-Version: 2.4
 Name: caltechdata_api
-Version: 2.2.2
+Version: 2.2.4
 Summary: Python wrapper for CaltechDATA API.
 Author: Rohan Bhattarai, Elizabeth Won
-Author-email: Thomas E Morrell <tmorrell@caltech.edu>, Alexander A Abakah <aabakah@caltech.edu>, Kshemaahna Nagi <knagi@caltech.edu>
+Author-email: Thomas E Morrell <tmorrell@caltech.edu>, Alexander A Abakah <aabakah@caltech.edu>, Kshemaahna Nagi <knagi@caltech.edu>, Robert Doiel <rsdoiel@caltech.edu>
 Maintainer-email: Thomas E Morrell <tmorrell@caltech.edu>
 License-Expression: BSD-3-Clause
 Project-URL: Homepage, https://github.com/caltechlibrary/caltechdata_api

{caltechdata_api-2.2.2.dist-info → caltechdata_api-2.2.4.dist-info}/RECORD

@@ -1,10 +1,10 @@
 caltechdata_api/__init__.py,sha256=bzrm-nSBmVz7k73oI3hniolXeKbzlJFOMhoyqQ61DwI,585
-caltechdata_api/caltechdata_edit.py,sha256=pXYkIPwRvhbG_x_6hZIJnP38AdJdnq3nsv3XTYr6KCY,12043
-caltechdata_api/caltechdata_write.py,sha256=C-MZwZi8d7OhreBJaB4C51DRH5gQcLo5zEZCPjFUbB0,10338
+caltechdata_api/caltechdata_edit.py,sha256=GjsSvln0rn1Gi5WGdsHtHWnXZ4wfEJyu9zpO-xx8-6g,12697
+caltechdata_api/caltechdata_write.py,sha256=BrcXMJIhPctYdR18oXcjnrFKMK_DY8Q7nfQ7hWVbNkU,10732
 caltechdata_api/cli.py,sha256=4hoUJK5U6dWWKgvIATG8VR85Q1JOuNG38UWYu5QlX1c,31788
 caltechdata_api/customize_schema.py,sha256=3aLbbIlG2PTmP6yXUGuTp56PwFso2qiMgDmy6-qahHs,26510
 caltechdata_api/download_file.py,sha256=IXObPtkS7mKFUViY1ik2X-nBiNB7V6k-Zj8zf01qAQI,1983
-caltechdata_api/download_from_record.py,sha256=gtZRdlUbWevxyLIPUAFILoOpmWVx-ya7UPAuzlR2a3o,10320
+caltechdata_api/download_from_record.py,sha256=9WgvqM3Bh_1S_4L_jKvVi-s-dMH6HdFuqTYxdUZS0C0,12000
 caltechdata_api/get_metadata.py,sha256=IIneLJEx6n6OFGdD_RNz1Ed0mVuacy046UY1TmNG3Ys,4544
 caltechdata_api/md_to_json.py,sha256=T4rDiKPCKcOdkx1sa4kxoWL_rUQYu_QYBzn6FuR0vVc,7745
 caltechdata_api/utils.py,sha256=yD7PIiLFV9xxOWZl4v1YhRI5ChHmEBjXBjc23gfm2pA,2741
@@ -17,9 +17,9 @@ caltechdata_api/vocabularies/relation_types.yaml,sha256=gTPawCQrdeG8VDVZOtbCa7tP
 caltechdata_api/vocabularies/resource_types.yaml,sha256=w2KCOeQ0F3rHPJRHOhoPJn8gRDWn4AgwZ_rhYdYidqg,16372
 caltechdata_api/vocabularies/roles.yaml,sha256=Lgf_P4mDUpe_1GyZlbM3-PC6LAdl4kmNqCsVSqNP1uk,1815
 caltechdata_api/vocabularies/title_types.yaml,sha256=J3qHCGqTadwujy8cU3lP32PfnpIiA6E-nbQYspaDoLU,332
-caltechdata_api-2.2.2.dist-info/licenses/LICENSE,sha256=QvFsgOiOJGxfQjx34g5Fpw2twHYgiIqrcsp1AXxmZiM,1523
-caltechdata_api-2.2.2.dist-info/METADATA,sha256=X10yM3dEN4-KwTe3EgJHEOqem6-CtbEl84VAbiBYKYU,4290
-caltechdata_api-2.2.2.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
-caltechdata_api-2.2.2.dist-info/entry_points.txt,sha256=AYk_A9Pq_6I4jbRZ5rd_Mxbw2W_981mhyXLYgk1oGcI,61
-caltechdata_api-2.2.2.dist-info/top_level.txt,sha256=giC9aULvRY9HlV2IvaPZmwn1b46eLM1rbT3XqYiYOI0,16
-caltechdata_api-2.2.2.dist-info/RECORD,,
+caltechdata_api-2.2.4.dist-info/licenses/LICENSE,sha256=QvFsgOiOJGxfQjx34g5Fpw2twHYgiIqrcsp1AXxmZiM,1523
+caltechdata_api-2.2.4.dist-info/METADATA,sha256=PRX0x0R_F5j-e1eNJ2Zx8YN7A_Jnl1M4LzVMtHiClXw,4326
+caltechdata_api-2.2.4.dist-info/WHEEL,sha256=mOdXR9C3wMVov7cSY8PY-XCzo3SmmWCHvGQr5csJoao,91
+caltechdata_api-2.2.4.dist-info/entry_points.txt,sha256=AYk_A9Pq_6I4jbRZ5rd_Mxbw2W_981mhyXLYgk1oGcI,61
+caltechdata_api-2.2.4.dist-info/top_level.txt,sha256=giC9aULvRY9HlV2IvaPZmwn1b46eLM1rbT3XqYiYOI0,16
+caltechdata_api-2.2.4.dist-info/RECORD,,

{caltechdata_api-2.2.2.dist-info → caltechdata_api-2.2.4.dist-info}/WHEEL

@@ -1,5 +1,5 @@
 Wheel-Version: 1.0
-Generator: setuptools (84.0.0)
+Generator: setuptools (84.2.1)
 Root-Is-Purelib: true
 Tag: py3-none-any