caltechdata-api 2.0.0__tar.gz → 2.2.0__tar.gz

{caltechdata_api-2.0.0 → caltechdata_api-2.2.0}/PKG-INFO

@@ -1,20 +1,25 @@
 Metadata-Version: 2.4
 Name: caltechdata_api
-Version: 2.0.0
+Version: 2.2.0
 Summary: Python wrapper for CaltechDATA API.
-Home-page: https://github.com/caltechlibrary/caltechdata_api
-Author: Thomas E Morrell, Rohan Bhattarai, Elizabeth Won, Alexander A Abakah, Kshemaahna Nagi
-Author-email: tmorrell@caltech.edu, aabakah@caltech.edu, knagi@caltech.edu
-License: MIT
-Classifier: License :: OSI Approved :: MIT License
+Author: Rohan Bhattarai, Elizabeth Won
+Author-email: Thomas E Morrell <tmorrell@caltech.edu>, Alexander A Abakah <aabakah@caltech.edu>, Kshemaahna Nagi <knagi@caltech.edu>
+Maintainer-email: Thomas E Morrell <tmorrell@caltech.edu>
+License-Expression: BSD-3-Clause
+Project-URL: Homepage, https://github.com/caltechlibrary/caltechdata_api
+Project-URL: Repository, https://github.com/caltechlibrary/caltechdata_api
+Project-URL: Issues, https://github.com/caltechlibrary/caltechdata_api/issues
+Keywords: metadata,software,InvenioRDM
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.6.0
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: requests
@@ -44,7 +49,7 @@ The `caltechdata_api` Python library provides a convenient interface for interac
 
 ## Requirements
 
-- Python 3.6+
+- Python 3.9+
 
 ## Installation
 
@@ -54,6 +59,18 @@ Install the library via pip:
 pip install caltechdata_api
 ```
 
+Or add it to a [uv](https://docs.astral.sh/uv/) project:
+
+```shell
+uv add caltechdata_api
+```
+
+You can also run a script using uv:
+
+```shell
+uv run write.py
+```
+
 ## Examples
 
 There are some example python scripts in the GitHub repository.
@@ -61,7 +78,7 @@ There are some example python scripts in the GitHub repository.
 ### Create a record:
 
 ```shell
-python write.py example.json -fnames logo.gif
+uv run write.py example.json -fnames logo.gif
 # Output: pbkn6-m9y63 (unique identifier)
 ```
 > The response will be the unique identifier for the record. You can put this at
@@ -71,7 +88,7 @@ https://data.caltechlibrary.dev/records/pbkn6-m9y63)
 ### Edit a record 
 Make changes to the example.json file to see a change)
 ```
-python edit.py example.json -id pbkn6-m9y63
+uv run edit.py example.json -id pbkn6-m9y63
 10.33569/pbkn6-m9y63
 ```
 > The response is the DOI for the record, which includes the unique identifier
@@ -82,13 +99,13 @@ Some groups have worked with the library to create custom DOIs. These can be
 passed in the metadata like:
 
 ```shell
-python write.py example_custom.json -fnames logo.gif
+uv run write.py example_custom.json -fnames logo.gif
 m6zxz-p4j22
 ```
 
 And then you can edit with
 ```
-python edit.py example_custom.json -id m6zxz-p4j22
+uv run edit.py example_custom.json -id m6zxz-p4j22
 10.5281/inveniordm.1234
 ```
 

{caltechdata_api-2.0.0 → caltechdata_api-2.2.0}/README.md

@@ -15,7 +15,7 @@ The `caltechdata_api` Python library provides a convenient interface for interac
 
 ## Requirements
 
-- Python 3.6+
+- Python 3.9+
 
 ## Installation
 
@@ -25,6 +25,18 @@ Install the library via pip:
 pip install caltechdata_api
 ```
 
+Or add it to a [uv](https://docs.astral.sh/uv/) project:
+
+```shell
+uv add caltechdata_api
+```
+
+You can also run a script using uv:
+
+```shell
+uv run write.py
+```
+
 ## Examples
 
 There are some example python scripts in the GitHub repository.
@@ -32,7 +44,7 @@ There are some example python scripts in the GitHub repository.
 ### Create a record:
 
 ```shell
-python write.py example.json -fnames logo.gif
+uv run write.py example.json -fnames logo.gif
 # Output: pbkn6-m9y63 (unique identifier)
 ```
 > The response will be the unique identifier for the record. You can put this at
@@ -42,7 +54,7 @@ https://data.caltechlibrary.dev/records/pbkn6-m9y63)
 ### Edit a record 
 Make changes to the example.json file to see a change)
 ```
-python edit.py example.json -id pbkn6-m9y63
+uv run edit.py example.json -id pbkn6-m9y63
 10.33569/pbkn6-m9y63
 ```
 > The response is the DOI for the record, which includes the unique identifier
@@ -53,13 +65,13 @@ Some groups have worked with the library to create custom DOIs. These can be
 passed in the metadata like:
 
 ```shell
-python write.py example_custom.json -fnames logo.gif
+uv run write.py example_custom.json -fnames logo.gif
 m6zxz-p4j22
 ```
 
 And then you can edit with
 ```
-python edit.py example_custom.json -id m6zxz-p4j22
+uv run edit.py example_custom.json -id m6zxz-p4j22
 10.5281/inveniordm.1234
 ```
 

{caltechdata_api-2.0.0 → caltechdata_api-2.2.0}/caltechdata_api/__init__.py

@@ -13,5 +13,9 @@ from .caltechdata_edit import (
 from .customize_schema import customize_schema, validate_metadata
 from .get_metadata import get_metadata
 from .download_file import download_file, download_url
+from .download_from_record import (
+    get_files_from_record,
+    download_files_from_record,
+)
 from .utils import humanbytes
 from .md_to_json import parse_readme_to_json

caltechdata_api-2.2.0/caltechdata_api/download_from_record.py

@@ -0,0 +1,236 @@
+"""Functions to download files directly from a CaltechData record.
+
+A CaltechData record ID is the ten characters, separated into two groups
+of five by a dash, found at the end of a CaltechData URL or default DOI.
+For instance, in the URL ``https://data.caltech.edu/records/4rgh7-zss31``
+or DOI ``10.22002/4rgh7-zss31``, the record ID is ``4rgh7-zss31``.
+
+The same functions can download from CaltechAUTHORS by passing
+``authors=True``, and from the test (development) instances of either
+repository by passing ``production=False``.
+"""
+
+import argparse
+import os
+import requests
+from tqdm.auto import tqdm
+
+from typing import Any, Dict, Optional, Sequence
+
+
+def get_base_url(production: bool = True, authors: bool = False) -> str:
+    """Get the base URL of the repository to download from.
+
+    Parameters
+    ----------
+    production
+        Whether to use the production repository. If ``False``, the
+        test (development) instance is used instead.
+
+    authors
+        Whether to use CaltechAUTHORS instead of CaltechDATA.
+
+    Returns
+    -------
+    str
+        The base URL, without a trailing slash.
+    """
+    if production:
+        if authors:
+            return "https://authors.library.caltech.edu"
+        return "https://data.caltech.edu"
+    else:
+        if authors:
+            return "https://authors.caltechlibrary.dev"
+        return "https://data.caltechlibrary.dev"
+
+
+def get_files_from_record(
+    record_id: str, production: bool = True, authors: bool = False
+) -> Dict[str, Any]:
+    """Get a dictionary of files associated with a record.
+
+    Parameters
+    ----------
+    record_id
+        The record ID for which to obtain the list of files. See
+        the module documentation for how to find the record ID.
+
+    production
+        Whether to query the production repository. If ``False``, the
+        test (development) instance is used instead.
+
+    authors
+        Whether to query CaltechAUTHORS instead of CaltechDATA.
+
+    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)
+    with requests.get(f"{base_url}/api/records/{record_id}/files") as r:
+        r.raise_for_status()
+        files = dict()
+        for entry in r.json().get("entries", []):
+            key = entry.pop("key")
+            files[key] = entry
+
+        return files
+
+
+def download_files_from_record(
+    record_id: str,
+    output_path: os.PathLike,
+    filenames: Optional[Sequence[str]] = None,
+    max_redirects: int = 5,
+    production: bool = True,
+    authors: bool = False,
+):
+    """Download one or more files from a record.
+
+    Parameters
+    ----------
+    record_id
+        The record ID from which to download the file. See
+        the module documentation for how to find the record ID.
+
+    output_path
+        Where to download the files. Must be an existing directory.
+        If you want control over exactly how each file is named,
+        use :func:`get_files_from_record` to get the URLs for each
+        file, then manually call :func:`download_content` for each
+        file you wish to download.
+
+    filenames
+        The name of the files in the record. Must match exactly.
+        If you are not sure of the filenames in the record,
+        they are the keys of the dictionary returned by
+        :func:`get_files_from_record`. If omitted, all files
+        are downloaded.
+
+    max_redirects
+        If the record's link to the file content returns a
+        redirection to another location, this function will follow
+        that redirection. This parameter sets the maximum number of
+        hops that the function can take. Usually, only a single
+        redirection should be necessary (from the record to the file
+        provider), but the default allows for a few extra hops.
+
+    production
+        Whether to download from the production repository. If ``False``,
+        the test (development) instance is used instead.
+
+    authors
+        Whether to download from CaltechAUTHORS instead of CaltechDATA.
+    """
+    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)
+    if filenames is None:
+        filenames = sorted(files.keys())
+
+    for filename in filenames:
+        output_file = os.path.join(output_path, filename)
+        if filename not in files:
+            raise KeyError(f'File "{filename}" not found in record {record_id}')
+
+        entry = files[filename]
+        if "links" not in entry or "content" not in entry["links"]:
+            raise NotImplementedError(
+                f'Metadata for file "{filename}" in record {record_id} is '
+                "missing the content link"
+            )
+
+        content_url = entry["links"]["content"]
+        download_content(content_url, output_file, max_redirects=max_redirects)
+
+
+def download_content(content_url: str, fname: os.PathLike, max_redirects=5):
+    """Download the contents of a file.
+
+    Parameters
+    ----------
+    content_url
+        The URL pointing to the contents of the file. In the dictionary
+        returned by :func:`get_files_from_record` (call it ``D``), this
+        is usually the value at ``D[FILENAME]["links"]["content"]``.
+
+    fname
+        The path to which to save the file contents. Will be overwritten!
+
+
+    max_redirects
+        If the ``content_url`` returns a redirection to another location,
+        this function will follow that redirection. This parameter sets
+        the maximum number of hops that the function can take. Usually,
+        only a single redirection should be necessary (from the record to
+        the file provider), but the default allows for a few extra hops.
+    """
+    url = content_url
+    # If max_redirects == 0, then this loop will never run. Since the
+    # likely expected behavior for ``max_redirects = 0`` is to only
+    # look at the link directly given back by the record, we add 1
+    # for the loop to ensure it runs once in that case.
+    for _ in range(max_redirects + 1):
+        with requests.get(url, stream=True) as r:
+            r.raise_for_status()
+            if "Location" in r.headers:
+                # Redirection - follow to the next URL
+                url = r.headers["Location"]
+            else:
+                with open(fname, "wb") as f:
+                    content_length = r.headers.get("content-length", None)
+                    if content_length is not None:
+                        content_length = int(content_length)
+                    pbar = tqdm(total=content_length // 1024, unit="kB")
+                    for chunk in r.iter_content(chunk_size=1024):
+                        if chunk:
+                            pbar.update()
+                            f.write(chunk)
+                    print(f"Download to {fname} complete.")
+                    return
+    raise RuntimeError(f"Exceeded maximum number of redirects ({max_redirects})")
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(
+        description="download_from_record downloads the files attached to a "
+        "CaltechDATA or CaltechAUTHORS record"
+    )
+    parser.add_argument(
+        "record_id", help="The record ID for the record to download files from"
+    )
+    parser.add_argument(
+        "filenames",
+        nargs="*",
+        default=None,
+        help="The names of the files to download. If omitted, all files in "
+        "the record are downloaded.",
+    )
+    parser.add_argument(
+        "-output_path",
+        default=".",
+        help="Existing directory to download the files into",
+    )
+    parser.add_argument(
+        "-max_redirects",
+        type=int,
+        default=5,
+        help="Maximum number of redirects to follow per file",
+    )
+    parser.add_argument("-test", dest="production", action="store_false")
+    parser.add_argument("-authors", dest="authors", action="store_true")
+
+    args = parser.parse_args()
+
+    download_files_from_record(
+        args.record_id,
+        args.output_path,
+        filenames=args.filenames or None,
+        max_redirects=args.max_redirects,
+        production=args.production,
+        authors=args.authors,
+    )

{caltechdata_api-2.0.0 → caltechdata_api-2.2.0}/caltechdata_api.egg-info/PKG-INFO

@@ -1,20 +1,25 @@
 Metadata-Version: 2.4
 Name: caltechdata_api
-Version: 2.0.0
+Version: 2.2.0
 Summary: Python wrapper for CaltechDATA API.
-Home-page: https://github.com/caltechlibrary/caltechdata_api
-Author: Thomas E Morrell, Rohan Bhattarai, Elizabeth Won, Alexander A Abakah, Kshemaahna Nagi
-Author-email: tmorrell@caltech.edu, aabakah@caltech.edu, knagi@caltech.edu
-License: MIT
-Classifier: License :: OSI Approved :: MIT License
+Author: Rohan Bhattarai, Elizabeth Won
+Author-email: Thomas E Morrell <tmorrell@caltech.edu>, Alexander A Abakah <aabakah@caltech.edu>, Kshemaahna Nagi <knagi@caltech.edu>
+Maintainer-email: Thomas E Morrell <tmorrell@caltech.edu>
+License-Expression: BSD-3-Clause
+Project-URL: Homepage, https://github.com/caltechlibrary/caltechdata_api
+Project-URL: Repository, https://github.com/caltechlibrary/caltechdata_api
+Project-URL: Issues, https://github.com/caltechlibrary/caltechdata_api/issues
+Keywords: metadata,software,InvenioRDM
 Classifier: Programming Language :: Python :: 3
-Classifier: Programming Language :: Python :: 3.7
-Classifier: Programming Language :: Python :: 3.8
 Classifier: Programming Language :: Python :: 3.9
 Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Programming Language :: Python :: 3.14
 Classifier: Programming Language :: Python :: Implementation :: CPython
 Classifier: Operating System :: OS Independent
-Requires-Python: >=3.6.0
+Requires-Python: >=3.9
 Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: requests
@@ -44,7 +49,7 @@ The `caltechdata_api` Python library provides a convenient interface for interac
 
 ## Requirements
 
-- Python 3.6+
+- Python 3.9+
 
 ## Installation
 
@@ -54,6 +59,18 @@ Install the library via pip:
 pip install caltechdata_api
 ```
 
+Or add it to a [uv](https://docs.astral.sh/uv/) project:
+
+```shell
+uv add caltechdata_api
+```
+
+You can also run a script using uv:
+
+```shell
+uv run write.py
+```
+
 ## Examples
 
 There are some example python scripts in the GitHub repository.
@@ -61,7 +78,7 @@ There are some example python scripts in the GitHub repository.
 ### Create a record:
 
 ```shell
-python write.py example.json -fnames logo.gif
+uv run write.py example.json -fnames logo.gif
 # Output: pbkn6-m9y63 (unique identifier)
 ```
 > The response will be the unique identifier for the record. You can put this at
@@ -71,7 +88,7 @@ https://data.caltechlibrary.dev/records/pbkn6-m9y63)
 ### Edit a record 
 Make changes to the example.json file to see a change)
 ```
-python edit.py example.json -id pbkn6-m9y63
+uv run edit.py example.json -id pbkn6-m9y63
 10.33569/pbkn6-m9y63
 ```
 > The response is the DOI for the record, which includes the unique identifier
@@ -82,13 +99,13 @@ Some groups have worked with the library to create custom DOIs. These can be
 passed in the metadata like:
 
 ```shell
-python write.py example_custom.json -fnames logo.gif
+uv run write.py example_custom.json -fnames logo.gif
 m6zxz-p4j22
 ```
 
 And then you can edit with
 ```
-python edit.py example_custom.json -id m6zxz-p4j22
+uv run edit.py example_custom.json -id m6zxz-p4j22
 10.5281/inveniordm.1234
 ```
 

{caltechdata_api-2.0.0 → caltechdata_api-2.2.0}/caltechdata_api.egg-info/SOURCES.txt

@@ -1,15 +1,13 @@
 LICENSE
 README.md
 pyproject.toml
-setup.cfg
-setup.py
 caltechdata_api/__init__.py
 caltechdata_api/caltechdata_edit.py
 caltechdata_api/caltechdata_write.py
 caltechdata_api/cli.py
 caltechdata_api/customize_schema.py
 caltechdata_api/download_file.py
-caltechdata_api/get_files.py
+caltechdata_api/download_from_record.py
 caltechdata_api/get_metadata.py
 caltechdata_api/md_to_json.py
 caltechdata_api/utils.py

caltechdata_api-2.2.0/pyproject.toml

@@ -0,0 +1,69 @@
+[build-system]
+requires = ["setuptools>=77.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "caltechdata_api"
+version = "2.2.0"
+description = "Python wrapper for CaltechDATA API."
+readme = "README.md"
+requires-python = ">=3.9"
+license = "BSD-3-Clause"
+license-files = ["LICENSE"]
+authors = [
+    {name = "Thomas E Morrell", email = "tmorrell@caltech.edu"},
+    {name = "Rohan Bhattarai"},
+    {name = "Elizabeth Won"},
+    {name = "Alexander A Abakah", email = "aabakah@caltech.edu"},
+    {name = "Kshemaahna Nagi", email = "knagi@caltech.edu"},
+]
+maintainers = [
+    {name = "Thomas E Morrell", email = "tmorrell@caltech.edu"},
+]
+keywords = ["metadata", "software", "InvenioRDM"]
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Programming Language :: Python :: 3.13",
+    "Programming Language :: Python :: 3.14",
+    "Programming Language :: Python :: Implementation :: CPython",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+    "requests",
+    "datacite>1.1.0",
+    "tqdm>=4.62.3",
+    "pyyaml",
+    "s3fs",
+    "cryptography",
+    "s3cmd",
+    "jsonschema-specifications",
+]
+
+[project.urls]
+Homepage = "https://github.com/caltechlibrary/caltechdata_api"
+Repository = "https://github.com/caltechlibrary/caltechdata_api"
+Issues = "https://github.com/caltechlibrary/caltechdata_api/issues"
+
+[project.scripts]
+caltechdata_api = "caltechdata_api.cli:main"
+
+[dependency-groups]
+dev = [
+    "pytest>=7.0",
+    "black",
+]
+
+[tool.setuptools.packages.find]
+include = ["caltechdata_api*"]
+
+[tool.setuptools.package-data]
+caltechdata_api = ["vocabularies.yaml", "vocabularies/*"]
+
+[tool.pytest.ini_options]
+addopts = "--verbose"
+testpaths = ["tests"]
+pythonpath = ["tests"]

caltechdata_api-2.2.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

{caltechdata_api-2.0.0 → caltechdata_api-2.2.0}/tests/test_rdm.py

@@ -7,6 +7,10 @@ from caltechdata_api import (
 import json
 import os
 
+# Any file will do here, we just need something to attach to the test records
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+UPLOAD_FILE = os.path.join(BASE_DIR, "helpers.py")
+
 
 def test_datacite_rdm_conversion(full_datacite43_record, full_rdm_record):
 
@@ -48,7 +52,7 @@ def test_datacite_rdm_create_edit(full_datacite43_record):
         full_datacite43_record,
         schema="43",
         production=False,
-        files=["helpers.py"],
+        files=[UPLOAD_FILE],
         publish=True,
         token=env_token,
     )
@@ -77,7 +81,7 @@ def test_datacite_rdm_create_edit(full_datacite43_record):
     new_doi = caltechdata_edit(
         recid,
         full_datacite43_record,
-        files=["helpers.py"],
+        files=[UPLOAD_FILE],
         schema="43",
         production=False,
         publish=True,

caltechdata_api-2.2.0/tests/test_unit.py

@@ -0,0 +1,76 @@
+import os
+import pytest
+import logging
+from caltechdata_api import validate_metadata as validator43
+from helpers import load_json_path
+
+# Configure logging
+logging.basicConfig(level=logging.DEBUG)
+logger = logging.getLogger(__name__)
+
+# Dynamically determine the base path
+BASE_DIR = os.path.dirname(os.path.abspath(__file__))
+INVALID_DATACITE43_DIR = os.path.join(BASE_DIR, "data", "invalid_datacite43")
+
+
+# Function to get all JSON files in the directory
+def get_all_json_files(directory):
+    return [
+        os.path.join(directory, f) for f in os.listdir(directory) if f.endswith(".json")
+    ]
+
+
+# Get list of all valid and invalid JSON files
+VALID_DATACITE43_FILES = get_all_json_files(
+    os.path.join(BASE_DIR, "data", "datacite43")
+)
+INVALID_DATACITE43_FILES = get_all_json_files(INVALID_DATACITE43_DIR)
+
+
+@pytest.mark.parametrize("valid_file", VALID_DATACITE43_FILES)
+def test_valid_json(valid_file):
+    """Test that valid example files validate successfully."""
+    print(f"\nValidating file: {valid_file}")
+    json_data = load_json_path(valid_file)
+    validation_errors = None
+    try:
+        validation_errors = validator43(json_data)
+    except ValueError as e:
+        pytest.fail(f"Validation failed for: {valid_file}\nErrors: {str(e)}")
+
+    assert (
+        not validation_errors
+    ), f"Validation failed for: {valid_file}\nErrors: {validation_errors}"
+    print(f"Validation passed for: {valid_file}")
+
+
+@pytest.mark.parametrize("invalid_file", INVALID_DATACITE43_FILES)
+def test_invalid_json(invalid_file):
+    """Test that invalid example files do not validate successfully."""
+    logger.debug(f"Attempting to validate invalid file: {invalid_file}")
+
+    json_data = load_json_path(invalid_file)
+
+    def validate_wrapper():
+        try:
+            validation_errors = validator43(json_data)
+
+            logger.debug(f"Validation result for {invalid_file}: {validation_errors}")
+
+            if validation_errors:
+                logger.debug(f"Found validation errors in {invalid_file}")
+                return
+
+            logger.error(
+                f"No validation errors found for supposedly invalid file: {invalid_file}"
+            )
+            raise ValueError(
+                f"Validation did not fail for invalid file: {invalid_file}"
+            )
+
+        except Exception as e:
+            logger.error(f"Validation exception for {invalid_file}: {str(e)}")
+            raise
+
+    with pytest.raises((ValueError, KeyError, AssertionError, TypeError)):
+        validate_wrapper()

caltechdata_api-2.0.0/caltechdata_api/get_files.py

@@ -1,49 +0,0 @@
-import argparse
-import requests
-
-
-def get_files(idv, production=True):
-    # Returns file block
-
-    if production == True:
-        api_url = "https://data.caltech.edu/api/records/"
-    else:
-        api_url = "https://data.caltechlibrary.dev/api/records/"
-
-    r = requests.get(api_url + str(idv) + "/files")
-    r_data = r.json()
-    if "message" in r_data:
-        raise AssertionError(
-            "id "
-            + str(idv)
-            + " expected http status 200, got "
-            + str(r.status_code)
-            + " "
-            + r_data["message"]
-        )
-    if not "entries" in r_data:
-        raise AssertionError("expected as entries property in response, got " + r_data)
-    return r_data["entries"]
-
-
-if __name__ == "__main__":
-    parser = argparse.ArgumentParser(
-        description="get_files queries the caltechDATA (Invenio 3) API\
-    and returns file information"
-    )
-    parser.add_argument(
-        "ids",
-        metavar="ID",
-        type=str,
-        nargs="+",
-        help="The CaltechDATA ID for each record of interest",
-    )
-    parser.add_argument("-test", dest="production", action="store_false")
-
-    args = parser.parse_args()
-
-    production = args.production
-
-    for idv in args.ids:
-        metadata = get_files(idv, production)
-        print(metadata)

caltechdata_api-2.0.0/pyproject.toml

@@ -1,3 +0,0 @@
-[build-system]
-requires = ["setuptools>=61.0", "wheel"]
-build-backend = "setuptools.build_meta"

caltechdata_api-2.0.0/setup.cfg

@@ -1,55 +0,0 @@
-[build-system]
-requires = ["setuptools>=64.0","wheel"]
-build-backend = "setuptools.build_meta"
-
-[metadata]
-name = caltechdata_api
-version = 2.0.0
-author = Thomas E Morrell, Rohan Bhattarai, Elizabeth Won, Alexander A Abakah, Kshemaahna Nagi
-author_email = tmorrell@caltech.edu, aabakah@caltech.edu, knagi@caltech.edu
-description = Python wrapper for CaltechDATA API.
-long_description = file: README.md
-long_description_content_type = text/markdown
-url = https://github.com/caltechlibrary/caltechdata_api
-license = MIT
-classifiers = 
-	License :: OSI Approved :: MIT License
-	Programming Language :: Python :: 3
-	Programming Language :: Python :: 3.7
-	Programming Language :: Python :: 3.8
-	Programming Language :: Python :: 3.9
-	Programming Language :: Python :: 3.10
-	Programming Language :: Python :: Implementation :: CPython
-	Operating System :: OS Independent
-
-[options]
-packages = find:
-python_requires = >=3.6.0
-install_requires = 
-	requests
-	datacite>1.1.0
-	tqdm>=4.62.3
-	pyyaml
-	s3fs
-	cryptography
-	s3cmd
-	jsonschema-specifications
-include_package_data = True
-
-[options.packages.find]
-exclude = tests
-
-[options.package_data]
-caltechdata_api = vocabularies.yaml, vocabularies/*
-
-[options.entry_points]
-console_scripts = 
-	caltechdata_api=caltechdata_api.cli:main
-
-[tool:pytest]
-addopts = --verbose
-
-[egg_info]
-tag_build = 
-tag_date = 0
-

caltechdata_api-2.0.0/setup.py

@@ -1,3 +0,0 @@
-from setuptools import setup
-
-setup()

caltechdata_api-2.0.0/tests/test_unit.py

@@ -1,166 +0,0 @@
-import os
-import pytest
-import logging
-from caltechdata_api import validate_metadata as validator43
-from helpers import load_json_path
-
-# Configure logging
-logging.basicConfig(level=logging.DEBUG)
-logger = logging.getLogger(__name__)
-
-# Dynamically determine the base path
-BASE_DIR = os.path.dirname(os.path.abspath(__file__))
-INVALID_DATACITE43_DIR = os.path.join(BASE_DIR, "data", "invalid_datacite43")
-DATACITE43_DIR = os.path.join(BASE_DIR, "data")
-
-
-# Function to get all JSON files in the directory
-def get_all_json_files(directory):
-    return [
-        os.path.join(directory, f) for f in os.listdir(directory) if f.endswith(".json")
-    ]
-
-
-# Get list of all valid and invalid JSON files
-VALID_DATACITE43_FILES = get_all_json_files(
-    os.path.join(BASE_DIR, "data", "datacite43")
-)
-INVALID_DATACITE43_FILES = get_all_json_files(INVALID_DATACITE43_DIR)
-
-
-@pytest.mark.parametrize("valid_file", VALID_DATACITE43_FILES)
-def test_valid_json(valid_file):
-    """Test that valid example files validate successfully."""
-    print(f"\nValidating file: {valid_file}")
-    json_data = load_json_path(valid_file)
-    validation_errors = None
-    try:
-        validation_errors = validator43(json_data)
-    except ValueError as e:
-        pytest.fail(f"Validation failed for: {valid_file}\nErrors: {str(e)}")
-
-    assert (
-        not validation_errors
-    ), f"Validation failed for: {valid_file}\nErrors: {validation_errors}"
-    print(f"Validation passed for: {valid_file}")
-
-
-@pytest.mark.parametrize("invalid_file", INVALID_DATACITE43_FILES)
-def test_invalid_json(invalid_file):
-    """Test that invalid example files do not validate successfully."""
-    logger.debug(f"Attempting to validate invalid file: {invalid_file}")
-
-    json_data = load_json_path(invalid_file)
-
-    def validate_wrapper():
-        try:
-            validation_errors = validator43(json_data)
-
-            logger.debug(f"Validation result for {invalid_file}: {validation_errors}")
-
-            if validation_errors:
-                logger.debug(f"Found validation errors in {invalid_file}")
-                return
-
-            logger.error(
-                f"No validation errors found for supposedly invalid file: {invalid_file}"
-            )
-            raise ValueError(
-                f"Validation did not fail for invalid file: {invalid_file}"
-            )
-
-        except Exception as e:
-            logger.error(f"Validation exception for {invalid_file}: {str(e)}")
-            raise
-
-    with pytest.raises((ValueError, KeyError, AssertionError, TypeError)):
-        validate_wrapper()
-
-
-@pytest.mark.parametrize(
-    "missing_field_file",
-    [
-        {
-            "file": os.path.join(DATACITE43_DIR, "missing_creators.json"),
-            "missing_field": "creators",
-        },
-        {
-            "file": os.path.join(DATACITE43_DIR, "missing_titles.json"),
-            "missing_field": "titles",
-        },
-    ],
-)
-def test_missing_required_fields(missing_field_file):
-    """Test that JSON files missing required fields fail validation."""
-    print(
-        f"\nTesting missing field: {missing_field_file['missing_field']} in file: {missing_field_file['file']}"
-    )
-
-    # Skip the test if the file doesn't exist
-    if not os.path.exists(missing_field_file["file"]):
-        pytest.skip(f"Test file not found: {missing_field_file['file']}")
-
-    json_data = load_json_path(missing_field_file["file"])
-    with pytest.raises(
-        ValueError,
-        match=f"Missing required metadata field: {missing_field_file['missing_field']}",
-    ):
-        validator43(json_data)
-
-
-@pytest.mark.parametrize(
-    "type_error_file",
-    [
-        {
-            "file": os.path.join(DATACITE43_DIR, "type_error_creators.json"),
-            "field": "creators",
-        },
-        {
-            "file": os.path.join(DATACITE43_DIR, "type_error_dates.json"),
-            "field": "dates",
-        },
-    ],
-)
-def test_incorrect_field_types(type_error_file):
-    """Test that JSON files with incorrect field types fail validation."""
-    print(
-        f"\nTesting incorrect type in field: {type_error_file['field']} for file: {type_error_file['file']}"
-    )
-
-    # Skip the test if the file doesn't exist
-    if not os.path.exists(type_error_file["file"]):
-        pytest.skip(f"Test file not found: {type_error_file['file']}")
-
-    json_data = load_json_path(type_error_file["file"])
-    with pytest.raises(
-        ValueError, match=f"Incorrect type for field: {type_error_file['field']}"
-    ):
-        validator43(json_data)
-
-
-def test_multiple_errors():
-    """Test JSON file with multiple issues to check all errors are raised."""
-    multiple_errors_file = os.path.join(DATACITE43_DIR, "multiple_errors.json")
-
-    # Skip the test if the file doesn't exist
-    if not os.path.exists(multiple_errors_file):
-        pytest.skip(f"Test file not found: {multiple_errors_file}")
-
-    json_data = load_json_path(multiple_errors_file)
-    with pytest.raises(ValueError, match="Multiple validation errors"):
-        validator43(json_data)
-
-
-def test_error_logging(caplog):
-    """Test that errors are logged correctly during validation."""
-    some_invalid_file = os.path.join(INVALID_DATACITE43_DIR, "some_invalid_file.json")
-
-    # Skip the test if the file doesn't exist
-    if not os.path.exists(some_invalid_file):
-        pytest.skip(f"Test file not found: {some_invalid_file}")
-
-    json_data = load_json_path(some_invalid_file)
-    with caplog.at_level(logging.ERROR):
-        with pytest.raises(ValueError):
-            validator43(json_data)
-    assert "Validation failed" in caplog.text