jhpoelen
commented
4 months ago as seen in demo with @slint and @myrmoteras et al. at the Arcadia Sprint #1 at CERN on 12 March 2024 https://github.com/plazi/arcadia-project
Closed jhpoelen closed 4 months ago
jhpoelen
commented
4 months ago as seen in demo with @slint and @myrmoteras et al. at the Arcadia Sprint #1 at CERN on 12 March 2024 https://github.com/plazi/arcadia-project
jhpoelen
commented
4 months ago associated zenodo query was:
https://zenodo.org/api/records?q=files.entries.checksum:%22md5:58fd5af87a78f16c995c987ea4ab390e%22&allversions=1
with result:
{
"hits": {
"hits": [
{
"created": "2024-03-04T17:00:52.979185+00:00",
"modified": "2024-03-04T17:00:53.809349+00:00",
"id": 10778598,
"conceptrecid": "10778597",
"doi": "10.5281/zenodo.10778598",
"conceptdoi": "10.5281/zenodo.10778597",
"doi_url": "https://doi.org/10.5281/zenodo.10778598",
"metadata": {
"title": "Host selection behaviour of the parasitoid Leptopilina clavipes, in relation to survival in hosts.",
"doi": "10.5281/zenodo.10778598",
"publication_date": "1991",
"description": "Uploaded by Plazi for TaxoDros. We do not have abstracts.",
"access_right": "open",
"creators": [
{
"name": "Driessen, G.",
"affiliation": null
},
{
"name": "Hemerik, L.",
"affiliation": null
},
{
"name": "Boonstra, B.",
"affiliation": null
}
],
"keywords": [
"Biodiversity",
"Taxonomy",
"fruit flies",
"flies",
"Animalia",
"Arthropoda",
"Insecta",
"Diptera"
],
"related_identifiers": [
{
"identifier": "https://linker.bio/line:hash://md5/ff86b940567d278e50fa00672cf96629!/L45510-L45519",
"relation": "isDerivedFrom",
"scheme": "url"
},
{
"identifier": "10.5281/zenodo.10723540",
"relation": "isDerivedFrom",
"scheme": "doi"
},
{
"identifier": "https://www.taxodros.uzh.ch",
"relation": "isPartOf",
"scheme": "url"
}
],
"references": [
"Bächli, G. (2024). TaxoDros - The Database on Taxonomy of Drosophilidae hash://md5/26a67012dde325cf2a3a058cc2f9c1b8 hash://sha256/ca86d74b318a334bddbc7c6a387a09530a083b8617718f5369ad548744c602d3 [Data set]. Zenodo. https://doi.org/10.5281/zenodo.10723540"
],
"custom": {
"dwc:class": [
"Insecta"
],
"dwc:kingdom": [
"Animalia"
],
"dwc:order": [
"Diptera"
],
"dwc:phylum": [
"Arthropoda"
]
},
"resource_type": {
"title": "Journal article",
"type": "publication",
"subtype": "article"
},
"journal": {
"pages": "99-111",
"title": "Netherlands Journal of Zoology",
"volume": "41"
},
"alternate_identifiers": [
{
"identifier": "urn:lsid:taxodros.uzh.ch:id:driessen%20et%20al.%2C%201991"
},
{
"identifier": "hash://md5/58fd5af87a78f16c995c987ea4ab390e"
}
],
"license": {
"id": "cc-by-4.0"
},
"communities": [
{
"id": "biosyslit"
},
{
"id": "taxodros"
}
],
"relations": {
"version": [
{
"index": 0,
"is_last": true,
"parent": {
"pid_type": "recid",
"pid_value": "10778597"
}
}
]
}
},
"title": "Host selection behaviour of the parasitoid Leptopilina clavipes, in relation to survival in hosts.",
"links": {
"self": "https://zenodo.org/api/records/10778598",
"self_html": "https://zenodo.org/records/10778598",
"self_doi": "https://zenodo.org/doi/10.5281/zenodo.10778598",
"doi": "https://doi.org/10.5281/zenodo.10778598",
"parent": "https://zenodo.org/api/records/10778597",
"parent_html": "https://zenodo.org/records/10778597",
"parent_doi": "https://zenodo.org/doi/10.5281/zenodo.10778597",
"self_iiif_manifest": "https://zenodo.org/api/iiif/record:10778598/manifest",
"self_iiif_sequence": "https://zenodo.org/api/iiif/record:10778598/sequence/default",
"files": "https://zenodo.org/api/records/10778598/files",
"media_files": "https://zenodo.org/api/records/10778598/media-files",
"archive": "https://zenodo.org/api/records/10778598/files-archive",
"archive_media": "https://zenodo.org/api/records/10778598/media-files-archive",
"latest": "https://zenodo.org/api/records/10778598/versions/latest",
"latest_html": "https://zenodo.org/records/10778598/latest",
"draft": "https://zenodo.org/api/records/10778598/draft",
"versions": "https://zenodo.org/api/records/10778598/versions",
"access_links": "https://zenodo.org/api/records/10778598/access/links",
"access_users": "https://zenodo.org/api/records/10778598/access/users",
"access_request": "https://zenodo.org/api/records/10778598/access/request",
"access": "https://zenodo.org/api/records/10778598/access",
"reserve_doi": "https://zenodo.org/api/records/10778598/draft/pids/doi",
"communities": "https://zenodo.org/api/records/10778598/communities",
"communities-suggestions": "https://zenodo.org/api/records/10778598/communities-suggestions",
"requests": "https://zenodo.org/api/records/10778598/requests"
},
"updated": "2024-03-04T17:00:53.809349+00:00",
"recid": "10778598",
"revision": 5,
"files": [
{
"id": "b147e088-36a0-4ae3-96e5-ccf7139db5b9",
"key": "Driessen et al., 1991.pdf",
"size": 637155,
"checksum": "md5:58fd5af87a78f16c995c987ea4ab390e",
"links": {
"self": "https://zenodo.org/api/records/10778598/files/Driessen et al., 1991.pdf/content"
}
}
],
"owners": [
{
"id": 7292
}
],
"status": "published",
"stats": {
"downloads": 0,
"unique_downloads": 0,
"views": 0,
"unique_views": 0,
"version_downloads": 0,
"version_unique_downloads": 0,
"version_unique_views": 0,
"version_views": 0
},
"state": "done",
"submitted": true
}
],
"total": 1
},
"aggregations": {
"access_status": {
"buckets": [
{
"key": "open",
"doc_count": 1,
"label": "Open",
"is_selected": false
}
],
"label": "Access status"
},
"resource_type": {
"buckets": [
{
"key": "publication",
"doc_count": 1,
"label": "Publication",
"is_selected": false,
"inner": {
"buckets": [
{
"key": "publication-article",
"doc_count": 1,
"label": "Journal article",
"is_selected": false
}
]
}
}
],
"label": "Resource types"
},
"subject": {
"buckets": [
{
"key": "Animalia",
"doc_count": 1,
"label": "Animalia",
"is_selected": false
},
{
"key": "Arthropoda",
"doc_count": 1,
"label": "Arthropoda",
"is_selected": false
},
{
"key": "Biodiversity",
"doc_count": 1,
"label": "Biodiversity",
"is_selected": false
},
{
"key": "Diptera",
"doc_count": 1,
"label": "Diptera",
"is_selected": false
},
{
"key": "Insecta",
"doc_count": 1,
"label": "Insecta",
"is_selected": false
},
{
"key": "Taxonomy",
"doc_count": 1,
"label": "Taxonomy",
"is_selected": false
},
{
"key": "flies",
"doc_count": 1,
"label": "flies",
"is_selected": false
},
{
"key": "fruit flies",
"doc_count": 1,
"label": "fruit flies",
"is_selected": false
}
],
"label": "Subjects"
},
"file_type": {
"buckets": [
{
"key": "pdf",
"doc_count": 1,
"label": "PDF",
"is_selected": false
}
],
"label": "File type"
}
},
"links": {
"self": "https://zenodo.org/api/records?allversions=True&page=1&q=files.entries.checksum%3A%22md5%3A58fd5af87a78f16c995c987ea4ab390e%22&size=25&sort=bestmatch"
}
}note that the produced "self" link by zenodo is not a valid URI due to unescaped whitespaces .
"self": "https://zenodo.org/api/records/10778598/files/Driessen et al., 1991.pdf/content"After "manually" url encoding the self url in Preston code, the pdf was able to be retrieved:
preston cat --remote https://zenodo.org 'hash://md5/58fd5af87a78f16c995c987ea4ab390e' > document.pdf
[https://zenodo.org/api/r...0e%22&all_versions=true] 100.0% of 5 kB at 0.05 MB/s completed in < 1 minute
[https://zenodo.org/api/r....%2C%201991.pdf/content] 100.0% of 622 kB at 1.10 MB/s completed in < 1 minuteNote that "%20" encoding introduced by preston.
with verified matching md5 signatures
$ cat document.pdf | md5sum
58fd5af87a78f16c995c987ea4ab390e -as expected.
jhpoelen
commented
4 months ago after installing preston v0.8.4 on linker.bio, the expected pdf was loaded via:
https://linker.bio/hash://md5/58fd5af87a78f16c995c987ea4ab390e
produced an unexpected exception:
Caused by: java.net.URISyntaxException: Illegal character in path at index 54: https://zenodo.org/api/records/10778598/files/Driessen et al., 1991.pdf/content
expected that: