#!/bin/bash
#
# imports single github globi data repository and generates a review report if suitable for indexing by GloBI.
# If optional elton dataset dir is provided, no remote updates will be attempted.
#
# usage:
# check-dataset.sh [dataset namespace] [(optional) elton datasets dir]
#
# example:
# ./check-dataset.sh globalbioticinteractions/template-dataset
# ./check-dataset.sh globalbioticinteractions/template-dataset /var/cache/elton/datasets
#
# namespaces without urn:lsid: prefixes are assumed to be github repository org/name combinations (e.g., globalbioticinteractions/template-dataset)
#
set -x
export REVIEW_SCRIPT=$(readlink -f "$0")
export DATASET_NAMESPACE=$1
export ELTON_UPDATE_DISABLED=$2
export ELTON_DATASETS_DIR=${2:-$PWD/datasets}
export ELTON_VERSION=0.16.11
export ELTON_DATA_REPO_MAIN="https://raw.githubusercontent.com/${DATASET_NAMESPACE}/main"
export ELTON_JAR="$PWD/elton.jar"
export ELTON_OPTS=""
export NAME_PARSER="gbif-parse"
export HASH_ALGO="md5"
export PRESTON_VERSION=0.10.5
export PRESTON_JAR="$PWD/preston.jar"
export PRESTON_OPTS=" --algo ${HASH_ALGO}"
export PRESTON_DATA_DIR="$PWD/data/"
export GLOBINIZER_VERSION=0.4.0
export NOMER_VERSION=0.6.7
export NOMER_JAR="$PWD/nomer.jar"
export NOMER_REPLACE_PROPERTIES="$(mktemp)"
export NOMER_APPEND_PROPERTIES="$(mktemp)"
export NOMER_CACHE_DIR="${NOMER_CACHE_DIR:-$PWD/.cache/nomer}"
export NOMER_OPTS=""
export NETWORK_COMPILER_SCRIPT="$(echo "$REVIEW_SCRIPT" | sed -E 's+/[^/]{1,}$++g')/compile-network.sh"
export NETWORK_COMPILER_PRESENT=""
export NETWORK_CATALOG="col"
export NETWORK_CATALOG_DESCRIPTION="Catalogue of Life"
export REVIEW_REPO_HOST="blob.globalbioticinteractions.org"
export README=$(mktemp)
export REVIEW_DIR="${PWD}/review/${DATASET_NAMESPACE}"
export MLR_TSV_OPTS="--csvlite --fs tab"
export MLR_TSV_INPUT_OPTS="--icsvlite --ifs tab"
export MLR_TSV_OUTPUT_OPTS="--ocsvlite --ofs tab"
export MLR_TSV_OPTS="${MLR_TSV_INPUT_OPTS} ${MLR_TSV_OUTPUT_OPTS}"
export TAXONOMIES="col ncbi discoverlife gbif itis wfo mdd pbdb worms wikidata"
function echo_logo {
echo "$(cat <<_EOF_
_____ _ ____ _____ _____ _
/ ____| | | _ \_ _| | __ \ (_)
| | __| | ___ | |_) || | | |__) |_____ ___ _____ __
| | |_ | |/ _ \| _ < | | | _ // _ \ \ / / |/ _ \ \ /\ / /
| |__| | | (_) | |_) || |_ | | \ \ __/\ V /| | __/\ V V /
\_____|_|\___/|____/_____| |_| \_\___| \_/ |_|\___| \_/\_/
| | | ____| | |
| |__ _ _ | |__ | | |_ ___ _ __
| '_ \| | | | | __| | | __/ _ \| '_ \
| |_) | |_| | | |____| | || (_) | | | |
|_.__/ \__, | |______|_|\__\___/|_| |_|
__/ |
|___/
⚠️ Disclaimer: The results in this review should be considered
friendly, yet naive, notes from an unsophisticated robot.
Please carefully review the results listed below and share issues/ideas
by email info at globalbioticinteractions.org or by opening an issue at
https://github.com/globalbioticinteractions/globalbioticinteractions/issues .
_EOF_
)"
}
function echo_nomer_schema_replace {
# ignore authorship for now
echo "$(cat <<_EOF_
nomer.cache.dir=${NOMER_CACHE_DIR}
nomer.schema.input=[{"column":0,"type":"externalId"},{"column": 1,"type":"name"}]
nomer.schema.output=[{"column":0,"type":"externalId"},{"column": 1,"type":"name"}]
_EOF_
)"
}
function echo_nomer_schema_append {
# ignore authorship and path matching for now
echo "$(cat <<_EOF_
nomer.cache.dir=${NOMER_CACHE_DIR}
nomer.schema.input=[{"column":0,"type":"externalId"},{"column": 1,"type":"name"},{"column": 4,"type":"disable_path"}]
_EOF_
)"
}
function version_of {
head -n1\
| grep -o -E "([0-9]+[.]{0,1})+"\
| head -n1
}
function echo_review_badge {
local number_of_review_notes=$1
if [ ${number_of_review_notes} -gt 0 ]
then
echo "$(cat <<_EOF_
_EOF_
)"
else
echo "$(cat <<_EOF_
_EOF_
)"
fi
}
function generate_geopackage {
cat << _EOF_
SET extension_directory = '.duckdb/ext/';
INSTALL spatial;
LOAD spatial;
INSTALL h3 FROM community;
LOAD h3;
COPY (
SELECT
ST_GeomFromText(h3_cell_to_boundary_wkt(h3_cell)) as cell_boundary,
log_number_of_records
FROM (
SELECT
h3_latlng_to_cell(CAST(decimalLatitude AS DOUBLE),CAST(decimalLongitude AS DOUBLE),2) as h3_cell,
LOG(1+COUNT(*)) as log_number_of_records
FROM
'indexed-interactions.parquet'
WHERE
h3_cell IS NOT NULL
GROUP BY
h3_cell
)
WHERE ST_XMax(cell_boundary) - ST_XMin(cell_boundary) < 90
)
TO 'indexed-interactions-h3.gpkg'
WITH (FORMAT gdal, DRIVER 'GPKG', SRS 'EPSG:4326');
COPY (
SELECT
ST_POINT(CAST(decimalLongitude AS DOUBLE),CAST(decimalLatitude AS DOUBLE)) as point,
sourceTaxonName,
interactionTypeName,
targetTaxonName,
"http://rs.tdwg.org/dwc/terms/eventDate" as eventDate,
referenceCitation,
citation,
namespace,
lastSeenAt
FROM
'indexed-interactions.parquet'
WHERE
ST_IsValid(point)
)
TO 'indexed-interactions.gpkg'
WITH (FORMAT gdal, DRIVER 'GPKG', SRS 'EPSG:4326');
COPY (
SELECT *
FROM 'indexed-interactions.gpkg'
)
TO 'indexed-interactions.fgb'
WITH (FORMAT gdal, DRIVER 'FlatGeobuf', SRS 'EPSG:4326');
_EOF_
}
function generate_mapserver {
cat << _EOF_
MAP
SIZE 1600 800
EXTENT -180 -90 180 90
PROJECTION
"init=epsg:4326"
END
LAYER # MODIS WMS map from NASA
NAME "modis_nasa"
TYPE RASTER
OFFSITE 0 0 0
STATUS ON
CONNECTIONTYPE WMS
CONNECTION "https://gibs.earthdata.nasa.gov/wms/epsg4326/best/wms.cgi?"
METADATA
"wms_srs" "EPSG:4326"
"wms_name" "OSM_Land_Water_Map"
"wms_server_version" "1.1.1"
"wms_format" "image/jpeg"
END
CLASS
STYLE
COLOR 232 232 232
OUTLINECOLOR 32 32 32
END
END
END
LAYER
NAME "indexed-interactions"
TYPE POLYGON
STATUS ON
CONNECTIONTYPE OGR
CONNECTION "indexed-interactions-h3.gpkg"
DATA "indexed-interactions-h3"
CLASS
STYLE
COLORRANGE 253.0 231.0 37.0 32.0 164.0 134.0
DATARANGE $(duckdb -csv -c "SET extension_directory = '.duckdb/ext/'; INSTALL spatial; LOAD spatial; SELECT MIN(log_number_of_records), MAX(log_number_of_records) FROM 'indexed-interactions-h3.gpkg';" | tail -n+2 | tr ',' ' ')
RANGEITEM "log_number_of_records"
OUTLINECOLOR 0 0 0
END
END
END
END
_EOF_
}
function echo_reproduce {
echo -e "\n\nIf you'd like, you can generate your own review notes by:"
echo " - installing GloBI's Elton via https://github.com/globalbioticinteractions/elton"
echo " - running \"elton update $DATASET_NAMESPACE && elton review --type note --type summary $DATASET_NAMESPACE > review.tsv\""
echo " - inspecting review.tsv"
echo -e "\nPlease email info@globalbioticinteractions.org for questions/ comments."
}
function generate_process_diagram {
cat << _EOF_
digraph review {
origin [label="dataset origin"];
elton [label="Elton (a naive review bot)"];
elton -> origin [label="pull (1)"];
interactions [label="indexed interactions"];
elton -> interactions [label="generates (2)"];
alignment [label="name alignments"];
nomer [label="Nomer (a naive review bot)"];
catalog [label="name catalog"];
nomer -> interactions [label="extract names (3)"];
nomer -> catalog [label="uses (4)"];
nomer -> alignment [label="generates (5)"];
}
_EOF_
}
function generate_model_diagram {
cat << _EOF_
digraph model {
primaryTaxon [label="Primary Taxon"];
associatedTaxon [label="Associated Taxon"];
{
rank=same;
primaryOrganism [label="Primary Organism"];
associatedOrganism [label="Associated Organism"];
primaryOrganism -> associatedOrganism [label="interactsWith"];
}
primaryOrganism -> primaryTaxon [label="classifiedAs"];
associatedOrganism -> associatedTaxon [label="classifiedAs"];
}
_EOF_
}
function generate_bibliography {
cat << _EOF_
@article{Poelen_2014,
doi = {10.1016/j.ecoinf.2014.08.005},
url = {https://doi.org/10.1016%2Fj.ecoinf.2014.08.005},
year = 2014,
month = {nov},
publisher = {Elsevier {BV}},
volume = {24},
pages = {148--159},
author = {Jorrit H. Poelen and James D. Simons and Chris J. Mungall},
title = {Global biotic interactions: An open infrastructure to share and analyze species-interaction datasets},
journal = {Ecological Informatics}}
@article{Wilkinson_2016,
doi = {10.1038/sdata.2016.18},
url = {https://doi.org/10.1038%2Fsdata.2016.18},
year = 2016,
month = {mar},
publisher = {Springer Science and Business Media {LLC}},
volume = {3},
number = {1},
author = {Mark D. Wilkinson and Michel Dumontier and IJsbrand Jan Aalbersberg and Gabrielle Appleton and Myles Axton and Arie Baak and Niklas Blomberg and Jan-Willem Boiten and Luiz Bonino da Silva Santos and Philip E. Bourne and Jildau Bouwman and Anthony J. Brookes and Tim Clark and Merc{\`{e}} Crosas and Ingrid Dillo and Olivier Dumon and Scott Edmunds and Chris T. Evelo and Richard Finkers and Alejandra Gonzalez-Beltran and Alasdair J.G. Gray and Paul Groth and Carole Goble and Jeffrey S. Grethe and Jaap Heringa and Peter A.C 't Hoen and Rob Hooft and Tobias Kuhn and Ruben Kok and Joost Kok and Scott J. Lusher and Maryann E. Martone and Albert Mons and Abel L. Packer and Bengt Persson and Philippe Rocca-Serra and Marco Roos and Rene van Schaik and Susanna-Assunta Sansone and Erik Schultes and Thierry Sengstag and Ted Slater and George Strawn and Morris A. Swertz and Mark Thompson and Johan van der Lei and Erik van Mulligen and Jan Velterop and Andra Waagmeester and Peter Wittenburg and Katherine Wolstencroft and Jun Zhao and Barend Mons},
title = {The {FAIR} Guiding Principles for scientific data management and stewardship},
journal = {Scientific Data}
}
@misc{trekels_maarten_2023_8176978,
author = {Trekels, Maarten and
Pignatari Drucker, Debora and
Salim, José Augusto and
Ollerton, Jeff and
Poelen, Jorrit and
Miranda Soares, Filipi and
Rünzel, Max and
Kasina, Muo and
Groom, Quentin and
Devoto, Mariano},
title = {{WorldFAIR Project (D10.1) Agriculture-related
pollinator data standards use cases report}},
month = jul,
year = 2023,
publisher = {Zenodo},
version = 1,
doi = {10.5281/zenodo.8176978},
url = {https://doi.org/10.5281/zenodo.8176978}
}
@misc{ICZN_1999,
author = {ICZN},
title = {International Code of Zoological Nomenclature},
year = 1999,
publisher = {The International Trust for Zoological Nomenclature, London, UK.},
version = {Fourth Edition},
isbn = {0853010064},
url = {https://www.iczn.org/the-code/the-code-online/}
}
@software{Preston,
author = {Michael Elliott and
Jorrit Poelen and
Icaro Alzuru and
Emilio Berti and
partha04patel},
title = {bio-guoda/preston: 0.10.5},
month = jan,
year = 2025,
publisher = {Zenodo},
version = {0.10.5},
doi = {10.5281/zenodo.14662206},
url = {https://doi.org/10.5281/zenodo.14662206},
}
@software{Nomer,
author = {José Augusto Salim and
Jorrit Poelen},
title = {globalbioticinteractions/nomer: 0.5.15},
month = feb,
year = 2025,
publisher = {Zenodo},
version = {0.5.15},
doi = {10.5281/zenodo.14893840},
url = {https://doi.org/10.5281/zenodo.14893840},
swhid = {swh:1:dir:521e44bf3950da369f4a2d7320e1ef108fa7a5f9
;origin=https://doi.org/10.5281/zenodo.1145474;vis
it=swh:1:snp:cce707ad24abf51bac5504eb6eb8be7d774af
34f;anchor=swh:1:rel:5a29f84e40efcdfbbb76ae119af59
cb5ec6a8c7d;path=globalbioticinteractions-
nomer-a430fb0
},
}
@software{Elton,
author = {Tobias Kuhn and
Jorrit Poelen and
Katrin Leinweber},
title = {globalbioticinteractions/elton: 0.15.1},
month = feb,
year = 2025,
publisher = {Zenodo},
version = {0.15.1},
doi = {10.5281/zenodo.14927734},
url = {https://doi.org/10.5281/zenodo.14927734},
swhid = {swh:1:dir:2dfac02f031fe77f75189bdc9b0318ebf2f1fc96
;origin=https://doi.org/10.5281/zenodo.998263;visi
t=swh:1:snp:b4c744faa133fc25e44c287102e8690b7e7b6a
b0;anchor=swh:1:rel:65fdfa5fed21a599250c2bf3740332
9048e7443c;path=globalbioticinteractions-
elton-6a3ed51
},
}
@software{globinizer,
author = {Jorrit Poelen and
Katja Seltmann and
Daniel Mietchen},
title = {globalbioticinteractions/globinizer: 0.4.0},
month = feb,
year = 2024,
publisher = {Zenodo},
version = {0.4.5},
doi = {10.5281/zenodo.10647565},
url = {https://doi.org/10.5281/zenodo.10647565},
}
@dataset{NomerCorpus,
author = {Poelen, Jorrit H. (ed.)},
title = {Nomer Corpus of Taxonomic Resources hash://sha256/
b60c0d25a16ae77b24305782017b1a270b79b5d1746f832650
f2027ba536e276
hash://md5/17f1363a277ee0e4ecaf1b91c665e47e
},
month = jul,
year = 2024,
publisher = {Zenodo},
version = {0.27},
doi = {10.5281/zenodo.12695629},
url = {https://doi.org/10.5281/zenodo.12695629},
}
@InProceedings{Nanopub,
author="Kuhn, Tobias
and Dumontier, Michel",
editor="Presutti, Valentina
and d'Amato, Claudia
and Gandon, Fabien
and d'Aquin, Mathieu
and Staab, Steffen
and Tordai, Anna",
title="Trusty URIs: Verifiable, Immutable, and Permanent Digital Artifacts for Linked Data",
booktitle="The Semantic Web: Trends and Challenges",
year="2014",
publisher="Springer International Publishing",
address="Cham",
pages="395--410",
abstract="To make digital resources on the web verifiable, immutable, and permanent, we propose a technique to include cryptographic hash values in URIs. We call them trusty URIs and we show how they can be used for approaches like nanopublications to make not only specific resources but their entire reference trees verifiable. Digital artifacts can be identified not only on the byte level but on more abstract levels such as RDF graphs, which means that resources keep their hash values even when presented in a different format. Our approach sticks to the core principles of the web, namely openness and decentralized architecture, is fully compatible with existing standards and protocols, and can therefore be used right away. Evaluation of our reference implementations shows that these desired properties are indeed accomplished by our approach, and that it remains practical even for very large files.",
isbn="978-3-319-07443-6"
}
@software{mckenna_2025_17807263,
author = {McKenna, Jeff and
Lime, Steve and
Bonfort, Thomas and
Boué, Jérome and
Butler, Howard and
Girvin, Seth and
Kralidis, Tom and
Meissl, Stephan and
Morissette, Daniel and
Nacionales, Perry and
Rahkonen, Jukka and
Rouault, Even and
Smith, Mike and
Szekeres, Tamas},
title = {MapServer},
month = dec,
year = 2025,
publisher = {Zenodo},
version = {rel-8-6-0},
doi = {10.5281/zenodo.17807263},
url = {https://doi.org/10.5281/zenodo.17807263},
swhid = {swh:1:dir:66095259779ef8d39cc98da2bf3cc3f761fbfc69
;origin=https://doi.org/10.5281/zenodo.6994443;vis
it=swh:1:snp:0fd98a760178a7ca1c736fd8d70306c5defd3
e36;anchor=swh:1:rel:4458c2c9310f343b348ca2b7ba54f
c71116bc92b;path=MapServer-MapServer-42e41f8
},
}
_EOF_
}
function get_eml {
find "${PRESTON_DATA_DIR}" -type f\
| grep -E "[a-f0-9]{64}$"\
| awk '{ print "-p " $1 " eml.xml" }'\
| xargs -L1 unzip\
| xmllint -
}
function generate_title {
eml="$(get_eml)"
if [[ $? -eq 0 ]]
then
collectionName=$(echo "${eml}" | xmllint --xpath '//collectionName' - | head -n1)
echo "Versioned Darwin Core Archive Shared by ${collectionName}, Including a Review of Biotic Interactions and Taxon Names ${DATASET_VERSION}"
else
echo "Versioned Archive and Review of Biotic Interactions and Taxon Names Found within ${DATASET_NAMESPACE} ${DATASET_VERSION}"
fi
}
function generate_dataset_section {
eml="$(get_eml)"
if [[ $? -eq 0 ]]
then
datasetInfoUrl=$(echo "${eml}" | xmllint --xpath '//alternateIdentifier/text()' - | head -n1)
collectionName=$(echo "${eml}" | xmllint --xpath '//collectionName' - | head -n1)
licenseUrl=$(echo "${eml}" | xmllint --xpath '//intellectualRights/text()' - | head -n1)
cat <<_EOF_
## Dataset
![logo of ${collectionName}]($(echo "${eml}" | xmllint --xpath '//resourceLogoUrl/text()' - | head -n1))
$(echo "${eml}" | xmllint --xpath '//dataset/abstract//text()' -)
The dataset darwin core archive was published on $(echo "${eml}" | xmllint --xpath '//pubDate/text()' -) and provided by $(echo "${eml}" | xmllint --xpath '//organizationName/text()' -). This dataset is published under a ${licenseUrl} license.
**For more information**, see [${datasetInfoUrl}](${datasetInfoUrl}).
_EOF_
fi
}
function generate_dataset_citation {
cat <<_EOF_
$(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} cut -f citation,archiveURI,lastSeenAt | tail -n+2 | sort | uniq | tr '\t' ' ') ${DATASET_VERSION}
_EOF_
}
function pluralize {
numberToPluralize=$(echo $1 | sed 's/[^0-9]//g')
if [ ${numberToPluralize} -gt 1 ]
then
echo -e s
fi
}
function pluralize_taxon {
numberToPluralize=$(echo $1 | sed 's/[^0-9]//g')
if [ ${numberToPluralize} -gt 1 ]
then
echo -e taxa
else
echo -e taxon
fi
}
function generate_zenodo_deposit_metadata {
local report_md="${1}"
cat <<_EOF_
{
"metadata": {
"related_identifiers": [
{
"relation": "isAlternateIdentifier",
"identifier": "${DATASET_VERSION}"
},
{
"relation": "isAlternateIdentifier",
"identifier": "${DATASET_ID}"
},
{
"relation": "hasVersion",
"identifier": "${DATASET_VERSION}"
},
{
"relation": "isCompiledBy",
"identifier": "10.5281/zenodo.14927734",
"resource_type": "software"
},
{
"relation": "isCompiledBy",
"identifier": "10.5281/zenodo.14893840",
"resource_type": "software"
},
{
"relation": "isCompiledBy",
"identifier": "10.5281/zenodo.14662206",
"resource_type": "software"
}
],
"communities": [
{
"identifier": "globi-review"
}
],
"upload_type": "publication",
"creators": [
{
"name": "Elton"
},
{
"name": "Nomer"
},
{
"name": "Preston"
}
],
"publication_type": "datapaper",
"title": $(cat ${report_md} | yq -o json --front-matter=extract .title),
"publication_date": "$(cat ${report_md} | yq --front-matter=extract .date)",
"keywords": $(cat ${report_md} | yq -o json --front-matter=extract .keywords),
"description": $(cat ${report_md} | yq -o json --front-matter=extract .abstract),
"additional_descriptions": [{
"type": { "id": "technical-info" },
"description": $(cat ${report_md} | pandoc --citeproc - | jq -s -R . | sed -E 's/href=\\"([^.\":]+[.][a-z][^\":]+|HEAD)\\"/href=\\"\{\{ ZENODO_DEPOSIT_ID \}\}\/files\/\1?download=1\\"/g')
}],
"references":
$(generate_dataset_citation | jq -s -R '. | split("\n") | map(select(length > 0))')
}
}
_EOF_
}
function generate_md_report {
headCount=21
headCountWithoutHeader=20
numberOfInteractions="$(printf "%'d" $(cat indexed-interactions.tsv.gz | gunzip | tail -n+2 | wc -l))"
numberOfInteractionTypes="$(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} cut -f interactionTypeName | tail -n+2 | sort | uniq | wc -l)"
mostFrequentInteractionTypes="$(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} count-distinct -f interactionTypeName then sort -nr count then cut -f interactionTypeName | tail -n+2 | head -n1 | tr -d '\n')"
uniqueSourceTaxa="$(printf "%'d" $(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} cut -f sourceTaxonName | tail -n+2 | sort | uniq | wc -l))"
mostFrequentSourceTaxa="$(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} count-distinct -f sourceTaxonName then sort -nr count then cut -f sourceTaxonName | tail -n+2 | head -n1 | tr -d '\n')"
uniqueTargetTaxa="$(printf "%'d" $(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} cut -f targetTaxonName | tail -n+2 | sort | uniq | wc -l))"
mostFrequentTargetTaxa="$(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} count-distinct -f targetTaxonName then sort -nr count then cut -f targetTaxonName | tail -n+2 | head -n1 | tr -d '\n')"
datasetVolume="$(${PRESTON_CMD} head ${PRESTON_OPTS} | ${PRESTON_CMD} cat | ${PRESTON_CMD} cat | pv -f -b 2>&1 1>/dev/null | tr '\r' '\n' | grep -E '[0-9]' | tail -n1)"
summaryPhrase="dataset under review, named $DATASET_NAMESPACE, has fingerprint ${DATASET_VERSION}, is ${datasetVolume} in size and contains ${numberOfInteractions} interaction$(pluralize ${numberOfInteractions}) with ${numberOfInteractionTypes} unique type$(pluralize ${numberOfInteractionTypes}) of association$(pluralize ${numberOfInteractionTypes}) (e.g., ${mostFrequentInteractionTypes}) between ${uniqueSourceTaxa} primary $(pluralize_taxon ${uniqueSourceTaxa}) (e.g., ${mostFrequentSourceTaxa}) and ${uniqueTargetTaxa} associated $(pluralize_taxon ${uniqueTargetTaxa}) (e.g., ${mostFrequentTargetTaxa})."
cat <<_EOF_
---
title: $(generate_title)
date: $(date --iso-8601)
author:
- by Nomer, Elton and Preston, three naive review bots
- review@globalbioticinteractions.org
- https://globalbioticinteractions.org/contribute
abstract: |
Life on Earth is sustained by complex interactions between organisms and their environment. These biotic interactions can be captured in datasets and published digitally. We present a review and archiving process for such an openly accessible digital interactions dataset of known origin and discuss its outcome. The ${summaryPhrase} This report includes detailed summaries of interaction data, a taxonomic review from multiple catalogs, and an archived version of the dataset from which the reviews are derived.
bibliography: biblio.bib
keywords:
- biodiversity informatics
- ecology
- species interactions
- biotic interactions
- automated manuscripts
- taxonomic names
- taxonomic name alignment
- biology
reference-section-title: References
---
# Introduction
$(generate_dataset_section)
## Data Review and Archive
Data review and archiving can be a time-consuming process, especially when done manually. This review report aims to help facilitate both activities. It automates the archiving of datasets, including Darwin Core archives, and is a citable backup of a version of the dataset. Additionally, an automatic review of species interaction claims made in the dataset is generated and registered with Global Biotic Interactions [@Poelen_2014].
This review includes summary statistics about, and observations about, the dataset under review $DATASET_CITATION:
> $(generate_dataset_citation)
# Methods
The review is performed through programmatic scripts that leverage tools like Preston [@Preston], Elton [@Elton], Nomer [@Nomer], globinizer [@globinizer] combined with third-party tools like grep, mlr, tail and head.
| tool name | version |
| --- | --- |
| [preston](https://github.com/bio-guoda/preston) | $(echo "${PRESTON_VERSION}" | version_of) |
| [elton](https://github.com/globalbioticinteractions/elton) | $(echo "${ELTON_VERSION}" | version_of) |
| [nomer](https://github.com/globalbioticinteractions/nomer) | $(echo "${NOMER_VERSION}" | version_of) |
| [globinizer](https://github.com/globalbioticinteractions/globinizer) | $(echo "${GLOBINIZER_VERSION}" | version_of) |
| [mlr](https://miller.readthedocs.io/en/6.8.0/) | $(mlr --version | version_of) |
| [jq](https://jqlang.org/) | $(jq --version | version_of) |
| [yq](https://mikefarah.gitbook.io/yq) | $(yq --version | version_of) |
| [pandoc](https://pandoc.org/) | $(pandoc --version | version_of) |
| [duckdb](https://duckdb.org/) | $(duckdb --version | version_of) |
| [mapserver](https://mapserver.org/) | $(mapserv -v | version_of) |
: Tools used in this review process
The review process can be described in the form of the script below ^[Note that you have to first get the data (e.g., via elton pull ${DATASET_NAMESPACE}) before being able to generate reviews (e.g., elton review ${DATASET_NAMESPACE}), extract interaction claims (e.g., elton interactions ${DATASET_NAMESPACE}), or list taxonomic names (e.g., elton names ${DATASET_NAMESPACE})].
~~~
# get versioned copy of the dataset (size approx. ${datasetVolume}) under review
elton pull ${DATASET_NAMESPACE}
# generate review notes
elton review ${DATASET_NAMESPACE} \\
> review.tsv
# export indexed interaction records
elton interactions ${DATASET_NAMESPACE} \\
> interactions.tsv
# export names and align them with the Catalogue of Life using Nomer
elton names ${DATASET_NAMESPACE} \\
| nomer append col \\
> name-alignment.tsv
~~~
or visually, in a process diagram.
You can find a copy of the full review script at [check-data.sh](check-dataset.sh). See also [GitHub](https://github.com/globalbioticinteractions/globinizer/blob/master/check-dataset.sh) and [Codeberg](https://codeberg.org/globalbioticinteractions/globinizer/src/branch/master/check-dataset.sh).
# Results
In the following sections, the results of the review are summarized [^1]. Then, links to the detailed review reports are provided.
## Files
An extensive list of files produced as part of the review process can be found in [Appendix A. Review Files].
## Archived Dataset
Note that [_data.zip_](data.zip) file in this archive contains the complete, unmodified archived dataset under review.
## Biotic Interactions
In this review, biotic interactions (or biotic associations) are modeled as a primary (aka subject, source) organism interacting with an associate (aka object, target) organism. The dataset under review classified the primary/associate organisms with specific taxa. The primary and associate organisms The kind of interaction is documented as an interaction type.
The ${summaryPhrase}
An exhaustive list of indexed interaction claims can be found in gzipped [csv](indexed-interactions.csv.gz), [tsv](indexed-interactions.tsv.gz), [geopackage](indexed-interactions.gpkg) and [parquet](indexed-interactions.parquet) archives. To facilitate discovery, a preview of claims available in the gzipped html page at [indexed-interactions.html.gz](indexed-interactions.html.gz) are shown below.
The exhaustive list was used to create the following data summaries below.
$(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} --omd cut -r -f sourceTaxonName,interactionTypeName,targetTaxonName,referenceCitation | head -n6)
: Sample of Indexed Interaction Claims
$(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} --omd count-distinct -f interactionTypeName then sort -nr count | head -n${headCount})
: Most Frequently Mentioned Interaction Types (up to ${headCountWithoutHeader} most frequent)
$(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} --omd count-distinct -f sourceTaxonName then sort -nr count | head -n${headCount})
: Most Frequently Mentioned Primary Taxa (up to ${headCountWithoutHeader} most frequent)
$(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} --omd count-distinct -f targetTaxonName then sort -nr count | head -n${headCount})
: Most Frequently Mentioned Associate Taxa (up to ${headCountWithoutHeader} most frequent)
$(cat indexed-interactions.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} --omd count-distinct -f sourceTaxonName,interactionTypeName,targetTaxonName then sort -nr count | head -n${headCount})
: Most Frequent Interactions between Primary and Associate Taxa (up to ${headCountWithoutHeader} most frequent)
$(generate_network_graphs)
You can download the indexed dataset under review at [indexed-interactions.csv.gz](indexed-interactions.csv.gz). A tab-separated file can be found at [indexed-interactions.tsv.gz](indexed-interactions.tsv.gz)
## Geospatial Distribution
If geospatial information was extracted from the dataset under review, the map below will show their distribution. These maps were generated using MapServer [@mckenna_2025_17807263] tools configured via map configuration [indexed-interactions.map](indexed-interactions.map) :
~~~
$(cat indexed-interactions.map)
~~~
Associated data can be found in the geopackage files at [indexed-interactions.gpkg](indexed-interactions.gpkg) for point data and [indexed-interactions-h3.gpkg](indexed-interactions-h3.gpkg) for data clustered in geospatial h3 hexagonals.
Learn more about the structure of this download at [GloBI website](https://globalbioticinteractions.org), by opening a [GitHub issue](https://github.com/globalbioticinteractions/globalbioticinteractions/issues/new), or by sending an [email](mailto:info@globalbioticinteractions.org).
Another way to discover the dataset under review is by searching for it on the [GloBI website](https://www.globalbioticinteractions.org/?accordingTo=globi%3A$(echo ${DATASET_NAMESPACE} | sed 's+/+%2F+g')).
## Taxonomic Alignment
As part of the review, all names are aligned against various name catalogs (e.g., $(echo ${TAXONOMIES} | sed 's/ /, /g' | sed -E 's/, ([a-z]+)$/, and \1/g')). These alignments can help review name usage or aid in selecting of a suitable taxonomic name resource. Also, for each name, an alignment index is calculated where the alignment index for a specific name = 1 - (number of catalogs without the name) / (total number of catalogs) . So, if a name is not recognized by any catalog, the alignment index value for that name is 0. Also, if a name is recognized by all catalogues, the alignment index value for that name is 1.
$(cat indexed-names-resolved.tsv.gz | gunzip | mlr ${MLR_TSV_OPTS} cut -f providedName,relationName,resolvedCatalogName,resolvedName | mlr ${MLR_TSV_INPUT_OPTS} --omd uniq -f providedName,relationName,resolvedCatalogName,resolvedName | head -n6)
: Sample of Name Alignments
$(cat indexed-names-alignment-index.tsv.gz | gunzip | mlr ${MLR_TSV_INPUT_OPTS} --omd cat | head -n${headCount})
: Sample of Name Alignment Index (up to ${headCountWithoutHeader}). Names successfully aligned with all catalog have index value 1.0, whereas names aligned with none of the used catalogs have index 0.0. Suspicious taxonomic names (e.g., a name with typo like _Homo sapienz_) with low or 0.0 alignment index values are listed first to facilitate review. Full copies of alignment index for names under review can be found in [Appendix A. Review Files] in gzipped [html](indexed-names-alignment-index.html.gz), [csv](indexed-names-alignment-index.csv.gz), and [tsv](indexed-names-alignment-index.tsv.gz) formats.
$(cat indexed-names-resolved.tsv.gz | gunzip | mlr --tsvlite uniq -f providedName,resolvedCatalogName,resolvedRank | sed 's/\t$/\tNA/g' | mlr --itsvlite --omd count-distinct -f resolvedCatalogName,resolvedRank then sort -f resolvedCatalogName,resolvedRank)
: Distribution of Taxonomic Ranks of Aligned Names by Catalog. Names that were not aligned with a catalog are counted as NAs. So, the total number of unaligned names for a catalog will be listed in their NA row.
$(cat indexed-names-resolved.tsv.gz | gunzip | mlr ${MLR_TSV_INPUT_OPTS} --omd count-distinct -f resolvedCatalogName,relationName then sort -f resolvedCatalogName)
: Name relationship types per catalog. Name relationship type "NONE" means that a name was not recognized by the associated catalog. "SAME_AS" indicates either a "HAS_ACCEPTED_NAME" or "SYNONYM_OF" name relationship type. We recognize that "SYNONYM_OF" encompasses many types of nomenclatural synonymies [@ICZN_1999] (e.g., junior synonym, senior synonyms).
| catalog name | alignment results |
| --- | --- |
$(echo "${TAXONOMIES}" | tr ' ' '\n' | awk '{ print "| " $1 " | associated names alignments report in gzipped [html](indexed-names-resolved-" $1 ".html.gz), [csv](indexed-names-resolved-" $1 ".csv.gz), and [tsv](indexed-names-resolved-" $1 ".tsv.gz)) |"}')
: List of Available Name Alignment Reports
## Additional Reviews
Elton, Nomer, and other tools may have difficulties interpreting existing species interaction datasets. Or, they may misbehave, or otherwise show unexpected behavior. As part of the review process, detailed review notes are kept that document possibly misbehaving, or confused, review bots. An sample of review notes associated with this review can be found below.
$(cat review.tsv.gz | gunzip | mlr ${MLR_TSV_INPUT_OPTS} --omd cut -f reviewDate,reviewCommentType,reviewComment | head -n6)
: First few lines in the review notes.
In addition, you can find the most frequently occurring notes in the table below.
$(cat review.tsv.gz | gunzip | mlr ${MLR_TSV_INPUT_OPTS} --omd cut -f reviewCommentType,reviewComment then filter '$reviewCommentType == "note"' then count-distinct -f reviewComment then sort -nr count | head -n6)
: Most frequently occurring review notes, if any.
For additional information on review notes, please have a look at the first 500 [Review Notes](review-sample.html) in html format or the download full gzipped [csv](review.csv.gz) or [tsv](review.tsv.gz) archives.
## GloBI Review Badge
As part of the review, a review badge is generated. This review badge can be included in webpages to indicate the review status of the dataset under review.
]](review.svg)
Note that if the badge is green, no review notes were generated. If the badge is yellow, the review bots may need some help with interpreting the species interaction data.
## GloBI Index Badge
If the dataset under review has been [registered with GloBI](https://globalbioticinteractions.org/contribute), and has been succesfully indexed by GloBI, the GloBI Index Status Badge will turn green. This means that the dataset under review was indexed by GloBI and is available through GloBI services and derived data products.
]](https://api.globalbioticinteractions.org/interaction.svg?interactionType=ecologicallyRelatedTo&accordingTo=globi:${DATASET_NAMESPACE}&refutes=true&refutes=false)
If you'd like to keep track of reviews or index status of the dataset under review, please visit GloBI's dataset index ^[At time of writing ($(date --iso-8601)) the version of the GloBI dataset index was available at [https://globalbioticinteractions.org/datasets](https://globalbioticinteractions.org/datasets)] for badge examples.
# Discussion
This review and archive provides a means of creating citable versions of datasets that change frequently. This may be useful for dataset managers, including natural history collection data managers, as a backup archive of a shared Darwin Core archive. It also serves as a means of creating a trackable citation for the dataset in an automated way, while also including some information about the contents of the dataset.
This review aims to provide a perspective on the dataset to aid in understanding of species interaction claims discovered. However, it is important to note that this review does *not* assess the quality of the dataset. Instead, it serves as an indication of the open-ness[^2] and FAIRness [@Wilkinson_2016; @trekels_maarten_2023_8176978] of the dataset: to perform this review, the data was likely openly available, **F**indable, **A**ccessible, **I**nteroperable and **R**eusable. The current Open-FAIR assessment is qualitative, and a more quantitative approach can be implemented with specified measurement units.
This report also showcases the reuse of machine-actionable (meta)data, something highly recommended by the FAIR Data Principles [@Wilkinson_2016]. Making (meta)data machine-actionable enables more precise procesing by computers, enabling even naive review bots like Nomer and Elton to interpret the data effectively. This capability is crucial for not just automating the generation of reports, but also for facilitating seamless data exchanges, promoting interoperability.
# Acknowledgements
We thank the many humans that created us and those who created and maintained the data, software and other intellectual resources that were used for producing this review. In addition, we are grateful for the natural resources providing the basis for these human and bot activities. Also, thanks to https://github.com/zygoballus for helping improve the layout of the review tables.
# Author contributions
Nomer was responsible for name alignments. Elton carried out dataset extraction, and generated the review notes. Preston tracked, versioned, and packaged, the dataset under review.
# Appendix A. Review Files
The following files are produced in this review:
filename | description
--- | ---
[biblio.bib](biblio.bib) | list of bibliographic reference of this review
[check-dataset.sh](check-dataset.sh) | data review workflow/process as expressed in a bash script
[data.zip](data.zip) | a versioned archive of the data under review
[HEAD](HEAD) | the digital signature of the data under review
[index.docx](index.docx) | review in MS Word format
[index.html](index.html) | review in HTML format
[index.md](index.md) | review in Pandoc markdown format
[index.pdf](index.pdf) | review in PDF format
[indexed-citations.csv.gz](indexed-citations.csv.gz) | list of distinct reference citations for reviewed species interaction claims in gzipped comma-separated values file format
[indexed-citations.html.gz](indexed-citations.html.gz) | list of distinct reference citations for reviewed species interactions claims in gzipped html file format
[indexed-citations.tsv.gz](indexed-citations.tsv.gz) | list of distinct reference citations for reviewed species interaction claims in gzipped tab-separated values format
[indexed-interactions-col-family-col-family.svg](indexed-interactions-col-family-col-family.svg) | network diagram showing the taxon family to taxon family interaction claims in the dataset under review as interpreted by the Catalogue of Life via Nomer Corpus of Taxonomic Resources [@NomerCorpus]
[indexed-interactions-col-kingdom-col-kingdom.svg](indexed-interactions-col-kingdom-col-kingdom.svg) | network diagram showing the taxon kingdom to taxon kingom interaction claims in the dataset under review as interpreted by the Catalogue of Life via Nomer Corpus of Taxonomic Resources [@NomerCorpus]
[indexed-interactions.csv.gz](indexed-interactions.csv.gz) | species interaction claims indexed from the dataset under review in gzipped comma-separated values format
[indexed-interactions.html.gz](indexed-interactions.html.gz) | species interaction claims indexed from the dataset under review in gzipped html format
[indexed-interactions.tsv.gz](indexed-interactions.tsv.gz) | species interaction claims indexed from the dataset under review in gzipped tab-separated values format
[indexed-interactions.parquet](indexed-interactions.parquet) | species interaction claims indexed from the dataset under review in Apache Parquet format
[indexed-interactions.png](indexed-interactions.png) | species interaction claims indexed from the dataset under review plotted on a map
[indexed-interactions.map](indexed-interactions.map) | mapserver configuration to plot species interaction claims indexed from the dataset under review on a map
[indexed-interactions.gpkg](indexed-interactions.gpkg) | species interaction claims indexed from the dataset under review in GeoPackage format
[indexed-interactions.fgb](indexed-interactions.fgb) | species interaction claims indexed from the dataset under review in FlatGeoBuf format
[indexed-interactions-h3.gpkg](indexed-interactions-h3.gpkg) | geospatially clustered h3 species interaction claims indexed from the dataset under review in GeoPackage format
[indexed-interactions-sample.csv](indexed-interactions-sample.csv) | list of species interaction claims indexed from the dataset under review in gzipped comma-separated values format
[indexed-interactions-sample.html](indexed-interactions-sample.html) | first 500 species interaction claims indexed from the dataset under review in html format
[indexed-interactions-sample.tsv](indexed-interactions-sample.tsv) | first 500 species interaction claims indexed from the dataset under review in tab-separated values format
[indexed-names.csv.gz](indexed-names.csv.gz) | taxonomic names indexed from the dataset under review in gzipped comma-separated values format
[indexed-names.html.gz](indexed-names.html.gz) | taxonomic names found in the dataset under review in gzipped html format
[indexed-names.tsv.gz](indexed-names.tsv.gz) | taxonomic names found in the dataset under review in gzipped tab-separated values format
[indexed-names.parquet](indexed-names.parquet) | taxonomic names found in the dataset under review in Apache Parquet format
[indexed-names-alignment-index.csv.gz](indexed-names-alignment-index.csv.gz) | taxonomic names and their alignment index calculated using the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-alignment-index.tsv.gz](indexed-names-alignment-index.tsv.gz) | taxonomic names and their alignment index calculated using the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-alignment-index.html.gz](indexed-names-alignment-index.html.gz) | taxonomic names and their alignment index calculated using the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-col.csv.gz](indexed-names-resolved-col.csv.gz) | taxonomic names found in the dataset under review aligned with the Catalogue of Life as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-resolved-col.html.gz](indexed-names-resolved-col.html.gz) | taxonomic names found in the dataset under review aligned with the Catalogue of Life as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-col.tsv.gz](indexed-names-resolved-col.tsv.gz) | taxonomic names found in the dataset under review aligned with the Catalogue of Life as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-resolved-col.parquet](indexed-names-resolved-col.parquet) | taxonomic names found in the dataset under review aligned with the Catalogue of Life as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in Apache Parquet format
[indexed-names-resolved-discoverlife.csv.gz](indexed-names-resolved-discoverlife.csv.gz) | taxonomic names found in the dataset under review aligned with Discover Life bee species checklist as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-resolved-discoverlife.html.gz](indexed-names-resolved-discoverlife.html.gz) | taxonomic names found in the dataset under review aligned with Discover Life bee species checklist as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-discoverlife.tsv.gz](indexed-names-resolved-discoverlife.tsv.gz) | taxonomic names found in the dataset under review aligned with Discover Life bee species checklist as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-resolved-discoverlife.parquet](indexed-names-resolved-discoverlife.parquet) | taxonomic names found in the dataset under review aligned with Discover Life bee species checklist as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in Apache Parquet format
[indexed-names-resolved-gbif.csv.gz](indexed-names-resolved-gbif.csv.gz) | taxonomic names found in the dataset under review aligned with GBIF Backbone Taxonomy as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-resolved-gbif.html.gz](indexed-names-resolved-gbif.html.gz) | taxonomic names found in the dataset under review aligned with GBIF Backbone Taxonomy as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-gbif.tsv.gz](indexed-names-resolved-gbif.tsv.gz) | taxonomic names found in the dataset under review aligned with GBIF Backbone Taxonomy as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-resolved-gbif.parquet](indexed-names-resolved-gbif.parquet) | taxonomic names found in the dataset under review aligned with GBIF Backbone Taxonomy as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in Apache Parquet format
[indexed-names-resolved-itis.csv.gz](indexed-names-resolved-itis.csv.gz) | taxonomic names found in the dataset under review aligned with Integrated Taxonomic Information System (ITIS) as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-resolved-itis.html.gz](indexed-names-resolved-itis.html.gz) | taxonomic names found in the dataset under review aligned with Integrated Taxonomic Information System (ITIS) as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-itis.tsv.gz](indexed-names-resolved-itis.tsv.gz) | taxonomic names found in the dataset under review aligned with Integrated Taxonomic Information System (ITIS) as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-resolved-itis.parquet](indexed-names-resolved-itis.parquet) | taxonomic names found in the dataset under review aligned with Integrated Taxonomic Information System (ITIS) as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in Apache Parquet format
[indexed-names-resolved-mdd.csv.gz](indexed-names-resolved-mdd.csv.gz) | taxonomic names found in the dataset under review aligned with the Mammal Diversity Database as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-resolved-mdd.html.gz](indexed-names-resolved-mdd.html.gz) | taxonomic names found in the dataset under review aligned with Mammal Diversity Database as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-mdd.tsv.gz](indexed-names-resolved-mdd.tsv.gz) | taxonomic names found in the dataset under review aligned with Mammal Diversity Database as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-resolved-mdd.parquet](indexed-names-resolved-mdd.parquet) | taxonomic names found in the dataset under review aligned with Mammal Diversity Database as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in Apache Parquet format
[indexed-names-resolved-ncbi.csv.gz](indexed-names-resolved-ncbi.csv.gz) | taxonomic names found in the dataset under review aligned with the NCBI Taxonomy as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-resolved-ncbi.html.gz](indexed-names-resolved-ncbi.html.gz) | taxonomic names found in the dataset under review aligned with the NCBI Taxonomy as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-ncbi.tsv.gz](indexed-names-resolved-ncbi.tsv.gz) | taxonomic names found in the dataset under review aligned with the NCBI Taxonomy as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-resolved-ncbi.parquet](indexed-names-resolved-ncbi.parquet) | taxonomic names found in the dataset under review aligned with the NCBI Taxonomy as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in Apache Parquet format
[indexed-names-resolved-pbdb.csv.gz](indexed-names-resolved-pbdb.csv.gz) | taxonomic names found in the dataset under review aligned with the Paleobiology Database as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-resolved-pbdb.html.gz](indexed-names-resolved-pbdb.html.gz) | taxonomic names found in the dataset under review aligned with Paleobiology Database as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-pbdb.tsv.gz](indexed-names-resolved-pbdb.tsv.gz) | taxonomic names found in the dataset under review aligned with Paleobiology Database as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-resolved-pbdb.parquet](indexed-names-resolved-pbdb.parquet) | taxonomic names found in the dataset under review aligned with Paleobiology Database as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in Apache Parquet format
[indexed-names-resolved-tpt.csv.gz](indexed-names-resolved-tpt.csv.gz) | taxonomic names found in the dataset under review aligned with the Terrestrial Parasite Tracker (TPT) Taxonomic Resource as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-resolved-tpt.html.gz](indexed-names-resolved-tpt.html.gz) | taxonomic names found in the dataset under review aligned with the Terrestrial Parasite Tracker (TPT) Taxonomic Resource as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-tpt.tsv.gz](indexed-names-resolved-tpt.tsv.gz) | taxonomic names found in the dataset under review aligned with the Terrestrial Parasite Tracker (TPT) Taxonomic Resource as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-resolved-tpt.parquet](indexed-names-resolved-tpt.parquet) | taxonomic names found in the dataset under review aligned with the Terrestrial Parasite Tracker (TPT) Taxonomic Resource as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in Apache Parquet format
[indexed-names-resolved-wfo.csv.gz](indexed-names-resolved-wfo.csv.gz) | taxonomic names found in the dataset under review aligned with the World of Flora Online as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-resolved-wfo.html.gz](indexed-names-resolved-wfo.html.gz) | taxonomic names found in the dataset under review aligned with the World of Flora Online as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-wfo.tsv.gz](indexed-names-resolved-wfo.tsv.gz) | taxonomic names found in the dataset under review aligned with the World of Flora Online as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-resolved-wfo.parquet](indexed-names-resolved-wfo.parquet) | taxonomic names found in the dataset under review aligned with the World of Flora Online as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in Apache Parquet format
[indexed-names-resolved-worms.csv.gz](indexed-names-resolved-worms.csv.gz) | taxonomic names found in the dataset under review aligned with the World Register of Marine Species (WoRMS) as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped comma-separated values format
[indexed-names-resolved-worms.html.gz](indexed-names-resolved-worms.html.gz) | taxonomic names found in the dataset under review aligned with the World Register of Marine Species (WoRMS) as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped html format
[indexed-names-resolved-worms.tsv.gz](indexed-names-resolved-worms.tsv.gz) | taxonomic names found in the dataset under review aligned with the World Register of Marine Species (WoRMS) as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in gzipped tab-separated values format
[indexed-names-resolved-worms.parquet](indexed-names-resolved-worms.parquet) | taxonomic names found in the dataset under review aligned with the World Register of Marine Species (WoRMS) as accessed through the Nomer Corpus of Taxonomic Resources [@NomerCorpus] in Apache Parquet format
[indexed-names-sample.csv](indexed-names-sample.csv) | first 500 taxonomic names found in the dataset under review in comma-separated values format
[indexed-names-sample.html](indexed-names-sample.html) | first 500 taxonomic names found in the dataset under review in html format
[indexed-names-sample.tsv](indexed-names-sample.tsv) | first 500 taxonomic names found in the dataset under review in tab-separated values format
[interaction.svg](interaction.svg) | diagram summarizing the data model used to index species interaction claims
[nanopub-sample.trig](nanopub-sample.trig) | first 500 species interaction claims as expressed in the nanopub format [@Nanopub]
[nanopub.trig.gz](nanopub.trig.gz) | species interaction claims as expressed in the nanopub format [@Nanopub]
[process.svg](process.svg) | diagram summarizing the data review processing workflow
[prov.nq](prov.nq) | origin of the dataset under review as expressed in rdf/nquads
[review.csv.gz](review.csv.gz) | review notes associated with the dataset under review in gzipped comma-separated values format
[review.html.gz](review.html.gz) | review notes associated with the dataset under review in gzipped html format
[review.tsv.gz](review.tsv.gz) | review notes associated with the dataset under review in gzipped tab-separated values format
[review-sample.csv](review-sample.csv) | first 500 review notes associated with the dataset under review in comma-separated values format
[review-sample.html](review-sample.html) | first 500 review notes associated with the dataset under review in html format
[review-sample.tsv](review-sample.tsv) | first 500 review notes associated with the dataset under review in tab-separated values format
[review.svg](review.svg) | a review badge generated as part of the dataset review process
[zenodo.json](zenodo.json) | metadata of this review expressed in Zenodo record metadata
[^1]: Disclaimer: The results in this review should be considered friendly, yet naive, notes from an unsophisticated robot. Please keep that in mind when considering the review results.
[^2]: According to http://opendefinition.org/: "Open data is data that can be freely used, re-used and redistributed by anyone - subject only, at most, to the requirement to attribute and sharealike."
_EOF_
}
function clean_review_dir {
rm -rf ${REVIEW_DIR}
}
function use_review_dir {
clean_review_dir
mkdir -p ${REVIEW_DIR}
cd ${REVIEW_DIR}
}
function tee_readme {
tee --append $README
}
function save_readme {
cat ${README} > README.txt
}
function install_duckdb {
if [[ ! $(which duckdb) ]]; then
curl https://install.duckdb.org | sh &> /dev/null
export PATH=$HOME/.duckdb/cli/latest:$PATH
fi
}
function install_deps {
if [[ -n ${TRAVIS_REPO_SLUG} || -n ${GITHUB_REPOSITORY} ]]
then
sudo apt -q update &> /dev/null
sudo apt -q install miller jq -y &> /dev/null
curl --silent -L https://github.com/jgm/pandoc/releases/download/3.1.6.1/pandoc-3.1.6.1-1-amd64.deb > pandoc.deb && sudo apt install -q ./pandoc.deb &> /dev/null
curl --silent -L https://github.com/globalbioticinteractions/nomer/releases/download/${NOMER_VERSION}/nomer.deb > nomer.deb && sudo apt install -q ./nomer.deb &> /dev/null
curl --silent -L https://github.com/globalbioticinteractions/elton/releases/download/${ELTON_VERSION}/elton.deb > elton.deb && sudo apt install -q ./elton.deb &> /dev/null
curl --silent -L https://github.com/bio-guoda/preston/releases/download/${PRESTON_VERSION}/preston.deb > preston.deb && sudo apt install -q ./preston.deb &> /dev/null
curl --silent -L https://github.com/mikefarah/yq/releases/latest/download/yq_linux_amd64 > /usr/local/bin/yq && chmod +x /usr/local/bin/yq &> /dev/null
sudo apt -q install texlive texlive-xetex lmodern
sudo apt -q install graphviz
sudo apt -q install librsvg2-bin
sudo apt -q install libxml2-utils
sudo apt -q install pv
sudo apt -q install mapserver-bin
sudo pip install s3cmd &> /dev/null
fi
install_duckdb
mlr --version
s3cmd --version
java -version
pandoc --version
duckdb --version
}
function configure_network_compiler {
if [[ -x "${NETWORK_COMPILER_SCRIPT}" ]]
then
NETWORK_COMPILER_PRESENT=true
echo found network compile script at [${NETWORK_COMPILER_SCRIPT}]
fi
}
function patch_svg_width {
# replace graphviz's dot absolute svg width/height with relative
sed -E 's/^