Import Metadata from Chemotion to FIZ-OAI provider

Chemotion2OAI.sh

## 1) Get paginated list of Molecules from Chemotion
## 2) extract DOI and internal chemotion ID for each molecule with `jq`
## 3) Query each molecule and convert with `jq` to (bio)schemas
## 4) Embedd the JSON in a CDATA in a minimalistic XML
## 5) Pipe the XML to the FIZ-OAI backend running at $BACKEND, e.g. localhost

export BACKEND=http://localhost:8081/oai-backend

for I in 1 2 3 4 5 6 7 8 9 10; do
wget -O- "https://www.chemotion-repository.net/api/v1/public/molecules.json?page=$I&per_page=100" |\
jq --raw-output '.molecules | map([.id , .tag.taggable_data.chemotion.doi] | join("\t") ) | join("\n")' |\
while read ID DOI ; do
(
cat <<EOF
<json xmlns="http://denbi.de/schemas/json-container">
<![CDATA[
EOF

wget -q -O- https://www.chemotion-repository.net/api/v1/public/molecule.json?id=$ID |\
jq "$(cat <<EOF
{ "@context": "https://schema.org/",
  "@type": "MolecularEntity",
  "dct:conformsTo": { "http://purl.org/dc/terms/conformsTo": {
    "@id": "https://bioschemas.org/profiles/MolecularEntity/0.5-RELEASE",
    "@type": "CreativeWork" }
  },
  "@id": .molecule.tag.taggable_data.chemotion.doi,
  name: .molecule.iupac_name,
  url: "http://chemotion-repository.net/home/publications/molecules/\(.molecule.id)",
  identifier: "chemotion ID ?",
  iupacName:.molecule.iupac_name,
  smiles: .molecule.cano_smiles,
  inChI: .molecule.inchistring,
  inChIKey: .molecule.inchikey,
  molecularFormula: .molecule.sum_formular,
  molecularWeight: { value: .molecule.molecular_weight }
}
EOF
)"

cat <<EOF
]]>
</json>
EOF
) | curl -v -X POST -H 'Content-Type: multipart/form-data' \
  -i "$BACKEND/item"  \
  -F "item={\"identifier\":\"$DOI\",\"deleteFlag\":false,\"ingestFormat\":\"json_container\"};type=application/json" \
  -F content=@- ;\
done # while read
done # for