A lot of work on making this more production-ready

datacrate.js

@@ -2,6 +2,7 @@
 
 
 const datacrate = require('./lib/catalog.js');
+const calcyte = require('calcyte');
 const fs = require('fs-extra');
 const path = require('path');
 const ArgumentParser = require('argparse').ArgumentParser;
@@ -16,12 +17,16 @@ const ORGANISATION = {
 const OWNER = 'Kathryn.T.Braye@student.uts.edu.au';
 const APPROVER = 'Sharyn.Wise@uts.edu.au';
 
+const CITATION = 'Citation';
+const ZIP_PATH = 'https://test/'
 
 
-async function makedatacrate(doi, datapub, dest) {
+async function makecatalog(doi, datapub, dest, zip) {
 	await fs.ensureDir(dest);
 	const catalog = await datacrate.datapub2catalog({
 		id: doi,
+		bagged: true,
+		zip: zip,
 		datapub: datapub,
 		organisation: ORGANISATION,
 		owner: OWNER,
@@ -29,11 +34,35 @@ async function makedatacrate(doi, datapub, dest) {
 	});
 	const catfile = path.join(dest, 'CATALOG.json');
 	await fs.writeFile(catfile, JSON.stringify(catalog, null, 2));
+	return catalog;
 }
 
-async function convertdatapub(pid, jsonfile, dest) {
+async function makedatacrate(catalog, dir, citation, zip) {
+	const index = new calcyte.Index();
+	index.init(catalog, dir, true);
+	console.log("Writing DataCrate");
+	index.make_index_html(citation, zip);
+}
+
+// const catalog_json = path.join(dir, sails.config.datapubs.datacrate.catalog_json);
+// sails.log.info(`Building CATALOG.json with jsonld_h`);
+// sails.log.silly(`catalog = ${JSON.stringify(catalog)}`);
+// sails.log.info(`Writing CATALOG.json to ${catalog_json}`);
+// fs.writeFileSync(catalog_json, JSON.stringify(catalog, null, 2));
+// const index = new Index();
+// index.init(catalog, dir, false);
+// sails.log.info(`Writing CATALOG.html`);
+// index.make_index_html("text_citation", "zip_path"); //writeFileSync
+// return Observable.of({});
+
+
+
+
+async function convertdatapub(pid, jsonfile, dest, zip) {
 	const datapub = await fs.readJSON(jsonfile);
-	await makedatacrate(pid, datapub, dest);
+	const citation = datapub['citation_doi'];
+	const catalogfile = await makecatalog(pid, datapub, dest, zip);
+	await makedatacrate(catalogfile, dest, citation, zip);
 }
 
 
@@ -58,6 +87,14 @@ parser.addArgument(
 		required: true
 	});
 
+parser.addArgument(
+	['-z', '--zip'],
+	{
+		help: "The URL of the zipped datacrate when it is published",
+		defaultValue: ZIP_PATH
+	}
+);
+
 
 parser.addArgument(
 	['-d', '--directory'],
@@ -69,7 +106,8 @@ parser.addArgument(
 
 
 
+
 var args = parser.parseArgs();
 
-convertdatapub(args['persistentid'], args['input'], args['directory']);
+convertdatapub(args['persistentid'], args['input'], args['directory'], args['zip']);
 

lib/catalog.js

@@ -40,7 +40,8 @@ const RELATED_TYPES = {
 	'services': 'CreativeWork' // I'm not sure about this?
 };
 
-const ROOT_PATH = 'data/';
+const ROOT_PATH_BAGGED = 'data/';
+const ROOT_PATH_WORKING = './';
 
 const FUNDING_FIELDS = [ 'foaf:fundedBy_foaf:Agent', 'foaf:fundedBy_vivo:Grant' ];
 
@@ -124,10 +125,12 @@ async function datapub2catalog(options) {
 
 	const id = options['id'];
 	const datapub = options['datapub'];
+	const bagged = options['bagged'];
+	const zip = options['zip'];
 	const org = options['organisation'];
 	const owner = options['owner'];
 	const approver = options['approver'];
-	const dates = dates_default(options['dates'])
+	const dates = dates_default(options['dates']);
 	const prefixes = options['prefixes'] || DEFAULT_IRI_PREFS;
 
 	const organisation = { 
@@ -146,7 +149,7 @@ async function datapub2catalog(options) {
 	var people = make_creators(datapub, organisation);
 
 	const files = make_files(datapub);
-	const dataset = make_dataset(id, datapub, organisation, dates, files, people);
+	const dataset = make_dataset(id, datapub, bagged, organisation, dates, files, people);
 	const [ history, more_people ] = make_history(
 		dataset, people, owner, approver, dates
 	);
@@ -195,10 +198,31 @@ async function datapub2catalog(options) {
 		})
 	}
 
+    if( zip ) {
+      if( !dataset["distribution"] ) {
+        dataset["distribution"] = []
+      }
+      dataset["distribution"].push(
+        {
+          "@id": zip
+        }
+      );
+      graph.push(
+        {
+          "@id": zip,
+          "contentUrl": zip,
+          "@type": "DataDownload",
+          "encodingFormat": "zip"
+       });
+       context["DataDownload"] = "https://schema.org/DataDownload";
+       context["distribution"] = "https://schema.org/distribution";
+    }
+
 	const catalog = {
 		'@context': context,
 		'@graph': graph.filter((e) => e)
 	};
+
 	const jsonld = new calcyte.jsonld();
 	jsonld.init(catalog);
 	jsonld.trim_context();
@@ -227,11 +251,13 @@ function link_id(item) {
 
 // TODO: isBasedOn the data record
 
-function make_dataset(id, datapub, organisation, dates, files, creators) {
+// always does data/ as the root path
+
+function make_dataset(id, datapub, bagged, organisation, dates, files, creators) {
 	const ds = {
 		'@id': id,
 		'@type': 'Dataset',
-		'path': ROOT_PATH,
+		'path': bagged ? ROOT_PATH_BAGGED : ROOT_PATH_WORKING,
 		'name': datapub['title'],
 		'description': datapub['description'],
 		'dateCreated': dates['dateCreated'],
@@ -287,7 +313,7 @@ function make_history(dataset, people, owner, approver, dates) {
 	
   const history = [
 		{
-			'@id': dataset['@id'] + '_history1',
+			'@id': 'history1',
 			'@type': 'CreateAction',
 			'name': 'Create',
 			'description': 'Data record created',
@@ -296,7 +322,7 @@ function make_history(dataset, people, owner, approver, dates) {
 			'agent': link_id(owner_item)
 		},
 		{
-			'@id': dataset['@id'] + '_history2',
+			'@id': 'history2',
 			'@type': 'UpdateAction',
 			'name': 'Publish',
 			'endTime': dates['datePublished'],