Merge branch 'export-endpoint' into interface-changes-export-new

Konstiman · Konstiman · commit 62d81846a594 · 2022-02-07T11:42:38.000+01:00
diff --git a/README.md b/README.md
@@ -92,7 +92,7 @@ More information can be found in the following papers:
 
 Kraker, P., Schramm, M., Kittel, C., Chamberlain, S., & Arrow, T. (2018). [VIPER: The Visual Project Explorer](https://zenodo.org/record/1248119). Zenodo. doi:10.5281/zenodo.2587129
 
-Kraker, P., Kittel, C., & Enkhbayar, A. (2016). [Open Knowledge Maps: Creating a Visual Interface to the World’s Scientific Knowledge Based on Natural Language Processing](http://0277.ch/ojs/index.php/cdrs_0277/article/view/157/355). 027.7 Journal for Library Culture, 4(2), 98–103. doi:10.12685/027.7-4-2-157
+Kraker, P., Kittel, C., & Enkhbayar, A. (2016). [Open Knowledge Maps: Creating a Visual Interface to the World’s Scientific Knowledge Based on Natural Language Processing](https://doi.org/10.12685/027.7-4-2-157). 027.7 Journal for Library Culture, 4(2), 98–103. doi:10.12685/027.7-4-2-157
 
 Kraker, P., Schlögl, C. , Jack, K. & Lindstaedt, S. (2015). [Visualization of Co-Readership Patterns from an Online Reference Management System](http://arxiv.org/abs/1409.0348). Journal of Informetrics, 9(1), 169–182. doi:10.1016/j.joi.2014.12.003
 
diff --git a/server/preprocessing/other-scripts/base.R b/server/preprocessing/other-scripts/base.R
@@ -140,6 +140,8 @@ get_papers <- function(query, params, limit=100,
   subject_cleaned = gsub(" ?\\d[:?-?]?(\\d+.)+", "", subject_cleaned) # replace residuals like 5:621.313.323 or '5-76.95'
   subject_cleaned = gsub("\\w+:\\w+-(\\w+\\/)+", "", subject_cleaned) # replace residuals like Info:eu-repo/classification/
   subject_cleaned = gsub("^; $", "", subject_cleaned) # replace residuals like Info:eu-repo/classification/
+  subject_cleaned = gsub(",", ", ", subject_cleaned) # clean up keyword separation
+  subject_cleaned = gsub("\\s+", " ", subject_cleaned) # clean up keyword separation
 
   metadata$subject = subject_cleaned
 
diff --git a/server/services/exportMetadata.php b/server/services/exportMetadata.php
@@ -0,0 +1,52 @@
+<?php
+
+require_once dirname(__FILE__) . '/../classes/headstart/library/CommUtils.php';
+require_once dirname(__FILE__) . '/../classes/headstart/library/APIClient.php';
+require_once dirname(__FILE__) . '/../classes/headstart/library/toolkit.php';
+use headstart\library;
+
+function export($export_format, $metadata_json) {
+    $INI_DIR = dirname(__FILE__) . "/../preprocessing/conf/";
+    $ini_array = library\Toolkit::loadIni($INI_DIR);
+    $apiclient = new \headstart\library\APIClient($ini_array);
+
+
+    $payload = $metadata_json;
+    #$res = $apiclient->call_persistence("export/" . $export_format, $payload);
+    $res = $apiclient->call_api("export/" . $export_format, $payload);
+    return $res;
+};
+
+$json = file_get_contents('php://input');
+$format = (isset($_REQUEST['format'])) ? $_REQUEST['format'] : "bibtex";
+$download = (isset($_REQUEST['download'])) ? $_REQUEST['download'] : false;
+$result = export($format, $json);
+
+if (isset($result["status"]) && $result["status"] === "error") {
+    header('Content-type: application/json');
+    echo json_encode($result);
+}
+
+if (isset($download) & $download==true ) {
+    header('Content-type: application/text');
+    header('Content-Disposition: attachment; filename=metadata.' . $format);
+} else {
+    header('Content-type: text/plain');
+}
+
+// $origin = $_SERVER['HTTP_ORIGIN'];
+// $allowed_domains = [
+//     'http://openknowledgemaps.org',
+//     'https://openknowledgemaps.org',
+//     'http://dev.openknowledgemaps.org',
+//     'https://dev.openknowledgemaps.org'
+// ];
+
+// if (in_array($origin, $allowed_domains)) {
+//     header('Access-Control-Allow-Origin: ' . $origin);
+// }
+
+$result = json_decode($result["result"], true);
+echo $result["export"];
+
+?>
diff --git a/server/workers/api/requirements.txt b/server/workers/api/requirements.txt
@@ -12,3 +12,4 @@ pandas
 pyyaml
 flasgger
 psycopg2-binary
+bibtexparser
diff --git a/server/workers/api/src/apis/export.py b/server/workers/api/src/apis/export.py
@@ -0,0 +1,92 @@
+import os
+
+from flask import Blueprint, request, make_response, jsonify, abort
+from flask_restx import Namespace, Resource, fields
+from bibtexparser.bwriter import BibTexWriter 
+from bibtexparser.bibdatabase import BibDatabase
+
+export_ns = Namespace("export", description="metadata export API operations")
+
+def transform2bibtex(metadata):
+    # TODO: add mapping from resulttype to ARTICLETYPE
+    # possible published_in parser
+    # field renaming, e.g. paper_abstract to abstract
+    # choose correct fields, e.g. author_string for author
+    # use different field for ID
+    title = metadata.get("title", "")
+    author = metadata.get("authors", "")
+    abstract = metadata.get("abstract", "")
+    year = metadata.get("year", "")
+    doi = metadata.get("doi", "")
+    id = metadata.get("id", "")
+    published_in = metadata.get("published_in", "")
+    fields = {
+        "title": title,
+        "author": author,
+        "abstract": abstract,
+        "year": year,
+        "doi": doi,
+        "published_in": published_in,
+        "ENTRYTYPE": "article",
+        "ID": id
+    }
+    db = BibDatabase()
+    writer = BibTexWriter()
+    db.entries.append(fields)
+    export = writer.write(db)
+    result = {
+        "format": "bibtex",
+        "export": export
+    }
+    return result
+
+def parse_published_in(published_in):
+    pass
+
+def transform2ris(metadata):
+    pass
+
+@export_ns.route('/<format>')
+class exportMetadata(Resource):
+
+    def post(self, format):
+        try:
+            metadata = request.json
+            export_ns.logger.debug(metadata)
+            if format == "bibtex":
+                result = transform2bibtex(metadata)
+                headers = {'ContentType': 'application/text'}
+                code = 200
+            elif format == "ris":
+                result = transform2ris(metadata)
+                headers = {'ContentType': 'application/text'}
+                code = 200
+            else: 
+                result = {"status": "error",
+                        "reason": "output format not recognized, must bei either bibtex or ris"}
+                code = 400
+            export_ns.logger.debug(result)
+            headers = {'ContentType': 'application/json'}
+            return make_response(jsonify(result),
+                                code,
+                                headers)
+        except Exception as e:
+            export_ns.logger.error(e)
+            result = {'success': False, 'reason': e}
+            headers = {'ContentType': 'application/json'}
+            return make_response(jsonify(result),
+                                    500,
+                                    headers)
+
+
+@export_ns.route('/service_version')
+class ServiceVersion(Resource):
+    def get(self):
+        result = {"service_version": os.getenv("SERVICE_VERSION")}
+        return make_response(result, 200, {"Content-Type": "application/json"})
+
+@export_ns.route('/healthcheck')
+class Healthcheck(Resource):
+    def get(self):
+        result = {"status": "I'm good"}
+        return make_response(result, 200, {"Content-Type": "application/json"})
diff --git a/server/workers/api/src/app.py b/server/workers/api/src/app.py
@@ -11,6 +11,7 @@
 from apis.pubmed import pubmed_ns
 from apis.openaire import openaire_ns
 from apis.create_vis import vis_ns
+from apis.export import export_ns
 
 from utils.monkeypatches import ReverseProxied, __schema__, specs_url, _register_apidoc
 import logging
@@ -47,6 +48,7 @@ def api_patches(app):
 api.add_namespace(pubmed_ns, path='/pubmed')
 api.add_namespace(openaire_ns, path='/openaire')
 api.add_namespace(vis_ns, path='/vis')
+api.add_namespace(export_ns, path='/export')
 
 app.logger.debug(app.config)
 app.logger.debug(app.url_map)
