Get count from arvados

Separate pending/rejected tables

"Lastest results" is latest successful run.

Arvados-DCO-1.1-Signed-off-by: Peter Amstutz <peter.amstutz@curii.com>

3 files changed, 65 insertions, 39 deletions

diff --git a/bh20seqanalyzer/main.py b/bh20seqanalyzer/main.py
index 1746587..ce9a723 100644
--- a/bh20seqanalyzer/main.py
+++ b/bh20seqanalyzer/main.py
@@ -187,14 +187,15 @@ def get_workflow_output_from_project(api, uuid):
     cr = api.container_requests().list(filters=[['owner_uuid', '=', uuid],
                                                 ["requesting_container_uuid", "=", None]]).execute()
     if cr["items"] and cr["items"][0]["output_uuid"]:
-        return cr["items"][0]
-    else:
-        return None
+        container = api.containers().get(uuid=cr["items"][0]["container_uuid"]).execute()
+        if container["state"] == "Complete" and container["exit_code"] == 0:
+            return cr["items"][0]
+    return None
 
 
 def copy_most_recent_result(api, analysis_project, latest_result_uuid):
     most_recent_analysis = api.groups().list(filters=[['owner_uuid', '=', analysis_project]],
-                                                  order="created_at desc", limit=1).execute()
+                                                  order="created_at desc").execute()
     for m in most_recent_analysis["items"]:
         wf = get_workflow_output_from_project(api, m["uuid"])
         if wf:
@@ -220,6 +221,7 @@ def move_fastq_to_fasta_results(api, analysis_project, uploader_project):
                                      body={"owner_uuid": uploader_project}).execute()
             p["properties"]["moved_output"] = True
             api.groups().update(uuid=p["uuid"], body={"properties": p["properties"]}).execute()
+            break
 
 
 def upload_schema(api, workflow_def_project):
diff --git a/bh20simplewebuploader/main.py b/bh20simplewebuploader/main.py
index d602288..d4adbda 100644
--- a/bh20simplewebuploader/main.py
+++ b/bh20simplewebuploader/main.py
@@ -20,6 +20,7 @@ from markupsafe import Markup
 ARVADOS_API = 'lugli.arvadosapi.com'
 ANONYMOUS_TOKEN = '5o42qdxpxp5cj15jqjf7vnxx5xduhm4ret703suuoa3ivfglfh'
 UPLOADER_PROJECT = 'lugli-j7d0g-n5clictpuvwk8aa'
+VALIDATED_PROJECT = 'lugli-j7d0g-5ct8p1i1wrgyjvp'
 
 logging.basicConfig(level=logging.DEBUG)
 log = logging.getLogger(__name__ )
@@ -457,6 +458,47 @@ def download_page():
     buf = get_html_body('doc/web/download.html')
     return render_template('resource.html',menu='DOWNLOAD',embed=buf)
 
+def pending_table(output, items):
+    output.write(
+"""
+<table>
+<tr><th>Collection</th>
+<th>Sequence label</th></tr>
+""")
+    for r in items:
+        if r["status"] != "pending":
+            continue
+        output.write("<tr>")
+        output.write("<td><a href='https://workbench.lugli.arvadosapi.com/collections/%s'>%s</a></td>" % (r["uuid"], r["uuid"]))
+        output.write("<td>%s</td>" % Markup.escape(r["sequence_label"]))
+        output.write("</tr>")
+    output.write(
+"""
+</table>
+""")
+
+def rejected_table(output, items):
+    output.write(
+"""
+<table>
+<tr><th>Collection</th>
+<th>Sequence label</th>
+<th>Errors</th></tr>
+""")
+    for r in items:
+        if r["status"] != "rejected":
+            continue
+        output.write("<tr>")
+        output.write("<td><a href='https://workbench.lugli.arvadosapi.com/collections/%s'>%s</a></td>" % (r["uuid"], r["uuid"]))
+        output.write("<td>%s</td>" % Markup.escape(r["sequence_label"]))
+        output.write("<td><pre>%s</pre></td>" % Markup.escape("\n".join(r.get("errors", []))))
+        output.write("</tr>")
+    output.write(
+"""
+</table>
+""")
+
+
 @app.route('/status')
 def status_page():
     """
@@ -477,27 +519,18 @@ def status_page():
         status[prop["status"]] = status.get(prop["status"], 0) + 1
 
     output = io.StringIO()
-    for s in status:
-        output.write("<p>%s sequences %s QC</p>" % (status[s], s))
-    output.write(
-"""
-<table>
-<tr><th>Collection</th>
-<th>Sequence label</th>
-<th>Status</th>
-<th>Errors</th></tr>
-""")
-    for r in out:
-        output.write("<tr>")
-        output.write("<td><a href='https://workbench.lugli.arvadosapi.com/collections/%s'>%s</a></td>" % (r["uuid"], r["uuid"]))
-        output.write("<td>%s</td>" % Markup.escape(r["sequence_label"]))
-        output.write("<td>%s</td>" % r["status"])
-        output.write("<td><pre>%s</pre></td>" % Markup.escape("\n".join(r.get("errors", []))))
-        output.write("</tr>")
-    output.write(
-"""
-</table>
-""")
+
+    validated = api.collections().list(filters=[["owner_uuid", "=", VALIDATED_PROJECT]], limit=1).execute()
+    status["passed"] = validated["items_available"]
+
+    for s in (("passed", "/download"), ("pending", "#pending"), ("rejected", "#rejected")):
+        output.write("<p><a href='%s'>%s sequences QC %s</a></p>" % (s[1], status.get(s[0], 0), s[0]))
+
+    output.write("<a id='pending'><h1>Pending</h1>")
+    pending_table(output, out)
+
+    output.write("<a id='rejected'><h1>Rejected</h1>")
+    rejected_table(output, out)
 
     return render_template('status.html', table=Markup(output.getvalue()), menu='STATUS')
 
@@ -534,20 +567,10 @@ baseURL='http://sparql.genenetwork.org/sparql/'
 
 @app.route('/api/getCount', methods=['GET'])
 def getCount():
-    query="""
-PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/>
-select (COUNT(distinct ?dataset) as ?num)
-{
-   ?dataset pubseq:submitter ?id .
-   ?id ?p ?submitter
-}
-"""
-    payload = {'query': query, 'format': 'json'}
-    r = requests.get(baseURL, params=payload)
-    result = r.json()['results']['bindings']
-    # [{'num': {'type': 'typed-literal', 'datatype': 'http://www.w3.org/2001/XMLSchema#integer', 'value': '1352'}}]
-    # print(result, file=sys.stderr)
-    return jsonify({'sequences': int(result[0]["num"]["value"])})
+    api = arvados.api(host=ARVADOS_API, token=ANONYMOUS_TOKEN)
+    c = api.collections().list(filters=[["owner_uuid", "=", VALIDATED_PROJECT]], limit=1).execute()
+
+    return jsonify({'sequences': c["items_available"]})
 
 @app.route('/api/getAllaccessions', methods=['GET'])
 def getAllaccessions():
diff --git a/bh20simplewebuploader/templates/resource.html b/bh20simplewebuploader/templates/resource.html
index e0d344f..91b6c20 100644
--- a/bh20simplewebuploader/templates/resource.html
+++ b/bh20simplewebuploader/templates/resource.html
@@ -7,6 +7,7 @@
 
       <div class="status">
 	<p><img src="https://workbench.lugli.arvadosapi.com/collections/lugli-4zz18-z513nlpqm03hpca/relabeledSeqs_dedup_relabeledSeqs_dedup.png" height="300px"></p>
+	<p><a href="https://workbench.lugli.arvadosapi.com/projects/lugli-j7d0g-5ct8p1i1wrgyjvp#Data_collections">All sequences project</a></p>
 	<p><a href="https://workbench.lugli.arvadosapi.com/collections/lugli-4zz18-z513nlpqm03hpca/relabeledSeqs_dedup.fasta">All sequences (FASTA) relabled and deduplicated</a></p>
 	<p><a href="https://workbench.lugli.arvadosapi.com/collections/lugli-4zz18-z513nlpqm03hpca/mergedmetadata.ttl">Metadata (RDF) for all sequences</a></p>
 	<p><a href="https://workbench.lugli.arvadosapi.com/collections/lugli-4zz18-z513nlpqm03hpca/relabeledSeqs_dedup_relabeledSeqs_dedup.gfa">All sequences in Graphical Fragment Assembly (GFA)</a> - <a href="https://github.com/GFA-spec/GFA-spec">More about GFA</a></p>