Add duplicates and tube_ids feature

qiita_pet/handlers/admin_processing_job.py

@@ -16,6 +16,7 @@
 from qiita_db.study import Study
 
 from json import dumps
+from collections import Counter
 
 
 class AdminProcessingJobBaseClass(BaseHandler):
@@ -105,28 +106,64 @@ def get(self):
 
     @execute_as_transaction
     def post(self):
-
-        # Get user-inputted qiita id and sample names
+        # Get user-inputted qiita id and sample names / tube_ids
         qid = self.get_argument("qid")
         snames = self.get_argument("snames").split()
 
+        # Get study give qiita id
+        study = Study(qid).sample_template
+
         # Stripping leading qiita id from sample names
         # Example: 1.SKB1.640202 -> SKB1.640202
-        qsnames = list(Study(qid).sample_template)
+        qsnames = list(study)
         for i, qsname in enumerate(qsnames):
             if qsname.startswith(qid):
                 qsnames[i] = qsname.replace(f'{qid}.', "", 1)
 
+        # Creates a way to access a tube_id by its corresponding sample name
+        # and vice versa, which is important to adding tube_id in parentheses
+        # after a sample name a few lines later
+        tube_ids_lookup = dict()
+        tube_ids_rev = dict()
+        tube_ids = set()
+        if "anonymized_name" in study.categories:
+            for qsname, tid in study.get_category("anonymized_name").items():
+                formatted_name = qsname
+                if qsname.startswith(qid):
+                    formatted_name = qsname.replace(f'{qid}.', "", 1)
+
+                tube_ids.add(tid)
+                tube_ids_lookup[formatted_name] = tid
+                tube_ids_rev[tid] = formatted_name
+
+        # Adds tube ids after sample name in parentheses
+        if len(tube_ids) > 0:
+            for i, sname in enumerate(snames):
+                if sname in qsnames:
+                    snames[i] = f'{sname} ({tube_ids_lookup[sname]})'
+                elif sname in tube_ids:
+                    snames[i] = f'{tube_ids_rev[sname]} ({sname})'
+
+        # Finds duplicates in the samples
+        seen = Counter()
+        for sample in snames:
+            seen[sample] += 1
+        duplicates = [f'{s} \u00D7 {seen[s]}' for s in seen if seen[s] > 1]
+
         # Remove blank samples from sample names
-        blank = [x for x in snames if x.lower().startswith('blank')]
+        blank = set([x for x in snames if x.lower().startswith('blank')])
         snames = [x for x in snames if 'blank' not in x.lower()]
 
         # Validate user's sample names against qiita study
-        qsnames = set(qsnames)
+        if len(tube_ids) == 0:
+            qsnames = set(qsnames)
+        else:
+            qsnames = set([f'{x} ({tube_ids_lookup[x]})' for x in qsnames])
         snames = set(snames)
         matching = qsnames.intersection(snames)
         missing = qsnames.difference(snames)
         extra = snames.difference(qsnames)
 
         self.render("sample_validation.html", input=False, matching=matching,
-                    missing=missing, extra=extra, blank=blank)
+                    missing=missing, extra=extra, blank=blank,
+                    duplicates=duplicates)

qiita_pet/templates/sample_validation.html

@@ -3,7 +3,7 @@
 <style>
     .column {
     float: left;
-    width: 25%;
+    width: 20%;
     }
 
     .row:after {
@@ -49,6 +49,14 @@ <h2>Blank</h2>
             {% end %}
         </ul>
     </div>
+    <div class="column">
+        <h2>Duplicates</h2>
+        <ul>
+            {% for sample in duplicates %}
+            <li>{{ sample }}</li>
+            {% end %}
+        </ul>
+    </div>
     <div class="column">
         <h2>Extra</h2>
         <ul>