Make file analysis actually async and surface status in the UI

kaplancloudapp/models.py

@@ -456,7 +456,7 @@ def get_absolute_url(self):
     def save(self, *args, **kwargs):
         super().save(*args, **kwargs)
         if self.status == 1:
-            NewProjectReportThread(self).run()
+            NewProjectReportThread(self).start()
 
 
 class Segment(models.Model):

kaplancloudapp/static/project.js

@@ -1,10 +1,25 @@
+const REPORT_STATUS_LABELS = {
+  0: 'Blank',
+  1: 'Ready for Processing',
+  2: 'Processing',
+  3: 'Complete',
+};
+
 window.onload = function() {
   const assignLinguistForm = document.getElementById('assign-linguist-form').children[0];
   const checkboxMain = document.getElementById('checkbox-main');
   const contextMenu = document.getElementById('context-menu');
 
   let filesList = [];
 
+  document.querySelectorAll('#reports-body tr').forEach(row => {
+    const status = parseInt(row.dataset.status, 10);
+    if (status < 3) {
+      const uuid = row.id.replace(/^report-/, '');
+      checkReport(uuid);
+    }
+  });
+
   checkboxMain.onclick = function() {
     [...document.getElementsByClassName('checkbox')].forEach((item, i) => {
       item.checked = checkboxMain.checked;
@@ -139,13 +154,47 @@ function analyzeFiles(fileUuids)
     )
     .then(response => response.json())
     .then(data => {
+      addReportRow(data['uuid']);
       checkReport(data['uuid']);
     })
     .catch(error => {
       console.error(error);
     })
 }
 
+function addReportRow(reportUuid)
+{
+  const tbody = document.getElementById('reports-body');
+  const row = document.createElement('tr');
+  row.id = 'report-' + reportUuid;
+  row.dataset.status = '1';
+  row.className = 'hover:bg-base-200/30 transition-colors';
+  const href = '/report/' + reportUuid;
+  row.innerHTML = `
+    <td><a href="${href}" target="_blank" class="link link-hover">Just now</a></td>
+    <td><span class="badge badge-sm badge-ghost report-status">${REPORT_STATUS_LABELS[1]}</span></td>
+    <td>
+      <a href="${href}" target="_blank" class="btn btn-ghost btn-xs btn-square" aria-label="Open">
+        <svg xmlns="http://www.w3.org/2000/svg" class="w-4 h-4" fill="none" viewBox="0 0 24 24" stroke-width="1.5" stroke="currentColor" aria-hidden="true">
+          <path stroke-linecap="round" stroke-linejoin="round" d="M8.25 4.5l7.5 7.5-7.5 7.5" />
+        </svg>
+      </a>
+    </td>
+  `;
+  tbody.prepend(row);
+}
+
+function setReportStatus(reportUuid, status)
+{
+  const row = document.getElementById('report-' + reportUuid);
+  if (!row) return;
+  row.dataset.status = String(status);
+  const badge = row.querySelector('.report-status');
+  if (badge && REPORT_STATUS_LABELS[status] !== undefined) {
+    badge.textContent = REPORT_STATUS_LABELS[status];
+  }
+}
+
 function checkReport(reportUuid)
 {
   var url = new URL(window.location.origin + '/report/' + reportUuid);
@@ -156,14 +205,11 @@ function checkReport(reportUuid)
   .then(response => response.json())
   .then(data =>
     {
-      if (data['status'] == 1 || data['status'] == 2)
+      setReportStatus(reportUuid, data['status']);
+      if (data['status'] < 3)
       {
         setTimeout(checkReport, 5000, reportUuid);
       }
-      else
-      {
-        document.getElementById('report-toast').classList.add('show')
-      }
     }
   )
 }

kaplancloudapp/templates/project.html

@@ -6,8 +6,6 @@
   .modal-overlay { display: none; position: fixed; inset: 0; z-index: 50; align-items: center; justify-content: center; background: rgb(0 0 0 / 0.5); }
   .modal-overlay.show { display: flex; }
   #context-menu { display: none; }
-  #report-toast { display: none; }
-  #report-toast.show { display: flex; }
 </style>
 {% endblock %}
 
@@ -121,17 +119,36 @@ <h2 class="text-base font-semibold mb-3">Reference</h2>
     {# ── Reports section ── #}
     <section>
       <h2 class="text-base font-semibold mb-3">Reports</h2>
-      {% if reports %}
-      <ul class="space-y-1">
-        {% for report in reports %}
-        <li>
-          <a href="{% url 'report' report.uuid %}" target="_blank" class="link link-hover text-sm">{{ report.created_at }}</a>
-        </li>
-        {% endfor %}
-      </ul>
-      {% else %}
-      <p class="text-sm text-base-content/40">No reports yet.</p>
-      {% endif %}
+      <div class="overflow-x-auto rounded-lg border border-base-300">
+        <table class="table table-sm">
+          <thead>
+            <tr class="bg-base-200/50">
+              <th scope="col">Created</th>
+              <th scope="col">Status</th>
+              <th scope="col"></th>
+            </tr>
+          </thead>
+          <tbody id="reports-body">
+            {% for report in reports %}
+            <tr id="report-{{ report.uuid }}" data-status="{{ report.status }}" class="hover:bg-base-200/30 transition-colors">
+              <td>
+                <a href="{% url 'report' report.uuid %}" target="_blank" class="link link-hover">{{ report.created_at }}</a>
+              </td>
+              <td>
+                <span class="badge badge-sm badge-ghost report-status">{{ report.get_status_display }}</span>
+              </td>
+              <td>
+                <a href="{% url 'report' report.uuid %}" target="_blank" class="btn btn-ghost btn-xs btn-square" aria-label="Open">
+                  <svg xmlns="http://www.w3.org/2000/svg" class="w-4 h-4" fill="none" viewBox="0 0 24 24" stroke-width="1.5" stroke="currentColor" aria-hidden="true">
+                    <path stroke-linecap="round" stroke-linejoin="round" d="M8.25 4.5l7.5 7.5-7.5 7.5" />
+                  </svg>
+                </a>
+              </td>
+            </tr>
+            {% endfor %}
+          </tbody>
+        </table>
+      </div>
     </section>
   </div>
 </div>
@@ -199,13 +216,5 @@ <h3 class="text-lg font-semibold">Import Package</h3>
 </div>
 {% endif %}
 
-{# ── Report toast ── #}
-<div id="report-toast" class="fixed bottom-4 right-4 z-50 items-center gap-3 bg-base-100 border border-base-300 rounded-lg shadow-lg px-4 py-3 text-sm">
-  <svg xmlns="http://www.w3.org/2000/svg" class="w-5 h-5 text-success shrink-0" fill="none" viewBox="0 0 24 24" stroke-width="1.5" stroke="currentColor" aria-hidden="true">
-    <path stroke-linecap="round" stroke-linejoin="round" d="M9 12.75L11.25 15 15 9.75M21 12a9 9 0 11-18 0 9 9 0 0118 0z" />
-  </svg>
-  <p>Your report is ready. Please refresh this page to see it listed.</p>
-</div>
-
 {% csrf_token %}
 {% endblock %}

kaplancloudapp/templates/report.html

@@ -2,11 +2,13 @@
 {% block title %}Report | {{ project.name }} | Kaplan Cloud{% endblock %}
 
 {% block navbar_center %}
-<ul class="breadcrumb text-sm">
-  <li><a href="{% url 'projects' %}" class="link link-hover">Projects</a></li>
-  <li><a href="{% url 'project' project.uuid %}" class="link link-hover">{{ project.name }}</a></li>
-  <li>Report — {{ report.created_at|date:"N j, Y, P" }}</li>
-</ul>
+<div class="text-sm breadcrumbs">
+  <ul>
+    <li><a href="{% url 'projects' %}" class="text-base-content/60 hover:text-base-content">Projects</a></li>
+    <li><a href="{% url 'project' project.uuid %}" class="text-base-content/60 hover:text-base-content">{{ project.name }}</a></li>
+    <li class="font-semibold">Report — {{ report.created_at|date:"N j, Y, P" }}</li>
+  </ul>
+</div>
 {% endblock %}
 
 {% block div %}

kaplancloudapp/tests.py

@@ -442,14 +442,14 @@ def test_ordering_newest_first(self):
 
     @patch("kaplancloudapp.models.NewProjectReportThread")
     def test_save_with_status_1_triggers_thread(self, mock_thread):
-        mock_thread.return_value.run = MagicMock()
+        mock_thread.return_value.start = MagicMock()
         report = ProjectReport.objects.create(
             project=self.project, content={"s": "processing"}
         )
         report.status = 1
         report.save()
         mock_thread.assert_called_once()
-        mock_thread.return_value.run.assert_called_once()
+        mock_thread.return_value.start.assert_called_once()
 
 
 # ===========================================================================

kaplancloudapp/thread_classes.py

@@ -5,6 +5,7 @@
 
 import regex
 from django.apps import apps
+from django.db import connection
 from kaplan import open_bilingualfile
 from kaplan.kdb import KDB
 from kaplan.kxliff import KXLIFF
@@ -257,32 +258,20 @@ def __init__(self, projectreport_instance, **kwargs):
         super(NewProjectReportThread, self).__init__(**kwargs)
 
     def run(self):
-        instance = self.projectreport_instance
-
-        for project_file in instance.project_files.all():
-            if project_file.status == 1:
-                project_file.status = 2
-                project_file.save()
-
-        SegmentModel = apps.get_model("kaplancloudapp", "Segment")
-
-        entries = []
-
-        project_report = {}
-        project_total = {
-            "Repetitions": 0,
-            "100": 0,  # TODO
-            "95": 0,
-            "85": 0,
-            "75": 0,
-            "50": 0,
-            "New": 0,
-            "Total": 0,
-        }
-
-        sm = difflib.SequenceMatcher()
-        for project_file in instance.project_files.all():
-            file_report = {
+        try:
+            instance = self.projectreport_instance
+
+            for project_file in instance.project_files.all():
+                if project_file.status == 1:
+                    project_file.status = 2
+                    project_file.save()
+
+            SegmentModel = apps.get_model("kaplancloudapp", "Segment")
+
+            entries = []
+
+            project_report = {}
+            project_total = {
                 "Repetitions": 0,
                 "100": 0,  # TODO
                 "95": 0,
@@ -293,66 +282,83 @@ def run(self):
                 "Total": 0,
             }
 
-            for segment in SegmentModel.objects.filter(file=project_file):
-                source_segment = etree.fromstring(
-                    "<source>" + segment.source + "</source>"
-                )
-                source_entry, _ = KDB.segment_to_entry(source_segment)
-                word_count = len(source_entry.split())
-                char_count = len(source_entry)
+            sm = difflib.SequenceMatcher()
+            for project_file in instance.project_files.all():
+                file_report = {
+                    "Repetitions": 0,
+                    "100": 0,  # TODO
+                    "95": 0,
+                    "85": 0,
+                    "75": 0,
+                    "50": 0,
+                    "New": 0,
+                    "Total": 0,
+                }
+
+                for segment in SegmentModel.objects.filter(file=project_file):
+                    source_segment = etree.fromstring(
+                        "<source>" + segment.source + "</source>"
+                    )
+                    source_entry, _ = KDB.segment_to_entry(source_segment)
+                    word_count = len(source_entry.split())
+                    char_count = len(source_entry)
 
-                if source_entry in entries:
-                    file_report["Repetitions"] += word_count
-                # elif entry in project_tm_entries TODO
-                else:
-                    sm.set_seq2(source_entry)
-
-                    highest_match = 0.0
-                    for entry in filter(
-                        lambda x: len(x) >= char_count / 2 and len(x) <= char_count * 2,
-                        entries,
-                    ):
-                        sm.set_seq1(entry)
-                        highest_match = max(sm.ratio(), highest_match)
-                        if highest_match >= 0.95:
-                            break
-
-                    if highest_match >= 0.95:
-                        file_report["95"] += word_count
-                    elif highest_match >= 0.85:
-                        file_report["85"] += word_count
-                    elif highest_match >= 0.75:
-                        file_report["75"] += word_count
-                    elif highest_match >= 0.5:
-                        file_report["50"] += word_count
+                    if source_entry in entries:
+                        file_report["Repetitions"] += word_count
+                    # elif entry in project_tm_entries TODO
                     else:
-                        file_report["New"] += word_count
+                        sm.set_seq2(source_entry)
+
+                        highest_match = 0.0
+                        for entry in filter(
+                            lambda x: (
+                                len(x) >= char_count / 2 and len(x) <= char_count * 2
+                            ),
+                            entries,
+                        ):
+                            sm.set_seq1(entry)
+                            highest_match = max(sm.ratio(), highest_match)
+                            if highest_match >= 0.95:
+                                break
 
-                    entries.append(source_entry)
+                        if highest_match >= 0.95:
+                            file_report["95"] += word_count
+                        elif highest_match >= 0.85:
+                            file_report["85"] += word_count
+                        elif highest_match >= 0.75:
+                            file_report["75"] += word_count
+                        elif highest_match >= 0.5:
+                            file_report["50"] += word_count
+                        else:
+                            file_report["New"] += word_count
+
+                        entries.append(source_entry)
 
-                file_report["Total"] += word_count
+                    file_report["Total"] += word_count
 
-            project_total["Repetitions"] += file_report["Repetitions"]
-            project_total["100"] += file_report["100"]
-            project_total["95"] += file_report["95"]
-            project_total["85"] += file_report["85"]
-            project_total["75"] += file_report["75"]
-            project_total["50"] += file_report["50"]
-            project_total["New"] += file_report["New"]
-            project_total["Total"] += file_report["Total"]
+                project_total["Repetitions"] += file_report["Repetitions"]
+                project_total["100"] += file_report["100"]
+                project_total["95"] += file_report["95"]
+                project_total["85"] += file_report["85"]
+                project_total["75"] += file_report["75"]
+                project_total["50"] += file_report["50"]
+                project_total["New"] += file_report["New"]
+                project_total["Total"] += file_report["Total"]
 
-            project_report[project_file.name] = file_report
+                project_report[project_file.name] = file_report
 
-        project_report["Total"] = project_total
+            project_report["Total"] = project_total
 
-        instance.content = project_report
-        instance.status = 3
-        instance.save()
+            instance.content = project_report
+            instance.status = 3
+            instance.save()
 
-        for project_file in instance.project_files.all():
-            if project_file.status == 2:
-                project_file.status = 3
-                project_file.save()
+            for project_file in instance.project_files.all():
+                if project_file.status == 2:
+                    project_file.status = 3
+                    project_file.save()
+        finally:
+            connection.close()
 
 
 class TMImportThread(threading.Thread):