From de489d3c604727946202d49a3960c83cd3961193 Mon Sep 17 00:00:00 2001
From: Nick Sweeting <github@sweeting.me>
Date: Mon, 3 Jun 2024 04:00:18 -0700
Subject: [PATCH] minor snapshot details ui fixes and migrations log msg
 improvements

---
 .../core/migrations/0024_auto_20240513_1143.py     |  3 +++
 archivebox/core/views.py                           | 14 ++++++++------
 archivebox/templates/core/snapshot_live.html       | 14 +++++++-------
 3 files changed, 18 insertions(+), 13 deletions(-)

diff --git a/archivebox/core/migrations/0024_auto_20240513_1143.py b/archivebox/core/migrations/0024_auto_20240513_1143.py
index 31f1e773..95652a07 100644
--- a/archivebox/core/migrations/0024_auto_20240513_1143.py
+++ b/archivebox/core/migrations/0024_auto_20240513_1143.py
@@ -47,12 +47,14 @@ def calculate_abid(self):
 
 
 def copy_snapshot_uuids(apps, schema_editor):
+    print('   Copying snapshot.id -> snapshot.uuid...')
     Snapshot = apps.get_model("core", "Snapshot")
     for snapshot in Snapshot.objects.all():
         snapshot.uuid = snapshot.id
         snapshot.save(update_fields=["uuid"])
 
 def generate_snapshot_abids(apps, schema_editor):
+    print('   Generating snapshot.abid values...')
     Snapshot = apps.get_model("core", "Snapshot")
     for snapshot in Snapshot.objects.all():
         snapshot.abid_prefix = 'snp_'
@@ -65,6 +67,7 @@ def generate_snapshot_abids(apps, schema_editor):
         snapshot.save(update_fields=["abid"])
 
 def generate_archiveresult_abids(apps, schema_editor):
+    print('   Generating ArchiveResult.abid values... (may take an hour or longer for large collections...)')
     ArchiveResult = apps.get_model("core", "ArchiveResult")
     Snapshot = apps.get_model("core", "Snapshot")
     for result in ArchiveResult.objects.all():
diff --git a/archivebox/core/views.py b/archivebox/core/views.py
index efaca2f5..3b491b8e 100644
--- a/archivebox/core/views.py
+++ b/archivebox/core/views.py
@@ -90,7 +90,7 @@ class SnapshotView(View):
                 archiveresults[result.extractor] = result_info
 
         existing_files = {result['path'] for result in archiveresults.values()}
-        min_size_threshold = 128  # bytes
+        min_size_threshold = 10_000  # bytes
         allowed_extensions = {
             'txt',
             'html',
@@ -108,12 +108,14 @@ class SnapshotView(View):
             'md',
         }
 
+
         # iterate through all the files in the snapshot dir and add the biggest ones to the result list
-        for result_file in Path(snapshot.link_dir).glob('*/*/*'):
+        snap_dir = Path(snapshot.link_dir)
+        for result_file in (*snap_dir.glob('*'), *snap_dir.glob('*/*')):
             extension = result_file.suffix.lstrip('.').lower()
             if result_file.is_dir() or result_file.name.startswith('.') or extension not in allowed_extensions:
                 continue
-            if result_file.name in existing_files:
+            if result_file.name in existing_files or result_file.name == 'index.html':
                 continue
 
             file_size = result_file.stat().st_size or 0
@@ -121,7 +123,7 @@ class SnapshotView(View):
             if file_size > min_size_threshold:
                 archiveresults[result_file.name] = {
                     'name': result_file.stem,
-                    'path': result_file.relative_to(snapshot.link_dir),
+                    'path': result_file.relative_to(snap_dir),
                     'ts': ts_to_date_str(result_file.stat().st_mtime or 0),
                     'size': file_size,
                 }
@@ -140,7 +142,7 @@ class SnapshotView(View):
         link_info = link._asdict(extended=True)
 
         try:
-            warc_path = 'warc/' + list(Path(snapshot.link_dir).glob('warc/*.warc.*'))[0].name
+            warc_path = 'warc/' + list(Path(snap_dir).glob('warc/*.warc.*'))[0].name
         except IndexError:
             warc_path = 'warc/'
 
@@ -160,7 +162,7 @@ class SnapshotView(View):
             'warc_path': warc_path,
             'SAVE_ARCHIVE_DOT_ORG': SAVE_ARCHIVE_DOT_ORG,
             'PREVIEW_ORIGINALS': PREVIEW_ORIGINALS,
-            'archiveresults': sorted(archiveresults.values(), key=lambda r: all_types.index(r['name'])),
+            'archiveresults': sorted(archiveresults.values(), key=lambda r: all_types.index(r['name']) if r['name'] in all_types else -r['size']),
             'best_result': best_result,
             # 'tags_str': 'somealskejrewlkrjwer,werlmwrwlekrjewlkrjwer324m532l,4m32,23m324234',
         }
diff --git a/archivebox/templates/core/snapshot_live.html b/archivebox/templates/core/snapshot_live.html
index 32957516..73af92a5 100644
--- a/archivebox/templates/core/snapshot_live.html
+++ b/archivebox/templates/core/snapshot_live.html
@@ -401,13 +401,13 @@
                         <div class="col-lg-2">
                             <div class="card {% if forloop.first %}selected-card{% endif %}">
                                 <div class="card-body">
-                                    <a href="{{result.path}}" target="preview" title="./{{result.path}} (downloaded {{result.ts}})">
-                                        <h4>{{result.name}} <small>({{result.size|filesizeformat}})</small></h4>
+                                    <a href="{{result.path|urlencode}}" target="preview" title="./{{result.path}} (downloaded {{result.ts}})">
+                                        <h4>{{result.name|truncatechars:24}} <small>({{result.size|filesizeformat}})</small></h4>
                                         <!-- <p class="card-text" ><code>./{{result.path|truncatechars:30}}</code></p> -->
                                     </a>
                                     <!--<a href="{{result.path}}" target="preview"><h4 class="card-title">{{result.name}}</h4></a>-->
                                 </div>
-                                <iframe class="card-img-top" src="{{result.path}}" sandbox="allow-same-origin allow-top-navigation-by-user-activation allow-scripts allow-forms" scrolling="no" loading="lazy"></iframe>
+                                <iframe class="card-img-top" src="{{result.path|urlencode}}?autoplay=0" allow="autoplay 'none'; fullscreen 'none'; navigation-override 'none'; " sandbox="allow-same-origin allow-top-navigation-by-user-activation allow-scripts allow-forms" scrolling="no" loading="lazy"></iframe>
                             </div>
                         </div>
                     {% endfor %}
@@ -419,7 +419,7 @@
                                 <a href="./" target="preview">
                                     <h4>Headers, JSON, etc.</h4>
                                 </a>
-                                <!--<a href="{{result.path}}" target="preview"><h4 class="card-title">{{result.name}}</h4></a>-->
+                                <!--<a href="{{result.path|urlencode}}" target="preview"><h4 class="card-title">{{result.name}}</h4></a>-->
                             </div>
                             <iframe class="card-img-top" src="./" sandbox="" scrolling="no" loading="lazy"></iframe>
                         </div>
@@ -430,7 +430,7 @@
 
 
 
-        <iframe id="main-frame" sandbox="allow-same-origin allow-top-navigation-by-user-activation allow-scripts allow-forms" class="full-page-iframe" src="{{best_result.path}}" name="preview"></iframe>
+        <iframe id="main-frame" sandbox="allow-same-origin allow-top-navigation-by-user-activation allow-scripts allow-forms" class="full-page-iframe" src="{{best_result.path|urlencode}}" name="preview"></iframe>
     
 
 
@@ -444,9 +444,9 @@
                     this.src = this.src + '#toolbar=0'
                 }
                 this.onload = function() {
-                    if (this.src.endsWith('.pdf')) {
+                    if (this.src.includes('.pdf')) {
                         this.removeAttribute('sandbox')
-                        this.src = this.src + '#toolbar=0'
+                        this.src = this.src.split('?autoplay=')[0] + '#toolbar=0'
                     }
                     try {
                         // doesnt work if frame origin rules prevent accessing its DOM via JS