Store extension in CodebaseResource.name #467 (#493)

* Create migration on CodebaseResource to append extension to name, if name does not end with extension
    * Update exptected test results

Signed-off-by: Jono Yang <[email protected]>

Author: JonoYang

CHANGELOG.rst

@@ -73,6 +73,14 @@ v31.0.0 (next)
   to any filters.
   https://github.com/nexB/scancode.io/issues/296
 
+- CodebaseResource.name now contains both the bare file name with extension, as
+  opposed to just the bare file name without extension.
+
+  - Using a name stripped from its extension was something that was not used in
+    other AboutCode project or tools.
+
+  https://github.com/nexB/scancode.io/issues/467
+
 v30.2.0 (2021-12-17)
 --------------------
 

scanpipe/migrations/0019_auto_20220804_1836.py

@@ -0,0 +1,25 @@
+# Generated by Django 4.0.6 on 2022-08-04 18:36
+
+from django.db import migrations
+from django.db.models import F, Q
+from django.db.models.functions import Concat
+
+
+def concat_codebaseresource_name_and_extension(apps, schema_editor):
+    CodebaseResource = apps.get_model('scanpipe', 'CodebaseResource')
+    qs = CodebaseResource.objects.filter(
+        Q(extension__isnull=False)  # Has an "extension" value
+        & ~Q(name__endswith=F("extension"))  # "name" do not ends with the "extension"
+    )
+    qs.update(name=Concat(F("name"), F("extension")))
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('scanpipe', '0018_codebaseresource_tag'),
+    ]
+
+    operations = [
+        migrations.RunPython(concat_codebaseresource_name_and_extension),
+    ]

scanpipe/migrations/0020_alter_codebaseresource_name.py

@@ -0,0 +1,18 @@
+# Generated by Django 4.0.6 on 2022-08-09 17:08
+
+from django.db import migrations, models
+
+
+class Migration(migrations.Migration):
+
+    dependencies = [
+        ('scanpipe', '0019_auto_20220804_1836'),
+    ]
+
+    operations = [
+        migrations.AlterField(
+            model_name='codebaseresource',
+            name='name',
+            field=models.CharField(blank=True, help_text='File or directory name of this resource with its extension.', max_length=255),
+        ),
+    ]

scanpipe/models.py

@@ -1412,7 +1412,7 @@ class Type(models.TextChoices):
     name = models.CharField(
         max_length=255,
         blank=True,
-        help_text=_("File or directory name of this resource."),
+        help_text=_("File or directory name of this resource with its extension."),
     )
     extension = models.CharField(
         max_length=100,

scanpipe/pipes/scancode.py

@@ -136,7 +136,7 @@ def get_resource_info(location):
     file_info.update(
         {
             "type": resource_type,
-            "name": fileutils.file_base_name(location),
+            "name": fileutils.file_name(location),
             "extension": fileutils.file_extension(location),
         }
     )