Merge branch 'main' of github.com:nexB/scancode.io into main

Author: tdruez

CHANGELOG.rst

@@ -22,6 +22,9 @@
   calling XlsxWriter and report and error if the truncated can be truncated.
   https://github.com/nexB/scancode.io/issues/206
 
+- Add support for VMWare Photon-based Docker images and rootfs. This is an RPM-based
+  Linux distribution
+
 ### v21.6.10
 
 - Add support for VM image formats extraction such as VMDK, VDI and QCOW.
@@ -298,4 +301,4 @@
 
 ### v1.0.0 (2020-09-09)
 
-- Initial release
+- Initial release

scanpipe/models.py

@@ -35,6 +35,7 @@
 from django.db.models import Q
 from django.db.models import TextField
 from django.db.models.functions import Cast
+from django.db.models.functions import Lower
 from django.forms import model_to_dict
 from django.urls import reverse
 from django.utils import timezone
@@ -1160,12 +1161,35 @@ def children(self, codebase=None):
         Return a QuerySet of direct children CodebaseResource objects using a
         Database query on this CodebaseResource `path`.
 
+        Paths are returned in lower-cased sorted path order to reflect the
+        behavior of `commoncode.resource.Resource.children()`
+        https://github.com/nexB/commoncode/blob/76a03d9c1cd2a582dcec4351c768c3ef646e1b31/src/commoncode/resource.py#L1199
+
         `codebase` is not used in this context but required for compatibility
         with the commoncode.resource.VirtualCodebase class API.
         """
         exactly_one_sub_directory = "[^/]+$"
         children_regex = rf"^{self.path}/{exactly_one_sub_directory}"
-        return self.descendants().filter(path__regex=children_regex)
+        return (
+            self.descendants()
+            .filter(path__regex=children_regex)
+            .order_by(Lower("path"))
+        )
+
+    def walk(self, topdown=True):
+        """
+        Yield all descendant Resources of this Resource. Does not include self.
+
+        Walk the tree top-down, depth-first if `topdown` is True, otherwise walk
+        bottom-up.
+        """
+        for child in self.children().iterator():
+            if topdown:
+                yield child
+            for subchild in child.walk(topdown=topdown):
+                yield subchild
+            if not topdown:
+                yield child
 
     def get_absolute_url(self):
         return reverse("resource_detail", args=[self.project_id, self.pk])

scanpipe/pipes/codebase.py

@@ -76,8 +76,14 @@ def root(self):
     def resources(self):
         return self.project.codebaseresources.all()
 
-    def walk(self):
-        yield from self.resources.iterator()
+    def walk(self, topdown=True):
+        root = self.root
+        if topdown:
+            yield root
+        for resource in root.walk(topdown=topdown):
+            yield resource
+        if not topdown:
+            yield root
 
     def get_tree(self):
         return get_tree(self.root, fields=["name", "path"])

scanpipe/pipes/rootfs.py

@@ -47,6 +47,7 @@
     "sles": rpm.package_getter,
     "opensuse": rpm.package_getter,
     "opensuse-tumbleweed": rpm.package_getter,
+    "photon": rpm.package_getter,
 }