Add argument to make_codebase_resource to make the created CodebaseResource path relative to the project work path rather than the project codebase path

scanpipe/models.py

@@ -21,6 +21,7 @@
 # Visit https://github.com/nexB/scancode.io for support and download.
 
 import inspect
+import itertools
 import json
 import logging
 import re
@@ -73,6 +74,9 @@
 scanpipe_app = apps.get_app_config("scanpipe")
 
 
+ROOT_SYMBOL = "."
+
+
 class RunInProgressError(Exception):
     """Run are in progress or queued on this project."""
 
@@ -672,9 +676,10 @@ def get_latest_output(self, filename):
 
     def walk_codebase_path(self):
         """
-        Returns all files and directories path of the codebase/ directory recursively.
+        Returns all files and directories path of the codebase/ directory recursively,
+        including the codebase/ directory itself.
         """
-        return self.codebase_path.rglob("*")
+        return itertools.chain((self.codebase_path,), self.codebase_path.rglob("*"))
 
     @cached_property
     def can_add_input(self):
@@ -1372,6 +1377,9 @@ class CodebaseResource(
     """
     A project Codebase Resources are records of its code files and directories.
     Each record is identified by its path under the project workspace.
+
+    If a CodebaseResource has a path of ".", then it is considered the root
+    CodebaseResource of a codebase.
     """
 
     rootfs_path = models.CharField(
@@ -1488,11 +1496,14 @@ def from_db(cls, db, field_names, values):
 
         return new
 
-    def save(self, *args, **kwargs):
+    def save(self, codebase=None, *args, **kwargs):
         """
         Saves the current resource instance.
         Injects policies—if the feature is enabled—when the `licenses` field value is
         changed.
+
+        `codebase` is not used in this context but required for compatibility
+        with the commoncode.resource.Codebase class API.
         """
         if scanpipe_app.policies_enabled:
             loaded_licenses = getattr(self, "loaded_licenses", [])
@@ -1547,6 +1558,16 @@ def is_symlink(self):
         """
         return self.type == self.Type.SYMLINK
 
+    @property
+    def is_root(self):
+        """
+        Returns True, if the resource is the root of the codebase.
+
+        We consider the root resource of the codebase to be the resource whose
+        path is equal to ROOT_SYMBOL.
+        """
+        return self.path == ROOT_SYMBOL
+
     def compute_compliance_alert(self):
         """
         Computes and returns the compliance_alert value from the `licenses` policies.
@@ -1587,8 +1608,21 @@ def descendants(self):
         Returns a QuerySet of descendant CodebaseResource objects using a
         database query on the current CodebaseResource `path`.
         The current CodebaseResource is not included.
+
+        In the case where we are at the root CodebaseResource of a codebase, we
+        return all CodebaseResources, excluding the root CodebaseResource, whose
+        path is equal to ROOT_SYMBOL.
         """
-        return self.project.codebaseresources.filter(path__startswith=f"{self.path}/")
+        if self.is_root:
+            # We use a different query in the case we are at the root
+            # CodebaseResource because its path is equal to ROOT_SYMBOL, and no
+            # other CodebaseResource start with ROOT_SYMBOL. Using the other query
+            # would result in no CodebaseResources being returned.
+            return self.project.codebaseresources.exclude(path=ROOT_SYMBOL)
+        else:
+            return self.project.codebaseresources.filter(
+                path__startswith=f"{self.path}/"
+            )
 
     def children(self, codebase=None):
         """
@@ -1600,10 +1634,18 @@ def children(self, codebase=None):
         https://github.com/nexB/commoncode/blob/main/src/commoncode/resource.py
 
         `codebase` is not used in this context but required for compatibility
-        with the commoncode.resource.VirtualCodebase class API.
-        """
-        exactly_one_sub_directory = "[^/]+$"
-        children_regex = rf"^{self.path}/{exactly_one_sub_directory}"
+        with the commoncode.resource.Codebase class API.
+        """
+        if self.is_root:
+            # The root CodebaseResource has a path of ROOT_SYMBOL, and no other
+            # CodebaseResource paths starts with ROOT_SYMBOL. Because of this,
+            # we cannot use the path value of the root as part of the query, as
+            # no other CodebaseResources would be found.
+            unnested_file_or_directory = "^[^/]+$"
+            children_regex = rf"{unnested_file_or_directory}"
+        else:
+            exactly_one_sub_directory = "[^/]+$"
+            children_regex = rf"^{self.path}/{exactly_one_sub_directory}"
         return (
             self.descendants()
             .filter(path__regex=children_regex)

scanpipe/pipes/__init__.py

@@ -29,6 +29,7 @@
 
 from django.db.models import Count
 
+from scanpipe.models import ROOT_SYMBOL
 from scanpipe.models import CodebaseResource
 from scanpipe.models import DiscoveredPackage
 from scanpipe.pipes import scancode
@@ -61,10 +62,22 @@ def make_codebase_resource(project, location, **extra_fields):
     If a CodebaseResource already exists in the `project` with the same path,
     the error raised on save() is not stored in the database and the creation is
     skipped.
+
+    If `location` is the same as `project.codebase_path`, then the CodebaseResource
+    created will have a name of ".", and a path of ".".
     """
-    relative_path = Path(location).relative_to(project.codebase_path)
+    location_path = Path(location)
+    relative_path = location_path.relative_to(project.codebase_path)
     resource_data = scancode.get_resource_info(location=location)
 
+    if location_path == project.codebase_path:
+        # If we are making a CodebaseResource for the project codebase/
+        # directory, `relative_path` will be ROOT_SYMBOL. However, when we scan
+        # `location`, the `name` field will be "codebase". We have to overwrite
+        # the `name` field with ROOT_SYMBOL to be consistant with
+        # `relative_path`
+        resource_data["name"] = ROOT_SYMBOL
+
     if extra_fields:
         resource_data.update(**extra_fields)
 

scanpipe/pipes/codebase.py

@@ -22,6 +22,7 @@
 
 from django.core.exceptions import ObjectDoesNotExist
 
+from scanpipe.models import ROOT_SYMBOL
 from scanpipe.models import Project
 
 
@@ -70,7 +71,7 @@ def __init__(self, project):
     @property
     def root(self):
         try:
-            return self.project.codebaseresources.get(path="codebase")
+            return self.project.codebaseresources.get(path=ROOT_SYMBOL)
         except ObjectDoesNotExist:
             raise AttributeError("Codebase root cannot be determined.")
 

scanpipe/pipes/scancode.py

@@ -369,7 +369,7 @@ def create_codebase_resources(project, scanned_codebase):
     CodebaseResource objects as the existing objects (based on the `path`) will be
     skipped.
     """
-    for scanned_resource in scanned_codebase.walk(skip_root=True):
+    for scanned_resource in scanned_codebase.walk():
         resource_data = {}
 
         for field in CodebaseResource._meta.fields:
@@ -383,7 +383,14 @@ def create_codebase_resources(project, scanned_codebase):
 
         resource_type = "FILE" if scanned_resource.is_file else "DIRECTORY"
         resource_data["type"] = CodebaseResource.Type[resource_type]
-        resource_path = scanned_resource.get_path(strip_root=True)
+
+        if scanned_resource.is_root:
+            # In ScanCode.io, we represent the root CodebaseResource using "."
+            # as its name and path
+            resource_path = "."
+            resource_data["name"] = "."
+        else:
+            resource_path = scanned_resource.get_path(strip_root=True)
 
         codebase_resource, _ = CodebaseResource.objects.get_or_create(
             project=project,
@@ -494,6 +501,21 @@ def make_results_summary(project, scan_results_location):
     return summary
 
 
+def replace_root_path_and_name(scanned_codebase):
+    """
+    Set the name and path of the root Resource of `scanned_codebase` to "."
+    and strip the root prefix from the paths of the remaining Resources.
+    """
+    for scanned_resource in scanned_codebase.walk():
+        if scanned_resource.is_root:
+            scanned_resource.path = "."
+            scanned_resource.name = "."
+        else:
+            scanned_resource.path = scanned_resource.get_path(strip_root=True)
+        scanned_resource.save(scanned_codebase)
+    return scanned_codebase
+
+
 def create_inventory_from_scan(project, input_location):
     """
     Create CodebaseResource and DiscoveredPackage instances loaded from the scan