Make collection of non-existent files more clear

(DIS-962)

Author: pyrco

acquire/collector.py

@@ -341,6 +341,9 @@ def collect_path(
             path = self.target.fs.path(path)
 
         try:
+            # If a path does not exist, is_dir(), is_file() and is_symlink() will return False (and not raise an
+            # exception), so we need to explicitly check for this.
+            exists = self.target.fs.lexists(str(path))
             is_dir = path.is_dir()
             is_file = path.is_file()
             is_symlink = path.is_symlink()
@@ -360,19 +363,23 @@ def collect_path(
             self.report.add_path_failed(module_name, path)
             return
 
-        if is_dir:
-            self.collect_dir(path, seen_paths=seen_paths, module_name=module_name)
-        elif is_file:
-            self.collect_file(path, module_name=module_name)
-        elif is_symlink:
-            log.error(
-                "- Can't collect %s (symlink to %s) in module %s",
-                path,
-                path.get().readlink(),
-                module_name,
-            )
+        if exists:
+            if is_dir:
+                self.collect_dir(path, seen_paths=seen_paths, module_name=module_name)
+            elif is_file:
+                self.collect_file(path, module_name=module_name)
+            elif is_symlink:
+                log.error(
+                    "- Can't collect %s (symlink to %s) in module %s",
+                    path,
+                    path.get().readlink(),
+                    module_name,
+                )
+            else:
+                log.error("- Don't know how to collect %s in module %s", path, module_name)
         else:
-            log.error("- Don't know how to collect %s in module %s", path, module_name)
+            self.report.add_path_missing(module_name, path)
+            log.error("- Path %s is not found", path)
 
     def collect_command_output(
         self,

tests/test_collector.py

@@ -1,7 +1,8 @@
-from unittest.mock import Mock
+from unittest.mock import Mock, patch
 
+import pytest
 from dissect.target import Target
-from dissect.target.filesystem import VirtualFilesystem
+from dissect.target.filesystem import VirtualFile, VirtualFilesystem, VirtualSymlink
 
 from acquire.collector import Collector
 
@@ -23,3 +24,92 @@ def test_collector():
     collector.collect_file("$MFT", module_name="test")
 
     assert not collector.report.was_path_seen(fs_2.get("$MFT"))
+
+
+@pytest.fixture
+def mock_file():
+    return Mock()
+
+
+@pytest.fixture
+def mock_fs(mock_file):
+    fs = VirtualFilesystem(case_sensitive=False)
+    fs.makedirs("/foo/bar")
+    fs.map_file_entry("/foo/bar/some-file", VirtualFile(fs, "some-file", mock_file))
+    fs.map_file_entry("/foo/bar/some-symlink", VirtualSymlink(fs, "some-symlink", "/foo/bar/some_file"))
+    return fs
+
+
+@pytest.fixture
+def mock_target(mock_fs):
+    target = Target()
+    target.fs.mount("/", mock_fs)
+    target.filesystems.add(mock_fs)
+    return target
+
+
+@pytest.fixture
+def mock_collector(mock_target):
+    collector = Collector(mock_target, Mock())
+    return collector
+
+
+def test_collector_collect_path_no_module_name(mock_collector):
+    with pytest.raises(ValueError):
+        mock_collector.collect_path("/some/path")
+
+
+def test_collector_collect_path(mock_fs, mock_target, mock_collector):
+    mock_seen_paths = set()
+    mock_module_name = "DUMMY"
+
+    with patch("acquire.collector.log") as mock_log:
+        with patch.object(mock_collector, "report"):
+            with patch.object(mock_collector, "collect_dir"):
+                with patch.object(mock_collector, "collect_file"):
+                    path = mock_target.fs.path("/foo/bar")
+                    mock_collector.collect_path(
+                        path,
+                        seen_paths=mock_seen_paths,
+                        module_name=mock_module_name,
+                    )
+                    mock_collector.collect_dir.assert_called()
+
+                    mock_collector.collect_path(
+                        "/foo/bar",
+                        seen_paths=mock_seen_paths,
+                        module_name=mock_module_name,
+                    )
+                    mock_collector.collect_dir.assert_called()
+
+                    mock_collector.collect_path(
+                        "/foo/bar/some-file",
+                        seen_paths=mock_seen_paths,
+                        module_name=mock_module_name,
+                    )
+                    mock_collector.collect_file.assert_called()
+
+                    mock_collector.collect_path(
+                        "/foo/bar/some-symlink",
+                        seen_paths=mock_seen_paths,
+                        module_name=mock_module_name,
+                    )
+                    mock_log.error.assert_called()
+                    assert mock_log.error.call_args.args[0] == "- Can't collect %s (symlink to %s) in module %s"
+
+                    mock_collector.collect_path(
+                        "/foo/bar/non-existing-file",
+                        seen_paths=mock_seen_paths,
+                        module_name=mock_module_name,
+                    )
+                    mock_log.error.assert_called()
+                    assert mock_log.error.call_args.args[0] == "- Path %s is not found"
+
+                    with patch.object(mock_target.fs, "lexists", return_value=True):
+                        mock_collector.collect_path(
+                            "/foo/bar/non-existing-file",
+                            seen_paths=mock_seen_paths,
+                            module_name=mock_module_name,
+                        )
+                        mock_log.error.assert_called()
+                        assert mock_log.error.call_args.args[0] == "- Don't know how to collect %s in module %s"