Added crawling for init scripts on local files to assessment workflow (#960)

## Changes
Scanning Init Script for local file and S3

### Linked issues
#954 

Resolves #954 

### Functionality 

- [ ] added relevant user documentation
- [ ] added new CLI command
- [ ] modified existing command: `databricks labs ucx ...`
- [ ] added a new workflow
- [ ] modified existing workflow: `...`
- [ ] added a new table
- [ ] modified existing table: `...`

### Tests
<!-- How is this tested? Please see the checklist below and also
describe any other relevant tests -->

- [ ] manually tested
- [x] added unit tests
- [ ] added integration tests
- [ ] verified on staging environment (screenshot attached)

Author: prajin-29

src/databricks/labs/ucx/assessment/clusters.py

@@ -12,6 +12,7 @@
     DataSecurityMode,
     DbfsStorageInfo,
     InitScriptInfo,
+    LocalFileInfo,
     Policy,
     WorkspaceStorageInfo,
 )
@@ -20,6 +21,7 @@
     AZURE_SP_CONF_FAILURE_MSG,
     INCOMPATIBLE_SPARK_CONFIG_KEYS,
     INIT_SCRIPT_DBFS_PATH,
+    INIT_SCRIPT_LOCAL_PATH,
     azure_sp_conf_present_check,
     spark_version_compatibility,
 )
@@ -74,6 +76,14 @@ def _get_init_script_data(self, init_script_info: InitScriptInfo) -> str | None:
                     data = self._ws.workspace.export(workspace_file_destination).content
                     if data is not None:
                         return base64.b64decode(data).decode("utf-8")
+                case InitScriptInfo(file=LocalFileInfo(destination)):
+                    split = destination.split(":/")
+                    if len(split) != INIT_SCRIPT_LOCAL_PATH:
+                        return None
+                    with open(split[1], "r", encoding="utf-8") as file:
+                        data = file.read()
+                    return data
+
             return None
         except NotFound:
             return None

src/databricks/labs/ucx/assessment/crawlers.py

@@ -18,6 +18,7 @@
 ]
 AZURE_SP_CONF_FAILURE_MSG = "Uses azure service principal credentials config in"
 INIT_SCRIPT_DBFS_PATH = 2
+INIT_SCRIPT_LOCAL_PATH = 2
 
 
 def azure_sp_conf_in_init_scripts(init_script_data: str) -> bool:

tests/unit/assessment/clusters/init-scripts-file.json

@@ -0,0 +1,27 @@
+{
+  "autoscale": {
+    "max_workers": 6,
+    "min_workers": 1
+  },
+  "cluster_id": "01234-11223344-1122334455",
+  "cluster_name": "UCX Cluster",
+  "policy_id": "single-user-with-spn",
+  "spark_version": "13.3.x-cpu-ml-scala2.12",
+  "init_scripts": [
+    {
+      "file": {
+        "destination": "file:/users/init_scripts/test.sh"
+      }
+    },
+    {
+      "file": {
+        "destination": "file"
+      }
+    },
+    {
+      "workspace": {
+        "destination": "init.sh"
+      }
+    }
+  ]
+}

tests/unit/assessment/clusters/init-scripts-no-match.json

@@ -0,0 +1,17 @@
+{
+  "autoscale": {
+    "max_workers": 6,
+    "min_workers": 1
+  },
+  "cluster_id": "01234-11223344-1122334455",
+  "cluster_name": "UCX Cluster",
+  "policy_id": "single-user-with-spn",
+  "spark_version": "13.3.x-cpu-ml-scala2.12",
+  "init_scripts": [
+    {
+      "abfss": {
+        "destination": "abfss"
+      }
+    }
+  ]
+}

tests/unit/assessment/test_clusters.py

@@ -1,5 +1,5 @@
 import json
-from unittest.mock import MagicMock
+from unittest.mock import MagicMock, mock_open, patch
 
 import pytest
 from databricks.sdk.errors import DatabricksError, InternalError, NotFound
@@ -84,6 +84,19 @@ def test_cluster_init_script():
     assert len(init_crawler) == 1
 
 
+def test_cluster_file_init_script():
+    ws = workspace_client_mock(cluster_ids=['init-scripts-file'])
+    with patch("builtins.open", mock_open(read_data="data")):
+        init_crawler = ClustersCrawler(ws, MockBackend(), "ucx").snapshot()
+        assert len(init_crawler) == 1
+
+
+def test_cluster_no_match_file_init_script():
+    ws = workspace_client_mock(cluster_ids=['init-scripts-no-match'])
+    init_crawler = ClustersCrawler(ws, MockBackend(), "ucx").snapshot()
+    assert len(init_crawler) == 1
+
+
 def test_cluster_init_script_check_dbfs():
     ws = workspace_client_mock(cluster_ids=['init-scripts-dbfs'])
     ws.dbfs.read().data = "JXNoCmVjaG8gIj0="