Partial parsing bug with empty schema file - ensure None is not passe…

…d to load_yaml_text (#6494) (#6505)

Co-authored-by: Gerda Shank <[email protected]>

.changes/unreleased/Fixes-20230101-223405.yaml

@@ -0,0 +1,6 @@
+kind: Fixes
+body: Bug when partial parsing with an empty schema file
+time: 2023-01-01T22:34:05.97322-05:00
+custom:
+  Author: gshank
+  Issue: "4850"

core/dbt/context/base.py

@@ -636,9 +636,8 @@ def flags(self) -> Any:
             {% endif %}
 
         This supports all flags defined in flags submodule (core/dbt/flags.py)
-        TODO: Replace with object that provides read-only access to flag values
         """
-        return flags
+        return flags.get_flag_obj()
 
     @contextmember
     @staticmethod

core/dbt/flags.py

@@ -1,7 +1,9 @@
-import os
+# Do not import the os package because we expose this package in jinja
+from os import name as os_name, path as os_path, getcwd as os_getcwd, getenv as os_getenv
 import multiprocessing
+from argparse import Namespace
 
-if os.name != "nt":
+if os_name != "nt":
     # https://bugs.python.org/issue41567
     import multiprocessing.popen_spawn_posix  # type: ignore
 from pathlib import Path
@@ -10,14 +12,14 @@
 # PROFILES_DIR must be set before the other flags
 # It also gets set in main.py and in set_from_args because the rpc server
 # doesn't go through exactly the same main arg processing.
-GLOBAL_PROFILES_DIR = os.path.join(os.path.expanduser("~"), ".dbt")
-LOCAL_PROFILES_DIR = os.getcwd()
+GLOBAL_PROFILES_DIR = os_path.join(os_path.expanduser("~"), ".dbt")
+LOCAL_PROFILES_DIR = os_getcwd()
 # Use the current working directory if there is a profiles.yml file present there
-if os.path.exists(Path(LOCAL_PROFILES_DIR) / Path("profiles.yml")):
+if os_path.exists(Path(LOCAL_PROFILES_DIR) / Path("profiles.yml")):
     DEFAULT_PROFILES_DIR = LOCAL_PROFILES_DIR
 else:
     DEFAULT_PROFILES_DIR = GLOBAL_PROFILES_DIR
-PROFILES_DIR = os.path.expanduser(os.getenv("DBT_PROFILES_DIR", DEFAULT_PROFILES_DIR))
+PROFILES_DIR = os_path.expanduser(os_getenv("DBT_PROFILES_DIR", DEFAULT_PROFILES_DIR))
 
 STRICT_MODE = False  # Only here for backwards compatibility
 FULL_REFRESH = False  # subcommand
@@ -91,7 +93,7 @@ def env_set_truthy(key: str) -> Optional[str]:
     """Return the value if it was set to a "truthy" string value or None
     otherwise.
     """
-    value = os.getenv(key)
+    value = os_getenv(key)
     if not value or value.lower() in ("0", "false", "f"):
         return None
     return value
@@ -104,7 +106,7 @@ def env_set_bool(env_value):
 
 
 def env_set_path(key: str) -> Optional[Path]:
-    value = os.getenv(key)
+    value = os_getenv(key)
     if value is None:
         return value
     else:
@@ -184,7 +186,7 @@ def get_flag_value(flag, args, user_config):
     if flag in ["PRINTER_WIDTH", "EVENT_BUFFER_SIZE"]:  # must be ints
         flag_value = int(flag_value)
     if flag == "PROFILES_DIR":
-        flag_value = os.path.abspath(flag_value)
+        flag_value = os_path.abspath(flag_value)
 
     return flag_value
 
@@ -208,7 +210,7 @@ def _load_flag_value(flag, args, user_config):
 def _get_flag_value_from_env(flag):
     # Environment variables use pattern 'DBT_{flag name}'
     env_flag = _get_env_flag(flag)
-    env_value = os.getenv(env_flag)
+    env_value = os_getenv(env_flag)
     if env_value is None or env_value == "":
         return None
 
@@ -245,4 +247,21 @@ def get_flag_dict():
         "event_buffer_size": EVENT_BUFFER_SIZE,
         "quiet": QUIET,
         "no_print": NO_PRINT,
+        "cache_selected_only": CACHE_SELECTED_ONLY,
+        "target_path": TARGET_PATH,
+        "log_path": LOG_PATH,
     }
+
+
+# This is used by core/dbt/context/base.py to return a flag object
+# in Jinja.
+def get_flag_obj():
+    new_flags = Namespace()
+    for k, v in get_flag_dict().items():
+        setattr(new_flags, k.upper(), v)
+    # The following 3 are CLI arguments only so they're not full-fledged flags,
+    # but we put in flags for users.
+    setattr(new_flags, "FULL_REFRESH", FULL_REFRESH)
+    setattr(new_flags, "STORE_FAILURES", STORE_FAILURES)
+    setattr(new_flags, "WHICH", WHICH)
+    return new_flags

core/dbt/parser/schemas.py

@@ -114,7 +114,8 @@ def yaml_from_file(source_file: SchemaSourceFile) -> Dict[str, Any]:
     """If loading the yaml fails, raise an exception."""
     path = source_file.path.relative_path
     try:
-        return load_yaml_text(source_file.contents, source_file.path)
+        # source_file.contents can sometimes be None
+        return load_yaml_text(source_file.contents or "", source_file.path)
     except ValidationException as e:
         reason = validator_error_message(e)
         raise ParsingException(

test/integration/068_partial_parsing_tests/test_partial_parsing.py

@@ -477,6 +477,8 @@ def test_postgres_skip_macros(self):
         # initial run so we have a msgpack file
         self.setup_directories()
         self.copy_file('test-files/model_one.sql', 'models/model_one.sql')
+        # use empty_schema file for bug #4850
+        self.copy_file('test-files/empty_schema.yml', 'models/eschema.yml')
         results = self.run_dbt()
 
         # add a new ref override macro

tests/functional/context_methods/test_builtin_functions.py

@@ -112,8 +112,19 @@ def test_builtin_invocation_args_dict_function(self, project):
         expected = "invocation_result: {'debug': True, 'log_format': 'json', 'write_json': True, 'use_colors': True, 'printer_width': 80, 'version_check': True, 'partial_parse': True, 'static_parser': True, 'profiles_dir': "
         assert expected in str(result)
 
-        expected = "'send_anonymous_usage_stats': False, 'event_buffer_size': 100000, 'quiet': False, 'no_print': False, 'macro': 'validate_invocation', 'args': '{my_variable: test_variable}', 'which': 'run-operation', 'rpc_method': 'run-operation', 'indirect_selection': 'eager'}"
-        assert expected in str(result)
+        expected = (
+            "'send_anonymous_usage_stats': False",
+            "'quiet': False",
+            "'no_print': False",
+            "'cache_selected_only': False",
+            "'macro': 'validate_invocation'",
+            "'args': '{my_variable: test_variable}'",
+            "'which': 'run-operation'",
+            "'rpc_method': 'run-operation'",
+            "'indirect_selection': 'eager'",
+        )
+        for element in expected:
+            assert element in str(result)
 
     def test_builtin_dbt_metadata_envs_function(self, project, monkeypatch):
         envs = {