flow.record 3.15.dev9__tar.gz → 3.15.dev12__tar.gz

{flow.record-3.15.dev9/flow.record.egg-info → flow.record-3.15.dev12}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flow.record
-Version: 3.15.dev9
+Version: 3.15.dev12
 Summary: A library for defining and creating structured data (called records) that can be streamed to disk or piped to other tools that use flow.record
 Author-email: Dissect Team <dissect@fox-it.com>
 License: Affero General Public License v3

{flow.record-3.15.dev9 → flow.record-3.15.dev12}/flow/record/base.py

@@ -12,6 +12,7 @@ import os
 import re
 import sys
 import warnings
+from contextlib import contextmanager
 from datetime import datetime, timezone
 from itertools import zip_longest
 from pathlib import Path
@@ -118,6 +119,17 @@ def set_ignored_fields_for_comparison(ignored_fields: Iterable[str]) -> None:
     IGNORE_FIELDS_FOR_COMPARISON = set(ignored_fields)
 
 
+@contextmanager
+def ignore_fields_for_comparison(ignored_fields: Iterable[str]):
+    """Context manager to temporarily ignore fields for comparison."""
+    original_ignored_fields = IGNORE_FIELDS_FOR_COMPARISON
+    try:
+        set_ignored_fields_for_comparison(ignored_fields)
+        yield
+    finally:
+        set_ignored_fields_for_comparison(original_ignored_fields)
+
+
 class FieldType:
     def _typename(self):
         t = type(self)

{flow.record-3.15.dev9 → flow.record-3.15.dev12}/flow/record/version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '3.15.dev9'
-__version_tuple__ = version_tuple = (3, 15, 'dev9')
+__version__ = version = '3.15.dev12'
+__version_tuple__ = version_tuple = (3, 15, 'dev12')

{flow.record-3.15.dev9 → flow.record-3.15.dev12/flow.record.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: flow.record
-Version: 3.15.dev9
+Version: 3.15.dev12
 Summary: A library for defining and creating structured data (called records) that can be streamed to disk or piped to other tools that use flow.record
 Author-email: Dissect Team <dissect@fox-it.com>
 License: Affero General Public License v3

{flow.record-3.15.dev9 → flow.record-3.15.dev12}/pyproject.toml

@@ -79,4 +79,4 @@ include = ["flow.*"]
 
 [tool.setuptools_scm]
 local_scheme = "no-local-version"
-write_to = "flow/record/version.py"
+version_file = "flow/record/version.py"

{flow.record-3.15.dev9 → flow.record-3.15.dev12}/tests/test_record.py

@@ -19,6 +19,7 @@ from flow.record import (
     record_stream,
 )
 from flow.record.base import (
+    ignore_fields_for_comparison,
     merge_record_descriptors,
     normalize_fieldname,
     set_ignored_fields_for_comparison,
@@ -856,3 +857,68 @@ def test_compare_environment_variable():
         assert same_same == but_still_same
         assert same_same != but_different
         assert len(set(records)) == 2
+
+
+def test_ignore_fields_for_comparision_contextmanager():
+    TestRecord = RecordDescriptor(
+        "test/record",
+        [
+            ("string", "firstname"),
+            ("string", "lastname"),
+            ("string", "movie"),
+        ],
+    )
+    records = [
+        TestRecord("John", "Rambo", "First Blood"),
+        TestRecord("John", "Rambo", "Rambo: First Blood Part II"),
+        TestRecord("John", "Rambo", "Rambo III"),
+        TestRecord("John", "Rambo", "Rambo"),
+        TestRecord("John", "Rambo", "Rambo: Last Blood"),
+        TestRecord("Johnny", "English", "Johnny English"),
+        TestRecord("Johnny", "English", "Johnny English Strikes Again"),
+        TestRecord("John", "McClane", "Die Hard"),
+        TestRecord("John", "McClane", "Die Hard 2"),
+        TestRecord("John", "McClane", "Die Hard with a Vengeance"),
+        TestRecord("John", "McClane", "Live Free or Die Hard"),
+        TestRecord("John", "McClane", "A Good Day to Die Hard"),
+        TestRecord("John", "Wick", "John Wick"),
+        TestRecord("John", "Wick", "John Wick: Chapter 2"),
+        TestRecord("John", "Wick", "John Wick: Chapter 3 - Parabellum"),
+    ]
+
+    with ignore_fields_for_comparison({"_generated", "lastname", "movie"}):
+        # unique by firstname
+        first_name_records = set(records)
+        firstnames = [first_name.firstname for first_name in first_name_records]
+        assert len(first_name_records) == 2
+        assert firstnames.count("John") == 1
+        assert firstnames.count("Johnny") == 1
+        assert records[0] == records[1]
+
+        # test nested context manager
+        with ignore_fields_for_comparison({"_generated", "firstname", "movie"}):
+            # unique by lastname
+            last_name_records = set(records)
+            lastnames = [last_name.lastname for last_name in last_name_records]
+            assert len(lastnames) == 4
+            assert lastnames.count("Rambo") == 1
+            assert lastnames.count("English") == 1
+            assert lastnames.count("McClane") == 1
+            assert lastnames.count("Wick") == 1
+            assert records[0] == records[1]
+
+    # test if the contextmanager properly resets the ignored fields
+    with ignore_fields_for_comparison({"_generated", "movie"}):
+        # unique by firstname + lastname
+        main_character_records = set(records)
+        main_characters = [f"{r.firstname} {r.lastname}" for r in main_character_records]
+        assert len(main_characters) == 4
+        assert main_characters.count("John Rambo") == 1
+        assert main_characters.count("Johnny English") == 1
+        assert main_characters.count("John McClane") == 1
+        assert main_characters.count("John Wick") == 1
+        assert records[0] == records[1]
+
+    # test reset again
+    assert len(set(records)) == len(records)
+    assert records[0] != records[1]