sync v1 branch

Author: Konboi

.tagpr

@@ -41,3 +41,4 @@
 	releaseBranch = main
 	versionFile = -
 	changelog = false
+	fixedMajorVersion = v1

smart_tests/commands/record/attachment.py

@@ -1,25 +1,26 @@
 import fnmatch
+import os
 import tarfile
 import zipfile
 from io import BytesIO
-from typing import Annotated, List, Tuple
+from typing import Annotated, List, Optional, Set, Tuple
 
 import click
+from tabulate import tabulate
 
 import smart_tests.args4p.typer as typer
 from smart_tests.utils.session import SessionId, get_session
 
 from ... import args4p
 from ...app import Application
-from ...utils.fail_fast_mode import warn_and_exit_if_fail_fast_mode
 from ...utils.smart_tests_client import SmartTestsClient
-from tabulate import tabulate
 
 
 class AttachmentStatus:
     SUCCESS = "✓ Recorded successfully"
     FAILED = "⚠ Failed to record"
     SKIPPED_NON_TEXT = "⚠ Skipped: not a valid text file"
+    SKIPPED_DUPLICATE = "⚠ Skipped: duplicate"
 
 
 @args4p.command(help="Record attachment information")
@@ -39,6 +40,8 @@ def attachment(
 ):
     client = SmartTestsClient(app=app)
     summary_rows = []
+    used_filenames: Set[str] = set()
+
     try:
         # Note: Call get_session method to check test session exists
         _ = get_session(session, client)
@@ -60,9 +63,15 @@ def attachment(
                                 [zip_info.filename, AttachmentStatus.SKIPPED_NON_TEXT])
                             continue
 
+                        file_name = get_unique_filename(zip_info.filename, used_filenames)
+                        if not file_name:
+                            summary_rows.append(
+                                [zip_info.filename, AttachmentStatus.SKIPPED_DUPLICATE])
+                            continue
+
                         status = post_attachment(
-                            client, session, file_content, zip_info.filename)
-                        summary_rows.append([zip_info.filename, status])
+                            client, session, file_content, file_name)
+                        summary_rows.append([file_name, status])
 
             # If tar file (tar, tar.gz, tar.bz2, tgz, etc.)
             elif tarfile.is_tarfile(a):
@@ -85,9 +94,15 @@ def attachment(
                                 [tar_info.name, AttachmentStatus.SKIPPED_NON_TEXT])
                             continue
 
+                        file_name = get_unique_filename(tar_info.name, used_filenames)
+                        if not file_name:
+                            summary_rows.append(
+                                [tar_info.name, AttachmentStatus.SKIPPED_DUPLICATE])
+                            continue
+
                         status = post_attachment(
-                            client, session, file_content, tar_info.name)
-                        summary_rows.append([tar_info.name, status])
+                            client, session, file_content, file_name)
+                        summary_rows.append([file_name, status])
 
             else:
                 with open(a, mode='rb') as f:
@@ -98,15 +113,55 @@ def attachment(
                             [a, AttachmentStatus.SKIPPED_NON_TEXT])
                         continue
 
-                    status = post_attachment(client, session, file_content, a)
-                    summary_rows.append([a, status])
+                    file_name = get_unique_filename(a, used_filenames)
+                    if not file_name:
+                        summary_rows.append(
+                            [a, AttachmentStatus.SKIPPED_DUPLICATE])
+                        continue
+
+                    status = post_attachment(client, session, file_content, file_name)
+                    summary_rows.append([file_name, status])
+
     except Exception as e:
         client.print_exception_and_recover(e)
 
     display_summary_as_table(summary_rows)
 
 
-def matches_include_patterns(filename: str, include_patterns: List[str]) -> bool:
+def get_unique_filename(filepath: str, used_filenames: Set[str]) -> Optional[str]:
+    """
+    Get a unique filename by extracting the basename and prepending parent folders if needed.
+    Strategy:
+    1. First occurrence: use basename (e.g., app.log)
+    2. Duplicate: prepend parent directories until unique
+    """
+    # Normalize path separators to forward slash (archives always use forward slash in both linux, and windows)
+    normalized_path = filepath.replace(os.sep, '/')
+    normalized_path = normalize_filename(normalized_path)
+
+    basename = normalized_path.split('/')[-1]
+
+    # If basename is not used, return it
+    if basename not in used_filenames:
+        used_filenames.add(basename)
+        return basename
+
+    # Try prepending parents from nearest to farthest
+    path_parts = normalized_path.split('/')
+    parent_parts = [p for p in path_parts[:-1] if p]
+
+    prefixed_name = basename
+    for parent in reversed(parent_parts):
+        prefixed_name = f"{parent}/{prefixed_name}"
+
+        if prefixed_name not in used_filenames:
+            used_filenames.add(prefixed_name)
+            return prefixed_name
+
+    return None
+
+
+def matches_include_patterns(filename: str, include_patterns: Tuple[str, ...]) -> bool:
     """
     Check if a file should be included based on the include patterns.
     If no patterns are specified, all files are included.
@@ -121,6 +176,13 @@ def matches_include_patterns(filename: str, include_patterns: List[str]) -> bool
     return False
 
 
+def normalize_filename(filename: str) -> str:
+    """
+    Normalize filename by replacing whitespace with dashes.
+    """
+    return filename.replace(' ', '-')
+
+
 def valid_utf8_file(file_content: bytes) -> bool:
     # Check for null bytes (binary files)
     if b'\x00' in file_content:

smart_tests/test_runners/maven.py

@@ -1,18 +1,18 @@
 import glob
 import os
 import re
-from typing import Annotated
-from typing import Dict, List, Tuple
+from typing import Annotated, Dict, List
 
 import click
 
 import smart_tests.args4p.typer as typer
 from smart_tests.utils import glob as uglob
 from smart_tests.utils.java import junit5_nested_class_path_builder
-from . import smart_tests
+
 from ..args4p.exceptions import BadCmdLineException
 from ..commands.record.tests import RecordTests
 from ..commands.subset import Subset
+from . import smart_tests
 
 # Surefire has the default inclusion pattern
 # https://maven.apache.org/surefire/maven-surefire-plugin/test-mojo.html#includes
@@ -169,4 +169,12 @@ def record_tests(
     )],
 ):
     client.path_builder = junit5_nested_class_path_builder(client.path_builder)
+    original_report = client.report
+    IGNORED_FILES = {'failsafe-summary.xml', 'testng-results.xml'}
+
+    def report_with_filter(junit_report_file: str):
+        if not any(junit_report_file.endswith(f) for f in IGNORED_FILES):
+            original_report(junit_report_file)
+
+    client.report = report_with_filter
     smart_tests.CommonRecordTestImpls.load_report_files(client=client, source_roots=reports)

smart_tests/test_runners/pytest.py

@@ -3,7 +3,8 @@
 import os
 import pathlib
 import subprocess
-from typing import Annotated, Generator, Iterable, List
+from datetime import datetime, timezone
+from typing import Annotated, Generator, Iterable, List, Optional
 
 import click
 from junitparser import Properties, TestCase  # type: ignore
@@ -17,7 +18,6 @@
 from ..commands.subset import Subset
 from . import smart_tests
 
-
 # Please specify junit_family=legacy for pytest report format. if using pytest version 6 or higher.
 # - pytest has changed its default test report format from xunit1 to xunit2 since version 6.
 #     - https://docs.pytest.org/en/latest/deprecations.html#junit-family-default-value-change-to-xunit2
@@ -40,6 +40,15 @@
 # <testcase classname="tests.test_mod.TestClass" name="test__can_print_aaa" file="tests/test_mod.py"
 # line="3" time="0.001" />
 #
+
+
+def _timestamp_to_iso(ts: Optional[float]) -> Optional[str]:
+    # convert to ISO-8601 formatted date
+    if ts is None:
+        return None
+    return datetime.fromtimestamp(ts, tz=timezone.utc).isoformat()
+
+
 @smart_tests.subset
 def subset(
     client: Subset,
@@ -344,15 +353,39 @@ def parse_func(
                     else:
                         props = None
 
+                # extract raw timestamps
+                start_timestamp = data.get("start")
+                stop_timestamp = data.get("stop")
+
+                # convert to ISO-8601
+                start_timestamp_iso_format = _timestamp_to_iso(start_timestamp)
+                end_timestamp_iso_format = _timestamp_to_iso(stop_timestamp)
+
+                print(
+                    f"DEBUG pytest timing start={start_timestamp_iso_format}, stop={end_timestamp_iso_format}"
+                )
+
+                event_data = {}
+                if start_timestamp_iso_format:
+                    event_data["start_timestamp"] = start_timestamp_iso_format
+                if end_timestamp_iso_format:
+                    event_data["stop_timestamp"] = end_timestamp_iso_format
+
                 test_path = _parse_pytest_nodeid(nodeid)
                 for path in test_path:
                     if path.get("type") == "file":
                         path["name"] = pathlib.Path(path["name"]).as_posix()
 
+                data_payload = event_data if event_data else None
+
+                # end_timestamp_iso_format is being passed as timestamp as it reflects event finalization
+                # start + duration = stop
+                # sending both start and stop time in the event data field
                 yield CaseEvent.create(
                     test_path=test_path,
                     duration_secs=data.get("duration", 0),
                     status=status,
                     stdout=stdout,
                     stderr=stderr,
-                    data=props)
+                    timestamp=end_timestamp_iso_format,
+                    data=data_payload)

tests/commands/compare/test_subsets.py

@@ -201,17 +201,16 @@ def test_subsets_subset_ids(self):
                           mix_stderr=False)
 
         self.assert_success(result)
-        expect = """PTS subset change summary:
-────────────────────────────────
--> 3 tests analyzed | 1 ↑ promoted | 1 ↓ demoted
--> Code files affected: bbb.py, ccc.py, ddd.py
-────────────────────────────────
-
-Δ Rank    Subset Rank    Test Name    Reason                Density
---------  -------------  -----------  --------------------  ---------
-NEW       1              file=ddd.py  Changed file: ddd.py  0.9
-↑1        2              file=ccc.py  Changed file: ccc.py  0.7
-↓1        3              file=bbb.py  Changed file: bbb.py  0.5
-DELETED   -              file=aaa.py
-"""
-        self.assertEqual(result.stdout, expect)
+        output = result.stdout
+        self.assertIn("3 tests analyzed | 1 ↑ promoted | 1 ↓ demoted", output)
+        self.assertIn("Code files affected: bbb.py, ccc.py, ddd.py", output)
+        self.assertIn("Δ Rank", output)
+        self.assertIn("Density", output)
+        for expected_row in [
+            ("NEW", "1", "file=ddd.py", "Changed file: ddd.py", "0.9"),
+            ("↑1", "2", "file=ccc.py", "Changed file: ccc.py", "0.7"),
+            ("↓1", "3", "file=bbb.py", "Changed file: bbb.py", "0.5"),
+            ("DELETED", "-", "file=aaa.py"),
+        ]:
+            for cell in expected_row:
+                self.assertIn(cell, output)