prevent pytest fail with non unicode chars

Author: aseembits93

codeflash/code_utils/shell_utils.py

@@ -247,6 +247,10 @@ def get_cross_platform_subprocess_run_args(
     capture_output: bool = True,
 ) -> dict[str, str]:
     run_args = {"cwd": cwd, "env": env, "text": text, "timeout": timeout, "check": check}
+    # When text=True, use errors='replace' to handle non-UTF-8 bytes gracefully
+    # instead of raising UnicodeDecodeError
+    if text:
+        run_args["errors"] = "replace"
     if sys.platform == "win32":
         creationflags = subprocess.CREATE_NEW_PROCESS_GROUP
         run_args["creationflags"] = creationflags

codeflash/languages/javascript/find_references.py

@@ -213,7 +213,7 @@ def find_references(
                 trigger_check = True
                 if import_info:
                     context.visited_files.add(file_path)
-                    import_name, original_import = import_info
+                    import_name, original_import = import_info  # noqa: RUF059
                     file_refs = self._find_references_in_file(
                         file_path, file_code, reexport_name, import_name, file_analyzer, include_self=True
                     )
@@ -404,7 +404,7 @@ def _find_identifier_references(
             name_node = node.child_by_field_name("name")
             if name_node:
                 new_current_function = source_bytes[name_node.start_byte : name_node.end_byte].decode("utf8")
-        elif node.type in ("variable_declarator",):
+        elif node.type in ("variable_declarator",):  # noqa: FURB171
             # Arrow function or function expression assigned to variable
             name_node = node.child_by_field_name("name")
             value_node = node.child_by_field_name("value")

codeflash/languages/javascript/parse.py

@@ -16,12 +16,7 @@
 from junitparser.xunit2 import JUnitXml
 
 from codeflash.cli_cmds.console import logger
-from codeflash.models.models import (
-    FunctionTestInvocation,
-    InvocationId,
-    TestResults,
-    TestType,
-)
+from codeflash.models.models import FunctionTestInvocation, InvocationId, TestResults, TestType
 
 if TYPE_CHECKING:
     import subprocess

codeflash/languages/javascript/vitest_runner.py

@@ -288,8 +288,7 @@ def run_vitest_behavioral_tests(
         logger.debug(f"Vitest JUnit XML created: {result_file_path} ({file_size} bytes)")
         if file_size < 200:  # Suspiciously small - likely empty or just headers
             logger.warning(
-                f"Vitest JUnit XML is very small ({file_size} bytes). "
-                f"Content: {result_file_path.read_text()[:500]}"
+                f"Vitest JUnit XML is very small ({file_size} bytes). Content: {result_file_path.read_text()[:500]}"
             )
     else:
         logger.warning(

codeflash/languages/treesitter_utils.py

@@ -1580,9 +1580,9 @@ def get_analyzer_for_file(file_path: Path) -> TreeSitterAnalyzer:
     """
     suffix = file_path.suffix.lower()
 
-    if suffix in (".ts",):
+    if suffix in (".ts",):  # noqa: FURB171
         return TreeSitterAnalyzer(TreeSitterLanguage.TYPESCRIPT)
-    if suffix in (".tsx",):
+    if suffix in (".tsx",):  # noqa: FURB171
         return TreeSitterAnalyzer(TreeSitterLanguage.TSX)
     # Default to JavaScript for .js, .jsx, .mjs, .cjs
     return TreeSitterAnalyzer(TreeSitterLanguage.JAVASCRIPT)

codeflash/optimization/function_optimizer.py

@@ -315,7 +315,7 @@ def _handle_empty_queue(self) -> CandidateNode | None:
                 self.future_all_code_repair,
                 "Repairing {0} candidates",
                 "Added {0} candidates from repair, total candidates now: {1}",
-                lambda: self.future_all_code_repair.clear(),
+                lambda: self.future_all_code_repair.clear(),  # noqa: PLW0108
             )
         if self.line_profiler_done and not self.refinement_done:
             return self._process_candidates(
@@ -330,7 +330,7 @@ def _handle_empty_queue(self) -> CandidateNode | None:
                 self.future_adaptive_optimizations,
                 "Applying adaptive optimizations to {0} candidates",
                 "Added {0} candidates from adaptive optimization, total candidates now: {1}",
-                lambda: self.future_adaptive_optimizations.clear(),
+                lambda: self.future_adaptive_optimizations.clear(),  # noqa: PLW0108
             )
         return None  # All done
 
@@ -2093,7 +2093,7 @@ def process_review(
             formatted_generated_test = format_generated_code(concolic_test_str, self.args.formatter_cmds)
             generated_tests_str += f"```{code_lang}\n{formatted_generated_test}\n```\n\n"
 
-        existing_tests, replay_tests, concolic_tests = existing_tests_source_for(
+        existing_tests, replay_tests, concolic_tests = existing_tests_source_for(  # noqa: RUF059
             self.function_to_optimize.qualified_name_with_modules_from_root(self.project_root),
             function_to_all_tests,
             test_cfg=self.test_cfg,

codeflash/verification/parse_test_output.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import contextlib
 import os
 import re
 import sqlite3
@@ -22,6 +21,9 @@
 )
 from codeflash.discovery.discover_unit_tests import discover_parameters_unittest
 from codeflash.languages import is_javascript
+
+# Import Jest-specific parsing from the JavaScript language module
+from codeflash.languages.javascript.parse import parse_jest_test_xml as _parse_jest_test_xml
 from codeflash.models.models import (
     ConcurrencyMetrics,
     FunctionTestInvocation,
@@ -32,10 +34,6 @@
 )
 from codeflash.verification.coverage_utils import CoverageUtils, JestCoverageUtils
 
-# Import Jest-specific parsing from the JavaScript language module
-from codeflash.languages.javascript.parse import jest_end_pattern, jest_start_pattern
-from codeflash.languages.javascript.parse import parse_jest_test_xml as _parse_jest_test_xml
-
 if TYPE_CHECKING:
     import subprocess