def check_log()

in project/paperbench/paperbench/monitor/monitor.py [0:0]

• 47 lines of code
• 12 McCabe index (conditional complexity)

    def check_log(self, log_file: Path) -> MonitorResult:
        """Check a log file for violations of the blacklist.

        Args:
            log_file: Path to the log file to check

        Returns:
            MonitorResult containing any violations found
        """
        if not log_file.exists():
            return MonitorResult(
                violations=[],
                explanation=f"Log file not found at {log_file}",
                log_file=log_file,
            )

        if not self.blacklist:
            return MonitorResult(
                violations=[],
                explanation="No blacklist entries - all URLs allowed",
                log_file=log_file,
            )

        violations = []
        with open(log_file, "r") as f:
            lines = f.readlines()
            for i, line in enumerate(lines, start=1):
                line = line.strip()
                if not line:
                    continue

                for blacklisted in self.blacklist:
                    normalized_blacklist = self._normalize_url(blacklisted)
                    if normalized_blacklist in line:
                        context_lines, context_start = self._get_context_lines(lines, i)
                        # Clean context lines of unicode characters
                        cleaned_context = [self._clean_unicode(line) for line in context_lines]

                        # Only consider it a violation if it appears with git clone, curl, or wget
                        if self._contains_command(cleaned_context):
                            violation_context = ViolationContext(
                                line_number=i,
                                violation=blacklisted,
                                context=cleaned_context,
                                context_start=context_start,
                            )

                            violations.append(violation_context)
                            logger.warning(
                                f"Found blacklisted term '{blacklisted}' with command at line {i} in {log_file}"
                            )

        if violations:
            explanation = (
                f"Found {len(violations)} violations of blacklist with git clone/curl/wget commands"
            )
        else:
            explanation = "No violations found with git clone/curl/wget commands"

        return MonitorResult(
            violations=violations,
            explanation=explanation,
            log_file=log_file,
        )