From 4fb0ba7ca73d17c9ecd7ca02948ee4db09246309 Mon Sep 17 00:00:00 2001
From: "copilot-swe-agent[bot]" <198982749+Copilot@users.noreply.github.com>
Date: Fri, 15 Aug 2025 06:55:43 +0000
Subject: [PATCH] Remove unused xmlPatternGroups configuration for consistency

Co-authored-by: mssoftjp <115339791+mssoftjp@users.noreply.github.com>
---
 src/config/CleaningConfig.ts | 28 ----------------------------
 1 file changed, 28 deletions(-)

diff --git a/src/config/CleaningConfig.ts b/src/config/CleaningConfig.ts
index 3d0913d..4cbc51e 100644
--- a/src/config/CleaningConfig.ts
+++ b/src/config/CleaningConfig.ts
@@ -45,13 +45,6 @@ export interface RepetitionThresholds {
 export interface ContaminationPatterns {
     /** Instruction patterns to remove from text beginning */
     instructionPatterns: string[];
-    /** XML pattern groups for different contexts */
-    xmlPatternGroups: {
-        completeXmlTags: string[];
-        sentenceBoundedTags: string[];
-        lineBoundedTags: string[];
-        standaloneTags: string[];
-    };
     /** Context patterns for general cleanup */
     contextPatterns: string[];
     /** Prompt snippet lengths for partial matching */
@@ -113,27 +106,6 @@ export const CLEANING_CONFIG: CleaningConfig = {
             '화자의 발언 내용만 정확히 기록해주세요'
         ],
 
-        xmlPatternGroups: {
-            completeXmlTags: [
-                '/<TRANSCRIPT[^>]*>([\\s\\S]*?)<\\/TRANSCRIPT>/g',
-                '/<transcript[^>]*>([\\s\\S]*?)<\\/transcript>/g',
-                '/<TRANSCRIPTION[^>]*>([\\s\\S]*?)<\\/TRANSCRIPTION>/g'
-            ],
-            sentenceBoundedTags: [
-                '/<\\/?TRANSCRIPT[^>]*>/g',
-                '/<\\/?transcript[^>]*>/g',
-                '/<\\/?TRANSCRIPTION[^>]*>/g'
-            ],
-            lineBoundedTags: [
-                '/^\\s*<[^>]*>\\s*$/gm',
-                '/^\\s*<\\/[^>]*>\\s*$/gm'
-            ],
-            standaloneTags: [
-                '/<[^>]*\\/>/g',
-                '/<\\w+[^>]*>\\s*<\\/\\w+>/g'
-            ]
-        },
-
         contextPatterns: [
             // Universal context patterns (structural)
             '/^\\s*\\([^)]*Speaker[^)]*only[^)]*\\)\\s*$/gmi',