From d042cbc62e24833026c0d1e8840d7ec99addb65b Mon Sep 17 00:00:00 2001
From: wangxiaolei <fatelei@gmail.com>
Date: Thu, 9 Apr 2026 16:22:09 +0800
Subject: [PATCH] fix: fix remove_leading_symbols remove [ (#34832)

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
---
 api/core/tools/utils/text_processing_utils.py | 15 +++++-
 .../unit_tests/utils/test_text_processing.py  | 52 ++++++++++++++++++-
 2 files changed, 65 insertions(+), 2 deletions(-)

diff --git a/api/core/tools/utils/text_processing_utils.py b/api/core/tools/utils/text_processing_utils.py
index 4bfaa5e49b..1dd0605f28 100644
--- a/api/core/tools/utils/text_processing_utils.py
+++ b/api/core/tools/utils/text_processing_utils.py
@@ -19,5 +19,18 @@ def remove_leading_symbols(text: str) -> str:
 
     # Match Unicode ranges for punctuation and symbols
     # FIXME this pattern is confused quick fix for #11868 maybe refactor it later
-    pattern = r'^[\[\]\u2000-\u2025\u2027-\u206F\u2E00-\u2E7F\u3000-\u300F\u3011-\u303F"#$%&\'()*+,./:;<=>?@^_`~]+'
+    pattern = re.compile(
+        r"""
+        ^
+        (?:
+            [\u2000-\u2025]                # General Punctuation: spaces, quotes, dashes
+          | [\u2027-\u206F]                # General Punctuation: ellipsis, underscores, etc.
+          | [\u2E00-\u2E7F]                # Supplemental Punctuation: medieval, ancient marks
+          | [\u3000-\u300F]                # CJK Punctuation: 、。〃「」『》』 (excludes 【】)
+          | [\u3012-\u303F]                # CJK Punctuation: 〖〗〔〕〘〙〚〛〜 etc.
+          | ["#$%&'()*+,./:;<=>?@^_`~]     # ASCII punctuation (excludes []【】)
+        )+
+        """,
+        re.VERBOSE,
+    )
     return re.sub(pattern, "", text)
diff --git a/api/tests/unit_tests/utils/test_text_processing.py b/api/tests/unit_tests/utils/test_text_processing.py
index bf61162a66..5f6ccbcdff 100644
--- a/api/tests/unit_tests/utils/test_text_processing.py
+++ b/api/tests/unit_tests/utils/test_text_processing.py
@@ -19,7 +19,57 @@ from core.tools.utils.text_processing_utils import remove_leading_symbols
         ("[Google](https://google.com) is a search engine", "[Google](https://google.com) is a search engine"),
         ("[Example](http://example.com) some text", "[Example](http://example.com) some text"),
         # Leading symbols before markdown link are removed, including the opening bracket [
-        ("@[Test](https://example.com)", "Test](https://example.com)"),
+        ("@[Test](https://example.com)", "[Test](https://example.com)"),
+        ("~~标题~~", "标题~~"),
+        ('""quoted', "quoted"),
+        ("''test", "test"),
+        ("##话题", "话题"),
+        ("$$价格", "价格"),
+        ("%%百分比", "百分比"),
+        ("&&与逻辑", "与逻辑"),
+        ("((括号))", "括号))"),
+        ("**强调**", "强调**"),
+        ("++自增", "自增"),
+        (",,逗号", "逗号"),
+        ("..省略", "省略"),
+        ("//注释", "注释"),
+        ("::范围", "范围"),
+        (";;分号", "分号"),
+        ("<<左移", "左移"),
+        ("==等于", "等于"),
+        (">>右移", "右移"),
+        ("??疑问", "疑问"),
+        ("@@提及", "提及"),
+        ("^^上标", "上标"),
+        ("__下划线", "下划线"),
+        ("``代码", "代码"),
+        ("~~删除线", "删除线"),
+        ("　全角空格开头", "全角空格开头"),
+        ("、顿号开头", "顿号开头"),
+        ("。句号开头", "句号开头"),
+        ("「引号」测试", "引号」测试"),
+        ("『书名号』", "书名号』"),
+        ("【保留】测试", "【保留】测试"),
+        ("〖括号〗测试", "括号〗测试"),
+        ("〔括号〕测试", "括号〕测试"),
+        ("~~【保留】~~", "【保留】~~"),
+        ('"[公告]"', '[公告]"'),
+        ("[公告] 更新", "[公告] 更新"),
+        ("【通知】重要", "【通知】重要"),
+        ("[[嵌套]]", "[[嵌套]]"),
+        ("【【嵌套】】", "【【嵌套】】"),
+        ("[【混合】]", "[【混合】]"),
+        ("normal text", "normal text"),
+        ("123数字", "123数字"),
+        ("中文开头", "中文开头"),
+        ("alpha", "alpha"),
+        ("~", ""),
+        ("【", "【"),
+        ("[", "["),
+        ("~~~", ""),
+        ("【【【", "【【【"),
+        ("\t制表符", "\t制表符"),
+        ("\n换行", "\n换行"),
     ],
 )
 def test_remove_leading_symbols(input_text, expected_output):