From 24f4ffa73e274445f28ef3f3057c65f2eb6b6c64 Mon Sep 17 00:00:00 2001
From: Wenjie Zhang <xerrors@163.com>
Date: Tue, 29 Jul 2025 00:29:41 +0800
Subject: [PATCH] =?UTF-8?q?feat(knowledge=5Fbase):=20=E6=B7=BB=E5=8A=A0?=
 =?UTF-8?q?=E5=AF=B9CSV=E3=80=81Excel=E5=92=8CJSON=E6=96=87=E4=BB=B6?=
 =?UTF-8?q?=E7=9A=84=E6=94=AF=E6=8C=81?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

添加处理CSV、Excel和JSON文件的逻辑，将其内容转换为Markdown格式。使用pandas库处理表格数据，json库处理JSON数据，增强知识库的文件兼容性。
---
 pyproject.toml                  |  1 +
 src/knowledge/knowledge_base.py | 44 +++++++++++++++++++++++++++++++++
 2 files changed, 45 insertions(+)

diff --git a/pyproject.toml b/pyproject.toml
index 9dd008cd..9e5fc3f6 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -52,6 +52,7 @@ dependencies = [
     "rich>=13.7.1",
     "typer>=0.16.0",
     "mineru[core]>=2.1.6",
+    "tabulate>=0.9.0",
 ]
 [tool.ruff]
 line-length = 210  # 代码最大行宽
diff --git a/src/knowledge/knowledge_base.py b/src/knowledge/knowledge_base.py
index bf176cb0..6b8baf9e 100644
--- a/src/knowledge/knowledge_base.py
+++ b/src/knowledge/knowledge_base.py
@@ -425,6 +425,50 @@ class KnowledgeBase(ABC):
             text = md(content, heading_style="ATX")
             return f"# {file_path_obj.name}\n\n{text}"
 
+        elif file_ext == '.csv':
+            # 处理 CSV 文件
+            import pandas as pd
+            df = pd.read_csv(file_path_obj)
+            # 将每一行数据与表头组合成独立的表格
+            markdown_content = f"# {file_path_obj.name}\n\n"
+
+            for index, row in df.iterrows():
+                # 创建包含表头和当前行的小表格
+                row_df = pd.DataFrame([row], columns=df.columns)
+                markdown_table = row_df.to_markdown(index=False)
+                markdown_content += f"{markdown_table}\n\n"
+
+            return markdown_content.strip()
+
+        elif file_ext in ['.xls', '.xlsx']:
+            # 处理 Excel 文件
+            import pandas as pd
+            # 读取所有工作表
+            excel_file = pd.ExcelFile(file_path_obj)
+            markdown_content = f"# {file_path_obj.name}\n\n"
+
+            for sheet_name in excel_file.sheet_names:
+                df = pd.read_excel(file_path_obj, sheet_name=sheet_name)
+                markdown_content += f"## {sheet_name}\n\n"
+
+                # 将每一行数据与表头组合成独立的表格
+                for index, row in df.iterrows():
+                    # 创建包含表头和当前行的小表格
+                    row_df = pd.DataFrame([row], columns=df.columns)
+                    markdown_table = row_df.to_markdown(index=False)
+                    markdown_content += f"{markdown_table}\n\n"
+
+            return markdown_content.strip()
+
+        elif file_ext == '.json':
+            # 处理 JSON 文件
+            import json
+            with open(file_path_obj, encoding='utf-8') as f:
+                data = json.load(f)
+            # 将 JSON 数据格式化为 markdown 代码块
+            json_str = json.dumps(data, ensure_ascii=False, indent=2)
+            return f"# {file_path_obj.name}\n\n```json\n{json_str}\n```"
+
         else:
             # 尝试作为文本文件读取
             raise ValueError(f"Unsupported file type: {file_ext}")