add xls file suport (#3321)

api/app.py

@@ -4,12 +4,15 @@ from werkzeug.exceptions import Unauthorized
 
 if not os.environ.get("DEBUG") or os.environ.get("DEBUG").lower() != 'true':
     from gevent import monkey
+
     monkey.patch_all()
     # if os.environ.get("VECTOR_STORE") == 'milvus':
     import grpc.experimental.gevent
+
     grpc.experimental.gevent.init_gevent()
 
     import langchain
+
     langchain.verbose = True
 
 import json
@@ -44,6 +47,7 @@ from services.account_service import AccountService
 # DO NOT REMOVE BELOW
 from events import event_handlers
 from models import account, dataset, model, source, task, tool, tools, web
+
 # DO NOT REMOVE ABOVE
 
 
@@ -51,7 +55,7 @@ warnings.simplefilter("ignore", ResourceWarning)
 
 # fix windows platform
 if os.name == "nt":
-    os.system('tzutil /s "UTC"')    
+    os.system('tzutil /s "UTC"')
 else:
     os.environ['TZ'] = 'UTC'
     time.tzset()
@@ -60,6 +64,7 @@ else:
 class DifyApp(Flask):
     pass
 
+
 # -------------
 # Configuration
 # -------------
@@ -67,6 +72,7 @@ class DifyApp(Flask):
 
 config_type = os.getenv('EDITION', default='SELF_HOSTED')  # ce edition first
 
+
 # ----------------------------
 # Application Factory Function
 # ----------------------------
@@ -192,7 +198,6 @@ def register_blueprints(app):
 app = create_app()
 celery = app.extensions["celery"]
 
-
 if app.config['TESTING']:
     print("App is running in TESTING mode")
 

api/core/rag/extractor/excel_extractor.py

@@ -2,6 +2,7 @@
 from typing import Optional
 
 import pandas as pd
+import xlrd
 
 from core.rag.extractor.extractor_base import BaseExtractor
 from core.rag.models.document import Document
@@ -27,10 +28,37 @@ class ExcelExtractor(BaseExtractor):
         self._autodetect_encoding = autodetect_encoding
 
     def extract(self) -> list[Document]:
+        """ parse excel file"""
+        if self._file_path.endswith('.xls'):
+            return self._extract4xls()
+        elif self._file_path.endswith('.xlsx'):
+            return self._extract4xlsx()
+
+    def _extract4xls(self) -> list[Document]:
+        wb = xlrd.open_workbook(filename=self._file_path)
+        documents = []
+        # loop over all sheets
+        for sheet in wb.sheets():
+            for row_index, row in enumerate(sheet.get_rows(), start=1):
+                row_header = None
+                if self.is_blank_row(row):
+                    continue
+                if row_header is None:
+                    row_header = row
+                    continue
+                item_arr = []
+                for index, cell in enumerate(row):
+                    txt_value = str(cell.value)
+                    item_arr.append(f'{row_header[index].value}:{txt_value}')
+                item_str = "\n".join(item_arr)
+                document = Document(page_content=item_str, metadata={'source': self._file_path})
+                documents.append(document)
+        return documents
+
+    def _extract4xlsx(self) -> list[Document]:
         """Load from file path using Pandas."""
         data = []
-
-        # 使用 Pandas 读取 Excel 文件的每个工作表
+        # Read each worksheet of an Excel file using Pandas
         xls = pd.ExcelFile(self._file_path)
         for sheet_name in xls.sheet_names:
             df = pd.read_excel(xls, sheet_name=sheet_name)
@@ -43,5 +71,18 @@ class ExcelExtractor(BaseExtractor):
                 item = ';'.join(f'{k}:{v}' for k, v in row.items() if pd.notna(v))
                 document = Document(page_content=item, metadata={'source': self._file_path})
                 data.append(document)
-
         return data
+
+    @staticmethod
+    def is_blank_row(row):
+        """
+
+        Determine whether the specified line is a blank line.
+        :param row: row object。
+        :return: Returns True if the row is blank, False otherwise.
+        """
+        # Iterates through the cells and returns False if a non-empty cell is found
+        for cell in row:
+            if cell.value is not None and cell.value != '':
+                return False
+        return True

api/core/rag/extractor/extract_processor.py

@@ -84,7 +84,7 @@ class ExtractProcessor:
                 etl_type = current_app.config['ETL_TYPE']
                 unstructured_api_url = current_app.config['UNSTRUCTURED_API_URL']
                 if etl_type == 'Unstructured':
-                    if file_extension == '.xlsx':
+                    if file_extension == '.xlsx' or file_extension == '.xls':
                         extractor = ExcelExtractor(file_path)
                     elif file_extension == '.pdf':
                         extractor = PdfExtractor(file_path)
@@ -114,7 +114,7 @@ class ExtractProcessor:
                         extractor = UnstructuredTextExtractor(file_path, unstructured_api_url) if is_automatic \
                             else TextExtractor(file_path, autodetect_encoding=True)
                 else:
-                    if file_extension == '.xlsx':
+                    if file_extension == '.xlsx' or file_extension == '.xls':
                         extractor = ExcelExtractor(file_path)
                     elif file_extension == '.pdf':
                         extractor = PdfExtractor(file_path)

api/requirements.txt

@@ -82,3 +82,4 @@ qrcode~=7.4.2
 azure-storage-blob==12.9.0
 azure-identity==1.15.0
 lxml==5.1.0
+xlrd~=2.0.1

api/services/file_service.py

@@ -20,9 +20,10 @@ from services.errors.file import FileTooLargeError, UnsupportedFileTypeError
 IMAGE_EXTENSIONS = ['jpg', 'jpeg', 'png', 'webp', 'gif', 'svg']
 IMAGE_EXTENSIONS.extend([ext.upper() for ext in IMAGE_EXTENSIONS])
 
-ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx', 'docx', 'csv']
-UNSTRUSTURED_ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx',
+ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx', 'xls', 'docx', 'csv']
+UNSTRUSTURED_ALLOWED_EXTENSIONS = ['txt', 'markdown', 'md', 'pdf', 'html', 'htm', 'xlsx', 'xls',
                                    'docx', 'csv', 'eml', 'msg', 'pptx', 'ppt', 'xml', 'epub']
+
 PREVIEW_WORDS_LIMIT = 3000