Spaces:
Sleeping
Sleeping
Tuchuanhuhuhu
commited on
Commit
·
40e7d1c
1
Parent(s):
6431f64
优化Excel文档加载方式
Browse files- modules/llama_func.py +4 -1
- modules/utils.py +5 -9
modules/llama_func.py
CHANGED
|
@@ -70,7 +70,10 @@ def get_documents(file_src):
|
|
| 70 |
text_raw = loader.load_data(file=filepath)[0].text
|
| 71 |
elif file_type == ".xlsx":
|
| 72 |
logging.debug("Loading Excel...")
|
| 73 |
-
|
|
|
|
|
|
|
|
|
|
| 74 |
else:
|
| 75 |
logging.debug("Loading text file...")
|
| 76 |
with open(filepath, "r", encoding="utf-8") as f:
|
|
|
|
| 70 |
text_raw = loader.load_data(file=filepath)[0].text
|
| 71 |
elif file_type == ".xlsx":
|
| 72 |
logging.debug("Loading Excel...")
|
| 73 |
+
text_list = excel_to_string(filepath)
|
| 74 |
+
for elem in text_list:
|
| 75 |
+
documents.append(Document(elem))
|
| 76 |
+
continue
|
| 77 |
else:
|
| 78 |
logging.debug("Loading text file...")
|
| 79 |
with open(filepath, "r", encoding="utf-8") as f:
|
modules/utils.py
CHANGED
|
@@ -504,15 +504,15 @@ def add_details(lst):
|
|
| 504 |
return nodes
|
| 505 |
|
| 506 |
|
| 507 |
-
def sheet_to_string(sheet):
|
| 508 |
-
result =
|
| 509 |
for index, row in sheet.iterrows():
|
| 510 |
row_string = ""
|
| 511 |
for column in sheet.columns:
|
| 512 |
row_string += f"{column}: {row[column]}, "
|
| 513 |
row_string = row_string.rstrip(", ")
|
| 514 |
row_string += "."
|
| 515 |
-
result
|
| 516 |
return result
|
| 517 |
|
| 518 |
def excel_to_string(file_path):
|
|
@@ -520,17 +520,13 @@ def excel_to_string(file_path):
|
|
| 520 |
excel_file = pd.read_excel(file_path, engine='openpyxl', sheet_name=None)
|
| 521 |
|
| 522 |
# 初始化结果字符串
|
| 523 |
-
result =
|
| 524 |
|
| 525 |
# 遍历每一个工作表
|
| 526 |
for sheet_name, sheet_data in excel_file.items():
|
| 527 |
-
# 将工作表名称添加到结果字符串
|
| 528 |
-
result += f"Sheet: {sheet_name}\n"
|
| 529 |
|
| 530 |
# 处理当前工作表并添加到结果字符串
|
| 531 |
-
result += sheet_to_string(sheet_data)
|
| 532 |
|
| 533 |
-
# 在不同工作表之间添加分隔符
|
| 534 |
-
result += "\n" + ("-" * 20) + "\n\n"
|
| 535 |
|
| 536 |
return result
|
|
|
|
| 504 |
return nodes
|
| 505 |
|
| 506 |
|
| 507 |
+
def sheet_to_string(sheet, sheet_name = None):
|
| 508 |
+
result = []
|
| 509 |
for index, row in sheet.iterrows():
|
| 510 |
row_string = ""
|
| 511 |
for column in sheet.columns:
|
| 512 |
row_string += f"{column}: {row[column]}, "
|
| 513 |
row_string = row_string.rstrip(", ")
|
| 514 |
row_string += "."
|
| 515 |
+
result.append(row_string)
|
| 516 |
return result
|
| 517 |
|
| 518 |
def excel_to_string(file_path):
|
|
|
|
| 520 |
excel_file = pd.read_excel(file_path, engine='openpyxl', sheet_name=None)
|
| 521 |
|
| 522 |
# 初始化结果字符串
|
| 523 |
+
result = []
|
| 524 |
|
| 525 |
# 遍历每一个工作表
|
| 526 |
for sheet_name, sheet_data in excel_file.items():
|
|
|
|
|
|
|
| 527 |
|
| 528 |
# 处理当前工作表并添加到结果字符串
|
| 529 |
+
result += sheet_to_string(sheet_data, sheet_name=sheet_name)
|
| 530 |
|
|
|
|
|
|
|
| 531 |
|
| 532 |
return result
|