Update app.py
Browse files
app.py
CHANGED
|
@@ -1,4 +1,90 @@
|
|
| 1 |
-
import gradio as gr
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
import pandas as pd
|
| 3 |
import re
|
| 4 |
import json
|
|
|
|
| 1 |
+
import gradio as grimport gradio as gr
|
| 2 |
+
import pandas as pd
|
| 3 |
+
import re
|
| 4 |
+
import json
|
| 5 |
+
|
| 6 |
+
# 提取 JSON 格式中的文本部分
|
| 7 |
+
def extract_text_from_json(text):
|
| 8 |
+
try:
|
| 9 |
+
data = json.loads(text)
|
| 10 |
+
if isinstance(data, dict):
|
| 11 |
+
# 提取 JSON 中可能包含的文本內容
|
| 12 |
+
if 'question' in data:
|
| 13 |
+
return data['question']['content']
|
| 14 |
+
if 'content' in data:
|
| 15 |
+
return data['content']
|
| 16 |
+
except json.JSONDecodeError:
|
| 17 |
+
return text
|
| 18 |
+
return text
|
| 19 |
+
|
| 20 |
+
# 第一個檢查:檢查 $ 符號前後是否有空格
|
| 21 |
+
def check_spacing_around_dollar(df):
|
| 22 |
+
errors = []
|
| 23 |
+
for i, row in df.iterrows():
|
| 24 |
+
for col in df.columns:
|
| 25 |
+
text = extract_text_from_json(str(row[col]))
|
| 26 |
+
matches = re.finditer(r'(\$\S+|\S+\$)', text)
|
| 27 |
+
for match in matches:
|
| 28 |
+
if (match.start() > 0 and text[match.start() - 1] != ' ') or (match.end() < len(text) and text[match.end()] != ' '):
|
| 29 |
+
errors.append(f"行 {i+1} 列 '{col}': '{text}'")
|
| 30 |
+
return errors
|
| 31 |
+
|
| 32 |
+
# 第二個檢查:檢查 $ 符號之間是否有空格
|
| 33 |
+
def check_spacing_between_dollars(df):
|
| 34 |
+
errors = []
|
| 35 |
+
for i, row in df.iterrows():
|
| 36 |
+
for col in df.columns:
|
| 37 |
+
text = extract_text_from_json(str(row[col]))
|
| 38 |
+
matches = re.finditer(r'\$\S+?(?=\$)', text)
|
| 39 |
+
for match in matches:
|
| 40 |
+
if text[match.end()] != ' ' and text[match.start() - 1] != ' ':
|
| 41 |
+
errors.append(f"行 {i+1} 列 '{col}': '{text}'")
|
| 42 |
+
return errors
|
| 43 |
+
|
| 44 |
+
# 第三個檢查:檢查數字前後是否有 $ 符號
|
| 45 |
+
def check_numbers_surrounded_by_dollar(df):
|
| 46 |
+
errors = []
|
| 47 |
+
for i, row in df.iterrows():
|
| 48 |
+
for col in df.columns:
|
| 49 |
+
text = extract_text_from_json(str(row[col]))
|
| 50 |
+
matches = re.finditer(r'\b\d+\b', text)
|
| 51 |
+
for match in matches:
|
| 52 |
+
if not (match.start() > 0 and text[match.start() - 1] == '$' and match.end() < len(text) and text[match.end()] == '$'):
|
| 53 |
+
errors.append(f"行 {i+1} 列 '{col}': '{text}'")
|
| 54 |
+
return errors
|
| 55 |
+
|
| 56 |
+
# 處理檔案並執行檢查
|
| 57 |
+
def process_file(file):
|
| 58 |
+
if file.name.endswith('.csv'):
|
| 59 |
+
df = pd.read_csv(file.name)
|
| 60 |
+
elif file.name.endswith('.xlsx'):
|
| 61 |
+
df = pd.read_excel(file.name)
|
| 62 |
+
else:
|
| 63 |
+
return "只支持 CSV 和 XLSX 檔案"
|
| 64 |
+
|
| 65 |
+
# 執行檢查
|
| 66 |
+
errors1 = check_spacing_around_dollar(df)
|
| 67 |
+
errors2 = check_spacing_between_dollars(df)
|
| 68 |
+
errors3 = check_numbers_surrounded_by_dollar(df)
|
| 69 |
+
|
| 70 |
+
return {
|
| 71 |
+
"第一個檢查": errors1,
|
| 72 |
+
"第二個檢查": errors2,
|
| 73 |
+
"第三個檢查": errors3
|
| 74 |
+
}
|
| 75 |
+
|
| 76 |
+
# Gradio 介面
|
| 77 |
+
iface = gr.Interface(
|
| 78 |
+
fn=process_file,
|
| 79 |
+
inputs=gr.File(label="上傳 CSV 或 XLSX 檔案"),
|
| 80 |
+
outputs=gr.JSON(label="檢查結果"),
|
| 81 |
+
title="校對系統",
|
| 82 |
+
description="這個系統會檢查 CSV 或 XLSX 檔案中的格式錯誤,包括 $ 符號和數字的空格錯誤。"
|
| 83 |
+
)
|
| 84 |
+
|
| 85 |
+
if __name__ == "__main__":
|
| 86 |
+
iface.launch()
|
| 87 |
+
|
| 88 |
import pandas as pd
|
| 89 |
import re
|
| 90 |
import json
|