Update app.py
Browse files
app.py
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
import gradio as
|
2 |
import pandas as pd
|
3 |
import re
|
4 |
import json
|
@@ -23,7 +23,7 @@ def check_spacing_around_dollar(df):
|
|
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'
|
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}'")
|
@@ -55,79 +55,32 @@ def check_numbers_surrounded_by_dollar(df):
|
|
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
|
91 |
-
|
92 |
-
def extract_text_from_json(text):
|
93 |
try:
|
94 |
-
|
95 |
-
|
96 |
-
|
97 |
-
|
98 |
-
|
99 |
-
|
100 |
|
101 |
-
|
102 |
-
|
103 |
-
|
104 |
-
|
105 |
-
|
106 |
-
|
107 |
-
|
108 |
-
|
109 |
-
|
110 |
-
|
111 |
-
|
112 |
-
|
113 |
-
|
114 |
-
|
115 |
-
|
116 |
-
|
117 |
-
else:
|
118 |
-
return "只支持 CSV 和 XLSX 檔案"
|
119 |
-
|
120 |
-
# 執行檢查
|
121 |
-
errors1 = check_spacing_around_dollar(df)
|
122 |
-
errors2 = check_spacing_between_dollars(df)
|
123 |
-
errors3 = check_numbers_surrounded_by_dollar(df)
|
124 |
-
|
125 |
-
return {
|
126 |
-
"第一個檢查": errors1,
|
127 |
-
"第二個檢查": errors2,
|
128 |
-
"第三個檢查": errors3
|
129 |
-
}
|
130 |
|
|
|
131 |
iface = gr.Interface(
|
132 |
fn=process_file,
|
133 |
inputs=gr.File(label="上傳 CSV 或 XLSX 檔案"),
|
|
|
1 |
+
import gradio as gr
|
2 |
import pandas as pd
|
3 |
import re
|
4 |
import json
|
|
|
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}'")
|
|
|
55 |
|
56 |
# 處理檔案並執行檢查
|
57 |
def process_file(file):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
try:
|
59 |
+
if file.name.endswith('.csv'):
|
60 |
+
df = pd.read_csv(file.name)
|
61 |
+
elif file.name.endswith('.xlsx'):
|
62 |
+
df = pd.read_excel(file.name)
|
63 |
+
else:
|
64 |
+
return "只支持 CSV 和 XLSX 檔案"
|
65 |
|
66 |
+
# 打印 DataFrame 以檢查內容
|
67 |
+
print("讀取的 DataFrame:")
|
68 |
+
print(df.head())
|
69 |
+
|
70 |
+
# 執行檢查
|
71 |
+
errors1 = check_spacing_around_dollar(df)
|
72 |
+
errors2 = check_spacing_between_dollars(df)
|
73 |
+
errors3 = check_numbers_surrounded_by_dollar(df)
|
74 |
+
|
75 |
+
return {
|
76 |
+
"第一個檢查": errors1,
|
77 |
+
"第二個檢查": errors2,
|
78 |
+
"第三個檢查": errors3
|
79 |
+
}
|
80 |
+
except Exception as e:
|
81 |
+
return str(e)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
82 |
|
83 |
+
# Gradio 介面
|
84 |
iface = gr.Interface(
|
85 |
fn=process_file,
|
86 |
inputs=gr.File(label="上傳 CSV 或 XLSX 檔案"),
|