Spaces:
Paused
Paused
Update app.py
Browse files
app.py
CHANGED
@@ -12,9 +12,6 @@ import PyPDF2
|
|
12 |
|
13 |
app = Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
|
14 |
|
15 |
-
# Global variable to track conversion progress
|
16 |
-
conversion_progress = 0
|
17 |
-
|
18 |
app.layout = dbc.Container([
|
19 |
html.H1("Auto-Wiki", className="my-4"),
|
20 |
dcc.Upload(
|
@@ -37,11 +34,10 @@ app.layout = dbc.Container([
|
|
37 |
accept='.docx,.pdf'
|
38 |
),
|
39 |
html.Div(id='upload-output'),
|
40 |
-
dbc.
|
41 |
-
dbc.
|
42 |
dbc.Button("Convert and Download", id="convert-button", color="primary", className="mt-3", disabled=True),
|
43 |
-
dcc.Download(id="download-zip")
|
44 |
-
dcc.Interval(id='interval-component', interval=500, n_intervals=0)
|
45 |
])
|
46 |
|
47 |
def process_docx(contents, filename):
|
@@ -64,9 +60,8 @@ def process_pdf(contents, filename):
|
|
64 |
return '\n\n'.join(full_text)
|
65 |
|
66 |
def process_files(contents, filenames):
|
67 |
-
global conversion_progress
|
68 |
processed_files = []
|
69 |
-
for
|
70 |
if n.lower().endswith('.docx'):
|
71 |
text = process_docx(c, n)
|
72 |
elif n.lower().endswith('.pdf'):
|
@@ -75,7 +70,6 @@ def process_files(contents, filenames):
|
|
75 |
continue # Skip unsupported file types
|
76 |
md = markdown.markdown(text)
|
77 |
processed_files.append((n.replace('.docx', '.md').replace('.pdf', '.md'), md))
|
78 |
-
conversion_progress = (i + 1) / len(contents) * 100
|
79 |
time.sleep(0.1) # Simulate processing time
|
80 |
|
81 |
zip_buffer = io.BytesIO()
|
@@ -88,20 +82,16 @@ def process_files(contents, filenames):
|
|
88 |
@app.callback(
|
89 |
[Output('upload-output', 'children'),
|
90 |
Output('convert-button', 'disabled'),
|
91 |
-
Output('upload-
|
92 |
-
Output('
|
93 |
-
Output('conversion-progress', 'value'),
|
94 |
-
Output('conversion-progress', 'style'),
|
95 |
Output('download-zip', 'data')],
|
96 |
[Input('upload-data', 'contents'),
|
97 |
Input('upload-data', 'filename'),
|
98 |
-
Input('convert-button', 'n_clicks'),
|
99 |
-
Input('interval-component', 'n_intervals')],
|
100 |
[State('upload-data', 'contents'),
|
101 |
State('upload-data', 'filename')]
|
102 |
)
|
103 |
-
def update_output(list_of_contents, list_of_names, n_clicks,
|
104 |
-
global conversion_progress
|
105 |
ctx = callback_context
|
106 |
if not ctx.triggered:
|
107 |
return no_update
|
@@ -114,27 +104,18 @@ def update_output(list_of_contents, list_of_names, n_clicks, n_intervals, conten
|
|
114 |
html.Hr()
|
115 |
]) for name in list_of_names
|
116 |
]
|
117 |
-
return children, False,
|
118 |
return no_update
|
119 |
|
120 |
if ctx.triggered[0]['prop_id'] == 'convert-button.n_clicks':
|
121 |
-
if n_clicks is None:
|
122 |
-
return no_update
|
123 |
-
|
124 |
-
if not contents:
|
125 |
return no_update
|
126 |
|
127 |
-
|
128 |
-
|
129 |
-
|
130 |
|
131 |
-
return no_update, True,
|
132 |
-
|
133 |
-
if ctx.triggered[0]['prop_id'] == 'interval-component.n_intervals':
|
134 |
-
if conversion_progress == 100:
|
135 |
-
return no_update, False, 100, {"visibility": "visible"}, 100, {"visibility": "visible"}, dcc.send_bytes(process_files(contents, filenames), "converted_files.zip")
|
136 |
-
else:
|
137 |
-
return no_update, True, 100, {"visibility": "visible"}, conversion_progress, {"visibility": "visible"}, None
|
138 |
|
139 |
return no_update
|
140 |
|
|
|
12 |
|
13 |
app = Dash(__name__, external_stylesheets=[dbc.themes.BOOTSTRAP])
|
14 |
|
|
|
|
|
|
|
15 |
app.layout = dbc.Container([
|
16 |
html.H1("Auto-Wiki", className="my-4"),
|
17 |
dcc.Upload(
|
|
|
34 |
accept='.docx,.pdf'
|
35 |
),
|
36 |
html.Div(id='upload-output'),
|
37 |
+
dbc.Spinner(html.Div(id="upload-spinner"), color="primary", type="grow", style={"display": "none"}),
|
38 |
+
dbc.Spinner(html.Div(id="conversion-spinner"), color="secondary", type="grow", style={"display": "none"}),
|
39 |
dbc.Button("Convert and Download", id="convert-button", color="primary", className="mt-3", disabled=True),
|
40 |
+
dcc.Download(id="download-zip")
|
|
|
41 |
])
|
42 |
|
43 |
def process_docx(contents, filename):
|
|
|
60 |
return '\n\n'.join(full_text)
|
61 |
|
62 |
def process_files(contents, filenames):
|
|
|
63 |
processed_files = []
|
64 |
+
for c, n in zip(contents, filenames):
|
65 |
if n.lower().endswith('.docx'):
|
66 |
text = process_docx(c, n)
|
67 |
elif n.lower().endswith('.pdf'):
|
|
|
70 |
continue # Skip unsupported file types
|
71 |
md = markdown.markdown(text)
|
72 |
processed_files.append((n.replace('.docx', '.md').replace('.pdf', '.md'), md))
|
|
|
73 |
time.sleep(0.1) # Simulate processing time
|
74 |
|
75 |
zip_buffer = io.BytesIO()
|
|
|
82 |
@app.callback(
|
83 |
[Output('upload-output', 'children'),
|
84 |
Output('convert-button', 'disabled'),
|
85 |
+
Output('upload-spinner', 'style'),
|
86 |
+
Output('conversion-spinner', 'style'),
|
|
|
|
|
87 |
Output('download-zip', 'data')],
|
88 |
[Input('upload-data', 'contents'),
|
89 |
Input('upload-data', 'filename'),
|
90 |
+
Input('convert-button', 'n_clicks')],
|
|
|
91 |
[State('upload-data', 'contents'),
|
92 |
State('upload-data', 'filename')]
|
93 |
)
|
94 |
+
def update_output(list_of_contents, list_of_names, n_clicks, contents, filenames):
|
|
|
95 |
ctx = callback_context
|
96 |
if not ctx.triggered:
|
97 |
return no_update
|
|
|
104 |
html.Hr()
|
105 |
]) for name in list_of_names
|
106 |
]
|
107 |
+
return children, False, {"display": "none"}, {"display": "none"}, None
|
108 |
return no_update
|
109 |
|
110 |
if ctx.triggered[0]['prop_id'] == 'convert-button.n_clicks':
|
111 |
+
if n_clicks is None or not contents:
|
|
|
|
|
|
|
112 |
return no_update
|
113 |
|
114 |
+
def process_and_download():
|
115 |
+
zip_data = process_files(contents, filenames)
|
116 |
+
return dcc.send_bytes(zip_data, "converted_files.zip")
|
117 |
|
118 |
+
return no_update, True, {"display": "none"}, {"display": "block"}, process_and_download()
|
|
|
|
|
|
|
|
|
|
|
|
|
119 |
|
120 |
return no_update
|
121 |
|