Add application file

app.py

@@ -0,0 +1,256 @@
+from pathlib import Path
+import gradio as gr
+import re
+import pandas as pd
+import email
+from email import policy
+from email.parser import BytesParser
+import base64
+import quopri
+import xml.etree.ElementTree as ET
+import csv
+import os
+import json
+import gpxpy
+import gpxpy.gpx
+from icalendar import Calendar
+import zipfile
+
+def decode_email_content(content, content_transfer_encoding):
+    if content_transfer_encoding == 'base64':
+        return base64.b64decode(content)
+    elif content_transfer_encoding == 'quoted-printable':
+        return quopri.decodestring(content)
+    return content
+
+def parse_email(raw_email):
+    # Parsing the raw email content
+    msg = BytesParser(policy=policy.default).parsebytes(raw_email)
+
+    # Extracting email details
+    email_details = {
+        "From": msg["From"],
+        "To": msg["To"],
+        "Date": msg["Date"],
+        "Subject": msg["Subject"],
+        "Body": ""
+    }
+
+    # Extracting the email body content
+    if msg.is_multipart():
+        for part in msg.iter_parts():
+            content_type = part.get_content_type()
+            content_disposition = part.get("Content-Disposition")
+            content_transfer_encoding = part.get("Content-Transfer-Encoding")
+            payload = part.get_payload(decode=False)
+
+            if content_type == "text/plain" and content_disposition is None:
+                body = decode_email_content(payload, content_transfer_encoding)
+                charset = part.get_content_charset() or 'utf-8'
+                if isinstance(body, bytes):
+                    body = body.decode(charset)
+                email_details["Body"] += body.replace('\n', ' ').replace('\r', '')
+    else:
+        content_type = msg.get_content_type()
+        content_transfer_encoding = msg.get("Content-Transfer-Encoding")
+        payload = msg.get_payload(decode=False)
+        if content_type == "text/plain":
+            body = decode_email_content(payload, content_transfer_encoding)
+            charset = msg.get_content_charset() or 'utf-8'
+            if isinstance(body, bytes):
+                body = body.decode(charset)
+            email_details["Body"] = body.replace('\n', ' ').replace('\r', '')
+
+    return email_details
+
+def dataManipulator(converter, filepath):
+    global output_file
+    output_file = filepath
+
+    if converter == "Email Converter":
+        records = []
+        
+        with open(filepath, 'rb') as file:
+            raw_email_data = file.read()
+        
+        email_entries = raw_email_data.split(b'\nFrom ')
+
+        for raw_email in email_entries:
+            if not raw_email.startswith(b'From '):
+                raw_email = b'From ' + raw_email
+            
+            parsed_email = parse_email(raw_email)
+            
+            record_data = {
+                "date and time": parsed_email["Date"],
+                "from": parsed_email["From"],
+                "to": parsed_email["To"],
+                "Cc": "",  # Add Cc if needed, parse_email function does not extract it by default
+                "Subject": parsed_email["Subject"],
+                "Content": parsed_email["Body"]
+            }
+            
+            records.append(record_data)
+
+        output_file = os.path.basename(os.path.splitext(filepath)[0]) + '_converted.csv'
+        
+        columns = ["date and time", "from", "to", "Cc", "Subject", "Content"]
+        
+        with open(output_file, 'w', newline='') as csvfile:
+            writer = csv.DictWriter(csvfile, fieldnames=columns)
+            
+            writer.writeheader()
+            for record in records:
+                writer.writerow(record)
+        
+        return gr.DownloadButton(label=f"Download {output_file}", value=output_file, interactive=True)
+    if converter == "Calendar Converter":
+        with open(filepath, 'rb') as file:
+            calendar = Calendar.from_ical(file.read())
+
+        records = []
+        for component in calendar.walk():
+            if component.name == "VEVENT":
+                records.append({
+                    "summary": component.get('summary'),
+                    "dtstart": component.get('dtstart').dt,
+                    "dtend": component.get('dtend').dt,
+                    "description": component.get('description'),
+                    "location": component.get('location')
+                })
+
+        output_file = os.path.basename(os.path.splitext(filepath)[0]) + '_converted.csv'
+        
+        with open(output_file, 'w', newline='') as csvfile:
+            fieldnames = ["summary", "dtstart", "dtend", "description", "location"]
+            writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
+            
+            writer.writeheader()
+            for record in records:
+                writer.writerow(record)
+        
+        return gr.DownloadButton(label=f"Download {output_file}", value=output_file, interactive=True)
+    if converter == "AppleHealth Converter":
+        tree = ET.parse(filepath)
+        root = tree.getroot()
+        records = []
+        
+        columns = ["startDate", "endDate", "device", "sourceName", "type", "unit", "value"]
+        
+        for record in root.findall('Record'):
+            record_data = {key: record.attrib.get(key, '') for key in columns}
+            records.append(record_data)
+        
+        output_file = os.path.basename(os.path.splitext(filepath)[0]) + '_converted.csv'
+        
+        with open(output_file, 'w', newline='') as csvfile:
+            writer = csv.DictWriter(csvfile, fieldnames=columns)
+            
+            writer.writeheader()
+            for record in records:
+                writer.writerow(record)
+        
+        return gr.DownloadButton(label=f"Download {output_file}", value=output_file, interactive=True)
+    if converter == "AppleHealth GPS Converter":
+        with open(filepath, 'r') as filepath:
+            gpx = gpxpy.parse(filepath)
+
+        records = []
+        for track in gpx.tracks:
+            for segment in track.segments:
+                for point in segment.points:
+                    records.append({
+                        "latitude": point.latitude,
+                        "longitude": point.longitude,
+                        "elevation": point.elevation,
+                        "time": point.time
+                    })
+
+        output_file = os.path.basename(os.path.splitext(filepath.name)[0]) + '_converted.csv'
+        
+        with open(output_file, 'w', newline='') as csvfile:
+            fieldnames = records[0].keys()
+            writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
+            
+            writer.writeheader()
+            for record in records:
+                writer.writerow(record)
+        
+        return gr.DownloadButton(label=f"Download {output_file}", value=output_file, interactive=True)
+    if converter == "WhatsApp Converter":
+        with open(filepath, 'r', errors='ignore') as file:
+            lines = file.readlines()
+
+        records = []
+        for line in lines:
+            if ', ' in line and ': ' in line:
+                date_time, message = line.split(' - ', 1)
+                date, time = date_time.split(', ')
+                sender, message = message.split(': ', 1)
+                records.append({
+                    "date": date,
+                    "time": time,
+                    "sender": sender,
+                    "message": message
+                })
+
+        output_file = os.path.basename(os.path.splitext(filepath)[0]) + '_converted.csv'
+        
+        with open(output_file, 'w', newline='') as csvfile:
+            fieldnames = ["date", "time", "sender", "message"]
+            writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
+            
+            writer.writeheader()
+            for record in records:
+                writer.writerow(record)
+        
+        return gr.DownloadButton(label=f"Download {output_file}", value=output_file, interactive=True)
+    if converter == "Google Foto Converter":
+        records = []
+        # Unzip the file
+        with zipfile.ZipFile(filepath, 'r') as zip_ref:
+            zip_ref.extractall('json_folder')
+
+        # Process the extracted files
+        records = []
+        for filename in os.listdir('json_folder'):
+            if filename.endswith('.json'):
+                with open(os.path.join('json_folder', filename), 'r') as json_file:
+                    data = json.load(json_file)
+                    records.append(data)
+
+        for filename in os.listdir('json_folder'):
+            if filename.endswith('.json'):
+                with open(os.path.join('json_folder', filename), 'r') as json_file:
+                    data = json.load(json_file)
+                    records.append(data)
+
+        output_file = 'googleFotoConverted.csv'
+        
+        with open(output_file, 'w', newline='') as csvfile:
+            fieldnames = set()
+            for record in records:
+                fieldnames.update(record.keys())
+            writer = csv.DictWriter(csvfile, fieldnames=list(fieldnames))
+            
+            writer.writeheader()
+            for record in records:
+                writer.writerow(record)
+        
+        return gr.DownloadButton(label=f"Download {output_file}", value=output_file, interactive=True)
+    else:
+        return gr.DownloadButton(label="Download not ready", value="output_file", interactive=False)
+    
+
+demo = gr.Interface(
+    dataManipulator,
+    [
+        gr.Radio(["Email Converter", "Calendar Converter", "AppleHealth Converter", "AppleHealth GPS Converter", "WhatsApp Converter", "Google Foto Converter"], label="Select a converter:"),
+        gr.File(label="Upload a file"),
+    ],
+    outputs=gr.DownloadButton(label="Download not ready", value="output_file", interactive=False),
+    allow_flagging="never",
+)
+
+if __name__ == "__main__":
+    demo.launch()