import gradio as gr
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
import re
import traceback
from datetime import datetime
from bs4 import BeautifulSoup

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 parse_google_translate_html(filepath):
    try:
        with open(filepath, 'r', encoding='utf-8') as file:
            content = file.read()
        
        soup = BeautifulSoup(content, 'html.parser')

        translations = []
        for div in soup.find_all('div', class_='outer-cell mdl-cell mdl-cell--12-col mdl-shadow--2dp'):
            title = div.find('p', class_='mdl-typography--title')
            if title and "Google Traduttore" in title.text:
                content = div.find('div', class_='content-cell mdl-cell mdl-cell--6-col mdl-typography--body-1')
                if content:
                    text = content.text.strip()
                    link = content.find('a')
                    if link:
                        url = link.get('href', '')
                        query_params = url.split('&')
                        input_lang = output_lang = input_text = ''
                        for param in query_params:
                            if param.startswith('sl='):
                                input_lang = param.split('=')[1]
                            elif param.startswith('tl='):
                                output_lang = param.split('=')[1]
                            elif param.startswith('q='):
                                input_text = param.split('=')[1]
                        
                        input_text = input_text.replace('+', ' ')
                        language = f"{input_lang} -> {output_lang}"
                    else:
                        input_text = ''
                        language = ''

                    translation_match = re.search(r'\s+(?:<a.*?>)?"(.*?)"', str(content))
                    date_match = re.search(r'(\d{1,2}\s+\w{3}\s+\d{4}),\s+(\d{2}:\d{2}:\d{2}\s+\w+)', text)
                    
                    if translation_match and date_match:
                        output_text = translation_match.group(1)
                        date_str, time_str = date_match.groups()
                        try:
                            date = datetime.strptime(f"{date_str} {time_str}", '%d %b %Y %H:%M:%S %Z')
                            formatted_date = date.strftime('%d/%m/%Y')
                            formatted_time = date.strftime('%H:%M:%S')
                        except ValueError:
                            formatted_date = date_str
                            formatted_time = time_str
                        
                        translations.append({
                            'Date': formatted_date,
                            'Time': formatted_time,
                            'Requested translation': input_text,
                            'Language': language
                        })

        if not translations:
            print("No translations found in the file.")
        
        return translations

    except Exception as e:
        print(f"Error parsing HTML file: {str(e)}")
        return []

def google_translate_to_csv(filepath):
    translations = parse_google_translate_html(filepath)
    
    if not translations:
        print("No translations to write to CSV.")
        return None

    output_file = os.path.basename(os.path.splitext(filepath)[0]) + '_converted.csv'
    
    try:
        with open(output_file, 'w', newline='', encoding='utf-8') as csvfile:
            fieldnames = ['Date', 'Time', 'Requested translation', 'Language']
            writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
            
            writer.writeheader()
            for translation in translations:
                writer.writerow(translation)
        
        print(f"Successfully wrote {len(translations)} translations to {output_file}")
        return output_file

    except Exception as e:
        print(f"Error writing to CSV file: {str(e)}")
        return None
        
def dataManipulator(converter, filepath):
    global output_file
    output_file = filepath

    try:
        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', encoding='utf-8', errors='ignore') as file:
                lines = file.readlines()
    
            records = []
            pattern = r'^\[(\d{2}/\d{2}/\d{2}, \d{2}:\d{2}:\d{2})\] (.+?): (.+)$'
    
            for line in lines:
                line = line.strip()
                match = re.match(pattern, line)
                if match:
                    date_time, sender, message = match.groups()
                    date, time = date_time.split(', ')
                    
                    # Remove any leading special characters from the message
                    message = re.sub(r'^[\u200E\u200F\u202A-\u202E]', '', message)
                    
                    records.append({
                        "date": date,
                        "time": time,
                        "sender": sender,
                        "message": message
                    })
                else:
                    # If the line doesn't match the pattern, it might be a system message or continuation
                    if records:
                        records[-1]["message"] += " " + line
    
            output_file = os.path.basename(os.path.splitext(filepath)[0]) + '_converted.csv'
            
            with open(output_file, 'w', newline='', encoding='utf-8') 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), ""
        if converter == "Google Translate Converter":
            output_file = google_translate_to_csv(filepath)
            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), "You need to select a converter before"

    except Exception as e:
        error_message = f"An error occurred: {str(e)}\n\nTraceback:\n{traceback.format_exc()}"
        return gr.DownloadButton(label="Download not ready", value="output_file", interactive=False), error_message
    

demo = gr.Interface(
    dataManipulator,
    [
        gr.Radio(["Email Converter", "Calendar Converter", "AppleHealth Converter", "AppleHealth GPS Converter", "WhatsApp Converter", "Google Foto Converter", "Google Translate Converter"], label="Select a converter:"),
        gr.File(label="Upload a file"),
    ],
    outputs=[
        gr.DownloadButton(label="Download not ready", value="output_file", interactive=False),
        gr.Textbox(label="Error Message", visible=True)
            ],
    allow_flagging="never",
    description="""
    # Data Manipulator
    ## This space is designed to convert different datasets into .csv for the workshop [Data Physicalization Practices for Exploiting Personal Data](https://master-interaction-design.notion.site/Data-Physicalization-Practices-for-Exploiting-Personal-Data-0b5b228f0c024c27a66d9bac1c53fd6b?pvs=4).

    You can convert the following types of files:
    1. **Email converter**: you can convert the mbox file that your email app can output or can be exported from Google Takeout (if you have a Gmail account)
    2. **Calendar converter**: you can convert the .ics file of any calendar you want
    3. **AppleHealth Converter**: you can convert .xml files from your AppleHealth application
    4. **AppleHealth GPS Converter**: you can convert any .gpx file (tested only with files from AppleHealth application)
    5. **WhatsApp Converter**: you can convert any WhatsApp chat exported as .txt file
    6. **Google Foto Converter**: you can convert multiple JSON files, please upload a .zip file that only contains JSON files to be inserted into a CSV file
    7. **Google Translate Converter**: you can convert a single .html file from Google Takeout -> Google Translate Activity
    """,
    article="""
    The workshop is sponsored by the [Swiss Design Network](https://swissdesignnetwork.ch/) and the [MAKEAWARE! - Spearhead Project](https://spearhead-amr.github.io/makeaware/) and carried out at the [SUPSI FabLab](https://www.supsi.ch/fablab) in the context of the [Master of Arts in Interaction Design](https://maind.supsi.ch/master-interaction-design/en).
    """,
    )

if __name__ == "__main__":
    demo.launch()