import streamlit as st
import anthropic, openai, base64, cv2, glob, json, math, os, pytz, random, re, requests, textract, time, zipfile
import plotly.graph_objects as go
import streamlit.components.v1 as components
from datetime import datetime
from audio_recorder_streamlit import audio_recorder
from bs4 import BeautifulSoup
from collections import defaultdict, deque
from dotenv import load_dotenv
from gradio_client import Client
from huggingface_hub import InferenceClient
from io import BytesIO
from PIL import Image
from PyPDF2 import PdfReader
from urllib.parse import quote
from xml.etree import ElementTree as ET
from openai import OpenAI
import extra_streamlit_components as stx
from streamlit.runtime.scriptrunner import get_script_run_ctx
import asyncio
import edge_tts

# 🎯 1. Core Configuration & Setup
st.set_page_config(
    page_title="🚲BikeAI🏆 Claude/GPT Research",
    page_icon="🚲🏆",
    layout="wide",
    initial_sidebar_state="auto",
    menu_items={
        'Get Help': 'https://huggingface.co/awacke1',
        'Report a bug': 'https://huggingface.co/spaces/awacke1',
        'About': "🚲BikeAI🏆 Claude/GPT Research AI"
    }
)
load_dotenv()

# 🔑 2. API Setup & Clients
openai_api_key = os.getenv('OPENAI_API_KEY', "")
anthropic_key = os.getenv('ANTHROPIC_API_KEY_3', "")
xai_key = os.getenv('xai',"")
if 'OPENAI_API_KEY' in st.secrets:
    openai_api_key = st.secrets['OPENAI_API_KEY']
if 'ANTHROPIC_API_KEY' in st.secrets:
    anthropic_key = st.secrets["ANTHROPIC_API_KEY"]

openai.api_key = openai_api_key
claude_client = anthropic.Anthropic(api_key=anthropic_key)
openai_client = OpenAI(api_key=openai.api_key, organization=os.getenv('OPENAI_ORG_ID'))
HF_KEY = os.getenv('HF_KEY')
API_URL = os.getenv('API_URL')

# 📝 3. Session State Management
if 'transcript_history' not in st.session_state:
    st.session_state['transcript_history'] = []
if 'chat_history' not in st.session_state:
    st.session_state['chat_history'] = []
if 'openai_model' not in st.session_state:
    st.session_state['openai_model'] = "gpt-4o-2024-05-13"
if 'messages' not in st.session_state:
    st.session_state['messages'] = []
if 'last_voice_input' not in st.session_state:
    st.session_state['last_voice_input'] = ""
if 'editing_file' not in st.session_state:
    st.session_state['editing_file'] = None
if 'edit_new_name' not in st.session_state:
    st.session_state['edit_new_name'] = ""
if 'edit_new_content' not in st.session_state:
    st.session_state['edit_new_content'] = ""
if 'viewing_prefix' not in st.session_state:
    st.session_state['viewing_prefix'] = None
if 'should_rerun' not in st.session_state:
    st.session_state['should_rerun'] = False
if 'old_val' not in st.session_state:
    st.session_state['old_val'] = None

# 🎨 4. Custom CSS
st.markdown("""
<style>
    .main { background: linear-gradient(to right, #1a1a1a, #2d2d2d); color: #fff; }
    .stMarkdown { font-family: 'Helvetica Neue', sans-serif; }
    .stButton>button {
        margin-right: 0.5rem;
    }
</style>
""", unsafe_allow_html=True)

FILE_EMOJIS = {
    "md": "📝",
    "mp3": "🎵",
}

# 🧠 5. High-Information Content Extraction
def get_high_info_terms(text: str) -> list:
    """Extract high-information terms from text, including key phrases."""
    stop_words = set([
        'the', 'a', 'an', 'and', 'or', 'but', 'in', 'on', 'at', 'to', 'for', 'of', 'with',
        'by', 'from', 'up', 'about', 'into', 'over', 'after', 'is', 'are', 'was', 'were',
        'be', 'been', 'being', 'have', 'has', 'had', 'do', 'does', 'did', 'will', 'would',
        'should', 'could', 'might', 'must', 'shall', 'can', 'may', 'this', 'that', 'these',
        'those', 'i', 'you', 'he', 'she', 'it', 'we', 'they', 'what', 'which', 'who',
        'when', 'where', 'why', 'how', 'all', 'any', 'both', 'each', 'few', 'more', 'most',
        'other', 'some', 'such', 'than', 'too', 'very', 'just', 'there'
    ])

    key_phrases = [
        'artificial intelligence', 'machine learning', 'deep learning', 'neural network',
        'personal assistant', 'natural language', 'computer vision', 'data science',
        'reinforcement learning', 'knowledge graph', 'semantic search', 'time series',
        'large language model', 'transformer model', 'attention mechanism',
        'autonomous system', 'edge computing', 'quantum computing', 'blockchain technology',
        'cognitive science', 'human computer', 'decision making', 'arxiv search',
        'research paper', 'scientific study', 'empirical analysis'
    ]

    # Identify key phrases
    preserved_phrases = []
    lower_text = text.lower()
    for phrase in key_phrases:
        if phrase in lower_text:
            preserved_phrases.append(phrase)
            text = text.replace(phrase, '')

    # Extract individual words
    words = re.findall(r'\b\w+(?:-\w+)*\b', text)
    high_info_words = [
        word.lower() for word in words 
        if len(word) > 3
        and word.lower() not in stop_words
        and not word.isdigit()
        and any(c.isalpha() for c in word)
    ]

    all_terms = preserved_phrases + high_info_words
    seen = set()
    unique_terms = []
    for term in all_terms:
        if term not in seen:
            seen.add(term)
            unique_terms.append(term)

    max_terms = 5
    return unique_terms[:max_terms]

def clean_text_for_filename(text: str) -> str:
    """Remove punctuation and short filler words, return a compact string."""
    text = text.lower()
    text = re.sub(r'[^\w\s-]', '', text)
    words = text.split()
    stop_short = set(['the','and','for','with','this','that','from','just','very','then','been','only','also','about'])
    filtered = [w for w in words if len(w)>3 and w not in stop_short]
    return '_'.join(filtered)[:200]

# 📁 6. File Operations
def generate_filename(prompt, response, file_type="md"):
    """
    Generate filename with meaningful terms and short dense clips from prompt & response.
    The filename should be about 150 chars total, include high-info terms, and a clipped snippet.
    """
    prefix = datetime.now().strftime("%y%m_%H%M") + "_"
    combined = (prompt + " " + response).strip()
    info_terms = get_high_info_terms(combined)
    
    # Include a short snippet from prompt and response
    snippet = (prompt[:100] + " " + response[:100]).strip()
    snippet_cleaned = clean_text_for_filename(snippet)
    
    # Combine info terms and snippet
    # Prioritize info terms in front
    name_parts = info_terms + [snippet_cleaned]
    full_name = '_'.join(name_parts)

    # Trim to ~150 chars
    if len(full_name) > 150:
        full_name = full_name[:150]
    
    filename = f"{prefix}{full_name}.{file_type}"
    return filename

def create_file(prompt, response, file_type="md"):
    """Create file with intelligent naming"""
    filename = generate_filename(prompt.strip(), response.strip(), file_type)
    with open(filename, 'w', encoding='utf-8') as f:
        f.write(prompt + "\n\n" + response)
    return filename

def get_download_link(file):
    """Generate download link for file"""
    with open(file, "rb") as f:
        b64 = base64.b64encode(f.read()).decode()
    return f'<a href="data:file/zip;base64,{b64}" download="{os.path.basename(file)}">📂 Download {os.path.basename(file)}</a>'

# 🔊 7. Audio Processing
def clean_for_speech(text: str) -> str:
    """Clean text for speech synthesis"""
    text = text.replace("\n", " ")
    text = text.replace("</s>", " ")
    text = text.replace("#", "")
    text = re.sub(r"\(https?:\/\/[^\)]+\)", "", text)
    text = re.sub(r"\s+", " ", text).strip()
    return text

@st.cache_resource
def speech_synthesis_html(result):
    """Create HTML for speech synthesis"""
    html_code = f"""
    <html><body>
    <script>
    var msg = new SpeechSynthesisUtterance("{result.replace('"', '')}");
    window.speechSynthesis.speak(msg);
    </script>
    </body></html>
    """
    components.html(html_code, height=0)

async def edge_tts_generate_audio(text, voice="en-US-AriaNeural", rate=0, pitch=0):
    """Generate audio using Edge TTS"""
    text = clean_for_speech(text)
    if not text.strip():
        return None
    rate_str = f"{rate:+d}%"
    pitch_str = f"{pitch:+d}Hz"
    communicate = edge_tts.Communicate(text, voice, rate=rate_str, pitch=pitch_str)
    out_fn = generate_filename(text, text, "mp3")
    await communicate.save(out_fn)
    return out_fn

def speak_with_edge_tts(text, voice="en-US-AriaNeural", rate=0, pitch=0):
    """Wrapper for edge TTS generation"""
    return asyncio.run(edge_tts_generate_audio(text, voice, rate, pitch))

def play_and_download_audio(file_path):
    """Play and provide download link for audio"""
    if file_path and os.path.exists(file_path):
        st.audio(file_path)
        dl_link = f'<a href="data:audio/mpeg;base64,{base64.b64encode(open(file_path,"rb").read()).decode()}" download="{os.path.basename(file_path)}">Download {os.path.basename(file_path)}</a>'
        st.markdown(dl_link, unsafe_allow_html=True)

# 🎬 8. Media Processing
def process_image(image_path, user_prompt):
    """Process image with GPT-4V"""
    with open(image_path, "rb") as imgf:
        image_data = imgf.read()
    b64img = base64.b64encode(image_data).decode("utf-8")
    resp = openai_client.chat.completions.create(
        model=st.session_state["openai_model"],
        messages=[
            {"role": "system", "content": "You are a helpful assistant."},
            {"role": "user", "content": [
                {"type": "text", "text": user_prompt},
                {"type": "image_url", "image_url": {"url": f"data:image/png;base64,{b64img}"}}
            ]}
        ],
        temperature=0.0,
    )
    return resp.choices[0].message.content

def process_audio(audio_path):
    """Process audio with Whisper"""
    with open(audio_path, "rb") as f:
        transcription = openai_client.audio.transcriptions.create(model="whisper-1", file=f)
    st.session_state.messages.append({"role": "user", "content": transcription.text})
    return transcription.text

def process_video(video_path, seconds_per_frame=1):
    """Extract frames from video"""
    vid = cv2.VideoCapture(video_path)
    total = int(vid.get(cv2.CAP_PROP_FRAME_COUNT))
    fps = vid.get(cv2.CAP_PROP_FPS)
    skip = int(fps*seconds_per_frame)
    frames_b64 = []
    for i in range(0, total, skip):
        vid.set(cv2.CAP_PROP_POS_FRAMES, i)
        ret, frame = vid.read()
        if not ret: break
        _, buf = cv2.imencode(".jpg", frame)
        frames_b64.append(base64.b64encode(buf).decode("utf-8"))
    vid.release()
    return frames_b64

def process_video_with_gpt(video_path, prompt):
    """Analyze video frames with GPT-4V"""
    frames = process_video(video_path)
    resp = openai_client.chat.completions.create(
        model=st.session_state["openai_model"],
        messages=[
            {"role":"system","content":"Analyze video frames."},
            {"role":"user","content":[
                {"type":"text","text":prompt},
                *[{"type":"image_url","image_url":{"url":f"data:image/jpeg;base64,{fr}"}} for fr in frames]
            ]}
        ]
    )
    return resp.choices[0].message.content

# 🤖 9. AI Model Integration

def save_full_transcript(query, text):
    """Save full transcript of Arxiv results as a file."""
    create_file(query, text, "md")

def perform_ai_lookup(q, vocal_summary=True, extended_refs=False, titles_summary=True, full_audio=False):
    """Perform Arxiv search and generate audio summaries"""
    start = time.time()
    client = Client("awacke1/Arxiv-Paper-Search-And-QA-RAG-Pattern")
    refs = client.predict(q,20,"Semantic Search","mistralai/Mixtral-8x7B-Instruct-v0.1",api_name="/update_with_rag_md")[0]
    r2 = client.predict(q,"mistralai/Mixtral-8x7B-Instruct-v0.1",True,api_name="/ask_llm")

    result = f"### 🔎 {q}\n\n{r2}\n\n{refs}"

    st.markdown(result)

    # Generate full audio version if requested
    if full_audio:
        complete_text = f"Complete response for query: {q}. {clean_for_speech(r2)} {clean_for_speech(refs)}"
        audio_file_full = speak_with_edge_tts(complete_text)
        st.write("### 📚 Full Audio")
        play_and_download_audio(audio_file_full)

    if vocal_summary:
        main_text = clean_for_speech(r2)
        audio_file_main = speak_with_edge_tts(main_text)
        st.write("### 🎙 Short Audio")
        play_and_download_audio(audio_file_main)

    if extended_refs:
        summaries_text = "Extended references: " + refs.replace('"','')
        summaries_text = clean_for_speech(summaries_text)
        audio_file_refs = speak_with_edge_tts(summaries_text)
        st.write("### 📜 Long Refs")
        play_and_download_audio(audio_file_refs)

    if titles_summary:
        titles = []
        for line in refs.split('\n'):
            m = re.search(r"\[([^\]]+)\]", line)
            if m:
                titles.append(m.group(1))
        if titles:
            titles_text = "Titles: " + ", ".join(titles)
            titles_text = clean_for_speech(titles_text)
            audio_file_titles = speak_with_edge_tts(titles_text)
            st.write("### 🔖 Titles")
            play_and_download_audio(audio_file_titles)

    elapsed = time.time()-start
    st.write(f"**Total Elapsed:** {elapsed:.2f} s")

    # Always create a file with the result
    create_file(q, result, "md")

    return result

def process_with_gpt(text):
    """Process text with GPT-4"""
    if not text: return
    st.session_state.messages.append({"role":"user","content":text})
    with st.chat_message("user"):
        st.markdown(text)
    with st.chat_message("assistant"):
        c = openai_client.chat.completions.create(
            model=st.session_state["openai_model"],
            messages=st.session_state.messages,
            stream=False
        )
        ans = c.choices[0].message.content
        st.write("GPT-4o: " + ans)
        create_file(text, ans, "md")
        st.session_state.messages.append({"role":"assistant","content":ans})
    return ans

def process_with_claude(text):
    """Process text with Claude"""
    if not text: return
    with st.chat_message("user"):
        st.markdown(text)
    with st.chat_message("assistant"):
        r = claude_client.messages.create(
            model="claude-3-sonnet-20240229",
            max_tokens=1000,
            messages=[{"role":"user","content":text}]
        )
        ans = r.content[0].text
        st.write("Claude-3.5: " + ans)
        create_file(text, ans, "md")
        st.session_state.chat_history.append({"user":text,"claude":ans})
    return ans

# 📂 10. File Management
def create_zip_of_files(md_files, mp3_files):
    """Create zip with intelligent naming"""
    md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
    all_files = md_files + mp3_files
    if not all_files:
        return None

    # Collect content for high-info term extraction
    all_content = []
    for f in all_files:
        if f.endswith('.md'):
            with open(f, 'r', encoding='utf-8') as file:
                all_content.append(file.read())
        elif f.endswith('.mp3'):
            all_content.append(os.path.basename(f))
    
    combined_content = " ".join(all_content)
    info_terms = get_high_info_terms(combined_content)
    
    timestamp = datetime.now().strftime("%y%m_%H%M")
    name_text = '_'.join(term.replace(' ', '-') for term in info_terms[:3])
    zip_name = f"{timestamp}_{name_text}.zip"
    
    with zipfile.ZipFile(zip_name,'w') as z:
        for f in all_files:
            z.write(f)
    
    return zip_name

def load_files_for_sidebar():
    """Load and group files for sidebar display"""
    md_files = glob.glob("*.md")
    mp3_files = glob.glob("*.mp3")

    md_files = [f for f in md_files if os.path.basename(f).lower() != 'readme.md']
    all_files = md_files + mp3_files

    groups = defaultdict(list)
    for f in all_files:
        fname = os.path.basename(f)
        prefix = fname[:10]
        groups[prefix].append(f)

    for prefix in groups:
        groups[prefix].sort(key=lambda x: os.path.getmtime(x), reverse=True)

    sorted_prefixes = sorted(groups.keys(), 
                           key=lambda pre: max(os.path.getmtime(x) for x in groups[pre]), 
                           reverse=True)
    return groups, sorted_prefixes

def extract_keywords_from_md(files):
    """Extract keywords from markdown files"""
    text = ""
    for f in files:
        if f.endswith(".md"):
            c = open(f,'r',encoding='utf-8').read()
            text += " " + c
    return get_high_info_terms(text)

def display_file_manager_sidebar(groups, sorted_prefixes):
    """Display file manager in sidebar"""
    st.sidebar.title("🎵 Audio & Docs Manager")

    all_md = []
    all_mp3 = []
    for prefix in groups:
        for f in groups[prefix]:
            if f.endswith(".md"):
                all_md.append(f)
            elif f.endswith(".mp3"):
                all_mp3.append(f)

    top_bar = st.sidebar.columns(3)
    with top_bar[0]:
        if st.button("🗑 DelAllMD"):
            for f in all_md:
                os.remove(f)
            st.session_state.should_rerun = True
    with top_bar[1]:
        if st.button("🗑 DelAllMP3"):
            for f in all_mp3:
                os.remove(f)
            st.session_state.should_rerun = True
    with top_bar[2]:
        if st.button("⬇️ ZipAll"):
            z = create_zip_of_files(all_md, all_mp3)
            if z:
                st.sidebar.markdown(get_download_link(z),unsafe_allow_html=True)

    for prefix in sorted_prefixes:
        files = groups[prefix]
        kw = extract_keywords_from_md(files)
        keywords_str = " ".join(kw) if kw else "No Keywords"
        with st.sidebar.expander(f"{prefix} Files ({len(files)}) - KW: {keywords_str}", expanded=True):
            c1,c2 = st.columns(2)
            with c1:
                if st.button("👀ViewGrp", key="view_group_"+prefix):
                    st.session_state.viewing_prefix = prefix
            with c2:
                if st.button("🗑DelGrp", key="del_group_"+prefix):
                    for f in files:
                        os.remove(f)
                    st.success(f"Deleted group {prefix}!")
                    st.session_state.should_rerun = True

            for f in files:
                fname = os.path.basename(f)
                ctime = datetime.fromtimestamp(os.path.getmtime(f)).strftime("%Y-%m-%d %H:%M:%S")
                st.write(f"**{fname}** - {ctime}")

# 🎯 11. Main Application
def main():
    st.sidebar.markdown("### 🚲BikeAI🏆 Multi-Agent Research")
    tab_main = st.radio("Action:",["🎤 Voice","📸 Media","🔍 ArXiv","📝 Editor"],horizontal=True)

    mycomponent = components.declare_component("mycomponent", path="mycomponent")
    val = mycomponent(my_input_value="Hello")

    # Show input in a text box for editing if detected
    if val:
        val_stripped = val.replace('\n', ' ')
        edited_input = st.text_area("✏️ Edit Input:", value=val_stripped, height=100)
        run_option = st.selectbox("Model:", ["Arxiv", "GPT-4o", "Claude-3.5"])
        col1, col2 = st.columns(2)
        with col1:
            autorun = st.checkbox("⚙ AutoRun", value=False)
        with col2:
            full_audio = st.checkbox("📚FullAudio", value=False, 
                                     help="Generate full audio response")

        input_changed = (val != st.session_state.old_val)

        if autorun and input_changed:
            st.session_state.old_val = val
            if run_option == "Arxiv":
                perform_ai_lookup(edited_input, vocal_summary=True, extended_refs=False, 
                                  titles_summary=True, full_audio=full_audio)
            else:
                if run_option == "GPT-4o":
                    process_with_gpt(edited_input)
                elif run_option == "Claude-3.5":
                    process_with_claude(edited_input)
        else:
            if st.button("▶ Run"):
                st.session_state.old_val = val
                if run_option == "Arxiv":
                    perform_ai_lookup(edited_input, vocal_summary=True, extended_refs=False, 
                                      titles_summary=True, full_audio=full_audio)
                else:
                    if run_option == "GPT-4o":
                        process_with_gpt(edited_input)
                    elif run_option == "Claude-3.5":
                        process_with_claude(edited_input)

    if tab_main == "🔍 ArXiv":
        st.subheader("🔍 Query ArXiv")
        q = st.text_input("🔍 Query:")

        st.markdown("### 🎛 Options")
        vocal_summary = st.checkbox("🎙ShortAudio", value=True)
        extended_refs = st.checkbox("📜LongRefs", value=False)
        titles_summary = st.checkbox("🔖TitlesOnly", value=True)
        full_audio = st.checkbox("📚FullAudio", value=False,
                                 help="Full audio of results")
        full_transcript = st.checkbox("🧾FullTranscript", value=False,
                                      help="Generate a full transcript file")

        if q and st.button("🔍Run"):
            result = perform_ai_lookup(q, vocal_summary=vocal_summary, extended_refs=extended_refs, 
                                       titles_summary=titles_summary, full_audio=full_audio)
            if full_transcript:
                save_full_transcript(q, result)

        st.markdown("### Change Prompt & Re-Run")
        q_new = st.text_input("🔄 Modify Query:")
        if q_new and st.button("🔄 Re-Run with Modified Query"):
            result = perform_ai_lookup(q_new, vocal_summary=vocal_summary, extended_refs=extended_refs, 
                                       titles_summary=titles_summary, full_audio=full_audio)
            if full_transcript:
                save_full_transcript(q_new, result)


    elif tab_main == "🎤 Voice":
        st.subheader("🎤 Voice Input")
        user_text = st.text_area("💬 Message:", height=100)
        user_text = user_text.strip().replace('\n', ' ')
        if st.button("📨 Send"):
            process_with_gpt(user_text)
        st.subheader("📜 Chat History")
        t1,t2=st.tabs(["Claude History","GPT-4o History"])
        with t1:
            for c in st.session_state.chat_history:
                st.write("**You:**", c["user"])
                st.write("**Claude:**", c["claude"])
        with t2:
            for m in st.session_state.messages:
                with st.chat_message(m["role"]):
                    st.markdown(m["content"])

    elif tab_main == "📸 Media":
        st.header("📸 Images & 🎥 Videos")
        tabs = st.tabs(["🖼 Images", "🎥 Video"])
        with tabs[0]:
            imgs = glob.glob("*.png")+glob.glob("*.jpg")
            if imgs:
                c = st.slider("Cols",1,5,3)
                cols = st.columns(c)
                for i,f in enumerate(imgs):
                    with cols[i%c]:
                        st.image(Image.open(f),use_container_width=True)
                        if st.button(f"👀 Analyze {os.path.basename(f)}", key=f"analyze_{f}"):
                            a = process_image(f,"Describe this image.")
                            st.markdown(a)
            else:
                st.write("No images found.")
        with tabs[1]:
            vids = glob.glob("*.mp4")
            if vids:
                for v in vids:
                    with st.expander(f"🎥 {os.path.basename(v)}"):
                        st.video(v)
                        if st.button(f"Analyze {os.path.basename(v)}", key=f"analyze_{v}"):
                            a = process_video_with_gpt(v,"Describe video.")
                            st.markdown(a)
            else:
                st.write("No videos found.")

    elif tab_main == "📝 Editor":
        if getattr(st.session_state,'current_file',None):
            st.subheader(f"Editing: {st.session_state.current_file}")
            new_text = st.text_area("✏️ Content:", st.session_state.file_content, height=300)
            if st.button("💾 Save"):
                with open(st.session_state.current_file,'w',encoding='utf-8') as f:
                    f.write(new_text)
                st.success("Updated!")
                st.session_state.should_rerun = True
        else:
            st.write("Select a file from the sidebar to edit.")

    groups, sorted_prefixes = load_files_for_sidebar()
    display_file_manager_sidebar(groups, sorted_prefixes)

    if st.session_state.viewing_prefix and st.session_state.viewing_prefix in groups:
        st.write("---")
        st.write(f"**Viewing Group:** {st.session_state.viewing_prefix}")
        for f in groups[st.session_state.viewing_prefix]:
            fname = os.path.basename(f)
            ext = os.path.splitext(fname)[1].lower().strip('.')
            st.write(f"### {fname}")
            if ext == "md":
                content = open(f,'r',encoding='utf-8').read()
                st.markdown(content)
            elif ext == "mp3":
                st.audio(f)
            else:
                st.markdown(get_download_link(f), unsafe_allow_html=True)
        if st.button("❌ Close"):
            st.session_state.viewing_prefix = None

    if st.session_state.should_rerun:
        st.session_state.should_rerun = False
        st.rerun()

if __name__=="__main__":
    main()