app.py

import os
import pandas as pd
import streamlit as st
import re
import logging
import nltk
from docx import Document
import io
from langdetect import detect
from collections import Counter
from dotenv import load_dotenv
from langchain_groq import ChatGroq
from langchain_core.output_parsers import StrOutputParser
from langchain_core.prompts import ChatPromptTemplate
from transformers import pipeline


# Load environment variables
load_dotenv()

# Check if Groq API key is available
GROQ_API_KEY = os.getenv("GROQ_API_KEY")
if not GROQ_API_KEY:
    logging.error("Missing Groq API key. Please set the GROQ_API_KEY environment variable.")
    st.error("API key is missing. Please provide a valid API key.")

# Initialize logging
logging.basicConfig(level=logging.INFO, format="%(asctime)s - %(levelname)s - %(message)s")

# Initialize LLM (Groq API)
llm = ChatGroq(temperature=0.5, groq_api_key=GROQ_API_KEY, model_name="llama3-8b-8192")

# Download required NLTK resources
nltk.download("punkt")

# Tone categories for fallback method
tone_categories = {
    "Emotional": ["urgent", "violence", "disappearances", "forced", "killing", "crisis", "concern"],
    "Harsh": ["corrupt", "oppression", "failure", "repression", "exploit", "unjust", "authoritarian"],
    "Somber": ["tragedy", "loss", "pain", "sorrow", "mourning", "grief", "devastation"],
    "Motivational": ["rise", "resist", "mobilize", "inspire", "courage", "change", "determination"],
    "Informative": ["announcement", "event", "scheduled", "update", "details", "protest", "statement"],
    "Positive": ["progress", "unity", "hope", "victory", "together", "solidarity", "uplifting"],
    "Angry": ["rage", "injustice", "fury", "resentment", "outrage", "betrayal"],
    "Fearful": ["threat", "danger", "terror", "panic", "risk", "warning"],
    "Sarcastic": ["brilliant", "great job", "amazing", "what a surprise", "well done", "as expected"],
    "Hopeful": ["optimism", "better future", "faith", "confidence", "looking forward"]
}

# Frame categories for fallback method
frame_categories = {
    "Human Rights & Justice": ["rights", "law", "justice", "legal", "humanitarian"],
    "Political & State Accountability": ["government", "policy", "state", "corruption", "accountability"],
    "Gender & Patriarchy": ["gender", "women", "violence", "patriarchy", "equality"],
    "Religious Freedom & Persecution": ["religion", "persecution", "minorities", "intolerance", "faith"],
    "Grassroots Mobilization": ["activism", "community", "movement", "local", "mobilization"],
    "Environmental Crisis & Activism": ["climate", "deforestation", "water", "pollution", "sustainability"],
    "Anti-Extremism & Anti-Violence": ["extremism", "violence", "hate speech", "radicalism", "mob attack"],
    "Social Inequality & Economic Disparities": ["class privilege", "labor rights", "economic", "discrimination"],
    "Activism & Advocacy": ["justice", "rights", "demand", "protest", "march", "campaign", "freedom of speech"],
    "Systemic Oppression": ["discrimination", "oppression", "minorities", "marginalized", "exclusion"],
    "Intersectionality": ["intersecting", "women", "minorities", "struggles", "multiple oppression"],
    "Call to Action": ["join us", "sign petition", "take action", "mobilize", "support movement"],
    "Empowerment & Resistance": ["empower", "resist", "challenge", "fight for", "stand up"],
    "Climate Justice": ["environment", "climate change", "sustainability", "biodiversity", "pollution"],
    "Human Rights Advocacy": ["human rights", "violations", "honor killing", "workplace discrimination", "law reform"]
}

# Detect language
def detect_language(text):
    try:
        return detect(text)
    except Exception as e:
        logging.error(f"Error detecting language: {e}")
        return "unknown"

# Extract tone using Groq API (or fallback method)
def extract_tone(text):
    try:
        response = llm.chat([{"role": "system", "content": "Analyze the tone of the following text and provide descriptive tone labels."},
                             {"role": "user", "content": text}])
        return response["choices"][0]["message"]["content"].split(", ")
    except Exception as e:
        logging.error(f"Groq API error: {e}")
        return extract_tone_fallback(text)

# Fallback method for tone extraction
def extract_tone_fallback(text):
    detected_tones = set()
    text_lower = text.lower()
    for category, keywords in tone_categories.items():
        if any(word in text_lower for word in keywords):
            detected_tones.add(category)
    return list(detected_tones) if detected_tones else ["Neutral"]

# Extract hashtags
def extract_hashtags(text):
    return re.findall(r"#\w+", text)

# Categorize frames into Major, Significant, and Minor based on frequency
def categorize_frames(frame_list):
    frame_counter = Counter(frame_list)
    categorized_frames = {"Major Focus": [], "Significant Focus": [], "Minor Mention": []}

    sorted_frames = sorted(frame_counter.items(), key=lambda x: x[1], reverse=True)
    
    for i, (frame, count) in enumerate(sorted_frames):
        if i == 0:  # Highest frequency frame
            categorized_frames["Major Focus"].append(frame)
        elif i < 3:  # Top 3 most mentioned frames
            categorized_frames["Significant Focus"].append(frame)
        else:
            categorized_frames["Minor Mention"].append(frame)

    return categorized_frames

# Extract frames using keyword matching and categorize
def extract_frames_fallback(text):
    detected_frames = []
    text_lower = text.lower()

    for category, keywords in frame_categories.items():
        keyword_count = sum(1 for word in keywords if word in text_lower)
        if keyword_count > 0:
            detected_frames.append(category)

    return categorize_frames(detected_frames)

# Extract captions from DOCX
def extract_captions_from_docx(docx_file):
    doc = Document(docx_file)
    captions = {}
    current_post = None
    for para in doc.paragraphs:
        text = para.text.strip()
        if re.match(r"Post \d+", text, re.IGNORECASE):
            current_post = text
            captions[current_post] = []
        elif current_post:
            captions[current_post].append(text)
    return {post: " ".join(lines) for post, lines in captions.items() if lines}

# Extract metadata from Excel file
def extract_metadata_from_excel(excel_file):
    try:
        df = pd.read_excel(excel_file)
        extracted_data = df.to_dict(orient="records")
        return extracted_data
    except Exception as e:
        logging.error(f"Error processing Excel file: {e}")
        return []

# Merge metadata with generated analysis
def merge_metadata_with_generated_data(generated_data, excel_metadata):
    for post_data in excel_metadata:
        post_number = f"Post {post_data.get('Post Number', len(generated_data) + 1)}"
        if post_number in generated_data:
            generated_data[post_number].update(post_data)
        else:
            generated_data[post_number] = post_data  
    return generated_data

# Create DOCX file matching the uploaded format
def create_docx_from_data(extracted_data):
    doc = Document()

    for post_number, data in extracted_data.items():
        doc.add_heading(post_number, level=1)

        ordered_keys = [
            "Post Number", "Date of Post", "Media Type", "Number of Pictures",
            "Number of Videos", "Number of Audios", "Likes", "Comments", "Tagged Audience",
            "Full Caption", "Language", "Tone", "Hashtags", "Frames"
        ]

        for key in ordered_keys:
            value = data.get(key, "N/A")

            if key in ["Tone", "Hashtags"]:
                value = ", ".join(value) if isinstance(value, list) else value
            elif key == "Frames" and isinstance(value, dict):
                frame_text = "\n".join([f"  {category}: {', '.join(frames)}" for category, frames in value.items() if frames])
                value = f"\n{frame_text}" if frame_text else "N/A"

            doc.add_paragraph(f"**{key}:** {value}")

        doc.add_paragraph("\n")

    return doc

# Streamlit app
st.title("AI-Powered Activism Message Analyzer")

st.write("Enter text or upload a DOCX/Excel file for analysis:")

input_text = st.text_area("Input Text", height=200)
uploaded_docx = st.file_uploader("Upload a DOCX file", type=["docx"])
uploaded_excel = st.file_uploader("Upload an Excel file", type=["xlsx"])

output_data = {}

if input_text:
    output_data["Manual Input"] = {
        "Full Caption": input_text,
        "Language": detect_language(input_text),
        "Tone": extract_tone(input_text),
        "Hashtags": extract_hashtags(input_text),
        "Frames": extract_frames_fallback(input_text),
    }

if uploaded_docx:
    captions = extract_captions_from_docx(uploaded_docx)
    for caption, text in captions.items():
        output_data[caption] = {
            "Full Caption": text,
            "Language": detect_language(text),
            "Tone": extract_tone(text),
            "Hashtags": extract_hashtags(text),
            "Frames": extract_frames_fallback(text),
        }

if uploaded_excel:
    excel_metadata = extract_metadata_from_excel(uploaded_excel)
    output_data = merge_metadata_with_generated_data(output_data, excel_metadata)

# Display results in collapsible sections for better UI
if output_data:
    for post_number, data in output_data.items():
        with st.expander(post_number):
            for key, value in data.items():
                st.write(f"**{key}:** {value}")

if output_data:
    docx_output = create_docx_from_data(output_data)
    docx_io = io.BytesIO()
    docx_output.save(docx_io)
    docx_io.seek(0)
    st.download_button("Download Merged Analysis as DOCX", data=docx_io, file_name="merged_analysis.docx")