src/analyzer.py

import spacy
from transformers import pipeline

try:
    nlp = spacy.load("en_core_web_sm")
except OSError:
    import spacy.cli
    spacy.cli.download("en_core_web_sm")
    nlp = spacy.load("en_core_web_sm")

summarizer = pipeline("summarization", model="sshleifer/distilbart-cnn-12-6")
sentiment_task = pipeline("sentiment-analysis", model="distilbert-base-uncased-finetuned-sst-2-english")

def run_analysis(text):
    if not text or len(text.strip()) < 10:
        return {
            "summary": "Document contains insufficient text for analysis.",
            "key_points": [],
            "entities": {"names": [], "dates": [], "organizations": [], "amounts": []},
            "sentiment": "Neutral"
        }

    # Increased from 1500 to 2000 to read more of the document
    clean_text = text[:2000] 
    
    # --- 1. AI Summarization & Key Points ---
    try:
        # Increased max_length and min_length for richer content
        summary_result = summarizer(clean_text, max_length=200, min_length=60, do_sample=False)
        summary = summary_result[0]['summary_text']
        
        # PRO FEATURE: Extract sentences into bullet points
        doc_summary = nlp(summary)
        key_points = [sent.text.strip() for sent in doc_summary.sents if len(sent.text.strip()) > 15]
    except Exception:
        summary = "Summary generation failed due to text complexity."
        key_points = []

    # --- 2. Entity Extraction ---
    doc = nlp(text[:3000])
    entities = {"names": [], "dates": [], "organizations": [], "amounts": []}
    for ent in doc.ents:
        text_val = ent.text.strip()
        if len(text_val) < 2: continue
        if ent.label_ == "PERSON": entities["names"].append(text_val)
        elif ent.label_ in ["DATE", "TIME"]: entities["dates"].append(text_val)
        elif ent.label_ == "ORG": 
            if text_val.upper() not in ["AI", "PDF", "IDP"]: entities["organizations"].append(text_val)
        elif ent.label_ in ["MONEY", "PERCENT", "QUANTITY"]: entities["amounts"].append(text_val)

    for key in entities: entities[key] = list(dict.fromkeys(entities[key]))

    # --- 3. Sentiment Analysis ---
    try:
        sent_res = sentiment_task(clean_text[:512])[0]
        label = sent_res['label']
        sentiment_map = {"POSITIVE": "Positive", "NEGATIVE": "Negative"}
        sentiment = sentiment_map.get(label, "Neutral")
    except Exception:
        sentiment = "Neutral"
    
    return {
        "summary": summary,
        "key_points": key_points,
        "entities": entities,
        "sentiment": sentiment
    }