import os
import json
import warnings
from functools import lru_cache
from datetime import date, timedelta
from urllib.parse import urlparse

import pandas as pd
import gradio as gr
import plotly.graph_objects as go

from google.oauth2 import service_account
from google.analytics.data_v1beta import BetaAnalyticsDataClient
from google.analytics.data_v1beta.types import (
    RunReportRequest,
    FilterExpression,
    FilterExpressionList,
    Filter
)

from openai import OpenAI

# ===============================
# RUNTIME SAFETY
# ===============================
warnings.filterwarnings("ignore", category=FutureWarning)
warnings.filterwarnings("ignore", message=".*Invalid file descriptor.*")

# ===============================
# CONFIG
# ===============================
GA4_PROPERTY_ID = os.environ["GA4_PROPERTY_ID"]
SERVICE_ACCOUNT_JSON = json.loads(os.environ["SERVICE_ACCOUNT_JSON"])
OPENAI_API_KEY = os.environ["OPENAI_API_KEY"]
SITE_DOMAIN = "rishabhsoft.com"

llm = OpenAI(api_key=OPENAI_API_KEY)

# ===============================
# GA CLIENT
# ===============================
with open("service_account.json", "w") as f:
    json.dump(SERVICE_ACCOUNT_JSON, f)

creds = service_account.Credentials.from_service_account_file("service_account.json")
ga = BetaAnalyticsDataClient(credentials=creds)

# ===============================
# HELPERS
# ===============================
def clean_path(v):
    if not v:
        return "Unattributed (Page Unknown)"
    p = urlparse(v).path or v
    return "/ (Home)" if p == "/" else p

def classify_source(src):
    if not src or src == "(direct)":
        return "External"
    if src.startswith("/"):
        return "Internal"
    if src.startswith("http"):
        return "Internal" if SITE_DOMAIN in urlparse(src).netloc else "External"
    return "External"

def prev_period(start, end):
    s = pd.to_datetime(start)
    e = pd.to_datetime(end)
    delta = (e - s).days + 1
    prev_end = s - timedelta(days=1)
    prev_start = prev_end - timedelta(days=delta - 1)
    return str(prev_start.date()), str(prev_end.date())

# ===============================
# FAST PAGE LOAD
# ===============================
@lru_cache(maxsize=3)
def fetch_top_pages(start, end):
    req = RunReportRequest(
        property=f"properties/{GA4_PROPERTY_ID}",
        dimensions=[{"name": "pagePath"}],
        metrics=[{"name": "screenPageViews"}],
        date_ranges=[{"start_date": start, "end_date": end}],
        order_bys=[{"metric": {"metric_name": "screenPageViews"}, "desc": True}],
        limit=300
    )
    res = ga.run_report(req)
    return sorted({r.dimension_values[0].value for r in res.rows})

# ===============================
# JOURNEY DATA
# ===============================
def fetch_journey(start, end, landing_page):
    req = RunReportRequest(
        property=f"properties/{GA4_PROPERTY_ID}",
        dimensions=[{"name": "pageReferrer"}, {"name": "pagePath"}],
        metrics=[{"name": "screenPageViews"}],
        date_ranges=[{"start_date": start, "end_date": end}],
        dimension_filter=FilterExpression(
            filter=Filter(
                field_name="landingPage",
                string_filter={"match_type": 4, "value": landing_page}
            )
        ),
        limit=3000
    )

    rows = []
    for r in ga.run_report(req).rows:
        rows.append({
            "From": r.dimension_values[0].value or "(direct)",
            "To": r.dimension_values[1].value,
            "Views": int(r.metric_values[0].value)
        })

    return pd.DataFrame(rows)

# ===============================
# ACTION ATTRIBUTION (FORMS + EMAIL)
# ===============================
def fetch_action_attribution(start, end, landing_page):
    """
    Returns dataframe with enforced schema:
    Final Action Page | Previous Page / Source | Country | Source Type | Action | Count
    """

    ACTION_EVENTS = {
        "Form Submit": [
            "generate_lead",
            "form_submit",
            "submit",
            "contact_form_submit"
        ],
        "Email Click": [
            "email_click",
            "mailto_click",
            "click_email"
        ]
    }

    rows = []

    for action, events in ACTION_EVENTS.items():
        req = RunReportRequest(
            property=f"properties/{GA4_PROPERTY_ID}",
            dimensions=[
                {"name": "pagePath"},
                {"name": "pageReferrer"},
                {"name": "country"},
                {"name": "eventName"}
            ],
            metrics=[{"name": "eventCount"}],
            date_ranges=[{"start_date": start, "end_date": end}],
            dimension_filter=FilterExpression(
                and_group=FilterExpressionList(expressions=[
                    FilterExpression(
                        filter=Filter(
                            field_name="eventName",
                            in_list_filter={"values": events}
                        )
                    ),
                    FilterExpression(
                        filter=Filter(
                            field_name="landingPage",
                            string_filter={"match_type": 4, "value": landing_page}
                        )
                    )
                ])
            ),
            limit=3000
        )

        res = ga.run_report(req)

        for r in res.rows:
            final_page = clean_path(r.dimension_values[0].value)
            prev_page = clean_path(r.dimension_values[1].value)
            country = r.dimension_values[2].value or "Unknown"
            count = int(r.metric_values[0].value)

            if final_page == "Unattributed (Page Unknown)":
                rows.append({
                    "Final Action Page": "Unattributed (Page Unknown)",
                    "Previous Page / Source": "Unknown",
                    "Country": country,
                    "Source Type": "Unknown",
                    "Action": action,
                    "Count": count
                })
            else:
                rows.append({
                    "Final Action Page": final_page,
                    "Previous Page / Source": prev_page,
                    "Country": country,
                    "Source Type": classify_source(prev_page),
                    "Action": action,
                    "Count": count
                })

    EXPECTED_COLUMNS = [
        "Final Action Page",
        "Previous Page / Source",
        "Country",
        "Source Type",
        "Action",
        "Count"
    ]

    df = pd.DataFrame(rows)

    if df.empty:
        return pd.DataFrame(columns=EXPECTED_COLUMNS)

    return df

# ===============================
# AI INTENT CLASSIFIER
# ===============================
@lru_cache(maxsize=100)
def classify_intent(start_page, pages_tuple, converted):
    prompt = f"""
Classify user intent into ONE:
Conversion, Evaluation, Research, Navigation, Low Intent
Journey:
Start Page: {start_page}
Pages Visited: {", ".join(pages_tuple[:5])}
Converted: {"Yes" if converted else "No"}
Return:
Intent: <Intent>
Reason: <Short explanation>
"""
    resp = llm.chat.completions.create(
        model="gpt-4o-mini",
        messages=[{"role": "user", "content": prompt}],
        temperature=0
    )

    intent, reason = "Unknown", ""
    for line in resp.choices[0].message.content.splitlines():
        if line.lower().startswith("intent"):
            intent = line.split(":", 1)[1].strip()
        if line.lower().startswith("reason"):
            reason = line.split(":", 1)[1].strip()

    return intent, reason

def intent_confidence(form_count, page_depth):
    if form_count > 0:
        return "High"
    if page_depth >= 3:
        return "Medium"
    return "Low"

# ===============================
# MAIN ANALYSIS
# ===============================
def run_journey(start, end, landing_page):
    df = fetch_journey(start, end, landing_page)

    if df.empty:
        return None, pd.DataFrame(), "### No data for this selection."

    action_df = fetch_action_attribution(start, end, landing_page)

    if action_df.empty:
        form_count = 0
        email_count = 0
    else:
        form_count = int(
            action_df.loc[action_df["Action"] == "Form Submit", "Count"].sum()
        )
        email_count = int(
            action_df.loc[action_df["Action"] == "Email Click", "Count"].sum()
        )

    total_users = int(df["Views"].sum())
    conv_rate = round((form_count / total_users) * 100, 2) if total_users else 0.0

    top_pages = df.sort_values("Views", ascending=False)["To"].unique().tolist()

    intent, reason = classify_intent(
        clean_path(landing_page),
        tuple(clean_path(p) for p in top_pages),
        form_count > 0
    )
    confidence = intent_confidence(form_count, len(top_pages))

    labels = ["Start", "Exit", "Form Submit", "Email Click"]
    sources, targets, values = [], [], []

    if total_users:
        sources.append(0)
        targets.append(1)
        values.append(total_users - form_count - email_count)

    if form_count:
        sources.append(0)
        targets.append(2)
        values.append(form_count)

    if email_count:
        sources.append(0)
        targets.append(3)
        values.append(email_count)

    fig = go.Figure(go.Sankey(
        node=dict(label=labels, pad=24, thickness=18),
        link=dict(source=sources, target=targets, value=values)
    ))

    fig.update_layout(
        title=f"Journey → Final Actions ({clean_path(landing_page)})",
        height=600
    )

    summary = f"""
### 🧭 Journey Summary
**Start Page:** `{clean_path(landing_page)}`
**Date Range:** {start} → {end}
**Conversions**
- Form Submits: **{form_count}**
- Email Clicks: **{email_count}**
- Conversion Rate: **{conv_rate:.2f}%**
**Intent**
- Primary Intent: **{intent}**
- Confidence: **{confidence}**
- Reason: {reason}
ℹ️ *Unattributed actions are clearly labeled when GA4 does not provide page context.*
"""

    return fig, action_df, summary

# ===============================
# UI
# ===============================
with gr.Blocks() as app:
    gr.Markdown("## 🚀 Page-Aware Customer Journey Attribution (GA4 + AI)")

    with gr.Row():
        start_date = gr.Textbox("2025-12-01", label="Start Date")
        end_date = gr.Textbox(str(date.today()), label="End Date")

    page_path = gr.Dropdown(label="Starting Page", choices=[], allow_custom_value=True)

    with gr.Row():
        load_btn = gr.Button("⚡ Load Pages")
        run_btn = gr.Button("Analyze Journey", variant="primary")

    journey_chart = gr.Plot()
    action_table = gr.Dataframe(label="Final Action Attribution (Page-Scoped)")
    summary_md = gr.Markdown()

    load_btn.click(
        lambda s, e: gr.update(choices=fetch_top_pages(s, e)),
        inputs=[start_date, end_date],
        outputs=page_path
    )

    run_btn.click(
        run_journey,
        inputs=[start_date, end_date, page_path],
        outputs=[journey_chart, action_table, summary_md]
    )

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