#!/usr/bin/env python3
"""Create a CSV inventory from the iqon.com page sitemap.

SPEC: reports/live-captures/2026-05-20/page-sitemap.xml
Compliance date: 2026-05-20
Launch type: manual SEO inventory generation
Registry: iqon sitemap inventory parser
"""

from __future__ import annotations

import csv
import sys
import urllib.parse
import xml.etree.ElementTree as ET
from collections import Counter
from pathlib import Path


SITEMAP_NS = {"sm": "http://www.sitemaps.org/schemas/sitemap/0.9"}


def classify_url(url: str, duplicate_count: int) -> tuple[str, str]:
    parsed = urllib.parse.urlparse(url)
    decoded_path = urllib.parse.unquote(parsed.path)

    if duplicate_count > 1:
        return "duplicate", "canonicalize_or_remove_duplicate"
    if "%" in parsed.path:
        return "encoded_multilingual", "decide_hreflang_or_noindex_redirect"
    if decoded_path in {"/homepage/", "/hows-business/"}:
        return "legacy_home_alias", "redirect_to_root_or_rewrite"
    if "retail-wholesail" in decoded_path:
        return "typo_slug", "redirect_to_correct_spelling"
    if decoded_path == "/services-solutions/":
        return "thin_landing", "rewrite_as_services_overview"
    if decoded_path == "/contact/":
        return "contact", "verify_contact_data_then_keep"
    if decoded_path == "/":
        return "homepage", "rewrite_homepage_metadata_and_content"

    return "service_or_content", "review_rewrite_or_merge"


def iter_urls(path: Path) -> list[dict[str, str]]:
    tree = ET.parse(path)
    urls: list[dict[str, str]] = []

    for node in tree.findall("sm:url", SITEMAP_NS):
        loc_node = node.find("sm:loc", SITEMAP_NS)
        lastmod_node = node.find("sm:lastmod", SITEMAP_NS)
        if loc_node is None or not loc_node.text:
            continue

        loc = loc_node.text.strip()
        parsed = urllib.parse.urlparse(loc)
        urls.append(
            {
                "url": loc,
                "decoded_path": urllib.parse.unquote(parsed.path),
                "lastmod": (lastmod_node.text.strip() if lastmod_node is not None and lastmod_node.text else ""),
            }
        )

    counts = Counter(item["url"] for item in urls)
    for item in urls:
        duplicate_count = counts[item["url"]]
        item["duplicate_count"] = str(duplicate_count)
        item["class"], item["recommended_action"] = classify_url(item["url"], duplicate_count)

    return urls


def main() -> int:
    if len(sys.argv) not in {2, 3}:
        print("Usage: iqon-sitemap-inventory.py <page-sitemap.xml> [output.csv]", file=sys.stderr)
        return 2

    rows = iter_urls(Path(sys.argv[1]))
    output = open(sys.argv[2], "w", newline="", encoding="utf-8") if len(sys.argv) == 3 else sys.stdout
    writer = csv.DictWriter(
        output,
        fieldnames=["url", "decoded_path", "lastmod", "duplicate_count", "class", "recommended_action"],
    )
    writer.writeheader()
    writer.writerows(rows)
    if output is not sys.stdout:
        output.close()
    return 0


if __name__ == "__main__":
    raise SystemExit(main())