# 14_generate_static_descriptions.py

import json
from pathlib import Path

# === Top 30 reguł używanych w v4
top_rules = [
    "DL4006", "DL3008", "SC2086", "DL3003", "DL3015", "DL3047", "DL3009", "DL3004", "DL4001", "DL4000",
    "DL3059", "DL3018", "SC2016", "SC2046", "DL3006", "SC2028", "DL3027", "DL3020", "DL3025", "DL3042",
    "DL3013", "DL3007", "DL3033", "SC2043", "DL3019", "DL3005", "DL3002", "DL3048", "DL3045", "DL3032"
]

# === Opisy reguł — pobrane z dokumentacji hadolinta
descriptions = {
    "DL4006": "Set the SHELL option -o pipefail before using RUN with a pipe.",
    "DL3008": "Pin versions in apt-get install. Avoid floating dependencies.",
    "SC2086": "Double quote to prevent globbing and word splitting.",
    "DL3003": "Use WORKDIR to switch to a directory instead of RUN cd.",
    "DL3015": "Avoid installing unnecessary packages to keep the image lean.",
    "DL3047": "Do not use latest tag for the base image.",
    "DL3009": "Delete the apt-get lists after installing packages.",
    "DL3004": "Do not use sudo as it leads to unpredictable behavior in containers.",
    "DL4001": "Either use ADD for local tar archives or COPY for everything else.",
    "DL4000": "MAINTAINER is deprecated. Use LABEL instead.",
    "DL3059": "Multiple consecutive RUN instructions should be combined.",
    "DL3018": "Pin versions in apk add commands.",
    "SC2016": "Expressions don't expand in single quotes. Use double quotes.",
    "SC2046": "Quote this to prevent word splitting.",
    "DL3006": "Always tag the version of the base image explicitly.",
    "SC2028": "Quotes in echo may not behave as expected. Use printf instead.",
    "DL3027": "Use only an allowed registry in the FROM image.",
    "DL3020": "Use COPY instead of ADD for files and folders.",
    "DL3025": "Use COPY instead of ADD unless you need ADD's features.",
    "DL3042": "Avoid cache busting by rearranging ADD/RUN order properly.",
    "DL3013": "Avoid installing unnecessary packages in your container.",
    "DL3007": "Using yum install is discouraged. Prefer apk or apt.",
    "DL3033": "Specify version with pip install to ensure reproducibility.",
    "SC2043": "Use 'case' instead of many 'if' statements for simplicity.",
    "DL3019": "Do not use ADD with URLs; use curl or wget instead.",
    "DL3005": "Do not use apt-get upgrade or dist-upgrade.",
    "DL3002": "Last USER should not be root.",
    "DL3048": "Avoid using the ADD instruction; prefer COPY.",
    "DL3045": "Do not specify the same label multiple times.",
    "DL3032": "Do not use deprecated ADD syntax; use COPY."
}

# === Tworzenie struktury JSON
output_data = {}
for rule in top_rules:
    output_data[rule] = {
        "code": rule,
        "title": descriptions.get(rule, "No title available."),
        "description": descriptions.get(rule, "No description available."),
        "documentation": ""
    }

# === Zapis
output_path = Path("data/metadata/rules_descriptions_en.json")
output_path.parent.mkdir(parents=True, exist_ok=True)
with open(output_path, "w", encoding="utf-8") as f:
    json.dump(output_data, f, indent=2)

print(f"✅ Zapisano {len(output_data)} reguł do {output_path}")