Output Markdown text (name, url, description) from newly added Homebrew Formulae/Casks info.

brew-new-md.py

#!/usr/bin/env python3
# -*- coding: utf-8 -*-

# This script is designed to parse the output of `brew update` commands,
# extract relevant information about new formulae and casks, and then format that information
# for display. It uses regular expressions to identify and extract the name, version, URL,
# and description of each item. The script also includes debug statements to help trace the
# processing of the information. The final output is a formatted list of new formulae and casks
# with their details.

# usage (bash/zsh): brew update 2>&1 | (python3 brew-new-md.py)

# import fileinput
import pprint
import re
import subprocess
import sys
import tempfile


def get_item_info(name, type, info_text):
    lines = info_text.splitlines()
    version, url, description, description_label_match = "", "", "", None
    if type == "formula":
        description = lines[1].strip()
    for line in lines:
        line = line.strip()
        if description_label_match:
            description = line
            description_label_match = None
            continue
        version_match = re.match(rf"^==> {re.escape(name)}.*:\s*([^\(\)]+)\(?.*$", line)
        if version_match:
            version = version_match.group(1).strip()
        url_match = re.match(r"^(http(s?)://.*)$", line)
        if url_match:
            url = url_match.group(1)
        description_label_match = re.match(r"^==> Description$", line)
    # print(
    #     f"Debug: name={name}, type={type}, version={version}, url={url}, description={description}"
    # )
    return version, url, description


def main():
    fp = tempfile.NamedTemporaryFile(mode="w+", delete=True)
    formula, cask = False, False
    items = []
    # input_lines = fileinput.input()
    input_lines = sys.stdin.read().splitlines()
    for line in input_lines:
        line = line.strip()
        item = {}
        if re.match(r"(^==> Outdated.*$)|(^Error:.*$)", line):
            formula, cask = False, False
        if formula or cask:
            pattern_match1 = re.match(r"^([a-zA-Z0-9\-]+):?\s*(.*)$", line)
            pattern_match2 = re.match(r"^([a-zA-Z0-9\-\/]+)@([\d\.]+)$", line)
            if pattern_match2:
                item["name"] = pattern_match2.group(1)
                item["type"] = "formula" if formula else "cask"
                item["version"] = pattern_match2.group(2)
                items.append(item)
                continue
            if pattern_match1:
                item["name"] = pattern_match1.group(1)
                item["type"] = "formula" if formula else "cask"
                if pattern_match1.group(2):
                    item["desc"] = pattern_match1.group(2)
                items.append(item)
        if re.match(r"^==> New Formulae$", line):
            formula = True
            cask = False
        if re.match(r"^==> New Casks$", line):
            formula = False
            cask = True
    for item in items:
        info_text = None
        if item["type"] == "formula":
            info = subprocess.run(["brew", "info", item["name"]], capture_output=True)
        elif item["type"] == "cask":
            info = subprocess.run(
                ["brew", "info", "--cask", item["name"]], capture_output=True
            )
        if info.returncode == 0:
            info_text = info.stdout.decode("utf-8")
            print(f"Debug: info_text for {item['name']}:\n{info_text}\n")
        item["info"] = info_text
        if item["info"]:
            item["version"], item["url"], item["description"] = get_item_info(
                item["name"], item["type"], item["info"]
            )
    fp.write(pprint.pformat(items))
    fp.seek(0)
    # print(fp.read())
    fp.close()
    for item in items:
        name = item.get("name", "")
        url = item.get("url")
        if url:
            print(f"[{name}]({url})")
        else:
            print(name)
        print(f"Type: {item.get('type', '')}")
        print(f"Version: {item.get('version', '')}")
        print(f"Description: {item.get('description', '')}")
        print()


if __name__ == "__main__":
    main()