Simple script to display lowfat syntax trees from macula-greek on the command line

gr_tree.py

import xml.etree.ElementTree as ET
from difflib import get_close_matches
from pathlib import Path
import sys


DIR = Path('macula-greek/SBLGNT/lowfat/')
FILES = {
        'MAT': '01-matthew.xml',
        'MRK': '02-mark.xml',
        'LUK': '03-luke.xml',
        'JHN': '04-john.xml',
        'ACT': '05-acts.xml',
        'ROM': '06-romans.xml',
        '1CO': '07-1corinthians.xml',
        '2CO':  '08-2corinthians.xml',
        'GAL': '09-galatians.xml',
        'EPH': '10-ephesians.xml',
        'PHP': '11-philippians.xml',
        'COL': '12-colossians.xml',
        '1TH': '13-1thessalonians.xml',
        '2TH': '14-2thessalonians.xml',
        '1TI': '15-1timothy.xml',
        '2TI': '16-2timothy.xml',
        'TIT': '17-titus.xml',
        'PHM': '18-philemon.xml',
        'HEB': '19-hebrews.xml',
        'JAS': '20-james.xml',
        '1PE': '21-1peter.xml',
        '2PE': '22-2peter.xml',
        '1JN': '23-1john.xml',
        '2JN': '24-2john.xml',
        '3JN': '25-3john.xml',
        'JUD': '26-jude.xml',
        'REV': '27-revelation.xml',
}

target = sys.argv[1]


xml_file = target.split(' ')[0]

if len(sys.argv) > 2:
    SEP = sys.argv[2]
else: 
    SEP = '\t'
if xml_file not in FILES:
    print(f"{target} not found in files")
    print(f"did you mean {', '.join(get_close_matches(xml_file, FILES.keys()))}")
    exit()
tree = ET.parse(str(DIR / Path(FILES[xml_file])))
root = tree.getroot()


def handle_wg(xs, level, sep, last_level_was_blank):
    buffer = []
    for x in xs:
        if x.tag == 'wg':
            has_words = len(x.findall('./w')) < 1
            # head = f"{x.get('class', '')}[{x.get('role', '')}] ".replace('[]', '')
            head = f"{x.get('role', '')} ".upper()
            
            wg_type_mod = -1 if last_level_was_blank else 0
            if head.strip():
                buffer.append('\n' + sep * level + head + ' '.join(handle_wg(x.findall("./"), level + 1 + wg_type_mod, sep, has_words)))
            else:
                buffer.append(' '.join(handle_wg(x.findall("./"), level + 1 + wg_type_mod, sep, has_words)))
        if x.tag == 'w':
            role = x.get("role", '').upper()
            cl = x.get('class', '').upper()
            after = x.get('after', '').strip()
            if cl.strip().lower() == 'conj':
                buffer.append('\n' + sep * (level) + (role + ' ' + x.text + after).strip())
                level = level - 1
            elif role.strip():
                buffer.append('\n' + sep * level + (role + ' ' +  x.text + after).strip())
            else:
                buffer.append(x.text + after)
    return buffer

            

for elem in root.findall('.//sentence'):
    milestones = [e.get('id').strip() for e in elem.findall('.//milestone')]
    if not target in milestones:
        continue
    p = elem.find('./p').text
    for e in elem.findall('./wg'):
        print(' '.join(handle_wg(e.findall('./'), -1, SEP, False)).strip())