import re
from collections import Counter
from collections.abc import Iterable


WORDS_TO_REPLACE = {
    'fu': 'Test1',
    'ti': 'Test2',
    'jass': 'Test3',
    'hpea': 'Test4',
    'd': 'Test5',
}

words = '|'.join(re.escape(w) for w in WORDS_TO_REPLACE)
REGEX_WORDS = re.compile(rf'\b({words})\b')

REPLACEMENTS_N = Counter()
FOUND_IN_QUOTES = Counter()


def replacement(m: re.Match, /) -> str:
    word = m[0]
    start, end = m.span()
    assert start < end
    for s, e in SPANS:
        if s >= end: break

        if s <= start and end <= e:
            FOUND_IN_QUOTES[word] += 1
            return word

    REPLACEMENTS_N[word] += 1
    return WORDS_TO_REPLACE[word]


def find_quotes(content: str, /) -> Iterable[tuple[int, int]]:
    is_double = is_single = False
    start = end = -1
    for i, c in enumerate(content):
        if is_double:
            if c == '"':
                if content[i - 1] == '\\':
                    continue

                end = i + 1
                is_double = False

                assert start < end
                assert start > -1 and end > -1
                yield start, end
                start = end = -1
        elif is_single:
            if c == "'":
                if content[i - 1] == '\\':
                    continue

                end = i + 1
                is_single = False

                assert start < end
                assert start > -1 and end > -1
                yield start, end
                start = end = -1
        else:
            if c == '"':
                is_double = True
                start = i
            elif c == "'":
                is_single = True
                start = i


with open('war3map-actual.j') as f, open('output.j', 'w') as out:
    content = f.read()
    SPANS = tuple(find_quotes(content))
    out.write(REGEX_WORDS.sub(replacement, content))

col1_len = max(map(len, map(repr, REPLACEMENTS_N.keys() | FOUND_IN_QUOTES.keys())))
print('Replaced count:')
for w, n in sorted(REPLACEMENTS_N.items()):
    print(f'    {w!r:{col1_len}} -- {n}')
    
print('Found inside quotes:')
for w, n in sorted(FOUND_IN_QUOTES.items()):
    print(f'    {w!r:{col1_len}} -- {n}')