#!python3.10
# -*- encoding: utf-8 -*-
import unicodedata
from os.path import dirname, join

east_asian_width_path = join(dirname('EastAsianWidth.txt'))

NUM_CODEPOINTS = 0x110000

with open(east_asian_width_path) as file:
    for line in file:
        if line.startswith('# @missing:'):
            expected = [line.split()[-1]] * NUM_CODEPOINTS
        else:
            fields = line.partition('#')[0].split(';')

            if len(fields) == 2:
                codepoints = [int(field, 16) for field in fields[0].split('..')]
                lower, upper = codepoints[0], codepoints[-1]
                expected[lower : upper + 1] = [fields[1].strip()] * (upper - lower + 1)

differences = []

for c in range(NUM_CODEPOINTS):
    actual = unicodedata.east_asian_width(chr(c))

    if actual != expected[c]:
        differences.append((c, expected[c], actual))

print(f'{len(differences):_} differences found')
print()

lower, expected, actual = differences[0]
upper = lower

rows = [('Range', 'Expected', 'Actual')]

for c, e, a in differences[1 : ]:
    if (c, e, a) == (upper + 1, expected, actual):
        upper = c
    else:
        if lower == upper:
            rows.append((f'{lower:04X}', expected, actual))
        else:
            rows.append((f'{lower:04X}..{upper:04X}', expected, actual))

        lower, expected, actual = c, e, a
        upper = lower

if lower == upper:
    rows.append((f'{lower:04X}', expected, actual))
else:
    rows.append((f'{lower:04X}..{upper:04X}', expected, actual))

widths = tuple(max(len(cell) for cell in column) for column in zip(*rows))
fmt = ' | '.join(f'%-{width}s' for width in  widths)

print(fmt % rows.pop(0))
print('-+-'.join('-' * width for width in widths))

for row in rows:
    print(fmt % row)