UTF-8 print all Bengali Characters

utf8_bangali.py

import yaml

# Define the Unicode ranges for Bengali characters
# The ranges are tuples of start and end points, inclusive
# Unassigned code points will be skipped
bengali_char_ranges = [
    (0x0980, 0x0983),  # Bengali Anji, etc.
    (0x0985, 0x098C),  # Bengali vowels
    (0x098F, 0x0990),  # Bengali E, AI
    (0x0993, 0x09A8),  # Bengali O, etc.
    (0x09AA, 0x09B0),  # Bengali letter KA, etc.
    (0x09B2, 0x09B2),  # Bengali letter LA
    (0x09B6, 0x09B9),  # Bengali SHA, etc.
    (0x09BC, 0x09C4),  # Bengali sign NUKTA, etc.
    (0x09C7, 0x09C8),  # Bengali VOWEL SIGN E, AI
    (0x09CB, 0x09CE),  # Bengali VOWEL SIGN O, etc.
    (0x09D7, 0x09D7),  # Bengali AU Length Mark
    (0x09DC, 0x09DD),  # Bengali letter RRA, etc.
    (0x09DF, 0x09E3),  # Bengali letter YYA, etc.
    (0x09E6, 0x09FE),  # Bengali digits and signs
]

bengali_chars = {
    "characters": []
}

# Function to populate characters using the ranges
def populate_characters(ranges, char_dict):
    for start, end in ranges:
        for codepoint in range(start, end + 1):
            char = chr(codepoint)
            char_dict["characters"].append(char)

# Populate Bengali characters
populate_characters(bengali_char_ranges, bengali_chars)

# Save as YAML
yaml_file_path = "bengali_chars.yaml"
with open(yaml_file_path, "w", encoding="utf-8") as f:
    yaml.dump(bengali_chars, f, allow_unicode=True)