stephen schuresko
423b9250c5
- Added 'has', 'acquire', and 'without' to COMMON_ENGLISH_WORDS dictionary - Modified is_english detection threshold from 0.05 to 0.04 matches ratio - Added debug logging to show matches count during English detection
48 lines
2.7 KiB
Python
48 lines
2.7 KiB
Python
#!/usr/bin/env python3
|
|
"""Global array of all 2-letter language codes supported by YouTube"""
|
|
|
|
# Complete list of 2-letter language codes supported by YouTube
|
|
YOUTUBE_LANGUAGE_CODES = [
|
|
"af", "sq", "am", "ar", "hy", "az", "eu", "be", "bn", "bs", "bg", "ca", "ceb", "zh", "zh-Hant",
|
|
"co", "hr", "cs", "da", "nl", "en", "eo", "et", "fi", "fr", "fy", "gl", "ka", "de", "el", "gu",
|
|
"ht", "ha", "haw", "iw", "hi", "hmn", "hu", "is", "ig", "id", "ga", "it", "ja", "jw", "kn", "kk",
|
|
"km", "rw", "ko", "ku", "ky", "lo", "la", "lv", "lt", "lb", "mk", "mg", "ms", "ml", "mt", "mi",
|
|
"mr", "mn", "my", "ne", "no", "ny", "or", "ps", "fa", "pl", "pt", "pa", "ro", "ru", "sm", "gd",
|
|
"sr", "st", "sn", "sd", "si", "sk", "sl", "so", "es", "su", "sw", "sv", "tl", "tg", "ta", "tt",
|
|
"te", "th", "tr", "tk", "uk", "ur", "ug", "uz", "vi", "cy", "fy", "xh", "yi", "yo", "zu"
|
|
]
|
|
|
|
# Alternative: More focused list of commonly used languages for fallback
|
|
COMMON_FALLBACK_LANGUAGES = [
|
|
"en", "en-US", "en-GB", # English variants
|
|
"de", "fr", "es", "it", "pt", # Major European languages
|
|
"ru", "ja", "ko", "zh", "zh-Hant", # Major Asian languages
|
|
"ar", "hi", "bn", "pa", # Major world languages
|
|
"tr", "nl", "pl", "sv", "da", "fi", "no", # Nordic/Scandinavian
|
|
"cs", "sk", "hu", "ro", "bg", "hr", "sl", "pl", "lt", "lv", "et" # Eastern European
|
|
]
|
|
ENGLISH_LANGUAGES = ['en', 'en-US', 'en-GB']
|
|
# This can be used as the list of allowed fallback languages
|
|
ALLOWED_FALLBACK_LANGUAGES = COMMON_FALLBACK_LANGUAGES
|
|
COMMON_ENGLISH_WORDS = {
|
|
'the', 'be', 'to', 'of', 'and', 'a', 'in', 'that','has','acquire', 'have', 'i',
|
|
'it', 'for', 'not', 'on', 'with', 'he', 'as', 'you', 'do', 'at',
|
|
'this', 'but', 'his', 'by', 'from', 'they', 'we', 'say', 'her',
|
|
'she', 'or', 'an', 'will', 'my', 'one', 'all', 'would', 'there',
|
|
'their', 'what', 'so', 'up', 'out', 'if', 'about', 'who', 'get',
|
|
'which', 'go', 'me', 'when', 'make', 'can', 'like', 'time', 'no',
|
|
'just', 'him', 'know', 'take', 'people', 'into', 'year', 'your',
|
|
'good', 'some', 'could', 'them', 'see', 'other', 'than', 'then',
|
|
'now', 'look', 'only', 'come', 'its', 'over', 'think', 'also',
|
|
'back', 'after', 'use', 'two', 'how', 'our', 'work', 'first', 'well',
|
|
'way', 'even', 'new', 'want', 'because', 'any', 'these', 'give', 'day', 'without'
|
|
}
|
|
|
|
if __name__ == "__main__":
|
|
print("YouTube Language Codes:")
|
|
print(f"Total codes: {len(YOUTUBE_LANGUAGE_CODES)}")
|
|
print("First 10:", YOUTUBE_LANGUAGE_CODES[:10])
|
|
print()
|
|
print("Common fallback languages:")
|
|
print(f"Total fallback codes: {len(ALLOWED_FALLBACK_LANGUAGES)}")
|
|
print("Fallback codes:", ALLOWED_FALLBACK_LANGUAGES) |