mirror of
				https://github.com/explosion/spaCy.git
				synced 2025-10-31 16:07:41 +03:00 
			
		
		
		
	
		
			
				
	
	
		
			116 lines
		
	
	
		
			7.3 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
			
		
		
	
	
			116 lines
		
	
	
		
			7.3 KiB
		
	
	
	
		
			Python
		
	
	
	
	
	
| import pytest
 | ||
| 
 | ||
| # Examples taken from the "Big List of Naughty Strings"
 | ||
| # https://github.com/minimaxir/big-list-of-naughty-strings
 | ||
| 
 | ||
| 
 | ||
| NAUGHTY_STRINGS = [
 | ||
|     # ASCII punctuation
 | ||
|     r",./;'[]\-=",
 | ||
|     r'<>?:"{}|_+',
 | ||
|     r'!@#$%^&*()`~"',
 | ||
|     # Unicode additional control characters, byte order marks
 | ||
|     r"",
 | ||
|     r"",
 | ||
|     # Unicode Symbols
 | ||
|     r"Ω≈ç√∫˜µ≤≥÷",
 | ||
|     r"åß∂ƒ©˙∆˚¬…æ",
 | ||
|     "œ∑´®†¥¨ˆøπ“‘",
 | ||
|     r"¡™£¢∞§¶•ªº–≠",
 | ||
|     r"¸˛Ç◊ı˜Â¯˘¿",
 | ||
|     r"ÅÍÎÏ˝ÓÔÒÚÆ☃",
 | ||
|     r"Œ„´‰ˇÁ¨ˆØ∏”’",
 | ||
|     r"`⁄€‹›fifl‡°·‚—±",
 | ||
|     r"⅛⅜⅝⅞",
 | ||
|     r"ЁЂЃЄЅІЇЈЉЊЋЌЍЎЏАБВГДЕЖЗИЙКЛМНОПРСТУФХЦЧШЩЪЫЬЭЮЯабвгдежзийклмнопрстуфхцчшщъыьэюя",
 | ||
|     r"٠١٢٣٤٥٦٧٨٩",
 | ||
|     # Unicode Subscript/Superscript/Accents
 | ||
|     r"⁰⁴⁵",
 | ||
|     r"₀₁₂",
 | ||
|     r"⁰⁴⁵₀₁₂",
 | ||
|     r"ด้้้้้็็็็็้้้้้็็็็็้้้้้้้้็็็็็้้้้้็็็็็้้้้้้้้็็็็็้้้้้็็็็็้้้้้้้้็็็็็้้้้้็็็็ ด้้้้้็็็็็้้้้้็็็็็้้้้้้้้็็็็็้้้้้็็็็็้้้้้้้้็็็็็้้้้้็็็็็้้้้้้้้็็็็็้้้้้็็็็ ด้้้้้็็็็็้้้้้็็็็็้้้้้้้้็็็็็้้้้้็็็็็้้้้้้้้็็็็็้้้้้็็็็็้้้้้้้้็็็็็้้้้้็็็็",
 | ||
|     r" ̄  ̄",
 | ||
|     # Two-Byte Characters
 | ||
|     r"田中さんにあげて下さい",
 | ||
|     r"パーティーへ行かないか",
 | ||
|     r"和製漢語",
 | ||
|     r"部落格",
 | ||
|     r"사회과학원 어학연구소",
 | ||
|     r"찦차를 타고 온 펲시맨과 쑛다리 똠방각하",
 | ||
|     r"社會科學院語學研究所",
 | ||
|     r"울란바토르",
 | ||
|     r"𠜎𠜱𠝹𠱓𠱸𠲖𠳏",
 | ||
|     # Japanese Emoticons
 | ||
|     r"ヽ༼ຈل͜ຈ༽ノ ヽ༼ຈل͜ຈ༽ノ",
 | ||
|     r"(。◕ ∀ ◕。)",
 | ||
|     r"`ィ(´∀`∩",
 | ||
|     r"__ロ(,_,*)",
 | ||
|     r"・( ̄∀ ̄)・:*:",
 | ||
|     r"゚・✿ヾ╲(。◕‿◕。)╱✿・゚",
 | ||
|     r",。・:*:・゜’( ☻ ω ☻ )。・:*:・゜’",
 | ||
|     r"(╯°□°)╯︵ ┻━┻)" "(ノಥ益ಥ)ノ ┻━┻",
 | ||
|     r"┬─┬ノ( º _ ºノ)",
 | ||
|     r"( ͡° ͜ʖ ͡°)",
 | ||
|     # Emoji
 | ||
|     r"😍",
 | ||
|     r"👩🏽",
 | ||
|     r"👾 🙇 💁 🙅 🙆 🙋 🙎 🙍",
 | ||
|     r"🐵 🙈 🙉 🙊",
 | ||
|     r"❤️ 💔 💌 💕 💞 💓 💗 💖 💘 💝 💟 💜 💛 💚 💙",
 | ||
|     r"✋🏿 💪🏿 👐🏿 🙌🏿 👏🏿 🙏🏿",
 | ||
|     r"🚾 🆒 🆓 🆕 🆖 🆗 🆙 🏧",
 | ||
|     r"0️⃣ 1️⃣ 2️⃣ 3️⃣ 4️⃣ 5️⃣ 6️⃣ 7️⃣ 8️⃣ 9️⃣ 🔟",
 | ||
|     # Regional Indicator Symbols
 | ||
|     r"🇺🇸🇷🇺🇸 🇦🇫🇦🇲🇸",
 | ||
|     r"🇺🇸🇷🇺🇸🇦🇫🇦🇲",
 | ||
|     r"🇺🇸🇷🇺🇸🇦",
 | ||
|     # Unicode Numbers
 | ||
|     r"123",
 | ||
|     r"١٢٣",
 | ||
|     # Right-To-Left Strings
 | ||
|     r"ثم نفس سقطت وبالتحديد،, جزيرتي باستخدام أن دنو. إذ هنا؟ الستار وتنصيب كان. أهّل ايطاليا، بريطانيا-فرنسا قد أخذ. سليمان، إتفاقية بين ما, يذكر الحدود أي بعد, معاملة بولندا، الإطلاق عل إيو.",
 | ||
|     r"إيو.",
 | ||
|     r"בְּרֵאשִׁית, בָּרָא אֱלֹהִים, אֵת הַשָּׁמַיִם, וְאֵת הָאָרֶץ",
 | ||
|     r"הָיְתָהtestالصفحات التّحول",
 | ||
|     r"﷽",
 | ||
|     r"ﷺ",
 | ||
|     r"مُنَاقَشَةُ سُبُلِ اِسْتِخْدَامِ اللُّغَةِ فِي النُّظُمِ الْقَائِمَةِ وَفِيم يَخُصَّ التَّطْبِيقَاتُ الْحاسُوبِيَّةُ،",
 | ||
|     # Trick Unicode
 | ||
|     r"test",
 | ||
|     r"test",
 | ||
|     r"
test
",
 | ||
|     r"testtest",
 | ||
|     r"test",
 | ||
|     # Zalgo Text
 | ||
|     r"Ṱ̺̺̕o͞ ̷i̲̬͇̪͙n̝̗͕v̟̜̘̦͟o̶̙̰̠kè͚̮̺̪̹̱̤ ̖t̝͕̳̣̻̪͞h̼͓̲̦̳̘̲e͇̣̰̦̬͎ ̢̼̻̱̘h͚͎͙̜̣̲ͅi̦̲̣̰̤v̻͍e̺̭̳̪̰-m̢iͅn̖̺̞̲̯̰d̵̼̟͙̩̼̘̳ ̞̥̱̳̭r̛̗̘e͙p͠r̼̞̻̭̗e̺̠̣͟s̘͇̳͍̝͉e͉̥̯̞̲͚̬͜ǹ̬͎͎̟̖͇̤t͍̬̤͓̼̭͘ͅi̪̱n͠g̴͉ ͏͉ͅc̬̟h͡a̫̻̯͘o̫̟̖͍̙̝͉s̗̦̲.̨̹͈̣",
 | ||
|     r"̡͓̞ͅI̗̘̦͝n͇͇͙v̮̫ok̲̫̙͈i̖͙̭̹̠̞n̡̻̮̣̺g̲͈͙̭͙̬͎ ̰t͔̦h̞̲e̢̤ ͍̬̲͖f̴̘͕̣è͖ẹ̥̩l͖͔͚i͓͚̦͠n͖͍̗͓̳̮g͍ ̨o͚̪͡f̘̣̬ ̖̘͖̟͙̮c҉͔̫͖͓͇͖ͅh̵̤̣͚͔á̗̼͕ͅo̼̣̥s̱͈̺̖̦̻͢.̛̖̞̠̫̰",
 | ||
|     r"̗̺͖̹̯͓Ṯ̤͍̥͇͈h̲́e͏͓̼̗̙̼̣͔ ͇̜̱̠͓͍ͅN͕͠e̗̱z̘̝̜̺͙p̤̺̹͍̯͚e̠̻̠͜r̨̤͍̺̖͔̖̖d̠̟̭̬̝͟i̦͖̩͓͔̤a̠̗̬͉̙n͚͜ ̻̞̰͚ͅh̵͉i̳̞v̢͇ḙ͎͟-҉̭̩̼͔m̤̭̫i͕͇̝̦n̗͙ḍ̟ ̯̲͕͞ǫ̟̯̰̲͙̻̝f ̪̰̰̗̖̭̘͘c̦͍̲̞͍̩̙ḥ͚a̮͎̟̙͜ơ̩̹͎s̤.̝̝ ҉Z̡̖̜͖̰̣͉̜a͖̰͙̬͡l̲̫̳͍̩g̡̟̼̱͚̞̬ͅo̗͜.̟",
 | ||
|     r"̦H̬̤̗̤͝e͜ ̜̥̝̻͍̟́w̕h̖̯͓o̝͙̖͎̱̮ ҉̺̙̞̟͈W̷̼̭a̺̪͍į͈͕̭͙̯̜t̶̼̮s̘͙͖̕ ̠̫̠B̻͍͙͉̳ͅe̵h̵̬͇̫͙i̹͓̳̳̮͎̫̕n͟d̴̪̜̖ ̰͉̩͇͙̲͞ͅT͖̼͓̪͢h͏͓̮̻e̬̝̟ͅ ̤̹̝W͙̞̝͔͇͝ͅa͏͓͔̹̼̣l̴͔̰̤̟͔ḽ̫.͕",
 | ||
|     r"Z̮̞̠͙͔ͅḀ̗̞͈̻̗Ḷ͙͎̯̹̞͓G̻O̭̗̮",
 | ||
|     # Unicode Upsidedown
 | ||
|     r"˙ɐnbᴉlɐ ɐuƃɐɯ ǝɹolop ʇǝ ǝɹoqɐl ʇn ʇunpᴉpᴉɔuᴉ ɹodɯǝʇ poɯsnᴉǝ op pǝs 'ʇᴉlǝ ƃuᴉɔsᴉdᴉpɐ ɹnʇǝʇɔǝsuoɔ 'ʇǝɯɐ ʇᴉs ɹolop ɯnsdᴉ ɯǝɹo˥",
 | ||
|     r"00˙Ɩ$-",
 | ||
|     # Unicode font
 | ||
|     r"The quick brown fox jumps over the lazy dog",
 | ||
|     r"𝐓𝐡𝐞 𝐪𝐮𝐢𝐜𝐤 𝐛𝐫𝐨𝐰𝐧 𝐟𝐨𝐱 𝐣𝐮𝐦𝐩𝐬 𝐨𝐯𝐞𝐫 𝐭𝐡𝐞 𝐥𝐚𝐳𝐲 𝐝𝐨𝐠",
 | ||
|     r"𝕿𝖍𝖊 𝖖𝖚𝖎𝖈𝖐 𝖇𝖗𝖔𝖜𝖓 𝖋𝖔𝖝 𝖏𝖚𝖒𝖕𝖘 𝖔𝖛𝖊𝖗 𝖙𝖍𝖊 𝖑𝖆𝖟𝖞 𝖉𝖔𝖌",
 | ||
|     r"𝑻𝒉𝒆 𝒒𝒖𝒊𝒄𝒌 𝒃𝒓𝒐𝒘𝒏 𝒇𝒐𝒙 𝒋𝒖𝒎𝒑𝒔 𝒐𝒗𝒆𝒓 𝒕𝒉𝒆 𝒍𝒂𝒛𝒚 𝒅𝒐𝒈",
 | ||
|     r"𝓣𝓱𝓮 𝓺𝓾𝓲𝓬𝓴 𝓫𝓻𝓸𝔀𝓷 𝓯𝓸𝔁 𝓳𝓾𝓶𝓹𝓼 𝓸𝓿𝓮𝓻 𝓽𝓱𝓮 𝓵𝓪𝔃𝔂 𝓭𝓸𝓰",
 | ||
|     r"𝕋𝕙𝕖 𝕢𝕦𝕚𝕔𝕜 𝕓𝕣𝕠𝕨𝕟 𝕗𝕠𝕩 𝕛𝕦𝕞𝕡𝕤 𝕠𝕧𝕖𝕣 𝕥𝕙𝕖 𝕝𝕒𝕫𝕪 𝕕𝕠𝕘",
 | ||
|     r"𝚃𝚑𝚎 𝚚𝚞𝚒𝚌𝚔 𝚋𝚛𝚘𝚠𝚗 𝚏𝚘𝚡 𝚓𝚞𝚖𝚙𝚜 𝚘𝚟𝚎𝚛 𝚝𝚑𝚎 𝚕𝚊𝚣𝚢 𝚍𝚘𝚐",
 | ||
|     r"⒯⒣⒠ ⒬⒰⒤⒞⒦ ⒝⒭⒪⒲⒩ ⒡⒪⒳ ⒥⒰⒨⒫⒮ ⒪⒱⒠⒭ ⒯⒣⒠ ⒧⒜⒵⒴ ⒟⒪⒢",
 | ||
|     # File paths
 | ||
|     r"../../../../../../../../../../../etc/passwd%00",
 | ||
|     r"../../../../../../../../../../../etc/hosts",
 | ||
|     # iOS Vulnerabilities
 | ||
|     r"Powerلُلُصّبُلُلصّبُررً ॣ ॣh ॣ ॣ冗",
 | ||
|     r"🏳0🌈️",
 | ||
| ]
 | ||
| 
 | ||
| 
 | ||
| @pytest.mark.slow
 | ||
| @pytest.mark.parametrize("text", NAUGHTY_STRINGS)
 | ||
| def test_tokenizer_naughty_strings(tokenizer, text):
 | ||
|     tokens = tokenizer(text)
 | ||
|     assert tokens.text_with_ws == text
 |