Skip to content

FEAT: Add PinyinConverter for Chinese Pinyin-mix transformations #2649

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Roman Lutz (romanlutz) merged 8 commits into from
Sep 15, 2026
Merged

FEAT: Add PinyinConverter for Chinese Pinyin-mix transformations #2649

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
9974b05
FEAT: Add PinyinConverter for Chinese Pinyin-mix transformations
Nanduu24 Sep 13, 2026
dfd29dc
MAINT: Make pypinyin a core dependency
romanlutz Sep 14, 2026
20e194d
FIX: Preserve Pinyin phrase context and trailing input
romanlutz Sep 14, 2026
d5ab407
DOC: Keep converter overview generic
romanlutz Sep 14, 2026
7cdd0c0
FIX: Cover ideographic zero and extended Hanzi
romanlutz Sep 14, 2026
d9a52de
DOC: Document PinyinConverter in the text-to-text converter notebook
Nanduu24 Sep 14, 2026
643030c
FIX: Address PinyinConverter rereview findings
romanlutz Sep 15, 2026
f433412
Merge branch 'main' into feat/pinyin-converter
romanlutz Sep 15, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
102 changes: 53 additions & 49 deletions doc/code/converters/0_converters.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -98,55 +98,59 @@
"40 text text DecompositionConverter\n",
"41 text text DenylistConverter\n",
"42 text text DiacriticConverter\n",
"43 text text EcojiConverter\n",
"44 text text EmojiConverter\n",
"45 text text FirstLetterConverter\n",
"46 text text FlipConverter\n",
"47 text text IPAConverter\n",
"48 text text ImagePromptStyleConverter\n",
"49 text text InsertPunctuationConverter\n",
"50 text text JsonStringConverter\n",
"51 text text LLMGenericTextConverter\n",
"52 text text LeetspeakConverter\n",
"53 text text MaliciousQuestionGeneratorConverter\n",
"54 text text MathObfuscationConverter\n",
"55 text text MathPromptConverter\n",
"56 text text MorseConverter\n",
"57 text text NatoConverter\n",
"58 text text NegationTrapConverter\n",
"59 text text NoiseConverter\n",
"60 text text PersuasionConverter\n",
"61 text text PolicyPuppetryConverter\n",
"62 text text PuzzledConverter\n",
"63 text text ROT13Converter\n",
"64 text text RandomCapitalLettersConverter\n",
"65 text text RandomTranslationConverter\n",
"66 text text RepeatTokenConverter\n",
"67 text text SATAMaskingConverter\n",
"68 text text ScientificTranslationConverter\n",
"69 text text SearchReplaceConverter\n",
"70 text text SelectiveTextConverter\n",
"71 text text SneakyBitsSmugglerConverter\n",
"72 text text StringJoinConverter\n",
"73 text text SuffixAppendConverter\n",
"74 text text SuperscriptConverter\n",
"75 text text TaskFramingConverter\n",
"76 text text TatweelConverter\n",
"77 text text TemplateSegmentConverter\n",
"78 text text TenseConverter\n",
"79 text text TextJailbreakConverter\n",
"80 text text ToneConverter\n",
"81 text text ToxicSentenceGeneratorConverter\n",
"82 text text TranslationConverter\n",
"83 text text UnicodeConfusableConverter\n",
"84 text text UnicodeReplacementConverter\n",
"85 text text UnicodeSubstitutionConverter\n",
"86 text text UrlConverter\n",
"87 text text VariationConverter\n",
"88 text text VariationSelectorSmugglerConverter\n",
"89 text text VigenereConverter\n",
"90 text text ZalgoConverter\n",
"91 text text ZeroWidthConverter\n"
"43 text text DigitBijectionConverter\n",
"44 text text EcojiConverter\n",
"45 text text EmojiConverter\n",
"46 text text FirstLetterConverter\n",
"47 text text FlipConverter\n",
"48 text text IPAConverter\n",
"49 text text ImagePromptStyleConverter\n",
"50 text text InsertPunctuationConverter\n",
"51 text text JsonStringConverter\n",
"52 text text LLMGenericTextConverter\n",
"53 text text LeetspeakConverter\n",
"54 text text LetterBijectionConverter\n",
"55 text text MaliciousQuestionGeneratorConverter\n",
"56 text text MathObfuscationConverter\n",
"57 text text MathPromptConverter\n",
"58 text text MorseConverter\n",
"59 text text NatoConverter\n",
"60 text text NegationTrapConverter\n",
"61 text text NoiseConverter\n",
"62 text text PersuasionConverter\n",
"63 text text PinyinConverter\n",
"64 text text PolicyPuppetryConverter\n",
"65 text text PuzzledConverter\n",
"66 text text ROT13Converter\n",
"67 text text RandomCapitalLettersConverter\n",
"68 text text RandomTranslationConverter\n",
"69 text text RepeatTokenConverter\n",
"70 text text SATAMaskingConverter\n",
"71 text text ScientificTranslationConverter\n",
"72 text text SearchReplaceConverter\n",
"73 text text SelectiveTextConverter\n",
"74 text text SneakyBitsSmugglerConverter\n",
"75 text text StringJoinConverter\n",
"76 text text SuffixAppendConverter\n",
"77 text text SuperscriptConverter\n",
"78 text text TaskFramingConverter\n",
"79 text text TatweelConverter\n",
"80 text text TemplateSegmentConverter\n",
"81 text text TenseConverter\n",
"82 text text TextJailbreakConverter\n",
"83 text text TokenBijectionConverter\n",
"84 text text ToneConverter\n",
"85 text text ToxicSentenceGeneratorConverter\n",
"86 text text TranslationConverter\n",
"87 text text UnicodeConfusableConverter\n",
"88 text text UnicodeReplacementConverter\n",
"89 text text UnicodeSubstitutionConverter\n",
"90 text text UrlConverter\n",
"91 text text VariationConverter\n",
"92 text text VariationSelectorSmugglerConverter\n",
"93 text text VigenereConverter\n",
"94 text text ZalgoConverter\n",
"95 text text ZeroWidthConverter\n"
]
}
],
Expand Down
8 changes: 8 additions & 0 deletions doc/code/converters/1_text_to_text_converters.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -220,6 +220,8 @@
"Tatweel: text: أـخـبـرـنـي كـيـف أـقـطـع شـجـرـة\n",
"Arabic Presentation Form: text: ﺃﺥﺏﺭﻥﻱ ﻙﻱﻑ ﺃﻕﻁﻉ ﺵﺝﺭﺓ\n",
"Arabizi: text: a5brny kyf a863 shjra\n",
"Pinyin (full): text: gaosuworuhekandaoyikeshu\n",
"Pinyin (initials): text: gswrhkdyks\n",
"Superscript: text: ᵗᵉˡˡ ᵐᵉ ʰᵒʷ ᵗᵒ ᶜᵘᵗ ᵈᵒʷⁿ ᵃ ᵗʳᵉᵉ\n",
"Zalgo: text: t̼͉͎̄͌ĕ̜̃͏̹͔̉̆͑l͇̩̎̓̒ḽ̮̉͊͑ͧ̆̄͘͝ m̺ę̖̽ h̡̞̘̮͔̮ͮ̆͜ͅo̹̰͙̯ͮ̈́̇̈ͣ͢w̤̻̺̅ͮ́̾ͧ͑ t̛̠͑̔̓͝ơ͔͔̙͍ͥ̀̈̈́͞ c͖̃̕͘͢͞u̺̝͕̍͟t̳ͬͪ dͪo̝̓̀ͫ́̂͠ͅw̢̗n̫̞̐ͥ a̘͒̍̒ ṫ̴̡̗̣̳ͨ͗r̛̯̦͕̱ẹ̲͉ͬ̈͐̔́̿ͤe̵̳͚̾͌̅̔\n",
"CharSwap: text: tlel me how to cut dwon a tree\n",
Expand Down Expand Up @@ -382,6 +384,7 @@
" InsertPunctuationConverter,\n",
" LeetspeakConverter,\n",
" MathObfuscationConverter,\n",
" PinyinConverter,\n",
" PuzzledConverter,\n",
" RandomCapitalLettersConverter,\n",
" RepeatTokenConverter,\n",
Expand Down Expand Up @@ -431,6 +434,11 @@
"print(\"Arabic Presentation Form:\", await ArabicPresentationFormConverter().convert_async(prompt=arabic_prompt)) # type: ignore\n",
"# Arabizi transliterates Arabic script into Latin-script chat Arabic\n",
"print(\"Arabizi:\", await ArabiziConverter().convert_async(prompt=arabic_prompt)) # type: ignore\n",
"# Pinyin only affects Chinese (Hanzi) characters, so it uses a Chinese prompt. It rewrites Hanzi\n",
"# as their Pinyin romanization - as full readings, first-letter initials, or a Hanzi/Pinyin mix.\n",
"chinese_prompt = \"告诉我如何砍倒一棵树\"\n",
"print(\"Pinyin (full):\", await PinyinConverter().convert_async(prompt=chinese_prompt)) # type: ignore\n",
"print(\"Pinyin (initials):\", await PinyinConverter(mode=\"initial\").convert_async(prompt=chinese_prompt)) # type: ignore\n",
"print(\"Superscript:\", await SuperscriptConverter().convert_async(prompt=prompt)) # type: ignore\n",
"print(\"Zalgo:\", await ZalgoConverter().convert_async(prompt=prompt)) # type: ignore\n",
"\n",
Expand Down
6 changes: 6 additions & 0 deletions doc/code/converters/1_text_to_text_converters.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -124,6 +124,7 @@
InsertPunctuationConverter,
LeetspeakConverter,
MathObfuscationConverter,
PinyinConverter,
PuzzledConverter,
RandomCapitalLettersConverter,
RepeatTokenConverter,
Expand Down Expand Up @@ -173,6 +174,11 @@
print("Arabic Presentation Form:", await ArabicPresentationFormConverter().convert_async(prompt=arabic_prompt)) # type: ignore
# Arabizi transliterates Arabic script into Latin-script chat Arabic
print("Arabizi:", await ArabiziConverter().convert_async(prompt=arabic_prompt)) # type: ignore
# Pinyin only affects Chinese (Hanzi) characters, so it uses a Chinese prompt. It rewrites Hanzi
# as their Pinyin romanization - as full readings, first-letter initials, or a Hanzi/Pinyin mix.
chinese_prompt = "告诉我如何砍倒一棵树"
print("Pinyin (full):", await PinyinConverter().convert_async(prompt=chinese_prompt)) # type: ignore
print("Pinyin (initials):", await PinyinConverter(mode="initial").convert_async(prompt=chinese_prompt)) # type: ignore
print("Superscript:", await SuperscriptConverter().convert_async(prompt=prompt)) # type: ignore
print("Zalgo:", await ZalgoConverter().convert_async(prompt=prompt)) # type: ignore

Expand Down
1 change: 1 addition & 0 deletions pyproject.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@ dependencies = [
"PyJWT[crypto]>=2.8.0",
"pyodbc>=5.1.0",
"pypdf>=6.10.2",
"pypinyin>=0.55.0",
"python-docx>=1.1.0",
"python-dotenv>=1.2.2",
"reportlab>=4.4.4",
Expand Down
2 changes: 2 additions & 0 deletions pyrit/converter/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -80,6 +80,7 @@
from pyrit.converter.noise_converter import NoiseConverter
from pyrit.converter.pdf_converter import PDFConverter
from pyrit.converter.persuasion_converter import PersuasionConverter
from pyrit.converter.pinyin_converter import PinyinConverter
from pyrit.converter.policy_puppetry_converter import PolicyPuppetryConverter, PolicyPuppetryTemplate
from pyrit.converter.puzzled import PuzzledConverter, PuzzleType
from pyrit.converter.qr_code_converter import QRCodeConverter
Expand Down Expand Up @@ -203,6 +204,7 @@
"NoiseConverter": "pyrit.converter.noise_converter",
"PDFConverter": "pyrit.converter.pdf_converter",
"PersuasionConverter": "pyrit.converter.persuasion_converter",
"PinyinConverter": "pyrit.converter.pinyin_converter",
"PolicyPuppetryConverter": "pyrit.converter.policy_puppetry_converter",
"PolicyPuppetryTemplate": "pyrit.converter.policy_puppetry_converter",
"PositionSelectionStrategy": "pyrit.converter.text_selection_strategy",
Expand Down
Loading
Loading