1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280
//! A crate for converting an ASCII text string to a single unicode grapheme cluster and back.
//! Provides the non-macro functionality of the crate [`zalgo-codec`](https://docs.rs/zalgo-codec/latest/zalgo_codec/).
use core::{fmt, str};
/// Contains the implementation of [`ZalgoString`](zalgo_string::ZalgoString) as well as related iterators.
pub mod zalgo_string;
pub use zalgo_string::ZalgoString;
/// Takes in an ASCII string without control characters (except newlines)
/// and encodes it into a single grapheme cluster using a reversible encoding scheme.
///
/// The resulting string is a single unicode grapheme cluster and should
/// only take up a single character space horizontally when displayed
/// (though this can vary between platforms depending on how they deal with unicode).
/// The resulting string will be ~2 times larger than the original in terms of bytes, and it
/// can be decoded to recover the original string with [`zalgo_decode`].
/// # Example
/// ```
/// # use zalgo_codec_common::zalgo_encode;
/// assert_eq!(zalgo_encode("Zalgo").unwrap(), "É̺͇͌͏");
/// ```
/// # Notes
/// Can not encode carriage returns, present in e.g. line endings on Windows.
#[must_use = "the function returns a new value and does not modify the input"]
pub fn zalgo_encode(string_to_encode: &str) -> Result<String, Error> {
// The line we are currently encoding
let mut line = 1;
// The column on that line we are currently encoding
let mut column = 1;
// These are used for reporting a useful error if the encoding process fails.
// Every byte in the input will encode to two bytes. The extra byte is for the initial letter
// which is there in order for the output to be displayable in an intuitive way.
let mut result = Vec::with_capacity(2 * string_to_encode.len() + 1);
result.push(b'E');
// We will encode this many bytes at a time before pushing onto the result vector.
const BATCH_SIZE: usize = 16;
for batch in string_to_encode.as_bytes().chunks(BATCH_SIZE) {
let mut buffer = [0; 2 * BATCH_SIZE];
let mut encoded = 0;
for byte in batch {
// Only encode ASCII bytes corresponding to printable characters or newlines.
if (32..127).contains(byte) || *byte == b'\n' {
if *byte == b'\n' {
line += 1;
// `column` is still 1-indexed since it gets incremented at the end of the current loop iteration.
column = 0;
}
let v = ((i16::from(*byte) - 11).rem_euclid(133) - 21) as u8;
buffer[encoded] = (v >> 6) & 1 | 0b11001100;
buffer[encoded + 1] = (v & 63) | 0b10000000;
encoded += 2;
column += 1;
} else {
match nonprintable_char_repr(*byte) {
Some(repr) => return Err(Error::NonprintableAscii(*byte, line, column, repr)),
None => return Err(Error::NotAscii(*byte, line, column)),
}
}
}
result.extend_from_slice(&buffer[..encoded]);
}
// Safety: the encoding process does not produce invalid UTF-8
// if given valid printable ASCII + newlines,
// which is checked before this point
Ok(unsafe { String::from_utf8_unchecked(result) })
}
/// Takes in a string that was encoded by [`zalgo_encode`] and decodes it back into an ASCII string.
///
/// # Error
///
/// Returns an error if the decoded string is not valid UTF-8.
/// This can happen if the input is a string that was not encoded by [`zalgo_encode`],
/// since the byte manipulations that this function does could result in invalid unicode in that case.
/// Even if no error is returned in such a case the results are not meaningful.
/// If you want to be able to decode without this check, consider using a [`ZalgoString`].
///
/// # Examples
/// ```
/// # use zalgo_codec_common::zalgo_decode;
/// assert_eq!(zalgo_decode("É̺͇͌͏").unwrap(), "Zalgo");
/// ```
/// Decoding arbitrary strings not produced by [`zalgo_encode`] will most likely lead to errors,
/// and if it doesn't the results are not meaningful:
/// ```
/// # use zalgo_codec_common::zalgo_decode;
/// assert!(zalgo_decode("Shmårgl").is_err());
/// ```
#[must_use = "the function returns a new value and does not modify the input"]
pub fn zalgo_decode(encoded: &str) -> Result<String, std::string::FromUtf8Error> {
let mut res = vec![0; (encoded.len() - 1) / 2];
let bytes = encoded.as_bytes();
for (write, read) in (1..encoded.len()).step_by(2).enumerate() {
match bytes.get(read + 1) {
Some(next) => res[write] = decode_byte_pair(bytes[read], *next),
None => break,
}
}
String::from_utf8(res)
}
#[must_use = "the function returns a new value and does not modify its inputs"]
#[inline]
fn decode_byte_pair(odd: u8, even: u8) -> u8 {
((odd << 6 & 64 | even & 63) + 22) % 133 + 10
}
/// zalgo-encodes an ASCII string containing Python code and
/// wraps it in a decoder that decodes and executes it.
/// The resulting Python code should retain the functionality of the original.
/// # Notes
/// May not work correctly on python versions before 3.10,
/// see [this github issue](https://github.com/DaCoolOne/DumbIdeas/issues/1) for more information.
#[must_use = "the function returns a new value and does not modify the input"]
pub fn zalgo_wrap_python(string_to_encode: &str) -> Result<String, Error> {
let encoded_string = zalgo_encode(string_to_encode)?;
Ok(format!("b='{encoded_string}'.encode();exec(''.join(chr(((h<<6&64|c&63)+22)%133+10)for h,c in zip(b[1::2],b[2::2])))"))
}
#[derive(Debug, Clone, Copy, PartialEq)]
/// The error returned by [`zalgo_encode`], [`ZalgoString::new`], and [`zalgo_wrap_python`]
/// if they encounter a byte they can not encode.
pub enum Error {
/// Represents a valid ASCII character that is outside of the encodable set.
NonprintableAscii(u8, usize, usize, &'static str),
/// Represents some other unicode character.
NotAscii(u8, usize, usize),
}
impl Error {
/// Returns the 1-indexed line number of the line on which the unencodable byte occured.
/// # Examples
/// ```
/// # use zalgo_codec_common::{Error, zalgo_encode};
/// assert_eq!(zalgo_encode("❤️").err().unwrap().line(), 1);
/// assert_eq!(zalgo_encode("a\nb\nc\r\n").err().unwrap().line(), 3);
/// ```
#[must_use = "the method returns a new valus and does not modify `self`"]
pub const fn line(&self) -> usize {
match self {
Self::NonprintableAscii(_, line, _, _) | Self::NotAscii(_, line, _) => *line,
}
}
/// Returns the 1-indexed column where the unencodable byte occured.
/// Columns are counted from left to right and the count resets for each new line.
/// # Example
/// ```
/// # use zalgo_codec_common::{Error, zalgo_encode};
/// assert_eq!(zalgo_encode("I ❤️ 🎂").err().unwrap().column(), 3);
/// assert_eq!(zalgo_encode("I\n❤️\n🎂").err().unwrap().column(), 1);
/// ```
#[must_use = "the method returns a new valus and does not modify `self`"]
pub const fn column(&self) -> usize {
match self {
Self::NonprintableAscii(_, _, column, _) | Self::NotAscii(_, _, column) => *column,
}
}
/// Returns the value of the first byte of the unencodable character.
/// # Examples
/// ```
/// # use zalgo_codec_common::{Error, zalgo_encode};
/// assert_eq!(zalgo_encode("\r").err().unwrap().byte(), 13);
/// ```
/// Note that this might not be the complete representation of
/// the character in unicode, just the first byte of it.
/// ```
/// # use zalgo_codec_common::{Error, zalgo_encode};
/// assert_eq!(zalgo_encode("❤️").err().unwrap().byte(), 226);
/// // Even though
/// assert_eq!("❤️".as_bytes(), &[226, 157, 164, 239, 184, 143])
/// ```
#[must_use = "the method returns a new value and does not modify `self`"]
pub const fn byte(&self) -> u8 {
match self {
Self::NonprintableAscii(byte, _, _, _) | Self::NotAscii(byte, _, _) => *byte,
}
}
/// Return a representation of the unencodable byte.
/// This exists if the character is an unencodable ASCII character.
/// If it is some other unicode character we only know its first byte, so we can not
/// accurately represent it.
/// # Examples
/// ```
/// # use zalgo_codec_common::zalgo_encode;
/// assert_eq!(zalgo_encode("\r").err().unwrap().representation(), Some("Carriage Return"));
/// assert_eq!(zalgo_encode("❤️").err().unwrap().representation(), None);
/// ```
#[must_use = "the method returns a new value and does not modify `self`"]
pub const fn representation(&self) -> Option<&'static str> {
match self {
Self::NonprintableAscii(_, _, _, repr) => Some(*repr),
Self::NotAscii(_, _, _) => None,
}
}
}
impl fmt::Display for Error {
fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
match self {
Self::NonprintableAscii(byte, line, column, repr) => write!(
f,
"line {line} at column {column}: can not encode ASCII \"{repr}\" character with byte value {byte}"
),
Self::NotAscii(byte, line, column) => write!(
f,
"line {line} at column {column}: byte value {byte} does not correspond to an ASCII character"
),
}
}
}
impl std::error::Error for Error {
fn source(&self) -> Option<&(dyn std::error::Error + 'static)> {
None
}
}
/// Returns the representation of the given ASCII byte if it's not printable.
#[inline]
#[must_use = "the function returns a new value and does not modify the input"]
const fn nonprintable_char_repr(byte: u8) -> Option<&'static str> {
if byte < 10 {
Some(
[
"Null",
"Start Of Heading",
"Start Of Text",
"End Of Text",
"End Of Transmission",
"Enquiry",
"Acknowledge",
"Bell",
"Backspace",
"Horizontal Tab",
][byte as usize],
)
} else if byte >= 11 && byte < 32 {
Some(
[
"Vertical Tab",
"Form Feed",
"Carriage Return",
"Shift Out",
"Shift In",
"Data Link Escape",
"Data Control 1",
"Data Control 2",
"Data Control 3",
"Data Control 4",
"Negative Acknowledge",
"Synchronous Idle",
"End Of Transmission Block",
"Cancel",
"End Of Medium",
"Substitute",
"Escape",
"File Separator",
"Group Separator",
"Record Separator",
"Unit Separator",
][byte as usize - 11],
)
} else if byte == 127 {
Some("Delete")
} else {
None
}
}