basenc: implement --base58 encoding option (#8751)

* basenc: implement --base58 encoding option

Add support for Base58 encoding to basenc as per GNU coreutils 9.8.
Base58 uses the alphabet '123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz'
which excludes visually ambiguous characters (0, O, I, l).

Resolves issue #8744.

* basenc: fix clippy warnings and spelling issues

Fix explicit iteration clippy warnings. Add Base58 alphabet to spell-checker ignore list to resolve cspell errors.

Author: AnarchistHoneybun

src/uu/base32/locales/en-US.ftl

@@ -42,6 +42,7 @@ basenc-help-base2msbf = bit string with most significant bit (msb) first
 basenc-help-z85 = ascii85-like encoding;
   when encoding, input length must be a multiple of 4;
   when decoding, input length must be a multiple of 5
+basenc-help-base58 = visually unambiguous base58 encoding
 
 # Error messages
 basenc-error-missing-encoding-type = missing encoding type

src/uu/base32/locales/fr-FR.ftl

@@ -37,6 +37,7 @@ basenc-help-base2msbf = chaîne de bits avec le bit de poids fort (msb) en premi
 basenc-help-z85 = encodage de type ascii85 ;
   lors de l'encodage, la longueur d'entrée doit être un multiple de 4 ;
   lors du décodage, la longueur d'entrée doit être un multiple de 5
+basenc-help-base58 = encodage base58 visuellement non ambigu
 
 # Messages d'erreur
 basenc-error-missing-encoding-type = type d'encodage manquant

src/uu/base32/src/base_common.rs

@@ -12,8 +12,8 @@ use std::io::{self, ErrorKind, Read, Seek};
 use std::path::{Path, PathBuf};
 use uucore::display::Quotable;
 use uucore::encoding::{
-    BASE2LSBF, BASE2MSBF, Base64SimdWrapper, EncodingWrapper, Format, SupportsFastDecodeAndEncode,
-    Z85Wrapper,
+    BASE2LSBF, BASE2MSBF, Base58Wrapper, Base64SimdWrapper, EncodingWrapper, Format,
+    SupportsFastDecodeAndEncode, Z85Wrapper,
     for_base_common::{BASE32, BASE32HEX, BASE64URL, HEXUPPER_PERMISSIVE},
 };
 use uucore::error::{FromIo, UResult, USimpleError, UUsageError};
@@ -285,6 +285,7 @@ pub fn get_supports_fast_decode_and_encode(
             b"abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789=_-",
         )),
         Format::Z85 => Box::from(Z85Wrapper {}),
+        Format::Base58 => Box::from(Base58Wrapper {}),
     }
 }
 

src/uu/basenc/src/basenc.rs

@@ -39,6 +39,7 @@ fn get_encodings() -> Vec<(&'static str, Format, String)> {
             translate!("basenc-help-base2msbf"),
         ),
         ("z85", Format::Z85, translate!("basenc-help-z85")),
+        ("base58", Format::Base58, translate!("basenc-help-base58")),
     ]
 }
 

src/uucore/src/lib/features/encoding.rs

@@ -5,6 +5,7 @@
 
 // spell-checker:ignore (encodings) lsbf msbf
 // spell-checker:ignore unpadded
+// spell-checker:ignore ABCDEFGHJKLMNPQRSTUVWXY Zabcdefghijkmnopqrstuvwxyz
 
 use crate::error::{UResult, USimpleError};
 use base64_simd;
@@ -105,6 +106,7 @@ pub enum Format {
     Base2Lsbf,
     Base2Msbf,
     Z85,
+    Base58,
 }
 
 pub const BASE2LSBF: Encoding = new_encoding! {
@@ -119,6 +121,8 @@ pub const BASE2MSBF: Encoding = new_encoding! {
 
 pub struct Z85Wrapper {}
 
+pub struct Base58Wrapper {}
+
 pub struct EncodingWrapper {
     pub alphabet: &'static [u8],
     pub encoding: Encoding,
@@ -181,6 +185,142 @@ pub trait SupportsFastDecodeAndEncode {
     fn valid_decoding_multiple(&self) -> usize;
 }
 
+impl SupportsFastDecodeAndEncode for Base58Wrapper {
+    fn alphabet(&self) -> &'static [u8] {
+        // Base58 alphabet
+        b"123456789ABCDEFGHJKLMNPQRSTUVWXYZabcdefghijkmnopqrstuvwxyz"
+    }
+
+    fn decode_into_vec(&self, input: &[u8], output: &mut Vec<u8>) -> UResult<()> {
+        if input.is_empty() {
+            return Ok(());
+        }
+
+        // Count leading zeros (will become leading 1s in base58)
+        let leading_ones = input.iter().take_while(|&&b| b == b'1').count();
+
+        // Skip leading 1s for conversion
+        let input_trimmed = &input[leading_ones..];
+        if input_trimmed.is_empty() {
+            output.resize(output.len() + leading_ones, 0);
+            return Ok(());
+        }
+
+        // Convert base58 to big integer
+        let mut num: Vec<u32> = vec![0];
+        let alphabet = self.alphabet();
+
+        for &byte in input_trimmed {
+            // Find position in alphabet
+            let digit = alphabet
+                .iter()
+                .position(|&b| b == byte)
+                .ok_or_else(|| USimpleError::new(1, "error: invalid input".to_owned()))?;
+
+            // Multiply by 58 and add digit
+            let mut carry = digit as u32;
+            for n in &mut num {
+                let tmp = (*n as u64) * 58 + carry as u64;
+                *n = tmp as u32;
+                carry = (tmp >> 32) as u32;
+            }
+            if carry > 0 {
+                num.push(carry);
+            }
+        }
+
+        // Convert to bytes (little endian, then reverse)
+        let mut result = Vec::new();
+        for &n in &num {
+            result.extend_from_slice(&n.to_le_bytes());
+        }
+
+        // Remove trailing zeros and reverse to get big endian
+        while result.last() == Some(&0) && result.len() > 1 {
+            result.pop();
+        }
+        result.reverse();
+
+        // Add leading zeros for leading 1s in input
+        let mut final_result = vec![0; leading_ones];
+        final_result.extend_from_slice(&result);
+
+        output.extend_from_slice(&final_result);
+        Ok(())
+    }
+
+    fn encode_to_vec_deque(&self, input: &[u8], output: &mut VecDeque<u8>) -> UResult<()> {
+        if input.is_empty() {
+            return Ok(());
+        }
+
+        // Count leading zeros
+        let leading_zeros = input.iter().take_while(|&&b| b == 0).count();
+
+        // Skip leading zeros
+        let input_trimmed = &input[leading_zeros..];
+        if input_trimmed.is_empty() {
+            for _ in 0..leading_zeros {
+                output.push_back(b'1');
+            }
+            return Ok(());
+        }
+
+        // Convert bytes to big integer
+        let mut num: Vec<u32> = Vec::new();
+        for &byte in input_trimmed {
+            let mut carry = byte as u32;
+            for n in &mut num {
+                let tmp = (*n as u64) * 256 + carry as u64;
+                *n = tmp as u32;
+                carry = (tmp >> 32) as u32;
+            }
+            if carry > 0 {
+                num.push(carry);
+            }
+        }
+
+        // Convert to base58
+        let mut result = Vec::new();
+        let alphabet = self.alphabet();
+
+        while !num.is_empty() && num.iter().any(|&n| n != 0) {
+            let mut carry = 0u64;
+            for n in num.iter_mut().rev() {
+                let tmp = carry * (1u64 << 32) + *n as u64;
+                *n = (tmp / 58) as u32;
+                carry = tmp % 58;
+            }
+            result.push(alphabet[carry as usize]);
+
+            // Remove leading zeros
+            while num.last() == Some(&0) && num.len() > 1 {
+                num.pop();
+            }
+        }
+
+        // Add leading 1s for leading zeros in input
+        for _ in 0..leading_zeros {
+            output.push_back(b'1');
+        }
+
+        // Add result (reversed because we built it backwards)
+        for byte in result.into_iter().rev() {
+            output.push_back(byte);
+        }
+
+        Ok(())
+    }
+
+    fn unpadded_multiple(&self) -> usize {
+        1 // Base58 doesn't use padding
+    }
+
+    fn valid_decoding_multiple(&self) -> usize {
+        1 // Any length is valid for Base58
+    }
+}
+
 impl SupportsFastDecodeAndEncode for Z85Wrapper {
     fn alphabet(&self) -> &'static [u8] {
         // Z85 alphabet

tests/by-util/test_basenc.rs

@@ -185,21 +185,30 @@ fn test_base2lsbf_decode() {
 }
 
 #[test]
-fn test_choose_last_encoding_z85() {
+fn test_z85_decode() {
     new_ucmd!()
-        .args(&[
-            "--base2lsbf",
-            "--base2msbf",
-            "--base16",
-            "--base32hex",
-            "--base64url",
-            "--base32",
-            "--base64",
-            "--z85",
-        ])
-        .pipe_in("Hello, World")
+        .args(&["--z85", "-d"])
+        .pipe_in("nm=QNz.92jz/PV8")
+        .succeeds()
+        .stdout_only("Hello, World");
+}
+
+#[test]
+fn test_base58() {
+    new_ucmd!()
+        .arg("--base58")
+        .pipe_in("Hello, World!")
+        .succeeds()
+        .stdout_only("72k1xXWG59fYdzSNoA\n");
+}
+
+#[test]
+fn test_base58_decode() {
+    new_ucmd!()
+        .args(&["--base58", "-d"])
+        .pipe_in("72k1xXWG59fYdzSNoA")
         .succeeds()
-        .stdout_only("nm=QNz.92jz/PV8\n");
+        .stdout_only("Hello, World!");
 }
 
 #[test]
@@ -238,6 +247,15 @@ fn test_choose_last_encoding_base2lsbf() {
         .stdout_only("00110110110011100100011001100110\n");
 }
 
+#[test]
+fn test_choose_last_encoding_base58() {
+    new_ucmd!()
+        .args(&["--base64", "--base32", "--base16", "--z85", "--base58"])
+        .pipe_in("Hello!")
+        .succeeds()
+        .stdout_only("d3yC1LKr\n");
+}
+
 #[test]
 fn test_base32_decode_repeated() {
     new_ucmd!()