/rust/registry/src/index.crates.io-1949cf8c6b5b557f/csv-1.4.0/src/debug.rs

Source
/// A type that provides a human readable debug impl for arbitrary bytes.
///
/// This generally works best when the bytes are presumed to be mostly UTF-8,
/// but will work for anything.
///
/// N.B. This is copied nearly verbatim from regex-automata. Sigh.
pub(crate) struct Bytes<'a>(pub(crate) &'a [u8]);

impl<'a> core::fmt::Debug for Bytes<'a> {
    fn fmt(&self, f: &mut core::fmt::Formatter) -> core::fmt::Result {
        write!(f, "\"")?;
        // This is a sad re-implementation of a similar impl found in bstr.
        let mut bytes = self.0;
        while let Some(result) = utf8_decode(bytes) {
            let ch = match result {
                Ok(ch) => ch,
                Err(byte) => {
                    write!(f, r"\x{:02x}", byte)?;
                    bytes = &bytes[1..];
                    continue;
                }
            };
            bytes = &bytes[ch.len_utf8()..];
            match ch {
                '\0' => write!(f, "\\0")?,
                // ASCII control characters except \0, \n, \r, \t
                '\x01'..='\x08'
                | '\x0b'
                | '\x0c'
                | '\x0e'..='\x19'
                | '\x7f' => {
                    write!(f, "\\x{:02x}", u32::from(ch))?;
                }
                '\n' | '\r' | '\t' | _ => {
                    write!(f, "{}", ch.escape_debug())?;
                }
            }
        }
        write!(f, "\"")?;
        Ok(())
    }
}

/// Decodes the next UTF-8 encoded codepoint from the given byte slice.
///
/// If no valid encoding of a codepoint exists at the beginning of the given
/// byte slice, then the first byte is returned instead.
///
/// This returns `None` if and only if `bytes` is empty.
pub(crate) fn utf8_decode(bytes: &[u8]) -> Option<Result<char, u8>> {
    fn len(byte: u8) -> Option<usize> {
        if byte <= 0x7F {
            Some(1)
        } else if byte & 0b1100_0000 == 0b1000_0000 {
            None
        } else if byte <= 0b1101_1111 {
            Some(2)
        } else if byte <= 0b1110_1111 {
            Some(3)
        } else if byte <= 0b1111_0111 {
            Some(4)
        } else {
            None
        }
    }

    if bytes.is_empty() {
        return None;
    }
    let len = match len(bytes[0]) {
        None => return Some(Err(bytes[0])),
        Some(len) if len > bytes.len() => return Some(Err(bytes[0])),
        Some(1) => return Some(Ok(char::from(bytes[0]))),
        Some(len) => len,
    };
    match core::str::from_utf8(&bytes[..len]) {
        Ok(s) => Some(Ok(s.chars().next().unwrap())),
        Err(_) => Some(Err(bytes[0])),
    }
}

Coverage Report

Created: 2026-07-30 06:46

Line	Count	Source
1		/// A type that provides a human readable debug impl for arbitrary bytes.
2		///
3		/// This generally works best when the bytes are presumed to be mostly UTF-8,
4		/// but will work for anything.
5		///
6		/// N.B. This is copied nearly verbatim from regex-automata. Sigh.
7		pub(crate) struct Bytes<'a>(pub(crate) &'a [u8]);
8
9		impl<'a> core::fmt::Debug for Bytes<'a> {
10	0	fn fmt(&self, f: &mut core::fmt::Formatter) -> core::fmt::Result {
11	0	write!(f, "\"")?;
12		// This is a sad re-implementation of a similar impl found in bstr.
13	0	let mut bytes = self.0;
14	0	while let Some(result) = utf8_decode(bytes) {
15	0	let ch = match result {
16	0	Ok(ch) => ch,
17	0	Err(byte) => {
18	0	write!(f, r"\x{:02x}", byte)?;
19	0	bytes = &bytes[1..];
20	0	continue;
21		}
22		};
23	0	bytes = &bytes[ch.len_utf8()..];
24	0	match ch {
25	0	'\0' => write!(f, "\\0")?,
26		// ASCII control characters except \0, \n, \r, \t
27	0	'\x01'..='\x08'
28		\| '\x0b'
29		\| '\x0c'
30	0	\| '\x0e'..='\x19'
31		\| '\x7f' => {
32	0	write!(f, "\\x{:02x}", u32::from(ch))?;
33		}
34		'\n' \| '\r' \| '\t' \| _ => {
35	0	write!(f, "{}", ch.escape_debug())?;
36		}
37		}
38		}
39	0	write!(f, "\"")?;
40	0	Ok(())
41	0	}
42		}
43
44		/// Decodes the next UTF-8 encoded codepoint from the given byte slice.
45		///
46		/// If no valid encoding of a codepoint exists at the beginning of the given
47		/// byte slice, then the first byte is returned instead.
48		///
49		/// This returns `None` if and only if `bytes` is empty.
50	0	pub(crate) fn utf8_decode(bytes: &[u8]) -> Option<Result<char, u8>> {
51	0	fn len(byte: u8) -> Option<usize> {
52	0	if byte <= 0x7F {
53	0	Some(1)
54	0	} else if byte & 0b1100_0000 == 0b1000_0000 {
55	0	None
56	0	} else if byte <= 0b1101_1111 {
57	0	Some(2)
58	0	} else if byte <= 0b1110_1111 {
59	0	Some(3)
60	0	} else if byte <= 0b1111_0111 {
61	0	Some(4)
62		} else {
63	0	None
64		}
65	0	}
66
67	0	if bytes.is_empty() {
68	0	return None;
69	0	}
70	0	let len = match len(bytes[0]) {
71	0	None => return Some(Err(bytes[0])),
72	0	Some(len) if len > bytes.len() => return Some(Err(bytes[0])),
73	0	Some(1) => return Some(Ok(char::from(bytes[0]))),
74	0	Some(len) => len,
75		};
76	0	match core::str::from_utf8(&bytes[..len]) {
77	0	Ok(s) => Some(Ok(s.chars().next().unwrap())),
78	0	Err(_) => Some(Err(bytes[0])),
79		}
80	0	}