utf8_iter 1.0.4: utf8_iter

# This file is automatically @generated by Cargo.
# It is not intended for manual editing.
version = 4

[[package]]
name = "sample-utf8-iter"
version = "1.0.0"
dependencies = [
 "utf8_iter",
]

[[package]]
name = "utf8_iter"
version = "1.0.4"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "b6c140620e7ffbb22c2dee59cafe6084a59b5ffc27a8859a5f0d494b5d52b6be"

[package]
name = "sample-utf8-iter"
version = "1.0.0"
edition = "2021"
publish = false

[dependencies]
utf8_iter = "=1.0.4"

[[bin]]
name = "contract"
path = "test/contract.rs"

Clean-room public code sample — generation instructions

Write a brand-new, minimal, self-contained code sample in this clean-room directory.
Do not copy, paraphrase, or reference any existing project source. Work only from this spec.

A csx.json manifest scaffold already exists. Do not recreate it from memory. Preserve its case.goal, packages and symbols; fill its empty case.contract with exact assertions and correct its environment, commands and verifierAdapter for the files you generate.

Goal: verify utf8_iter in pkg:cargo/utf8_iter@1.0.4
Kind: HOW

Use EXACTLY these public packages and versions:
  - pkg:cargo/utf8_iter@1.0.4
Demonstrate these symbols/APIs:
  - utf8_iter

Rules:
  - One focused purpose; the smallest project that proves the goal.
  - Include a contract test (test/contract.*) that runs OFFLINE and exits 0 exactly when the goal behavior works.
  - Pin every dependency with a lockfile so resolution is reproducible.
  - No secrets, credentials, or tokens. No real URLs (only example.com or localhost). No absolute paths.
  - No personal names, emails, company names, or project identifiers of any kind.
  - No binaries and no generated output (node_modules, dist, target, venv, .git, .env).
  - Keep it under 200 files and 256KB packed.

{"case":{"caseId":"case:sha256:c3fb51d22bac64cb3aa18e582ba1eb7169628de7e97d42d446529b8acef813d4","contract":["Utf8CharsEx::chars iterates over byte slices yielding chars and matches String::from_utf8_lossy on invalid sequences","Utf8CharsEx::char_indices tracks byte offsets alongside decoded characters","Utf8Chars supports double-ended reverse iteration over byte slices","ErrorReportingUtf8Chars reports Utf8CharsError for invalid UTF-8 byte sequences","Utf8Chars and Utf8CharIndices expose remaining unparsed bytes via as_slice"],"goal":"verify utf8_iter in pkg:cargo/utf8_iter@1.0.4","kind":"HOW","packages":["pkg:cargo/utf8_iter@1.0.4"],"schemaVersion":1,"symbols":["utf8_iter"]},"contractCommand":["cargo","run","--offline"],"environment":{"arch":"x64","distro":"alpine","ecosystem":"cargo","libc":"musl","os":"linux","packageManager":"cargo","schemaVersion":1},"license":"MIT-0","packages":["pkg:cargo/utf8_iter@1.0.4"],"schemaVersion":1,"subject":"pkg:cargo/utf8_iter@1.0.4","symbols":["utf8_iter"],"verifierAdapter":"cargo@1"}

{
  "schemaVersion": 1,
  "goal": "verify utf8_iter in pkg:cargo/utf8_iter@1.0.4",
  "kind": "HOW",
  "packages": [
    "pkg:cargo/utf8_iter@1.0.4"
  ],
  "symbols": [
    "utf8_iter"
  ]
}

//! Clean-room verification sample for utf8_iter.

pub use utf8_iter::*;

use utf8_iter::{ErrorReportingUtf8Chars, Utf8CharIndices, Utf8Chars, Utf8CharsEx};

fn main() {
    // 1. Utf8CharsEx::chars iterates over byte slices yielding chars and matches String::from_utf8_lossy on invalid sequences
    let data = b"Hello, \xF0\x9F\xA6\x80 \xFF\xC2 world!";
    let from_iter: String = data.chars().collect();
    let from_lossy = String::from_utf8_lossy(data);
    assert_eq!(from_iter, from_lossy);

    let pure_ascii = b"abc";
    let pure_chars: Vec<char> = pure_ascii.chars().collect();
    assert_eq!(pure_chars, vec!['a', 'b', 'c']);

    // 2. Utf8CharsEx::char_indices tracks byte offsets alongside decoded characters
    let sample = "🦀 rust".as_bytes();
    let indices: Vec<(usize, char)> = sample.char_indices().collect();
    assert_eq!(
        indices,
        vec![
            (0, '🦀'),
            (4, ' '),
            (5, 'r'),
            (6, 'u'),
            (7, 's'),
            (8, 't'),
        ]
    );

    // 3. Utf8Chars supports double-ended reverse iteration over byte slices
    let text = "a🦀b".as_bytes();
    let mut iter = Utf8Chars::new(text);
    assert_eq!(iter.next_back(), Some('b'));
    assert_eq!(iter.next_back(), Some('🦀'));
    assert_eq!(iter.next_back(), Some('a'));
    assert_eq!(iter.next_back(), None);

    // 4. ErrorReportingUtf8Chars reports Utf8CharsError for invalid UTF-8 byte sequences
    let invalid_bytes = b"valid\xFFinvalid";
    let reporting = ErrorReportingUtf8Chars::new(invalid_bytes);
    let results: Vec<_> = reporting.collect();
    assert_eq!(results[0], Ok('v'));
    assert!(results[5].is_err());
    if let Err(ref err) = results[5] {
        assert_eq!(format!("{}", err), "byte sequence not well-formed UTF-8");
    }

    // 5. Utf8Chars and Utf8CharIndices expose remaining unparsed bytes via as_slice
    let mut chars_iter = Utf8Chars::new(b"xyz");
    assert_eq!(chars_iter.as_slice(), b"xyz");
    assert_eq!(chars_iter.next(), Some('x'));
    assert_eq!(chars_iter.as_slice(), b"yz");

    let mut indices_iter = Utf8CharIndices::new(b"xyz");
    assert_eq!(indices_iter.as_slice(), b"xyz");
    assert_eq!(indices_iter.next(), Some((0, 'x')));
    assert_eq!(indices_iter.as_slice(), b"yz");

    println!("All utf8_iter contract assertions passed successfully.");
}