utf8parse 0.2.2

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

[[package]]
name = "sample-utf8parse"
version = "1.0.0"
dependencies = [
 "utf8parse",
]

[[package]]
name = "utf8parse"
version = "0.2.2"
source = "registry+https://github.com/rust-lang/crates.io-index"
checksum = "06abde3611657adf66d383f00b093d7faecc7fa57071cce2578660c9f1010821"

[package]
name = "sample-utf8parse"
version = "1.0.0"
edition = "2021"
publish = false

[dependencies]
utf8parse = "=0.2.2"

[[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 pkg:cargo/utf8parse@0.2.2
Kind: HOW

Use EXACTLY these public packages and versions:
  - pkg:cargo/utf8parse@0.2.2

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:sha256:644f02414e40a36f7e54f3d891a6e1ff7dd299c04c683f8118efdec88b7361b4","contract":["Parser::new initializes a default ground-state UTF-8 parser","Parser::advance emits single-byte ASCII codepoints via Receiver::codepoint","Parser::advance parses 2-byte, 3-byte, and 4-byte UTF-8 sequences","Parser::advance invokes Receiver::invalid_sequence on malformed byte sequences","Parser processes continuous multi-character byte stream with mixed lengths"],"goal":"verify pkg:cargo/utf8parse@0.2.2","kind":"HOW","packages":["pkg:cargo/utf8parse@0.2.2"],"schemaVersion":1},"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/utf8parse@0.2.2"],"schemaVersion":1,"subject":"pkg:cargo/utf8parse@0.2.2","verifierAdapter":"cargo@1"}

{
  "schemaVersion": 1,
  "goal": "verify pkg:cargo/utf8parse@0.2.2",
  "kind": "HOW",
  "packages": [
    "pkg:cargo/utf8parse@0.2.2"
  ]
}

//! Clean-room verification sample for utf8parse.

pub use utf8parse::*;

use utf8parse::{Parser, Receiver};

#[derive(Default)]
struct TestReceiver {
    codepoints: Vec<char>,
    invalid_count: usize,
}

impl Receiver for TestReceiver {
    fn codepoint(&mut self, c: char) {
        self.codepoints.push(c);
    }

    fn invalid_sequence(&mut self) {
        self.invalid_count += 1;
    }
}

fn main() {
    // 1. Parser::new initializes a default ground-state UTF-8 parser
    let mut parser = Parser::new();
    assert_eq!(parser, Parser::default());

    // 2. Parser::advance emits single-byte ASCII codepoints via Receiver::codepoint
    let mut ascii_receiver = TestReceiver::default();
    for &b in b"ASCII" {
        parser.advance(&mut ascii_receiver, b);
    }
    assert_eq!(ascii_receiver.codepoints, vec!['A', 'S', 'C', 'I', 'I']);
    assert_eq!(ascii_receiver.invalid_count, 0);

    // 3. Parser::advance parses 2-byte, 3-byte, and 4-byte UTF-8 sequences
    let mut multi_receiver = TestReceiver::default();
    let mut multi_parser = Parser::new();
    for &b in "§".as_bytes() {
        multi_parser.advance(&mut multi_receiver, b);
    }
    for &b in "€".as_bytes() {
        multi_parser.advance(&mut multi_receiver, b);
    }
    for &b in "🦀".as_bytes() {
        multi_parser.advance(&mut multi_receiver, b);
    }
    assert_eq!(multi_receiver.codepoints, vec!['§', '€', '🦀']);
    assert_eq!(multi_receiver.invalid_count, 0);

    // 4. Parser::advance invokes Receiver::invalid_sequence on malformed byte sequences
    let mut err_receiver = TestReceiver::default();
    let mut err_parser = Parser::new();
    err_parser.advance(&mut err_receiver, 0xFF);
    err_parser.advance(&mut err_receiver, 0x80);
    assert_eq!(err_receiver.invalid_count, 2);
    assert!(err_receiver.codepoints.is_empty());

    // 5. Parser processes continuous multi-character byte stream with mixed lengths
    let text = "Rust 2026: 한글, café, 🦀!";
    let mut stream_receiver = TestReceiver::default();
    let mut stream_parser = Parser::new();
    for &b in text.as_bytes() {
        stream_parser.advance(&mut stream_receiver, b);
    }
    let collected: String = stream_receiver.codepoints.into_iter().collect();
    assert_eq!(collected, text);
    assert_eq!(stream_receiver.invalid_count, 0);

    println!("All utf8parse contract assertions passed successfully.");
}