golang.org/x/text v0.3.2: unicode.UTF8

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 unicode.UTF8 in pkg:golang/golang.org/x/text@v0.3.2
Kind: HOW

Use EXACTLY these public packages and versions:
  - pkg:golang/golang.org/x/text@v0.3.2
Demonstrate these symbols/APIs:
  - unicode.UTF8

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:sha256:58b6b7318f0bda54a7112d7d07bb89f1e8c853a474264e051efedaf3a95ac3df","contract":["unicode.UTF8 NewEncoder encodes valid UTF-8 strings into identical byte sequences","unicode.UTF8 NewDecoder decodes valid UTF-8 byte sequences into original text","unicode.UTF8 NewDecoder replaces invalid UTF-8 sequences with the Unicode replacement character","unicode.UTF8 NewEncoder replaces invalid UTF-8 sequences with the Unicode replacement character"],"goal":"verify unicode.UTF8 in pkg:golang/golang.org/x/text@v0.3.2","kind":"HOW","packages":["pkg:golang/golang.org/x/text@v0.3.2"],"schemaVersion":1,"symbols":["unicode.UTF8"]},"contractCommand":["go","run","./test"],"environment":{"arch":"x64","distro":"ubuntu","ecosystem":"golang","libc":"glibc","libcVersion":"2.39","os":"linux","osVersionBucket":"24","packageManager":"go","schemaVersion":1},"license":"MIT-0","packages":["pkg:golang/golang.org/x/text@v0.3.2"],"schemaVersion":1,"subject":"pkg:golang/golang.org/x/text@v0.3.2","symbols":["unicode.UTF8"],"verifierAdapter":"golang@1"}

module example.com/sample

go 1.22

require golang.org/x/text v0.3.2

golang.org/x/text v0.3.2 h1:tW2bmiBqwgJj/UpqtC8EpXEZVYOwU0yG4iWbprSVAcs=
golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=

package main

import (
	"fmt"
	"os"

	"golang.org/x/text/encoding/unicode"
)

func main() {
	// 1. Encode valid UTF-8 string
	enc := unicode.UTF8.NewEncoder()
	text := "Hello, 世界!"
	encoded, err := enc.String(text)
	if err != nil {
		fmt.Fprintf(os.Stderr, "encode error: %v\n", err)
		os.Exit(1)
	}
	fmt.Printf("Encoded: %s\n", encoded)

	// 2. Decode valid UTF-8 bytes
	dec := unicode.UTF8.NewDecoder()
	decoded, err := dec.String(encoded)
	if err != nil {
		fmt.Fprintf(os.Stderr, "decode error: %v\n", err)
		os.Exit(1)
	}
	fmt.Printf("Decoded: %s\n", decoded)

	// 3. Decoding invalid bytes with replacement
	invalidBytes := []byte{0xff, 0xfe, 'o', 'k'}
	sanitized, err := dec.Bytes(invalidBytes)
	if err != nil {
		fmt.Fprintf(os.Stderr, "sanitization error: %v\n", err)
		os.Exit(1)
	}
	fmt.Printf("Sanitized: %s\n", string(sanitized))
}

{
  "schemaVersion": 1,
  "goal": "verify unicode.UTF8 in pkg:golang/golang.org/x/text@v0.3.2",
  "kind": "HOW",
  "packages": [
    "pkg:golang/golang.org/x/text@v0.3.2"
  ],
  "symbols": [
    "unicode.UTF8"
  ]
}

package main

import (
	"bytes"
	"fmt"
	"os"

	"golang.org/x/text/encoding/unicode"
)

func main() {
	// Assertion 1: unicode.UTF8 NewEncoder encodes valid UTF-8 strings into identical byte sequences
	enc := unicode.UTF8.NewEncoder()
	src := "Hello, 世界! 🚀"
	encodedBytes, err := enc.Bytes([]byte(src))
	if err != nil {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 encode error: %v\n", err)
		os.Exit(1)
	}
	if !bytes.Equal(encodedBytes, []byte(src)) {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 encoded bytes mismatch: got %v, want %v\n", encodedBytes, []byte(src))
		os.Exit(1)
	}

	encodedStr, err := enc.String(src)
	if err != nil {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 encode string error: %v\n", err)
		os.Exit(1)
	}
	if encodedStr != src {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 encoded string mismatch: got %q, want %q\n", encodedStr, src)
		os.Exit(1)
	}

	// Assertion 2: unicode.UTF8 NewDecoder decodes valid UTF-8 byte sequences into original text
	dec := unicode.UTF8.NewDecoder()
	decodedBytes, err := dec.Bytes(encodedBytes)
	if err != nil {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 decode error: %v\n", err)
		os.Exit(1)
	}
	if !bytes.Equal(decodedBytes, []byte(src)) {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 decoded bytes mismatch: got %v, want %v\n", decodedBytes, []byte(src))
		os.Exit(1)
	}

	decodedStr, err := dec.String(encodedStr)
	if err != nil {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 decode string error: %v\n", err)
		os.Exit(1)
	}
	if decodedStr != src {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 decoded string mismatch: got %q, want %q\n", decodedStr, src)
		os.Exit(1)
	}

	// Assertion 3: unicode.UTF8 NewDecoder replaces invalid UTF-8 sequences with the Unicode replacement character
	invalidInput := []byte{0xff, 0xfe, 'a', 'b'}
	decodedInvalid, err := dec.Bytes(invalidInput)
	if err != nil {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 decode invalid bytes error: %v\n", err)
		os.Exit(1)
	}
	expectedReplacement := "\uFFFD\uFFFDab"
	if string(decodedInvalid) != expectedReplacement {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 replacement mismatch: got %q, want %q\n", string(decodedInvalid), expectedReplacement)
		os.Exit(1)
	}

	// Assertion 4: unicode.UTF8 NewEncoder replaces invalid UTF-8 sequences with the Unicode replacement character
	encInvalid, err := enc.Bytes([]byte{0x80, 'o', 'k'})
	if err != nil {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 encode invalid bytes error: %v\n", err)
		os.Exit(1)
	}
	if !bytes.Equal(encInvalid, []byte("\uFFFDok")) {
		fmt.Fprintf(os.Stderr, "FAIL: UTF8 encode replacement mismatch: got %q, want %q\n", string(encInvalid), "\uFFFDok")
		os.Exit(1)
	}

	fmt.Println("PASS: unicode.UTF8 contract verified")
}