charset-normalizer 3.5.1: detect

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:pypi/charset-normalizer@3.5.1
Kind: HOW

Use EXACTLY these public packages and versions:
  - pkg:pypi/charset-normalizer@3.5.1
Demonstrate these symbols/APIs:
  - detect
Constraints:
  - executionContext: node
Required runtime conditions:
  - ecosystem: npm
  - language: javascript
  - moduleSystem: cjs
  - packageManager: npm@10.9.8
  - runtime: node@22.23.2

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:dbd0035c0a8c816596136aff2a614d7559e16554b59e9c1294e9c2f08fb8a948","contract":["charset_normalizer.detect(data) detects character encoding from raw byte sequences","detect(data) returns dictionary with encoding, language, and confidence","detect(data) accurately identifies utf-8 and ascii encodings with 1.0 confidence","detect(data) raises TypeError when input is not bytes or bytearray"],"goal":"verify pkg:pypi/charset-normalizer@3.5.1","kind":"HOW","packages":["pkg:pypi/charset-normalizer@3.5.1"],"schemaVersion":1,"symbols":["detect"]},"contractCommand":["python","test/contract.py"],"environment":{"arch":"x64","distro":"alpine","ecosystem":"pypi","language":"python","libc":"musl","libcVersion":"1.2","os":"linux","osVersionBucket":"24","packageManager":"pip","runtime":"python","runtimeVersion":"3.12","schemaVersion":1},"license":"MIT-0","packages":["pkg:pypi/charset-normalizer@3.5.1"],"schemaVersion":1,"subject":"pkg:pypi/charset-normalizer@3.5.1","symbols":["detect"],"verifierAdapter":"python@1"}

charset-normalizer==3.5.1

{
  "schemaVersion": 1,
  "goal": "verify pkg:pypi/charset-normalizer@3.5.1",
  "kind": "HOW",
  "packages": [
    "pkg:pypi/charset-normalizer@3.5.1"
  ],
  "symbols": [
    "detect"
  ],
  "constraints": {
    "executionContext": "node"
  },
  "runtimeConditions": {
    "ecosystem": "npm",
    "language": "javascript",
    "moduleSystem": "cjs",
    "packageManager": "npm@10.9.8",
    "runtime": "node@22.23.2"
  }
}

"""Charset detection module demonstrating charset_normalizer.detect."""

import charset_normalizer


def detect_encoding(data: bytes) -> dict:
    """Detect encoding and language from a raw byte sequence using charset_normalizer.detect.

    Args:
        data: Raw byte string (bytes or bytearray) to analyze.

    Returns:
        dict containing 'encoding', 'language', and 'confidence'.

    Raises:
        TypeError: If data is not bytes or bytearray.
    """
    if not isinstance(data, (bytes, bytearray)):
        raise TypeError(f"Expected object of type bytes or bytearray, got: {type(data)}")

    return charset_normalizer.detect(data)

"""Contract verification test for charset_normalizer.detect."""

import os
import sys

# Ensure repository root is on sys.path
sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

import charset_normalizer
from src.detector import detect_encoding


def test_detect_utf8():
    sample_text = "Bonjour le monde! Ça va bien? Café & thé."
    raw_bytes = sample_text.encode("utf-8")

    result = charset_normalizer.detect(raw_bytes)
    assert isinstance(result, dict), f"Expected dict, got {type(result)}"
    assert result.get("encoding") == "utf-8", f"Expected utf-8, got {result.get('encoding')}"
    assert result.get("confidence") == 1.0, f"Expected 1.0 confidence, got {result.get('confidence')}"


def test_detect_ascii():
    sample_text = "Simple ASCII text payload for charset detection."
    raw_bytes = sample_text.encode("ascii")

    result = charset_normalizer.detect(raw_bytes)
    assert isinstance(result, dict), f"Expected dict, got {type(result)}"
    assert result.get("encoding") == "ascii", f"Expected ascii, got {result.get('encoding')}"
    assert result.get("confidence") == 1.0, f"Expected 1.0 confidence, got {result.get('confidence')}"
    assert result.get("language") == "English", f"Expected English language, got {result.get('language')}"


def test_detect_helper_wrapper():
    sample_text = "Guten Tag! Schönen Tag noch."
    raw_bytes = sample_text.encode("utf-8")

    result = detect_encoding(raw_bytes)
    assert result.get("encoding") == "utf-8", f"Unexpected encoding: {result.get('encoding')}"
    assert result.get("confidence") == 1.0, f"Unexpected confidence: {result.get('confidence')}"


def test_detect_type_error():
    try:
        charset_normalizer.detect("string instead of bytes")
        assert False, "Expected TypeError when passing str to detect"
    except TypeError:
        pass

    try:
        detect_encoding(12345)
        assert False, "Expected TypeError when passing int to detect_encoding"
    except TypeError:
        pass


def main():
    test_detect_utf8()
    test_detect_ascii()
    test_detect_helper_wrapper()
    test_detect_type_error()
    print("Contract tests for charset_normalizer.detect passed successfully.")
    return 0


if __name__ == "__main__":
    sys.exit(main())