#!/bin/sh
# sample-utf8.sh: UTF-8 test file for shell scripts.
# Free sample from 99helpers.com/file-types/sh
# Run: sh sample-utf8.sh   (or bash sample-utf8.sh)
# The shell doesn't decode the file: it passes the bytes through to the
# terminal. Whether you see the text correctly depends on your terminal
# and locale (the LANG and LC_ALL settings), not on the script.

set -eu

# 1. Which locale is this shell using? Step 3 depends on it.
printf 'Locale: LANG=%s LC_ALL=%s\n' "${LANG:-unset}" "${LC_ALL:-unset}"

# 2. Non-ASCII text, printed as is.
for text in "Goedemorgen, café-eigenaar" "Grüß Gott, Straße" "Ça va, Zoë ?" \
            "Καλημέρα" "Здравствуйте" "مرحبا" "שלום" "नमस्ते" \
            "こんにちは" "你好" "안녕하세요" "€ £ ¥ ₹ ≤ ≥ ∞ ✓" "👋🌍🐚"; do
  # 3. ${#text} counts characters in bash, zsh and ksh with a UTF-8 locale,
  #    but bytes in the C locale and in dash. wc -c always counts bytes.
  bytes=$(printf '%s' "$text" | wc -c | tr -d ' ')
  printf '%s  (length %s, %s bytes)\n' "$text" "${#text}" "$bytes"
done

# 4. File names can be non-ASCII too: always quote them.
file_name="résumé 2026.txt"
printf 'A file name with an accent and a space: "%s"\n' "$file_name"