metadata:
  version: "1.0.0"
  last_updated: "2026-02-01"
  source_urls: []

category: encoding
subcategory: charset
tier: T2

bugs_caught:
  - "Character encoding detection"
  - "BOM handling"
  - "Mojibake"

values:
  utf8_bom:
    value: "\xEF\xBB\xBFHello"
    bugs_caught:
      - "UTF-8 BOM handling"
      - "Invisible prefix"
    safe_for_automation: true
    bytes: "EF BB BF 48 65 6C 6C 6F"

  utf16_le_bom:
    value: "\xFF\xFEH\x00e\x00l\x00l\x00o\x00"
    bugs_caught:
      - "UTF-16 LE detection"
    safe_for_automation: true
    bytes: "FF FE 48 00 65 00 6C 00 6C 00 6F 00"

  utf16_be_bom:
    value: "\xFE\xFF\x00H\x00e\x00l\x00l\x00o"
    bugs_caught:
      - "UTF-16 BE detection"
    safe_for_automation: true
    bytes: "FE FF 00 48 00 65 00 6C 00 6C 00 6F"

  latin1_high:
    value: "\xe9"
    bugs_caught:
      - "Latin-1 high byte (é)"
      - "UTF-8 vs Latin-1 confusion"
    safe_for_automation: true
    note: "é in Latin-1, invalid UTF-8"

  windows_1252:
    value: "\x93\x94"
    bugs_caught:
      - "Windows smart quotes"
      - "CP1252 vs Latin-1"
    safe_for_automation: true
    note: "Smart quotes in Windows-1252"

  ascii_only:
    value: "Hello World 123"
    bugs_caught:
      - "Pure ASCII handling"
    safe_for_automation: true

  high_ascii:
    value: "\x80\x81\x82"
    bugs_caught:
      - "High ASCII bytes"
      - "Extended ASCII handling"
    safe_for_automation: true

  mixed_valid_invalid:
    value: "Hello\xFFWorld"
    bugs_caught:
      - "Invalid byte in string"
      - "Replacement character handling"
    safe_for_automation: true

  null_byte_middle:
    value: "Hello\x00World"
    bugs_caught:
      - "Null byte in string"
      - "C-string truncation"
    safe_for_automation: true