{
  "version": 1,
  "categories": {
    "invisible": "Zero-width and filler characters survive copy-paste, break string comparisons, corrupt YAML and JSON, and show up as phantom diffs in git.",
    "bidi": "Bidirectional control characters can reorder how source code and filenames are displayed. This is the Trojan Source technique (CVE-2021-42574).",
    "tags": "Unicode tag characters are invisible but carry ASCII payloads. They are used for text watermarking and for smuggling hidden instructions past human reviewers.",
    "variation": "Variation selectors are invisible modifiers. Outside emoji and CJK ideographs they serve no purpose in plain text and can encode hidden data.",
    "spaces": "Spaces that look like ordinary spaces but are not. They break search, deduplication, shell commands, and CSV parsing. The narrow no-break space is a known fingerprint of AI chat output.",
    "typography": "Smart quotes, em dashes, and the single-character ellipsis read fine in prose but break code, config files, and shell one-liners, and they are common tells of machine-generated text.",
    "confusables": "Cyrillic or Greek letters hiding inside Latin words. Used in phishing domains and to defeat plagiarism and spam filters. The word looks normal and matches nothing."
  },
  "rules": [
    {
      "codepoint": "U+200B",
      "name": "ZERO WIDTH SPACE",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+2060",
      "name": "WORD JOINER",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+FEFF",
      "name": "ZERO WIDTH NO-BREAK SPACE (BOM)",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+00AD",
      "name": "SOFT HYPHEN",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+180E",
      "name": "MONGOLIAN VOWEL SEPARATOR",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+2061",
      "name": "FUNCTION APPLICATION",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+2062",
      "name": "INVISIBLE TIMES",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+2063",
      "name": "INVISIBLE SEPARATOR",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+2064",
      "name": "INVISIBLE PLUS",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+3164",
      "name": "HANGUL FILLER",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+FFA0",
      "name": "HALFWIDTH HANGUL FILLER",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+115F",
      "name": "HANGUL CHOSEONG FILLER",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+1160",
      "name": "HANGUL JUNGSEONG FILLER",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+200C",
      "name": "ZERO WIDTH NON-JOINER",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+200D",
      "name": "ZERO WIDTH JOINER",
      "category": "invisible",
      "replacement": ""
    },
    {
      "codepoint": "U+200E",
      "name": "LEFT-TO-RIGHT MARK",
      "category": "bidi",
      "replacement": ""
    },
    {
      "codepoint": "U+200F",
      "name": "RIGHT-TO-LEFT MARK",
      "category": "bidi",
      "replacement": ""
    },
    {
      "codepoint": "U+061C",
      "name": "ARABIC LETTER MARK",
      "category": "bidi",
      "replacement": ""
    },
    {
      "codepoint": "U+00A0",
      "name": "NO-BREAK SPACE",
      "category": "spaces",
      "replacement": " "
    },
    {
      "codepoint": "U+202F",
      "name": "NARROW NO-BREAK SPACE",
      "category": "spaces",
      "replacement": " "
    },
    {
      "codepoint": "U+1680",
      "name": "OGHAM SPACE MARK",
      "category": "spaces",
      "replacement": " "
    },
    {
      "codepoint": "U+205F",
      "name": "MEDIUM MATHEMATICAL SPACE",
      "category": "spaces",
      "replacement": " "
    },
    {
      "codepoint": "U+3000",
      "name": "IDEOGRAPHIC SPACE",
      "category": "spaces",
      "replacement": " "
    },
    {
      "codepoint": "U+2018",
      "name": "LEFT SINGLE QUOTATION MARK",
      "category": "typography",
      "replacement": "'"
    },
    {
      "codepoint": "U+2019",
      "name": "RIGHT SINGLE QUOTATION MARK",
      "category": "typography",
      "replacement": "'"
    },
    {
      "codepoint": "U+201C",
      "name": "LEFT DOUBLE QUOTATION MARK",
      "category": "typography",
      "replacement": "\""
    },
    {
      "codepoint": "U+201D",
      "name": "RIGHT DOUBLE QUOTATION MARK",
      "category": "typography",
      "replacement": "\""
    },
    {
      "codepoint": "U+2032",
      "name": "PRIME",
      "category": "typography",
      "replacement": "'"
    },
    {
      "codepoint": "U+2033",
      "name": "DOUBLE PRIME",
      "category": "typography",
      "replacement": "\""
    },
    {
      "codepoint": "U+2026",
      "name": "HORIZONTAL ELLIPSIS",
      "category": "typography",
      "replacement": "..."
    },
    {
      "codepoint": "U+2011",
      "name": "NON-BREAKING HYPHEN",
      "category": "typography",
      "replacement": "-"
    },
    {
      "codepoint": "U+2212",
      "name": "MINUS SIGN",
      "category": "typography",
      "replacement": "-"
    },
    {
      "codepoint": "U+2013",
      "name": "EN DASH",
      "category": "typography",
      "replacement": "-"
    },
    {
      "codepoint": "U+2014",
      "name": "EM DASH",
      "category": "typography",
      "replacement": ", "
    },
    {
      "range": "U+202A..U+202E",
      "name": "BIDI EMBEDDING/OVERRIDE CONTROL",
      "category": "bidi",
      "replacement": ""
    },
    {
      "range": "U+2066..U+2069",
      "name": "BIDI ISOLATE CONTROL",
      "category": "bidi",
      "replacement": ""
    },
    {
      "range": "U+2000..U+200A",
      "name": "TYPOGRAPHIC SPACE",
      "category": "spaces",
      "replacement": " "
    },
    {
      "range": "U+FE00..U+FE0F",
      "name": "VARIATION SELECTOR",
      "category": "variation",
      "replacement": ""
    },
    {
      "range": "U+E0100..U+E01EF",
      "name": "VARIATION SELECTOR SUPPLEMENT",
      "category": "variation",
      "replacement": ""
    },
    {
      "range": "U+E0000..U+E007F",
      "name": "TAG CHARACTER",
      "category": "tags",
      "replacement": ""
    }
  ],
  "confusables": {
    "а": "a",
    "е": "e",
    "о": "o",
    "р": "p",
    "с": "c",
    "у": "y",
    "х": "x",
    "ѕ": "s",
    "і": "i",
    "ј": "j",
    "һ": "h",
    "ԛ": "q",
    "ԝ": "w",
    "А": "A",
    "В": "B",
    "Е": "E",
    "К": "K",
    "М": "M",
    "Н": "H",
    "О": "O",
    "Р": "P",
    "С": "C",
    "Т": "T",
    "У": "Y",
    "Х": "X",
    "Ѕ": "S",
    "І": "I",
    "Ј": "J",
    "ο": "o",
    "ν": "v",
    "Α": "A",
    "Β": "B",
    "Ε": "E",
    "Ζ": "Z",
    "Η": "H",
    "Ι": "I",
    "Κ": "K",
    "Μ": "M",
    "Ν": "N",
    "Ο": "O",
    "Ρ": "P",
    "Τ": "T",
    "Υ": "Y",
    "Χ": "X"
  }
}