Xiaodong Su

use once_cell::sync::Lazy;
use regex::Regex;
use std::collections::HashMap;

/// Highlighting rules for a "family" of languages.
struct LangRule {
    line_comments: &'static [&'static str],
    block_comments: &'static [(&'static str, &'static str)],
    /// If true, enables strings delimited by " and '
    strings: bool,
    /// If true, also enables triple-quoted strings (Python)
    triple_quote: bool,
    /// If true, also enables backtick template strings (JS/TS)
    backtick: bool,
    /// If true, keywords are matched case-insensitively (e.g. SQL)
    case_insensitive_keywords: bool,
    keywords: &'static [&'static str],
}

const EMPTY_KW: &[&str] = &[];

fn rule_for(lang: &str) -> LangRule {
    match lang {
        "rust" => LangRule {
            line_comments: &["//"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "as", "break", "const", "continue", "crate", "dyn", "else", "enum", "extern",
                "false", "fn", "for", "if", "impl", "in", "let", "loop", "match", "mod", "move",
                "mut", "pub", "ref", "return", "self", "Self", "static", "struct", "super",
                "trait", "true", "type", "unsafe", "use", "where", "while", "async", "await",
                "union",
            ],
        },
        "python" => LangRule {
            line_comments: &["#"],
            block_comments: &[],
            strings: true,
            triple_quote: true,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "False", "None", "True", "and", "as", "assert", "async", "await", "break",
                "class", "continue", "def", "del", "elif", "else", "except", "finally", "for",
                "from", "global", "if", "import", "in", "is", "lambda", "nonlocal", "not", "or",
                "pass", "raise", "return", "try", "while", "with", "yield", "self",
            ],
        },
        "javascript" | "typescript" => LangRule {
            line_comments: &["//"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: true,
            case_insensitive_keywords: false,
            keywords: &[
                "break", "case", "catch", "class", "const", "continue", "debugger", "default",
                "delete", "do", "else", "export", "extends", "finally", "for", "function", "if",
                "import", "in", "instanceof", "new", "return", "super", "switch", "this", "throw",
                "try", "typeof", "var", "void", "while", "with", "yield", "let", "static",
                "async", "await", "of", "null", "true", "false", "undefined", "interface",
                "type", "enum", "implements", "namespace", "readonly", "public", "private",
                "protected", "abstract", "as", "declare", "from", "get", "set",
            ],
        },
        "java" => LangRule {
            line_comments: &["//"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "abstract", "assert", "boolean", "break", "byte", "case", "catch", "char",
                "class", "const", "continue", "default", "do", "double", "else", "enum",
                "extends", "final", "finally", "float", "for", "goto", "if", "implements",
                "import", "instanceof", "int", "interface", "long", "native", "new", "package",
                "private", "protected", "public", "return", "short", "static", "strictfp",
                "super", "switch", "synchronized", "this", "throw", "throws", "transient", "try",
                "void", "volatile", "while", "true", "false", "null", "var", "record", "yield",
                "sealed", "permits",
            ],
        },
        "c" => LangRule {
            line_comments: &["//"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "auto", "break", "case", "char", "const", "continue", "default", "do", "double",
                "else", "enum", "extern", "float", "for", "goto", "if", "inline", "int", "long",
                "register", "restrict", "return", "short", "signed", "sizeof", "static",
                "struct", "switch", "typedef", "union", "unsigned", "void", "volatile", "while",
            ],
        },
        "cpp" => LangRule {
            line_comments: &["//"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "auto", "break", "case", "char", "const", "continue", "default", "do", "double",
                "else", "enum", "extern", "float", "for", "goto", "if", "inline", "int", "long",
                "register", "return", "short", "signed", "sizeof", "static", "struct", "switch",
                "typedef", "union", "unsigned", "void", "volatile", "while", "class",
                "namespace", "template", "typename", "public", "private", "protected", "virtual",
                "friend", "this", "new", "delete", "try", "catch", "throw", "using", "operator",
                "explicit", "mutable", "bool", "true", "false", "nullptr", "constexpr",
                "decltype", "noexcept", "override", "final",
            ],
        },
        "csharp" => LangRule {
            line_comments: &["//"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "abstract", "as", "base", "bool", "break", "byte", "case", "catch", "char",
                "checked", "class", "const", "continue", "decimal", "default", "delegate", "do",
                "double", "else", "enum", "event", "explicit", "extern", "false", "finally",
                "fixed", "float", "for", "foreach", "goto", "if", "implicit", "in", "int",
                "interface", "internal", "is", "lock", "long", "namespace", "new", "null",
                "object", "operator", "out", "override", "params", "private", "protected",
                "public", "readonly", "ref", "return", "sbyte", "sealed", "short", "sizeof",
                "stackalloc", "static", "string", "struct", "switch", "this", "throw", "true",
                "try", "typeof", "uint", "ulong", "unchecked", "unsafe", "ushort", "using",
                "virtual", "void", "volatile", "while", "var", "async", "await", "yield",
                "nameof",
            ],
        },
        "go" => LangRule {
            line_comments: &["//"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: true,
            case_insensitive_keywords: false,
            keywords: &[
                "break", "case", "chan", "const", "continue", "default", "defer", "else",
                "fallthrough", "for", "func", "go", "goto", "if", "import", "interface", "map",
                "package", "range", "return", "select", "struct", "switch", "type", "var",
                "true", "false", "nil", "iota",
            ],
        },
        "ruby" => LangRule {
            line_comments: &["#"],
            block_comments: &[],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "def", "end", "if", "elsif", "else", "unless", "while", "until", "for", "in",
                "do", "begin", "rescue", "ensure", "raise", "class", "module", "self", "nil",
                "true", "false", "and", "or", "not", "then", "yield", "return", "break", "next",
                "redo", "retry", "super", "require", "require_relative", "attr_accessor",
                "attr_reader", "attr_writer", "private", "public", "protected",
            ],
        },
        "php" => LangRule {
            line_comments: &["//", "#"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "abstract", "and", "array", "as", "break", "callable", "case", "catch", "class",
                "clone", "const", "continue", "declare", "default", "do", "echo", "else",
                "elseif", "empty", "extends", "final", "finally", "fn", "for", "foreach",
                "function", "global", "goto", "if", "implements", "include", "include_once",
                "instanceof", "interface", "isset", "list", "match", "namespace", "new", "or",
                "print", "private", "protected", "public", "require", "require_once", "return",
                "static", "switch", "throw", "trait", "try", "unset", "use", "var", "while",
                "xor", "yield", "true", "false", "null", "self", "parent",
            ],
        },
        "bash" => LangRule {
            line_comments: &["#"],
            block_comments: &[],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "if", "then", "else", "elif", "fi", "for", "while", "until", "do", "done",
                "case", "esac", "function", "in", "return", "break", "continue", "local",
                "export", "readonly", "shift", "exit", "echo", "source",
            ],
        },
        "sql" => LangRule {
            line_comments: &["--"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: true,
            keywords: &[
                "select", "from", "where", "insert", "into", "values", "update", "set",
                "delete", "create", "table", "alter", "drop", "join", "inner", "left", "right",
                "outer", "on", "group", "by", "order", "having", "as", "and", "or", "not",
                "null", "is", "in", "like", "limit", "offset", "distinct", "union", "all",
                "exists", "between", "case", "when", "then", "end", "primary", "key", "foreign",
                "references", "default", "index", "view", "trigger", "procedure", "function",
                "begin", "commit", "rollback",
            ],
        },
        "lua" => LangRule {
            line_comments: &["--"],
            block_comments: &[("--[[", "]]")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "and", "break", "do", "else", "elseif", "end", "false", "for", "function", "if",
                "in", "local", "nil", "not", "or", "repeat", "return", "then", "true", "until",
                "while",
            ],
        },
        "kotlin" => LangRule {
            line_comments: &["//"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "as", "break", "class", "continue", "do", "else", "false", "for", "fun", "if",
                "in", "interface", "is", "null", "object", "package", "return", "super", "this",
                "throw", "true", "try", "typealias", "val", "var", "when", "while", "by",
                "companion", "constructor", "data", "enum", "import", "init", "override",
                "private", "protected", "public", "sealed", "suspend",
            ],
        },
        "swift" => LangRule {
            line_comments: &["//"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &[
                "class", "deinit", "enum", "extension", "func", "import", "init", "internal",
                "let", "operator", "private", "protocol", "public", "static", "struct",
                "subscript", "typealias", "var", "break", "case", "continue", "default", "do",
                "else", "fallthrough", "if", "in", "for", "return", "switch", "where", "while",
                "as", "false", "true", "guard", "nil", "self", "super", "throw", "try", "async",
                "await",
            ],
        },
        "css" | "scss" | "less" => LangRule {
            line_comments: &[],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: EMPTY_KW,
        },
        "xml" => LangRule {
            line_comments: &[],
            block_comments: &[("<!--", "-->")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: EMPTY_KW,
        },
        "json" => LangRule {
            line_comments: &[],
            block_comments: &[],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &["true", "false", "null"],
        },
        "yaml" => LangRule {
            line_comments: &["#"],
            block_comments: &[],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &["true", "false", "null", "yes", "no"],
        },
        "ini" => LangRule {
            line_comments: &["#", ";"],
            block_comments: &[],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: EMPTY_KW,
        },
        "dockerfile" => LangRule {
            line_comments: &["#"],
            block_comments: &[],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: true,
            keywords: &[
                "from", "run", "cmd", "label", "expose", "env", "add", "copy", "entrypoint",
                "volume", "user", "workdir", "arg", "onbuild", "stopsignal", "healthcheck",
                "shell",
            ],
        },
        "makefile" => LangRule {
            line_comments: &["#"],
            block_comments: &[],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: EMPTY_KW,
        },
        "graphql" => LangRule {
            line_comments: &["#"],
            block_comments: &[],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &["query", "mutation", "subscription", "type", "input", "enum", "interface", "fragment", "on"],
        },
        // Language families without detailed specific rules: still
        // highlight comments/strings/numbers generically.
        "perl" => LangRule {
            line_comments: &["#"],
            block_comments: &[],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &["my", "our", "sub", "if", "elsif", "else", "unless", "while", "for", "foreach", "return", "use", "package"],
        },
        "groovy" => LangRule {
            line_comments: &["//"],
            block_comments: &[("/*", "*/")],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: EMPTY_KW,
        },
        "r" => LangRule {
            line_comments: &["#"],
            block_comments: &[],
            strings: true,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: &["function", "if", "else", "for", "while", "repeat", "break", "next", "return", "TRUE", "FALSE", "NULL", "NA"],
        },
        "diff" => LangRule {
            line_comments: &[],
            block_comments: &[],
            strings: false,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: EMPTY_KW,
        },
        // markdown, plaintext, cmake, vbnet, dos, powershell, etc:
        // no specific highlighting, plain but formatted text.
        _ => LangRule {
            line_comments: &[],
            block_comments: &[],
            strings: false,
            triple_quote: false,
            backtick: false,
            case_insensitive_keywords: false,
            keywords: EMPTY_KW,
        },
    }
}

/// Cache of compiled regexes (one per language actually encountered).
static REGEX_CACHE: Lazy<std::sync::Mutex<HashMap<String, Option<Regex>>>> =
    Lazy::new(|| std::sync::Mutex::new(HashMap::new()));

fn build_regex(rule: &LangRule) -> Option<Regex> {
    let mut comment_alts: Vec<String> = Vec::new();
    for (start, end) in rule.block_comments {
        comment_alts.push(format!(
            "(?s:{}.*?{})",
            regex::escape(start),
            regex::escape(end)
        ));
    }
    for prefix in rule.line_comments {
        comment_alts.push(format!("{}[^\n]*", regex::escape(prefix)));
    }

    let mut string_alts: Vec<String> = Vec::new();
    if rule.triple_quote {
        string_alts.push(r#"(?s:"""(?:[^"\\]|\\.)*?""")"#.to_string());
        string_alts.push(r#"(?s:'''(?:[^'\\]|\\.)*?''')"#.to_string());
    }
    if rule.strings {
        string_alts.push(r#""(?:[^"\\\n]|\\.)*""#.to_string());
        string_alts.push(r#"'(?:[^'\\\n]|\\.)*'"#.to_string());
    }
    if rule.backtick {
        string_alts.push(r"(?s:`(?:[^`\\]|\\.)*`)".to_string());
    }

    let number_pat = r"\b0[xX][0-9a-fA-F]+\b|\b\d+\.\d+(?:[eE][+-]?\d+)?\b|\b\d+\b".to_string();

    let mut keyword_alt = String::new();
    if !rule.keywords.is_empty() {
        let escaped: Vec<String> = rule.keywords.iter().map(|k| regex::escape(k)).collect();
        let joined = escaped.join("|");
        keyword_alt = if rule.case_insensitive_keywords {
            format!("(?i:\\b(?:{})\\b)", joined)
        } else {
            format!("\\b(?:{})\\b", joined)
        };
    }

    let mut parts: Vec<String> = Vec::new();
    if !comment_alts.is_empty() {
        parts.push(format!("(?P<comment>{})", comment_alts.join("|")));
    }
    if !string_alts.is_empty() {
        parts.push(format!("(?P<string>{})", string_alts.join("|")));
    }
    parts.push(format!("(?P<number>{})", number_pat));
    if !keyword_alt.is_empty() {
        parts.push(format!("(?P<keyword>{})", keyword_alt));
    }

    if parts.is_empty() {
        return None;
    }

    Regex::new(&parts.join("|")).ok()
}

fn escape_html(s: &str) -> String {
    let mut out = String::with_capacity(s.len());
    for c in s.chars() {
        match c {
            '&' => out.push_str("&amp;"),
            '<' => out.push_str("&lt;"),
            '>' => out.push_str("&gt;"),
            '"' => out.push_str("&quot;"),
            '\'' => out.push_str("&#39;"),
            _ => out.push(c),
        }
    }
    out
}

/// Highlights the source code and returns HTML that's already escaped
/// and ready to insert inside a `<pre><code>...</code></pre>`.
/// No JavaScript involved: all the work happens here, in Rust,
/// at file-generation time.
pub fn highlight_code(content: &str, lang: &str) -> String {
    let rule = rule_for(lang);

    let regex_opt = {
        let mut cache = REGEX_CACHE.lock().unwrap();
        cache
            .entry(lang.to_string())
            .or_insert_with(|| build_regex(&rule))
            .clone()
    };

    let Some(re) = regex_opt else {
        return escape_html(content);
    };

    let mut out = String::with_capacity(content.len() + content.len() / 4);
    let mut last = 0;

    for caps in re.captures_iter(content) {
        let m = caps.get(0).unwrap();
        out.push_str(&escape_html(&content[last..m.start()]));

        let class = if caps.name("comment").is_some() {
            "c"
        } else if caps.name("string").is_some() {
            "s"
        } else if caps.name("number").is_some() {
            "n"
        } else if caps.name("keyword").is_some() {
            "k"
        } else {
            ""
        };

        let escaped_match = escape_html(m.as_str());
        if class.is_empty() {
            out.push_str(&escaped_match);
        } else {
            out.push_str(&format!("<span class=\"{}\">{}</span>", class, escaped_match));
        }
        last = m.end();
    }
    out.push_str(&escape_html(&content[last..]));
    out
}