//! Minimal glob matcher for tool/extension allow- and deny-lists.
//!
//! Patterns and names are dot-delimited segments (e.g. `std.git.status`).
//! Matching operates on whole segments, never on individual characters.
//!
//! Supported segment wildcards:
//!   - `*` matches exactly one segment. `std.*` matches `std.read` but
//!     not `std.git.status` (greedy within a segment, but not
//!     dot-agnostic).
//!   - `**` matches one or more segments. `std.**` matches both
//!     `std.read` and `std.git.status`.
//!
//! A wildcard is only recognized as a whole segment: `std.*` and `std.**`
//! are wildcards, but `std.rea*` is a literal segment (the `*` has no
//! special meaning mid-segment). Everything else is matched literally.

const std = @import("std");

/// Returns true if `name` matches `pattern` under the segment rules above.
pub fn match(pattern: []const u8, name: []const u8) bool {
    var pat_it = std.mem.splitScalar(u8, pattern, '.');
    var name_it = std.mem.splitScalar(u8, name, '.');
    return matchSegments(&pat_it, &name_it);
}

const SegmentIter = std.mem.SplitIterator(u8, .scalar);

fn matchSegments(pat_it: *SegmentIter, name_it: *SegmentIter) bool {
    while (pat_it.next()) |seg| {
        if (std.mem.eql(u8, seg, "**")) {
            // `**` matches one or more remaining segments. Try the
            // shortest match first (one segment), then extend.
            const rest_pat = pat_it.*; // pattern after `**`
            while (name_it.next()) |_| {
                var pat_copy = rest_pat;
                var name_copy = name_it.*;
                if (matchSegments(&pat_copy, &name_copy)) return true;
            }
            // `**` requires at least one segment, and the trailing
            // pattern must have matched the remainder above.
            return false;
        }

        const name_seg = name_it.next() orelse return false;
        if (std.mem.eql(u8, seg, "*")) {
            // Matches exactly one (any) segment.
            continue;
        }
        if (!std.mem.eql(u8, seg, name_seg)) return false;
    }

    // Pattern exhausted: match iff name is also exhausted.
    return name_it.next() == null;
}

// ---------------------------------------------------------------------------
// Specificity
// ---------------------------------------------------------------------------

/// How specific a pattern is, used to rank rules that match the same name in
/// an allow/deny list. `order` gives an *ascending* order: less specific
/// sorts before more specific, so a "last matching rule wins" scan picks the
/// most specific match. Only meaningful when comparing patterns that both
/// match a given name; the metric is a consistent proxy (narrower match set).
pub const Specificity = struct {
    /// Count of literal (non-wildcard) segments — the dominant signal.
    literals: usize = 0,
    /// Total segment count (a longer pattern constrains more positions).
    segments: usize = 0,
    /// Count of `**` segments (the loosest wildcard).
    double_stars: usize = 0,

    /// Ascending order: `.lt` means `a` is *less* specific than `b`. Ranking:
    ///   1. more literal segments  (a.b.* > a.*, a.b.** > a.**)
    ///   2. more total segments    (a.*.* > a.*)
    ///   3. fewer `**` segments    (a.* > a.**)
    pub fn order(a: Specificity, b: Specificity) std.math.Order {
        if (a.literals != b.literals) return std.math.order(a.literals, b.literals);
        if (a.segments != b.segments) return std.math.order(a.segments, b.segments);
        // Fewer `**` → more specific (invert: `*` beats `**`).
        return std.math.order(b.double_stars, a.double_stars);
    }
};

/// Compute the specificity of a dot-delimited glob pattern.
pub fn specificity(pattern: []const u8) Specificity {
    var s: Specificity = .{};
    var it = std.mem.splitScalar(u8, pattern, '.');
    while (it.next()) |seg| {
        s.segments += 1;
        if (std.mem.eql(u8, seg, "**")) {
            s.double_stars += 1;
        } else if (!std.mem.eql(u8, seg, "*")) {
            s.literals += 1;
        }
    }
    return s;
}

// ---------------------------------------------------------------------------
// Tests
// ---------------------------------------------------------------------------

const testing = std.testing;

test "specificity: more literals wins" {
    // agent.rules (2 literals) is more specific than agent.* (1 literal).
    try testing.expectEqual(std.math.Order.gt, specificity("agent.rules").order(specificity("agent.*")));
    try testing.expectEqual(std.math.Order.lt, specificity("agent.*").order(specificity("agent.rules")));
}

test "specificity: single star beats double star" {
    // Same literal count and length; `*` is more specific than `**`.
    try testing.expectEqual(std.math.Order.gt, specificity("agent.*").order(specificity("agent.**")));
}

test "specificity: a longer glob trumps a shorter one" {
    // Same literal count; more segments constrains more → more specific.
    try testing.expectEqual(std.math.Order.gt, specificity("a.*.*").order(specificity("a.*")));
    try testing.expectEqual(std.math.Order.gt, specificity("a.**.**").order(specificity("a.**")));
    // Literal count still dominates length.
    try testing.expectEqual(std.math.Order.gt, specificity("a.b.*").order(specificity("a.*")));
    try testing.expectEqual(std.math.Order.gt, specificity("a.b.**").order(specificity("a.**")));
}

test "specificity: literal-heavier pattern beats a broad ** even if longer" {
    // agent.rules.detail (3 literals) more specific than agent.** (1 literal).
    try testing.expectEqual(std.math.Order.gt, specificity("agent.rules.detail").order(specificity("agent.**")));
}

test "specificity: bare ** is the least specific" {
    try testing.expectEqual(std.math.Order.lt, specificity("**").order(specificity("agent.rules")));
    try testing.expectEqual(std.math.Order.lt, specificity("**").order(specificity("*")));
}

test "literal match" {
    try testing.expect(match("std.read", "std.read"));
    try testing.expect(!match("std.read", "std.write"));
    try testing.expect(!match("std.read", "std.read.more"));
    try testing.expect(!match("std.read.more", "std.read"));
}

test "single star matches exactly one segment" {
    try testing.expect(match("std.*", "std.read"));
    try testing.expect(match("std.*", "std.write"));
    try testing.expect(!match("std.*", "std.git.status"));
    try testing.expect(!match("std.*", "std"));
    try testing.expect(!match("std.*", "other.read"));
}

test "double star is dot-agnostic, one or more segments" {
    try testing.expect(match("std.**", "std.read"));
    try testing.expect(match("std.**", "std.git.status"));
    try testing.expect(!match("std.**", "std"));
    try testing.expect(!match("std.**", "other.read"));
}

test "bare single star matches one segment" {
    try testing.expect(match("*", "std"));
    try testing.expect(!match("*", "std.read"));
    // An empty name is a single empty segment, which `*` matches.
    try testing.expect(match("*", ""));
}

test "bare double star matches everything non-empty" {
    try testing.expect(match("**", "std"));
    try testing.expect(match("**", "std.read"));
    try testing.expect(match("**", "std.git.status"));
}

test "star in middle" {
    try testing.expect(match("*.read", "std.read"));
    try testing.expect(match("*.*", "std.read"));
    try testing.expect(!match("*.*", "std.git.status"));
    try testing.expect(match("std.*.status", "std.git.status"));
    try testing.expect(!match("std.*.status", "std.status"));
}

test "double star in middle" {
    try testing.expect(match("std.**.status", "std.git.status"));
    try testing.expect(match("std.**.status", "std.a.b.status"));
    try testing.expect(!match("std.**.status", "std.status"));
    try testing.expect(match("**.status", "std.git.status"));
}

test "wildcard only recognized as whole segment" {
    // A `*` embedded in a segment is a literal, not a wildcard.
    try testing.expect(match("std.rea*", "std.rea*"));
    try testing.expect(!match("std.rea*", "std.read"));
}

test "empty pattern only matches empty name" {
    try testing.expect(match("", ""));
    try testing.expect(!match("", "x"));
}