commit 7b301e96bffcfcc2d53e60db1f4dfc80fc9ec28a
Author: Pascal P. <pascal@phelipot.me>
Date:   Mon Jul 13 16:14:34 2026 +0200

    Initial commit

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..3389c86
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+.zig-cache/
+zig-out/
diff --git a/build.zig b/build.zig
new file mode 100644
index 0000000..886e5de
--- /dev/null
+++ b/build.zig
@@ -0,0 +1,156 @@
+const std = @import("std");
+
+// Although this function looks imperative, it does not perform the build
+// directly and instead it mutates the build graph (`b`) that will be then
+// executed by an external runner. The functions in `std.Build` implement a DSL
+// for defining build steps and express dependencies between them, allowing the
+// build runner to parallelize the build automatically (and the cache system to
+// know when a step doesn't need to be re-run).
+pub fn build(b: *std.Build) void {
+    // Standard target options allow the person running `zig build` to choose
+    // what target to build for. Here we do not override the defaults, which
+    // means any target is allowed, and the default is native. Other options
+    // for restricting supported target set are available.
+    const target = b.standardTargetOptions(.{});
+    // Standard optimization options allow the person running `zig build` to select
+    // between Debug, ReleaseSafe, ReleaseFast, and ReleaseSmall. Here we do not
+    // set a preferred release mode, allowing the user to decide how to optimize.
+    const optimize = b.standardOptimizeOption(.{});
+    // It's also possible to define more custom flags to toggle optional features
+    // of this build script using `b.option()`. All defined flags (including
+    // target and optimize options) will be listed when running `zig build --help`
+    // in this directory.
+
+    // This creates a module, which represents a collection of source files alongside
+    // some compilation options, such as optimization mode and linked system libraries.
+    // Zig modules are the preferred way of making Zig code available to consumers.
+    // addModule defines a module that we intend to make available for importing
+    // to our consumers. We must give it a name because a Zig package can expose
+    // multiple modules and consumers will need to be able to specify which
+    // module they want to access.
+    const mod = b.addModule("yareg", .{
+        // The root source file is the "entry point" of this module. Users of
+        // this module will only be able to access public declarations contained
+        // in this file, which means that if you have declarations that you
+        // intend to expose to consumers that were defined in other files part
+        // of this module, you will have to make sure to re-export them from
+        // the root file.
+        .root_source_file = b.path("src/root.zig"),
+        // Later on we'll use this module as the root module of a test executable
+        // which requires us to specify a target.
+        .target = target,
+    });
+
+    // Here we define an executable. An executable needs to have a root module
+    // which needs to expose a `main` function. While we could add a main function
+    // to the module defined above, it's sometimes preferable to split business
+    // logic and the CLI into two separate modules.
+    //
+    // If your goal is to create a Zig library for others to use, consider if
+    // it might benefit from also exposing a CLI tool. A parser library for a
+    // data serialization format could also bundle a CLI syntax checker, for example.
+    //
+    // If instead your goal is to create an executable, consider if users might
+    // be interested in also being able to embed the core functionality of your
+    // program in their own executable in order to avoid the overhead involved in
+    // subprocessing your CLI tool.
+    //
+    // If neither case applies to you, feel free to delete the declaration you
+    // don't need and to put everything under a single module.
+    const exe = b.addExecutable(.{
+        .name = "yareg",
+        .root_module = b.createModule(.{
+            // b.createModule defines a new module just like b.addModule but,
+            // unlike b.addModule, it does not expose the module to consumers of
+            // this package, which is why in this case we don't have to give it a name.
+            .root_source_file = b.path("src/main.zig"),
+            // Target and optimization levels must be explicitly wired in when
+            // defining an executable or library (in the root module), and you
+            // can also hardcode a specific target for an executable or library
+            // definition if desireable (e.g. firmware for embedded devices).
+            .target = target,
+            .optimize = optimize,
+            // List of modules available for import in source files part of the
+            // root module.
+            .imports = &.{
+                // Here "yareg" is the name you will use in your source code to
+                // import this module (e.g. `@import("yareg")`). The name is
+                // repeated because you are allowed to rename your imports, which
+                // can be extremely useful in case of collisions (which can happen
+                // importing modules from different packages).
+                .{ .name = "yareg", .module = mod },
+            },
+        }),
+    });
+
+    // This declares intent for the executable to be installed into the
+    // install prefix when running `zig build` (i.e. when executing the default
+    // step). By default the install prefix is `zig-out/` but can be overridden
+    // by passing `--prefix` or `-p`.
+    b.installArtifact(exe);
+
+    // This creates a top level step. Top level steps have a name and can be
+    // invoked by name when running `zig build` (e.g. `zig build run`).
+    // This will evaluate the `run` step rather than the default step.
+    // For a top level step to actually do something, it must depend on other
+    // steps (e.g. a Run step, as we will see in a moment).
+    const run_step = b.step("run", "Run the app");
+
+    // This creates a RunArtifact step in the build graph. A RunArtifact step
+    // invokes an executable compiled by Zig. Steps will only be executed by the
+    // runner if invoked directly by the user (in the case of top level steps)
+    // or if another step depends on it, so it's up to you to define when and
+    // how this Run step will be executed. In our case we want to run it when
+    // the user runs `zig build run`, so we create a dependency link.
+    const run_cmd = b.addRunArtifact(exe);
+    run_step.dependOn(&run_cmd.step);
+
+    // By making the run step depend on the default step, it will be run from the
+    // installation directory rather than directly from within the cache directory.
+    run_cmd.step.dependOn(b.getInstallStep());
+
+    // This allows the user to pass arguments to the application in the build
+    // command itself, like this: `zig build run -- arg1 arg2 etc`
+    if (b.args) |args| {
+        run_cmd.addArgs(args);
+    }
+
+    // Creates an executable that will run `test` blocks from the provided module.
+    // Here `mod` needs to define a target, which is why earlier we made sure to
+    // set the releative field.
+    const mod_tests = b.addTest(.{
+        .root_module = mod,
+    });
+
+    // A run step that will run the test executable.
+    const run_mod_tests = b.addRunArtifact(mod_tests);
+
+    // Creates an executable that will run `test` blocks from the executable's
+    // root module. Note that test executables only test one module at a time,
+    // hence why we have to create two separate ones.
+    const exe_tests = b.addTest(.{
+        .root_module = exe.root_module,
+    });
+
+    // A run step that will run the second test executable.
+    const run_exe_tests = b.addRunArtifact(exe_tests);
+
+    // A top level step for running all tests. dependOn can be called multiple
+    // times and since the two run steps do not depend on one another, this will
+    // make the two of them run in parallel.
+    const test_step = b.step("test", "Run tests");
+    test_step.dependOn(&run_mod_tests.step);
+    test_step.dependOn(&run_exe_tests.step);
+
+    // Just like flags, top level steps are also listed in the `--help` menu.
+    //
+    // The Zig build system is entirely implemented in userland, which means
+    // that it cannot hook into private compiler APIs. All compilation work
+    // orchestrated by the build system will result in other Zig compiler
+    // subcommands being invoked with the right flags defined. You can observe
+    // these invocations when one fails (or you pass a flag to increase
+    // verbosity) to validate assumptions and diagnose problems.
+    //
+    // Lastly, the Zig build system is relatively simple and self-contained,
+    // and reading its source code will allow you to master it.
+}
diff --git a/build.zig.zon b/build.zig.zon
new file mode 100644
index 0000000..c63041e
--- /dev/null
+++ b/build.zig.zon
@@ -0,0 +1,81 @@
+.{
+    // This is the default name used by packages depending on this one. For
+    // example, when a user runs `zig fetch --save <url>`, this field is used
+    // as the key in the `dependencies` table. Although the user can choose a
+    // different name, most users will stick with this provided value.
+    //
+    // It is redundant to include "zig" in this name because it is already
+    // within the Zig package namespace.
+    .name = .yareg,
+    // This is a [Semantic Version](https://semver.org/).
+    // In a future version of Zig it will be used for package deduplication.
+    .version = "0.0.0",
+    // Together with name, this represents a globally unique package
+    // identifier. This field is generated by the Zig toolchain when the
+    // package is first created, and then *never changes*. This allows
+    // unambiguous detection of one package being an updated version of
+    // another.
+    //
+    // When forking a Zig project, this id should be regenerated (delete the
+    // field and run `zig build`) if the upstream project is still maintained.
+    // Otherwise, the fork is *hostile*, attempting to take control over the
+    // original project's identity. Thus it is recommended to leave the comment
+    // on the following line intact, so that it shows up in code reviews that
+    // modify the field.
+    .fingerprint = 0x2d5332e2dba9f7aa, // Changing this has security and trust implications.
+    // Tracks the earliest Zig version that the package considers to be a
+    // supported use case.
+    .minimum_zig_version = "0.16.0",
+    // This field is optional.
+    // Each dependency must either provide a `url` and `hash`, or a `path`.
+    // `zig build --fetch` can be used to fetch all dependencies of a package, recursively.
+    // Once all dependencies are fetched, `zig build` no longer requires
+    // internet connectivity.
+    .dependencies = .{
+        // See `zig fetch --save <url>` for a command-line interface for adding dependencies.
+        //.example = .{
+        //    // When updating this field to a new URL, be sure to delete the corresponding
+        //    // `hash`, otherwise you are communicating that you expect to find the old hash at
+        //    // the new URL. If the contents of a URL change this will result in a hash mismatch
+        //    // which will prevent zig from using it.
+        //    .url = "https://example.com/foo.tar.gz",
+        //
+        //    // This is computed from the file contents of the directory of files that is
+        //    // obtained after fetching `url` and applying the inclusion rules given by
+        //    // `paths`.
+        //    //
+        //    // This field is the source of truth; packages do not come from a `url`; they
+        //    // come from a `hash`. `url` is just one of many possible mirrors for how to
+        //    // obtain a package matching this `hash`.
+        //    //
+        //    // Uses the [multihash](https://multiformats.io/multihash/) format.
+        //    .hash = "...",
+        //
+        //    // When this is provided, the package is found in a directory relative to the
+        //    // build root. In this case the package's hash is irrelevant and therefore not
+        //    // computed. This field and `url` are mutually exclusive.
+        //    .path = "foo",
+        //
+        //    // When this is set to `true`, a package is declared to be lazily
+        //    // fetched. This makes the dependency only get fetched if it is
+        //    // actually used.
+        //    .lazy = false,
+        //},
+    },
+    // Specifies the set of files and directories that are included in this package.
+    // Only files and directories listed here are included in the `hash` that
+    // is computed for this package. Only files listed here will remain on disk
+    // when using the zig package manager. As a rule of thumb, one should list
+    // files required for compilation plus any license(s).
+    // Paths are relative to the build root. Use the empty string (`""`) to refer to
+    // the build root itself.
+    // A directory listed here means that all files within, recursively, are included.
+    .paths = .{
+        "build.zig",
+        "build.zig.zon",
+        "src",
+        // For example...
+        //"LICENSE",
+        //"README.md",
+    },
+}
diff --git a/notes.md b/notes.md
new file mode 100644
index 0000000..73c5655
--- /dev/null
+++ b/notes.md
@@ -0,0 +1,5 @@
+Sources:
+
+https://en.wikipedia.org/wiki/Thompson%27s_construction
+https://rhaeguard.github.io/posts/regex/
+https://www.abstractsyntaxseed.com/blog/regex-engine/introduction
diff --git a/src/lib.zig b/src/lib.zig
new file mode 100644
index 0000000..7046186
--- /dev/null
+++ b/src/lib.zig
@@ -0,0 +1,29 @@
+const std = @import("std");
+
+pub const TokenGroupType = enum(u8) { group, namedGroup, nonCaptureGroup };
+pub const TokenGroupNamed = struct { name: []u8, group: TokenGroupBase };
+pub const TokenGroupNonCapturing = struct { group: TokenGroupBase };
+pub const TokenGroupBase = struct { value: u8 };
+pub const TokenGroup = union(TokenGroupType) { group: TokenGroupBase, namedGroup: TokenGroupNamed, nonCaptureGroup: TokenGroupNonCapturing };
+pub const TokenRange = struct { value: []u8 };
+pub const TokenUnion = struct { value: u8 };
+pub const TokenLiteral = struct { value: u8 };
+
+pub const TokenType = enum(u8) { group, literal, range, _union };
+pub const Token = union(TokenType) { group: TokenGroup, literal: TokenLiteral, range: TokenRange, _union: TokenUnion };
+
+pub const ParserCtx = struct {
+    const Self = @This();
+
+    _allocator: std.mem.Allocator,
+    pos: usize = 0,
+    tokens: std.MultiArrayList(Token),
+    pub fn init(allocator: std.mem.Allocator) !Self {
+        const ctx: ParserCtx = .{ ._allocator = allocator, .tokens = .empty };
+        return ctx;
+    }
+    pub fn deinit(self: *Self) void {
+        self.tokens.items()
+        self.tokens.deinit(self._allocator);
+    }
+};
diff --git a/src/main.zig b/src/main.zig
new file mode 100644
index 0000000..0d67966
--- /dev/null
+++ b/src/main.zig
@@ -0,0 +1,71 @@
+const std = @import("std");
+const Io = std.Io;
+
+const yareg = @import("yareg");
+
+pub fn main(init: std.process.Init) !void {
+    // Prints to stderr, unbuffered, ignoring potential errors.
+    std.debug.print("All your {s} are belong to us.\n", .{"codebase"});
+
+    // This is appropriate for anything that lives as long as the process.
+    const arena: std.mem.Allocator = init.arena.allocator();
+
+    // Accessing command line arguments:
+    const args = try init.minimal.args.toSlice(arena);
+    for (args) |arg| {
+        std.log.info("arg: {s}", .{arg});
+    }
+
+    // In order to do I/O operations need an `Io` instance.
+    const io = init.io;
+
+    // Stdout is for the actual output of your application, for example if you
+    // are implementing gzip, then only the compressed bytes should be sent to
+    // stdout, not any debugging messages.
+    var stdout_buffer: [1024]u8 = undefined;
+    var stdout_file_writer: Io.File.Writer = .init(.stdout(), io, &stdout_buffer);
+    const stdout_writer = &stdout_file_writer.interface;
+
+    try yareg.printAnotherMessage(stdout_writer);
+
+    try stdout_writer.flush(); // Don't forget to flush!
+}
+
+test "simple test" {
+    const gpa = std.testing.allocator;
+    var list: std.ArrayList(i32) = .empty;
+    defer list.deinit(gpa); // Try commenting this out and see if zig detects the memory leak!
+    try list.append(gpa, 42);
+    try std.testing.expectEqual(@as(i32, 42), list.pop());
+}
+
+test "fuzz example" {
+    try std.testing.fuzz({}, testOne, .{});
+}
+
+fn testOne(context: void, smith: *std.testing.Smith) !void {
+    _ = context;
+    // Try passing `--fuzz` to `zig build test` and see if it manages to fail this test case!
+
+    const gpa = std.testing.allocator;
+    var list: std.ArrayList(u8) = .empty;
+    defer list.deinit(gpa);
+    while (!smith.eos()) switch (smith.value(enum { add_data, dup_data })) {
+        .add_data => {
+            const slice = try list.addManyAsSlice(gpa, smith.value(u4));
+            smith.bytes(slice);
+        },
+        .dup_data => {
+            if (list.items.len == 0) continue;
+            if (list.items.len > std.math.maxInt(u32)) return error.SkipZigTest;
+            const len = smith.valueRangeAtMost(u32, 1, @min(32, list.items.len));
+            const off = smith.valueRangeAtMost(u32, 0, @intCast(list.items.len - len));
+            try list.appendSlice(gpa, list.items[off..][0..len]);
+            try std.testing.expectEqualSlices(
+                u8,
+                list.items[off..][0..len],
+                list.items[list.items.len - len ..],
+            );
+        },
+    };
+}
diff --git a/src/parser.zig b/src/parser.zig
new file mode 100644
index 0000000..c8336e8
--- /dev/null
+++ b/src/parser.zig
@@ -0,0 +1,97 @@
+const std = @import("std");
+const lib = @import("lib.zig");
+
+fn parse_range(regex_str: []const u8, ctx: *lib.ParserCtx) !void {
+    const starting_pos = ctx.pos;
+    std.debug.print("parsing range from '{s}'\n", .{regex_str[starting_pos..]});
+    ctx.pos += 1;
+
+    var litterals: std.ArrayList(u8) = .empty;
+    defer litterals.deinit(ctx._allocator);
+    var ranges: std.ArrayList([2]u8) = .empty;
+    defer ranges.deinit(ctx._allocator);
+
+    var last_ch: ?u8 = null;
+    while (regex_str[ctx.pos] != ']') {
+        const ch = regex_str[ctx.pos];
+
+        if (ch == '-' and last_ch != null and ctx.pos + 1 < regex_str.len) {
+            const next_ch = regex_str[ctx.pos + 1];
+            std.debug.print("found range ? {c} to {c}\n", .{ last_ch.?, next_ch });
+            try ranges.append(ctx._allocator, .{ last_ch.?, next_ch });
+            _ = litterals.pop();
+            ctx.pos += 1;
+            last_ch = null; // character in range cannot be reused
+        } else {
+            try litterals.append(ctx._allocator, ch);
+            last_ch = ch;
+        }
+        ctx.pos += 1;
+
+        if (ctx.pos >= regex_str.len) {
+            std.debug.print("Unclosed '[' pos {d} in '{s}'\n", .{ starting_pos, regex_str[starting_pos..] });
+            return error.UnclosedBracket;
+        }
+    }
+
+    std.debug.print("range literrals: {s}\n", .{litterals.items});
+    std.debug.print("ranges: {any}\n", .{ranges.items});
+
+    var litteralSet: std.ArrayList(u8) = .empty;
+    defer litteralSet.deinit(ctx._allocator);
+    for (ranges.items) |item| {
+        const start = item[0];
+        const end: u8 = item[1];
+        if (end <= start) {
+            std.debug.print("Invalid range {c}-{c}\n", .{ start, end });
+            return error.InvalidRange;
+        }
+        for (start..end) |c| {
+            for (litteralSet.items) |set_item| {
+                if (c == set_item) {
+                    break;
+                }
+            } else {
+                try litteralSet.append(ctx._allocator, @intCast(c));
+            }
+        }
+    }
+    for (litterals.items) |c| {
+        for (litteralSet.items) |set_item| {
+            if (c == set_item) {
+                break;
+            }
+        } else {
+            try litteralSet.append(ctx._allocator, @intCast(c));
+        }
+    }
+
+    std.debug.print("range covers: {s}\n", .{litteralSet.items});
+    try ctx.tokens.append(ctx._allocator, .{ .range = .{ .value = try ctx._allocator.dupe(u8, litteralSet.items) } });
+}
+fn parse_regex(regex_str: []const u8, ctx: *lib.ParserCtx) !void {
+    const ch: u8 = regex_str[ctx.pos];
+    switch (ch) {
+        '(' => {},
+        '[' => {
+            try parse_range(regex_str, ctx);
+        },
+        '*' | '?' | '+' => {},
+        '{' => {},
+        else => {
+            // TODO: Handle special chars and escaped chars
+            try ctx.tokens.append(ctx._allocator, .{ .literal = .{ .value = ch } });
+        },
+    }
+}
+
+test "parser regex basic" {
+    const alloc = std.testing.allocator;
+    const regex_to_parse = "[a-zA-Z0-9_]+@[a-zA-Z0-9_]+\\.[a-zA-Z]{2,}";
+    std.debug.print("Trying to parse '{s}'\n", .{regex_to_parse});
+    var ctx = try lib.ParserCtx.init(alloc);
+    defer ctx.deinit();
+    try parse_regex(regex_to_parse, &ctx);
+
+    std.debug.print("tokens: {any}", .{ctx.tokens.pop()});
+}
diff --git a/src/root.zig b/src/root.zig
new file mode 100644
index 0000000..fb437a5
--- /dev/null
+++ b/src/root.zig
@@ -0,0 +1,7 @@
+const std = @import("std");
+const parser = @import("parser.zig");
+
+test {
+    std.testing.refAllDecls(@This());
+    std.testing.refAllDecls(parser);
+}