From 46e1a1e2ce2807440e78c338e17d0ee5d6e2abe3 Mon Sep 17 00:00:00 2001
From: Lorenzo Torres <lorenzo@sagittarius-a.org>
Date: Tue, 16 Dec 2025 14:21:41 +0100
Subject: [PATCH] first commit

---
 .gitignore     |   2 +
 build.zig      | 156 +++++++++++++++++++++++++++++++++++++++++++++
 build.zig.zon  |  81 +++++++++++++++++++++++
 graph          |   5 ++
 src/Lexer.zig  | 132 ++++++++++++++++++++++++++++++++++++++
 src/Parser.zig | 170 +++++++++++++++++++++++++++++++++++++++++++++++++
 src/main.zig   |  42 ++++++++++++
 src/root.zig   |   2 +
 8 files changed, 590 insertions(+)
 create mode 100644 .gitignore
 create mode 100644 build.zig
 create mode 100644 build.zig.zon
 create mode 100755 graph
 create mode 100644 src/Lexer.zig
 create mode 100644 src/Parser.zig
 create mode 100644 src/main.zig
 create mode 100644 src/root.zig

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..dca1103
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,2 @@
+zig-out/
+.zig-cache/
diff --git a/build.zig b/build.zig
new file mode 100644
index 0000000..53ebf25
--- /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("al", .{
+        // 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 = "al",
+        .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 "al" is the name you will use in your source code to
+                // import this module (e.g. `@import("al")`). 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 = "al", .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..1eada01
--- /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 = .al,
+    // 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 = 0x793b656ad110237c, // 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 = "0.15.2",
+    // 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/graph b/graph
new file mode 100755
index 0000000..5434453
--- /dev/null
+++ b/graph
@@ -0,0 +1,5 @@
+#!/bin/bash
+
+zig build run 2>&1 >/dev/null | dot -Tpdf -o graph.pdf
+zathura graph.pdf
+rm graph.pdf
diff --git a/src/Lexer.zig b/src/Lexer.zig
new file mode 100644
index 0000000..6e7e8aa
--- /dev/null
+++ b/src/Lexer.zig
@@ -0,0 +1,132 @@
+const std = @import("std");
+const Lexer = @This();
+
+index: usize,
+source: []u8,
+start: usize,
+
+pub const TokenType = enum {
+    plus,
+    minus,
+    star,
+    slash,
+    integer,
+    float,
+    identifier,
+
+    eof,
+    illegal,
+};
+
+pub const Token = struct {
+    @"type": TokenType,
+    lexeme: []u8,
+};
+
+pub fn parseSpecial(lexer: *Lexer) Token {
+    var token_type: TokenType = .eof;
+    switch (lexer.source[lexer.index]) {
+        '+' => token_type = .plus,
+        '-' => token_type = .minus,
+        '*' => token_type = .star,
+        '/' => token_type = .slash,
+        else => token_type = .eof,
+    }
+
+    lexer.index += 1;
+
+    return .{
+        .@"type" = token_type,
+        .lexeme = undefined,
+    };
+}
+
+pub fn next(lexer: *Lexer) Token {
+    lexer.skipWhitespaceAndComments();
+
+    if (lexer.index >= lexer.source.len) {
+        return lexer.makeToken(.eof);
+    }
+
+    const c = lexer.source[lexer.index];
+    
+    // Numbers
+    if (std.ascii.isDigit(c)) {
+        return lexer.number();
+    }
+
+    // Identifiers
+    if (std.ascii.isAlphabetic(c)) {
+    }
+
+    // Single Character Tokens
+    lexer.index += 1;
+    switch (c) {
+        '+' => return lexer.makeToken(.plus),
+        '-' => return lexer.makeToken(.minus),
+        '*' => return lexer.makeToken(.star),
+        '/' => return lexer.makeToken(.slash),
+        else => return lexer.makeToken(.illegal),
+    }
+}
+
+fn makeToken(lexer: *Lexer, @"type": TokenType) Token {
+    return .{
+        .@"type" = @"type",
+        // Safely slice the source
+        .lexeme = if (lexer.index <= lexer.source.len) 
+                     lexer.source[lexer.start..lexer.index] 
+                  else 
+                     "",
+    };
+}
+
+fn skipWhitespaceAndComments(lexer: *Lexer) void {
+    while (lexer.index < lexer.source.len) {
+        const c = lexer.source[lexer.index];
+        switch (c) {
+            // Whitespace
+            ' ', '\t', '\r', '\n' => {
+                lexer.index += 1;
+            },
+            // Comments
+            '#' => {
+                while (lexer.index < lexer.source.len and lexer.source[lexer.index] != '\n') {
+                    lexer.index += 1;
+                }
+            },
+            else => {
+                lexer.start = lexer.index;
+                return;
+            }
+        }
+    }
+}
+
+fn number(lexer: *Lexer) Token {
+    while (lexer.index < lexer.source.len and std.ascii.isDigit(lexer.source[lexer.index])) {
+        lexer.index += 1;
+    }
+
+    if (lexer.index < lexer.source.len and lexer.source[lexer.index] == '.') {
+        if (lexer.index + 1 < lexer.source.len and std.ascii.isDigit(lexer.source[lexer.index + 1])) {
+            lexer.index += 1; // consume dot
+            while (lexer.index < lexer.source.len and std.ascii.isDigit(lexer.source[lexer.index])) {
+                lexer.index += 1;
+            }
+            return lexer.makeToken(.float);
+        }
+    }
+
+    return lexer.makeToken(.integer);
+}
+
+/// If `source` was allocated on the heap,
+/// the caller must free it.
+pub fn init(source: []u8) Lexer {
+    return .{
+        .index = 0,
+        .source = source,
+        .start = 0,
+    };
+}
diff --git a/src/Parser.zig b/src/Parser.zig
new file mode 100644
index 0000000..75bd9bd
--- /dev/null
+++ b/src/Parser.zig
@@ -0,0 +1,170 @@
+const std = @import("std");
+const Lexer = @import("Lexer.zig");
+const Parser = @This();
+
+lexer: *Lexer,
+allocator: std.mem.Allocator,
+node_table: std.AutoHashMap(u64, *Node),
+previous: Lexer.Token,
+current: Lexer.Token,
+
+pub const NodeType = enum {
+    add,
+    sub,
+    mul,
+    div,
+
+    integer,
+    float,
+
+    start,
+    @"return",
+};
+
+pub const Node = struct {
+    @"type": NodeType,
+    id: u64,
+    inputs: std.ArrayList(*Node),
+    outputs: std.ArrayList(*Node),
+    data: extern union {
+        integer: u64,
+        float: f64,
+    },
+
+    pub fn init(parser: *Parser, @"type": NodeType) !*Node {
+        var node = try parser.allocator.create(Node);
+        node.@"type" = @"type";
+        node.inputs = .{};
+        node.outputs = .{};
+        node.data = undefined;
+        return node;
+    }
+
+    pub fn globalNumbering(node: *Node, parser: *Parser) !*Node {
+        const node_hash = node.hash();
+        node.id = node_hash;
+        if (parser.node_table.get(node_hash)) |n| {
+            parser.allocator.destroy(node);
+            return n;
+        }
+
+        try parser.node_table.put(node_hash, node);
+
+        return node;
+    }
+
+    pub fn hash(node: *Node) u64 {
+        var hasher = std.hash.Wyhash.init(0);
+        std.hash.autoHash(&hasher, node.@"type");
+
+        switch (node.@"type") {
+            .integer => std.hash.autoHash(&hasher, node.data.integer),
+            .float => std.hash.autoHash(&hasher, @as(u64, @bitCast(node.data.float))),
+            else => {},
+        }
+
+        for (node.inputs.items) |n| {
+            std.hash.autoHash(&hasher, @intFromPtr(n));
+        }
+
+        return hasher.final();
+    }
+
+    pub fn deinit(node: *Node, parser: *Parser) void {
+        parser.allocator.destroy(node);
+    }
+};
+
+pub fn match(parser: *Parser, expected: Lexer.TokenType) bool {
+    if (parser.current.@"type" == expected) {
+        parser.advance(); 
+        return true;
+    }
+    return false;
+}
+
+pub fn advance(parser: *Parser) void {
+    parser.previous = parser.current;
+    parser.current = parser.lexer.next();
+}
+
+pub fn buildFactor(parser: *Parser) !?*Node {
+    const token = parser.current;
+    switch (token.@"type") {
+        .integer => {
+            parser.advance();
+            const node = try Node.init(parser, .integer);
+            node.data.integer = std.fmt.parseInt(u64, token.lexeme, 10) catch 0;
+            return node.globalNumbering(parser);
+        },
+        .float => {
+            parser.advance();
+            const node = try Node.init(parser, .float);
+            node.data.float = std.fmt.parseFloat(f64, token.lexeme) catch 0;
+            return node.globalNumbering(parser);
+        },
+        else => {}
+    }
+
+    return null;
+}
+
+pub fn buildTerm(parser: *Parser) !?*Node {
+    var lhs = try parser.buildFactor();
+
+    while (parser.match(.star) or parser.match(.slash)) {
+        const node_type: NodeType = switch (parser.previous.@"type") {
+            .star => .mul,
+            .slash => .div,
+            else => unreachable,
+        };
+        var node = try Node.init(parser, node_type);
+        try node.inputs.append(parser.allocator, (try parser.buildFactor()).?);
+        try node.inputs.append(parser.allocator, lhs.?);
+        node = try node.globalNumbering(parser);
+        lhs = node;
+    }
+
+    return lhs;
+}
+
+pub fn buildExpression(parser: *Parser) !?*Node {
+    var lhs = try parser.buildTerm();
+
+    while (parser.match(.plus) or parser.match(.minus)) {
+        const node_type: NodeType = switch (parser.previous.@"type") {
+            .plus => .add,
+            .minus => .sub,
+            else => unreachable,
+        };
+        var node = try Node.init(parser, node_type);
+        try node.inputs.append(parser.allocator, (try parser.buildTerm()).?);
+        try node.inputs.append(parser.allocator, lhs.?);
+        node = try node.globalNumbering(parser);
+        lhs = node;
+    }
+
+    return lhs;
+}
+
+pub fn buildGraph(parser: *Parser) !?*Node {
+    return try buildExpression(parser);
+}
+
+pub fn init(allocator: std.mem.Allocator, lexer: *Lexer) Parser {
+    var parser: Parser = .{
+        .lexer = lexer,
+        .allocator = allocator,
+        .node_table = std.AutoHashMap(u64, *Node).init(allocator),
+        .previous = undefined,
+        .current = undefined,
+    };
+
+    parser.advance();
+
+    return parser;
+}
+
+pub fn deinit(parser: *Parser) void {
+    parser.node_table.deinit();
+}
diff --git a/src/main.zig b/src/main.zig
new file mode 100644
index 0000000..8c5faad
--- /dev/null
+++ b/src/main.zig
@@ -0,0 +1,42 @@
+const std = @import("std");
+const al = @import("al");
+
+pub fn nodeName(node: *al.Parser.Node) void {
+    switch (node.@"type") {
+        .start => std.debug.print("{d} [label=\"start\",fillcolor=yellow, color=black, shape=box]", .{node.id}),
+        .add => std.debug.print("{d} [label=\"+\"]", .{node.id}),
+        .sub => std.debug.print("{d} [label=\"-\"]", .{node.id}),
+        .mul => std.debug.print("{d} [label=\"*\"]", .{node.id}),
+        .div => std.debug.print("{d} [label=\"/\"]", .{node.id}),
+        .integer => std.debug.print("{d} [label=\"{d}\"]", .{node.id, node.data.integer}),
+        .float => std.debug.print("{d} [label=\"{d}\"]", .{node.id, node.data.float}),
+        else => {},
+    }
+    std.debug.print("\n", .{});
+}
+
+pub fn printGraph(node: *al.Parser.Node) void {
+    for (node.inputs.items) |n| {
+        nodeName(n);
+        std.debug.print("{d}->{d}\n", .{node.id, n.id});
+        printGraph(n);
+    }
+}
+
+pub fn main() !void {
+    var gpa = std.heap.DebugAllocator(.{}).init;
+    defer {
+        //_ = gpa.detectLeaks();
+    }
+    const allocator = gpa.allocator();
+
+    var lexer = al.Lexer.init(@constCast("3*2+2.2"));
+    var parser = al.Parser.init(allocator, &lexer);
+    defer parser.deinit();
+    const graph = try parser.buildGraph();
+    defer graph.?.deinit(&parser);
+    std.debug.print("digraph G {{\n", .{});
+    nodeName(graph.?);
+    printGraph(graph.?);
+    std.debug.print("}}\n", .{});
+}
diff --git a/src/root.zig b/src/root.zig
new file mode 100644
index 0000000..2a6ebfc
--- /dev/null
+++ b/src/root.zig
@@ -0,0 +1,2 @@
+pub const Lexer = @import("Lexer.zig");
+pub const Parser = @import("Parser.zig");