Initial commit

6 files changed, 239 insertions, 0 deletions

diff --git a/.gitignore b/.gitignore
new file mode 100644
index 0000000..9ae02d6
--- /dev/null
+++ b/.gitignore
@@ -0,0 +1,3 @@
+out/
+zig-out/
+zig-cache/
diff --git a/build.zig b/build.zig
new file mode 100644
index 0000000..f04131f
--- /dev/null
+++ b/build.zig
@@ -0,0 +1,38 @@
+const std = @import("std");
+
+pub fn build(b: *std.Build) void {
+    const target = b.standardTargetOptions(.{});
+
+    const optimize = b.standardOptimizeOption(.{});
+
+    const exe = b.addExecutable(.{
+        .name = "compiler",
+        .root_source_file = b.path("src/main.zig"),
+        .target = target,
+        .optimize = optimize,
+    });
+
+    b.installArtifact(exe);
+
+    const run_cmd = b.addRunArtifact(exe);
+
+    run_cmd.step.dependOn(b.getInstallStep());
+
+    if (b.args) |args| {
+        run_cmd.addArgs(args);
+    }
+
+    const run_step = b.step("run", "Run the app");
+    run_step.dependOn(&run_cmd.step);
+
+    const exe_unit_tests = b.addTest(.{
+        .root_source_file = b.path("src/main.zig"),
+        .target = target,
+        .optimize = optimize,
+    });
+
+    const run_exe_unit_tests = b.addRunArtifact(exe_unit_tests);
+
+    const test_step = b.step("test", "Run unit tests");
+    test_step.dependOn(&run_exe_unit_tests.step);
+}
diff --git a/build.zig.zon b/build.zig.zon
new file mode 100644
index 0000000..39f7607
--- /dev/null
+++ b/build.zig.zon
@@ -0,0 +1,67 @@
+.{
+    .name = "compiler",
+    // 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",
+
+    // This field is optional.
+    // This is currently advisory only; Zig does not yet do anything
+    // with this value.
+    //.minimum_zig_version = "0.11.0",
+
+    // 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.
+        //    .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.
+    // 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 = .{
+        // This makes *all* files, recursively, included in this package. It is generally
+        // better to explicitly list the files and directories instead, to insure that
+        // fetching from tarballs, file system paths, and version control all result
+        // in the same contents hash.
+        "",
+        // For example...
+        //"build.zig",
+        //"build.zig.zon",
+        //"src",
+        //"LICENSE",
+        //"README.md",
+    },
+}
diff --git a/examples/test1.gft b/examples/test1.gft
new file mode 100644
index 0000000..16f566f
--- /dev/null
+++ b/examples/test1.gft
@@ -0,0 +1 @@
+return 69;
diff --git a/src/main.zig b/src/main.zig
new file mode 100644
index 0000000..18239b1
--- /dev/null
+++ b/src/main.zig
@@ -0,0 +1,64 @@
+const std = @import("std");
+const tok = @import("tokenize.zig");
+
+const gftCompilerError = error{NoInputFile};
+
+pub fn main() !void {
+    if (std.os.argv.len != 2) return gftCompilerError.NoInputFile;
+    var gpa = std.heap.GeneralPurposeAllocator(.{}){};
+    defer _ = gpa.deinit();
+    var args = std.process.args();
+    _ = args.skip();
+    const inputFileName = args.next();
+    const inputFile = try std.fs.cwd().openFile(inputFileName.?, .{});
+    defer inputFile.close();
+
+    std.fs.cwd().makeDir("out") catch |err| {
+        if (err != error.PathAlreadyExists) return err;
+    };
+    const outfile = try std.fs.cwd().createFile("out/out.asm", .{});
+    const outWriter = outfile.writer();
+    defer outfile.close();
+
+    // Logic here to compile language
+    const all = try inputFile.readToEndAlloc(gpa.allocator(), 2048);
+    defer gpa.allocator().free(all);
+
+    const toks = try tok.tokenize(gpa.allocator(), all);
+    defer gpa.allocator().free(toks);
+    var tokIter = tok.TokenIterator{ .tokens = toks };
+    try outWriter.print("global _start:\n", .{});
+    while (tokIter.next()) |t| {
+        switch (t) {
+            .ret => {
+                const num = tokIter.next();
+                switch (num.?) {
+                    .intLit => {},
+                    else => break,
+                }
+                switch (tokIter.next().?) {
+                    .semiCol => {},
+                    else => break,
+                }
+                try outWriter.print(
+                    \\  mov rax, 60
+                    \\  mov rdi, {}
+                    \\  syscall
+                    \\
+                , .{num.?.intLit});
+                gpa.allocator().free(t.ret);
+            },
+            else => {},
+        }
+    }
+
+    const nasmargv = [_][]const u8{ "nasm", "-felf64", "out/out.asm" };
+    const nasmproc = try std.ChildProcess.run(.{ .argv = &nasmargv, .allocator = gpa.allocator() });
+    defer gpa.allocator().free(nasmproc.stdout);
+    defer gpa.allocator().free(nasmproc.stderr);
+
+    const ldargv = [_][]const u8{ "ld", "-o", "out/out", "out/out.o" };
+    const ldproc = try std.ChildProcess.run(.{ .argv = &ldargv, .allocator = gpa.allocator() });
+    defer gpa.allocator().free(ldproc.stdout);
+    defer gpa.allocator().free(ldproc.stderr);
+}
diff --git a/src/tokenize.zig b/src/tokenize.zig
new file mode 100644
index 0000000..b5d5d23
--- /dev/null
+++ b/src/tokenize.zig
@@ -0,0 +1,66 @@
+const std = @import("std");
+
+const TokenError = error{UnknownToken};
+
+const Token = union(enum) {
+    ret: []const u8,
+    intLit: i32,
+    semiCol: u8,
+    nil: void,
+};
+
+pub const TokenIterator = struct {
+    tokens: []const Token,
+    index: usize = 0,
+
+    pub fn next(self: *TokenIterator) ?Token {
+        defer self.*.index = self.*.index + 1;
+        if (self.*.index >= self.*.tokens.len) return null;
+        return self.*.tokens[self.*.index];
+    }
+};
+
+pub fn tokenize(allocator: std.mem.Allocator, buff: []const u8) ![]const Token {
+    var toks = std.ArrayList(Token).init(allocator);
+    defer toks.deinit();
+    var str = std.ArrayList(u8).init(allocator);
+    defer str.deinit();
+
+    var i: u32 = 0;
+    while (i < buff.len) {
+        switch (buff[i]) {
+            ' ', '\n', '\t' => {
+                i = i + 1;
+                continue;
+            },
+            '0'...'9' => {
+                while (std.ascii.isDigit(buff[i])) {
+                    try str.append(buff[i]);
+                    i = i + 1;
+                }
+                const num: i32 = try std.fmt.parseInt(i32, str.items, 10);
+                try toks.append(.{ .intLit = num });
+                str.deinit();
+                str = std.ArrayList(u8).init(allocator);
+            },
+            'a'...'z', 'A'...'Z' => {
+                while (std.ascii.isAlphanumeric(buff[i])) {
+                    try str.append(buff[i]);
+                    i = i + 1;
+                }
+                try toks.append(.{ .ret = try str.toOwnedSlice() });
+                str.deinit();
+                str = std.ArrayList(u8).init(allocator);
+            },
+            ';' => {
+                i = i + 1;
+                try toks.append(.{ .semiCol = ';' });
+            },
+            '+', '-', '*', '/' => {
+                // Process operator
+            },
+            else => {},
+        }
+    }
+    return toks.toOwnedSlice();
+}