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/README.md b/README.md new file mode 100644 index 0000000..e69de29 diff --git a/build.zig b/build.zig new file mode 100644 index 0000000..af96aa6 --- /dev/null +++ b/build.zig @@ -0,0 +1,285 @@ +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. + + // We need to use curl for this as the domain doesn't work with zig TLS + const model_step = DownloadStep("https://www.link.cs.cmu.edu/link/ftp-site/link-grammar/link-4.1b/unix/link-4.1b.tar.gz").create(b); + + // 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("pos", .{ + // 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 + // 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 = "pos", + .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 "pos" is the name you will use in your source code to + // import this module (e.g. `@import("pos")`). 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 = "pos", .module = mod }, + }, + }), + }); + + exe.step.dependOn(&model_step.step); + // 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, + }); + exe.step.dependOn(&model_step.step); + + // 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. +} + +fn DownloadStep(comptime link: []const u8) type { + return struct { + step: std.Build.Step, + builder: *std.Build, + + const download_link = link; + const download_uri = std.Uri.parse(link) catch @compileError("download link is not a valid Uri"); + const file_type: enum { + targz, + zip, + } = if (std.mem.endsWith(u8, link, ".tar.gz")) .targz else if (std.mem.endsWith(u8, link, "zip")) .zip else @compileError("can only download tar.gz or zip files"); + + const Self = @This(); + + fn fileName(uri: std.Uri) []const u8 { + const path = switch (uri.path) { + .raw => |r| r, + .percent_encoded => |p| p, + }; + var it = std.mem.splitBackwardsScalar(u8, path, '/'); + return it.first(); + } + + fn fileNameNoExtension() []const u8 { + const file_name = fileName(download_uri); + return switch (file_type) { + .targz => file_name[0..std.mem.lastIndexOf(u8, file_name, ".tar.gz").?], + .zip => file_name[0..std.mem.lastIndexOf(u8, file_name, ".zip").?], + }; + } + + pub fn create(builder: *std.Build) *Self { + const self = builder.allocator.create(Self) catch @panic("OOM"); + self.* = .{ + .step = std.Build.Step.init(.{ + .id = .custom, + .name = "download-model", + .owner = builder, + .makeFn = make, + }), + .builder = builder, + }; + return self; + } + + pub fn getOutputPath(self: *Self) std.Build.LazyPath { + var hasher = std.hash.Wyhash.init(0); + hasher.update(download_link); + const cache_hash = hasher.final(); + + var cache_dir_buf: [std.fs.max_path_bytes]u8 = undefined; + const cache_dir = std.fmt.bufPrint(&cache_dir_buf, "{s}/o/{x}/{s}", .{ self.builder.cache_root.path.?, cache_hash, fileNameNoExtension() }) catch @panic("path too long"); + + return .{ .cwd_relative = self.builder.allocator.dupe(u8, cache_dir) catch @panic("OOM") }; + } + + fn make(step: *std.Build.Step, options: std.Build.Step.MakeOptions) anyerror!void { + _ = options; + const self: *Self = @fieldParentPtr("step", step); + + const model_dir = fileNameNoExtension(); + + // Create a cache hash based on the URL + var hasher = std.hash.Wyhash.init(0); + hasher.update(link); + const cache_hash = hasher.final(); + + var cache_dir_buf: [std.fs.max_path_bytes]u8 = undefined; + const cache_dir = std.fmt.bufPrint(&cache_dir_buf, "{s}/o/{x}", .{ self.builder.cache_root.path.?, cache_hash }) catch @panic("path too long"); + + const cached_model_dir = std.fmt.allocPrint( + self.builder.allocator, + "{s}/{s}", + .{ cache_dir, model_dir }, + ) catch @panic("OOM"); + defer self.builder.allocator.free(cached_model_dir); + + // Check if already cached + if (std.fs.cwd().access(cached_model_dir, .{})) |_| { + step.result_cached = true; + return; + } else |_| {} + + // Not cached, need to download + std.fs.cwd().makePath(cache_dir) catch @panic("Could not create cache directory"); + + const archive = std.fmt.allocPrint( + self.builder.allocator, + "{s}/{s}", + .{ cache_dir, fileName(download_uri) }, + ) catch @panic("OOM"); + defer self.builder.allocator.free(archive); + + // Download + const download_result = std.process.Child.run(.{ + .allocator = self.builder.allocator, + .argv = &.{ "curl", "-s", "-o", archive, link }, + }) catch return error.DownloadFailed; + if (download_result.term.Exited != 0) return error.DownloadFailed; + + switch (file_type) { + .zip => { + // Extract to cache using stdlib + var zip_file = std.fs.cwd().openFile(archive, .{}) catch return error.UnzipFailed; + defer zip_file.close(); + + var cache_dir_handle = std.fs.cwd().openDir(cache_dir, .{}) catch return error.UnzipFailed; + defer cache_dir_handle.close(); + + var zip_file_buffer: [4096]u8 = undefined; + var zip_file_reader = zip_file.reader(&zip_file_buffer); + + std.zip.extract(cache_dir_handle, &zip_file_reader, .{}) catch return error.UnzipFailed; + + step.result_cached = false; + }, + .targz => { + @compileError("tar.gz extraction not yet implemented"); + }, + } + } + }; +} diff --git a/build.zig.zon b/build.zig.zon new file mode 100644 index 0000000..29fa25a --- /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 `, 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 = .pos, + // 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 = 0x80d9e6acc1db9e17, // 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 = "0.15.1", + // 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 ` 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/src/main.zig b/src/main.zig new file mode 100644 index 0000000..465ad99 --- /dev/null +++ b/src/main.zig @@ -0,0 +1,27 @@ +const std = @import("std"); +const pos = @import("pos"); + +pub fn main() !void { + // Prints to stderr, ignoring potential errors. + std.debug.print("All your {s} are belong to us.\n", .{"codebase"}); + try pos.bufferedPrint(); +} + +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" { + const Context = struct { + fn testOne(context: @This(), input: []const u8) anyerror!void { + _ = context; + // Try passing `--fuzz` to `zig build test` and see if it manages to fail this test case! + try std.testing.expect(!std.mem.eql(u8, "canyoufindme", input)); + } + }; + try std.testing.fuzz(Context{}, Context.testOne, .{}); +} diff --git a/src/root.zig b/src/root.zig new file mode 100644 index 0000000..94c7cd0 --- /dev/null +++ b/src/root.zig @@ -0,0 +1,23 @@ +//! By convention, root.zig is the root source file when making a library. +const std = @import("std"); + +pub fn bufferedPrint() !void { + // 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_writer = std.fs.File.stdout().writer(&stdout_buffer); + const stdout = &stdout_writer.interface; + + try stdout.print("Run `zig build test` to run the tests.\n", .{}); + + try stdout.flush(); // Don't forget to flush! +} + +pub fn add(a: i32, b: i32) i32 { + return a + b; +} + +test "basic add functionality" { + try std.testing.expect(add(3, 7) == 10); +}