Files
bun.sh/src/interchange/toml.zig
pfg 05d0475c6c Update to zig 0.15.2 (#24204)
Fixes ENG-21287

Build times, from `bun run build && echo '//' >> src/main.zig && time
bun run build`

|Platform|0.14.1|0.15.2|Speedup|
|-|-|-|-|
|macos debug asan|126.90s|106.27s|1.19x|
|macos debug noasan|60.62s|50.85s|1.19x|
|linux debug asan|292.77s|241.45s|1.21x|
|linux debug noasan|146.58s|130.94s|1.12x|
|linux debug use_llvm=false|n/a|78.27s|1.87x|
|windows debug asan|177.13s|142.55s|1.24x|

Runtime performance:

- next build memory usage may have gone up by 5%. Otherwise seems the
same. Some code with writers may have gotten slower, especially one
instance of a counting writer and a few instances of unbuffered writers
that now have vtable overhead.
- File size reduced by 800kb (from 100.2mb to 99.4mb)

Improvements:

- `@export` hack is no longer needed for watch
- native x86_64 backend for linux builds faster. to use it, set use_llvm
false and no_link_obj false. also set `ASAN_OPTIONS=detect_leaks=0`
otherwise it will spam the output with tens of thousands of lines of
debug info errors. may need to use the zig lldb fork for debugging.
- zig test-obj, which we will be able to use for zig unit tests

Still an issue:

- false 'dependency loop' errors remain in watch mode
- watch mode crashes observed

Follow-up:

- [ ] search `comptime Writer: type` and `comptime W: type` and remove
- [ ] remove format_mode in our zig fork
- [ ] remove deprecated.zig autoFormatLabelFallback
- [ ] remove deprecated.zig autoFormatLabel
- [ ] remove deprecated.BufferedWriter and BufferedReader
- [ ] remove override_no_export_cpp_apis as it is no longer needed
- [ ] css Parser(W) -> Parser, and remove all the comptime writer: type
params
- [ ] remove deprecated writer fully

Files that add lines:

```
649     src/deprecated.zig
167     scripts/pack-codegen-for-zig-team.ts
54      scripts/cleartrace-impl.js
46      scripts/cleartrace.ts
43      src/windows.zig
18      src/fs.zig
17      src/bun.js/ConsoleObject.zig
16      src/output.zig
12      src/bun.js/test/debug.zig
12      src/bun.js/node/node_fs.zig
8       src/env_loader.zig
7       src/css/printer.zig
7       src/cli/init_command.zig
7       src/bun.js/node.zig
6       src/string/escapeRegExp.zig
6       src/install/PnpmMatcher.zig
5       src/bun.js/webcore/Blob.zig
4       src/crash_handler.zig
4       src/bun.zig
3       src/install/lockfile/bun.lock.zig
3       src/cli/update_interactive_command.zig
3       src/cli/pack_command.zig
3       build.zig
2       src/Progress.zig
2       src/install/lockfile/lockfile_json_stringify_for_debugging.zig
2       src/css/small_list.zig
2       src/bun.js/webcore/prompt.zig
1       test/internal/ban-words.test.ts
1       test/internal/ban-limits.json
1       src/watcher/WatcherTrace.zig
1       src/transpiler.zig
1       src/shell/builtin/cp.zig
1       src/js_printer.zig
1       src/io/PipeReader.zig
1       src/install/bin.zig
1       src/css/selectors/selector.zig
1       src/cli/run_command.zig
1       src/bun.js/RuntimeTranspilerStore.zig
1       src/bun.js/bindings/JSRef.zig
1       src/bake/DevServer.zig
```

Files that remove lines:

```
-1      src/test/recover.zig
-1      src/sql/postgres/SocketMonitor.zig
-1      src/sql/mysql/MySQLRequestQueue.zig
-1      src/sourcemap/CodeCoverage.zig
-1      src/css/values/color_js.zig
-1      src/compile_target.zig
-1      src/bundler/linker_context/convertStmtsForChunk.zig
-1      src/bundler/bundle_v2.zig
-1      src/bun.js/webcore/blob/read_file.zig
-1      src/ast/base.zig
-2      src/sql/postgres/protocol/ArrayList.zig
-2      src/shell/builtin/mkdir.zig
-2      src/install/PackageManager/patchPackage.zig
-2      src/install/PackageManager/PackageManagerDirectories.zig
-2      src/fmt.zig
-2      src/css/declaration.zig
-2      src/css/css_parser.zig
-2      src/collections/baby_list.zig
-2      src/bun.js/bindings/ZigStackFrame.zig
-2      src/ast/E.zig
-3      src/StandaloneModuleGraph.zig
-3      src/deps/picohttp.zig
-3      src/deps/libuv.zig
-3      src/btjs.zig
-4      src/threading/Futex.zig
-4      src/shell/builtin/touch.zig
-4      src/meta.zig
-4      src/install/lockfile.zig
-4      src/css/selectors/parser.zig
-5      src/shell/interpreter.zig
-5      src/css/error.zig
-5      src/bun.js/web_worker.zig
-5      src/bun.js.zig
-6      src/cli/test_command.zig
-6      src/bun.js/VirtualMachine.zig
-6      src/bun.js/uuid.zig
-6      src/bun.js/bindings/JSValue.zig
-9      src/bun.js/test/pretty_format.zig
-9      src/bun.js/api/BunObject.zig
-14     src/install/install_binding.zig
-14     src/fd.zig
-14     src/bun.js/node/path.zig
-14     scripts/pack-codegen-for-zig-team.sh
-17     src/bun.js/test/diff_format.zig
```

`git diff --numstat origin/main...HEAD | awk '{ print ($1-$2)"\t"$3 }' |
sort -rn`

---------

Co-authored-by: autofix-ci[bot] <114827586+autofix-ci[bot]@users.noreply.github.com>
Co-authored-by: Dylan Conway <dylan.conway567@gmail.com>
Co-authored-by: Meghan Denny <meghan@bun.com>
Co-authored-by: tayor.fish <contact@taylor.fish>
2025-11-10 14:38:26 -08:00

387 lines
13 KiB
Zig

const HashMapPool = struct {
const HashMap = std.HashMap(u64, void, IdentityContext, 80);
const LinkedList = bun.deprecated.SinglyLinkedList(HashMap);
threadlocal var list: LinkedList = undefined;
threadlocal var loaded: bool = false;
pub fn get(_: std.mem.Allocator) *LinkedList.Node {
if (loaded) {
if (list.popFirst()) |node| {
node.data.clearRetainingCapacity();
return node;
}
}
const new_node = default_allocator.create(LinkedList.Node) catch unreachable;
new_node.* = LinkedList.Node{ .data = HashMap.initContext(default_allocator, IdentityContext{}) };
return new_node;
}
pub fn release(node: *LinkedList.Node) void {
if (loaded) {
list.prepend(node);
return;
}
list = LinkedList{ .first = node };
loaded = true;
}
};
pub const TOML = struct {
lexer: Lexer,
log: *logger.Log,
allocator: std.mem.Allocator,
pub fn init(allocator: std.mem.Allocator, source_: logger.Source, log: *logger.Log, redact_logs: bool) !TOML {
return TOML{
.lexer = try Lexer.init(log, source_, allocator, redact_logs),
.allocator = allocator,
.log = log,
};
}
pub inline fn source(p: *const TOML) *const logger.Source {
return &p.lexer.source;
}
pub fn e(_: *TOML, t: anytype, loc: logger.Loc) Expr {
const Type = @TypeOf(t);
if (@typeInfo(Type) == .pointer) {
return Expr.init(std.meta.Child(Type), t.*, loc);
} else {
return Expr.init(Type, t, loc);
}
}
const Rope = js_ast.E.Object.Rope;
pub fn parseKeySegment(p: *TOML) anyerror!?Expr {
const loc = p.lexer.loc();
switch (p.lexer.token) {
.t_string_literal => {
const str = p.lexer.toString(loc);
try p.lexer.next();
return str;
},
.t_identifier => {
const str = E.String{ .data = p.lexer.identifier };
try p.lexer.next();
return p.e(str, loc);
},
.t_false => {
try p.lexer.next();
return p.e(
E.String{
.data = "false",
},
loc,
);
},
.t_true => {
try p.lexer.next();
return p.e(
E.String{
.data = "true",
},
loc,
);
},
// what we see as a number here could actually be a string
.t_numeric_literal => {
const literal = p.lexer.raw();
try p.lexer.next();
return p.e(E.String{ .data = literal }, loc);
},
else => return null,
}
}
pub fn parseKey(p: *TOML, allocator: std.mem.Allocator) anyerror!*Rope {
var rope = try allocator.create(Rope);
const head = rope;
rope.* = .{
.head = (try p.parseKeySegment()) orelse {
try p.lexer.expectedString("key");
return error.SyntaxError;
},
.next = null,
};
while (p.lexer.token == .t_dot) {
try p.lexer.next();
rope = try rope.append((try p.parseKeySegment()) orelse break, allocator);
}
return head;
}
pub fn parse(source_: *const logger.Source, log: *logger.Log, allocator: std.mem.Allocator, redact_logs: bool) !Expr {
switch (source_.contents.len) {
// This is to be consisntent with how disabled JS files are handled
0 => {
return Expr{ .loc = logger.Loc{ .start = 0 }, .data = Expr.init(E.Object, E.Object{}, logger.Loc.Empty).data };
},
else => {},
}
var parser = try TOML.init(allocator, source_.*, log, redact_logs);
return try parser.runParser();
}
fn runParser(p: *TOML) anyerror!Expr {
var root = p.e(E.Object{}, p.lexer.loc());
var head = root.data.e_object;
var stack = std.heap.stackFallback(@sizeOf(Rope) * 6, p.allocator);
const key_allocator = stack.get();
while (true) {
const loc = p.lexer.loc();
switch (p.lexer.token) {
.t_end_of_file => {
return root;
},
// child table
.t_open_bracket => {
try p.lexer.next();
const key = try p.parseKey(key_allocator);
try p.lexer.expect(.t_close_bracket);
if (!p.lexer.has_newline_before) {
try p.lexer.expectedString("line break");
}
const parent_object = root.data.e_object.getOrPutObject(key, p.allocator) catch |err| {
switch (err) {
error.Clobber => {
try p.lexer.addDefaultError("Table already defined");
return error.SyntaxError;
},
else => return err,
}
};
head = parent_object.data.e_object;
stack.fixed_buffer_allocator.reset();
},
// child table array
.t_open_bracket_double => {
try p.lexer.next();
const key = try p.parseKey(key_allocator);
try p.lexer.expect(.t_close_bracket_double);
if (!p.lexer.has_newline_before) {
try p.lexer.expectedString("line break");
}
var array = root.data.e_object.getOrPutArray(key, p.allocator) catch |err| {
switch (err) {
error.Clobber => {
try p.lexer.addDefaultError("Cannot overwrite table array");
return error.SyntaxError;
},
else => return err,
}
};
const new_head = p.e(E.Object{}, loc);
try array.data.e_array.push(p.allocator, new_head);
head = new_head.data.e_object;
stack.fixed_buffer_allocator.reset();
},
else => {
try p.parseAssignment(head, key_allocator);
stack.fixed_buffer_allocator.reset();
},
}
}
}
pub fn parseAssignment(p: *TOML, obj: *E.Object, allocator: std.mem.Allocator) anyerror!void {
p.lexer.allow_double_bracket = false;
const rope = try p.parseKey(allocator);
const rope_end = p.lexer.start;
const is_array = p.lexer.token == .t_empty_array;
if (is_array) {
try p.lexer.next();
}
try p.lexer.expectAssignment();
if (!is_array) {
obj.setRope(rope, p.allocator, try p.parseValue()) catch |err| {
switch (err) {
error.Clobber => {
const loc = rope.head.loc;
assert(loc.start > 0);
const start: u32 = @intCast(loc.start);
const key_name = std.mem.trimRight(u8, p.source().contents[start..rope_end], &std.ascii.whitespace);
p.lexer.addError(start, "Cannot redefine key '{s}'", .{key_name});
return error.SyntaxError;
},
else => return err,
}
};
}
p.lexer.allow_double_bracket = true;
}
pub fn parseValue(p: *TOML) anyerror!Expr {
const loc = p.lexer.loc();
p.lexer.allow_double_bracket = true;
switch (p.lexer.token) {
.t_false => {
try p.lexer.next();
return p.e(E.Boolean{
.value = false,
}, loc);
},
.t_true => {
try p.lexer.next();
return p.e(E.Boolean{
.value = true,
}, loc);
},
.t_string_literal => {
const result = p.lexer.toString(loc);
try p.lexer.next();
return result;
},
.t_identifier => {
const str: E.String = E.String{ .data = p.lexer.identifier };
try p.lexer.next();
return p.e(str, loc);
},
.t_numeric_literal => {
const value = p.lexer.number;
try p.lexer.next();
return p.e(E.Number{ .value = value }, loc);
},
.t_minus => {
try p.lexer.next();
const value = p.lexer.number;
try p.lexer.expect(.t_numeric_literal);
return p.e(E.Number{ .value = -value }, loc);
},
.t_plus => {
try p.lexer.next();
const value = p.lexer.number;
try p.lexer.expect(.t_numeric_literal);
return p.e(E.Number{ .value = value }, loc);
},
.t_open_brace => {
try p.lexer.next();
var is_single_line = !p.lexer.has_newline_before;
var stack = std.heap.stackFallback(@sizeOf(Rope) * 6, p.allocator);
const key_allocator = stack.get();
const expr = p.e(E.Object{}, loc);
const obj = expr.data.e_object;
while (p.lexer.token != .t_close_brace) {
if (obj.properties.len > 0) {
if (p.lexer.has_newline_before) {
is_single_line = false;
}
if (!try p.parseMaybeTrailingComma(.t_close_brace)) {
break;
}
if (p.lexer.has_newline_before) {
is_single_line = false;
}
}
try p.parseAssignment(obj, key_allocator);
p.lexer.allow_double_bracket = false;
stack.fixed_buffer_allocator.reset();
}
if (p.lexer.has_newline_before) {
is_single_line = false;
}
p.lexer.allow_double_bracket = true;
try p.lexer.expect(.t_close_brace);
return expr;
},
.t_empty_array => {
try p.lexer.next();
p.lexer.allow_double_bracket = true;
return p.e(E.Array{}, loc);
},
.t_open_bracket => {
try p.lexer.next();
var is_single_line = !p.lexer.has_newline_before;
const array_ = p.e(E.Array{}, loc);
var array = array_.data.e_array;
const allocator = p.allocator;
p.lexer.allow_double_bracket = false;
while (p.lexer.token != .t_close_bracket) {
if (array.items.len > 0) {
if (p.lexer.has_newline_before) {
is_single_line = false;
}
if (!try p.parseMaybeTrailingComma(.t_close_bracket)) {
break;
}
if (p.lexer.has_newline_before) {
is_single_line = false;
}
}
array.push(allocator, try p.parseValue()) catch unreachable;
}
if (p.lexer.has_newline_before) {
is_single_line = false;
}
p.lexer.allow_double_bracket = true;
try p.lexer.expect(.t_close_bracket);
return array_;
},
else => {
try p.lexer.unexpected();
return error.SyntaxError;
},
}
}
pub fn parseMaybeTrailingComma(p: *TOML, closer: T) !bool {
try p.lexer.expect(.t_comma);
if (p.lexer.token == closer) {
return false;
}
return true;
}
};
pub const lexer = @import("./toml/lexer.zig");
pub const Lexer = lexer.Lexer;
const T = lexer.T;
const string = []const u8;
const std = @import("std");
const IdentityContext = @import("../identity_context.zig").IdentityContext;
const expect = std.testing.expect;
const bun = @import("bun");
const assert = bun.assert;
const default_allocator = bun.default_allocator;
const logger = bun.logger;
const js_ast = bun.ast;
const E = js_ast.E;
const Expr = js_ast.Expr;