ludic syntax, and ludic-dev syntax: every grammar written from the compiler's vocabulary and checked against it

`ludic syntax [--json] [-o FILE]` prints what `ludicc --emit-syntax` does (a line
per entry, or the JSON). `ludic-dev syntax` writes, between "ludic-dev syntax:
begin" / "end" lines, the keyword, type, phase and attribute tables of
ludic_syntax.h, LudicVocabulary's sets (JetBrains), ludic-mode.el's lists and the
language server's word tests (is_keyword_word and the rest; is_contextual_word is
every word the parser does not reserve, and every declaring or modifying one),
and every TextMate pattern marked "comment": "ludic-dev syntax: <group>" (shared
and the VS Code copy). The grammars gain module uses port bind action reducer
dispatch registry def open component prop view alias friend unsafe numbers of as
from mut system; import and extern colour as declarations; the phase clause
knows Overlay; the bitwise pattern matches | and ^ on their own again.

`ludic-dev syntax --check` - and check-vocabulary, whose old parser comparison it
replaces, and the regression suite (syntax_cases, one line per file) - fails when
a written list is behind, when a grammar lacks a keyword, type or phase, when
docs/language has no page for a keyword, type, phase or attribute, or when the
parser (a scan of selfhost/frontend: is_id / text == words, a == / ann ==
attributes) tests a word or reads an attribute vocab.ludic lacks, or the reverse.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Orkun ÇAKILKAYA 2026-09-29 23:59:30 +03:00
parent 73f7d0b7a3
commit 2ad6edaae3
15 changed files with 784 additions and 118 deletions

View file

@ -484,19 +484,7 @@ function grammar_alt(root: JVal, node: pointer, marker: pointer) -> []pointer {
return out
}
# keywords the self-host parser dispatches on: is_id("x") + streq(t.text, "x")
function parser_keywords() -> []pointer {
let out = new []pointer
add_parser_kw(out, "selfhost/frontend/parse.ludic")
add_parser_kw(out, "selfhost/frontend/parse_game.ludic")
return out
}
function add_parser_kw(out: []pointer, path: pointer) -> void {
let t = read_file(path)
if t == null { return }
add_lower(out, collect_after(t, "is_id(" + dq()))
add_lower(out, collect_after(t, "streq(t.text, " + dq()))
}
# the lower-case names among `src` into `out` (a set)
function add_lower(out: []pointer, src: []pointer) -> void {
var i = 0
while i < len(src) { if all_lower(src[i]) { set_add(out, src[i]) }; i += 1 }
@ -537,7 +525,6 @@ function cmd_check_vocab() -> int {
let h_widgets = table_set(h, "LUDIC_WIDGETS")
let h_builtins = c_table_names(h, "LUDIC_BUILTINS")
let h_intrinsics = c_table_names(h, "LUDIC_INTRINSICS")
let h_reserved = table_set(h, "LUDIC_KW_RESERVED")
# --- against the JetBrains lexer ---
let kt = read_file("tools/editors/jetbrains/src/main/kotlin/io/ludic/ide/LudicTokens.kt")
@ -561,16 +548,26 @@ function cmd_check_vocab() -> int {
cmp_sets("primitive types", h_types, grammar_alt(g, "keyword", "fixed"), "ludic.tmLanguage.json")
}
# --- against the self-host parser ---
let pkw = parser_keywords()
if len(pkw) == 0 {
cv_problem("could not extract any keywords from selfhost/frontend/parse*.ludic")
} else {
cmp_unparsed("declaration keywords", h_decl, pkw, h_reserved)
cmp_unparsed("clause keywords", h_clause, pkw, h_reserved)
# reserved words the parser now accepts should be promoted
var i = 0
while i < len(h_reserved) { if set_has(pkw, h_reserved[i]) { cv_problem("LUDIC_KW_RESERVED lists a keyword the parser now accepts — promote it: " + h_reserved[i]) }; i += 1 }
# --- the keyword, type and phase tables, the docs and the parser, against the compiler's own
# vocabulary (ludicc --emit-syntax; syntax_gen.ludic) ---
if sx_vocab() == null { cv_problem("bin/ludicc has no --emit-syntax: rebuild it (ludic-dev build)") }
else {
g_sx_prob = new []pointer
let ts = sx_targets()
var ti = 0
while ti < len(ts) {
let text = read_file(ts[ti])
if text != null {
let want = sx_regenerate(ts[ti], text)
if want != null and not (want == text) { cv_problem(ts[ti] + " is behind the vocabulary - run ludic-dev syntax") }
}
sx_carries(ts[ti])
ti += 1
}
sx_docs()
sx_parser()
var pi2 = 0
while pi2 < len(g_sx_prob) { cv_problem(g_sx_prob[pi2]); pi2 += 1 }
}
if CV_N > 0 {
@ -581,16 +578,6 @@ function cmd_check_vocab() -> int {
return 0
}
# keywords in `kws` the parser never dispatches on (minus reserved) are a problem
function cmp_unparsed(label: pointer, kws: []pointer, pkw: []pointer, reserved: []pointer) -> void {
var i = 0
while i < len(kws) {
if not set_has(pkw, kws[i]) {
if not set_has(reserved, kws[i]) { cv_problem("ludic_syntax.h lists a " + label + " the selfhost parser never dispatches on: " + kws[i]) }
}
i += 1
}
}
# ============================================================================
# json/xml asset validation — replaces the python3 json.load / xml.dom checks