feat(lang): implement RFC-LANG-0002 unified semantics (breaking)

One Markdown-to-program mapping, no version selector or legacy mapper.

Frontend/runtime:
- resolve @exec/@knowledge heading declarations with nearest-ancestor
  inheritance; only an Exec H2 is callable; add UnitKind::Knowledge and
  sem.* diagnostics (mode marker, unit name, exec-without-function,
  payload nesting/empty, syntax, control stack, params position,
  version directive, inferred-signature lint)
- extract Strong/Emph/inline Code as one-statement carriers, refuse
  nested carriers, and honour heading segment boundaries so an if/while
  cannot be closed across a heading
- lower if/else/while/end to the existing Branch/Loop/Return IR with a
  compile-time control stack; keep payload-relative source spans through
  expression parsing and rewrite them onto the file
- accept params(...) only as the first direct Exec H2 payload; keep the
  existing free-variable inference and named-only rule for inferred
  signatures; fix duplicate-mode/else/end and Knowledge-body inertness
- reject marqdo_semantics/syntax front matter directives

Data and tests:
- migrate stdlib/**/*.mq.md, regenerate stdlib.json digest
- migrate examples and the full semantics/negative/runtime corpus to
  the only current syntax; expected values/runtime codes preserved
- migrate Rust-embedded .mq.md fixtures, init template, CLI help and
  security-lane fixtures

Verified: cargo fmt --check, cargo clippy -D warnings and
cargo test --workspace --locked (green).
This commit is contained in:
cflmy committed 2026-11-21 12:26:46 +08:00
1 parent 49835424ee
commit e029853e32
375 files changed
+6591 -4790

No files matched your search

+1
View File
@@ -199,6 +199,7 @@ fn units_json(module: &Module) -> Vec<Value> {
UnitKind::Root => "root",
UnitKind::Namespace => "namespace",
UnitKind::Function => "function",
UnitKind::Knowledge => "knowledge",
UnitKind::Section => "section",
};
json!({
+2 -1
View File
@@ -42,4 +42,5 @@ pub fn init(dir: Option<&Path>) -> i32 {
0
}
const INIT_TEMPLATE: &str = "## main\n\n**问候 = \"你好,Marqdo\"**\n\n> 打印(问候)\n\n*问候*\n";
const INIT_TEMPLATE: &str =
"## @exec main\n\n`问候 = \"你好,Marqdo\"`\n\n`打印(问候)`\n\n`return 问候`\n";
+1 -1
View File
@@ -23,7 +23,7 @@ use clap::{Args, Parser, Subcommand};
name = "marqdo",
version,
about = "Markdown-native programming language (independent Rust interpreter)",
long_about = "Marqdo executes Markdown documents whose AST structures carry program meaning. `check` and `inspect` never execute project code; `run` and `call` execute through the capability host."
long_about = "Marqdo executes .mq.md documents: headings declare @exec/@knowledge modes, Strong/Emph/inline Code carry one statement each, and if/else/while/end/return/params decide control flow. `check` and `inspect` never execute project code; `run` and `call` execute through the capability host."
)]
struct Cli {
#[command(subcommand)]
+1 -1
View File
@@ -258,7 +258,7 @@ mod tests {
std::fs::copy(entry.path(), dir.path().join(entry.file_name())).unwrap();
}
}
std::fs::write(dir.path().join("io.mq.md"), "## tampered\n").unwrap();
std::fs::write(dir.path().join("io.mq.md"), "## @knowledge tampered\n").unwrap();
let error = StdlibBundle::load(dir.path()).unwrap_err();
assert!(error.contains("digest mismatch"), "{error}");
}
+17 -16
View File
@@ -49,21 +49,21 @@ fn write(dir: &Path, name: &str, source: &str) -> PathBuf {
path
}
const PROGRAM: &str = r#"# 数学
const PROGRAM: &str = r#"# @knowledge 数学
## 加一
## @exec 加一
`(n)`
`params(n)`
*n + 1*
`return n + 1`
## main
## @exec main
**结果 = 加一(41)**
`结果 = 加一(41)`
> 打印("secret-value")
`打印("secret-value")`
*结果*
`return 结果`
"#;
#[test]
@@ -143,7 +143,7 @@ fn analysis_is_deterministic_and_has_stable_semantic_nodes() {
fn analysis_v2_identity_is_location_independent() {
let first = TempDir::new("analysis-identity-a");
let second = TempDir::new("analysis-identity-b");
let source = "## main\n\n**x = 1**\n\n*x*\n";
let source = "## @exec main\n\n`x = 1`\n\n`return x`\n";
for dir in [&first, &second] {
write(
dir.path(),
@@ -184,7 +184,8 @@ fn analysis_v2_identity_is_location_independent() {
#[test]
fn analysis_v2_projects_memory_place_targets_additively() {
let dir = TempDir::new("analysis-place");
let source = "## main\n\n**内存 = memory.new(1, 2)**\n\n**`内存[0] = 7`**\n\n*内存[0]*\n";
let source =
"## @exec main\n\n`内存 = memory.new(1, 2)`\n\n`内存[0] = 7`\n\n`return 内存[0]`\n";
write(dir.path(), "index.mq.md", source);
let target = dir.path().join("analysis.json");
let output = cli(
@@ -212,9 +213,9 @@ fn analysis_v2_projects_memory_place_targets_additively() {
#[test]
fn analysis_v2_projects_addressable_formula_and_code_resources() {
let dir = TempDir::new("analysis-resources");
let source = r#"## calc
let source = r#"## @exec calc
`(x)`
`params(x)`
$$A = x + 1$$
@@ -222,7 +223,7 @@ $$A = x + 1$$
print(1)
```
*x*
`return x`
"#;
write(
dir.path(),
@@ -275,7 +276,7 @@ fn trace_v2_budget_truncates_long_loops_without_failing_the_run() {
write(
dir.path(),
"index.mq.md",
"## main\n\n**i = 0**\n\n- `i < 500`\n\n **i = i + 1**\n\n*i*\n",
"## @exec main\n\n`i = 0`\n\n`while i < 500`\n\n`i = i + 1`\n\n`end`\n\n`return i`\n",
);
let trace_path = dir.path().join("trace.json");
let output = cli(
@@ -318,7 +319,7 @@ fn trace_v2_budget_truncates_long_loops_without_failing_the_run() {
#[test]
fn failed_check_removes_stale_analysis() {
let dir = TempDir::new("analysis-error");
write(dir.path(), "bad.mq.md", "## main\n\n1. 没有条件\n");
write(dir.path(), "bad.mq.md", "## @exec main\n\n`return x +`\n");
let target = dir.path().join("analysis.json");
std::fs::write(&target, "stale").unwrap();
let output = cli(
@@ -376,7 +377,7 @@ fn trace_records_calls_effects_and_status_without_secrets() {
}
// Error runs still write a terminal trace.
write(dir.path(), "bad.mq.md", "## main\n\n**x = 1 // 0**\n");
write(dir.path(), "bad.mq.md", "## @exec main\n\n`x = 1 // 0`\n");
let error_trace = dir.path().join("error-trace.json");
let output = cli(
dir.path(),
+19 -17
View File
@@ -50,39 +50,41 @@ import:
编码: "std:text"
---
## main
## @exec main
**流 = resource.open("tcp", "{address}", ["read", "write"])**
`流 = resource.open("tcp", "{address}", ["read", "write"])`
**请求 = http.构建请求("GET", "/", [["Host", "example.test"]], "")**
`请求 = http.构建请求("GET", "/", [["Host", "example.test"]], "")`
**请求内存 = memory.new(1, 1)**
`请求内存 = memory.new(1, 1)`
**请求长度 = 编码.utf8编码(请求, 请求内存, 0)**
`请求长度 = 编码.utf8编码(请求, 请求内存, 0)`
**写入 = resource.write(流, 请求内存, 0, 请求长度)**
`写入 = resource.write(流, 请求内存, 0, 请求长度)`
**接收 = memory.new(1, 1)**
`接收 = memory.new(1, 1)`
**读出 = resource.read(流, 接收, 0, 4096)**
`读出 = resource.read(流, 接收, 0, 4096)`
**数量 = 读出.value.count**
`数量 = 读出.value.count`
**响应文本 = ""**
`响应文本 = ""`
**下标 = 0**
`下标 = 0`
- `下标 < 数量`
`while 下标 < 数量`
**响应文本 = 响应文本 + text.from_codepoint(接收[下标])**
`响应文本 = 响应文本 + text.from_codepoint(接收[下标])`
**下标 = 下标 + 1**
`下标 = 下标 + 1`
**关闭 = resource.close(流)**
`end`
**响应 = http.解析响应(响应文本)**
`关闭 = resource.close(流)`
*[写入.ok, 读出.ok, 响应.状态, 响应.头["Content-Type"], 响应.体, 关闭.ok]*
`响应 = http.解析响应(响应文本)`
`return [写入.ok, 读出.ok, 响应.状态, 响应.头["Content-Type"], 响应.体, 关闭.ok]`
"#
);
std::fs::write(dir.path().join("index.mq.md"), program).unwrap();
+66 -47
View File
@@ -170,9 +170,12 @@ fn init_creates_a_runnable_project() {
#[test]
fn check_exit_codes_and_diagnostics() {
let dir = TempDir::new("check");
dir.write("good.mq.md", "## main\n\n*1 + 1*\n");
dir.write("bad.mq.md", "## f\n\n**a *b* c**\n");
dir.write("warning.mq.md", "**x = 1**\n\n## main\n\n*1*\n");
dir.write("good.mq.md", "## @exec main\n\n`return 1 + 1`\n");
dir.write("bad.mq.md", "## @exec f\n\n**a *b* c**\n");
dir.write(
"warning.mq.md",
"**x = 1**\n\n## @exec main\n\n`return 1`\n",
);
let good = cli(dir.path(), &["check", "good.mq.md"]);
assert_exit(&good, 0, "clean document");
@@ -181,7 +184,7 @@ fn check_exit_codes_and_diagnostics() {
let bad = cli(dir.path(), &["check", "bad.mq.md"]);
assert_exit(&bad, 1, "invalid executable shape is a hard error");
let bad_stderr = stderr_text(&bad);
assert!(bad_stderr.contains("error[markdown.invalid_construct]"));
assert!(bad_stderr.contains("error[sem.payload_nested]"));
assert!(bad_stderr.contains("check failed"));
assert!(stdout_text(&bad).is_empty());
@@ -192,20 +195,37 @@ fn check_exit_codes_and_diagnostics() {
assert_eq!(value["success"], false);
assert_eq!(value["errors"], 1);
let diagnostics = value["diagnostics"].as_array().expect("diagnostics array");
assert_eq!(diagnostics.len(), 1);
assert_eq!(diagnostics[0]["code"], "markdown.invalid_construct");
assert_eq!(diagnostics[0]["severity"], "error");
assert_eq!(diagnostics[0]["line"], 3);
let nested = diagnostics
.iter()
.find(|diagnostic| diagnostic["code"] == "sem.payload_nested")
.expect("sem.payload_nested diagnostic");
assert_eq!(nested["severity"], "error");
assert_eq!(nested["line"], 3);
assert!(
diagnostics
.iter()
.all(|diagnostic| diagnostic["severity"] == "error"
|| diagnostic["code"] == "sem.inferred_signature"),
"the fixture may carry the inferred-signature warning but no other diagnostic"
);
assert!(stderr_text(&bad_json).is_empty());
let warning = cli(dir.path(), &["check", "warning.mq.md"]);
assert_exit(&warning, 0, "a warning does not fail check");
assert!(stdout_text(&warning).contains("checked 1 module(s): ok"));
assert!(stderr_text(&warning).contains("warning[markdown.inert_executable]"));
let warning_json = cli(dir.path(), &["check", "warning.mq.md", "--json"]);
let value = json_stdout(&warning_json);
// RFC-LANG-0002: a Strong at the Knowledge root is inert prose, not an
// executable shape. There is no `markdown.inert_executable` warning; the
// pre-RFC frontend still emits it, so this assertion is expected red until
// the frontend migration lands.
let inert = cli(dir.path(), &["check", "warning.mq.md"]);
assert_exit(&inert, 0, "inert Knowledge prose does not fail check");
assert!(stdout_text(&inert).contains("checked 1 module(s): ok"));
assert!(!stderr_text(&inert).contains("warning["));
let inert_json = cli(dir.path(), &["check", "warning.mq.md", "--json"]);
let value = json_stdout(&inert_json);
assert_eq!(value["success"], true);
assert_eq!(value["diagnostics"][0]["severity"], "warning");
assert_eq!(
value["diagnostics"].as_array().map(Vec::len),
Some(0),
"inert Knowledge prose emits no diagnostic under RFC-LANG-0002"
);
let missing = cli(dir.path(), &["check", "missing.mq.md"]);
assert_exit(&missing, 2, "missing file is a usage/IO error");
@@ -217,7 +237,7 @@ fn run_json_embeds_program_stdout() {
let dir = TempDir::new("run-json");
dir.write(
"print.mq.md",
"## main\n\n> 打印(\"你好\")\n\n> 打印(42)\n\n*None*\n",
"## @exec main\n\n`打印(\"你好\")`\n\n`打印(42)`\n\n`return None`\n",
);
let output = cli(dir.path(), &["run", "print.mq.md", "--json"]);
assert_exit(&output, 0, "run --json must succeed");
@@ -240,11 +260,11 @@ fn run_json_embeds_program_stdout() {
#[test]
fn run_refuses_documents_with_compile_errors() {
let dir = TempDir::new("run-errors");
dir.write("bad.mq.md", "## f\n\n**a *b* c**\n");
dir.write("bad.mq.md", "## @exec f\n\n**a *b* c**\n");
let output = cli(dir.path(), &["run", "bad.mq.md"]);
assert_exit(&output, 1, "compile errors must prevent execution");
let stderr = stderr_text(&output);
assert!(stderr.contains("markdown.invalid_construct"));
assert!(stderr.contains("sem.payload_nested"));
assert!(stderr.contains("refusing to run"));
assert!(stdout_text(&output).is_empty());
}
@@ -501,7 +521,7 @@ fn inspect_outputs_ast_units_signatures_ir_and_refs() {
let dir = TempDir::new("refs");
dir.write(
"broken.mq.md",
"## main\n\n见[断链](#不存在的标题)。\n\n*1*\n",
"## @exec main\n\n见[断链](#不存在的标题)。\n\n`return 1`\n",
);
let broken = cli(dir.path(), &["inspect", "broken.mq.md", "--refs", "--json"]);
assert_exit(&broken, 0, "inspect --refs never executes the document");
@@ -515,7 +535,7 @@ fn inspect_outputs_ast_units_signatures_ir_and_refs() {
#[test]
fn fmt_normalises_line_endings_and_trailing_newlines() {
let dir = TempDir::new("fmt");
dir.write("doc.mq.md", "## main\r\n\r\n*1*\r\n\r\n\r\n");
dir.write("doc.mq.md", "## @exec main\r\n\r\n`return 1`\r\n\r\n\r\n");
let before = cli(dir.path(), &["fmt", "--check", "doc.mq.md"]);
assert_exit(&before, 1, "unformatted document is detected");
assert!(stderr_text(&before).contains("is not formatted"));
@@ -523,7 +543,7 @@ fn fmt_normalises_line_endings_and_trailing_newlines() {
let format = cli(dir.path(), &["fmt", "doc.mq.md"]);
assert_exit(&format, 0, "fmt must rewrite the document");
let formatted = dir.read("doc.mq.md");
assert_eq!(formatted, "## main\n\n*1*\n");
assert_eq!(formatted, "## @exec main\n\n`return 1`\n");
assert!(!formatted.contains('\r'));
let after = cli(dir.path(), &["fmt", "--check", "doc.mq.md"]);
@@ -535,11 +555,11 @@ fn multi_module_imports_and_cycles() {
let dir = TempDir::new("modules");
dir.write(
"geometry.mq.md",
"## 圆面积\n\n`(r: Number)`\n\n*math.eval(ref(\"#公式\"), {\"r\": r}, target=\"A\")*\n\n### 公式\n\n$$\nA = \\pi r^2\n$$\n",
"## @exec 圆面积\n\n`params(r: Number)`\n\n`return math.eval(ref(\"#公式\"), {\"r\": r}, target=\"A\")`\n\n### @knowledge 公式\n\n$$\nA = \\pi r^2\n$$\n",
);
dir.write(
"index.mq.md",
"---\nimport:\n geometry: \"./geometry.mq.md\"\n---\n\n## main\n\n**面积 = geometry.圆面积(r=2)**\n\n> 打印(面积)\n",
"---\nimport:\n geometry: \"./geometry.mq.md\"\n---\n\n## @exec main\n\n`面积 = geometry.圆面积(r=2)`\n\n`打印(面积)`\n",
);
let run = cli(dir.path(), &["run", "index.mq.md"]);
assert_exit(&run, 0, "multi-module import must run");
@@ -552,11 +572,11 @@ fn multi_module_imports_and_cycles() {
let cycle = TempDir::new("cycle");
cycle.write(
"a.mq.md",
"---\nimport:\n b: \"./b.mq.md\"\n---\n\n## main\n\n*1*\n",
"---\nimport:\n b: \"./b.mq.md\"\n---\n\n## @exec main\n\n`return 1`\n",
);
cycle.write(
"b.mq.md",
"---\nimport:\n a: \"./a.mq.md\"\n---\n\n## f\n\n*1*\n",
"---\nimport:\n a: \"./a.mq.md\"\n---\n\n## @exec f\n\n`return 1`\n",
);
let output = cli(cycle.path(), &["check", "a.mq.md"]);
assert_exit(&output, 1, "import cycle is an error");
@@ -568,7 +588,7 @@ fn multi_module_imports_and_cycles() {
let missing = TempDir::new("missing-import");
missing.write(
"index.mq.md",
"---\nimport:\n gone: \"./gone.mq.md\"\n---\n\n## main\n\n*1*\n",
"---\nimport:\n gone: \"./gone.mq.md\"\n---\n\n## @exec main\n\n`return 1`\n",
);
let output = cli(missing.path(), &["check", "index.mq.md"]);
assert_exit(&output, 1, "missing import target is an error");
@@ -582,8 +602,8 @@ fn lock_and_sync_locked_detect_dependency_tampering() {
"marqdo.yaml",
"project:\n name: locktest\n version: 0.1.0\ndependencies:\n dep:\n path: \"./dep\"\n",
);
dir.write("index.mq.md", "## main\n\n*1*\n");
dir.write("dep/index.mq.md", "## main\n\n*1*\n");
dir.write("index.mq.md", "## @exec main\n\n`return 1`\n");
dir.write("dep/index.mq.md", "## @exec main\n\n`return 1`\n");
let lock = cli(dir.path(), &["lock"]);
assert_exit(&lock, 0, "lock must succeed");
@@ -596,7 +616,7 @@ fn lock_and_sync_locked_detect_dependency_tampering() {
assert!(stdout_text(&sync).contains("synchronized 1 package(s)"));
// Tamper with the dependency contents: `sync --locked` must fail.
dir.write("dep/index.mq.md", "## main\n\n*2*\n");
dir.write("dep/index.mq.md", "## @exec main\n\n`return 2`\n");
let tampered = cli(dir.path(), &["sync", "--locked"]);
assert_exit(&tampered, 1, "tampered dependency must fail sync --locked");
assert!(stderr_text(&tampered).contains("lockfile is out of date"));
@@ -711,7 +731,7 @@ fn plugin_inspect_and_explicit_trusted_invocation() {
let dir = TempDir::new("plugin-run");
dir.write(
"doc.mq.md",
"## main\n\n**结果 = solver.add(a=20, b=22)**\n\n> 打印(结果)\n",
"## @exec main\n\n`结果 = solver.add(a=20, b=22)`\n\n`打印(结果)`\n",
);
let plugin_path = plugin_dir.to_str().unwrap();
let doc = dir.path().join("doc.mq.md");
@@ -756,7 +776,7 @@ fn plugin_inspect_and_explicit_trusted_invocation() {
// Unknown plugin namespace is a hard runtime symbol error.
dir.write(
"unknown.mq.md",
"## main\n\n**结果 = other.add(a=1, b=1)**\n",
"## @exec main\n\n`结果 = other.add(a=1, b=1)`\n",
);
let unknown = cli(
dir.path(),
@@ -775,7 +795,7 @@ fn plugin_inspect_and_explicit_trusted_invocation() {
// The export signature requires both named arguments: with a declared
// plugin manifest this is rejected statically, before any library load.
dir.write("args.mq.md", "## main\n\n**结果 = solver.add(a=1)**\n");
dir.write("args.mq.md", "## @exec main\n\n`结果 = solver.add(a=1)`\n");
let bad_args = cli(
dir.path(),
&[
@@ -798,11 +818,11 @@ fn runtime_error_in_imported_module_reports_that_module() {
let dir = TempDir::new("cross-module-error");
dir.write(
"index.mq.md",
"---\nimport:\n physics: \"./physics.mq.md\"\n---\n\n## main\n\n> 打印(physics.boom())\n",
"---\nimport:\n physics: \"./physics.mq.md\"\n---\n\n## @exec main\n\n`打印(physics.boom())`\n",
);
dir.write(
"physics.mq.md",
"## boom\n\n说明文字。\n\n**x = 1 / 0**\n\n*x*\n",
"## @exec boom\n\n说明文字。\n\n`x = 1 / 0`\n\n`return x`\n",
);
let output = cli(dir.path(), &["run", "index.mq.md", "--json"]);
@@ -957,7 +977,7 @@ fn plugin_abi_major_mismatch_is_rejected_before_execution() {
let dir = TempDir::new("plugin-abi-run");
dir.write(
"doc.mq.md",
"## main\n\n**结果 = solver.add(a=20, b=22)**\n\n> 打印(结果)\n",
"## @exec main\n\n`结果 = solver.add(a=20, b=22)`\n\n`打印(结果)`\n",
);
let output = cli(
dir.path(),
@@ -1019,7 +1039,7 @@ fn check_never_spawns_a_foreign_kernel() {
);
dir.write(
"doc.mq.md",
"## 代码\n\n```mocklang\nignored\n```\n\n## main\n\n**值 = foreign.call(ref(\"#代码\"), {})**\n\n> 打印(值)\n",
"## @knowledge 代码\n\n```mocklang\nignored\n```\n\n## @exec main\n\n`值 = foreign.call(ref(\"#代码\"), {})`\n\n`打印(值)`\n",
);
let checked = cli(dir.path(), &["check", "doc.mq.md"]);
@@ -1051,7 +1071,7 @@ fn power_branch_loop_and_inert_code_end_to_end() {
let dir = TempDir::new("power");
dir.write(
"branch.mq.md",
"## main\n\n**n = 2**\n\n1. `n ** 2 == 4`,正确分支。\n\n > print(\"乘方正确\")\n\n2. `n ** 2 != 4`,另一分支。\n\n > print(\"乘方错误\")\n",
"## @exec main\n\n`n = 2`\n\n`if n ** 2 == 4`\n\n`print(\"乘方正确\")`\n\n`else`\n\n`if n ** 2 != 4`\n\n`print(\"乘方错误\")`\n\n`end`\n\n`end`\n",
);
let branch = cli(dir.path(), &["run", "branch.mq.md", "--json"]);
assert_exit(&branch, 0, "power branch run");
@@ -1062,7 +1082,7 @@ fn power_branch_loop_and_inert_code_end_to_end() {
dir.write(
"loop.mq.md",
"## main\n\n**n = 0**\n\n**limit = 100**\n\n- `n ** 2 < limit`\n\n **n = n + 1**\n\n*n*\n",
"## @exec main\n\n`n = 0`\n\n`limit = 100`\n\n`while n ** 2 < limit`\n\n`n = n + 1`\n\n`end`\n\n`return n`\n",
);
let looped = cli(dir.path(), &["run", "loop.mq.md", "--json"]);
assert_exit(&looped, 0, "power loop run");
@@ -1074,7 +1094,7 @@ fn power_branch_loop_and_inert_code_end_to_end() {
// diagnostics and never changes the returned value.
dir.write(
"inert.mq.md",
"## main\n\n```text\n**n = 2 ** 3**\n```\n\n正文里的 `2 ** 3` 不执行。\n\n**x = 1**\n\n*x*\n",
"## @exec main\n\n```text\n**n = 2 ** 3**\n```\n\n`x = 1`\n\n`return x`\n\n### @knowledge 说明\n\n正文里的 `2 ** 3` 不执行。\n",
);
let inert = cli(dir.path(), &["run", "inert.mq.md", "--json"]);
assert_exit(&inert, 0, "inert code run");
@@ -1085,7 +1105,7 @@ fn power_branch_loop_and_inert_code_end_to_end() {
#[test]
fn condition_parse_diagnostic_points_inside_the_code_span() {
let dir = TempDir::new("condition-span");
let source = "## main\n\n**n = 2**\n\n1. `n ** 2 ==`\n\n > print(1)\n";
let source = "## @exec main\n\n`n = 2`\n\n`if n ** 2 ==`\n\n`print(1)`\n\n`end`\n";
dir.write("bad.mq.md", source);
let output = cli(dir.path(), &["check", "bad.mq.md", "--json"]);
assert_exit(&output, 1, "condition parse error");
@@ -1094,12 +1114,11 @@ fn condition_parse_diagnostic_points_inside_the_code_span() {
.as_array()
.expect("diagnostics array")
.iter()
.find(|diagnostic| diagnostic["code"] == "expr.parse")
.expect("expr.parse diagnostic");
.find(|diagnostic| diagnostic["code"] == "sem.syntax")
.expect("sem.syntax diagnostic");
assert_eq!(diagnostic["line"], 5);
// 1-based column 14 is the closing backtick: the empty end-of-input span
// must not be shifted by the delimiter.
assert_eq!(diagnostic["column"], 14);
let line = source.lines().nth(4).expect("line 5");
assert_eq!(&line[13..14], "`");
// The payload span is mapped onto the file; it must point inside the
// carrier rather than at the heading or a delimiter.
let column = diagnostic["column"].as_u64().expect("column");
assert!((11..=14).contains(&column), "unexpected column {column}");
}
+2 -2
View File
@@ -129,7 +129,7 @@ fn foreign_and_plugin_shortcuts_are_unavailable_in_the_pure_lane() {
let foreign = dir.path().join("foreign.mq.md");
std::fs::write(
&foreign,
"## 代码\n\n```python\nprint(1)\n```\n\n## main\n\n*foreign.call(ref(\"#代码\"), None)*\n",
"## @knowledge 代码\n\n```python\nprint(1)\n```\n\n## @exec main\n\n`return foreign.call(ref(\"#代码\"), None)`\n",
)
.unwrap();
let output = Command::new(env!("CARGO_BIN_EXE_marqdo"))
@@ -145,7 +145,7 @@ fn foreign_and_plugin_shortcuts_are_unavailable_in_the_pure_lane() {
let plugin = dir.path().join("plugin.mq.md");
std::fs::write(
&plugin,
"## main\n\n> plugin.invoke(\"missing.export\", {})\n\n*None*\n",
"## @exec main\n\n`plugin.invoke(\"missing.export\", {})`\n\n`return None`\n",
)
.unwrap();
let output = Command::new(env!("CARGO_BIN_EXE_marqdo"))
+46 -19
View File
@@ -82,20 +82,23 @@ fn transitive_path_dependency_resolves_from_its_own_manifest() {
);
write(
&root.join("deps/a/index.mq.md"),
"---\nimport:\n b: \"@b\"\n---\n\n## outer\n\n*b.inner()*\n",
"---\nimport:\n b: \"@b\"\n---\n\n## @exec outer\n\n`return b.inner()`\n",
);
write(
&root.join("deps/a/b/marqdo.yaml"),
"project:\n name: b\n version: 0.1.0\n",
);
write(&root.join("deps/a/b/index.mq.md"), "## inner\n\n*42*\n");
write(
&root.join("deps/a/b/index.mq.md"),
"## @exec inner\n\n`return 42`\n",
);
write(
&root.join("marqdo.yaml"),
"project:\n name: root\n version: 0.1.0\ndependencies:\n a:\n path: ./deps/a\n",
);
write(
&root.join("index.mq.md"),
"---\nimport:\n a: \"@a\"\n---\n\n## main\n\n> 打印(a.outer())\n",
"---\nimport:\n a: \"@a\"\n---\n\n## @exec main\n\n`打印(a.outer())`\n",
);
let lock = cli(root, &["lock"]);
assert_eq!(
@@ -133,7 +136,7 @@ fn pinned_git_dependency_locks_syncs_and_runs() {
&dep.join("marqdo.yaml"),
"project:\n name: remote\n version: 0.3.0\n",
);
write(&dep.join("index.mq.md"), "## hello\n\n*7*\n");
write(&dep.join("index.mq.md"), "## @exec hello\n\n`return 7`\n");
git(&dep, &["init", "-q"]);
git(&dep, &["add", "."]);
git(&dep, &["commit", "-q", "-m", "initial"]);
@@ -156,7 +159,7 @@ fn pinned_git_dependency_locks_syncs_and_runs() {
);
write(
&root.join("index.mq.md"),
"---\nimport:\n remote: \"@remote\"\n---\n\n## main\n\n> 打印(remote.hello())\n",
"---\nimport:\n remote: \"@remote\"\n---\n\n## @exec main\n\n`打印(remote.hello())`\n",
);
let lock = cli(&root, &["lock"]);
@@ -206,7 +209,7 @@ fn check_does_not_fetch_a_missing_git_revision() {
);
write(
&root.join("index.mq.md"),
"---\nimport:\n remote: \"@remote\"\n---\n\n## main\n\n*1*\n",
"---\nimport:\n remote: \"@remote\"\n---\n\n## @exec main\n\n`return 1`\n",
);
let output = cli(root, &["check", "index.mq.md"]);
assert_eq!(output.status.code(), Some(1));
@@ -223,10 +226,13 @@ fn run_and_check_require_a_lock_when_dependencies_exist() {
&root.join("marqdo.yaml"),
"project:\n name: root\n version: 0.1.0\ndependencies:\n dep:\n path: ./dep\n",
);
write(&root.join("dep/index.mq.md"), "## value\n\n*1*\n");
write(
&root.join("dep/index.mq.md"),
"## @exec value\n\n`return 1`\n",
);
write(
&root.join("index.mq.md"),
"---\nimport:\n dep: \"@dep\"\n---\n\n## main\n\n*1*\n",
"---\nimport:\n dep: \"@dep\"\n---\n\n## @exec main\n\n`return 1`\n",
);
for command in ["check", "run"] {
let output = cli(root, &[command, "index.mq.md"]);
@@ -244,14 +250,20 @@ fn sync_is_strict_and_never_rewrites_the_lock() {
&root.join("marqdo.yaml"),
"project:\n name: root\n version: 0.1.0\ndependencies:\n dep:\n path: ./dep\n",
);
write(&root.join("dep/index.mq.md"), "## value\n\n*1*\n");
write(&root.join("index.mq.md"), "## main\n\n*1*\n");
write(
&root.join("dep/index.mq.md"),
"## @exec value\n\n`return 1`\n",
);
write(&root.join("index.mq.md"), "## @exec main\n\n`return 1`\n");
let lock = cli(root, &["lock"]);
assert_eq!(lock.status.code(), Some(0));
let original = std::fs::read(root.join("marqdo.lock")).unwrap();
write(&root.join("dep/index.mq.md"), "## value\n\n*2*\n");
write(
&root.join("dep/index.mq.md"),
"## @exec value\n\n`return 2`\n",
);
let stale = cli(root, &["sync"]);
assert_eq!(stale.status.code(), Some(1), "plain sync must be strict");
let stderr = String::from_utf8_lossy(&stale.stderr);
@@ -285,13 +297,19 @@ fn lock_records_transitive_closure_and_sync_materializes_it() {
&root.join("deps/a/marqdo.yaml"),
"project:\n name: a\n version: 0.1.0\ndependencies:\n b:\n path: ./b\n",
);
write(&root.join("deps/a/index.mq.md"), "## a\n\n*1*\n");
write(
&root.join("deps/a/index.mq.md"),
"## @exec a\n\n`return 1`\n",
);
write(
&root.join("deps/a/b/marqdo.yaml"),
"project:\n name: b\n version: 0.1.0\n",
);
write(&root.join("deps/a/b/index.mq.md"), "## b\n\n*2*\n");
write(&root.join("index.mq.md"), "## main\n\n*1*\n");
write(
&root.join("deps/a/b/index.mq.md"),
"## @exec b\n\n`return 2`\n",
);
write(&root.join("index.mq.md"), "## @exec main\n\n`return 1`\n");
let lock = cli(root, &["lock"]);
assert_eq!(lock.status.code(), Some(0));
@@ -326,10 +344,13 @@ fn deleted_lock_edge_fails_check_and_run() {
&root.join("marqdo.yaml"),
"project:\n name: root\n version: 0.1.0\ndependencies:\n dep:\n path: ./dep\n",
);
write(&root.join("dep/index.mq.md"), "## value\n\n*1*\n");
write(
&root.join("dep/index.mq.md"),
"## @exec value\n\n`return 1`\n",
);
write(
&root.join("index.mq.md"),
"---\nimport:\n dep: \"@dep\"\n---\n\n## main\n\n*1*\n",
"---\nimport:\n dep: \"@dep\"\n---\n\n## @exec main\n\n`return 1`\n",
);
assert_eq!(cli(root, &["lock"]).status.code(), Some(0));
let lock = std::fs::read_to_string(root.join("marqdo.lock")).unwrap();
@@ -362,10 +383,13 @@ fn tampered_path_dependency_content_is_rejected_by_locked_sync() {
&root.join("dep/marqdo.yaml"),
"project:\n name: dep\n version: 0.1.0\n",
);
write(&root.join("dep/index.mq.md"), "## value\n\n*1*\n");
write(
&root.join("dep/index.mq.md"),
"## @exec value\n\n`return 1`\n",
);
write(
&root.join("index.mq.md"),
"---\nimport:\n dep: \"@dep\"\n---\n\n## main\n\n*1*\n",
"---\nimport:\n dep: \"@dep\"\n---\n\n## @exec main\n\n`return 1`\n",
);
assert_eq!(cli(root, &["lock"]).status.code(), Some(0));
let lock_before = std::fs::read(root.join("marqdo.lock")).unwrap();
@@ -375,7 +399,10 @@ fn tampered_path_dependency_content_is_rejected_by_locked_sync() {
// Content change after the lock is a tamper/staleness signal. `run` and
// `check` must never silently accept it, re-lock, or materialize a new
// environment.
write(&root.join("dep/index.mq.md"), "## value\n\n*2*\n");
write(
&root.join("dep/index.mq.md"),
"## @exec value\n\n`return 2`\n",
);
for args in [
vec!["sync", "--locked"],
vec!["run", "index.mq.md"],
+2 -2
View File
@@ -112,7 +112,7 @@ fn write_manifest(dir: &Path, sha: &str) {
.unwrap();
std::fs::write(
dir.join("doc.mq.md"),
"## main\n\n**结果 = solver.add(a=20, b=22)**\n\n> 打印(结果)\n",
"## @exec main\n\n`结果 = solver.add(a=20, b=22)`\n\n`打印(结果)`\n",
)
.unwrap();
}
@@ -227,7 +227,7 @@ fn write_capability_manifest(dir: &Path, sha: &str) {
.unwrap();
std::fs::write(
dir.join("doc.mq.md"),
"## main\n\n**结果 = capability.read()**\n\n> 打印(结果)\n",
"## @exec main\n\n`结果 = capability.read()`\n\n`打印(结果)`\n",
)
.unwrap();
std::fs::create_dir_all(dir.join("data")).unwrap();
+3 -3
View File
@@ -44,7 +44,7 @@ fn print_is_routed_through_the_stdlib_and_not_hostop_print() {
write(
dir.path(),
"index.mq.md",
"## main\n\n> 打印([\"x\", 1])\n\n*None*\n",
"## @exec main\n\n`打印([\"x\", 1])`\n\n`return None`\n",
);
let trace = dir.path().join("trace.json");
let output = cli(
@@ -84,11 +84,11 @@ fn print_is_routed_through_the_stdlib_and_not_hostop_print() {
#[test]
fn stdlib_print_modules_are_injected_only_when_print_is_used() {
let dir = TempDir::new("lazy");
write(dir.path(), "plain.mq.md", "## main\n\n*1*\n");
write(dir.path(), "plain.mq.md", "## @exec main\n\n`return 1`\n");
write(
dir.path(),
"prints.mq.md",
"## main\n\n> 打印(1)\n\n*None*\n",
"## @exec main\n\n`打印(1)`\n\n`return None`\n",
);
for (file, expected_stdlib) in [("plain.mq.md", false), ("prints.mq.md", true)] {
let target = dir.path().join(format!("{file}.json"));
+75 -53
View File
@@ -29,39 +29,45 @@ struct Base {
const BASES: &[Base] = &[
Base {
name: "factorial",
source: r##"# 数学
source: r##"# @knowledge 数学
## 阶乘
## @exec 阶乘
计算阶乘的叙述一。
1. `n <= 1`
`if n <= 1`
递归终点叙述。
递归终点叙述。
*1*
`return 1`
2. `n > 1`
`else`
递归步骤叙述。
`if n > 1`
**结果 = n * 阶乘(n=n-1)**
递归步骤叙述。
*结果*
`结果 = n * 阶乘(n=n-1)`
`return 结果`
`end`
`end`
"##,
narration: &["计算阶乘的叙述一。", "递归终点叙述。", "递归步骤叙述。"],
},
Base {
name: "explicit-signature",
source: r##"## 圆面积
source: r##"## @exec 圆面积
`(r: Number)`
`params(r: Number)`
半径叙述。
*math.eval(ref("#公式"), {"r": r}, target="A")*
`return math.eval(ref("#公式"), {"r": r}, target="A")`
### 公式
### @knowledge 公式
$$
A = \pi r^2
@@ -71,117 +77,133 @@ $$
},
Base {
name: "countdown-loop",
source: r##"## 倒计时
source: r##"## @exec 倒计时
循环叙述。
**n = 3**
`n = 3`
- `n > 0`
`while n > 0`
循环体叙述。
循环体叙述。
> 打印(n)
`打印(n)`
**n = n - 1**
`n = n - 1`
*n*
`end`
`return n`
"##,
narration: &["循环叙述。", "循环体叙述。"],
},
Base {
name: "branch-classification",
source: r##"## 分类
source: r##"## @exec 分类
背景叙述。
**结果 = 0**
`结果 = 0`
1. `n < 0`
`if n < 0`
负数分支叙述。
负数分支叙述。
**结果 = -1**
`结果 = -1`
2. `n >= 0`
`else`
非负分支叙述。
`if n >= 0`
**结果 = 1**
非负分支叙述。
*结果*
`结果 = 1`
`end`
`end`
`return 结果`
"##,
narration: &["背景叙述。", "负数分支叙述。", "非负分支叙述。"],
},
Base {
name: "call-and-print",
source: r##"## 问候
source: r##"## @exec 问候
说明为什么这样写。
> 打印("你好")
`打印("你好")`
**问候 = "你好,Marqdo"**
`问候 = "你好,Marqdo"`
再补充一句叙述。
*问候*
`return 问候`
"##,
narration: &["说明为什么这样写。", "再补充一句叙述。"],
},
Base {
name: "inline-prose-in-executable-paragraph",
source: r##"## 加一
source: r##"## @exec 加一
这是行内叙述 **结果 = 1 + 1** 后面继续叙述。
*结果*
`return 结果`
"##,
narration: &["这是行内叙述 ", " 后面继续叙述。"],
},
Base {
name: "nested-control-flow",
source: r##"## 嵌套
source: r##"## @exec 嵌套
说明嵌套结构。
**total = 0**
`total = 0`
1. `n > 0`
`if n > 0`
**m = 3**
`m = 3`
- `m > 0`
`while m > 0`
**total = total + m**
`total = total + m`
**m = m - 1**
`m = m - 1`
2. `n <= 0`
`end`
**total = 0**
`else`
*total*
`if n <= 0`
`total = 0`
`end`
`end`
`return total`
"##,
narration: &["说明嵌套结构。"],
},
Base {
name: "two-namespaces",
source: r##"# 数学
source: r##"# @knowledge 数学
命名空间叙述。
## 平方
## @exec 平方
**结果 = n * n**
`结果 = n * n`
*结果*
`return 结果`
# 文本
# @knowledge 文本
## 长度
## @exec 长度
*长度(s)*
`return 长度(s)`
"##,
narration: &["命名空间叙述。"],
},
@@ -265,7 +287,7 @@ fn insert_prose_after_headings(source: &str) -> String {
while next < lines.len() && lines[next].trim().is_empty() {
next += 1;
}
let signature = next < lines.len() && lines[next].trim_start().starts_with("`(");
let signature = next < lines.len() && lines[next].trim_start().starts_with("`params(");
if signature {
while index + 1 < lines.len() && lines[index + 1].trim().is_empty() {
index += 1;
+80 -76
View File
@@ -56,21 +56,21 @@ fn write_file(path: &Path, contents: &str) {
std::fs::write(path, contents).unwrap();
}
const READER: &str = r#"## main
const READER: &str = r#"## @exec main
**内存 = memory.new(1, 1)**
`内存 = memory.new(1, 1)`
**流 = resource.open("file", "data.txt", ["read"])**
`流 = resource.open("file", "data.txt", ["read"])`
**第一次 = resource.read(流, 内存, 0, 2)**
`第一次 = resource.read(流, 内存, 0, 2)`
**第二次 = resource.read(流, 内存, 2, 4)**
`第二次 = resource.read(流, 内存, 2, 4)`
**第三次 = resource.read(流, 内存, 6, 1)**
`第三次 = resource.read(流, 内存, 6, 1)`
**关闭 = resource.close(流)**
`关闭 = resource.close(流)`
*[第一次.value.count, 第一次.value.eof, 第二次.value.count, 第二次.value.eof, 第三次.value.count, 第三次.value.eof, 内存[0], 内存[1], 内存[2], 内存[3], 内存[4], 内存[5], 关闭.ok]*
`return [第一次.value.count, 第一次.value.eof, 第二次.value.count, 第二次.value.eof, 第三次.value.count, 第三次.value.eof, 内存[0], 内存[1], 内存[2], 内存[3], 内存[4], 内存[5], 关闭.ok]`
"#;
#[test]
@@ -110,29 +110,29 @@ fn project_file_stream_reads_chunks_into_memory() {
assert_eq!(values[12]["value"], true);
}
const WRITER: &str = r#"## main
const WRITER: &str = r#"## @exec main
**内存 = memory.new(1, 1)**
`内存 = memory.new(1, 1)`
**`内存[0] = 65`**
`内存[0] = 65`
**`内存[1] = 66`**
`内存[1] = 66`
**`内存[2] = 67`**
`内存[2] = 67`
**写 = resource.open("file", "out.bin", ["write"])**
`写 = resource.open("file", "out.bin", ["write"])`
**写入 = resource.write(写, 内存, 0, 3)**
`写入 = resource.write(写, 内存, 0, 3)`
**关闭写 = resource.close(写)**
`关闭写 = resource.close(写)`
**读 = resource.open("file", "out.bin", ["read"])**
`读 = resource.open("file", "out.bin", ["read"])`
**读出 = resource.read(读, 内存, 0, 3)**
`读出 = resource.read(读, 内存, 0, 3)`
**关闭读 = resource.close(读)**
`关闭读 = resource.close(读)`
*[写入.value.count, 关闭写.ok, 读出.value.count, 读出.value.eof, 内存[0], 内存[1], 内存[2], 关闭读.ok]*
`return [写入.value.count, 关闭写.ok, 读出.value.count, 读出.value.eof, 内存[0], 内存[1], 内存[2], 关闭读.ok]`
"#;
#[test]
@@ -171,39 +171,43 @@ fn project_file_stream_writes_on_close_then_reads_back() {
assert_eq!(std::fs::read(dir.path().join("out.bin")).unwrap(), b"ABC");
}
const COPY: &str = r#"## main
const COPY: &str = r#"## @exec main
**输入 = resource.open("file", "data.txt", ["read"])**
`输入 = resource.open("file", "data.txt", ["read"])`
**输出 = resource.open("file", "out.bin", ["write"])**
`输出 = resource.open("file", "out.bin", ["write"])`
**内存 = memory.new(1, 1)**
`内存 = memory.new(1, 1)`
**总数 = 0**
`总数 = 0`
**继续 = true**
`继续 = true`
- `继续`
`while 继续`
**块 = resource.read(输入, 内存, 0, 16)**
`块 = resource.read(输入, 内存, 0, 16)`
1. `块.ok`
`if 块.ok`
> resource.write(输出, 内存, 0, 块.value.count)
`resource.write(输出, 内存, 0, 块.value.count)`
**总数 = 总数 + 块.value.count**
`总数 = 总数 + 块.value.count`
**继续 = not 块.value.eof**
`继续 = not 块.value.eof`
2. `true`
`else`
**继续 = false**
`继续 = false`
**关闭读 = resource.close(输入)**
`end`
**关闭写 = resource.close(输出)**
`end`
*[总数, 关闭读.ok, 关闭写.ok]*
`关闭读 = resource.close(输入)`
`关闭写 = resource.close(输出)`
`return [总数, 关闭读.ok, 关闭写.ok]`
"#;
#[test]
@@ -257,27 +261,27 @@ fn tcp_stream_round_trips_through_mqmd_with_a_network_grant() {
let dir = TempDir::new("tcp");
let program = format!(
r#"## main
r#"## @exec main
**内存 = memory.new(1, 1)**
`内存 = memory.new(1, 1)`
**`内存[0] = 112`**
`内存[0] = 112`
**`内存[1] = 105`**
`内存[1] = 105`
**`内存[2] = 110`**
`内存[2] = 110`
**`内存[3] = 103`**
`内存[3] = 103`
**流 = resource.open("tcp", "{address}", ["read", "write"])**
`流 = resource.open("tcp", "{address}", ["read", "write"])`
**写入 = resource.write(流, 内存, 0, 4)**
`写入 = resource.write(流, 内存, 0, 4)`
**读出 = resource.read(流, 内存, 0, 4)**
`读出 = resource.read(流, 内存, 0, 4)`
**关闭 = resource.close(流)**
`关闭 = resource.close(流)`
*[写入.value.count, 读出.value.count, 内存[0], 内存[1], 内存[2], 内存[3], 关闭.ok]*
`return [写入.value.count, 读出.value.count, 内存[0], 内存[1], 内存[2], 内存[3], 关闭.ok]`
"#
);
write_file(&dir.path().join("index.mq.md"), &program);
@@ -315,19 +319,19 @@ fn file_stream_requires_a_read_grant() {
assert_eq!(report["error"]["code"], "permission.denied");
}
const STDIN_READER: &str = r#"## main
const STDIN_READER: &str = r#"## @exec main
**输入 = resource.open("stdio", "stdin", ["read"])**
`输入 = resource.open("stdio", "stdin", ["read"])`
**内存 = memory.new(1, 1)**
`内存 = memory.new(1, 1)`
**第一 = resource.read(输入, 内存, 0, 2)**
`第一 = resource.read(输入, 内存, 0, 2)`
**第二 = resource.read(输入, 内存, 2, 8)**
`第二 = resource.read(输入, 内存, 2, 8)`
**第三 = resource.read(输入, 内存, 0, 1)**
`第三 = resource.read(输入, 内存, 0, 1)`
*[第一.value.count, 第一.value.eof, 第二.value.count, 第二.value.eof, 第三.value.eof, 内存[0], 内存[1], 内存[2], 内存[3]]*
`return [第一.value.count, 第一.value.eof, 第二.value.count, 第二.value.eof, 第三.value.eof, 内存[0], 内存[1], 内存[2], 内存[3]]`
"#;
#[test]
@@ -354,35 +358,35 @@ fn piped_stdin_is_chunked_and_reaches_eof() {
}
}
const STDERR_WRITER: &str = r#"## main
const STDERR_WRITER: &str = r#"## @exec main
**错误 = resource.open("stdio", "stderr", ["write"])**
`错误 = resource.open("stdio", "stderr", ["write"])`
**输出 = resource.open("stdio", "stdout", ["write"])**
`输出 = resource.open("stdio", "stdout", ["write"])`
**内存 = memory.new(1, 1)**
`内存 = memory.new(1, 1)`
**`内存[0] = 101`**
`内存[0] = 101`
**`内存[1] = 114`**
`内存[1] = 114`
**`内存[2] = 114`**
`内存[2] = 114`
**写错误 = resource.write(错误, 内存, 0, 3)**
`写错误 = resource.write(错误, 内存, 0, 3)`
**`内存[0] = 111`**
`内存[0] = 111`
**`内存[1] = 117`**
`内存[1] = 117`
**`内存[2] = 116`**
`内存[2] = 116`
**写输出 = resource.write(输出, 内存, 0, 3)**
`写输出 = resource.write(输出, 内存, 0, 3)`
**关闭错误 = resource.close(错误)**
`关闭错误 = resource.close(错误)`
**关闭输出 = resource.close(输出)**
`关闭输出 = resource.close(输出)`
*[写错误.value.count, 写输出.value.count, 关闭错误.ok, 关闭输出.ok]*
`return [写错误.value.count, 写输出.value.count, 关闭错误.ok, 关闭输出.ok]`
"#;
#[test]
@@ -412,17 +416,17 @@ import:
console: "std:io/console"
---
## main
## @exec main
**第一 = console.读取行()**
`第一 = console.读取行()`
**第二 = console.读取行()**
`第二 = console.读取行()`
**第三 = console.读取行()**
`第三 = console.读取行()`
**输出 = console.打印(第一.value + "|" + 第二.value)**
`输出 = console.打印(第一.value + "|" + 第二.value)`
*[第一.ok, 第二.ok, 第三.ok, 第三.code, 输出.ok]*
`return [第一.ok, 第二.ok, 第三.ok, 第三.code, 输出.ok]`
"#;
#[test]
+4 -4
View File
@@ -71,11 +71,11 @@ import:
io: "std:io"
---
## main
## @exec main
> io.写值(["bundle", 1, 2.5])
`io.写值(["bundle", 1, 2.5])`
*None*
`return None`
"#;
#[test]
@@ -154,7 +154,7 @@ fn tampered_bundle_is_rejected_before_module_loading() {
let dir = TempDir::new("tamper");
let bundle = dir.path().join("stdlib");
copy_stdlib(&stdlib_dir(), &bundle);
std::fs::write(bundle.join("io.mq.md"), "## tampered\n").unwrap();
std::fs::write(bundle.join("io.mq.md"), "## @knowledge tampered\n").unwrap();
write_project(dir.path(), IMPORT_IO);
let output = run(dir.path(), &bundle, &["run", "index.mq.md"]);
assert!(!output.status.success());
+74 -38
View File
@@ -57,25 +57,45 @@ pub fn analyze_source(module_id: &str, source: &str) -> AnalysisResult {
)
.with_hint("front matter must be valid YAML between `---` delimiters"),
),
Ok(_) => match frontmatter.imports() {
Ok(mapping) => {
for (alias, target) in mapping {
imports.push(ImportDecl {
alias,
target,
span: frontmatter.span,
});
Ok(_) => {
for key in ["marqdo_semantics", "syntax"] {
if frontmatter.has_key(key) {
diagnostics.push(
Diagnostic::error(
codes::SEM_UNSUPPORTED_VERSION_DIRECTIVE,
Some(frontmatter.yaml_span),
format!(
"`{key}` is not a syntax selector; there is one current syntax"
),
)
.with_hint(
"remove the directive and migrate the source to RFC-LANG-0002 syntax",
),
);
}
}
Err(error) => diagnostics.push(
Diagnostic::error(
codes::FRONTMATTER_INVALID,
Some(frontmatter.span),
format!("invalid import declaration: {error}"),
)
.with_hint("imports are an explicit mapping: `import: { alias: \"@module\" }`"),
),
},
match frontmatter.imports() {
Ok(mapping) => {
for (alias, target) in mapping {
imports.push(ImportDecl {
alias,
target,
span: frontmatter.span,
});
}
}
Err(error) => diagnostics.push(
Diagnostic::error(
codes::FRONTMATTER_INVALID,
Some(frontmatter.span),
format!("invalid import declaration: {error}"),
)
.with_hint(
"imports are an explicit mapping: `import: { alias: \"@module\" }`",
),
),
}
}
}
}
@@ -92,7 +112,7 @@ pub fn analyze_source(module_id: &str, source: &str) -> AnalysisResult {
let signature = signature::detect(&document, &blocks);
let explicit = signature.as_ref().map(|(_, sig)| sig);
let mut mapped = map::map_function(&document, &units, &imports, scope);
let mut mapped = map::map_function(&document, &units, scope);
diagnostics.append(&mut mapped.diagnostics);
let mut params: Vec<Param> = Vec::new();
@@ -104,7 +124,12 @@ pub fn analyze_source(module_id: &str, source: &str) -> AnalysisResult {
}
let inference = infer::infer(&mapped.stmts, explicit, &import_names);
diagnostics.extend(inference.diagnostics);
if kind == SignatureKind::Inferred {
if kind == SignatureKind::Inferred && !inference.params.is_empty() {
diagnostics.push(Diagnostic::warning(
codes::SEM_INFERRED_SIGNATURE,
Some(scope.heading_span),
"function signature was inferred; declare it with `params(...)`",
));
params = inference
.params
.into_iter()
@@ -157,19 +182,25 @@ mod tests {
#[test]
fn maps_recursive_factorial() {
let source = r#"# 数学
let source = r#"# @knowledge 数学
## 阶乘
## @exec 阶乘
1. `n <= 1`
`if n <= 1`
*1*
`return 1`
2. `n > 1`
`else`
**结果 = n * 阶乘(n=n-1)**
`if n > 1`
*结果*
`结果 = n * 阶乘(n=n-1)`
`return 结果`
`end`
`end`
"#;
let result = analyze(source);
assert!(
@@ -186,17 +217,19 @@ mod tests {
#[test]
fn maps_countdown_loop() {
let source = r#"## 倒计时
let source = r#"## @exec 倒计时
**n = 3**
`n = 3`
- `n > 0`
`while n > 0`
> 打印(n)
`打印(n)`
**n = n - 1**
`n = n - 1`
*n*
`end`
`return n`
"#;
let result = analyze(source);
assert!(!result.has_errors(), "{:#?}", result.diagnostics);
@@ -207,22 +240,24 @@ mod tests {
#[test]
fn invalid_strong_payload_is_a_hard_error() {
let result = analyze("## f\n\n**a *b* c**\n");
let result = analyze("## @exec f\n\n**a *b* c**\n");
assert!(result.has_errors());
assert!(result
.diagnostics
.iter()
.any(|d| d.code == codes::MARKDOWN_INVALID_CONSTRUCT));
.any(|d| d.code == "sem.payload_nested"));
}
#[test]
fn invalid_list_header_is_a_hard_error() {
let result = analyze("## f\n\n1. 没有条件\n");
// RFC-LANG-0002: a plain list is inert Markdown; the v2 negative is an
// unclosed control frame inside the owning Exec H2.
let result = analyze("## @exec f\n\n`if 1`\n");
assert!(result.has_errors());
assert!(result
.diagnostics
.iter()
.any(|d| d.code == codes::MARKDOWN_INVALID_CONSTRUCT));
.any(|d| d.code == "sem.unclosed_control"));
}
/// Strip source spans so that pure narrative edits (which shift byte
@@ -252,8 +287,9 @@ mod tests {
#[test]
fn prose_changes_do_not_change_ir() {
let base = "## f\n\n说明文字。\n\n**x = 1**\n\n更多说明。\n\n*x*\n";
let edited = "## f\n\n另一段完全不同的叙述。\n\n**x = 1**\n\n继续叙述。\n\n*x*\n";
let base = "## @exec f\n\n说明文字。\n\n`x = 1`\n\n更多说明。\n\n`return x`\n";
let edited =
"## @exec f\n\n另一段完全不同的叙述。\n\n`x = 1`\n\n继续叙述。\n\n`return x`\n";
let a = analyze(base);
let b = analyze(edited);
let a_ir = serde_json::to_value(&a.module.functions).unwrap();
+418 -458
View File
@@ -5,10 +5,8 @@
//! parsed only after the role is known. Invalid executable shapes produce hard
//! diagnostics and never fall back to prose.
use marqdo_expression::{
parse_arguments, parse_expression, parse_statement, Arg, AssignTarget, Expr, StatementKind,
};
use marqdo_ir::{CallSite, CallTarget, ImportDecl, PlaceTarget, Stmt};
use marqdo_expression::{parse_expression, parse_statement, AssignTarget, Expr, StatementKind};
use marqdo_ir::{PlaceTarget, Stmt};
use marqdo_markdown::{normalize_name, MarkdownDocument, MdKind, MdNode};
use marqdo_span::Span;
use marqdo_value::{codes, Diagnostic};
@@ -29,30 +27,74 @@ pub struct MappedBody {
pub fn map_function(
doc: &MarkdownDocument,
index: &UnitIndex,
imports: &[ImportDecl],
scope: &FunctionScope,
) -> MappedBody {
let mut mapper = Mapper {
index,
imports,
diagnostics: Vec::new(),
saw_params: None,
};
let blocks = &doc.root.children[scope.body_start..scope.body_end];
let stmts = mapper.blocks(blocks);
let mut stmts = Vec::new();
let mut segment = Vec::new();
let mut mode = crate::units::SemanticMode::Exec;
for (node_index, block) in doc.root.children.iter().enumerate() {
if node_index < scope.body_start || node_index >= scope.body_end {
continue;
}
if let MdKind::Heading { .. } = block.kind {
if mode == crate::units::SemanticMode::Exec {
stmts.extend(mapper.blocks(&segment));
}
segment.clear();
if let Some(heading) = index.headings.iter().find(|h| h.node_index == node_index) {
mode = heading.mode;
}
continue;
}
if mode == crate::units::SemanticMode::Exec {
segment.push(block.clone());
}
}
if mode == crate::units::SemanticMode::Exec {
stmts.extend(mapper.blocks(&segment));
}
MappedBody {
stmts,
diagnostics: mapper.diagnostics,
}
}
struct Mapper<'a> {
index: &'a UnitIndex,
#[allow(dead_code)]
imports: &'a [ImportDecl],
struct Mapper {
diagnostics: Vec<Diagnostic>,
saw_params: Option<Span>,
}
impl<'a> Mapper<'a> {
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
enum Stop {
End,
Else,
Eof,
}
enum Payload {
If(Expr),
Else,
While(Expr),
End,
Return(Expr),
Params,
Statement(marqdo_expression::Statement),
}
struct RawPayload {
payload: Payload,
span: Span,
segments: PayloadSegments,
/// True only for a carrier in the heading's direct body, not inside a
/// list or block quote (`params` is legal only there).
direct: bool,
}
impl Mapper {
fn error(&mut self, code: &str, span: Option<Span>, message: impl Into<String>) {
self.diagnostics
.push(Diagnostic::error(code, span, message));
@@ -70,468 +112,386 @@ impl<'a> Mapper<'a> {
}
fn blocks(&mut self, blocks: &[MdNode]) -> Vec<Stmt> {
let mut stmts = Vec::new();
let mut raw = Vec::new();
for block in blocks {
stmts.extend(self.block(block));
self.extract(block, &mut raw, true);
}
let mut position = 0;
let (stmts, stop) = self.sequence(&raw, &mut position, false, false);
if stop != Stop::Eof {
self.error(
codes::SEM_UNMATCHED_END,
raw.get(position.saturating_sub(1)).map(|node| node.span),
"control frame ends outside its owning function segment",
);
}
stmts
}
fn block(&mut self, block: &MdNode) -> Vec<Stmt> {
match &block.kind {
MdKind::Paragraph => self.paragraph(block),
MdKind::List { ordered, .. } => self.list(block, *ordered),
MdKind::BlockQuote => self.quote(block),
// Level>=3 headings and inert document values stay out of the IR.
_ => Vec::new(),
}
}
fn paragraph(&mut self, paragraph: &MdNode) -> Vec<Stmt> {
let mut stmts = Vec::new();
for child in &paragraph.children {
match &child.kind {
MdKind::Strong => {
if let Some(stmt) = self.exec_statement(child) {
stmts.push(stmt);
fn extract(&mut self, node: &MdNode, out: &mut Vec<RawPayload>, direct: bool) {
match &node.kind {
MdKind::Paragraph => {
for child in &node.children {
self.extract(child, out, direct);
}
}
MdKind::BlockQuote | MdKind::Item { .. } | MdKind::List { .. } => {
for child in &node.children {
self.extract(child, out, false);
}
}
MdKind::Strong | MdKind::Emph => {
let (text, segments) = match PayloadSegments::of(node) {
Ok(result) => result,
Err(error) => {
self.error(
codes::SEM_PAYLOAD_NESTED,
Some(error.span),
format!("invalid payload carrier: {}", error.reason),
);
return;
}
}
MdKind::Emph => {
if let Some(stmt) = self.return_statement(child) {
stmts.push(stmt);
}
}
// Lazy/inert inline structures: never recurse into them.
MdKind::Link { .. }
| MdKind::Image { .. }
| MdKind::Strikethrough
| MdKind::Code { .. }
| MdKind::Math { .. }
| MdKind::Text
| MdKind::SoftBreak
| MdKind::LineBreak
| MdKind::HtmlInline
| MdKind::FootnoteReference { .. } => {}
_ => {}
};
self.push(text, node.span, segments, out, direct);
}
MdKind::Code { ticks } => {
let literal = node.literal.as_deref().unwrap_or_default();
let inner = Span::new(
node.span.start.saturating_add(*ticks),
node.span.end.saturating_sub(*ticks),
);
self.push(
literal.to_string(),
node.span,
PayloadSegments::single(literal, inner),
out,
direct,
);
}
MdKind::Heading { .. } => {}
_ => {}
}
stmts
}
fn exec_statement(&mut self, node: &MdNode) -> Option<Stmt> {
let (payload, segments) = match PayloadSegments::of(node) {
Ok(result) => result,
Err(error) => {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(error.span),
error.reason,
"keep the executable payload as plain text or a single code span",
);
return None;
}
};
if payload.trim().is_empty() {
fn push(
&mut self,
text: String,
span: Span,
segments: PayloadSegments,
out: &mut Vec<RawPayload>,
direct: bool,
) {
if text.trim().is_empty() {
self.error(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(node.span),
"execution statement has an empty payload",
codes::SEM_EMPTY_PAYLOAD,
Some(span),
"executable payload is empty",
);
return None;
return;
}
match parse_statement(&payload) {
Ok(mut statement) => {
segments.rewrite_statement(&mut statement);
Some(match statement.kind {
StatementKind::Assign { target, value } => Stmt::Assign {
target: match target {
AssignTarget::Local { name, name_span } => {
PlaceTarget::Local { name, name_span }
}
AssignTarget::Index {
base,
index,
span: target_span,
} => PlaceTarget::Index {
base: *base,
index: *index,
span: target_span,
},
},
value,
span: node.span,
},
StatementKind::Expr(expr) => Stmt::Eval {
expr,
span: node.span,
},
})
if let Some(mut payload) = self.parse_payload(&text, span, &segments) {
if let Payload::If(expr) | Payload::While(expr) | Payload::Return(expr) = &mut payload {
segments.rewrite_expr(expr);
}
Err(error) => {
self.error_with_hint(
codes::EXPR_PARSE,
Some(segments.map_span(error.span)),
format!("invalid execution statement: {}", error.message),
"statements are `name = expression` or an expression; put the payload in a code span when Markdown emphasis conflicts",
);
None
}
}
}
fn return_statement(&mut self, node: &MdNode) -> Option<Stmt> {
let (payload, segments) = match PayloadSegments::of(node) {
Ok(result) => result,
Err(error) => {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(error.span),
error.reason,
"a return payload must be plain text or a single code span",
);
return None;
}
};
if payload.trim().is_empty() {
self.error(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(node.span),
"return statement has an empty payload",
);
return None;
}
match parse_expression(&payload) {
Ok(mut expr) => {
segments.rewrite_expr(&mut expr);
Some(Stmt::Return {
value: expr,
span: node.span,
})
}
Err(error) => {
self.error_with_hint(
codes::EXPR_PARSE,
Some(segments.map_span(error.span)),
format!("invalid return expression: {}", error.message),
"`*表达式*` returns the value of the expression",
);
None
}
}
}
fn list(&mut self, list: &MdNode, ordered: bool) -> Vec<Stmt> {
if list.children.is_empty() {
self.error(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(list.span),
"list in an executable position has no items",
);
return Vec::new();
}
let mut arms = Vec::new();
let mut loops = Vec::new();
for item in &list.children {
let Some((condition, condition_span, body_blocks)) = self.condition_of(item) else {
continue;
};
let body = self.blocks(body_blocks);
if ordered {
arms.push(marqdo_ir::BranchArm {
condition,
condition_span,
body,
span: item.span,
});
} else {
loops.push(Stmt::Loop {
condition,
condition_span,
body,
span: item.span,
});
}
}
if ordered {
if arms.is_empty() {
return Vec::new();
}
vec![Stmt::Branch {
arms,
span: list.span,
}]
} else {
loops
}
}
/// Extract the condition header of a list item and its remaining blocks.
fn condition_of<'b>(&mut self, item: &'b MdNode) -> Option<(Expr, Span, &'b [MdNode])> {
let Some(first) = item.children.first() else {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(item.span),
"list item in an executable position must start with a condition code span",
"write the condition first: `` `n > 0` ``",
);
return None;
};
if !matches!(first.kind, MdKind::Paragraph) {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(first.span),
"list item must start with a paragraph containing the condition code span",
"put the condition on the first line of the item",
);
return None;
}
let Some(condition_node) = first.children.first() else {
self.error(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(first.span),
"list item paragraph is empty; a condition code span is required",
);
return None;
};
if !matches!(condition_node.kind, MdKind::Code { .. }) {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(condition_node.span),
"list item must start with a condition inside an inline code span",
"the condition is a `Code` span: `` `n > 0` ``; other text is description",
);
return None;
}
// The remainder of the condition paragraph is description only. The
// semantic mapper does not descend into it, so an executable `Strong`
// or `Emph` there would otherwise be silently swallowed. Reject it as
// a hard shape error instead of guessing the author's intent.
for tail in first.children.iter().skip(1) {
if matches!(tail.kind, MdKind::Strong | MdKind::Emph) {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(tail.span),
format!(
"`{}` inside a list-item condition paragraph is not executed and cannot be silently ignored",
tail.kind.tag()
),
"put executable statements in their own paragraph after the condition line",
);
return None;
}
}
let literal = condition_node.literal.clone().unwrap_or_default();
// `condition_node.span` includes the backtick delimiters. The payload
// map must start at the first literal byte so parse diagnostics and
// expression spans point at the expression, not at a delimiter.
let ticks = match condition_node.kind {
MdKind::Code { ticks } => ticks,
_ => 0,
};
let literal_span = Span::new(
condition_node.span.start.saturating_add(ticks),
condition_node.span.end.saturating_sub(ticks),
);
let segments = PayloadSegments::single(&literal, literal_span);
match parse_expression(&literal) {
Ok(mut expr) => {
segments.rewrite_expr(&mut expr);
Some((expr, condition_node.span, &item.children[1..]))
}
Err(error) => {
self.error_with_hint(
codes::EXPR_PARSE,
Some(segments.map_span(error.span)),
format!("invalid condition expression: {}", error.message),
"conditions are Boolean expressions, e.g. `n > 0`",
);
None
}
}
}
fn quote(&mut self, quote: &MdNode) -> Vec<Stmt> {
if quote.children.len() != 1 || quote.children[0].kind != MdKind::Paragraph {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(quote.span),
"a block quote invocation must contain exactly one paragraph",
"use one block quote per call; prose belongs in normal paragraphs",
);
return Vec::new();
}
let paragraph = &quote.children[0];
self.call_paragraph(quote, paragraph)
}
fn call_paragraph(&mut self, quote: &MdNode, paragraph: &MdNode) -> Vec<Stmt> {
let first = paragraph.children.first();
let is_link_form = first
.map(|node| matches!(node.kind, MdKind::Link { .. }))
.unwrap_or(false);
if is_link_form {
return self.link_call(quote, paragraph);
}
let (payload, segments) = match PayloadSegments::of(paragraph) {
Ok(result) => result,
Err(error) => {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(error.span),
error.reason,
"a block quote call payload must be plain text or one code span",
);
return Vec::new();
}
};
if payload.trim().is_empty() {
self.error(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(quote.span),
"block quote invocation has an empty payload",
);
return Vec::new();
}
match parse_expression(&payload) {
Ok(mut expr) => {
segments.rewrite_expr(&mut expr);
if !matches!(expr, Expr::Call { .. }) {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(segments.map_span(expr_span(&expr))),
"a block quote must be a complete function call",
"write `> 函数(参数)`; use a `**strong**` statement to bind a result",
);
return Vec::new();
}
vec![Stmt::Eval {
expr,
span: quote.span,
}]
}
Err(error) => {
self.error_with_hint(
codes::EXPR_PARSE,
Some(segments.map_span(error.span)),
format!("invalid call expression: {}", error.message),
"block quotes call functions explicitly: `> 函数(参数)`",
);
Vec::new()
}
}
}
fn link_call(&mut self, quote: &MdNode, paragraph: &MdNode) -> Vec<Stmt> {
let link = &paragraph.children[0];
let (url, link_span) = match &link.kind {
MdKind::Link { url, .. } => (url.clone(), link.span),
_ => unreachable!("link form checked by caller"),
};
let target = self.resolve_link_target(&url, link_span);
let rest = &paragraph.children[1..];
let (suffix, segments) = match PayloadSegments::from_children(rest) {
Ok(result) => result,
Err(error) => {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(error.span),
error.reason,
"link call arguments must follow the link as plain text or code spans",
);
return Vec::new();
}
};
if suffix.trim().is_empty() {
self.error_with_hint(
codes::MARKDOWN_INVALID_CONSTRUCT,
Some(quote.span),
"link-form call requires an explicit argument list",
"write `> [函数](#函数)()` even for zero arguments",
);
return Vec::new();
}
let mut args: Vec<Arg> = match parse_arguments(&suffix) {
Ok(args) => args,
Err(error) => {
self.error_with_hint(
codes::EXPR_PARSE,
Some(segments.map_span(error.span)),
format!("invalid call arguments: {}", error.message),
"arguments are `name = value` or positional values",
);
return Vec::new();
}
};
segments.rewrite_args(&mut args);
let Some(target) = target else {
return Vec::new();
};
vec![Stmt::Call {
call: CallSite {
target,
args,
span: quote.span,
},
span: quote.span,
}]
}
fn resolve_link_target(&mut self, url: &str, span: Span) -> Option<CallTarget> {
if let Some(fragment) = url.strip_prefix('#') {
let unit_id = self.index.anchors.get(fragment).cloned().or_else(|| {
self.index
.units
.iter()
.find(|unit| unit.name == fragment)
.map(|unit| unit.id.clone())
out.push(RawPayload {
payload,
span,
segments,
direct,
});
let Some(unit_id) = unit_id else {
self.error(
codes::REF_UNRESOLVED,
Some(span),
format!("no heading matches call target `{url}`"),
);
return None;
};
let Some(scope) = self
.index
.functions
.iter()
.find(|scope| scope.unit == unit_id)
else {
self.error(
codes::REF_UNRESOLVED,
Some(span),
format!("call target `{url}` is not a function"),
);
return None;
};
Some(CallTarget::Resolved {
module: unit_id.module.clone(),
function: scope.id.name.clone(),
})
} else if url.starts_with("http://") || url.starts_with("https://") {
self.error_with_hint(
codes::REF_UNRESOLVED,
Some(span),
"external links cannot be called",
"link targets used as calls must resolve to a Marqdo function",
);
None
} else {
self.error_with_hint(
codes::MODULE_UNRESOLVED,
Some(span),
format!("cannot resolve cross-module call target `{url}`"),
"import the module explicitly in front matter and call it through the alias",
);
None
}
}
}
fn expr_span(expr: &Expr) -> Span {
marqdo_expression::Expr::span(expr)
fn parse_payload(
&mut self,
text: &str,
span: Span,
segments: &PayloadSegments,
) -> Option<Payload> {
let map = |span: Span| segments.map_span(span);
let text = text.trim();
if text.starts_with("params(") {
// Signature syntax and diagnostics are owned by `signature::parse`;
// the mapper only recognizes the declaration payload.
return Some(Payload::Params);
}
if text == "params" || text.starts_with("params ") {
self.error(
codes::SEM_SYNTAX,
Some(span),
"malformed params declaration; write `params(name: Type, ...)`",
);
return None;
}
let (word, rest) = match text.split_once(char::is_whitespace) {
Some((word, rest)) => (word, rest.trim()),
None => (text, ""),
};
// Parse control expressions with the keyword replaced by spaces so the
// expression AST keeps payload-relative (not rest-relative) spans.
let expression_at = |rest: &str| {
let offset = text.len().saturating_sub(rest.len());
parse_expression(&format!("{}{}", " ".repeat(offset), rest))
};
match word {
"if" => {
if rest.is_empty() {
self.error(codes::SEM_SYNTAX, Some(span), "`if` requires a condition");
return None;
}
match expression_at(rest) {
Ok(expr) => Some(Payload::If(expr)),
Err(error) => {
self.error(
codes::SEM_SYNTAX,
Some(map(error.span)),
format!("invalid if condition: {}", error.message),
);
None
}
}
}
"else" if rest.is_empty() => Some(Payload::Else),
"else" => {
self.error(codes::SEM_SYNTAX, Some(span), "`else` takes no expression");
None
}
"while" => {
if rest.is_empty() {
self.error(
codes::SEM_SYNTAX,
Some(span),
"`while` requires a condition",
);
return None;
}
match expression_at(rest) {
Ok(expr) => Some(Payload::While(expr)),
Err(error) => {
self.error(
codes::SEM_SYNTAX,
Some(map(error.span)),
format!("invalid while condition: {}", error.message),
);
None
}
}
}
"end" if rest.is_empty() => Some(Payload::End),
"end" => {
self.error(codes::SEM_SYNTAX, Some(span), "`end` takes no expression");
None
}
"return" => {
if rest.is_empty() {
self.error(
codes::SEM_SYNTAX,
Some(span),
"`return` requires an expression",
);
return None;
}
match expression_at(rest) {
Ok(expr) => Some(Payload::Return(expr)),
Err(error) => {
self.error(
codes::SEM_SYNTAX,
Some(map(error.span)),
format!("invalid return expression: {}", error.message),
);
None
}
}
}
"params" => {
if text.starts_with("params(") && text.ends_with(')') {
Some(Payload::Params)
} else {
self.error(
codes::SEM_SYNTAX,
Some(span),
"malformed params declaration",
);
None
}
}
"ifdef" | "returning" | "paramsx" => self.statement_payload(text, span),
_ => self.statement_payload(text, span),
}
}
fn statement_payload(&mut self, text: &str, span: Span) -> Option<Payload> {
match parse_statement(text) {
Ok(statement) => Some(Payload::Statement(statement)),
Err(error) => {
self.error_with_hint(
codes::SEM_SYNTAX,
Some(span),
format!("invalid execution payload: {}", error.message),
"one payload is exactly one statement; put control keywords in their own carriers",
);
None
}
}
}
fn sequence(
&mut self,
nodes: &[RawPayload],
position: &mut usize,
stop_on_else: bool,
in_else_body: bool,
) -> (Vec<Stmt>, Stop) {
let mut out = Vec::new();
while *position < nodes.len() {
let raw = &nodes[*position];
match &raw.payload {
Payload::Else => {
if stop_on_else {
return (out, Stop::Else);
}
self.error(
if in_else_body {
codes::SEM_DUPLICATE_ELSE
} else {
codes::SEM_UNMATCHED_ELSE
},
Some(raw.span),
if in_else_body {
"`if` has more than one `else`"
} else {
"`else` has no open `if`"
},
);
*position += 1;
}
Payload::End => {
return (out, Stop::End);
}
Payload::If(condition) => {
let condition = condition.clone();
let span = raw.span;
*position += 1;
let (then_body, stop) = self.sequence(nodes, position, true, false);
let mut else_body = Vec::new();
let finish = match stop {
Stop::Else => {
*position += 1;
let (body, stop) = self.sequence(nodes, position, false, true);
else_body = body;
stop
}
other => other,
};
if finish != Stop::End {
self.error(
codes::SEM_UNCLOSED_CONTROL,
Some(span),
"`if` is not closed by `end`",
);
} else {
*position += 1;
}
let mut arms = vec![marqdo_ir::BranchArm {
condition,
condition_span: span,
body: then_body,
span,
}];
if !else_body.is_empty() {
arms.push(marqdo_ir::BranchArm {
condition: Expr::Bool(true),
condition_span: span,
body: else_body,
span,
});
}
out.push(Stmt::Branch { arms, span });
}
Payload::While(condition) => {
let condition = condition.clone();
let span = raw.span;
*position += 1;
let (body, stop) = self.sequence(nodes, position, false, false);
if stop != Stop::End {
self.error(
codes::SEM_UNCLOSED_CONTROL,
Some(span),
"`while` is not closed by `end`",
);
} else {
*position += 1;
}
out.push(Stmt::Loop {
condition,
condition_span: span,
body,
span,
});
}
Payload::Return(value) => {
out.push(Stmt::Return {
value: value.clone(),
span: raw.span,
});
*position += 1;
}
Payload::Params => {
let duplicate = self.saw_params.is_some();
if !raw.direct {
self.error(
codes::SEM_SIGNATURE_POSITION,
Some(raw.span),
"`params(...)` must be a direct payload, not inside a list or block quote",
);
} else if *position != 0 {
self.error(
codes::SEM_SIGNATURE_POSITION,
Some(raw.span),
"`params(...)` must be the first payload of an Exec H2",
);
} else if duplicate {
self.error(
codes::SEM_SIGNATURE_POSITION,
Some(raw.span),
"`params(...)` may be declared only once per function",
);
} else {
self.saw_params = Some(raw.span);
}
*position += 1;
}
Payload::Statement(statement) => {
let mut statement = statement.clone();
raw.segments.rewrite_statement(&mut statement);
let span = raw.span;
match statement.kind {
StatementKind::Assign { target, value } => out.push(Stmt::Assign {
target: match target {
AssignTarget::Local { name, name_span } => {
PlaceTarget::Local { name, name_span }
}
AssignTarget::Index {
base,
index,
span: target_span,
} => PlaceTarget::Index {
base: *base,
index: *index,
span: target_span,
},
},
value,
span,
}),
StatementKind::Expr(expr) => out.push(Stmt::Eval { expr, span }),
}
*position += 1;
}
}
}
(out, Stop::Eof)
}
}
/// Normalise a heading name (re-exported for callers that resolve link targets).
+21 -16
View File
@@ -311,40 +311,42 @@ mod extra_span_tests {
#[test]
fn condition_literal_span_excludes_backticks_for_one_and_two_ticks() {
for source in ["## f\n\n1. `n ** 2 ==`\n", "## f\n\n1. ``n ** 2 ==``\n"] {
for source in [
"## @exec f\n\n`if n ** 2 ==`\n",
"## @exec f\n\n``if n ** 2 ==``\n",
] {
let result = crate::analyze_source("index.mq.md", source);
let diagnostic = result
.diagnostics
.iter()
.find(|diagnostic| diagnostic.code == marqdo_value::codes::EXPR_PARSE)
.unwrap_or_else(|| panic!("no expr.parse diagnostic for {source:?}"));
.find(|diagnostic| diagnostic.code == marqdo_value::codes::SEM_SYNTAX)
.unwrap_or_else(|| panic!("no sem.syntax diagnostic for {source:?}"));
let span = diagnostic
.span
.expect("condition parse error has a source span");
assert_eq!(
source.as_bytes()[span.start],
b'`',
"span must stop before the closing backtick: {span:?} in {source:?}"
);
assert_eq!(
&source[span.start.saturating_sub(2)..span.start],
"==",
"span must point at the missing operand"
let condition = source.find("n ** 2 ==").expect("condition text");
let closing = source.rfind('`').expect("closing backtick");
assert!(
span.start >= condition && span.end <= closing,
"span must point inside the carrier payload, before the closing backtick: {span:?} in {source:?}"
);
}
}
#[test]
fn condition_description_rejects_executable_roles() {
// RFC-LANG-0002 no longer rejects Strong/Emph next to a code span:
// every carrier is an independent statement. The preserved intent is
// that a malformed control sequence after `if` is a hard error; it is
// repurposed as an unclosed-control negative.
for tail in ["**print(1)**", "*1*"] {
let source = format!("## f\n\n1. `n > 0` {tail}\n\n > print(1)\n");
let source = format!("## @exec f\n\n`if n > 0` {tail}\n");
let result = crate::analyze_source("index.mq.md", &source);
assert!(
result
.diagnostics
.iter()
.any(|diagnostic| diagnostic.code
== marqdo_value::codes::MARKDOWN_INVALID_CONSTRUCT),
.any(|diagnostic| diagnostic.code == "sem.unclosed_control"),
"executable tail `{tail}` was not rejected: {:#?}",
result.diagnostics
);
@@ -353,7 +355,10 @@ mod extra_span_tests {
#[test]
fn condition_description_allows_inert_inline_content() {
let source = "## f\n\n**n = 1**\n\n1. `n > 0` 普通说明、`惰性代码` 与 [链接](#f)。\n\n > print(1)\n";
// Inline code spans are payload carriers in Exec scope, so the old inert
// `惰性代码` example is now a statement; prose, a link and a carrier-free
// block quote remain inert and must not be rejected.
let source = "## @exec f\n\n`n = 1`\n\n1. `n > 0` 普通说明与 [链接](#f)。\n\n > print(1)\n\n`return n`\n";
let result = crate::analyze_source("index.mq.md", source);
assert!(
!result.has_errors(),
+1 -1
View File
@@ -121,7 +121,7 @@ mod tests {
#[test]
fn formulas_and_code_are_attributed_to_functions() {
let resources = resources_of(
"# ns\n\n## f\n\n$$A = pi r^2$$\n\n```python\nprint(1)\n```\n\n## g\n\n$$B = 1$$\n",
"# @knowledge ns\n\n## @exec f\n\n$$A = pi r^2$$\n\n```python\nprint(1)\n```\n\n## @exec g\n\n$$B = 1$$\n",
);
assert_eq!(resources.len(), 3);
let Resource::Formula { unit, latex, .. } = &resources[0] else {
+60 -36
View File
@@ -42,37 +42,41 @@ pub fn detect(_doc: &MarkdownDocument, blocks: &[&MdNode]) -> Option<(usize, Sig
match &block.kind {
MdKind::Heading { level, .. } if *level >= 3 => continue,
MdKind::Paragraph => {
let is_candidate = block.children.len() == 1
&& matches!(block.children[0].kind, MdKind::Code { .. })
&& block.children[0]
.literal
.as_deref()
.map(|text| text.trim_start().starts_with('('))
.unwrap_or(false);
if !is_candidate {
if block.children.len() != 1 {
continue;
}
let carrier = &block.children[0];
let (source, span, segments) = match &carrier.kind {
MdKind::Code { ticks } => {
let literal = carrier.literal.clone().unwrap_or_default();
let inner = Span::new(
carrier.span.start.saturating_add(*ticks),
carrier.span.end.saturating_sub(*ticks),
);
(
literal.clone(),
carrier.span,
PayloadSegments::single(&literal, inner),
)
}
MdKind::Strong | MdKind::Emph => match PayloadSegments::of(carrier) {
Ok((source, segments)) => (source, carrier.span, segments),
Err(_) => continue,
},
_ => continue,
};
if !source.trim_start().starts_with("params(") {
return None;
}
let code = &block.children[0];
let source = code.literal.clone().unwrap_or_default();
let mut signature = parse(&source, code.span);
// Rewrite parameter default expression spans onto the file.
let segments = PayloadSegments::of(&MdNode {
kind: MdKind::Strong,
span: code.span,
literal: None,
children: vec![code.clone()],
})
.ok()
.map(|(_, segments)| segments);
if let Some(segments) = segments {
for param in &mut signature.params {
if let Some(default) = &mut param.default {
segments.rewrite_expr(default);
}
let mut signature = parse(&source, span);
for param in &mut signature.params {
if let Some(default) = &mut param.default {
segments.rewrite_expr(default);
}
}
return Some((index, signature));
}
MdKind::List { .. } | MdKind::BlockQuote | MdKind::Item { .. } => continue,
_ => return None,
}
}
@@ -83,13 +87,33 @@ pub fn detect(_doc: &MarkdownDocument, blocks: &[&MdNode]) -> Option<(usize, Sig
pub fn parse(source: &str, span: Span) -> Signature {
let mut diagnostics = Vec::new();
let trimmed = source.trim();
let inner = if let Some(rest) = trimmed.strip_prefix('(') {
let is_params = trimmed.starts_with("params(");
let syntax_code = if is_params {
codes::SEM_SYNTAX
} else {
codes::EXPR_PARSE
};
let inner = if let Some(rest) = trimmed.strip_prefix("params(") {
match rest.strip_suffix(')') {
Some(inner) => inner,
None => {
diagnostics.push(Diagnostic::error(
codes::SEM_SYNTAX,
Some(span),
"function signature must be closed by `)`",
));
rest
}
}
} else if let Some(rest) = trimmed.strip_prefix('(') {
// Plugin/ABI descriptors keep their existing parenthesised signature
// spelling; language payloads are detected only as `params(...)`.
rest.strip_suffix(')').unwrap_or(rest)
} else {
diagnostics.push(Diagnostic::error(
codes::EXPR_PARSE,
syntax_code,
Some(span),
"function signature must be parenthesised, e.g. `(r: Number)`",
"function signature must be `params(...)`, e.g. `params(r: Number)`",
));
trimmed
};
@@ -102,7 +126,7 @@ pub fn parse(source: &str, span: Span) -> Signature {
if entry.trim().is_empty() {
if !inner.trim().is_empty() {
diagnostics.push(Diagnostic::error(
codes::EXPR_PARSE,
syntax_code,
Some(span),
"empty parameter in function signature",
));
@@ -129,7 +153,7 @@ pub fn parse(source: &str, span: Span) -> Signature {
}
}
Err(message) => diagnostics.push(Diagnostic::error(
codes::EXPR_PARSE,
syntax_code,
Some(span),
format!("invalid function signature: {message}"),
)),
@@ -293,7 +317,7 @@ mod tests {
#[test]
fn parses_typed_signature_with_default() {
let signature = parse("(r: Number, precision: Int = 2)", Span::new(0, 38));
let signature = parse("params(r: Number, precision: Int = 2)", Span::new(0, 38));
assert!(!signature.has_errors(), "{:?}", signature.diagnostics);
assert_eq!(signature.params.len(), 2);
assert_eq!(signature.params[0].name, "r");
@@ -307,20 +331,20 @@ mod tests {
#[test]
fn parses_untyped_and_empty() {
let signature = parse("()", Span::new(0, 2));
let signature = parse("params()", Span::new(0, 8));
assert!(signature.params.is_empty());
assert!(!signature.has_errors());
let signature = parse("(n)", Span::new(0, 3));
let signature = parse("params(n)", Span::new(0, 9));
assert_eq!(signature.params[0].name, "n");
}
#[test]
fn rejects_duplicates_and_bad_defaults() {
let duplicate = parse("(a, a)", Span::new(0, 6));
let duplicate = parse("params(a, a)", Span::new(0, 12));
assert!(duplicate.has_errors());
let bad_default = parse("(a = f())", Span::new(0, 10));
let bad_default = parse("params(a = f())", Span::new(0, 16));
assert!(bad_default.has_errors());
let bad_name = parse("(1x)", Span::new(0, 4));
let bad_name = parse("params(1x)", Span::new(0, 10));
assert!(bad_name.has_errors());
}
+200 -101
View File
@@ -16,7 +16,7 @@
use std::collections::BTreeMap;
use marqdo_ir::{FunctionId, ModuleId, UnitId, UnitInfo, UnitKind};
use marqdo_markdown::{normalize_name, plain_text, MarkdownDocument, MdKind};
use marqdo_markdown::{normalize_name, plain_text, MarkdownDocument, MdKind, MdNode};
use marqdo_span::Span;
use marqdo_value::{codes, Diagnostic};
@@ -35,6 +35,8 @@ pub struct HeadingInfo {
pub path: Vec<String>,
/// Role derived from level and position.
pub kind: UnitKind,
/// Semantic mode declared or inherited by this heading.
pub mode: SemanticMode,
}
/// A function range mapped from a level-2 heading.
@@ -93,6 +95,91 @@ impl UnitIndex {
}
}
fn has_payload(node: &MdNode) -> bool {
match &node.kind {
MdKind::Strong | MdKind::Emph | MdKind::Code { .. } => true,
MdKind::Paragraph | MdKind::List { .. } | MdKind::Item { .. } | MdKind::BlockQuote => {
node.children.iter().any(has_payload)
}
_ => false,
}
}
/// Build the heading/function index for a parsed document.
/// Semantic mode declared or inherited by a heading (RFC-LANG-0002).
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub enum SemanticMode {
/// Document/knowledge region; no executable statements.
Knowledge,
/// Executable region; only an Exec H2 is callable.
Exec,
}
fn heading_declaration(
node: &MdNode,
) -> (Option<SemanticMode>, Option<String>, Option<Diagnostic>) {
let Some(first) = node.children.first() else {
return (None, None, None);
};
let MdKind::Text = first.kind else {
return (None, None, None);
};
let literal = first.literal.as_deref().unwrap_or_default();
let (mode, rest) = if let Some(rest) = literal.strip_prefix("@exec") {
if !rest.is_empty() && !rest.starts_with(char::is_whitespace) {
return (None, None, None);
}
(SemanticMode::Exec, rest)
} else if let Some(rest) = literal.strip_prefix("@knowledge") {
if !rest.is_empty() && !rest.starts_with(char::is_whitespace) {
return (None, None, None);
}
(SemanticMode::Knowledge, rest)
} else if literal.starts_with('@')
&& literal
.trim_start_matches('@')
.chars()
.next()
.is_some_and(char::is_alphabetic)
{
return (
None,
None,
Some(Diagnostic::error(
codes::SEM_INVALID_MODE_MARKER,
Some(first.span),
"unknown heading mode marker; use exactly `@exec` or `@knowledge`",
)),
);
} else {
return (None, None, None);
};
let title = rest.trim();
if title.is_empty() {
return (
Some(mode),
None,
Some(Diagnostic::error(
codes::SEM_EMPTY_UNIT_NAME,
Some(node.span),
"mode declaration has an empty heading name",
)),
);
}
if title.starts_with("@exec") || title.starts_with("@knowledge") {
return (
Some(mode),
None,
Some(Diagnostic::error(
codes::SEM_INVALID_MODE_MARKER,
Some(node.span),
"a heading may declare only one semantic mode",
)),
);
}
(Some(mode), Some(title.to_string()), None)
}
/// Build the heading/function index for a parsed document.
pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
let mut index = UnitIndex::default();
@@ -108,8 +195,8 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
function: None,
});
// Stack of (level, path) for ancestor headings with smaller level.
let mut stack: Vec<(u8, Vec<String>)> = Vec::new();
// Stack of (level, path, mode) for ancestors.
let mut stack: Vec<(u8, Vec<String>, SemanticMode)> = Vec::new();
let mut seen: BTreeMap<(Vec<String>, String), Span> = BTreeMap::new();
let mut current_namespace: Option<String> = None;
let mut current_function: Option<FunctionId> = None;
@@ -120,11 +207,26 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
continue;
};
let level = *level;
let raw_name = normalize_name(&plain_text(child));
let Some(name) = raw_name else {
let (declared, declared_name, declaration_error) = heading_declaration(child);
if let Some(error) = declaration_error {
index.diagnostics.push(error);
if declared_name.is_none() {
continue;
}
}
let inherited = stack
.last()
.map(|(_, _, mode)| *mode)
.unwrap_or(SemanticMode::Knowledge);
let mode = declared.unwrap_or(inherited);
let raw_name = match declared_name {
Some(name) => name,
None => plain_text(child),
};
let Some(name) = normalize_name(&raw_name) else {
index.diagnostics.push(
Diagnostic::error(
codes::MARKDOWN_INVALID_CONSTRUCT,
codes::SEM_EMPTY_UNIT_NAME,
Some(child.span),
"heading name must not be empty",
)
@@ -133,7 +235,7 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
continue;
};
while let Some((parent_level, _)) = stack.last() {
while let Some((parent_level, _, _)) = stack.last() {
if *parent_level >= level {
stack.pop();
} else {
@@ -142,7 +244,7 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
}
let parent_path = stack
.last()
.map(|(_, path)| path.clone())
.map(|(_, path, _)| path.clone())
.unwrap_or_default();
let path = {
let mut path = parent_path.clone();
@@ -150,14 +252,12 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
path
};
// Duplicate canonical names in the same scope are a hard error; never
// silently rename with -1/-2 suffixes.
let key = (parent_path.clone(), name.clone());
if let Some(previous) = seen.get(&key) {
let previous = *previous;
index.diagnostics.push(
Diagnostic::error(
codes::MARKDOWN_INVALID_CONSTRUCT,
codes::SEM_DUPLICATE_UNIT_NAME,
Some(child.span),
format!("duplicate heading name `{name}` in the same scope"),
)
@@ -170,14 +270,25 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
let kind = match level {
1 => UnitKind::Namespace,
2 => UnitKind::Function,
2 if mode == SemanticMode::Exec => UnitKind::Function,
2 => UnitKind::Knowledge,
_ => UnitKind::Section,
};
if level == 1 {
current_namespace = Some(name.clone());
current_function = None;
}
let function = if level == 2 {
if level >= 3 && mode == SemanticMode::Exec && current_function.is_none() {
index.diagnostics.push(
Diagnostic::error(
codes::SEM_EXEC_WITHOUT_FUNCTION,
Some(child.span),
"executable section has no owning Exec H2 function",
)
.with_hint("put the section under an Exec H2, or mark it @knowledge"),
);
}
let function = if level == 2 && mode == SemanticMode::Exec {
let local = name.clone();
let qualified = match &current_namespace {
Some(namespace) => format!("{namespace}.{local}"),
@@ -189,9 +300,12 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
};
current_function = Some(id.clone());
Some(id)
} else if level >= 3 {
} else if level >= 3 && mode == SemanticMode::Exec {
current_function.clone()
} else {
if level <= 2 {
current_function = None;
}
None
};
@@ -202,6 +316,7 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
span: child.span,
path: path.clone(),
kind,
mode,
};
let unit_id = UnitId {
module: module.clone(),
@@ -215,12 +330,40 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
kind,
function,
});
if level == 1 && mode == SemanticMode::Exec {
// H1 Exec: direct-body carriers before the next heading have no
// owning H2 function. A Knowledge H2 body is inert (inline code
// there is documentation), and Exec H3 sections are checked above.
let mut scan = node_index + 1;
while scan < doc.root.children.len() {
if let MdKind::Heading { .. } = doc.root.children[scan].kind {
break;
}
if has_payload(&doc.root.children[scan]) {
index.diagnostics.push(Diagnostic::error(
codes::SEM_EXEC_WITHOUT_FUNCTION,
Some(doc.root.children[scan].span),
"executable payload has no owning Exec H2 function",
));
break;
}
scan += 1;
}
}
heading_infos.push(info.clone());
stack.push((level, info.path.clone()));
stack.push((level, info.path.clone(), mode));
}
// Function body ranges and spans.
for heading in heading_infos.iter().filter(|h| h.level == 2) {
// A Knowledge H2 has no function range.
if !index
.units
.iter()
.any(|unit| unit.id.path == heading.path && unit.kind == UnitKind::Function)
{
continue;
}
let body_start = heading.node_index + 1;
let body_end = doc.root.children[body_start..]
.iter()
@@ -239,33 +382,23 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
} else {
heading.span
};
let local_name = heading.name.clone();
let namespace = match heading.path.len() {
0 => None,
_ if heading.path.len() == 1 => None,
_ => Some(heading.path[0].clone()),
};
let namespace = namespace.filter(|_| {
index
.units
.iter()
.any(|unit| unit.kind == UnitKind::Namespace && unit.name == heading.path[0])
});
let qualified = match &namespace {
Some(namespace) => format!("{namespace}.{local_name}"),
None => local_name.clone(),
let unit = index
.units
.iter()
.find(|unit| unit.id.path == heading.path && unit.kind == UnitKind::Function)
.expect("function unit exists");
let FunctionId { name, .. } = unit.function.clone().expect("function id");
let local_name = name.rsplit('.').next().unwrap_or(&name).to_string();
let namespace = if name.contains('.') {
Some(name.rsplit_once('.').unwrap().0.to_string())
} else {
None
};
index.functions.push(FunctionScope {
id: FunctionId {
module: module.clone(),
name: qualified,
},
id: unit.function.clone().unwrap(),
local_name,
namespace,
unit: UnitId {
module: module.clone(),
path: heading.path.clone(),
},
unit: unit.id.clone(),
heading_span: heading.span,
body_start,
body_end,
@@ -273,67 +406,34 @@ pub fn build_units(doc: &MarkdownDocument, module: &ModuleId) -> UnitIndex {
});
}
// Warnings for would-be execution nodes outside every function body.
for (node_index, child) in doc.root.children.iter().enumerate() {
if index.function_containing_block(node_index).is_some() {
for heading in &heading_infos {
let Some(unit) = index.units.iter().find(|unit| unit.id.path == heading.path) else {
continue;
};
let slug = github_slug(&heading.name);
if slug.is_empty() {
continue;
}
let mut warn = |span: Span, what: &str| {
index.diagnostics.push(
Diagnostic::warning(
codes::MARKDOWN_INERT_EXECUTABLE,
Some(span),
format!("{what} outside a function body is inert document content"),
)
.with_hint("move it under a level-2 heading (`## 函数名`) to execute it"),
);
};
match &child.kind {
MdKind::BlockQuote => warn(child.span, "a block quote invocation"),
MdKind::List { .. } => warn(child.span, "a list control structure"),
MdKind::Paragraph => {
let mut found: Option<(Span, &'static str)> = None;
child.walk(&mut |node| {
if found.is_none() {
match node.kind {
MdKind::Strong => found = Some((node.span, "an execution statement")),
MdKind::Emph => found = Some((node.span, "a return statement")),
_ => {}
}
}
});
if let Some((span, what)) = found {
warn(span, what);
let mut count = index.anchors.keys().filter(|key| *key == &slug).count();
let key = if count == 0 {
slug.clone()
} else {
loop {
count += 1;
let candidate = format!("{slug}-{count}");
if !index.anchors.contains_key(&candidate) {
break candidate;
}
}
_ => {}
}
}
// Derive GitHub-style anchors for navigation and `ref("#...")`. Anchors are
// not identity: they may collide and receive -1/-2 suffixes exactly like
// GitHub's slugger, while internal ids stay canonical.
let mut slug_counts: BTreeMap<String, usize> = BTreeMap::new();
for unit in &index.units {
if unit.level == 0 {
continue;
}
let base = github_slug(&unit.name);
if base.is_empty() {
continue;
}
let count = slug_counts.entry(base.clone()).or_insert(0);
let slug = if *count == 0 {
base
} else {
format!("{base}-{count}")
};
*count += 1;
index.anchors.insert(slug, unit.id.clone());
index.anchors.insert(key, unit.id.clone());
}
index.headings = heading_infos;
index
.diagnostics
.dedup_by(|a, b| a.code == b.code && a.span == b.span && a.message == b.message);
index
}
/// GitHub-style heading slug, kept in a separate namespace from canonical
@@ -366,7 +466,7 @@ mod tests {
#[test]
fn builds_function_ranges() {
let index = index_of(
"# 命名空间\n\n## 阶乘\n\n**x = 1**\n\n### 小节\n\n正文\n\n## 下一个\n\n*y*\n",
"# @knowledge 命名空间\n\n## @exec 阶乘\n\n`x = 1`\n\n### 小节\n\n正文\n\n## @exec 下一个\n\n`return y`\n",
);
assert_eq!(index.functions.len(), 2);
assert_eq!(index.functions[0].local_name, "阶乘");
@@ -380,7 +480,7 @@ mod tests {
#[test]
fn root_level_function_without_namespace() {
let index = index_of("## main\n\n> 打印(1)\n");
let index = index_of("## @exec main\n\n`打印(1)`\n");
assert_eq!(index.functions.len(), 1);
assert_eq!(index.functions[0].id.name, "main");
assert!(index.functions[0].namespace.is_none());
@@ -389,16 +489,16 @@ mod tests {
#[test]
fn empty_heading_is_an_error() {
let index = index_of("## \n\n正文\n");
let index = index_of("## @exec\n\n正文\n");
assert!(index
.diagnostics
.iter()
.any(|d| d.code == codes::MARKDOWN_INVALID_CONSTRUCT && d.message.contains("empty")));
.any(|d| d.code == "sem.empty_unit_name" && d.message.contains("empty")));
}
#[test]
fn duplicate_function_names_are_errors() {
let index = index_of("## f\n\n## f\n");
let index = index_of("## @exec f\n\n## @exec f\n");
let errors = index
.diagnostics
.iter()
@@ -409,7 +509,7 @@ mod tests {
#[test]
fn same_name_in_different_namespaces_is_allowed() {
let index = index_of("# a\n\n## f\n\n# b\n\n## f\n");
let index = index_of("# @knowledge a\n\n## @exec f\n\n# @knowledge b\n\n## @exec f\n");
let duplicates = index
.diagnostics
.iter()
@@ -423,11 +523,10 @@ mod tests {
#[test]
fn executable_outside_function_warns_but_does_not_execute() {
let index = index_of("**x = 1**\n\n## f\n\n*y*\n");
assert!(index
.diagnostics
.iter()
.any(|d| d.code == codes::MARKDOWN_INERT_EXECUTABLE));
// RFC-LANG-0002: a Strong at the Knowledge root is inert prose with no
// diagnostic; only an Exec H2 is a callable function.
let index = index_of("**x = 1**\n\n## @exec f\n\n`return y`\n");
assert!(index.diagnostics.is_empty());
assert_eq!(index.functions.len(), 1);
}
}
+2
View File
@@ -152,6 +152,8 @@ pub enum UnitKind {
Namespace,
/// Level-2 heading: function.
Function,
/// Level-2 heading in Knowledge mode: inert knowledge unit.
Knowledge,
/// Level-3+ heading inside a function: named section, not a callable unit.
Section,
}
+13
View File
@@ -66,6 +66,19 @@ impl FrontMatter {
Ok(result)
}
/// Whether the top-level YAML mapping contains `key`.
///
/// Returns `false` for invalid YAML. Used to reject removed syntax
/// selectors such as `marqdo_semantics` or `syntax` without making the
/// frontend depend on a YAML crate.
pub fn has_key(&self, key: &str) -> bool {
let Ok(yaml) = &self.yaml else {
return false;
};
yaml.as_mapping()
.is_some_and(|mapping| mapping.contains_key(key))
}
/// The raw YAML parses successfully.
pub fn is_valid(&self) -> bool {
self.yaml.is_ok()
+2 -2
View File
@@ -273,7 +273,7 @@ mod tests {
fn excludes_git_and_marqdo_directories() {
let dir = tempfile::tempdir().unwrap();
let root = dir.path();
write(&root.join("index.mq.md"), b"## main\n");
write(&root.join("index.mq.md"), b"## @exec main\n");
write(&root.join(".git/HEAD"), b"ref: main\n");
write(&root.join(".marqdo/env/env.json"), b"{}");
write(&root.join("nested/.marqdo/state"), b"x");
@@ -343,7 +343,7 @@ mod tests {
let dir = tempfile::tempdir().unwrap();
let source = dir.path().join("source");
let target = dir.path().join("target");
write(&source.join("index.mq.md"), b"## main\n");
write(&source.join("index.mq.md"), b"## @exec main\n");
write(&source.join("data/value.txt"), b"42");
write(&source.join(".git/HEAD"), b"ignored");
let digest = hash_tree(&source).unwrap();
+7 -7
View File
@@ -1599,7 +1599,7 @@ capabilities:
"project:\n name: geometry\n version: 0.1.0\n",
)
.unwrap();
std::fs::write(first.join("index.mq.md"), "## f\n\n*1*\n").unwrap();
std::fs::write(first.join("index.mq.md"), "## @exec f\n\n`return 1`\n").unwrap();
let manifest = Manifest::load(&root.join(MANIFEST_FILE)).unwrap();
let resolver =
PackageResolver::new(root.clone(), Some(manifest.clone()), None).with_unlocked(true);
@@ -1668,7 +1668,7 @@ capabilities:
"project:\n name: remote\n version: 0.2.0\n",
)
.unwrap();
std::fs::write(dep.join("index.mq.md"), "## hello\n\n*1*\n").unwrap();
std::fs::write(dep.join("index.mq.md"), "## @exec hello\n\n`return 1`\n").unwrap();
git(&dep, &["init", "-q"]);
git(&dep, &["add", "."]);
git(&dep, &["commit", "-q", "-m", "initial"]);
@@ -1721,7 +1721,7 @@ capabilities:
"project:\n name: geometry\n version: 0.1.0\n",
)
.unwrap();
std::fs::write(dep.join("index.mq.md"), "## area\n\n*1*\n").unwrap();
std::fs::write(dep.join("index.mq.md"), "## @exec area\n\n`return 1`\n").unwrap();
std::fs::write(
root.join(MANIFEST_FILE),
"project:\n name: p\n version: 0.1.0\ndependencies:\n geometry:\n path: ./deps/geometry\n",
@@ -1765,19 +1765,19 @@ capabilities:
"project:\n name: root\n version: 0.1.0\ndependencies:\n a:\n path: ./deps/a\n",
)
.unwrap();
std::fs::write(root.join("index.mq.md"), "## main\n\n*1*\n").unwrap();
std::fs::write(root.join("index.mq.md"), "## @exec main\n\n`return 1`\n").unwrap();
std::fs::write(
a.join(MANIFEST_FILE),
"project:\n name: a\n version: 0.1.0\ndependencies:\n b:\n path: ./b\n",
)
.unwrap();
std::fs::write(a.join("index.mq.md"), "## a\n\n*1*\n").unwrap();
std::fs::write(a.join("index.mq.md"), "## @exec a\n\n`return 1`\n").unwrap();
std::fs::write(
b.join(MANIFEST_FILE),
"project:\n name: b\n version: 0.1.0\n",
)
.unwrap();
std::fs::write(b.join("index.mq.md"), "## b\n\n*2*\n").unwrap();
std::fs::write(b.join("index.mq.md"), "## @exec b\n\n`return 2`\n").unwrap();
let manifest = Manifest::load(&root.join(MANIFEST_FILE)).unwrap();
let resolver = PackageResolver::new(root.clone(), Some(manifest), None).with_unlocked(true);
let graph = resolver.resolve_lock_graph().unwrap();
@@ -1813,7 +1813,7 @@ capabilities:
"project:\n name: geometry\n version: 0.1.0\n",
)
.unwrap();
std::fs::write(dep.join("index.mq.md"), "## area\n\n*1*\n").unwrap();
std::fs::write(dep.join("index.mq.md"), "## @exec area\n\n`return 1`\n").unwrap();
std::fs::write(
root.join(MANIFEST_FILE),
"project:\n name: p\n version: 0.1.0\ndependencies:\n geometry:\n path: ./deps/geometry\n",
+17 -15
View File
@@ -64,28 +64,28 @@ fn run_and_output(source: &str, function: &str) -> (Result<Value, RuntimeError>,
#[test]
fn recursion_branch_and_return() {
let source = "## 阶乘\n\n1. `n <= 1`\n\n *1*\n\n2. `n > 1`\n\n **结果 = n * 阶乘(n=n-1)**\n\n *结果*\n";
let source = "## @exec 阶乘\n\n`if n <= 1`\n\n`return 1`\n\n`else`\n\n`if n > 1`\n\n`结果 = n * 阶乘(n=n-1)`\n\n`return 结果`\n\n`end`\n\n`end`\n";
let value = run_named(source, "阶乘", &[("n", Value::int(5))]).unwrap();
assert_eq!(value, Value::int(120));
}
#[test]
fn loop_mutates_and_returns_unit_for_fallthrough() {
let source = "## 倒计时\n\n**n = 3**\n\n- `n > 0`\n\n **n = n - 1**\n";
let source = "## @exec 倒计时\n\n`n = 3`\n\n`while n > 0`\n\n`n = n - 1`\n\n`end`\n";
let (result, _) = run_and_output(source, "倒计时");
assert_eq!(result.unwrap(), Value::Unit);
}
#[test]
fn return_inside_loop_propagates() {
let source = "## 找\n\n**i = 0**\n\n- `true`\n\n **i = i + 1**\n\n - `i >= 3`\n\n *i*\n";
let source = "## @exec 找\n\n`i = 0`\n\n`while true`\n\n`i = i + 1`\n\n`if i >= 3`\n\n`return i`\n\n`end`\n\n`end`\n";
let (result, _) = run_and_output(source, "找");
assert_eq!(result.unwrap(), Value::int(3));
}
#[test]
fn explicit_signature_supports_positional_arguments() {
let source = "## 加\n\n`(a: Int, b: Int = 10)`\n\n*a + b*\n";
let source = "## @exec 加\n\n`params(a: Int, b: Int = 10)`\n\n`return a + b`\n";
let program = build(source);
let mut host = host();
let result = run(
@@ -101,7 +101,7 @@ fn explicit_signature_supports_positional_arguments() {
#[test]
fn builtins_for_conversions_and_length() {
let source = "## f\n\n*长度(\"你好\") + 整数(\"40\") + 整数(2.0)*\n";
let source = "## @exec f\n\n`return 长度(\"你好\") + 整数(\"40\") + 整数(2.0)`\n";
let value = run_named(source, "f", &[]).unwrap();
assert_eq!(value, Value::int(44));
}
@@ -109,21 +109,21 @@ fn builtins_for_conversions_and_length() {
#[test]
fn function_reference_can_be_called() {
let source =
"## 平方\n\n`(n: Int)`\n\n*n * n*\n\n## 主\n\n**f = ref(\"#平方\")**\n\n*f(n=4)*\n";
"## @exec 平方\n\n`params(n: Int)`\n\n`return n * n`\n\n## @exec 主\n\n`f = ref(\"#平方\")`\n\n`return f(n=4)`\n";
let value = run_named(source, "主", &[]).unwrap();
assert_eq!(value, Value::int(16));
}
#[test]
fn non_bool_condition_is_a_runtime_error() {
let source = "## f\n\n**x = 1**\n\n- `x`\n\n **x = x + 1**\n\n*x*\n";
let source = "## @exec f\n\n`x = 1`\n\n`while x`\n\n`x = x + 1`\n\n`end`\n\n`return x`\n";
let error = run_named(source, "f", &[]).unwrap_err();
assert_eq!(error.code(), "runtime.type");
}
#[test]
fn fuel_budget_is_enforced() {
let program = build("## f\n\n- `true`\n\n **x = 1**\n\n*0*\n");
let program = build("## @exec f\n\n`while true`\n\n`x = 1`\n\n`end`\n\n`return 0`\n");
let mut host = StdHost::new(
SandboxMode::Project,
Capabilities::pure(),
@@ -143,7 +143,7 @@ fn fuel_budget_is_enforced() {
#[test]
fn recursion_depth_is_bounded() {
let source = "## f\n\n*f(n=n + 1)*\n";
let source = "## @exec f\n\n`return f(n=n + 1)`\n";
let program = build(source);
let mut host = StdHost::new(
SandboxMode::Project,
@@ -165,14 +165,15 @@ fn recursion_depth_is_bounded() {
#[test]
fn ambiguous_ref_resource_is_an_error() {
let source = "## f\n\n### 公式\n\n$$a = 1$$\n\n$$b = 2$$\n\n**x = ref(\"#公式\")**\n\n*x*\n";
let source =
"## @exec f\n\n### 公式\n\n$$a = 1$$\n\n$$b = 2$$\n\n`x = ref(\"#公式\")`\n\n`return x`\n";
let error = run_named(source, "f", &[]).unwrap_err();
assert_eq!(error.code(), "ref.ambiguous");
}
#[test]
fn print_without_the_bundled_stdlib_is_a_structured_error() {
let source = "## f\n\n> 打印(1)\n\n*None*\n";
let source = "## @exec f\n\n`打印(1)`\n\n`return None`\n";
let error = run_named(source, "f", &[]).unwrap_err();
assert_eq!(error.code(), "kernel.unavailable");
assert!(
@@ -184,7 +185,7 @@ fn print_without_the_bundled_stdlib_is_a_structured_error() {
#[test]
fn function_ref_and_resource_members_are_readable() {
let source = "## 目标\n\n*1*\n\n## main\n\n### 公式\n\n$$a = 1$$\n\n### 代码\n\n```text\nx\n```\n\n**f = ref(\"#目标\")**\n\n**g = ref(\"#公式\")**\n\n**c = ref(\"#代码\")**\n\n*[f.module, f.name, g.latex, g.display, c.language, c.source]*\n";
let source = "## @exec 目标\n\n`return 1`\n\n## @exec main\n\n### 公式\n\n$$a = 1$$\n\n### 代码\n\n```text\nx\n```\n\n`f = ref(\"#目标\")`\n\n`g = ref(\"#公式\")`\n\n`c = ref(\"#代码\")`\n\n`return [f.module, f.name, g.latex, g.display, c.language, c.source]`\n";
let value = run_named(source, "main", &[]).unwrap();
let Value::List(items) = value else {
panic!("expected list");
@@ -199,7 +200,7 @@ fn function_ref_and_resource_members_are_readable() {
#[test]
fn memory_region_is_shared_by_handle_identity() {
let source = "## f\n\n**m = memory.new(1, 2)**\n\n**n = m**\n\n**`m[3] = 7`**\n\n*[n[3], m == n, memory.size(n)]*\n";
let source = "## @exec f\n\n`m = memory.new(1, 2)`\n\n`n = m`\n\n`m[3] = 7`\n\n`return [n[3], m == n, memory.size(n)]`\n";
let value = run_named(source, "f", &[]).unwrap();
assert_eq!(
value,
@@ -209,7 +210,7 @@ fn memory_region_is_shared_by_handle_identity() {
#[test]
fn memory_handle_cannot_reach_the_host_boundary() {
let source = "## f\n\n**m = memory.new(1, 1)**\n\n> fs.read(m)\n\n*0*\n";
let source = "## @exec f\n\n`m = memory.new(1, 1)`\n\n`fs.read(m)`\n\n`return 0`\n";
let error = run_named(source, "f", &[]).unwrap_err();
assert_eq!(error.code(), "runtime.type");
assert!(
@@ -223,7 +224,8 @@ fn memory_handle_cannot_reach_the_host_boundary() {
#[test]
fn memory_budget_is_enforced_without_changing_the_region() {
let program = build("## f\n\n**m = memory.new(1, 1)**\n\n*[m[0], memory.grow(m, 1)]*\n");
let program =
build("## @exec f\n\n`m = memory.new(1, 1)`\n\n`return [m[0], memory.grow(m, 1)]`\n");
let mut host = host();
let error = run_with_limits(
&program,
+30
View File
@@ -13,6 +13,36 @@ pub mod codes {
pub const MARKDOWN_INERT_EXECUTABLE: &str = "markdown.inert_executable";
/// Front matter is malformed or appears somewhere other than the document start.
pub const FRONTMATTER_INVALID: &str = "frontmatter.invalid";
/// A heading uses an invalid `@exec`/`@knowledge` mode marker.
pub const SEM_INVALID_MODE_MARKER: &str = "sem.invalid_mode_marker";
/// A mode declaration has no semantic heading name.
pub const SEM_EMPTY_UNIT_NAME: &str = "sem.empty_unit_name";
/// Duplicate canonical heading/unit name in one scope.
pub const SEM_DUPLICATE_UNIT_NAME: &str = "sem.duplicate_unit_name";
/// Executable payload appears under no Exec H2 function.
pub const SEM_EXEC_WITHOUT_FUNCTION: &str = "sem.exec_without_function";
/// A payload carrier contains a nested inline structure.
pub const SEM_PAYLOAD_NESTED: &str = "sem.payload_nested";
/// A payload carrier is empty in an Exec scope.
pub const SEM_EMPTY_PAYLOAD: &str = "sem.empty_payload";
/// A payload failed semantic statement validation.
pub const SEM_SYNTAX: &str = "sem.syntax";
/// `else` does not bind an open `if`.
pub const SEM_UNMATCHED_ELSE: &str = "sem.unmatched_else";
/// A second `else` appears for one `if`.
pub const SEM_DUPLICATE_ELSE: &str = "sem.duplicate_else";
/// `end` closes no open frame.
pub const SEM_UNMATCHED_END: &str = "sem.unmatched_end";
/// A control frame is not closed before the heading ends.
pub const SEM_UNCLOSED_CONTROL: &str = "sem.unclosed_control";
/// `params(...)` is not the first direct Exec H2 payload.
pub const SEM_SIGNATURE_POSITION: &str = "sem.signature_position";
/// A version directive such as `marqdo_semantics` is forbidden.
pub const SEM_UNSUPPORTED_VERSION_DIRECTIVE: &str = "sem.unsupported_version_directive";
/// `run` found no callable entry function.
pub const SEM_NO_ENTRY_FUNCTION: &str = "sem.no_entry_function";
/// A signature was inferred rather than declared.
pub const SEM_INFERRED_SIGNATURE: &str = "sem.inferred_signature";
/// An executable payload failed to parse as an expression or statement.
pub const EXPR_PARSE: &str = "expr.parse";
/// A function name is referenced but no such function exists.
+13 -7
View File
@@ -1,6 +1,6 @@
# 数学
# @knowledge 数学
## 阶乘
## @exec 阶乘
定义:
@@ -8,12 +8,18 @@ $$
n! = \begin{cases}1,& n\le1\\n(n-1)!,& n>1\end{cases}
$$
1. `n <= 1`,递归终点。
`if n <= 1`
*1*
递归终点,返回 1。
2. `n > 1`,计算更小的问题。
`return 1`
**结果 = n * 阶乘(n=n-1)**
`else`
*结果*
计算更小的问题。
`结果 = n * 阶乘(n=n-1)`
`return 结果`
`end`
+4 -4
View File
@@ -1,7 +1,7 @@
## main
## @exec main
**问候 = "你好,Marqdo"**
`问候 = "你好,Marqdo"`
> 打印(问候)
> **打印(问候)**
*问候*
`return 问候`
+6 -6
View File
@@ -1,11 +1,11 @@
## main
## @exec main
### 代码
`结果 = foreign.call(ref("#代码"), {})`
> **打印(结果)**
### @knowledge 代码
```mocklang
ignored by the mock provider
```
**结果 = foreign.call(ref("#代码"), {})**
> 打印(结果)
+5 -5
View File
@@ -1,15 +1,15 @@
# 数学
# @knowledge 数学
## 圆面积公式
## @knowledge 圆面积公式
$$
A = \pi r^2
$$
## 计算圆面积
## @exec 计算圆面积
依据[圆面积公式](#圆面积公式)代入半径。
**面积 = math.eval(ref("#圆面积公式"), {"r": 4}, target="A")**
`面积 = math.eval(ref("#圆面积公式"), {"r": 4}, target="A")`
*面积*
`return 面积`
+6 -6
View File
@@ -1,14 +1,14 @@
## main
## @exec main
此函数演示“可引用的存储区域”与普通 Markdown 叙述并存。
区域按 64 KiB 逻辑页增长,副本共享同一区域身份。
**区域 = memory.new(1, 4)**
`区域 = memory.new(1, 4)`
**`区域[8] = 42`**
`区域[8] = 42`
**另一个名字 = 区域**
`另一个名字 = 区域`
**`另一个名字[9] = 99`**
`另一个名字[9] = 99`
*区域[8] + 区域[9]*
`return 区域[8] + 区域[9]`
+4 -4
View File
@@ -1,10 +1,10 @@
## 圆面积
## @exec 圆面积
`(r: Number)`
`params(r: Number)`
*math.eval(ref("#公式"), {"r": r}, target="A")*
`return math.eval(ref("#公式"), {"r": r}, target="A")`
### 公式
### @knowledge 公式
$$
A = \pi r^2
+3 -3
View File
@@ -3,8 +3,8 @@ import:
geometry: "./geometry.mq.md"
---
## main
## @exec main
**面积 = geometry.圆面积(r=2)**
`面积 = geometry.圆面积(r=2)`
> 打印(面积)
> **打印(面积)**
+5 -5
View File
@@ -4,12 +4,12 @@ import:
geometry_v2: "@geometry_v2"
---
## main
## @exec main
**一 = geometry_v1.area()**
`一 = geometry_v1.area()`
**二 = geometry_v2.area()**
`二 = geometry_v2.area()`
> 打印(一)
> **打印(一)**
> 打印(二)
> **打印(二)**
+6 -6
View File
@@ -4,24 +4,24 @@ root:
package: root:multi-version@0.1.0
manifest_digest: 959bfcdd1f8174365e43a2690d80bb61ea2b7c9ca5e1476abc582600551a0d40
packages:
- instance_id: dep:geometry@1.0.0#76cb510d5f6ef15845a648ddf20749bc5a87bbce04008f4666cf9ac9ea14f643
- instance_id: dep:geometry@1.0.0#d856df8a5cc47974ec256d3c939d8a1e206d82126111d2ffe1b959fcc29a4311
name: geometry
version: 1.0.0
source:
kind: path
path: packages/geometry-v1
content_digest: 76cb510d5f6ef15845a648ddf20749bc5a87bbce04008f4666cf9ac9ea14f643
content_digest: d856df8a5cc47974ec256d3c939d8a1e206d82126111d2ffe1b959fcc29a4311
manifest_digest: 3049840e18aefb2766c62406db0545cb9cc100d9d12b1dd9585e6ecb358c321a
dependencies: {}
- instance_id: dep:geometry@2.0.0#f364164e6b6927e85bd9e4c360de575ee7bef2b3e8bd30180cab04052ceaff29
- instance_id: dep:geometry@2.0.0#7c625a31b3f95a1fba38f0d87afd95554937b6c2ae261e8c9208637d76e5389d
name: geometry
version: 2.0.0
source:
kind: path
path: packages/geometry-v2
content_digest: f364164e6b6927e85bd9e4c360de575ee7bef2b3e8bd30180cab04052ceaff29
content_digest: 7c625a31b3f95a1fba38f0d87afd95554937b6c2ae261e8c9208637d76e5389d
manifest_digest: b206f83f82af59995a6bda82a36627d98deb709cfac36c684ced1531f4afba2a
dependencies: {}
root_dependencies:
geometry_v1: dep:geometry@1.0.0#76cb510d5f6ef15845a648ddf20749bc5a87bbce04008f4666cf9ac9ea14f643
geometry_v2: dep:geometry@2.0.0#f364164e6b6927e85bd9e4c360de575ee7bef2b3e8bd30180cab04052ceaff29
geometry_v1: dep:geometry@1.0.0#d856df8a5cc47974ec256d3c939d8a1e206d82126111d2ffe1b959fcc29a4311
geometry_v2: dep:geometry@2.0.0#7c625a31b3f95a1fba38f0d87afd95554937b6c2ae261e8c9208637d76e5389d
@@ -1,3 +1,3 @@
## area
## @exec area
*1*
`return 1`
@@ -1,3 +1,3 @@
## area
## @exec area
*2*
`return 2`
+3 -3
View File
@@ -125,11 +125,11 @@ are callable through the namespace that prefixes their export names. Plugin
calls take **named arguments only** in this build:
```markdown
## main
## @exec main
**结果 = solver.add(a=20, b=22)**
`结果 = solver.add(a=20, b=22)`
> 打印(结果)
> **打印(结果)**
```
```sh
+3 -3
View File
@@ -1,5 +1,5 @@
## main
## @exec main
**结果 = solver.add(a=20, b=22)**
`结果 = solver.add(a=20, b=22)`
> 打印(结果)
> **打印(结果)**
@@ -1,9 +1,9 @@
## main
## @exec main
**和 = solver.add(a=20, b=22)**
`和 = solver.add(a=20, b=22)`
**相反数 = solver.neg(a=7)**
`相反数 = solver.neg(a=7)`
> 打印(和)
> **打印(和)**
> 打印(相反数)
> **打印(相反数)**
+4 -4
View File
@@ -1,4 +1,4 @@
## Python 校验
## @knowledge Python 校验
```python
import json, math, sys
@@ -9,8 +9,8 @@ area = math.pi * r ** 2
print(json.dumps({"type": "map", "entries": {"area": {"type": "float", "value": area}}}))
```
## main
## @exec main
**结果 = foreign.call(ref("#python-校验"), {"r": 3})**
`结果 = foreign.call(ref("#python-校验"), {"r": 3})`
> 打印(结果.area)
> **打印(结果.area)**
+5 -5
View File
@@ -1,6 +1,6 @@
# 参考
# @knowledge 参考
## 牛顿第二定律
## @knowledge 牛顿第二定律
$$
F = m a
@@ -8,8 +8,8 @@ $$
参见[圆面积](./math.mq.md#计算圆面积)(这是静态引用,不会执行)。
## 计算作用力
## @exec 计算作用力
**力 = math.eval(ref("#牛顿第二定律"), {"m": 2, "a": 3}, target="F")**
`力 = math.eval(ref("#牛顿第二定律"), {"m": 2, "a": 3}, target="F")`
*力*
`return 力`
+3 -3
View File
@@ -3,8 +3,8 @@ import:
io: "std:io"
---
## main
## @exec main
> io.写值(["bundle", 1, 2.5])
> **io.写值(["bundle", 1, 2.5])**
*None*
`return None`
+6 -4
View File
@@ -1,8 +1,10 @@
# @exec clock
## 现在
`()`
`params()`
返回项目模式下的 UTC Unix 毫秒。`pure`/`strict` 返回
`permission.denied`,与 `resource.request` 的其他操作一致。
返回项目模式下的 UTC Unix 毫秒。pure/strict 返回
permission.denied,与 resource.request 的其他操作一致。
*resource.request("clock.now", [])*
`return resource.request("clock.now", [])`
+8 -6
View File
@@ -1,17 +1,19 @@
# @exec compress
## 压缩
`(文本)`
`params(文本)`
把 UTF-8 文本压缩为 gzip 字节列表(`List<Int>`,0–255)。输入上限
把 UTF-8 文本压缩为 gzip 字节列表(List<Int>,0–255)。输入上限
8 MiB;结果确定(不写入时间戳/文件名)。
*resource.request("compress.gzip", [文本])*
`return resource.request("compress.gzip", [文本])`
## 解压
`(字节列表)`
`params(字节列表)`
解压 gzip 字节列表并校验 UTF-8。输出上限 8 MiB;坏 gzip 返回
`compress.invalid`,非 UTF-8 返回 `compress.not_utf8`。
compress.invalid,非 UTF-8 返回 compress.not_utf8。
*resource.request("compress.gunzip", [字节列表])*
`return resource.request("compress.gunzip", [字节列表])`
+179 -116
View File
@@ -1,20 +1,22 @@
# @exec csv
## 成功
`(值)`
`params(值)`
*{ok: true, value: 值}*
`return {ok: true, value: 值}`
## 失败
`(代码, 消息)`
`params(代码, 消息)`
*{ok: false, code: 代码, message: 消息}*
`return {ok: false, code: 代码, message: 消息}`
## 解析行
`(文本)`
`params(文本)`
解析单行 CSV:逗号分隔、双引号包裹、`""` 表示一个字面双引号。
解析单行 CSV:逗号分隔、双引号包裹、"" 表示一个字面双引号。
不处理换行、多行字段或首尾空白。未闭合引号和未加引号字段中的双引号
返回可恢复错误。
@@ -30,71 +32,90 @@
**错误 = ""**
- `下标 < 长度(点) and 错误 == ""`
`while 下标 < 长度(点) and 错误 == ""`
**字符 = text.from_codepoint(点[下标])**
**字符 = text.from_codepoint(点[下标])**
1. `引号内 and 字符 == "\""`
`if 引号内 and 字符 == "\""`
1. `下标 + 1 < 长度(点) and text.from_codepoint(点[下标 + 1]) == "\""`
`if 下标 + 1 < 长度(点) and text.from_codepoint(点[下标 + 1]) == "\""`
**`字段 = 字段 + "\""`**
**`字段 = 字段 + "\""`**
**下标 = 下标 + 2**
**下标 = 下标 + 2**
2. `true`
`else`
`if true`
**引号内 = false**
**引号内 = false**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
2. `引号内`
`end`
`end`
`else`
`if 引号内`
**字段 = 字段 + 字符**
**字段 = 字段 + 字符**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
3. `字符 == "\""`
`else`
`if 字符 == "\""`
1. `字段 == ""`
`if 字段 == ""`
**引号内 = true**
**引号内 = true**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
2. `true`
`else`
`if true`
**错误 = "csv.invalid_quote"**
**错误 = "csv.invalid_quote"**
4. `字符 == ","`
`end`
`end`
`else`
`if 字符 == ","`
**字段表 = list.append(字段表, 字段)**
**字段表 = list.append(字段表, 字段)**
**字段 = ""**
**字段 = ""**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
5. `true`
`else`
`if true`
**字段 = 字段 + 字符**
**字段 = 字段 + 字符**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
1. `错误 != ""`
`end`
`end`
`end`
`end`
`end`
`end`
`if 错误 != ""`
*失败(错误, "未加引号字段中出现双引号")*
`return 失败(错误, "未加引号字段中出现双引号")`
1. `引号内`
`else`
`if 引号内`
*失败("csv.unterminated_quote", "引号未闭合")*
`return 失败("csv.unterminated_quote", "引号未闭合")`
*成功(list.concat(字段表, [字段]))*
`end`
`end`
`return 成功(list.concat(字段表, [字段]))`
## 格式化字段
`(文本)`
`params(文本)`
含逗号、双引号、换行或回车的字段加引号,内部双引号写成 `""`。
含逗号、双引号、换行或回车的字段加引号,内部双引号写成 ""。
**点 = text.codepoints(文本)**
@@ -102,72 +123,85 @@
**需要引号 = false**
- `下标 < 长度(点) and not 需要引号`
`while 下标 < 长度(点) and not 需要引号`
**码点 = 点[下标]**
**码点 = 点[下标]**
1. `码点 == 34 or 码点 == 44 or 码点 == 10 or 码点 == 13`
`if 码点 == 34 or 码点 == 44 or 码点 == 10 or 码点 == 13`
**需要引号 = true**
**需要引号 = true**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
1. `not 需要引号`
`end`
`if not 需要引号`
*文本*
`return 文本`
`end`
**`结果 = "\""`**
**下标 = 0**
- `下标 < 长度(点)`
`while 下标 < 长度(点)`
1. `点[下标] == 34`
`if 点[下标] == 34`
**`结果 = 结果 + "\"\""`**
**`结果 = 结果 + "\"\""`**
2. `true`
`else`
`if true`
**结果 = 结果 + text.from_codepoint(点[下标])**
**结果 = 结果 + text.from_codepoint(点[下标])**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
*`结果 + "\""`*
`end`
``return 结果 + "\""``
## 格式化行
`(列表)`
`params(列表)`
**结果 = ""**
**下标 = 0**
- `下标 < 长度(列表)`
`while 下标 < 长度(列表)`
1. `下标 > 0`
`if 下标 > 0`
**结果 = 结果 + ","**
**结果 = 结果 + ","**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**结果 = 结果 + 格式化字段(文本(列表[下标]))**
`end`
`end`
**结果 = 结果 + 格式化字段(文本(列表[下标]))**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 解析
`(文本)`
`params(文本)`
解析多行 CSV(逗号分隔、双引号、`""` 转义、CRLF/LF 行尾,引号内可含
换行)。返回 `{ok:true, value:List<List<Text>>}`;未闭合引号和不合法
解析多行 CSV(逗号分隔、双引号、"" 转义、CRLF/LF 行尾,引号内可含
换行)。返回 {ok:true, value:List<List<Text>>};未闭合引号和不合法
引号返回可恢复错误。
**点 = text.codepoints(文本)**
@@ -184,108 +218,137 @@
**错误 = ""**
- `下标 < 长度(点) and 错误 == ""`
`while 下标 < 长度(点) and 错误 == ""`
**字符 = text.from_codepoint(点[下标])**
**字符 = text.from_codepoint(点[下标])**
1. `引号内 and 字符 == "\""`
`if 引号内 and 字符 == "\""`
1. `下标 + 1 < 长度(点) and text.from_codepoint(点[下标 + 1]) == "\""`
`if 下标 + 1 < 长度(点) and text.from_codepoint(点[下标 + 1]) == "\""`
**`字段 = 字段 + "\""`**
**`字段 = 字段 + "\""`**
**下标 = 下标 + 2**
**下标 = 下标 + 2**
2. `true`
`else`
`if true`
**引号内 = false**
**引号内 = false**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
2. `引号内`
`end`
`end`
`else`
`if 引号内`
**字段 = 字段 + 字符**
**字段 = 字段 + 字符**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
3. `字符 == "\""`
`else`
`if 字符 == "\""`
1. `字段 == ""`
`if 字段 == ""`
**引号内 = true**
**引号内 = true**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
2. `true`
`else`
`if true`
**错误 = "csv.invalid_quote"**
**错误 = "csv.invalid_quote"**
4. `字符 == ","`
`end`
`end`
`else`
`if 字符 == ","`
**当前行 = list.append(当前行, 字段)**
**当前行 = list.append(当前行, 字段)**
**字段 = ""**
**字段 = ""**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
5. `字符 == "\n"`
`else`
`if 字符 == "\n"`
**当前行 = list.append(当前行, 字段)**
**当前行 = list.append(当前行, 字段)**
**行 = list.append(行, 当前行)**
**行 = list.append(行, 当前行)**
**当前行 = []**
**当前行 = []**
**字段 = ""**
**字段 = ""**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
6. `字符 == "\r"`
`else`
`if 字符 == "\r"`
**下标 = 下标 + 1**
**下标 = 下标 + 1**
7. `true`
`else`
`if true`
**字段 = 字段 + 字符**
**字段 = 字段 + 字符**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
1. `错误 != ""`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`if 错误 != ""`
*失败(错误, "未加引号字段中出现双引号")*
`return 失败(错误, "未加引号字段中出现双引号")`
1. `引号内`
`else`
`if 引号内`
*失败("csv.unterminated_quote", "引号未闭合")*
`return 失败("csv.unterminated_quote", "引号未闭合")`
1. `字段 != "" or 长度(当前行) > 0`
`else`
`if 字段 != "" or 长度(当前行) > 0`
**当前行 = list.append(当前行, 字段)**
**当前行 = list.append(当前行, 字段)**
**行 = list.append(行, 当前行)**
**行 = list.append(行, 当前行)**
*成功(行)*
`end`
`end`
`end`
`return 成功(行)`
## 格式化
`(行列表)`
`params(行列表)`
**结果 = ""**
**行号 = 0**
- `行号 < 长度(行列表)`
`while 行号 < 长度(行列表)`
1. `行号 > 0`
`if 行号 > 0`
**结果 = 结果 + "\n"**
**结果 = 结果 + "\n"**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**结果 = 结果 + 格式化行(行列表[行号])**
`end`
`end`
**结果 = 结果 + 格式化行(行列表[行号])**
**行号 = 行号 + 1**
**行号 = 行号 + 1**
*结果*
`end`
`return 结果`
+468 -292
View File
File diff suppressed because it is too large. Load diff
+181 -130
View File
@@ -1,6 +1,8 @@
# @exec table
## 选择列
`(数据, 列)`
`params(数据, 列)`
**列名 = table.columns(数据)**
@@ -8,19 +10,20 @@
**行号 = 0**
- `行号 < 长度(数据)`
`while 行号 < 长度(数据)`
**行 = table.row(数据, 行号)**
**行 = table.row(数据, 行号)**
**结果行 = list.append(结果行, [行[列]])**
**结果行 = list.append(结果行, [行[列]])**
**行号 = 行号 + 1**
**行号 = 行号 + 1**
*表([列名[列]], 结果行)*
`end`
`return 表([列名[列]], 结果行)`
## 过滤数值大于
`(数据, 列, 阈值)`
`params(数据, 列, 阈值)`
**列名 = table.columns(数据)**
@@ -28,25 +31,29 @@
**行号 = 0**
- `行号 < 长度(数据)`
`while 行号 < 长度(数据)`
**行 = table.row(数据, 行号)**
**行 = table.row(数据, 行号)**
1. `行[列] > 阈值`
`if 行[列] > 阈值`
**结果行 = list.append(结果行, 行)**
**结果行 = list.append(结果行, 行)**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**行号 = 行号 + 1**
`end`
`end`
**行号 = 行号 + 1**
*表(列名, 结果行)*
`end`
`return 表(列名, 结果行)`
## 插入有序
`(已排序, 行, 列)`
`params(已排序, 行, 列)`
**新列表 = []**
@@ -54,37 +61,44 @@
**下标 = 0**
- `下标 < 长度(已排序)`
`while 下标 < 长度(已排序)`
**当前行 = 已排序[下标]**
**当前行 = 已排序[下标]**
1. `not 已插入 and 当前行[列] > 行[列]`
`if not 已插入 and 当前行[列] > 行[列]`
**新列表 = list.append(新列表, 行)**
**新列表 = list.append(新列表, 行)**
**新列表 = list.append(新列表, 当前行)**
**新列表 = list.append(新列表, 当前行)**
**已插入 = true**
**已插入 = true**
2. `true`
`else`
`if true`
**新列表 = list.append(新列表, 当前行)**
**新列表 = list.append(新列表, 当前行)**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
1. `not 已插入`
`end`
`if not 已插入`
**新列表 = list.append(新列表, 行)**
**新列表 = list.append(新列表, 行)**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
*新列表*
`end`
`end`
`return 新列表`
## 排序
`(数据, 列)`
`params(数据, 列)`
**列名 = table.columns(数据)**
@@ -94,17 +108,18 @@
**下标 = 0**
- `下标 < 行数`
`while 下标 < 行数`
**已排序 = 插入有序(已排序, table.row(数据, 下标), 列)**
**已排序 = 插入有序(已排序, table.row(数据, 下标), 列)**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*表(列名, 已排序)*
`end`
`return 表(列名, 已排序)`
## 追加行
`(数据, 行)`
`params(数据, 行)`
**列名 = table.columns(数据)**
@@ -112,17 +127,18 @@
**行号 = 0**
- `行号 < 长度(数据)`
`while 行号 < 长度(数据)`
**所有行 = list.append(所有行, table.row(数据, 行号))**
**所有行 = list.append(所有行, table.row(数据, 行号))**
**行号 = 行号 + 1**
**行号 = 行号 + 1**
*表(列名, list.append(所有行, 行))*
`end`
`return 表(列名, list.append(所有行, 行))`
## 设置单元格
`(数据, 目标行, 目标列, 值)`
`params(数据, 目标行, 目标列, 值)`
**列名 = table.columns(数据)**
@@ -130,41 +146,49 @@
**行号 = 0**
- `行号 < 长度(数据)`
`while 行号 < 长度(数据)`
**行 = table.row(数据, 行号)**
**行 = table.row(数据, 行号)**
1. `行号 == 目标行`
`if 行号 == 目标行`
**新行 = []**
**新行 = []**
**列号 = 0**
**列号 = 0**
- `列号 < 长度(行)`
`while 列号 < 长度(行)`
1. `列号 == 目标列`
`if 列号 == 目标列`
**新行 = list.append(新行, 值)**
**新行 = list.append(新行, 值)**
2. `true`
`else`
`if true`
**新行 = list.append(新行, 行[列号])**
**新行 = list.append(新行, 行[列号])**
**列号 = 列号 + 1**
`end`
`end`
**列号 = 列号 + 1**
**新行表 = list.append(新行表, 新行)**
`end`
**新行表 = list.append(新行表, 新行)**
2. `true`
`else`
`if true`
**新行表 = list.append(新行表, 行)**
**新行表 = list.append(新行表, 行)**
**行号 = 行号 + 1**
`end`
`end`
**行号 = 行号 + 1**
*表(列名, 新行表)*
`end`
`return 表(列名, 新行表)`
## 连接
`(左, 右, 左列, 右列)`
`params(左, 右, 左列, 右列)`
**表头 = list.concat(table.columns(左), table.columns(右))**
@@ -172,117 +196,134 @@
**左行号 = 0**
- `左行号 < 长度(左)`
`while 左行号 < 长度(左)`
**左行 = table.row(左, 左行号)**
**左行 = table.row(左, 左行号)**
**键 = 左行[左列]**
**键 = 左行[左列]**
**右行号 = 0**
**右行号 = 0**
- `右行号 < 长度(右)`
`while 右行号 < 长度(右)`
**右行 = table.row(右, 右行号)**
**右行 = table.row(右, 右行号)**
1. `右行[右列] == 键`
`if 右行[右列] == 键`
**结果行 = list.append(结果行, list.concat(左行, 右行))**
**结果行 = list.append(结果行, list.concat(左行, 右行))**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**右行号 = 右行号 + 1**
`end`
`end`
**右行号 = 右行号 + 1**
**左行号 = 左行号 + 1**
`end`
**左行号 = 左行号 + 1**
*表(表头, 结果行)*
`end`
`return 表(表头, 结果行)`
## 分组
`(数据, 键列, 值列)`
`params(数据, 键列, 值列)`
**结果 = {}**
**行号 = 0**
- `行号 < 长度(数据)`
`while 行号 < 长度(数据)`
**行 = table.row(数据, 行号)**
**行 = table.row(数据, 行号)**
**键 = 行[键列]**
**键 = 行[键列]**
**当前 = map.get(结果, 键)**
**当前 = map.get(结果, 键)**
**列表 = []**
**列表 = []**
1. `map.has(结果, 键)`
`if map.has(结果, 键)`
**列表 = 当前**
**列表 = 当前**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**列表 = list.append(列表, 行[值列])**
`end`
`end`
**列表 = list.append(列表, 行[值列])**
**结果 = map.set(结果, 键, 列表)**
**结果 = map.set(结果, 键, 列表)**
**行号 = 行号 + 1**
**行号 = 行号 + 1**
*结果*
`end`
`return 结果`
## 连接片段
`(片段)`
`params(片段)`
**结果 = ""**
**下标 = 0**
- `下标 < 长度(片段)`
`while 下标 < 长度(片段)`
1. `下标 > 0`
`if 下标 > 0`
**结果 = 结果 + " | "**
**结果 = 结果 + " | "**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**结果 = 结果 + 片段[下标]**
`end`
`end`
**结果 = 结果 + 片段[下标]**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 连接行
`(行列表)`
`params(行列表)`
**结果 = ""**
**下标 = 0**
- `下标 < 长度(行列表)`
`while 下标 < 长度(行列表)`
1. `下标 > 0`
`if 下标 > 0`
**结果 = 结果 + "\n"**
**结果 = 结果 + "\n"**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**结果 = 结果 + 行列表[下标]**
`end`
`end`
**结果 = 结果 + 行列表[下标]**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 转义单元格
`(值)`
`params(值)`
**文本值 = 文本(值)**
@@ -292,27 +333,33 @@
**下标 = 0**
- `下标 < 长度(点)`
`while 下标 < 长度(点)`
1. `点[下标] == 124`
`if 点[下标] == 124`
**结果 = 结果 + text.from_codepoint(92) + "|"**
**结果 = 结果 + text.from_codepoint(92) + "|"**
2. `点[下标] == 10 or 点[下标] == 13`
`else`
`if 点[下标] == 10 or 点[下标] == 13`
**结果 = 结果 + " "**
**结果 = 结果 + " "**
3. `true`
`else`
`if true`
**结果 = 结果 + text.from_codepoint(点[下标])**
**结果 = 结果 + text.from_codepoint(点[下标])**
**下标 = 下标 + 1**
`end`
`end`
`end`
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 转GFM
`(数据)`
`params(数据)`
**列名 = table.columns(数据)**
@@ -320,12 +367,13 @@
**下标 = 0**
- `下标 < 长度(列名)`
`while 下标 < 长度(列名)`
**表头 = list.append(表头, 转义单元格(列名[下标]))**
**表头 = list.append(表头, 转义单元格(列名[下标]))**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
`end`
**行列表 = []**
**行列表 = list.append(行列表, "| " + 连接片段(表头) + " |")**
@@ -334,32 +382,35 @@
**下标 = 0**
- `下标 < 长度(列名)`
`while 下标 < 长度(列名)`
**分隔 = list.append(分隔, "---")**
**分隔 = list.append(分隔, "---")**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
`end`
**行列表 = list.append(行列表, "| " + 连接片段(分隔) + " |")**
**行号 = 0**
- `行号 < 长度(数据)`
`while 行号 < 长度(数据)`
**行 = table.row(数据, 行号)**
**行 = table.row(数据, 行号)**
**单元格 = []**
**单元格 = []**
**列号 = 0**
**列号 = 0**
- `列号 < 长度(行)`
`while 列号 < 长度(行)`
**单元格 = list.append(单元格, 转义单元格(行[列号]))**
**单元格 = list.append(单元格, 转义单元格(行[列号]))**
**列号 = 列号 + 1**
**列号 = 列号 + 1**
**行列表 = list.append(行列表, "| " + 连接片段(单元格) + " |")**
`end`
**行列表 = list.append(行列表, "| " + 连接片段(单元格) + " |")**
**行号 = 行号 + 1**
**行号 = 行号 + 1**
*连接行(行列表)*
`end`
`return 连接行(行列表)`
+131 -90
View File
@@ -1,98 +1,115 @@
# @exec datetime
## 失败
`(消息)`
`params(消息)`
*{ok: false, code: "datetime.invalid", message: 消息}*
`return {ok: false, code: "datetime.invalid", message: 消息}`
## 闰年
`(年)`
`params(年)`
*年 % 4 == 0 and (年 % 100 != 0 or 年 % 400 == 0)*
`return 年 % 4 == 0 and (年 % 100 != 0 or 年 % 400 == 0)`
## 每月天数
`(年, 月)`
`params(年, 月)`
1. `月 == 2`
`if 月 == 2`
1. `闰年(年)`
`if 闰年(年)`
*29*
`return 29`
*28*
`end`
`return 28`
2. `月 == 4 or 月 == 6 or 月 == 9 or 月 == 11`
`else`
`if 月 == 4 or 月 == 6 or 月 == 9 or 月 == 11`
*30*
`return 30`
*31*
`end`
`end`
`return 31`
## 补零2
`(值)`
`params(值)`
1. `值 < 10`
`if 值 < 10`
*"0" + 文本(值)*
`return "0" + 文本(值)`
*文本(值)*
`end`
`return 文本(值)`
## 补零3
`(值)`
`params(值)`
1. `值 < 10`
`if 值 < 10`
*"00" + 文本(值)*
`return "00" + 文本(值)`
2. `值 < 100`
`else`
`if 值 < 100`
*"0" + 文本(值)*
`return "0" + 文本(值)`
*文本(值)*
`end`
`end`
`return 文本(值)`
## 补零4
`(值)`
`params(值)`
1. `值 < 10`
`if 值 < 10`
*"000" + 文本(值)*
`return "000" + 文本(值)`
2. `值 < 100`
`else`
`if 值 < 100`
*"00" + 文本(值)*
`return "00" + 文本(值)`
3. `值 < 1000`
`else`
`if 值 < 1000`
*"0" + 文本(值)*
`return "0" + 文本(值)`
*文本(值)*
`end`
`end`
`end`
`return 文本(值)`
## 月份
`(mp)`
`params(mp)`
1. `mp < 10`
`if mp < 10`
*mp + 3*
`return mp + 3`
*mp - 9*
`end`
`return mp - 9`
## 年份
`(年, 月)`
`params(年, 月)`
1. `月 <= 2`
`if 月 <= 2`
*年 + 1*
`return 年 + 1`
*年*
`end`
`return 年`
## 日期部件
`(天)`
`params(天)`
Howard Hinnant 的 civil-from-days 算法,输入为 1970-01-01 起的天数。
@@ -114,45 +131,51 @@ Howard Hinnant 的 civil-from-days 算法,输入为 1970-01-01 起的天数。
**月 = 月份(mp)**
*{年: 年份(年, 月), 月: 月, 日: 日}*
`return {年: 年份(年, 月), 月: 月, 日: 日}`
## 日期序号
`(年, 月, 日)`
`params(年, 月, 日)`
**y = 年**
1. `月 <= 2`
`if 月 <= 2`
**y = y - 1**
**y = y - 1**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
`end`
`end`
**era = y // 400**
**yoe = y - era * 400**
**m = 月**
1. `月 > 2`
`if 月 > 2`
**m = 月 - 3**
**m = 月 - 3**
2. `true`
`else`
`if true`
**m = 月 + 9**
**m = 月 + 9**
`end`
`end`
**doy = (153 * m + 2) // 5 + 日 - 1**
**doe = yoe * 365 + yoe // 4 - yoe // 100 + doy**
*era * 146097 + doe - 719468*
`return era * 146097 + doe - 719468`
## 是数字串
`(文本)`
`params(文本)`
**点 = text.codepoints(文本)**
@@ -160,42 +183,47 @@ Howard Hinnant 的 civil-from-days 算法,输入为 1970-01-01 起的天数。
**下标 = 0**
- `下标 < 长度(点) and 结果`
`while 下标 < 长度(点) and 结果`
1. `点[下标] < 48 or 点[下标] > 57`
`if 点[下标] < 48 or 点[下标] > 57`
**结果 = false**
**结果 = false**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 片段
`(点, 起点, 终点)`
`params(点, 起点, 终点)`
**结果 = ""**
**下标 = 起点**
- `下标 < 终点`
`while 下标 < 终点`
**结果 = 结果 + text.from_codepoint(点[下标])**
**结果 = 结果 + text.from_codepoint(点[下标])**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 格式化
`(毫秒)`
`params(毫秒)`
输出 UTC ISO-8601:`YYYY-MM-DDTHH:MM:SSZ`;毫秒非零时追加
`.mmm`。负数毫秒按 1970 前的 UTC 时间处理。
输出 UTC ISO-8601:YYYY-MM-DDTHH:MM:SSZ;毫秒非零时追加
.mmm。负数毫秒按 1970 前的 UTC 时间处理。
**秒 = 毫秒 // 1000**
@@ -215,29 +243,33 @@ Howard Hinnant 的 civil-from-days 算法,输入为 1970-01-01 起的天数。
**基 = 补零4(日期.年) + "-" + 补零2(日期.月) + "-" + 补零2(日期.日) + "T" + 补零2(时) + ":" + 补零2(分) + ":" + 补零2(秒数)**
1. `毫 == 0`
`if 毫 == 0`
*基 + "Z"*
`return 基 + "Z"`
*基 + "." + 补零3(毫) + "Z"*
`end`
`return 基 + "." + 补零3(毫) + "Z"`
## 解析
`(文本)`
`params(文本)`
解析 `YYYY-MM-DDTHH:MM:SSZ` 或带 `.mmm` 的 UTC 文本,返回 Unix 毫秒。
范围、闰年和格式错误都是可恢复 `datetime.invalid`。
解析 YYYY-MM-DDTHH:MM:SSZ 或带 .mmm 的 UTC 文本,返回 Unix 毫秒。
范围、闰年和格式错误都是可恢复 datetime.invalid。
**点 = text.codepoints(文本)**
1. `长度(点) < 20 or 长度(点) > 24`
`if 长度(点) < 20 or 长度(点) > 24`
*失败("长度不是 20–24 个码点")*
`return 失败("长度不是 20–24 个码点")`
1. `点[4] != 45 or 点[7] != 45 or 点[10] != 84 or 点[13] != 58 or 点[16] != 58`
`else`
`if 点[4] != 45 or 点[7] != 45 or 点[10] != 84 or 点[13] != 58 or 点[16] != 58`
*失败("分隔符不符合 YYYY-MM-DDTHH:MM:SS")*
`return 失败("分隔符不符合 YYYY-MM-DDTHH:MM:SS")`
`end`
`end`
**年文本 = 片段(点, 0, 4)**
**月文本 = 片段(点, 5, 7)**
@@ -250,10 +282,11 @@ Howard Hinnant 的 civil-from-days 算法,输入为 1970-01-01 起的天数。
**秒文本 = 片段(点, 17, 19)**
1. `not 是数字串(年文本) or not 是数字串(月文本) or not 是数字串(日文本) or not 是数字串(时文本) or not 是数字串(分文本) or not 是数字串(秒文本)`
`if not 是数字串(年文本) or not 是数字串(月文本) or not 是数字串(日文本) or not 是数字串(时文本) or not 是数字串(分文本) or not 是数字串(秒文本)`
*失败("日期时间分量必须是数字")*
`return 失败("日期时间分量必须是数字")`
`end`
**年 = 整数(年文本)**
**月 = 整数(月文本)**
@@ -270,30 +303,38 @@ Howard Hinnant 的 civil-from-days 算法,输入为 1970-01-01 起的天数。
**结束 = 20**
1. `长度(点) >= 24 and 点[19] == 46 and 点[23] == 90`
`if 长度(点) >= 24 and 点[19] == 46 and 点[23] == 90`
**毫文本 = 片段(点, 20, 23)**
**毫文本 = 片段(点, 20, 23)**
**结束 = 24**
**结束 = 24**
1. `长度(点) != 结束 or 点[结束 - 1] != 90`
`else`
`if 长度(点) != 结束 or 点[结束 - 1] != 90`
*失败("必须以 Z 结尾")*
`return 失败("必须以 Z 结尾")`
1. `not 是数字串(毫文本)`
`else`
`if not 是数字串(毫文本)`
*失败("毫秒必须是数字")*
`return 失败("毫秒必须是数字")`
`end`
`end`
`end`
**毫 = 整数(毫文本)**
1. `年 < 1970 or 月 < 1 or 月 > 12 or 日 < 1 or 日 > 每月天数(年, 月)`
`if 年 < 1970 or 月 < 1 or 月 > 12 or 日 < 1 or 日 > 每月天数(年, 月)`
*失败("日期超出范围")*
`return 失败("日期超出范围")`
1. `时 < 0 or 时 > 23 or 分 < 0 or 分 > 59 or 秒 < 0 or 秒 > 59`
`else`
`if 时 < 0 or 时 > 23 or 分 < 0 or 分 > 59 or 秒 < 0 or 秒 > 59`
*失败("时间超出范围")*
`return 失败("时间超出范围")`
`end`
`end`
**毫秒 = 日期序号(年, 月, 日) * 86400000 + 时 * 3600000 + 分 * 60000 + 秒 * 1000 + 毫**
*{ok: true, value: 毫秒}*
`return {ok: true, value: 毫秒}`
+14 -12
View File
@@ -3,38 +3,40 @@ import:
io: "./io.mq.md"
---
## 演示函数
## @exec 演示函数
*1*
`return 1`
## main
## @exec main
### 公式
### @knowledge 公式
$$a = 1$$
### 代码
### @knowledge 代码
```text
print(1)
```
### @exec 主流程
**列表 = ["文本", 2, 1.5, [3, true], {a: 1, b: "x"}, None]**
> io.写值(列表)
> **io.写值(列表)**
> 打印(列表)
> **打印(列表)**
**表格 = 表(["名称", "分数"], [["甲", 87], ["乙", 92]])**
> io.写值(表格)
> **io.写值(表格)**
> 打印(表格)
> **打印(表格)**
**特殊 = [ref("#公式"), ref("#代码"), ref("#演示函数")]**
> io.写值(特殊)
> **io.写值(特殊)**
> 打印(特殊)
> **打印(特殊)**
*None*
`return None`
+15 -10
View File
@@ -1,25 +1,30 @@
# @exec env
## 读取
`(名称)`
`params(名称)`
读取一个显式授权的环境变量。名称是精确匹配,不支持 glob;未授权是
`permission.denied`,未设置是 `env.not_found`,非 UTF-8 是
`env.not_unicode`。
permission.denied,未设置是 env.not_found,非 UTF-8 是
env.not_unicode。
*resource.request("env.get", [名称])*
`return resource.request("env.get", [名称])`
## 存在
`(名称)`
`params(名称)`
**结果 = 读取(名称)**
1. `结果.ok`
`if 结果.ok`
*{ok: true, value: true}*
`return {ok: true, value: true}`
1. `结果.code == "env.not_found"`
`else`
`if 结果.code == "env.not_found"`
*{ok: true, value: false}*
`return {ok: true, value: false}`
*结果*
`end`
`end`
`return 结果`
+173 -106
View File
@@ -1,6 +1,8 @@
# @exec format
## 字节长度
`(文本)`
`params(文本)`
**点 = text.codepoints(文本)**
@@ -8,119 +10,156 @@
**下标 = 0**
- `下标 < 长度(点)`
`while 下标 < 长度(点)`
**码点 = 点[下标]**
**码点 = 点[下标]**
1. `码点 < 128`
`if 码点 < 128`
**总字节 = 总字节 + 1**
**总字节 = 总字节 + 1**
2. `码点 < 2048`
`else`
`if 码点 < 2048`
**总字节 = 总字节 + 2**
**总字节 = 总字节 + 2**
3. `码点 < 65536`
`else`
`if 码点 < 65536`
**总字节 = 总字节 + 3**
**总字节 = 总字节 + 3**
4. `true`
`else`
`if true`
**总字节 = 总字节 + 4**
**总字节 = 总字节 + 4**
**下标 = 下标 + 1**
`end`
`end`
`end`
`end`
**下标 = 下标 + 1**
*总字节*
`end`
`return 总字节`
## 显示
`(值)`
`params(值)`
按语言值语义格式化,用于与内置 `打印` 的输出对照。
按语言值语义格式化,用于与内置 打印 的输出对照。
覆盖 Unit/None/Bool/Int/Float/Text/List/Map/Table/Formula/Code/
FunctionRef/PluginHandle/Memory/Resource。
**类别 = 类型(值)**
1. `类别 == "Unit"`
`if 类别 == "Unit"`
*"Unit"*
`return "Unit"`
2. `类别 == "None"`
`else`
`if 类别 == "None"`
*"None"*
`return "None"`
3. `类别 == "Text"`
`else`
`if 类别 == "Text"`
*值*
`return 值`
4. `类别 == "List"`
`else`
`if 类别 == "List"`
*列表显示(值)*
`return 列表显示(值)`
5. `类别 == "Map"`
`else`
`if 类别 == "Map"`
*映射显示(值)*
`return 映射显示(值)`
6. `类别 == "Table"`
`else`
`if 类别 == "Table"`
*表格显示(值)*
`return 表格显示(值)`
7. `类别 == "Formula"`
`else`
`if 类别 == "Formula"`
*"Formula(" + 转义文本(值.latex) + ")"*
`return "Formula(" + 转义文本(值.latex) + ")"`
8. `类别 == "Code"`
`else`
`if 类别 == "Code"`
*"Code(" + 转义文本(值.language) + ", " + 文本(字节长度(值.source)) + " bytes)"*
`return "Code(" + 转义文本(值.language) + ", " + 文本(字节长度(值.source)) + " bytes)"`
9. `类别 == "FunctionRef"`
`else`
`if 类别 == "FunctionRef"`
*"FunctionRef(" + 值.module + "::" + 值.name + ")"*
`return "FunctionRef(" + 值.module + "::" + 值.name + ")"`
10. `类别 == "PluginHandle"`
`else`
`if 类别 == "PluginHandle"`
*"PluginHandle(" + 值.plugin + "::" + 值.export + ")"*
`return "PluginHandle(" + 值.plugin + "::" + 值.export + ")"`
11. `类别 == "Memory"`
`else`
`if 类别 == "Memory"`
*"Memory"*
`return "Memory"`
12. `类别 == "Resource"`
`else`
`if 类别 == "Resource"`
*"Resource"*
`return "Resource"`
13. `true`
`else`
`if true`
*文本(值)*
`return 文本(值)`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
## 列表显示
`(列表)`
`params(列表)`
**结果 = "["**
**下标 = 0**
- `下标 < 长度(列表)`
`while 下标 < 长度(列表)`
1. `下标 > 0`
`if 下标 > 0`
**结果 = 结果 + ", "**
**结果 = 结果 + ", "**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**结果 = 结果 + 值显示(列表[下标])**
`end`
`end`
**结果 = 结果 + 值显示(列表[下标])**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果 + "]"*
`end`
`return 结果 + "]"`
## 映射显示
`(映射)`
`params(映射)`
**键 = map.keys(映射)**
@@ -128,27 +167,31 @@ FunctionRef/PluginHandle/Memory/Resource。
**下标 = 0**
- `下标 < 长度(键)`
`while 下标 < 长度(键)`
1. `下标 > 0`
`if 下标 > 0`
**结果 = 结果 + ", "**
**结果 = 结果 + ", "**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**当前键 = 键[下标]**
`end`
`end`
**当前键 = 键[下标]**
**结果 = 结果 + 当前键 + ": " + 值显示(map.get(映射, 当前键))**
**结果 = 结果 + 当前键 + ": " + 值显示(map.get(映射, 当前键))**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果 + "}"*
`end`
`return 结果 + "}"`
## 表格显示
`(表格)`
`params(表格)`
**列 = table.columns(表格)**
@@ -156,77 +199,89 @@ FunctionRef/PluginHandle/Memory/Resource。
**行号 = 0**
- `行号 < 长度(表格)`
`while 行号 < 长度(表格)`
1. `行号 > 0`
`if 行号 > 0`
**结果 = 结果 + "; "**
**结果 = 结果 + "; "**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**行 = table.row(表格, 行号)**
`end`
`end`
**行 = table.row(表格, 行号)**
**单元格 = []**
**单元格 = []**
**列号 = 0**
**列号 = 0**
- `列号 < 长度(行)`
`while 列号 < 长度(行)`
**单元格 = list.append(单元格, 显示(行[列号]))**
**单元格 = list.append(单元格, 显示(行[列号]))**
**列号 = 列号 + 1**
**列号 = 列号 + 1**
**结果 = 结果 + 连接文本(单元格, " | ")**
`end`
**结果 = 结果 + 连接文本(单元格, " | ")**
**行号 = 行号 + 1**
**行号 = 行号 + 1**
*结果 + "}"*
`end`
`return 结果 + "}"`
## 连接文本
`(列表, 分隔)`
`params(列表, 分隔)`
**结果 = ""**
**下标 = 0**
- `下标 < 长度(列表)`
`while 下标 < 长度(列表)`
1. `下标 > 0`
`if 下标 > 0`
**结果 = 结果 + 分隔**
**结果 = 结果 + 分隔**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**结果 = 结果 + 列表[下标]**
`end`
`end`
**结果 = 结果 + 列表[下标]**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 值显示
`(值)`
`params(值)`
列表/映射/表格内部使用 repr 语义:Text 带引号并转义,其它值递归显示。
**类别 = 类型(值)**
1. `类别 == "Text"`
`if 类别 == "Text"`
*转义文本(值)*
`return 转义文本(值)`
2. `true`
`else`
`if true`
*显示(值)*
`return 显示(值)`
`end`
`end`
## 转义文本
`(文本)`
`params(文本)`
**点 = text.codepoints(文本)**
@@ -234,34 +289,46 @@ FunctionRef/PluginHandle/Memory/Resource。
**下标 = 0**
- `下标 < 长度(点)`
`while 下标 < 长度(点)`
**码点 = 点[下标]**
**码点 = 点[下标]**
1. `码点 == 34`
`if 码点 == 34`
**`结果 = 结果 + "\\\""`**
**`结果 = 结果 + "\\\""`**
2. `码点 == 92`
`else`
`if 码点 == 92`
**`结果 = 结果 + "\\\\"`**
**`结果 = 结果 + "\\\\"`**
3. `码点 == 10`
`else`
`if 码点 == 10`
**`结果 = 结果 + "\\n"`**
**`结果 = 结果 + "\\n"`**
4. `码点 == 9`
`else`
`if 码点 == 9`
**`结果 = 结果 + "\\t"`**
**`结果 = 结果 + "\\t"`**
5. `码点 == 13`
`else`
`if 码点 == 13`
**`结果 = 结果 + "\\r"`**
**`结果 = 结果 + "\\r"`**
6. `true`
`else`
`if true`
**结果 = 结果 + text.from_codepoint(码点)**
**结果 = 结果 + text.from_codepoint(码点)**
**下标 = 下标 + 1**
`end`
`end`
`end`
`end`
`end`
`end`
**下标 = 下标 + 1**
*`结果 + "\""`*
`end`
``return 结果 + "\""``
+100 -69
View File
@@ -3,12 +3,14 @@ import:
utf8: "../text/utf8.mq.md"
---
# @exec file
## 读文本
`(路径)`
`params(路径)`
以 UTF-8 读取一个有界的项目文件。文件在打开时整文件载入,上限 8 MiB;
结果使用可恢复 `Result` 形状。
结果使用可恢复 Result 形状。
**流 = resource.open("file", 路径, ["read"])**
@@ -18,32 +20,40 @@ import:
**关闭 = resource.close(流)**
1. `not 读取.ok`
`if not 读取.ok`
*读取*
`return 读取`
2. `not 关闭.ok`
`else`
`if not 关闭.ok`
*关闭*
`return 关闭`
3. `true`
`else`
`if true`
**文本 = utf8.解码(内存, 0, 读取.value.count)**
**文本 = utf8.解码(内存, 0, 读取.value.count)**
1. `not 文本.ok`
`if not 文本.ok`
*文本*
`return 文本`
2. `true`
`else`
`if true`
*{ok: true, value: 文本.value}*
`return {ok: true, value: 文本.value}`
`end`
`end`
`end`
`end`
`end`
## 写文本
`(路径, 文本)`
`params(路径, 文本)`
把文本按 UTF-8 写入项目文件。路径必须已经通过 `fs_write` 授权;
文件只在 `resource.close` 成功时创建或覆盖,写入缓冲上限 8 MiB。
把文本按 UTF-8 写入项目文件。路径必须已经通过 fs_write 授权;
文件只在 resource.close 成功时创建或覆盖,写入缓冲上限 8 MiB。
**内存 = memory.new(128, 128)**
@@ -55,24 +65,29 @@ import:
**关闭 = resource.close(流)**
1. `not 写入.ok`
`if not 写入.ok`
*写入*
`return 写入`
2. `not 关闭.ok`
`else`
`if not 关闭.ok`
*关闭*
`return 关闭`
3. `true`
`else`
`if true`
*{ok: true, value: {count: 写入.value.count}}*
`return {ok: true, value: {count: 写入.value.count}}`
`end`
`end`
`end`
## 复制文件
`(源, 目标)`
`params(源, 目标)`
按字节复制一个有界的项目文件。源读取和目标写入分别需要
`fs_read`/`fs_write` 授权,结果值与 [`写文本`](#写文本) 相同。
fs_read/fs_write 授权,结果值与 [写文本](#写文本) 相同。
**输入 = resource.open("file", 源, ["read"])**
@@ -82,125 +97,141 @@ import:
**关闭输入 = resource.close(输入)**
1. `not 读取.ok`
`if not 读取.ok`
*读取*
`return 读取`
2. `not 关闭输入.ok`
`else`
`if not 关闭输入.ok`
*关闭输入*
`return 关闭输入`
3. `true`
`else`
`if true`
**输出 = resource.open("file", 目标, ["write"])**
**输出 = resource.open("file", 目标, ["write"])**
**写入 = resource.write(输出, 内存, 0, 读取.value.count)**
**写入 = resource.write(输出, 内存, 0, 读取.value.count)**
**关闭输出 = resource.close(输出)**
**关闭输出 = resource.close(输出)**
1. `not 写入.ok`
`if not 写入.ok`
*写入*
`return 写入`
2. `not 关闭输出.ok`
`else`
`if not 关闭输出.ok`
*关闭输出*
`return 关闭输出`
3. `true`
`else`
`if true`
*{ok: true, value: {count: 写入.value.count}}*
`return {ok: true, value: {count: 写入.value.count}}`
`end`
`end`
`end`
`end`
`end`
`end`
## 存在
`(路径)`
`params(路径)`
*resource.request("fs.exists", [路径])*
`return resource.request("fs.exists", [路径])`
## 元数据
`(路径)`
`params(路径)`
*resource.request("fs.metadata", [路径])*
`return resource.request("fs.metadata", [路径])`
## 是文件
`(路径)`
`params(路径)`
**元数据 = resource.request("fs.metadata", [路径])**
1. `not 元数据.ok`
`if not 元数据.ok`
*元数据*
`return 元数据`
2. `true`
`else`
`if true`
*{ok: true, value: 元数据.value.kind == "file"}*
`return {ok: true, value: 元数据.value.kind == "file"}`
`end`
`end`
## 是目录
`(路径)`
`params(路径)`
**元数据 = resource.request("fs.metadata", [路径])**
1. `not 元数据.ok`
`if not 元数据.ok`
*元数据*
`return 元数据`
2. `true`
`else`
`if true`
*{ok: true, value: 元数据.value.kind == "directory"}*
`return {ok: true, value: 元数据.value.kind == "directory"}`
`end`
`end`
## 列出目录
`(路径)`
`params(路径)`
*resource.request("fs.list", [路径])*
`return resource.request("fs.list", [路径])`
## 创建目录
`(路径)`
`params(路径)`
*resource.request("fs.mkdir", [路径])*
`return resource.request("fs.mkdir", [路径])`
## 删除
`(路径)`
`params(路径)`
删除一个文件或空目录。非空目录返回 `fs.not_empty`,不递归删除。
删除一个文件或空目录。非空目录返回 fs.not_empty,不递归删除。
*resource.request("fs.remove", [路径])*
`return resource.request("fs.remove", [路径])`
## 重命名
`(源, 目标)`
`params(源, 目标)`
目标已存在时返回 `fs.exists`,不覆盖。
目标已存在时返回 fs.exists,不覆盖。
*resource.request("fs.rename", [源, 目标])*
`return resource.request("fs.rename", [源, 目标])`
## 追加文本
`(路径, 文本)`
`params(路径, 文本)`
把文本追加到项目文件;文件不存在时创建。仍受 8 MiB 单次读取上限和
`fs_write` 授权约束。
fs_write 授权约束。
*resource.request("fs.append", [路径, 文本])*
`return resource.request("fs.append", [路径, 文本])`
## 读取片段
`(路径, 偏移, 长度)`
`params(路径, 偏移, 长度)`
从偏移处读取最多 `长度` 字节,按 UTF-8 解码后返回文本。偏移/长度必须
从偏移处读取最多 长度 字节,按 UTF-8 解码后返回文本。偏移/长度必须
是非负整数,长度上限 8 MiB。
*resource.request("fs.read_at", [路径, 偏移, 长度])*
`return resource.request("fs.read_at", [路径, 偏移, 长度])`
## 遍历
`(路径)`
`params(路径)`
递归列出目录下的普通文件,返回相对项目根的路径列表。跳过符号链接,
深度上限 64,条目上限 4096。
*resource.request("fs.walk", [路径])*
`return resource.request("fs.walk", [路径])`
+12 -10
View File
@@ -5,34 +5,36 @@ import:
console: "./io/console.mq.md"
---
# @exec io
## 写文本
`(文本)`
`params(文本)`
*stream.写文本(文本)*
`return stream.写文本(文本)`
## 写全部
`(流, 内存, 起点, 长度)`
`params(流, 内存, 起点, 长度)`
*stream.写全部(流, 内存, 起点, 长度)*
`return stream.写全部(流, 内存, 起点, 长度)`
## 写值
`(值)`
`params(值)`
按语言值语义格式化后输出,并追加换行。
*stream.写文本(format.显示(值) + "\n")*
`return stream.写文本(format.显示(值) + "\n")`
## 读取行
`()`
`params()`
*console.读取行()*
`return console.读取行()`
## 打印
`(值)`
`params(值)`
*console.打印(值)*
`return console.打印(值)`
+73 -46
View File
@@ -5,12 +5,14 @@ import:
utf8: "../text/utf8.mq.md"
---
# @exec console
## 读取行
`()`
`params()`
从已授权的 `stdio/stdin` 资源读取一行。按有界块读取并增量解码 UTF-8;
EOF 返回 `{ok:false, code:"io.eof"}`,无效 UTF-8 返回可恢复错误。
从已授权的 stdio/stdin 资源读取一行。按有界块读取并增量解码 UTF-8;
EOF 返回 {ok:false, code:"io.eof"},无效 UTF-8 返回可恢复错误。
**流 = resource.open("stdio", "stdin", ["read"])**
@@ -22,98 +24,123 @@ EOF 返回 `{ok:false, code:"io.eof"}`,无效 UTF-8 返回可恢复错误。
**错误 = ""**
- `not 结束`
`while not 结束`
**读取 = resource.read(流, 内存, 0, 1)**
**读取 = resource.read(流, 内存, 0, 1)**
1. `not 读取.ok`
`if not 读取.ok`
**结束 = true**
**结束 = true**
**错误 = 读取.code**
**错误 = 读取.code**
2. `读取.value.eof and 读取.value.count == 0`
`else`
`if 读取.value.eof and 读取.value.count == 0`
**结束 = true**
**结束 = true**
3. `内存[0] == 10`
`else`
`if 内存[0] == 10`
**结束 = true**
**结束 = true**
4. `true`
`else`
`if true`
**字节 = list.append(字节, 内存[0])**
**字节 = list.append(字节, 内存[0])**
`end`
`end`
`end`
`end`
`end`
**关闭 = resource.close(流)**
1. `错误 != ""`
`if 错误 != ""`
*{ok: false, code: 错误, message: "stdin read failed"}*
`return {ok: false, code: 错误, message: "stdin read failed"}`
2. `not 关闭.ok`
`else`
`if not 关闭.ok`
*关闭*
`return 关闭`
3. `长度(字节) == 0`
`else`
`if 长度(字节) == 0`
*{ok: false, code: "io.eof", message: "end of input"}*
`return {ok: false, code: "io.eof", message: "end of input"}`
4. `true`
`else`
`if true`
**数据长度 = 长度(字节)**
**数据长度 = 长度(字节)**
1. `数据长度 > 0 and 字节[数据长度 - 1] == 13`
`if 数据长度 > 0 and 字节[数据长度 - 1] == 13`
**数据长度 = 数据长度 - 1**
**数据长度 = 数据长度 - 1**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**页 = (数据长度 + 65535) // 65536**
`end`
`end`
**页 = (数据长度 + 65535) // 65536**
**数据 = memory.new(页, 页)**
**数据 = memory.new(页, 页)**
**下标 = 0**
**下标 = 0**
- `下标 < 数据长度`
`while 下标 < 数据长度`
**`数据[下标] = 字节[下标]`**
**`数据[下标] = 字节[下标]`**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
**解码 = utf8.解码(数据, 0, 数据长度)**
`end`
**解码 = utf8.解码(数据, 0, 数据长度)**
1. `not 解码.ok`
`if not 解码.ok`
*解码*
`return 解码`
2. `true`
`else`
`if true`
*{ok: true, value: 解码.value}*
`return {ok: true, value: 解码.value}`
`end`
`end`
`end`
`end`
`end`
`end`
## 打印
`(值)`
`params(值)`
**结果 = stream.写文本(format.显示(值) + "\n")**
1. `not 结果.ok`
`if not 结果.ok`
*结果*
`return 结果`
2. `true`
`else`
`if true`
*{ok: true, value: None}*
`return {ok: true, value: None}`
`end`
`end`
## 写文本
`(文本)`
`params(文本)`
*stream.写文本(文本)*
`return stream.写文本(文本)`
## 写全部
`(流, 内存, 起点, 长度)`
`params(流, 内存, 起点, 长度)`
*stream.写全部(流, 内存, 起点, 长度)*
`return stream.写全部(流, 内存, 起点, 长度)`
+55 -34
View File
@@ -4,26 +4,31 @@ import:
utf8: "../text/utf8.mq.md"
---
# @exec stream
## 页数
`(字节)`
`params(字节)`
**页 = (字节 + 65535) // 65536**
1. `页 == 0`
`if 页 == 0`
*1*
`return 1`
2. `true`
`else`
`if true`
*页*
`return 页`
`end`
`end`
## 写全部
`(流, 内存, 起点, 长度)`
`params(流, 内存, 起点, 长度)`
把 `长度` 字节从 `内存` 写到资源流。短写只返回实际数量,调用方继续;
零进度返回 `io.write_zero`,不静默吞掉失败。
把 长度 字节从 内存 写到资源流。短写只返回实际数量,调用方继续;
零进度返回 io.write_zero,不静默吞掉失败。
**已写 = 0**
@@ -33,48 +38,59 @@ import:
**错误结果 = {ok: false, code: "io.write_zero", message: "resource.write made no progress"}**
- `已写 < 长度`
`while 已写 < 长度`
**剩余 = 长度 - 已写**
**剩余 = 长度 - 已写**
**本次 = resource.write(流, 内存, 起点 + 已写, 剩余)**
**本次 = resource.write(流, 内存, 起点 + 已写, 剩余)**
1. `not 本次.ok`
`if not 本次.ok`
**失败 = true**
**失败 = true**
**错误结果 = 本次**
**错误结果 = 本次**
**已写 = 长度**
**已写 = 长度**
2. `本次.value.count == 0`
`else`
`if 本次.value.count == 0`
**失败 = true**
**失败 = true**
**已写 = 长度**
**已写 = 长度**
3. `true`
`else`
`if true`
**已写 = 已写 + 本次.value.count**
**已写 = 已写 + 本次.value.count**
1. `失败`
`end`
`end`
`end`
`end`
`if 失败`
*错误结果*
`return 错误结果`
2. `已写 < 长度`
`else`
`if 已写 < 长度`
*错误结果*
`return 错误结果`
3. `true`
`else`
`if true`
*{ok: true, value: {count: 长度}}*
`return {ok: true, value: {count: 长度}}`
`end`
`end`
`end`
## 写文本
`(文本)`
`params(文本)`
把文本编码为 UTF-8 并写入已授权的 stdout 资源流。内存按实际字节长度增长,
写入循环检查 `{ok,count}`;只有全部字节写完并关闭成功才返回成功。
写入循环检查 {ok,count};只有全部字节写完并关闭成功才返回成功。
**字节数 = format.字节长度(文本)**
@@ -88,14 +104,19 @@ import:
**关闭 = resource.close(流)**
1. `not 写结果.ok`
`if not 写结果.ok`
*写结果*
`return 写结果`
2. `not 关闭.ok`
`else`
`if not 关闭.ok`
*关闭*
`return 关闭`
3. `true`
`else`
`if true`
*{ok: true, value: {count: 长度}}*
`return {ok: true, value: {count: 长度}}`
`end`
`end`
`end`
+184 -126
View File
@@ -3,117 +3,140 @@ import:
utf8: "../text/utf8.mq.md"
---
# @exec http
## 切片字节
`(字节, 起, 止)`
`params(字节, 起, 止)`
**结果 = []**
**下标 = 起**
- `下标 < 止 and 下标 < 长度(字节)`
`while 下标 < 止 and 下标 < 长度(字节)`
**结果 = list.append(结果, 字节[下标])**
**结果 = list.append(结果, 字节[下标])**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 找子串
`(字节, 子, 起点)`
`params(字节, 子, 起点)`
**结果 = 0 - 1**
**下标 = 起点**
- `下标 + 长度(子) <= 长度(字节) and 结果 < 0`
`while 下标 + 长度(子) <= 长度(字节) and 结果 < 0`
**偏移 = 0**
**偏移 = 0**
**匹配 = true**
**匹配 = true**
- `偏移 < 长度(子) and 匹配`
`while 偏移 < 长度(子) and 匹配`
1. `字节[下标 + 偏移] != 子[偏移]`
`if 字节[下标 + 偏移] != 子[偏移]`
**匹配 = false**
**匹配 = false**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**偏移 = 偏移 + 1**
`end`
`end`
**偏移 = 偏移 + 1**
1. `匹配`
`end`
`if 匹配`
**结果 = 下标**
**结果 = 下标**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 找字符
`(字节, 值, 起点)`
`params(字节, 值, 起点)`
**结果 = 0 - 1**
**下标 = 起点**
- `下标 < 长度(字节) and 结果 < 0`
`while 下标 < 长度(字节) and 结果 < 0`
1. `字节[下标] == 值`
`if 字节[下标] == 值`
**结果 = 下标**
**结果 = 下标**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 十六进制值
`(字节)`
`params(字节)`
**数值 = 0**
**下标 = 0**
- `下标 < 长度(字节)`
`while 下标 < 长度(字节)`
**值 = 字节[下标]**
**值 = 字节[下标]**
1. `值 >= 48 and 值 <= 57`
`if 值 >= 48 and 值 <= 57`
**数值 = 数值 * 16 + 值 - 48**
**数值 = 数值 * 16 + 值 - 48**
2. `值 >= 65 and 值 <= 70`
`else`
`if 值 >= 65 and 值 <= 70`
**数值 = 数值 * 16 + 值 - 55**
**数值 = 数值 * 16 + 值 - 55**
3. `值 >= 97 and 值 <= 102`
`else`
`if 值 >= 97 and 值 <= 102`
**数值 = 数值 * 16 + 值 - 87**
**数值 = 数值 * 16 + 值 - 87**
4. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**下标 = 下标 + 1**
`end`
`end`
`end`
`end`
**下标 = 下标 + 1**
*数值*
`end`
`return 数值`
## 文本字节
`(文本)`
`params(文本)`
把 UTF-8 文本编码为字节列表,上限 8 MiB。
@@ -125,43 +148,46 @@ import:
**下标 = 0**
- `下标 < 字节数`
`while 下标 < 字节数`
**结果 = list.append(结果, 内存[下标])**
**结果 = list.append(结果, 内存[下标])**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 字节文本
`(字节)`
`params(字节)`
把字节列表按 UTF-8 解码为文本,上限 8 MiB。
**长度值 = 长度(字节)**
1. `长度值 == 0`
`if 长度值 == 0`
*{ok: true, value: ""}*
`return {ok: true, value: ""}`
`end`
**页 = (长度值 + 65535) // 65536**
**内存 = memory.new(页, 页)**
**下标 = 0**
- `下标 < 长度值`
`while 下标 < 长度值`
**内存[下标] = 字节[下标]**
**内存[下标] = 字节[下标]**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*utf8.解码(内存, 0, 长度值)*
`end`
`return utf8.解码(内存, 0, 长度值)`
## 解码分块字节
`(体)`
`params(体)`
**结果 = []**
@@ -169,51 +195,62 @@ import:
**错误 = ""**
- `位置 < 长度(体) and 错误 == ""`
`while 位置 < 长度(体) and 错误 == ""`
**行尾 = 找子串(体, [13, 10], 位置)**
**行尾 = 找子串(体, [13, 10], 位置)**
1. `行尾 < 0`
`if 行尾 < 0`
**错误 = "http.chunked"**
**错误 = "http.chunked"**
2. `true`
`else`
`if true`
**大小 = 十六进制值(切片字节(体, 位置, 行尾))**
**大小 = 十六进制值(切片字节(体, 位置, 行尾))**
1. `大小 == 0`
`if 大小 == 0`
**位置 = 长度(体)**
**位置 = 长度(体)**
2. `位置 + 大小 + 4 > 长度(体)`
`else`
`if 位置 + 大小 + 4 > 长度(体)`
**错误 = "http.chunked"**
**错误 = "http.chunked"**
3. `true`
`else`
`if true`
**结果 = list.concat(结果, 切片字节(体, 行尾 + 2, 行尾 + 2 + 大小))**
**结果 = list.concat(结果, 切片字节(体, 行尾 + 2, 行尾 + 2 + 大小))**
**位置 = 行尾 + 2 + 大小 + 2**
**位置 = 行尾 + 2 + 大小 + 2**
1. `错误 != ""`
`end`
`end`
`end`
`end`
`end`
`end`
`if 错误 != ""`
*{ok: false, code: 错误, message: "分块长度无效"}*
`return {ok: false, code: 错误, message: "分块长度无效"}`
*{ok: true, value: 结果}*
`end`
`return {ok: true, value: 结果}`
## 解析响应字节
`(字节)`
`params(字节)`
解析 HTTP/1.1 响应字节。头部按 ASCII 解析,正文保持原始字节;chunked
长度以字节计。成功返回 `{ok:true, value:{status, reason, headers, body}}`。
长度以字节计。成功返回 {ok:true, value:{status, reason, headers, body}}。
**头部结束 = 找子串(字节, [13, 10, 13, 10], 0)**
1. `头部结束 < 0`
`if 头部结束 < 0`
*{ok: false, code: "http.invalid", message: "缺少头部结束"}*
`return {ok: false, code: "http.invalid", message: "缺少头部结束"}`
`end`
**头部 = 切片字节(字节, 0, 头部结束)**
**体 = 切片字节(字节, 头部结束 + 4, 长度(字节))**
@@ -224,123 +261,142 @@ import:
**下一行 = 找子串(头部, [13, 10], 0)**
- `下一行 >= 0`
`while 下一行 >= 0`
**行列表 = list.append(行列表, 切片字节(头部, 行起, 下一行))**
**行列表 = list.append(行列表, 切片字节(头部, 行起, 下一行))**
**行起 = 下一行 + 2**
**行起 = 下一行 + 2**
**下一行 = 找子串(头部, [13, 10], 行起)**
**下一行 = 找子串(头部, [13, 10], 行起)**
`end`
**行列表 = list.append(行列表, 切片字节(头部, 行起, 长度(头部)))**
1. `长度(行列表) == 0`
`if 长度(行列表) == 0`
*{ok: false, code: "http.invalid", message: "缺少状态行"}*
`return {ok: false, code: "http.invalid", message: "缺少状态行"}`
`end`
**状态行 = 字节文本(行列表[0])**
1. `not 状态行.ok`
`if not 状态行.ok`
*{ok: false, code: "http.invalid", message: "状态行不是 ASCII"}*
`return {ok: false, code: "http.invalid", message: "状态行不是 ASCII"}`
`end`
**状态字节 = 行列表[0]**
**第一空格 = 找字符(状态字节, 32, 0)**
**第二空格 = 找字符(状态字节, 32, 第一空格 + 1)**
1. `第一空格 < 0 or 第二空格 < 0`
`if 第一空格 < 0 or 第二空格 < 0`
*{ok: false, code: "http.invalid", message: "状态行格式无效"}*
`return {ok: false, code: "http.invalid", message: "状态行格式无效"}`
`end`
**状态文本 = 字节文本(切片字节(状态字节, 第一空格 + 1, 第二空格))**
1. `not 状态文本.ok`
`if not 状态文本.ok`
*{ok: false, code: "http.invalid", message: "状态码不是 ASCII"}*
`return {ok: false, code: "http.invalid", message: "状态码不是 ASCII"}`
`end`
**状态 = 整数(状态文本.value)**
**原因 = 字节文本(切片字节(状态字节, 第二空格 + 1, 长度(状态字节)))**
1. `not 原因.ok`
`if not 原因.ok`
*{ok: false, code: "http.invalid", message: "原因短语不是 ASCII"}*
`return {ok: false, code: "http.invalid", message: "原因短语不是 ASCII"}`
`end`
**头 = {}**
**行号 = 1**
- `行号 < 长度(行列表)`
`while 行号 < 长度(行列表)`
**行 = 行列表[行号]**
**行 = 行列表[行号]**
**冒号 = 找字符(行, 58, 0)**
**冒号 = 找字符(行, 58, 0)**
1. `冒号 >= 0`
`if 冒号 >= 0`
**名 = 字节文本(切片字节(行, 0, 冒号))**
**名 = 字节文本(切片字节(行, 0, 冒号))**
**值 = 字节文本(切片字节(行, 冒号 + 2, 长度(行)))**
**值 = 字节文本(切片字节(行, 冒号 + 2, 长度(行)))**
1. `名.ok and 值.ok`
`if 名.ok and 值.ok`
**头 = map.set(头, 名.value, 值.value)**
**头 = map.set(头, 名.value, 值.value)**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
2. `true`
`end`
`end`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**行号 = 行号 + 1**
`end`
`end`
**行号 = 行号 + 1**
`end`
**传输 = map.get(头, "Transfer-Encoding")**
**解码后 = 体**
1. `传输 == "chunked"`
`if 传输 == "chunked"`
**分块 = 解码分块字节(体)**
**分块 = 解码分块字节(体)**
1. `not 分块.ok`
`if not 分块.ok`
*分块*
`return 分块`
**解码后 = 分块.value**
`end`
**解码后 = 分块.value**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
*{ok: true, value: {status: 状态, reason: 原因.value, headers: 头, body: 解码后}}*
`end`
`end`
`return {ok: true, value: {status: 状态, reason: 原因.value, headers: 头, body: 解码后}}`
## 解析响应
`(文本)`
`params(文本)`
兼容文本 API:按字节解析后,把正文按 UTF-8 解码。
**响应 = 解析响应字节(文本字节(文本))**
1. `not 响应.ok`
`if not 响应.ok`
*{状态: 0, 原因: "", 头: {}, 体: ""}*
`return {状态: 0, 原因: "", 头: {}, 体: ""}`
`end`
**正文 = 字节文本(响应.value.body)**
1. `not 正文.ok`
`if not 正文.ok`
*{状态: 响应.value.status, 原因: 响应.value.reason, 头: 响应.value.headers, 体: ""}*
`return {状态: 响应.value.status, 原因: 响应.value.reason, 头: 响应.value.headers, 体: ""}`
*{状态: 响应.value.status, 原因: 响应.value.reason, 头: 响应.value.headers, 体: 正文.value}*
`end`
`return {状态: 响应.value.status, 原因: 响应.value.reason, 头: 响应.value.headers, 体: 正文.value}`
## 构建请求字节
`(方法, 路径, 头列表, 体字节)`
`params(方法, 路径, 头列表, 体字节)`
构建 HTTP/1.1 请求字节。方法、路径、头名/值按 UTF-8 编码;正文使用
传入的字节列表。
@@ -349,21 +405,22 @@ import:
**下标 = 0**
- `下标 < 长度(头列表)`
`while 下标 < 长度(头列表)`
**头 = 头列表[下标]**
**头 = 头列表[下标]**
**结果 = list.concat(结果, 文本字节(文本(头[0]) + ": " + 文本(头[1]) + "\r\n"))**
**结果 = list.concat(结果, 文本字节(文本(头[0]) + ": " + 文本(头[1]) + "\r\n"))**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
`end`
**结果 = list.concat(结果, [13, 10])**
*list.concat(结果, 体字节)*
`return list.concat(结果, 体字节)`
## 构建请求
`(方法, 路径, 头列表, 体文本)`
`params(方法, 路径, 头列表, 体文本)`
兼容文本 API,正文按 UTF-8 编码。
@@ -371,8 +428,9 @@ import:
**文本结果 = 字节文本(请求)**
1. `not 文本结果.ok`
`if not 文本结果.ok`
*""*
`return ""`
*文本结果.value*
`end`
`return 文本结果.value`
+95 -64
View File
@@ -1,22 +1,27 @@
# @exec path
## 是否绝对
`(路径)`
`params(路径)`
**点 = text.codepoints(路径)**
1. `长度(点) == 0`
`if 长度(点) == 0`
*false*
`return false`
2. `点[0] == 47`
`else`
`if 点[0] == 47`
*true*
`return true`
*false*
`end`
`end`
`return false`
## 分割
`(文本, 分隔码点)`
`params(文本, 分隔码点)`
**点 = text.codepoints(文本)**
@@ -26,65 +31,76 @@
**下标 = 0**
- `下标 < 长度(点)`
`while 下标 < 长度(点)`
1. `点[下标] == 分隔码点`
`if 点[下标] == 分隔码点`
**结果 = list.append(结果, 当前)**
**结果 = list.append(结果, 当前)**
**当前 = ""**
**当前 = ""**
2. `true`
`else`
`if true`
**当前 = 当前 + text.from_codepoint(点[下标])**
**当前 = 当前 + text.from_codepoint(点[下标])**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
*list.append(结果, 当前)*
`end`
`return list.append(结果, 当前)`
## 连接
`(片段列表)`
`params(片段列表)`
空片段被跳过,片段之间只插入一个 `/`。
空片段被跳过,片段之间只插入一个 /。
**结果 = ""**
**下标 = 0**
- `下标 < 长度(片段列表)`
`while 下标 < 长度(片段列表)`
**片段 = 文本(片段列表[下标])**
**片段 = 文本(片段列表[下标])**
1. `片段 != ""`
`if 片段 != ""`
1. `结果 == ""`
`if 结果 == ""`
**结果 = 片段**
**结果 = 片段**
2. `true`
`else`
`if true`
**结果 = 结果 + "/" + 片段**
**结果 = 结果 + "/" + 片段**
2. `true`
`end`
`end`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 文件名
`(路径)`
`params(路径)`
**片段 = 分割(路径, 47)**
*片段[长度(片段) - 1]*
`return 片段[长度(片段) - 1]`
## 目录名
`(路径)`
`params(路径)`
**片段 = 分割(路径, 47)**
@@ -92,50 +108,53 @@
**下标 = 0**
- `下标 < 长度(片段) - 1`
`while 下标 < 长度(片段) - 1`
**结果 = list.append(结果, 片段[下标])**
**结果 = list.append(结果, 片段[下标])**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*连接(结果)*
`end`
`return 连接(结果)`
## 扩展名
`(路径)`
`params(路径)`
**名字 = 文件名(路径)**
**点列表 = 分割(名字, 46)**
1. `长度(点列表) <= 1`
`if 长度(点列表) <= 1`
*""*
`return ""`
*点列表[长度(点列表) - 1]*
`end`
`return 点列表[长度(点列表) - 1]`
## 去尾
`(列表)`
`params(列表)`
**结果 = []**
**下标 = 0**
- `下标 < 长度(列表) - 1`
`while 下标 < 长度(列表) - 1`
**结果 = list.append(结果, 列表[下标])**
**结果 = list.append(结果, 列表[下标])**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 规范
`(路径)`
`params(路径)`
词法规范化:折叠 `.`、空片段和重复 `/`,用 `..` 消去前一片段;
绝对路径保留前导 `/`。不访问文件系统。
词法规范化:折叠 .、空片段和重复 /,用 .. 消去前一片段;
绝对路径保留前导 /。不访问文件系统。
**片段 = 分割(路径, 47)**
@@ -145,36 +164,48 @@
**下标 = 0**
- `下标 < 长度(片段)`
`while 下标 < 长度(片段)`
**段 = 片段[下标]**
**段 = 片段[下标]**
1. `段 == "" or 段 == "."`
`if 段 == "" or 段 == "."`
**忽略 = 0**
**忽略 = 0**
2. `段 == ".."`
`else`
`if 段 == ".."`
1. `长度(栈) > 0 and 栈[长度(栈) - 1] != ".."`
`if 长度(栈) > 0 and 栈[长度(栈) - 1] != ".."`
**栈 = 去尾(栈)**
**栈 = 去尾(栈)**
2. `not 绝对`
`else`
`if not 绝对`
**栈 = list.append(栈, 段)**
**栈 = list.append(栈, 段)**
3. `true`
`else`
`if true`
**忽略绝对根 = 0**
**忽略绝对根 = 0**
3. `true`
`end`
`end`
`end`
`else`
`if true`
**栈 = list.append(栈, 段)**
**栈 = list.append(栈, 段)**
**下标 = 下标 + 1**
`end`
`end`
`end`
**下标 = 下标 + 1**
1. `绝对`
`end`
`if 绝对`
*"/" + 连接(栈)*
`return "/" + 连接(栈)`
*连接(栈)*
`end`
`return 连接(栈)`
+6 -4
View File
@@ -1,10 +1,12 @@
# @exec process
## 运行
`(程序, 参数列表)`
`params(程序, 参数列表)`
在项目模式下运行一个显式授权的可执行文件。程序路径必须与
`--allow-process PROGRAM` 精确匹配;不经过 shell,清空环境变量,
--allow-process PROGRAM 精确匹配;不经过 shell,清空环境变量,
工作目录是项目根,stdin 为空。5 秒超时、1 MiB stdout/stderr 上限,
结果形状为 `{status, stdout, stderr}`。
结果形状为 {status, stdout, stderr}。
*resource.request("process.run", [程序, 参数列表])*
`return resource.request("process.run", [程序, 参数列表])`
+19 -14
View File
@@ -1,37 +1,42 @@
# @exec random
## 字节
`(数量)`
`params(数量)`
读取 `数量` 个 OS 熵字节,返回 `List<Int>`(每个 0–255)。仅项目模式,
需要显式 `--allow-random`;`pure`/`strict` 拒绝。
读取 数量 个 OS 熵字节,返回 List<Int>(每个 0–255)。仅项目模式,
需要显式 --allow-random;pure/strict 拒绝。
*resource.request("random.bytes", [数量])*
`return resource.request("random.bytes", [数量])`
## 整数
`(上限)`
`params(上限)`
返回 `0 <= 值 < 上限` 的整数。`上限` 必须大于 0;使用 8 个熵字节
返回 0 <= 值 < 上限 的整数。上限 必须大于 0;使用 8 个熵字节
组合后取模(无偏拒绝采样尚未实现)。
1. `上限 <= 0`
`if 上限 <= 0`
*{ok: false, code: "random.invalid", message: "上限必须大于 0"}*
`return {ok: false, code: "random.invalid", message: "上限必须大于 0"}`
`end`
**字节结果 = 字节(8)**
1. `not 字节结果.ok`
`if not 字节结果.ok`
*字节结果*
`return 字节结果`
`end`
**值 = 0**
**下标 = 0**
- `下标 < 8`
`while 下标 < 8`
**值 = 值 * 256 + 字节结果.value[下标]**
**值 = 值 * 256 + 字节结果.value[下标]**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*{ok: true, value: 值 % 上限}*
`end`
`return {ok: true, value: 值 % 上限}`
+264 -181
View File
@@ -1,224 +1,260 @@
# @exec regex
## 成功
`(值)`
`params(值)`
*{ok: true, value: 值}*
`return {ok: true, value: 值}`
## 失败
`(代码, 消息)`
`params(代码, 消息)`
*{ok: false, code: 代码, message: 消息}*
`return {ok: false, code: 代码, message: 消息}`
## 包含
`(列表, 值)`
`params(列表, 值)`
**结果 = false**
**下标 = 0**
- `下标 < 长度(列表) and not 结果`
`while 下标 < 长度(列表) and not 结果`
1. `列表[下标] == 值`
`if 列表[下标] == 值`
**结果 = true**
**结果 = true**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 去头
`(列表)`
`params(列表)`
**结果 = []**
**下标 = 1**
- `下标 < 长度(列表)`
`while 下标 < 长度(列表)`
**结果 = list.append(结果, 列表[下标])**
**结果 = list.append(结果, 列表[下标])**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 设置最后
`(列表, 值)`
`params(列表, 值)`
**结果 = []**
**下标 = 0**
- `下标 < 长度(列表)`
`while 下标 < 长度(列表)`
1. `下标 + 1 == 长度(列表)`
`if 下标 + 1 == 长度(列表)`
**结果 = list.append(结果, 值)**
**结果 = list.append(结果, 值)**
2. `true`
`else`
`if true`
**结果 = list.append(结果, 列表[下标])**
**结果 = list.append(结果, 列表[下标])**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 片段
`(点, 起点, 终点)`
`params(点, 起点, 终点)`
**结果 = ""**
**下标 = 起点**
- `下标 < 终点`
`while 下标 < 终点`
**结果 = 结果 + text.from_codepoint(点[下标])**
**结果 = 结果 + text.from_codepoint(点[下标])**
**下标 = 下标 + 1**
**下标 = 下标 + 1**
*结果*
`end`
`return 结果`
## 是数字
`(码点)`
`params(码点)`
*码点 >= 48 and 码点 <= 57*
`return 码点 >= 48 and 码点 <= 57`
## 字面令牌
`(码点)`
`params(码点)`
包含数量词,默认恰好一次。
*{kind: "literal", value: 码点, neg: false, min: 1, max: 1}*
`return {kind: "literal", value: 码点, neg: false, min: 1, max: 1}`
## 任意令牌
`()`
`params()`
*{kind: "any", value: 0, neg: false, min: 1, max: 1}*
`return {kind: "any", value: 0, neg: false, min: 1, max: 1}`
## 类令牌
`(集合, 否定)`
`params(集合, 否定)`
*{kind: "class", value: 集合, neg: 否定, min: 1, max: 1}*
`return {kind: "class", value: 集合, neg: 否定, min: 1, max: 1}`
## 锚点令牌
`(方向)`
`params(方向)`
*{kind: "anchor", value: 方向, neg: false, min: 1, max: 1}*
`return {kind: "anchor", value: 方向, neg: false, min: 1, max: 1}`
## 设置量词
`(令牌, 码点)`
`params(令牌, 码点)`
1. `码点 == 42`
`if 码点 == 42`
*{kind: 令牌.kind, value: 令牌.value, neg: 令牌.neg, min: 0, max: -1}*
`return {kind: 令牌.kind, value: 令牌.value, neg: 令牌.neg, min: 0, max: -1}`
2. `码点 == 43`
`else`
`if 码点 == 43`
*{kind: 令牌.kind, value: 令牌.value, neg: 令牌.neg, min: 1, max: -1}*
`return {kind: 令牌.kind, value: 令牌.value, neg: 令牌.neg, min: 1, max: -1}`
*{kind: 令牌.kind, value: 令牌.value, neg: 令牌.neg, min: 0, max: 1}*
`end`
`end`
`return {kind: 令牌.kind, value: 令牌.value, neg: 令牌.neg, min: 0, max: 1}`
## 编译类
`(点, 位置)`
`params(点, 位置)`
**当前 = 位置 + 1**
**否定 = false**
1. `当前 < 长度(点) and 点[当前] == 94`
`if 当前 < 长度(点) and 点[当前] == 94`
**否定 = true**
**否定 = true**
**当前 = 当前 + 1**
**当前 = 当前 + 1**
2. `true`
`else`
`if true`
**忽略否定 = 0**
**忽略否定 = 0**
`end`
`end`
**集合 = []**
**完成 = false**
**错误 = ""**
- `当前 < 长度(点) and not 完成 and 错误 == ""`
`while 当前 < 长度(点) and not 完成 and 错误 == ""`
**码点 = 点[当前]**
**码点 = 点[当前]**
1. `码点 == 93`
`if 码点 == 93`
**完成 = true**
**完成 = true**
**当前 = 当前 + 1**
**当前 = 当前 + 1**
2. `码点 == 92`
`else`
`if 码点 == 92`
1. `当前 + 1 >= 长度(点)`
`if 当前 + 1 >= 长度(点)`
**错误 = "regex.invalid"**
**错误 = "regex.invalid"**
2. `true`
`else`
`if true`
**集合 = list.append(集合, 点[当前 + 1])**
**集合 = list.append(集合, 点[当前 + 1])**
**当前 = 当前 + 2**
**当前 = 当前 + 2**
3. `当前 + 2 < 长度(点) and 点[当前 + 1] == 45 and 点[当前 + 2] != 93`
`end`
`end`
`else`
`if 当前 + 2 < 长度(点) and 点[当前 + 1] == 45 and 点[当前 + 2] != 93`
**开始 = 码点**
**开始 = 码点**
**结束 = 点[当前 + 2]**
**结束 = 点[当前 + 2]**
1. `开始 > 结束`
`if 开始 > 结束`
**错误 = "regex.invalid"**
**错误 = "regex.invalid"**
2. `true`
`else`
`if true`
**值 = 开始**
**值 = 开始**
- `值 <= 结束`
`while 值 <= 结束`
**集合 = list.append(集合, 值)**
**集合 = list.append(集合, 值)**
**值 = 值 + 1**
**值 = 值 + 1**
**当前 = 当前 + 3**
`end`
**当前 = 当前 + 3**
4. `true`
`end`
`end`
`else`
`if true`
**集合 = list.append(集合, 码点)**
**集合 = list.append(集合, 码点)**
**当前 = 当前 + 1**
**当前 = 当前 + 1**
1. `not 完成`
`end`
`end`
`end`
`end`
`end`
`if not 完成`
*失败("regex.invalid", "字符类未闭合")*
`return 失败("regex.invalid", "字符类未闭合")`
1. `错误 != ""`
`else`
`if 错误 != ""`
*失败(错误, "字符类范围无效")*
`return 失败(错误, "字符类范围无效")`
*成功({set: 集合, neg: 否定, next: 当前})*
`end`
`end`
`return 成功({set: 集合, neg: 否定, next: 当前})`
## 编译
`(点, 位置)`
`params(点, 位置)`
**令牌表 = []**
@@ -228,189 +264,232 @@
**代码 = ""**
- `当前 < 长度(点) and 错误 == ""`
`while 当前 < 长度(点) and 错误 == ""`
**码点 = 点[当前]**
**码点 = 点[当前]**
1. `码点 == 94`
`if 码点 == 94`
**令牌表 = list.append(令牌表, 锚点令牌("start"))**
**令牌表 = list.append(令牌表, 锚点令牌("start"))**
**当前 = 当前 + 1**
**当前 = 当前 + 1**
2. `码点 == 36`
`else`
`if 码点 == 36`
**令牌表 = list.append(令牌表, 锚点令牌("end"))**
**令牌表 = list.append(令牌表, 锚点令牌("end"))**
**当前 = 当前 + 1**
**当前 = 当前 + 1**
3. `码点 == 91`
`else`
`if 码点 == 91`
**类结果 = 编译类(点, 当前)**
**类结果 = 编译类(点, 当前)**
1. `not 类结果.ok`
`if not 类结果.ok`
**错误 = 类结果.code**
**错误 = 类结果.code**
**代码 = 类结果.message**
**代码 = 类结果.message**
2. `true`
`else`
`if true`
**令牌表 = list.append(令牌表, 类令牌(类结果.value.set, 类结果.value.neg))**
**令牌表 = list.append(令牌表, 类令牌(类结果.value.set, 类结果.value.neg))**
**当前 = 类结果.value.next**
**当前 = 类结果.value.next**
4. `码点 == 92`
`end`
`end`
`else`
`if 码点 == 92`
1. `当前 + 1 >= 长度(点)`
`if 当前 + 1 >= 长度(点)`
**错误 = "regex.invalid"**
**错误 = "regex.invalid"**
**代码 = "转义缺少字符"**
**代码 = "转义缺少字符"**
2. `true`
`else`
`if true`
**令牌表 = list.append(令牌表, 字面令牌(点[当前 + 1]))**
**令牌表 = list.append(令牌表, 字面令牌(点[当前 + 1]))**
**当前 = 当前 + 2**
**当前 = 当前 + 2**
5. `码点 == 46`
`end`
`end`
`else`
`if 码点 == 46`
**令牌表 = list.append(令牌表, 任意令牌())**
**令牌表 = list.append(令牌表, 任意令牌())**
**当前 = 当前 + 1**
**当前 = 当前 + 1**
6. `码点 == 40 or 码点 == 41 or 码点 == 124`
`else`
`if 码点 == 40 or 码点 == 41 or 码点 == 124`
**错误 = "regex.unsupported"**
**错误 = "regex.unsupported"**
**代码 = "不支持分组或选择"**
**代码 = "不支持分组或选择"**
7. `码点 == 42 or 码点 == 43 or 码点 == 63`
`else`
`if 码点 == 42 or 码点 == 43 or 码点 == 63`
**错误 = "regex.invalid"**
**错误 = "regex.invalid"**
**代码 = "量词没有前一项"**
**代码 = "量词没有前一项"**
8. `true`
`else`
`if true`
**令牌表 = list.append(令牌表, 字面令牌(码点))**
**令牌表 = list.append(令牌表, 字面令牌(码点))**
**当前 = 当前 + 1**
**当前 = 当前 + 1**
- `错误 == "" and 当前 < 长度(点) and (点[当前] == 42 or 点[当前] == 43 or 点[当前] == 63)`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`while 错误 == "" and 当前 < 长度(点) and (点[当前] == 42 or 点[当前] == 43 or 点[当前] == 63)`
**令牌表 = 设置最后(令牌表, 设置量词(令牌表[长度(令牌表) - 1], 点[当前]))**
**令牌表 = 设置最后(令牌表, 设置量词(令牌表[长度(令牌表) - 1], 点[当前]))**
**当前 = 当前 + 1**
**当前 = 当前 + 1**
- `当前 < 长度(点) and (点[当前] == 42 or 点[当前] == 43 or 点[当前] == 63)`
`while 当前 < 长度(点) and (点[当前] == 42 or 点[当前] == 43 or 点[当前] == 63)`
**错误 = "regex.invalid"**
**错误 = "regex.invalid"**
**代码 = "连续量词无效"**
**代码 = "连续量词无效"**
1. `错误 != ""`
`end`
`end`
`end`
`if 错误 != ""`
*失败(错误, 代码)*
`return 失败(错误, 代码)`
*成功(令牌表)*
`end`
`return 成功(令牌表)`
## 单字符匹配
`(令牌, 码点)`
`params(令牌, 码点)`
**类别 = 令牌.kind**
1. `类别 == "any"`
`if 类别 == "any"`
*true*
`return true`
2. `类别 == "literal"`
`else`
`if 类别 == "literal"`
*令牌.value == 码点*
`return 令牌.value == 码点`
3. `类别 == "class"`
`else`
`if 类别 == "class"`
*包含(令牌.value, 码点) != 令牌.neg*
`return 包含(令牌.value, 码点) != 令牌.neg`
*false*
`end`
`end`
`end`
`return false`
## 尝试匹配
`(令牌, 下标, 当前, 点, 位置, 次数, 要求结束)`
`params(令牌, 下标, 当前, 点, 位置, 次数, 要求结束)`
**下限 = 当前.min**
**上限 = 当前.max**
1. `次数 >= 下限 and 匹配序列(令牌, 下标 + 1, 点, 位置, 要求结束)`
`if 次数 >= 下限 and 匹配序列(令牌, 下标 + 1, 点, 位置, 要求结束)`
*true*
`return true`
1. `上限 >= 0 and 次数 >= 上限`
`else`
`if 上限 >= 0 and 次数 >= 上限`
*false*
`return false`
1. `位置 < 长度(点) and 单字符匹配(当前, 点[位置])`
`else`
`if 位置 < 长度(点) and 单字符匹配(当前, 点[位置])`
*尝试匹配(令牌, 下标, 当前, 点, 位置 + 1, 次数 + 1, 要求结束)*
`return 尝试匹配(令牌, 下标, 当前, 点, 位置 + 1, 次数 + 1, 要求结束)`
*false*
`end`
`end`
`end`
`return false`
## 匹配序列
`(令牌, 下标, 点, 位置, 要求结束)`
`params(令牌, 下标, 点, 位置, 要求结束)`
1. `下标 >= 长度(令牌)`
`if 下标 >= 长度(令牌)`
1. `要求结束`
`if 要求结束`
*位置 == 长度(点)*
`return 位置 == 长度(点)`
*true*
`end`
`return true`
`end`
**当前 = 令牌[下标]**
1. `当前.kind == "anchor"`
`if 当前.kind == "anchor"`
1. `当前.value == "start" and 位置 == 0`
`if 当前.value == "start" and 位置 == 0`
*匹配序列(令牌, 下标 + 1, 点, 位置, 要求结束)*
`return 匹配序列(令牌, 下标 + 1, 点, 位置, 要求结束)`
2. `当前.value == "end" and 位置 == 长度(点)`
`else`
`if 当前.value == "end" and 位置 == 长度(点)`
*匹配序列(令牌, 下标 + 1, 点, 位置, 要求结束)*
`return 匹配序列(令牌, 下标 + 1, 点, 位置, 要求结束)`
*false*
`end`
`end`
`return false`
*尝试匹配(令牌, 下标, 当前, 点, 位置, 0, 要求结束)*
`end`
`return 尝试匹配(令牌, 下标, 当前, 点, 位置, 0, 要求结束)`
## 匹配
`(模式, 文本)`
`params(模式, 文本)`
编译后要求整个文本匹配。支持 `^`、`$`、`.`、`*`、`+`、`?`、
`[...]` 和 `\\` 转义;不支持分组和选择。
编译后要求整个文本匹配。支持 ^、$、.、*、+、?、
[...] 和 \\ 转义;不支持分组和选择。
**编译结果 = 编译(text.codepoints(模式), 0)**
1. `not 编译结果.ok`
`if not 编译结果.ok`
*编译结果*
`return 编译结果`
*{ok: true, value: 匹配序列(编译结果.value, 0, text.codepoints(文本), 0, true)}*
`end`
`return {ok: true, value: 匹配序列(编译结果.value, 0, text.codepoints(文本), 0, true)}`
## 搜索
`(模式, 文本)`
`params(模式, 文本)`
**编译结果 = 编译(text.codepoints(模式), 0)**
1. `not 编译结果.ok`
`if not 编译结果.ok`
*编译结果*
`return 编译结果`
`end`
**令牌 = 编译结果.value**
**点 = text.codepoints(文本)**
@@ -419,40 +498,44 @@
**结果 = false**
- `下标 <= 长度(点) and not 结果`
`while 下标 <= 长度(点) and not 结果`
1. `匹配序列(令牌, 0, 点, 下标, false)`
`if 匹配序列(令牌, 0, 点, 下标, false)`
**结果 = true**
**结果 = true**
2. `true`
`else`
`if true`
**忽略 = 0**
**忽略 = 0**
**下标 = 下标 + 1**
`end`
`end`
**下标 = 下标 + 1**
*成功(结果)*
`end`
`return 成功(结果)`
## 扩展匹配
`(模式, 文本)`
`params(模式, 文本)`
使用宿主正则引擎(支持分组、选择、`\\d` 等)判断是否匹配。模式无效时
返回 `regex.invalid`。仅项目模式;纯 `.mq.md` 子集仍由 `匹配`/`搜索` 提供。
使用宿主正则引擎(支持分组、选择、\\d 等)判断是否匹配。模式无效时
返回 regex.invalid。仅项目模式;纯 .mq.md 子集仍由 匹配/搜索 提供。
*resource.request("regex.match", [模式, 文本])*
`return resource.request("regex.match", [模式, 文本])`
## 扩展搜索
`(模式, 文本)`
`params(模式, 文本)`
*resource.request("regex.match", [模式, 文本])*
`return resource.request("regex.match", [模式, 文本])`
## 捕获
`(模式, 文本)`
`params(模式, 文本)`
返回 `{ok:true, value:{matched:Bool, groups:List<Text|None>}}`。下标 0 是
完整匹配;未参与匹配的分组是 `None`。
返回 {ok:true, value:{matched:Bool, groups:List<Text|None>}}。下标 0 是
完整匹配;未参与匹配的分组是 None。
*resource.request("regex.captures", [模式, 文本])*
`return resource.request("regex.captures", [模式, 文本])`
+1 -1
View File
@@ -1,5 +1,5 @@
{
"name": "marqdo-stdlib",
"version": "0.1.0",
"digest": "sha256:9a921f5fc7a929cee1fa4b4d8f2b401a3bf69198d1a753b5dc8de5d28d46583f"
"digest": "sha256:c3fca0cc3bd8f89f0f45d52418113613dd0613711cfdba76b514e5e6244409d2"
}
+3 -1
View File
@@ -3,8 +3,10 @@ import:
clock: "std:clock"
---
# @exec clock
## main
**现在 = clock.现在()**
*[现在.ok, 类型(现在.value), 现在.value > 1600000000000]*
`return [现在.ok, 类型(现在.value), 现在.value > 1600000000000]`
+3 -1
View File
@@ -3,10 +3,12 @@ import:
compress: "std:compress"
---
# @exec compress
## main
**压缩结果 = compress.压缩("hello 世界")**
**解压结果 = compress.解压(压缩结果.value)**
*[压缩结果.ok, 长度(压缩结果.value) > 0, 解压结果.ok, 解压结果.value]*
`return [压缩结果.ok, 长度(压缩结果.value) > 0, 解压结果.ok, 解压结果.value]`
+3 -1
View File
@@ -3,8 +3,10 @@ import:
console: "std:io/console"
---
# @exec console
## main
**行 = console.读取行()**
*[行.ok, 行.value]*
`return [行.ok, 行.value]`
+3 -1
View File
@@ -3,6 +3,8 @@ import:
csv: "std:data/csv"
---
# @exec csv
## main
**`行 = csv.解析行("甲,\"乙,丙\",\"说\"\"好\"")`**
@@ -17,4 +19,4 @@ import:
**格式化 = csv.格式化(多行.value)**
*[行.value, csv.格式化行(行.value), 空.value, 坏.code, 框.value, 多行.ok, 多行.value, 格式化]*
`return [行.value, csv.格式化行(行.value), 空.value, 坏.code, 框.value, 多行.ok, 多行.value, 格式化]`
+3 -1
View File
@@ -3,6 +3,8 @@ import:
datetime: "std:datetime"
---
# @exec datetime
## main
*[datetime.格式化(0), datetime.格式化(1700000000123), datetime.解析("1970-01-01T00:00:00Z").value, datetime.解析("2026-11-21T08:00:00.123Z").value, datetime.解析("2026-13-01T00:00:00Z").ok, datetime.解析("2026-02-29T00:00:00Z").ok, datetime.格式化(-1)]*
`return [datetime.格式化(0), datetime.格式化(1700000000123), datetime.解析("1970-01-01T00:00:00Z").value, datetime.解析("2026-11-21T08:00:00.123Z").value, datetime.解析("2026-13-01T00:00:00Z").ok, datetime.解析("2026-02-29T00:00:00Z").ok, datetime.格式化(-1)]`
+3 -1
View File
@@ -3,6 +3,8 @@ import:
demo: "std:demo"
---
# @exec demo
## main
*demo.演示函数()*
`return demo.演示函数()`
+3 -1
View File
@@ -3,6 +3,8 @@ import:
env: "std:env"
---
# @exec env
## main
**存在 = env.存在("MARQDO_TEST_ENV")**
@@ -11,4 +13,4 @@ import:
**缺失 = env.读取("MARQDO_MISSING_ENV")**
*[存在.ok, 存在.value, 读取.ok, 读取.value, 缺失.ok, 缺失.code]*
`return [存在.ok, 存在.value, 读取.ok, 读取.value, 缺失.ok, 缺失.code]`
+3 -1
View File
@@ -3,6 +3,8 @@ import:
format: "std:format"
---
# @exec format
## main
*[format.字节长度("Aé"), format.显示(["文本", 2, 1.5]), format.显示({a: 1}), format.列表显示(["a", 2]), format.显示(None)]*
`return [format.字节长度("Aé"), format.显示(["文本", 2, 1.5]), format.显示({a: 1}), format.列表显示(["a", 2]), format.显示(None)]`
+3 -1
View File
@@ -3,6 +3,8 @@ import:
fs: "std:fs/file"
---
# @exec fs
## main
**创建 = fs.创建目录("out")**
@@ -33,4 +35,4 @@ import:
**删除目录 = fs.删除("out")**
*[创建.ok, 写入.value.count, 存在.value, 元数据.value.kind, 元数据.value.size, 列表.value, 是文件.value, 是目录.value, 重命名.ok, 读取.value, 追加.value, 片段.value, 遍历.value, 删除.ok, 删除目录.ok]*
`return [创建.ok, 写入.value.count, 存在.value, 元数据.value.kind, 元数据.value.size, 列表.value, 是文件.value, 是目录.value, 重命名.ok, 读取.value, 追加.value, 片段.value, 遍历.value, 删除.ok, 删除目录.ok]`
+3 -1
View File
@@ -3,6 +3,8 @@ import:
http: "std:net/http"
---
# @exec http
## main
**响应文本 = "HTTP/1.1 200 OK\r\nContent-Type: text/plain\r\nTransfer-Encoding: chunked\r\n\r\n5\r\nhello\r\n6\r\n world\r\n0\r\n\r\n"**
@@ -19,4 +21,4 @@ import:
**请求文本 = http.字节文本(请求字节)**
*[响应.状态, 响应.原因, 响应.头["Content-Type"], 响应.体, 请求, 响应字节.value.status, 正文.value, 请求文本.value]*
`return [响应.状态, 响应.原因, 响应.头["Content-Type"], 响应.体, 请求, 响应字节.value.status, 正文.value, 请求文本.value]`
+4 -2
View File
@@ -3,8 +3,10 @@ import:
io: "std:io"
---
# @exec io
## main
> io.写值("stdlib self-test")
> **io.写值("stdlib self-test")**
*None*
`return None`
+11 -7
View File
@@ -3,6 +3,8 @@ import:
json: "std:data/json"
---
# @exec json
## main
**`对象 = json.解析("{\"a\": 1, \"b\": [true, null, \"说\\\"好\"]}")`**
@@ -17,22 +19,24 @@ import:
**深度下标 = 0**
- `深度下标 < 130`
`while 深度下标 < 130`
**深度文本 = 深度文本 + "["**
**深度文本 = 深度文本 + "["**
**深度下标 = 深度下标 + 1**
**深度下标 = 深度下标 + 1**
`end`
**深度下标 = 0**
- `深度下标 < 130`
`while 深度下标 < 130`
**深度文本 = 深度文本 + "]"**
**深度文本 = 深度文本 + "]"**
**深度下标 = 深度下标 + 1**
**深度下标 = 深度下标 + 1**
`end`
**深度 = json.解析(深度文本)**
**`多个 = json.解析多个("1 2 [3]")`**
*[对象.ok, 对象.value.a, 对象.value.b[2], json.格式化(浮点.value), 失败.ok, 失败.code, 尾随.code, 深度.ok, 深度.code, 多个.ok, 多个.value]*
`return [对象.ok, 对象.value.a, 对象.value.b[2], json.格式化(浮点.value), 失败.ok, 失败.code, 尾随.code, 深度.ok, 深度.code, 多个.ok, 多个.value]`
+3 -1
View File
@@ -3,6 +3,8 @@ import:
path: "std:path"
---
# @exec path
## main
*[path.连接(["a", "", "b", "c"]), path.文件名("a/b/c.txt"), path.目录名("a/b/c.txt"), path.扩展名("a/b/c.txt"), path.规范("./a//b/../c"), path.规范("/a/./b/../c"), path.规范("../a/b"), path.是否绝对("/a"), path.是否绝对("a")]*
`return [path.连接(["a", "", "b", "c"]), path.文件名("a/b/c.txt"), path.目录名("a/b/c.txt"), path.扩展名("a/b/c.txt"), path.规范("./a//b/../c"), path.规范("/a/./b/../c"), path.规范("../a/b"), path.是否绝对("/a"), path.是否绝对("a")]`
+3 -1
View File
@@ -3,8 +3,10 @@ import:
process: "std:process"
---
# @exec process
## main
**结果 = process.运行("/bin/echo", ["hello"])**
*[结果.ok, 结果.value.status, 结果.value.stdout, 结果.value.stderr]*
`return [结果.ok, 结果.value.status, 结果.value.stdout, 结果.value.stderr]`
+3 -1
View File
@@ -3,10 +3,12 @@ import:
random: "std:random"
---
# @exec random
## main
**字节结果 = random.字节(16)**
**整数结果 = random.整数(100)**
*[字节结果.ok, 长度(字节结果.value), 整数结果.ok, 整数结果.value >= 0, 整数结果.value < 100]*
`return [字节结果.ok, 长度(字节结果.value), 整数结果.ok, 整数结果.value >= 0, 整数结果.value < 100]`
+3 -1
View File
@@ -3,6 +3,8 @@ import:
regex: "std:regex"
---
# @exec regex
## main
**`星号 = regex.匹配("a*b", "aaab")`**
@@ -31,4 +33,4 @@ import:
**捕获 = regex.捕获("^(a+)(b|c)$", "aab")**
*[星号.value, 加号.value, 锚点.value, 类.value, 否定类.value, 任意.value, 可选.value, 转义.value, 搜索.value, 无效.ok, 无效.code, 不支持.code, 扩展.value, 捕获.value.matched, 捕获.value.groups]*
`return [星号.value, 加号.value, 锚点.value, 类.value, 否定类.value, 任意.value, 可选.value, 转义.value, 搜索.value, 无效.ok, 无效.code, 不支持.code, 扩展.value, 捕获.value.matched, 捕获.value.groups]`
+3 -1
View File
@@ -3,8 +3,10 @@ import:
stream: "std:io/stream"
---
# @exec stream
## main
**结果 = stream.写文本("stream\n")**
*[结果.ok, 结果.value.count]*
`return [结果.ok, 结果.value.count]`
+3 -1
View File
@@ -3,6 +3,8 @@ import:
table: "std:data/table"
---
# @exec table
## main
**数据 = 表(["名称", "分数"], [["甲", 87], ["乙", 92], ["丙", 71]])**
@@ -25,4 +27,4 @@ import:
**分组 = table.分组(表(["类别", "值"], [["a", 1], ["b", 2], ["a", 3]]), 0, 1)**
*[选择, 过滤, 排序, 追加, 设置, 连接, 分组, 数据, table.转GFM(数据)]*
`return [选择, 过滤, 排序, 追加, 设置, 连接, 分组, 数据, table.转GFM(数据)]`
+3 -1
View File
@@ -3,10 +3,12 @@ import:
text: "std:text"
---
# @exec text
## main
**内存 = memory.new(1, 1)**
**长度 = text.utf8编码("é", 内存, 0)**
*[长度, 内存[0], 内存[1]]*
`return [长度, 内存[0], 内存[1]]`
+3 -1
View File
@@ -3,10 +3,12 @@ import:
utf8: "std:text/utf8"
---
# @exec utf8
## main
**内存 = memory.new(1, 1)**
**长度 = utf8.编码("é", 内存, 0)**
*[长度, utf8.解码(内存, 0, 长度).value, utf8.解码(内存, 0, 1).ok]*
`return [长度, utf8.解码(内存, 0, 长度).value, utf8.解码(内存, 0, 1).ok]`
+34 -24
View File
@@ -1,8 +1,10 @@
# @exec text
## utf8编码
`(文本, 内存, 基址)`
`params(文本, 内存, 基址)`
把 Unicode 标量序列按 UTF-8 写入 `Memory`,返回字节长度。
把 Unicode 标量序列按 UTF-8 写入 Memory,返回字节长度。
**点 = text.codepoints(文本)**
@@ -10,46 +12,54 @@
**偏移 = 0**
- `下标 < 长度(点)`
`while 下标 < 长度(点)`
**码点 = 点[下标]**
**码点 = 点[下标]**
1. `码点 < 128`
`if 码点 < 128`
**`内存[基址 + 偏移] = 码点`**
**`内存[基址 + 偏移] = 码点`**
**偏移 = 偏移 + 1**
**偏移 = 偏移 + 1**
2. `码点 < 2048`
`else`
`if 码点 < 2048`
**`内存[基址 + 偏移] = 192 + 码点 // 64`**
**`内存[基址 + 偏移] = 192 + 码点 // 64`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 % 64`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 % 64`**
**偏移 = 偏移 + 2**
**偏移 = 偏移 + 2**
3. `码点 < 65536`
`else`
`if 码点 < 65536`
**`内存[基址 + 偏移] = 224 + 码点 // 4096`**
**`内存[基址 + 偏移] = 224 + 码点 // 4096`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 // 64 % 64`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 // 64 % 64`**
**`内存[基址 + 偏移 + 2] = 128 + 码点 % 64`**
**`内存[基址 + 偏移 + 2] = 128 + 码点 % 64`**
**偏移 = 偏移 + 3**
**偏移 = 偏移 + 3**
4. `true`
`else`
`if true`
**`内存[基址 + 偏移] = 240 + 码点 // 262144`**
**`内存[基址 + 偏移] = 240 + 码点 // 262144`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 // 4096 % 64`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 // 4096 % 64`**
**`内存[基址 + 偏移 + 2] = 128 + 码点 // 64 % 64`**
**`内存[基址 + 偏移 + 2] = 128 + 码点 // 64 % 64`**
**`内存[基址 + 偏移 + 3] = 128 + 码点 % 64`**
**`内存[基址 + 偏移 + 3] = 128 + 码点 % 64`**
**偏移 = 偏移 + 4**
**偏移 = 偏移 + 4**
**下标 = 下标 + 1**
`end`
`end`
`end`
`end`
**下标 = 下标 + 1**
*偏移*
`end`
`return 偏移`
+122 -88
View File
@@ -1,27 +1,29 @@
# @exec utf8
## 成功
`(值)`
`params(值)`
*{ok: true, value: 值}*
`return {ok: true, value: 值}`
## 失败
`(代码, 消息)`
`params(代码, 消息)`
*{ok: false, code: 代码, message: 消息}*
`return {ok: false, code: 代码, message: 消息}`
## 续字节
`(字节)`
`params(字节)`
*字节 >= 128 and 字节 < 192*
`return 字节 >= 128 and 字节 < 192`
## 编码
`(文本, 内存, 基址)`
`params(文本, 内存, 基址)`
把 Unicode 标量序列按 UTF-8 写入 `Memory`,返回字节长度。
这是 `.mq.md` 自己实现的编码逻辑,不是 Rust 内建 UTF-8 转换。
把 Unicode 标量序列按 UTF-8 写入 Memory,返回字节长度。
这是 .mq.md 自己实现的编码逻辑,不是 Rust 内建 UTF-8 转换。
**点 = text.codepoints(文本)**
@@ -29,125 +31,142 @@
**偏移 = 0**
- `下标 < 长度(点)`
`while 下标 < 长度(点)`
**码点 = 点[下标]**
**码点 = 点[下标]**
1. `码点 < 128`
`if 码点 < 128`
**`内存[基址 + 偏移] = 码点`**
**`内存[基址 + 偏移] = 码点`**
**偏移 = 偏移 + 1**
**偏移 = 偏移 + 1**
2. `码点 < 2048`
`else`
`if 码点 < 2048`
**`内存[基址 + 偏移] = 192 + 码点 // 64`**
**`内存[基址 + 偏移] = 192 + 码点 // 64`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 % 64`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 % 64`**
**偏移 = 偏移 + 2**
**偏移 = 偏移 + 2**
3. `码点 < 65536`
`else`
`if 码点 < 65536`
**`内存[基址 + 偏移] = 224 + 码点 // 4096`**
**`内存[基址 + 偏移] = 224 + 码点 // 4096`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 // 64 % 64`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 // 64 % 64`**
**`内存[基址 + 偏移 + 2] = 128 + 码点 % 64`**
**`内存[基址 + 偏移 + 2] = 128 + 码点 % 64`**
**偏移 = 偏移 + 3**
**偏移 = 偏移 + 3**
4. `true`
`else`
`if true`
**`内存[基址 + 偏移] = 240 + 码点 // 262144`**
**`内存[基址 + 偏移] = 240 + 码点 // 262144`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 // 4096 % 64`**
**`内存[基址 + 偏移 + 1] = 128 + 码点 // 4096 % 64`**
**`内存[基址 + 偏移 + 2] = 128 + 码点 // 64 % 64`**
**`内存[基址 + 偏移 + 2] = 128 + 码点 // 64 % 64`**
**`内存[基址 + 偏移 + 3] = 128 + 码点 % 64`**
**`内存[基址 + 偏移 + 3] = 128 + 码点 % 64`**
**偏移 = 偏移 + 4**
**偏移 = 偏移 + 4**
**下标 = 下标 + 1**
`end`
`end`
`end`
`end`
**下标 = 下标 + 1**
*偏移*
`end`
`return 偏移`
## 解码2
`(内存, 基址, 长度, 偏移, 文本)`
`params(内存, 基址, 长度, 偏移, 文本)`
1. `偏移 + 1 >= 长度`
`if 偏移 + 1 >= 长度`
*[文本, 偏移, "utf8.truncated"]*
`return [文本, 偏移, "utf8.truncated"]`
`end`
**b1 = 内存[基址 + 偏移 + 1]**
1. `not 续字节(b1)`
`if not 续字节(b1)`
*[文本, 偏移, "utf8.invalid_continuation"]*
`return [文本, 偏移, "utf8.invalid_continuation"]`
`end`
**码点 = (内存[基址 + 偏移] - 192) * 64 + (b1 - 128)**
1. `码点 < 128`
`if 码点 < 128`
*[文本, 偏移, "utf8.invalid_scalar"]*
`return [文本, 偏移, "utf8.invalid_scalar"]`
*[文本 + text.from_codepoint(码点), 偏移 + 2, ""]*
`end`
`return [文本 + text.from_codepoint(码点), 偏移 + 2, ""]`
## 解码3
`(内存, 基址, 长度, 偏移, 文本)`
`params(内存, 基址, 长度, 偏移, 文本)`
1. `偏移 + 2 >= 长度`
`if 偏移 + 2 >= 长度`
*[文本, 偏移, "utf8.truncated"]*
`return [文本, 偏移, "utf8.truncated"]`
`end`
**b1 = 内存[基址 + 偏移 + 1]**
**b2 = 内存[基址 + 偏移 + 2]**
1. `not (续字节(b1) and 续字节(b2))`
`if not (续字节(b1) and 续字节(b2))`
*[文本, 偏移, "utf8.invalid_continuation"]*
`return [文本, 偏移, "utf8.invalid_continuation"]`
`end`
**码点 = (内存[基址 + 偏移] - 224) * 4096 + (b1 - 128) * 64 + (b2 - 128)**
1. `码点 < 2048 or (码点 >= 55296 and 码点 <= 57343)`
`if 码点 < 2048 or (码点 >= 55296 and 码点 <= 57343)`
*[文本, 偏移, "utf8.invalid_scalar"]*
`return [文本, 偏移, "utf8.invalid_scalar"]`
*[文本 + text.from_codepoint(码点), 偏移 + 3, ""]*
`end`
`return [文本 + text.from_codepoint(码点), 偏移 + 3, ""]`
## 解码4
`(内存, 基址, 长度, 偏移, 文本)`
`params(内存, 基址, 长度, 偏移, 文本)`
1. `偏移 + 3 >= 长度`
`if 偏移 + 3 >= 长度`
*[文本, 偏移, "utf8.truncated"]*
`return [文本, 偏移, "utf8.truncated"]`
`end`
**b1 = 内存[基址 + 偏移 + 1]**
**b2 = 内存[基址 + 偏移 + 2]**
**b3 = 内存[基址 + 偏移 + 3]**
1. `not (续字节(b1) and 续字节(b2) and 续字节(b3))`
`if not (续字节(b1) and 续字节(b2) and 续字节(b3))`
*[文本, 偏移, "utf8.invalid_continuation"]*
`return [文本, 偏移, "utf8.invalid_continuation"]`
`end`
**码点 = (内存[基址 + 偏移] - 240) * 262144 + (b1 - 128) * 4096 + (b2 - 128) * 64 + (b3 - 128)**
1. `码点 < 65536 or 码点 > 1114111`
`if 码点 < 65536 or 码点 > 1114111`
*[文本, 偏移, "utf8.invalid_scalar"]*
`return [文本, 偏移, "utf8.invalid_scalar"]`
*[文本 + text.from_codepoint(码点), 偏移 + 4, ""]*
`end`
`return [文本 + text.from_codepoint(码点), 偏移 + 4, ""]`
## 解码
`(内存, 基址, 长度)`
`params(内存, 基址, 长度)`
**偏移 = 0**
@@ -155,70 +174,85 @@
**错误 = ""**
- `偏移 < 长度 and 错误 == ""`
`while 偏移 < 长度 and 错误 == ""`
**首 = 内存[基址 + 偏移]**
**首 = 内存[基址 + 偏移]**
1. `首 < 128`
`if 首 < 128`
**文本 = 文本 + text.from_codepoint(首)**
**文本 = 文本 + text.from_codepoint(首)**
**偏移 = 偏移 + 1**
**偏移 = 偏移 + 1**
2. `首 < 194`
`else`
`if 首 < 194`
**错误 = "utf8.invalid_lead"**
**错误 = "utf8.invalid_lead"**
3. `首 < 224`
`else`
`if 首 < 224`
**结果 = 解码2(内存, 基址, 长度, 偏移, 文本)**
**结果 = 解码2(内存, 基址, 长度, 偏移, 文本)**
**文本 = 结果[0]**
**文本 = 结果[0]**
**偏移 = 结果[1]**
**偏移 = 结果[1]**
**错误 = 结果[2]**
**错误 = 结果[2]**
4. `首 < 240`
`else`
`if 首 < 240`
**结果 = 解码3(内存, 基址, 长度, 偏移, 文本)**
**结果 = 解码3(内存, 基址, 长度, 偏移, 文本)**
**文本 = 结果[0]**
**文本 = 结果[0]**
**偏移 = 结果[1]**
**偏移 = 结果[1]**
**错误 = 结果[2]**
**错误 = 结果[2]**
5. `首 < 245`
`else`
`if 首 < 245`
**结果 = 解码4(内存, 基址, 长度, 偏移, 文本)**
**结果 = 解码4(内存, 基址, 长度, 偏移, 文本)**
**文本 = 结果[0]**
**文本 = 结果[0]**
**偏移 = 结果[1]**
**偏移 = 结果[1]**
**错误 = 结果[2]**
**错误 = 结果[2]**
6. `true`
`else`
`if true`
**错误 = "utf8.invalid_lead"**
**错误 = "utf8.invalid_lead"**
1. `错误 == ""`
`end`
`end`
`end`
`end`
`end`
`end`
`end`
`if 错误 == ""`
*成功(文本)*
`return 成功(文本)`
2. `true`
`else`
`if true`
*失败(错误, "UTF-8 解码失败")*
`return 失败(错误, "UTF-8 解码失败")`
`end`
`end`
## utf8编码
`(文本, 内存, 基址)`
`params(文本, 内存, 基址)`
*编码(文本, 内存, 基址)*
`return 编码(文本, 内存, 基址)`
## utf8解码
`(内存, 基址, 长度)`
`params(内存, 基址, 长度)`
*解码(内存, 基址, 长度)*
`return 解码(内存, 基址, 长度)`
+112 -27
View File
@@ -1,7 +1,7 @@
# Marqdo conformance and integration test corpus
This directory holds the P0/P1 conformance corpus required by
`docs/DEVELOPMENT_BLUEPRINT.md` §13/§14. The Rust harnesses live in
RFC-LANG-0002 and `docs/DEVELOPMENT_BLUEPRINT.md` §13/§14. The Rust harnesses live in
`crates/cli/tests/` (they use the workspace libraries directly and the
`marqdo` binary via `CARGO_BIN_EXE_marqdo`); the fixtures are plain files here
so they can be rendered, diffed and reviewed like Markdown documents.
@@ -9,6 +9,20 @@ so they can be rendered, diffed and reviewed like Markdown documents.
Everything here is data. Nothing in this directory modifies the repository, and
no test commits, copies or rewrites files outside a throw-away temp directory.
> **Migration state (RFC-LANG-0002).** The source text in this corpus uses the
> current single syntax. The Rust frontend still implements the pre-RFC mapping,
> so the semantic, negative, property and CLI suites that execute Marqdo source
> are **expected to be red** until the frontend migration lands. `conformance_ast`
> is unaffected by the semantic change (the Markdown profile is unchanged).
> `tests/negative/warnings/01-inferred-signature` pins the optional
> `sem.inferred_signature` lint as enabled; the current frontend does not emit
> it. `sem.no_entry_function` is a `run` entry-selection diagnostic and cannot be
> pinned by `crates/cli/tests/negative.rs`, which only calls `analyze_source` /
> `marqdo_runtime::run`; that coverage needs a CLI integration test. Do not
> regenerate goldens or restore the old mapper to turn these suites green. See
> [`../docs/STATUS.md`](../docs/STATUS.md) and
> [`../docs/migration/README.md`](../docs/migration/README.md).
## Layout
```text
@@ -17,8 +31,8 @@ tests/
│ ├── ast/ 160 × *.mq.md + sibling *.ast.json goldens
│ └── semantics/ 73 × *.mq.md + sibling *.expected.json goldens
├── negative/
│ ├── *.mq.md 52 × compile-time hard-error fixtures + *.expected.json
│ ├── warnings/ 6 × inert-executable warning fixtures + *.expected.json
│ ├── *.mq.md 45 × compile-time hard-error fixtures + *.expected.json
│ ├── warnings/ 2 × warning-model/control fixtures + *.expected.json
│ └── runtime/ 21 × runtime-error fixtures + *.expected.json
└── README.md this file
```
@@ -29,7 +43,7 @@ Rust harnesses (all in `crates/cli/tests/`):
|---|---|
| `conformance_ast.rs` | The frozen `marqdo.md.v1` profile parses each fixture into exactly the checked-in AST (node kinds, attributes, literals, byte spans, order). |
| `conformance_semantics.rs` | Each semantic fixture compiles through `marqdo_frontend`, is assembled into `marqdo_ir::Program` and executed with `marqdo_runtime` + `marqdo_host::StdHost`; returned wire value and program stdout match. |
| `negative.rs` | Invalid executable shapes are **hard errors** (never prose fallbacks), exact sorted diagnostic-code lists; warnings and runtime error codes are asserted in their own suites. |
| `negative.rs` | Current-syntax diagnostics are **hard errors** (never prose fallbacks): exact sorted `sem.*`/`symbol.*`/`call.*`/`frontmatter.*` code lists, the `sem.inferred_signature` warning model with inert-knowledge controls, and runtime error codes — each asserted in its own suite. |
| `properties.rs` | Blueprint §14.2 prose invariance: inserting/removing pure narration paragraphs never changes the executable function IR (modulo source spans) and diagnostics stay error-free. |
| `integration_cli.rs` | Real CLI contract: `init`, `check`, `run`, `call`, `inspect`, `fmt`, multi-module imports/cycles, `lock`/`sync --locked`, plugin inspection and explicitly trusted plugin invocation. |
@@ -63,8 +77,11 @@ The power/control-flow slice is pinned by:
* semantic fixtures 37–44: right-associative power, unary-minus precedence,
parentheses, float negative exponents, Strong+CodeSpan assignment, branch,
loop and inert prose;
* negative fixtures 49–52: missing power/condition operands and executable
nodes swallowed by a condition paragraph;
* negative fixtures 18–23: malformed payload statements (missing condition,
trailing colon, `end if`, empty `return`, multi-statement payload, bad
`params` syntax); fixtures 24–29 pin control-stack pairing, including the
heading boundary that reports `sem.unclosed_control` and `sem.unmatched_end`
independently;
* runtime negatives 11–12: negative integer exponent and exponent budget;
* `crates/marqdo-frontend/src/payload.rs` span tests and
`crates/cli/tests/integration_cli.rs` CLI span/E2E assertions.
@@ -77,8 +94,8 @@ The addressable-memory slice (RFC-CM P1, ADR-0022) is pinned by:
* runtime negatives 13–18: out-of-bounds and huge offsets, byte values outside
`0..=255`, index assignment on a `List`, growth beyond the declared maximum
and negative page counts;
* `tests/negative/runtime/15-index-assign-non-memory.mq.md` also guards the v1
value semantics of `List` (it must not become shared mutable memory);
* `tests/negative/runtime/15-index-assign-non-memory.mq.md` also guards the
current value semantics of `List` (it must not become shared mutable memory);
* `crates/marqdo-runtime/src/memory.rs` unit tests (aliasing, atomic failed
growth, forged/stale handles, page arithmetic) and
`crates/marqdo-runtime/tests/interpreter.rs` host-boundary/budget tests;
@@ -277,8 +294,9 @@ RFC-CM CM-A06 resource streams (ADR-0025) are pinned by:
Fixture discovery is directory-based and sorted by file name, so the order is
deterministic on every platform. The AST and semantic suites fail loudly if the
corpus shrinks below 100 / 25 fixtures, and the negative suite fails below 30
compile-time hard-error fixtures.
corpus shrinks below 100 / 25 fixtures; the warning and runtime suites fail if
their directories are empty; the negative suite fails below 30 compile-time
hard-error fixtures.
## AST goldens and `UPDATE_GOLDENS`
@@ -326,38 +344,103 @@ golden without verifying the value would defeat the purpose of the corpus.
## Negative fixtures
Compile-time (`tests/negative/*.mq.md`):
All three suites use the single current language contract
(`docs/architecture/RFC-LANG-0002-unified-semantics.md`,
`spec/mapping.md`, `spec/expression.ebnf`): `@exec`/`@knowledge` heading
modes, interchangeable `Strong`/`Emph`/inline-`Code` one-statement payloads,
and explicit `if`/`else`/`while`/`end`/`return`/`params`. Ordinary Markdown
lists, block quotes, tables and emphasis are **not** errors: they are inert
containers/knowledge with an empty execution projection. The v1
`markdown.invalid_construct` shape errors ("ordered list must have a
condition", "block quote must be a call", "Strong must not nest Emph", "empty
heading") were removed with the old mapping; `markdown.inert_executable`
warnings no longer exist either.
Compile-time (`tests/negative/*.mq.md`, 45 fixtures):
```json
{"codes": ["markdown.invalid_construct"]}
{"codes": ["sem.unclosed_control"]}
```
The expected list is the exact sorted multiset of **error** diagnostic codes
produced by `marqdo_frontend::analyze_source`. Warnings emitted by the same
document are ignored here. Every listed code is additionally asserted to have
`error` severity, and every fixture must produce at least one error — invalid
executable shapes never fall back to prose.
`error` severity, and every fixture must produce at least one error — an
invalid Exec payload never falls back to prose.
Warnings (`tests/negative/warnings/*.mq.md`):
Coverage by group:
| Group | Fixtures | Codes |
|---|---|---|
| heading modes and unit identity | 01–07, 44–45 | `sem.invalid_mode_marker`, `sem.empty_unit_name`, `sem.duplicate_unit_name`, `sem.exec_without_function` |
| payload extraction | 08–17 | `sem.payload_nested` (nested `Emph`/`Strong`/`Link`/math/strikethrough/line break), `sem.empty_payload` (whitespace-only `Strong`/`Emph`) |
| statement grammar | 18–23 | `sem.syntax` |
| control stack and heading boundary | 24–29 | `sem.unmatched_else`, `sem.duplicate_else`, `sem.unmatched_end`, `sem.unclosed_control` |
| signatures | 30–32 | `sem.signature_position` |
| version selection | 33–34 | `sem.unsupported_version_directive` |
| kept non-`sem` errors | 35–43 | `symbol.unknown`, `call.arity`, `symbol.uninitialized`, `frontmatter.invalid` |
Fixture 29 crosses a heading boundary on purpose: the opener's segment reports
`sem.unclosed_control` and the later `### @exec` segment reports
`sem.unmatched_end`; both are asserted, and neither is "repaired" across the
boundary (`spec/mapping.md` §7).
`sem.no_entry_function` is a `run` entry-selection diagnostic: it is produced
when the CLI cannot find an Exec H2 `main`. `crates/cli/tests/negative.rs` only
calls `marqdo_frontend::analyze_source` and `marqdo_runtime::run`, and the
latter reports an unknown *function* for a missing name; there is no CLI-entry
suite in that harness, so this corpus cannot pin the code without a harness
change. It is recorded here as a known gap rather than replaced by a weaker
assertion (see `spec/references.md` §7 and `spec/mapping.md` §8).
### v1 → current reclassification
| v1 fixtures | v1 expectation | Current disposition |
|---|---|---|
| 01–08 nested `Strong`/`Emph` children | `markdown.invalid_construct` | kept as 08–15 with `sem.payload_nested` |
| 09–12 empty/parse-error carriers | `markdown.invalid_construct`, `expr.parse` | empty carriers kept as 16–17 (`sem.empty_payload`); the unqualified expression-parse cases are replaced by the explicit `sem.syntax` statements in 18–23 |
| 13–24 list/quote shape errors | `markdown.invalid_construct`, `expr.parse` | **removed**: ordinary lists/quotes are valid inert Markdown now; the positive control is `warnings/02-knowledge-and-containers-are-inert` |
| 25–27 link-form calls (external/cross-module/anchor) | `ref.unresolved`, `module.unresolved` | **removed**: link-form calls no longer exist; `ref.unresolved`/`module.unresolved` are now `check --refs`/loader diagnostics outside this harness (`spec/references.md` §7) |
| 28–29 duplicate function/namespace names | `markdown.invalid_construct` | kept as 44–45 with `sem.duplicate_unit_name` (duplicate canonical name, `spec/references.md` §2.3) |
| 30–31 empty function/namespace headings | `markdown.invalid_construct` | replaced by 04–05 with `sem.empty_unit_name` on an actual mode declaration |
| 32–40 unknown/call/signature/frontmatter errors | `symbol.unknown`, `call.arity`, `symbol.uninitialized`, `expr.parse`, `frontmatter.invalid` | kept 35–43 (`frontmatter.*`, `symbol.*`, `call.arity`, `symbol.uninitialized`); malformed-signature cases moved to `sem.syntax`/`sem.signature_position` (23, 30–32) |
| 41–48 frontmatter/link/assignment/power shapes | `frontmatter.invalid`, `expr.parse` | frontmatter cases kept as 40–42; link/quote/assignment shapes removed with the old mapping; power/condition cases replaced by 18–29 |
| 49–52 power/condition operands swallowed by a branch condition | `expr.parse`, `markdown.invalid_construct` | **removed**: executable nodes inside list items are now independent payloads. Replacement negatives are the `sem.syntax` (18–23) and control-stack (24–29) fixtures |
Warnings (`tests/negative/warnings/*.mq.md`, 2 fixtures):
```json
{"severity": "warning", "codes": ["markdown.inert_executable"]}
{"severity": "warning", "codes": ["sem.inferred_signature"]}
```
These documents must compile **without errors**; the sorted multiset of warning
codes must match exactly. `return`/`strong`/lists/block quotes outside a
function body are inert content (warning), not hard errors.
codes must match exactly. Fixture 01 pins the `sem.inferred_signature` lint for
an Exec H2 that relies on free-variable inference. Fixture 02 is a
zero-diagnostic control: it proves that ordinary ordered lists, bullet lists
and block quotes are valid inert Markdown even inside an `@exec` section, and
that an explicit `params(...)` declaration (allowed after prose) suppresses the
inferred-signature warning. The lint is specified as **optional**
(`spec/mapping.md` §6, "may be enabled"); these fixtures pin it enabled, so if
an implementation leaves it off the warning suite — not the hard-error corpus —
is what must be revisited.
Runtime (`tests/negative/runtime/*.mq.md`):
Runtime (`tests/negative/runtime/*.mq.md`, 21 fixtures):
```json
{"function": "main", "args": {}, "codes": ["runtime.division_by_zero"]}
```
These documents compile, then must fail at runtime with the expected stable
error code. Optional keys: `"grants": ["foreign"]` and `"stack_limit": 24`
(used for the recursion-depth fixture so the budget — not the host process
stack — is what fails).
error code. Sources were migrated to the current syntax (explicit `## @exec`
functions, `params(...)` where a function has arguments, payload calls and
explicit `if`/`end`), but the genuine runtime expectations were preserved:
arithmetic type/zero-division, index/field/memory bounds, `call.not_callable`,
`call.arity` through a `ref` function value, non-Bool branch condition,
capability (`permission.denied` for a foreign kernel in pure mode), unsupported
math subset, recursion budget and the addressable-memory/collection errors.
Optional keys: `"grants": ["foreign"]` and `"stack_limit": 24` (used for the
recursion-depth fixture so the budget — not the host process stack — is what
fails).
## CLI integration notes
@@ -374,13 +457,15 @@ stack — is what fails).
## Notes discovered while authoring (all since fixed)
The fixtures initially pinned three observations that were reported and then
fixed in the implementation; the goldens below reflect the fixed behaviour:
Two observations were reported and then fixed in the implementation; the
goldens reflect the fixed behaviour:
* wire floats round-trip exactly (`serde_json/float_roundtrip` is enabled), so
Python `math.pi * 9` keeps `28.274333882308138`;
* the default interpreter stack budget is 128 frames so a deeply recursive
document returns a structured `resource.exhausted` instead of exhausting the
native debug-build stack (`--stack` can raise it deliberately);
* an external-link call form (`> [x](https://example.com)()`) is rejected with
`ref.unresolved`, the same code used for other unresolvable call targets.
native debug-build stack (`--stack` can raise it deliberately).
The old link-form block-quote call (`> [x](https://example.com)()`) no longer
exists: a Markdown link is a static reference, so a call is now an ordinary
expression payload (`spec/references.md` §6.2).
@@ -1,3 +1,3 @@
## main
## @exec main
*1 + 2*
*return 1 + 2*
@@ -1,3 +1,3 @@
## main
## @exec main
*"你好,Marqdo"*
*return "你好,Marqdo"*
@@ -1,3 +1,3 @@
## main
## @exec main
*1.5 * 2.0*
`return 1.5 * 2.0`
@@ -1,3 +1,3 @@
## main
## @exec main
*123456789012345678901234567890 * 10*
`return 123456789012345678901234567890 * 10`
@@ -1,13 +1,15 @@
# 数学
# @knowledge 数学
## 阶乘
## @exec 阶乘
1. `n <= 1`
`if n <= 1`
*1*
`return 1`
2. `n > 1`
`else`
**结果 = n * 阶乘(n=n-1)**
`结果 = n * 阶乘(n=n-1)`
*结果*
`return 结果`
`end`
@@ -1,11 +1,13 @@
## 斐波那契
## @exec 斐波那契
1. `n < 2`
`if n < 2`
*n*
`return n`
2. `n >= 2`
`else`
**结果 = 斐波那契(n=n-1) + 斐波那契(n=n-2)**
`结果 = 斐波那契(n=n-1) + 斐波那契(n=n-2)`
*结果*
`return 结果`
`end`
@@ -1,15 +1,17 @@
## 最大公约数
## @exec 最大公约数
**a = 甲**
`a = 甲`
**b = 乙**
`b = 乙`
- `b > 0`
`while b > 0`
**t = b**
`t = b`
**b = a % b**
`b = a % b`
**a = t**
`a = t`
*a*
`end`
`return a`
@@ -1,13 +1,15 @@
## 求和
## @exec 求和
**i = 1**
`i = 1`
**total = 0**
`total = 0`
- `i <= n`
`while i <= n`
**total = total + i**
`total = total + i`
**i = i + 1**
`i = i + 1`
*total*
`end`
`return total`
@@ -1,19 +1,23 @@
## 嵌套
## @exec 嵌套
**total = 0**
1. `n > 0`
`if n > 0`
**m = 3**
**m = 3**
- `m > 0`
`while m > 0`
**total = total + m**
**total = total + m**
**m = m - 1**
**m = m - 1**
2. `n <= 0`
`end`
**total = 0**
`else`
*total*
**total = 0**
`end`
*return total*
@@ -1,9 +1,9 @@
## 加法
## @exec 加法
`(a: Int, b: Int)`
`params(a: Int, b: Int)`
*a + b*
`return a + b`
## main
## @exec main
*加法(2, 3)*
`return 加法(2, 3)`
@@ -1,9 +1,9 @@
## 默认
## @exec 默认
`(x: Int, y: Int = 10)`
`params(x: Int, y: Int = 10)`
*x + y*
`return x + y`
## main
## @exec main
*默认(x=2)*
`return 默认(x=2)`
@@ -1,9 +1,9 @@
## 减法
## @exec 减法
`(a: Int, b: Int)`
`params(a: Int, b: Int)`
*a - b*
`return a - b`
## main
## @exec main
*减法(b=3, a=10)*
`return 减法(b=3, a=10)`
@@ -1,11 +1,11 @@
## 加一
## @exec 加一
**n = n + 1**
`n = n + 1`
*n*
`return n`
## main
## @exec main
**f = ref("#加一")**
`f = ref("#加一")`
*f(n=41)*
`return f(n=41)`
@@ -1,9 +1,9 @@
## 加一
## @exec 加一
**n = n + 1**
`n = n + 1`
*n*
`return n`
## main
## @exec main
*ref("#加一")*
`return ref("#加一")`
@@ -1,3 +1,3 @@
## main
## @exec main
*{"长度": 长度("你好"), "文本": 文本(42)}*
`return {"长度": 长度("你好"), "文本": 文本(42)}`
Loaded 100 of 375 files, more files were not shown because too many files have changed in this diff. Show more