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:
1 parent
49835424ee
commit
e029853e32
375 files changed
+6591
-4790
No files matched your search
+122
-88
@@ -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)`
|
||||
Reference in new issue
Block a user