feat(stdlib): add JSON and CSV product parsers
This commit is contained in:
1 parent
fbe36bcc43
commit
bde6f1d0ba
10 files changed
+942
-8
No files matched your search
@@ -128,11 +128,13 @@ fn every_public_stdlib_module_has_a_product_test() {
|
||||
names,
|
||||
vec![
|
||||
"console.mq.md",
|
||||
"csv.mq.md",
|
||||
"demo.mq.md",
|
||||
"format.mq.md",
|
||||
"fs.mq.md",
|
||||
"http.mq.md",
|
||||
"io.mq.md",
|
||||
"json.mq.md",
|
||||
"stream.mq.md",
|
||||
"table.mq.md",
|
||||
"text.mq.md",
|
||||
@@ -184,6 +186,51 @@ fn fs_test_exercises_the_file_operation_surface() {
|
||||
);
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn json_test_parses_and_formats_nested_values() {
|
||||
let report = run_product_test(
|
||||
product_tests()
|
||||
.iter()
|
||||
.find(|file| file.name == "json.mq.md")
|
||||
.expect("json test"),
|
||||
);
|
||||
let items = report["value"]["items"].as_array().expect("list");
|
||||
assert_eq!(items[0]["value"], true);
|
||||
assert_eq!(items[1]["decimal"], "1");
|
||||
assert_eq!(items[2]["value"], "说\"好");
|
||||
assert_eq!(
|
||||
items[3]["value"],
|
||||
"[1, 2.5, -300.0, 0.4, {\"a\": 1.0}, \"x\"]"
|
||||
);
|
||||
assert_eq!(items[4]["value"], false);
|
||||
assert_eq!(items[5]["value"], "json.invalid_array");
|
||||
assert_eq!(items[6]["value"], "json.trailing");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn csv_test_parses_and_formats_quoted_rows() {
|
||||
let report = run_product_test(
|
||||
product_tests()
|
||||
.iter()
|
||||
.find(|file| file.name == "csv.mq.md")
|
||||
.expect("csv test"),
|
||||
);
|
||||
let items = report["value"]["items"].as_array().expect("list");
|
||||
let row = items[0]["items"].as_array().expect("row");
|
||||
assert_eq!(row.len(), 3);
|
||||
assert_eq!(row[0]["value"], "甲");
|
||||
assert_eq!(row[1]["value"], "乙,丙");
|
||||
assert_eq!(row[2]["value"], "说\"好");
|
||||
assert_eq!(items[1]["value"], "甲,\"乙,丙\",\"说\"\"好\"");
|
||||
let empty = items[2]["items"].as_array().expect("empty row");
|
||||
assert_eq!(empty.len(), 1);
|
||||
assert_eq!(empty[0]["value"], "");
|
||||
assert_eq!(items[3]["value"], "csv.unterminated_quote");
|
||||
let quoted = items[4]["items"].as_array().expect("quoted row");
|
||||
assert_eq!(quoted[0]["value"], "a");
|
||||
assert_eq!(quoted[1]["value"], "b");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn format_test_pins_value_semantics_and_handle_observation() {
|
||||
let report = run_product_test(
|
||||
|
||||
+6
-5
@@ -58,7 +58,7 @@ byte-identical).
|
||||
cargo fmt --all -- --check PASS
|
||||
cargo clippy --workspace --all-targets -- -D warnings PASS
|
||||
cargo test --workspace --locked PASS
|
||||
467 passed, 0 failed, 2 ignored; includes 7/7 Linux security tests
|
||||
469 passed, 0 failed, 2 ignored; includes 7/7 Linux security tests
|
||||
```
|
||||
|
||||
The documentation and test migration is local work; re-run this block after it
|
||||
@@ -200,10 +200,11 @@ This is still a **local VM lane**, not a self-hosted GitHub Actions security URL
|
||||
`Value::Table`; inputs are never mutated; GFM AST laziness and physical T0
|
||||
storage are unchanged. `std:fs/file` provides bounded `读文本`/`写文本`/`复制文件`
|
||||
over the existing `resource.*` ABI plus `存在`/`元数据`/`列出目录`/`创建目录`/
|
||||
`删除`/`重命名` over `resource.request` (ADR-0041). Append/seek/watch and a
|
||||
recursive walk remain open.
|
||||
`删除`/`重命名` over `resource.request` (ADR-0041); `data/json`/`data/csv`
|
||||
provide recursive JSON and quoted single-row CSV product parsers. Append/seek/
|
||||
watch, recursive walk, streaming JSON/CSV and a JSON depth bound remain open.
|
||||
- Bundled standard library (CM-A10, ADR-0028): `stdlib/` ships
|
||||
`format`/`text`/`io`/`fs`; explicit `std:` imports resolve only inside the bundle;
|
||||
`format`/`text`/`io`/`fs`/`data`; explicit `std:` imports resolve only inside the bundle;
|
||||
a SHA-256 digest over `*.mq.md` is verified before loading; Analysis records
|
||||
`project.stdlib`; a frozen-binary test asserts the CLI hash is unchanged after
|
||||
running a `std:io` project and that tampering is rejected. `打印/print` is
|
||||
@@ -229,7 +230,7 @@ This is still a **local VM lane**, not a self-hosted GitHub Actions security URL
|
||||
status/index links and SHA-pinned evidence; `crates/cli/tests/architecture_boundaries.rs`
|
||||
pins the workspace graph, `marqdo-runtime -> marqdo-host`, the bundled stdlib
|
||||
digest and the stdio/file/TCP endpoints; `crates/cli/tests/stdlib_product.rs`
|
||||
runs every public stdlib module (`console/demo/format/fs/http/io/stream/table/text/utf8`)
|
||||
runs every public stdlib module (`console/csv/demo/format/fs/http/io/json/stream/table/text/utf8`)
|
||||
through `std:` imports over `stdlib/tests/*.mq.md`. `tools/pack-stdlib.py`
|
||||
now sorts `.mq.md` by the same relative path key as the CLI. Source/test baseline
|
||||
`0d40de7`; later docs-only commits keep code/test bytes identical. Evidence:
|
||||
|
||||
@@ -18,7 +18,7 @@ platform".
|
||||
| Dimension | Current state | Source |
|
||||
|---|---|---|
|
||||
| Implemented | Rust workspace `0.1.0`: Markdown/frontend/IR, tree-walk runtime, `Memory`, capability host, Tool/Analysis/Trace, Plugin ABI, Foreign kernels, bundled stdlib, CLI composition root | `Cargo.toml`, `crates/`, `stdlib/` |
|
||||
| Tested locally | `cargo test --workspace --locked`: **467 passed, 0 failed, 2 ignored** on Linux x86_64 at the baseline | `docs/STATUS.md` §3 |
|
||||
| Tested locally | `cargo test --workspace --locked`: **469 passed, 0 failed, 2 ignored** on Linux x86_64 at the baseline | `docs/STATUS.md` §3 |
|
||||
| Bundled stdlib released | In-repo bundle `marqdo-stdlib@0.1.0`, SHA-256 digest verified before loading; it is **not** an external registry package | `stdlib/stdlib.json`, `stdlib/README.md` |
|
||||
| Multi-platform verified | Linux local gate is the only executed lane here; Windows/macOS native lanes are **UNVERIFIED**, and the GitHub security lane remains a **VM-only** gate | `docs/STATUS.md` §1, §4 |
|
||||
|
||||
@@ -88,6 +88,8 @@ review RFC, not a new crate per provider.
|
||||
| project file write | `resource.open("file", path, ["write"])`; buffers until `close`, never flush-on-drop | implemented, project mode | `resource_streams`, `stdlib_product` |
|
||||
| `std:fs/file` | `fs.读文本`, `fs.写文本`, `fs.复制文件` over `resource.open/read/write/close` and `Memory`; bounded at 8 MiB | implemented (read/write/copy) | `stdlib_product` |
|
||||
| `resource.request` | `resource.request("fs.exists|metadata|list|mkdir|remove|rename", paths)`; project mode, grant-checked, recoverable fs Result | implemented `fs.*`; no seek/append/watch | `resource_streams`, `stdlib_product` |
|
||||
| `std:data/json` | `json.解析(文本)` -> Result with nested Value; `json.格式化(值)` -> Text | implemented (recursive, recoverable errors) | `stdlib_product` |
|
||||
| `std:data/csv` | `csv.解析行(文本)` -> Result with List<Text>; `csv.格式化行(列表)` -> Text | implemented (single row, quoted) | `stdlib_product` |
|
||||
| file metadata / directory / rename / remove / mkdir | not part of the current Resource contract | **not implemented**; needs a separate Resource Operation ADR | — |
|
||||
| TCP | `resource.open("tcp", ip:port, ["read","write"])`; exact IP grant, 5 s timeout | implemented; no DNS/TLS/server socket/UDP | `tcp_endpoint`, `http_over_tcp` |
|
||||
| HTTP/1.1 | `stdlib/net/http.mq.md`: status/header/chunked-byte parse, request build | implemented over an already-authorized TCP stream; not a DNS/TLS client | `stdlib_http`, `http_over_tcp`, `stdlib_product` |
|
||||
@@ -115,7 +117,7 @@ that a phase is complete.
|
||||
| P0 | Documentation drift between `STATUS.md`, the architecture index and the evidence | being fixed by this migration and the docs gate |
|
||||
| P1 | `std:fs/file` read/write/copy and `resource.request` fs metadata/directory operations are implemented; append/seek/watch/recursive walk remain open | open |
|
||||
| P1 | No file append/seek/watch/recursive directory walk | open; future Resource Operation extension |
|
||||
| P1 | JSON/CSV/UTF-8 decode remain mainly under `tests/conformance` | open as product stdlib API |
|
||||
| P1 | JSON/CSV product parsers are implemented; no streaming/multi-line CSV or depth-bounded JSON walker | open |
|
||||
| P1 | `crates/cli/src/commands.rs` and `crates/marqdo-host/src/host.rs` still mix multiple responsibilities | open refactor, behavior-preserving |
|
||||
| P2 | HTTP parsing is Unicode-codepoint oriented; a general byte body is not the only path | open; convert before a general network release |
|
||||
| P2 | No DNS, TLS, listener or UDP provider | open |
|
||||
|
||||
@@ -0,0 +1,49 @@
|
||||
# Evidence: `std:data/json` and `std:data/csv`
|
||||
|
||||
Date: 2026-11-21 (Asia/Shanghai)
|
||||
Source baseline: `fbe36bcc431ccadcb95b5aba74ecd7c39113f9ae`
|
||||
Repository: `marqdo-cli`
|
||||
RFC item: P1 JSON/CSV product stdlib APIs
|
||||
|
||||
## Implemented
|
||||
|
||||
`stdlib/data/json.mq.md` is a recursive JSON parser/formatter written only in
|
||||
`.mq.md`:
|
||||
|
||||
- `解析(文本)` -> `{ok:true, value}` or `{ok:false, code, message}`;
|
||||
rejects malformed numbers, strings, escapes, arrays, objects and trailing
|
||||
input (`json.trailing`).
|
||||
- `格式化(值)` -> canonical text: strings escaped, lists/objects comma-space
|
||||
separated, `None` as `null`, Text/Int/Float/Bool by their value form.
|
||||
|
||||
`stdlib/data/csv.mq.md` is a quoted single-row CSV parser/formatter:
|
||||
|
||||
- `解析行(文本)` -> `{ok:true, value:List<Text>}`; `""` is a literal quote;
|
||||
unterminated quotes and a quote inside an unquoted field are recoverable
|
||||
`csv.unterminated_quote`/`csv.invalid_quote`.
|
||||
- `格式化行(列表)` -> quotes fields containing comma/quote/CR/LF and doubles
|
||||
inner quotes.
|
||||
|
||||
No Rust builtin, `HostOp` or parser change was added. Both modules are pure
|
||||
`.mq.md` value functions.
|
||||
|
||||
## Tests
|
||||
|
||||
`stdlib/tests/json.mq.md` and `stdlib/tests/csv.mq.md` run through
|
||||
`std:data/json` and `std:data/csv` and are pinned by
|
||||
`crates/cli/tests/stdlib_product.rs` (8 product tests total).
|
||||
|
||||
```text
|
||||
cargo fmt --all -- --check PASS
|
||||
cargo clippy --workspace --all-targets -- -D warnings PASS
|
||||
cargo test --workspace 469 passed, 0 failed, 2 ignored
|
||||
cargo test -p marqdo-cli --test stdlib_product 8 passed
|
||||
python3 tools/pack-stdlib.py PASS
|
||||
```
|
||||
|
||||
## Not covered
|
||||
|
||||
No streaming/incremental JSON, no depth bound (deep nesting can exhaust the
|
||||
interpreter stack), no multi-line CSV fields, no duplicate-key policy beyond
|
||||
last-write-wins, and no `std:data/json` conversion to `Table`. Those remain
|
||||
open product work.
|
||||
@@ -12,6 +12,8 @@ module; a mismatch is a hard error.
|
||||
- `io/stream.mq.md` — `写全部` / `写文本` with short-write and close checking
|
||||
- `io/console.mq.md` — `读取行` / `打印` over `stdio/stdin` and `stdio/stdout`
|
||||
- `demo.mq.md` — side-by-side comparison with builtin `打印`
|
||||
- `data/json.mq.md` — recursive JSON parser and formatter (recoverable Result)
|
||||
- `data/csv.mq.md` — quoted single-row CSV parser and formatter
|
||||
- `data/table.mq.md` — value-returning table select/filter/sort/append/set/join/group/GFM
|
||||
- `net/http.mq.md` — HTTP/1.1 response parsing (headers/chunked) and request builder
|
||||
- `tests/` — product self-tests for every public module
|
||||
|
||||
@@ -0,0 +1,163 @@
|
||||
## 成功
|
||||
|
||||
`(值)`
|
||||
|
||||
*{ok: true, value: 值}*
|
||||
|
||||
## 失败
|
||||
|
||||
`(代码, 消息)`
|
||||
|
||||
*{ok: false, code: 代码, message: 消息}*
|
||||
|
||||
## 解析行
|
||||
|
||||
`(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。
|
||||
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。
|
||||
|
||||
**点 = text.codepoints(文本)**
|
||||
|
||||
**下标 = 0**
|
||||
|
||||
**字段 = ""**
|
||||
|
||||
**字段表 = []**
|
||||
|
||||
**引号内 = false**
|
||||
|
||||
**错误 = ""**
|
||||
|
||||
- `下标 < 长度(点) and 错误 == ""`
|
||||
|
||||
**字符 = text.from_codepoint(点[下标])**
|
||||
|
||||
1. `引号内 and 字符 == "\""`
|
||||
|
||||
1. `下标 + 1 < 长度(点) and text.from_codepoint(点[下标 + 1]) == "\""`
|
||||
|
||||
**`字段 = 字段 + "\""`**
|
||||
|
||||
**下标 = 下标 + 2**
|
||||
|
||||
2. `true`
|
||||
|
||||
**引号内 = false**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
2. `引号内`
|
||||
|
||||
**字段 = 字段 + 字符**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
3. `字符 == "\""`
|
||||
|
||||
1. `字段 == ""`
|
||||
|
||||
**引号内 = true**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
2. `true`
|
||||
|
||||
**错误 = "csv.invalid_quote"**
|
||||
|
||||
4. `字符 == ","`
|
||||
|
||||
**字段表 = list.append(字段表, 字段)**
|
||||
|
||||
**字段 = ""**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
5. `true`
|
||||
|
||||
**字段 = 字段 + 字符**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
1. `错误 != ""`
|
||||
|
||||
*失败(错误, "未加引号字段中出现双引号")*
|
||||
|
||||
1. `引号内`
|
||||
|
||||
*失败("csv.unterminated_quote", "引号未闭合")*
|
||||
|
||||
*成功(list.concat(字段表, [字段]))*
|
||||
|
||||
## 格式化字段
|
||||
|
||||
`(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 `""`。
|
||||
|
||||
**点 = text.codepoints(文本)**
|
||||
|
||||
**下标 = 0**
|
||||
|
||||
**需要引号 = false**
|
||||
|
||||
- `下标 < 长度(点) and not 需要引号`
|
||||
|
||||
**码点 = 点[下标]**
|
||||
|
||||
1. `码点 == 34 or 码点 == 44 or 码点 == 10 or 码点 == 13`
|
||||
|
||||
**需要引号 = true**
|
||||
|
||||
2. `true`
|
||||
|
||||
**忽略 = 0**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
1. `not 需要引号`
|
||||
|
||||
*文本*
|
||||
|
||||
**`结果 = "\""`**
|
||||
|
||||
**下标 = 0**
|
||||
|
||||
- `下标 < 长度(点)`
|
||||
|
||||
1. `点[下标] == 34`
|
||||
|
||||
**`结果 = 结果 + "\"\""`**
|
||||
|
||||
2. `true`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(点[下标])**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
*`结果 + "\""`*
|
||||
|
||||
## 格式化行
|
||||
|
||||
`(列表)`
|
||||
|
||||
**结果 = ""**
|
||||
|
||||
**下标 = 0**
|
||||
|
||||
- `下标 < 长度(列表)`
|
||||
|
||||
1. `下标 > 0`
|
||||
|
||||
**结果 = 结果 + ","**
|
||||
|
||||
2. `true`
|
||||
|
||||
**忽略 = 0**
|
||||
|
||||
**结果 = 结果 + 格式化字段(文本(列表[下标]))**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
*结果*
|
||||
@@ -0,0 +1,638 @@
|
||||
## 解析
|
||||
|
||||
`(文本)`
|
||||
|
||||
解析一个完整的 JSON 文本。值之后只允许空白;多余输入返回
|
||||
`json.trailing`。成功结果只保留 `{ok, value}`,不暴露内部游标。
|
||||
|
||||
**点 = text.codepoints(文本)**
|
||||
|
||||
**结果 = 解析值(点, 0)**
|
||||
|
||||
1. `not 结果.ok`
|
||||
|
||||
*结果*
|
||||
|
||||
**位置 = 跳过空白(点, 结果.next)**
|
||||
|
||||
1. `位置 != 长度(点)`
|
||||
|
||||
*失败("json.trailing", "值后存在多余输入")*
|
||||
|
||||
*{ok: true, value: 结果.value}*
|
||||
|
||||
## 成功值
|
||||
|
||||
`(值, 下一位置)`
|
||||
|
||||
*{ok: true, value: 值, next: 下一位置}*
|
||||
|
||||
## 失败
|
||||
|
||||
`(代码, 消息)`
|
||||
|
||||
*{ok: false, code: 代码, message: 消息}*
|
||||
|
||||
## 是空白
|
||||
|
||||
`(码点)`
|
||||
|
||||
*码点 == 32 or 码点 == 9 or 码点 == 10 or 码点 == 13*
|
||||
|
||||
## 是数字
|
||||
|
||||
`(码点)`
|
||||
|
||||
*码点 >= 48 and 码点 <= 57*
|
||||
|
||||
## 跳过空白
|
||||
|
||||
`(点, 位置)`
|
||||
|
||||
**当前 = 位置**
|
||||
|
||||
- `当前 < 长度(点) and 是空白(点[当前])`
|
||||
|
||||
**当前 = 当前 + 1**
|
||||
|
||||
*当前*
|
||||
|
||||
## 匹配
|
||||
|
||||
`(点, 位置, 文本)`
|
||||
|
||||
**目标 = text.codepoints(文本)**
|
||||
|
||||
**下标 = 0**
|
||||
|
||||
**结果 = true**
|
||||
|
||||
- `下标 < 长度(目标) and 结果`
|
||||
|
||||
1. `位置 + 下标 >= 长度(点)`
|
||||
|
||||
**结果 = false**
|
||||
|
||||
2. `点[位置 + 下标] != 目标[下标]`
|
||||
|
||||
**结果 = false**
|
||||
|
||||
3. `true`
|
||||
|
||||
**继续 = 0**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
*结果*
|
||||
|
||||
## 片段
|
||||
|
||||
`(点, 起点, 终点)`
|
||||
|
||||
**结果 = ""**
|
||||
|
||||
**下标 = 起点**
|
||||
|
||||
- `下标 < 终点`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(点[下标])**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
*结果*
|
||||
|
||||
## 解析数字
|
||||
|
||||
`(点, 位置)`
|
||||
|
||||
JSON 数字:可选负号、整数位、可选小数位、可选指数;含 `.`/`e` 返回 Float。
|
||||
|
||||
**开始 = 位置**
|
||||
|
||||
**当前 = 位置**
|
||||
|
||||
1. `text.from_codepoint(点[当前]) == "-"`
|
||||
|
||||
**当前 = 当前 + 1**
|
||||
|
||||
2. `true`
|
||||
|
||||
**非负 = 0**
|
||||
|
||||
**整数位 = 0**
|
||||
|
||||
- `当前 < 长度(点) and 是数字(点[当前])`
|
||||
|
||||
**整数位 = 整数位 + 1**
|
||||
|
||||
**当前 = 当前 + 1**
|
||||
|
||||
**有小数 = false**
|
||||
|
||||
**小数位 = 0**
|
||||
|
||||
1. `当前 < 长度(点) and text.from_codepoint(点[当前]) == "."`
|
||||
|
||||
**有小数 = true**
|
||||
|
||||
**当前 = 当前 + 1**
|
||||
|
||||
- `当前 < 长度(点) and 是数字(点[当前])`
|
||||
|
||||
**小数位 = 小数位 + 1**
|
||||
|
||||
**当前 = 当前 + 1**
|
||||
|
||||
2. `true`
|
||||
|
||||
**忽略 = 0**
|
||||
|
||||
**指数位 = 0**
|
||||
|
||||
**指数标记 = false**
|
||||
|
||||
1. `当前 < 长度(点) and (text.from_codepoint(点[当前]) == "e" or text.from_codepoint(点[当前]) == "E")`
|
||||
|
||||
**有小数 = true**
|
||||
|
||||
**指数标记 = true**
|
||||
|
||||
**当前 = 当前 + 1**
|
||||
|
||||
1. `当前 < 长度(点) and (text.from_codepoint(点[当前]) == "+" or text.from_codepoint(点[当前]) == "-")`
|
||||
|
||||
**当前 = 当前 + 1**
|
||||
|
||||
2. `true`
|
||||
|
||||
**忽略指数符号 = 0**
|
||||
|
||||
- `当前 < 长度(点) and 是数字(点[当前])`
|
||||
|
||||
**指数位 = 指数位 + 1**
|
||||
|
||||
**当前 = 当前 + 1**
|
||||
|
||||
1. `整数位 == 0`
|
||||
|
||||
*失败("json.invalid_number", "数字缺少整数位")*
|
||||
|
||||
1. `有小数 and not 指数标记 and 小数位 == 0`
|
||||
|
||||
*失败("json.invalid_number", "小数缺少位数")*
|
||||
|
||||
1. `指数标记 and 指数位 == 0`
|
||||
|
||||
*失败("json.invalid_number", "指数缺少位数")*
|
||||
|
||||
**原文 = 片段(点, 开始, 当前)**
|
||||
|
||||
1. `有小数`
|
||||
|
||||
*成功值(小数(原文), 当前)*
|
||||
|
||||
*成功值(整数(原文), 当前)*
|
||||
|
||||
## 十六进制值
|
||||
|
||||
`(码点)`
|
||||
|
||||
1. `码点 >= 48 and 码点 <= 57`
|
||||
|
||||
*码点 - 48*
|
||||
|
||||
2. `码点 >= 65 and 码点 <= 70`
|
||||
|
||||
*码点 - 55*
|
||||
|
||||
3. `码点 >= 97 and 码点 <= 102`
|
||||
|
||||
*码点 - 87*
|
||||
|
||||
*0 - 1*
|
||||
|
||||
## 解析字符串
|
||||
|
||||
`(点, 位置)`
|
||||
|
||||
**当前 = 位置 + 1**
|
||||
|
||||
**结果 = ""**
|
||||
|
||||
**完成 = false**
|
||||
|
||||
**错误 = ""**
|
||||
|
||||
- `当前 < 长度(点) and not 完成 and 错误 == ""`
|
||||
|
||||
**码点 = 点[当前]**
|
||||
|
||||
1. `码点 == 34`
|
||||
|
||||
**完成 = true**
|
||||
|
||||
**当前 = 当前 + 1**
|
||||
|
||||
2. `码点 == 92`
|
||||
|
||||
1. `当前 + 1 >= 长度(点)`
|
||||
|
||||
**错误 = "json.invalid_escape"**
|
||||
|
||||
2. `true`
|
||||
|
||||
**转义码点 = 点[当前 + 1]**
|
||||
|
||||
1. `转义码点 == 34`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(34)**
|
||||
|
||||
**当前 = 当前 + 2**
|
||||
|
||||
2. `转义码点 == 92`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(92)**
|
||||
|
||||
**当前 = 当前 + 2**
|
||||
|
||||
3. `转义码点 == 47`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(47)**
|
||||
|
||||
**当前 = 当前 + 2**
|
||||
|
||||
4. `转义码点 == 98`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(8)**
|
||||
|
||||
**当前 = 当前 + 2**
|
||||
|
||||
5. `转义码点 == 102`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(12)**
|
||||
|
||||
**当前 = 当前 + 2**
|
||||
|
||||
6. `转义码点 == 110`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(10)**
|
||||
|
||||
**当前 = 当前 + 2**
|
||||
|
||||
7. `转义码点 == 114`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(13)**
|
||||
|
||||
**当前 = 当前 + 2**
|
||||
|
||||
8. `转义码点 == 116`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(9)**
|
||||
|
||||
**当前 = 当前 + 2**
|
||||
|
||||
9. `转义码点 == 117`
|
||||
|
||||
1. `当前 + 5 >= 长度(点)`
|
||||
|
||||
**错误 = "json.invalid_escape"**
|
||||
|
||||
2. `true`
|
||||
|
||||
**数字 = 十六进制值(点[当前 + 2]) * 4096 + 十六进制值(点[当前 + 3]) * 256 + 十六进制值(点[当前 + 4]) * 16 + 十六进制值(点[当前 + 5])**
|
||||
|
||||
1. `数字 < 0 or (数字 >= 55296 and 数字 <= 57343)`
|
||||
|
||||
**错误 = "json.invalid_escape"**
|
||||
|
||||
2. `true`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(数字)**
|
||||
|
||||
**当前 = 当前 + 6**
|
||||
|
||||
10. `true`
|
||||
|
||||
**错误 = "json.invalid_escape"**
|
||||
|
||||
3. `true`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(码点)**
|
||||
|
||||
**当前 = 当前 + 1**
|
||||
|
||||
1. `错误 != ""`
|
||||
|
||||
*失败("json.invalid_string", "字符串转义无效")*
|
||||
|
||||
1. `not 完成`
|
||||
|
||||
*失败("json.unexpected_eof", "字符串未闭合")*
|
||||
|
||||
*成功值(结果, 当前)*
|
||||
|
||||
## 解析对象
|
||||
|
||||
`(点, 位置)`
|
||||
|
||||
*解析对象项(点, 位置 + 1, {})*
|
||||
|
||||
## 解析对象项
|
||||
|
||||
`(点, 位置, 已解析)`
|
||||
|
||||
**位置 = 跳过空白(点, 位置)**
|
||||
|
||||
1. `位置 >= 长度(点)`
|
||||
|
||||
*失败("json.unexpected_eof", "对象未闭合")*
|
||||
|
||||
**当前 = text.from_codepoint(点[位置])**
|
||||
|
||||
1. `当前 == "}"`
|
||||
|
||||
*成功值(已解析, 位置 + 1)*
|
||||
|
||||
**键结果 = 解析字符串(点, 位置)**
|
||||
|
||||
1. `not 键结果.ok`
|
||||
|
||||
*键结果*
|
||||
|
||||
**键 = 键结果.value**
|
||||
|
||||
**位置 = 跳过空白(点, 键结果.next)**
|
||||
|
||||
1. `位置 >= 长度(点)`
|
||||
|
||||
*失败("json.unexpected_eof", "对象缺少冒号")*
|
||||
|
||||
1. `text.from_codepoint(点[位置]) != ":"`
|
||||
|
||||
*失败("json.invalid_object", "对象缺少冒号")*
|
||||
|
||||
**位置 = 跳过空白(点, 位置 + 1)**
|
||||
|
||||
**值结果 = 解析值(点, 位置)**
|
||||
|
||||
1. `not 值结果.ok`
|
||||
|
||||
*值结果*
|
||||
|
||||
**新的已解析 = map.set(已解析, 键, 值结果.value)**
|
||||
|
||||
**位置 = 跳过空白(点, 值结果.next)**
|
||||
|
||||
1. `位置 >= 长度(点)`
|
||||
|
||||
*失败("json.unexpected_eof", "对象未闭合")*
|
||||
|
||||
**分隔 = text.from_codepoint(点[位置])**
|
||||
|
||||
1. `分隔 == ","`
|
||||
|
||||
*解析对象项(点, 位置 + 1, 新的已解析)*
|
||||
|
||||
2. `分隔 == "}"`
|
||||
|
||||
*成功值(新的已解析, 位置 + 1)*
|
||||
|
||||
3. `true`
|
||||
|
||||
*失败("json.invalid_object", "对象缺少逗号或 }")*
|
||||
|
||||
## 解析值
|
||||
|
||||
`(点, 位置)`
|
||||
|
||||
**位置 = 跳过空白(点, 位置)**
|
||||
|
||||
1. `位置 >= 长度(点)`
|
||||
|
||||
*失败("json.unexpected_eof", "需要值")*
|
||||
|
||||
**首 = text.from_codepoint(点[位置])**
|
||||
|
||||
**首码点 = 点[位置]**
|
||||
|
||||
1. `首码点 == 34`
|
||||
|
||||
*解析字符串(点, 位置)*
|
||||
|
||||
2. `首码点 == 123`
|
||||
|
||||
*解析对象(点, 位置)*
|
||||
|
||||
3. `首 == "["`
|
||||
|
||||
*解析数组(点, 位置)*
|
||||
|
||||
4. `首 == "-" or 是数字(点[位置])`
|
||||
|
||||
*解析数字(点, 位置)*
|
||||
|
||||
5. `首 == "t"`
|
||||
|
||||
1. `匹配(点, 位置, "true")`
|
||||
|
||||
*成功值(true, 位置 + 4)*
|
||||
|
||||
2. `true`
|
||||
|
||||
*失败("json.invalid_literal", "无效字面量")*
|
||||
|
||||
6. `首 == "f"`
|
||||
|
||||
1. `匹配(点, 位置, "false")`
|
||||
|
||||
*成功值(false, 位置 + 5)*
|
||||
|
||||
2. `true`
|
||||
|
||||
*失败("json.invalid_literal", "无效字面量")*
|
||||
|
||||
7. `首 == "n"`
|
||||
|
||||
1. `匹配(点, 位置, "null")`
|
||||
|
||||
*成功值(None, 位置 + 4)*
|
||||
|
||||
2. `true`
|
||||
|
||||
*失败("json.invalid_literal", "无效字面量")*
|
||||
|
||||
8. `true`
|
||||
|
||||
*失败("json.unexpected_token", "不支持的值")*
|
||||
|
||||
## 解析数组
|
||||
|
||||
`(点, 位置)`
|
||||
|
||||
*解析数组项(点, 位置 + 1, [])*
|
||||
|
||||
## 解析数组项
|
||||
|
||||
`(点, 位置, 已解析)`
|
||||
|
||||
**位置 = 跳过空白(点, 位置)**
|
||||
|
||||
1. `位置 >= 长度(点)`
|
||||
|
||||
*失败("json.unexpected_eof", "数组未闭合")*
|
||||
|
||||
**当前 = text.from_codepoint(点[位置])**
|
||||
|
||||
1. `当前 == "]"`
|
||||
|
||||
*成功值(已解析, 位置 + 1)*
|
||||
|
||||
**项 = 解析值(点, 位置)**
|
||||
|
||||
1. `not 项.ok`
|
||||
|
||||
*项*
|
||||
|
||||
**新的已解析 = list.append(已解析, 项.value)**
|
||||
|
||||
**位置 = 跳过空白(点, 项.next)**
|
||||
|
||||
1. `位置 >= 长度(点)`
|
||||
|
||||
*失败("json.unexpected_eof", "数组未闭合")*
|
||||
|
||||
**分隔 = text.from_codepoint(点[位置])**
|
||||
|
||||
1. `分隔 == ","`
|
||||
|
||||
*解析数组项(点, 位置 + 1, 新的已解析)*
|
||||
|
||||
2. `分隔 == "]"`
|
||||
|
||||
*成功值(新的已解析, 位置 + 1)*
|
||||
|
||||
3. `true`
|
||||
|
||||
*失败("json.invalid_array", "数组缺少逗号或 ]")*
|
||||
|
||||
## 格式化文本
|
||||
|
||||
`(文本)`
|
||||
|
||||
**点 = text.codepoints(文本)**
|
||||
|
||||
**`结果 = "\""`**
|
||||
|
||||
**下标 = 0**
|
||||
|
||||
- `下标 < 长度(点)`
|
||||
|
||||
**码点 = 点[下标]**
|
||||
|
||||
1. `码点 == 34`
|
||||
|
||||
**`结果 = 结果 + "\\\""`**
|
||||
|
||||
2. `码点 == 92`
|
||||
|
||||
**`结果 = 结果 + "\\\\"`**
|
||||
|
||||
3. `码点 == 10`
|
||||
|
||||
**`结果 = 结果 + "\\n"`**
|
||||
|
||||
4. `码点 == 9`
|
||||
|
||||
**`结果 = 结果 + "\\t"`**
|
||||
|
||||
5. `码点 == 13`
|
||||
|
||||
**`结果 = 结果 + "\\r"`**
|
||||
|
||||
6. `true`
|
||||
|
||||
**结果 = 结果 + text.from_codepoint(码点)**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
*`结果 + "\""`*
|
||||
|
||||
## 格式化列表
|
||||
|
||||
`(列表)`
|
||||
|
||||
**结果 = "["**
|
||||
|
||||
**下标 = 0**
|
||||
|
||||
- `下标 < 长度(列表)`
|
||||
|
||||
1. `下标 > 0`
|
||||
|
||||
**结果 = 结果 + ", "**
|
||||
|
||||
2. `true`
|
||||
|
||||
**忽略 = 0**
|
||||
|
||||
**结果 = 结果 + 格式化(列表[下标])**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
*结果 + "]"*
|
||||
|
||||
## 格式化对象
|
||||
|
||||
`(映射)`
|
||||
|
||||
**键列表 = map.keys(映射)**
|
||||
|
||||
**结果 = "{"**
|
||||
|
||||
**下标 = 0**
|
||||
|
||||
- `下标 < 长度(键列表)`
|
||||
|
||||
1. `下标 > 0`
|
||||
|
||||
**结果 = 结果 + ", "**
|
||||
|
||||
2. `true`
|
||||
|
||||
**忽略 = 0**
|
||||
|
||||
**当前键 = 键列表[下标]**
|
||||
|
||||
**结果 = 结果 + 格式化文本(当前键) + ": " + 格式化(map.get(映射, 当前键))**
|
||||
|
||||
**下标 = 下标 + 1**
|
||||
|
||||
*结果 + "}"*
|
||||
|
||||
## 格式化
|
||||
|
||||
`(值)`
|
||||
|
||||
**类别 = 类型(值)**
|
||||
|
||||
1. `类别 == "Text"`
|
||||
|
||||
*格式化文本(值)*
|
||||
|
||||
2. `类别 == "None"`
|
||||
|
||||
*"null"*
|
||||
|
||||
3. `类别 == "Bool" or 类别 == "Int" or 类别 == "Float"`
|
||||
|
||||
*文本(值)*
|
||||
|
||||
4. `类别 == "List"`
|
||||
|
||||
*格式化列表(值)*
|
||||
|
||||
5. `类别 == "Map"`
|
||||
|
||||
*格式化对象(值)*
|
||||
|
||||
*"null"*
|
||||
+1
-1
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"name": "marqdo-stdlib",
|
||||
"version": "0.1.0",
|
||||
"digest": "sha256:3a1544c355ad4b08d679126b4c51f7bc79d282a1b22c9a2bda805f24cc3d4023"
|
||||
"digest": "sha256:dc0ab593afeaabde0c1f688b039f35d6efac28936412ba624a408cf0d587aeb8"
|
||||
}
|
||||
@@ -0,0 +1,16 @@
|
||||
---
|
||||
import:
|
||||
csv: "std:data/csv"
|
||||
---
|
||||
|
||||
## main
|
||||
|
||||
**`行 = csv.解析行("甲,\"乙,丙\",\"说\"\"好\"")`**
|
||||
|
||||
**`空 = csv.解析行("")`**
|
||||
|
||||
**`坏 = csv.解析行("\"a")`**
|
||||
|
||||
**`框 = csv.解析行("a,\"b\"")`**
|
||||
|
||||
*[行.value, csv.格式化行(行.value), 空.value, 坏.code, 框.value]*
|
||||
@@ -0,0 +1,16 @@
|
||||
---
|
||||
import:
|
||||
json: "std:data/json"
|
||||
---
|
||||
|
||||
## main
|
||||
|
||||
**`对象 = json.解析("{\"a\": 1, \"b\": [true, null, \"说\\\"好\"]}")`**
|
||||
|
||||
**`浮点 = json.解析("[1, 2.5, -3e2, 4E-1, {\"a\": 1.0}, \"x\"]")`**
|
||||
|
||||
**`失败 = json.解析("[1 2]")`**
|
||||
|
||||
**`尾随 = json.解析("1 2")`**
|
||||
|
||||
*[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]*
|
||||
Reference in new issue
Block a user