refactor: extract shared lint record primitives
This commit is contained in:
@@ -0,0 +1,13 @@
|
||||
[package]
|
||||
name = "lint-common"
|
||||
version = "0.1.0"
|
||||
edition.workspace = true
|
||||
license.workspace = true
|
||||
|
||||
[dependencies]
|
||||
chrono = { version = "0.4", features = ["serde"] }
|
||||
serde = { workspace = true, features = ["derive"] }
|
||||
thiserror = { workspace = true }
|
||||
|
||||
[dev-dependencies]
|
||||
serde_json = { workspace = true }
|
||||
@@ -0,0 +1,81 @@
|
||||
//! Common frontmatter helpers.
|
||||
|
||||
use chrono::{DateTime, Utc};
|
||||
|
||||
use crate::RecordLintError;
|
||||
|
||||
/// Trait record frontmatter types implement so linters can drive them uniformly.
|
||||
pub trait Frontmatter: Sized {
|
||||
/// Hard upper bound on body chars (excluding the frontmatter block).
|
||||
const BODY_LIMIT: usize;
|
||||
|
||||
fn created_at(&self) -> Option<DateTime<Utc>>;
|
||||
fn updated_at(&self) -> Option<DateTime<Utc>>;
|
||||
}
|
||||
|
||||
const FRONTMATTER_DELIM: &str = "---";
|
||||
|
||||
/// Split a markdown document into `(yaml_frontmatter, body)`.
|
||||
///
|
||||
/// Expects the document to start with `---\n` and have a closing
|
||||
/// `---\n` (or `---` at EOF) somewhere downstream. Trailing newline
|
||||
/// after the closing delimiter is consumed.
|
||||
pub fn split_frontmatter(content: &str) -> Result<(&str, &str), RecordLintError> {
|
||||
// The opening delimiter must be the very first line.
|
||||
let after_open = content
|
||||
.strip_prefix(FRONTMATTER_DELIM)
|
||||
.and_then(|s| s.strip_prefix('\n').or(Some(s)))
|
||||
.ok_or(RecordLintError::MissingFrontmatter)?;
|
||||
|
||||
// Look for the closing `---` on its own line.
|
||||
let mut yaml_end = None;
|
||||
let mut byte_offset = 0usize;
|
||||
for line in after_open.split_inclusive('\n') {
|
||||
let trimmed = line.trim_end_matches('\n').trim_end_matches('\r');
|
||||
if trimmed == FRONTMATTER_DELIM {
|
||||
yaml_end = Some((byte_offset, byte_offset + line.len()));
|
||||
break;
|
||||
}
|
||||
byte_offset += line.len();
|
||||
}
|
||||
|
||||
let (yaml_end_excl, body_start) = yaml_end.ok_or_else(|| {
|
||||
RecordLintError::MalformedFrontmatter("missing closing `---` line".to_string())
|
||||
})?;
|
||||
|
||||
let yaml = &after_open[..yaml_end_excl];
|
||||
let body = &after_open[body_start..];
|
||||
Ok((yaml, body))
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn splits_simple() {
|
||||
let doc = "---\nfoo: 1\n---\nbody here\n";
|
||||
let (y, b) = split_frontmatter(doc).unwrap();
|
||||
assert_eq!(y, "foo: 1\n");
|
||||
assert_eq!(b, "body here\n");
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_leading_delim_errors() {
|
||||
let err = split_frontmatter("hello").unwrap_err();
|
||||
assert!(matches!(err, RecordLintError::MissingFrontmatter));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn no_closing_delim_errors() {
|
||||
let err = split_frontmatter("---\nfoo: 1\nno close\n").unwrap_err();
|
||||
assert!(matches!(err, RecordLintError::MalformedFrontmatter(_)));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn handles_empty_body() {
|
||||
let doc = "---\nfoo: 1\n---\n";
|
||||
let (_, b) = split_frontmatter(doc).unwrap();
|
||||
assert_eq!(b, "");
|
||||
}
|
||||
}
|
||||
@@ -0,0 +1,20 @@
|
||||
//! Shared record lint primitives for memory and workflow files.
|
||||
|
||||
mod frontmatter;
|
||||
mod slug;
|
||||
|
||||
pub use frontmatter::{Frontmatter, split_frontmatter};
|
||||
pub use slug::{Slug, is_valid_slug};
|
||||
|
||||
/// Common lint errors for Markdown record syntax shared by memory and workflow.
|
||||
#[derive(Debug, Clone, thiserror::Error, PartialEq, Eq)]
|
||||
pub enum RecordLintError {
|
||||
#[error("invalid slug `{0}`: must match ^[a-z0-9](?:[a-z0-9-]{{0,62}}[a-z0-9])?$")]
|
||||
InvalidSlug(String),
|
||||
|
||||
#[error("malformed frontmatter: {0}")]
|
||||
MalformedFrontmatter(String),
|
||||
|
||||
#[error("frontmatter is missing or document is empty")]
|
||||
MissingFrontmatter,
|
||||
}
|
||||
@@ -0,0 +1,146 @@
|
||||
//! Slug type and validation.
|
||||
//!
|
||||
//! Syntax (agent-skills compatible):
|
||||
//! ^[a-z0-9](?:[a-z0-9-]{0,62}[a-z0-9])?$
|
||||
//! - 1–64 chars
|
||||
//! - lowercase ASCII alphanumerics and `-`
|
||||
//! - cannot start or end with `-`
|
||||
//! - no consecutive `--`
|
||||
|
||||
use std::fmt;
|
||||
use std::str::FromStr;
|
||||
|
||||
use serde::{Deserialize, Deserializer, Serialize};
|
||||
|
||||
use crate::RecordLintError;
|
||||
|
||||
const MIN_LEN: usize = 1;
|
||||
const MAX_LEN: usize = 64;
|
||||
|
||||
/// Validated slug. Constructible only via [`Slug::parse`].
|
||||
#[derive(Debug, Clone, PartialEq, Eq, Hash, PartialOrd, Ord, Serialize)]
|
||||
#[serde(transparent)]
|
||||
pub struct Slug(String);
|
||||
|
||||
impl Slug {
|
||||
/// Parse and validate. Returns [`RecordLintError::InvalidSlug`] on rejection.
|
||||
pub fn parse(s: impl Into<String>) -> Result<Self, RecordLintError> {
|
||||
let s = s.into();
|
||||
if is_valid_slug(&s) {
|
||||
Ok(Self(s))
|
||||
} else {
|
||||
Err(RecordLintError::InvalidSlug(s))
|
||||
}
|
||||
}
|
||||
|
||||
pub fn as_str(&self) -> &str {
|
||||
&self.0
|
||||
}
|
||||
|
||||
pub fn into_string(self) -> String {
|
||||
self.0
|
||||
}
|
||||
}
|
||||
|
||||
impl fmt::Display for Slug {
|
||||
fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result {
|
||||
f.write_str(&self.0)
|
||||
}
|
||||
}
|
||||
|
||||
impl AsRef<str> for Slug {
|
||||
fn as_ref(&self) -> &str {
|
||||
&self.0
|
||||
}
|
||||
}
|
||||
|
||||
impl FromStr for Slug {
|
||||
type Err = RecordLintError;
|
||||
|
||||
fn from_str(s: &str) -> Result<Self, Self::Err> {
|
||||
Self::parse(s)
|
||||
}
|
||||
}
|
||||
|
||||
impl<'de> Deserialize<'de> for Slug {
|
||||
fn deserialize<D>(deserializer: D) -> Result<Self, D::Error>
|
||||
where
|
||||
D: Deserializer<'de>,
|
||||
{
|
||||
let raw = String::deserialize(deserializer)?;
|
||||
Self::parse(raw).map_err(serde::de::Error::custom)
|
||||
}
|
||||
}
|
||||
|
||||
/// Pure-fn predicate matching the agent-skills slug regex without
|
||||
/// pulling in the `regex` crate.
|
||||
pub fn is_valid_slug(s: &str) -> bool {
|
||||
let bytes = s.as_bytes();
|
||||
let len = bytes.len();
|
||||
if len < MIN_LEN || len > MAX_LEN {
|
||||
return false;
|
||||
}
|
||||
if !is_alnum_lower(bytes[0]) || !is_alnum_lower(bytes[len - 1]) {
|
||||
return false;
|
||||
}
|
||||
let mut prev_dash = false;
|
||||
for &b in bytes {
|
||||
if b == b'-' {
|
||||
if prev_dash {
|
||||
return false;
|
||||
}
|
||||
prev_dash = true;
|
||||
} else if is_alnum_lower(b) {
|
||||
prev_dash = false;
|
||||
} else {
|
||||
return false;
|
||||
}
|
||||
}
|
||||
true
|
||||
}
|
||||
|
||||
fn is_alnum_lower(b: u8) -> bool {
|
||||
b.is_ascii_digit() || b.is_ascii_lowercase()
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
|
||||
#[test]
|
||||
fn accepts_basic_slugs() {
|
||||
for s in ["a", "ab", "abc-def", "x9", "a-b-c", "123", "a-1"] {
|
||||
assert!(is_valid_slug(s), "expected `{s}` valid");
|
||||
assert!(Slug::parse(s).is_ok());
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn rejects_bad_slugs() {
|
||||
for s in [
|
||||
"", "-", "-foo", "foo-", "Foo", "foo_bar", "foo bar", "foo--bar", "foo.bar", "ä",
|
||||
] {
|
||||
assert!(!is_valid_slug(s), "expected `{s}` invalid");
|
||||
assert!(Slug::parse(s).is_err());
|
||||
}
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn enforces_length_bounds() {
|
||||
let too_long = "a".repeat(MAX_LEN + 1);
|
||||
assert!(!is_valid_slug(&too_long));
|
||||
let max = "a".repeat(MAX_LEN);
|
||||
assert!(is_valid_slug(&max));
|
||||
}
|
||||
|
||||
#[test]
|
||||
fn deserializes_via_serde() {
|
||||
let json = "\"valid-slug\"";
|
||||
let slug: Slug = serde_json::from_str(json).unwrap();
|
||||
assert_eq!(slug.as_str(), "valid-slug");
|
||||
|
||||
let bad = "\"BAD\"";
|
||||
let err: Result<Slug, _> = serde_json::from_str(bad);
|
||||
assert!(err.is_err());
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user