Files
DevFlow/crates/df-project/src/scan/discover.rs
T

277 lines
9.3 KiB
Rust

//! 历史项目发现 — monorepo 识别 + 子项目展开(纯规则,不跑 LLM)。
use std::path::Path;
use anyhow::Result;
use super::stack::{detect_stack, has_file_with_ext};
use super::SAMPLE_IGNORED_DIRS;
/// monorepo 工作区配置文件名(JS 生态主流:pnpm/lerna/turbo/nx)
const MONOREPO_MARKERS: &[&str] = &[
"pnpm-workspace.yaml",
"lerna.json",
"turbo.json",
"nx.json",
];
/// 判定目录是否为 monorepo 根(JS 生态主流工作区管理器)。
///
/// 命中任一即视为 monorepo:
/// - pnpm-workspace.yaml / lerna.json / turbo.json / nx.json 存在
/// - package.json 含 `workspaces` 字段(npm/yarn workspaces)
pub fn is_monorepo(root: &Path) -> bool {
if !root.is_dir() {
return false;
}
for marker in MONOREPO_MARKERS {
if root.join(marker).is_file() {
return true;
}
}
// package.json workspaces 字段(npm/yarn)。数组(`["packages/*"]`)或对象
// (`{"packages":[...]}`,Yarn)均为真正的工作区;JSON 显式 null 表示「无」,
// 不应误判为 monorepo(`.is_some()` 对 key 存在但值为 null 仍返回 true → 误报)。
let pkg_path = root.join("package.json");
if pkg_path.is_file() {
if let Ok(content) = std::fs::read_to_string(&pkg_path) {
if let Ok(pkg) = serde_json::from_str::<serde_json::Value>(&content) {
if pkg.get("workspaces").is_some_and(|v| !v.is_null()) {
return true;
}
}
}
}
false
}
/// 单个发现的候选项目(monorepo 子项目或独立项目)
#[derive(Debug, Clone)]
pub struct DiscoveredProject {
/// 项目根目录绝对路径
pub path: String,
/// 推断的项目名(目录名)
pub name: String,
/// 规则探测的技术栈(空=未识别)
pub stack: Vec<String>,
/// 是否为 monorepo 根(便于前端标记)
pub is_monorepo: bool,
}
/// 在指定根目录下发现候选项目。
///
/// 策略(只展开一层,不做深递归):
/// 1. 根目录本身有项目标志(Cargo.toml/package.json/go.mod 等)→ 根为独立项目
/// 2. 根目录是 monorepo → 展开 packages/\*/apps/\* 直接子目录(各子目录跑 detect_stack 过滤空)
/// 3. 否则:扫根的直接子目录,凡 detect_stack 非空的视为候选项目
///
/// 不跑 LLM(快),不读源码。空 stack 的目录在 monorepo 展开/子目录扫描时被过滤。
pub fn discover_projects(root: &Path) -> Result<Vec<DiscoveredProject>> {
if !root.is_dir() {
anyhow::bail!("路径不是目录: {}", root.display());
}
let mut out: Vec<DiscoveredProject> = Vec::new();
let mono = is_monorepo(root);
// 1. 根目录自身是项目(有 manifest 标志)
if has_project_manifest(root) {
let stack = detect_stack(root).unwrap_or_default();
out.push(DiscoveredProject {
path: root.to_string_lossy().to_string(),
name: root
.file_name()
.and_then(|n| n.to_str())
.map(|s| s.to_string())
.unwrap_or_else(|| root.to_string_lossy().to_string()),
stack,
is_monorepo: mono,
});
}
// 2. monorepo → 展开 packages/* apps/* 直接子目录
// 3. 普通目录 → 扫直接子目录,凡 detect_stack 非空的入选
let scan_globs: &[&str] = if mono {
&["packages", "apps"]
} else {
&[""]
};
for glob in scan_globs {
let target = if glob.is_empty() {
root.to_path_buf()
} else {
root.join(glob)
};
if !target.is_dir() {
continue;
}
let Ok(entries) = std::fs::read_dir(&target) else {
continue;
};
for e in entries.flatten() {
let p = e.path();
if !p.is_dir() {
continue;
}
let name = e.file_name().to_string_lossy().to_string();
if SAMPLE_IGNORED_DIRS.contains(&name.as_str()) || name.starts_with('.') {
continue;
}
// 必须有项目标志 + detect_stack 非空
if !has_project_manifest(&p) {
continue;
}
let stack = match detect_stack(&p) {
Ok(s) => s,
Err(_) => continue,
};
if stack.is_empty() {
continue;
}
out.push(DiscoveredProject {
path: p.to_string_lossy().to_string(),
name,
stack,
is_monorepo: false,
});
}
}
Ok(out)
}
/// 目录是否含任一项目清单标志文件
fn has_project_manifest(dir: &Path) -> bool {
const MARKS: &[&str] = &[
"Cargo.toml",
"package.json",
"go.mod",
"pyproject.toml",
"requirements.txt",
"pom.xml",
"build.gradle",
"build.gradle.kts",
];
MARKS.iter().any(|m| dir.join(m).is_file()) || has_file_with_ext(dir, "csproj")
}
#[cfg(test)]
mod tests {
use super::*;
use std::fs;
use std::path::PathBuf;
/// 在系统临时目录建唯一子目录(以进程号隔离并发),返回路径
fn scratch(name: &str) -> PathBuf {
let mut p = std::env::temp_dir();
p.push(format!("df-project-scan-{}-{}", name, std::process::id()));
let _ = fs::remove_dir_all(&p);
fs::create_dir_all(&p).unwrap();
p
}
#[test]
fn detects_monorepo_pnpm() {
let d = scratch("mono-pnpm");
fs::write(d.join("pnpm-workspace.yaml"), "packages:\n - packages/*\n").unwrap();
assert!(is_monorepo(&d));
fs::remove_dir_all(&d).ok();
}
#[test]
fn detects_monorepo_npm_workspaces() {
let d = scratch("mono-npm");
fs::write(
d.join("package.json"),
r#"{"name":"root","workspaces":["packages/*"]}"#,
)
.unwrap();
assert!(is_monorepo(&d));
fs::remove_dir_all(&d).ok();
}
#[test]
fn detects_non_monorepo() {
let d = scratch("nonmono");
fs::write(d.join("package.json"), r#"{"name":"x"}"#).unwrap();
assert!(!is_monorepo(&d));
fs::remove_dir_all(&d).ok();
}
#[test]
fn discover_monorepo_children() {
let d = scratch("discover-mono");
fs::write(d.join("pnpm-workspace.yaml"), "packages:\n - packages/*\n").unwrap();
// 子项目:packages/web(有 package.json + vue)、packages/cli(有 Cargo.toml)
fs::create_dir_all(d.join("packages/web")).unwrap();
fs::write(
d.join("packages/web/package.json"),
r#"{"name":"web","dependencies":{"vue":"3"}}"#,
)
.unwrap();
fs::create_dir_all(d.join("packages/cli")).unwrap();
fs::write(d.join("packages/cli/Cargo.toml"), "[package]\nname=\"cli\"\n").unwrap();
// 空 stack 子目录应过滤
fs::create_dir_all(d.join("packages/empty")).unwrap();
fs::write(d.join("packages/empty/x.txt"), "x").unwrap();
let found = discover_projects(&d).unwrap();
// 根自身无 manifest 不入选;packages/web + packages/cli 入选;empty 过滤
let names: Vec<_> = found.iter().map(|p| p.name.as_str()).collect();
assert!(names.contains(&"web"), "names={names:?}");
assert!(names.contains(&"cli"), "names={names:?}");
assert!(!names.contains(&"empty"), "空 stack 未过滤: {names:?}");
fs::remove_dir_all(&d).ok();
}
#[test]
fn discover_flat_children() {
// 非 monorepo:扫根直接子目录中 detect_stack 非空的
let d = scratch("discover-flat");
fs::create_dir_all(d.join("proj-a")).unwrap();
fs::write(d.join("proj-a/Cargo.toml"), "").unwrap();
fs::create_dir_all(d.join("not-a-project")).unwrap();
fs::write(d.join("not-a-project/readme.txt"), "x").unwrap();
let found = discover_projects(&d).unwrap();
let names: Vec<_> = found.iter().map(|p| p.name.as_str()).collect();
assert!(names.contains(&"proj-a"), "names={names:?}");
assert!(!names.contains(&"not-a-project"), "空 stack 未过滤: {names:?}");
fs::remove_dir_all(&d).ok();
}
// ── is_monorepo workspaces:null 防回归(wd2fnjh3s) ──
// .is_some_and(!is_null) 修复点:key 存在但值为 JSON null 时不得判为 monorepo。
#[test]
fn is_monorepo_workspaces_null_not_misclassified() {
let d = scratch("ws-null");
fs::write(
d.join("package.json"),
r#"{"name":"x","workspaces":null}"#,
)
.unwrap();
assert!(
!is_monorepo(&d),
"workspaces: null 不应判为 monorepo(回归 wd2fnjh3s)"
);
fs::remove_dir_all(&d).ok();
}
#[test]
fn is_monorepo_workspaces_object_treated_as_real() {
// Yarn 形式 {"packages":[...]} —— 非 null,应判为 monorepo
let d = scratch("ws-obj");
fs::write(
d.join("package.json"),
r#"{"name":"y","workspaces":{"packages":["packages/*"]}}"#,
)
.unwrap();
assert!(is_monorepo(&d), "Yarn workspaces 对象形式应判为 monorepo");
fs::remove_dir_all(&d).ok();
}
#[test]
fn is_monorepo_non_dir_returns_false() {
assert!(!is_monorepo(Path::new("definitely-not-exist-xyz-456")));
}
}