feat(p10-1a-1): kebab-parse-code crate (lang + repo + skip)

Tasks 5-8: new `kebab-parse-code` crate with three infrastructure modules
for the code ingest framework. Ships lang.rs (extension→language identifier
mapping), repo.rs (.git walk-up via gix 0.70 for RepoMeta), and skip.rs
(BUILTIN_BLACKLIST, is_generated_file, is_oversized). 14 integration tests
across three test files, all passing; clippy -D warnings clean.

Note: gix pinned to 0.70 (not 0.83 as originally suggested) because 0.83
fails to compile against Rust 1.94.1 due to non-exhaustive match patterns
in gix-hash. 0.70 resolves cleanly and has identical head_name/head_id API.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

crates/kebab-parse-code/Cargo.toml

@@ -0,0 +1,13 @@
+[package]
+name = "kebab-parse-code"
+version       = { workspace = true }
+edition       = { workspace = true }
+license       = { workspace = true }
+
+[dependencies]
+anyhow      = { workspace = true }
+gix         = { workspace = true }
+kebab-core  = { path = "../kebab-core" }
+
+[dev-dependencies]
+tempfile = { workspace = true }

crates/kebab-parse-code/src/lang.rs

@@ -0,0 +1,42 @@
+//! Canonical extension → language identifier mapping (spec §3.5).
+//!
+//! Lowercase canonical identifiers, matching tree-sitter parser conventions:
+//! `rust`, `python`, `typescript`, `javascript`, `go`, `java`, `kotlin`, `c`,
+//! `cpp`, `yaml`, `toml`, `json`, `shell`, `make`, `dockerfile`.
+
+use std::path::Path;
+
+/// Returns the canonical language identifier for a given file path, or
+/// `None` if the extension / filename is not recognized.
+///
+/// Matching priority:
+///   1. exact filename match (e.g. `Dockerfile`, `Makefile`)
+///   2. lowercase extension match
+pub fn code_lang_for_path(path: &Path) -> Option<&'static str> {
+    if let Some(name) = path.file_name().and_then(|n| n.to_str()) {
+        match name {
+            "Dockerfile" => return Some("dockerfile"),
+            "Makefile" | "GNUmakefile" => return Some("make"),
+            _ => {}
+        }
+    }
+    let ext = path.extension()?.to_str()?.to_ascii_lowercase();
+    match ext.as_str() {
+        "rs" => Some("rust"),
+        "py" | "pyi" => Some("python"),
+        "ts" | "tsx" => Some("typescript"),
+        "js" | "mjs" | "cjs" | "jsx" => Some("javascript"),
+        "go" => Some("go"),
+        "java" => Some("java"),
+        "kt" | "kts" => Some("kotlin"),
+        "c" | "h" => Some("c"),
+        "cpp" | "cc" | "cxx" | "hpp" | "hh" | "hxx" => Some("cpp"),
+        "yaml" | "yml" => Some("yaml"),
+        "toml" => Some("toml"),
+        "json" => Some("json"),
+        "sh" | "bash" | "zsh" => Some("shell"),
+        "mk" => Some("make"),
+        "dockerfile" => Some("dockerfile"),
+        _ => None,
+    }
+}

crates/kebab-parse-code/src/lib.rs

@@ -0,0 +1,22 @@
+//! `kebab-parse-code` — language-aware parsing for code corpora.
+//!
+//! Phase 1A-1 ships infrastructure only:
+//!
+//! - [`lang::code_lang_for_path`] — extension → language identifier.
+//! - [`repo::detect_repo`] — `.git/` walk-up → repo / branch / commit metadata.
+//! - [`skip::is_generated_file`] / [`skip::is_oversized`] — pre-ingest skip
+//!   helpers consulted by `kebab-source-fs`.
+//! - [`skip::BUILTIN_BLACKLIST`] — 6-entry safety-net pattern list.
+//!
+//! Per-language parser modules (`rust`, `python`, `typescript`, …) land in
+//! later phases (1A-2 onwards). The crate boundary follows other
+//! `kebab-parse-*` crates per design §8: must NOT depend on store / embed
+//! / llm / rag.
+
+pub mod lang;
+pub mod repo;
+pub mod skip;
+
+pub use lang::code_lang_for_path;
+pub use repo::{RepoMeta, detect_repo};
+pub use skip::{BUILTIN_BLACKLIST, is_generated_file, is_oversized};

crates/kebab-parse-code/src/repo.rs

@@ -0,0 +1,61 @@
+//! Git repo auto-detection (spec §5.1).
+//!
+//! Walks up from `path` looking for a `.git/` directory. If found, reads
+//! repo dir name, current branch, and HEAD commit using `gix` (pure Rust;
+//! no `git` binary on PATH required).
+
+use std::path::Path;
+
+#[derive(Clone, Debug, PartialEq, Eq)]
+pub struct RepoMeta {
+    pub name: String,
+    pub branch: Option<String>,
+    pub commit: Option<String>,
+}
+
+/// Walk up from `path` until a `.git/` directory is found. Returns repo
+/// metadata, or `None` if no repo boundary is reached before the filesystem
+/// root.
+///
+/// - `name`: directory name containing `.git/`.
+/// - `branch`: current HEAD branch, or `"detached"` if detached HEAD, or
+///   `None` if branch can't be read.
+/// - `commit`: 40-hex commit SHA at HEAD, or `None` if empty repo / read
+///   failure.
+///
+/// `.git/` as a file (worktree marker / submodule) returns `None` for
+/// `branch` and `commit` and falls back to the parent dir name for `name`.
+pub fn detect_repo(path: &Path) -> Option<RepoMeta> {
+    let mut cur = if path.is_dir() { path } else { path.parent()? };
+    loop {
+        let dotgit = cur.join(".git");
+        if dotgit.is_dir() {
+            let name = cur.file_name()?.to_string_lossy().into_owned();
+            let (branch, commit) = read_head(cur);
+            return Some(RepoMeta { name, branch, commit });
+        } else if dotgit.is_file() {
+            let name = cur.file_name()?.to_string_lossy().into_owned();
+            return Some(RepoMeta { name, branch: None, commit: None });
+        }
+        cur = cur.parent()?;
+    }
+}
+
+fn read_head(repo_dir: &Path) -> (Option<String>, Option<String>) {
+    match gix::open(repo_dir) {
+        Ok(repo) => {
+            let branch = repo
+                .head_name()
+                .ok()
+                .flatten()
+                .map(|n| n.shorten().to_string())
+                .or_else(|| Some("detached".to_string()));
+            let commit = repo
+                .head_id()
+                .ok()
+                .map(|id| id.to_string());
+            (branch, commit)
+        }
+        Err(_) => (None, None),
+    }
+}

crates/kebab-parse-code/src/skip.rs

@@ -0,0 +1,65 @@
+//! Pre-ingest skip helpers (spec §5.2 + §5.3 + §5.4).
+//!
+//! - [`BUILTIN_BLACKLIST`] — 6 gitignore-style patterns universal across
+//!   ecosystems. Source of truth: spec §5.2.
+//! - [`is_generated_file`] — reads first ~512 bytes, checks for 7
+//!   case-insensitive markers.
+//! - [`is_oversized`] — byte cap then line cap.
+
+use anyhow::Result;
+use std::fs::File;
+use std::io::{BufRead, BufReader, Read};
+use std::path::Path;
+
+/// 6 built-in gitignore-style patterns. Applied in addition to `.gitignore`
+/// + `.kebabignore`. User can override via `.kebabignore` negation
+///   (`!pattern`).
+pub const BUILTIN_BLACKLIST: &[&str] = &[
+    "**/node_modules/**",
+    "**/target/**",
+    "**/__pycache__/**",
+    "**/.venv/**",
+    "**/venv/**",
+    "**/env/**",
+];
+
+/// Read first 512 bytes, check for any of 7 case-insensitive generated-file
+/// markers. Returns Ok(true) on match, Ok(false) otherwise.
+pub fn is_generated_file(path: &Path) -> Result<bool> {
+    let mut buf = [0u8; 512];
+    let mut f = File::open(path)?;
+    let n = f.read(&mut buf)?;
+    if n == 0 {
+        return Ok(false);
+    }
+    let head = std::str::from_utf8(&buf[..n]).unwrap_or("");
+    let lower: String = head.lines().take(10).collect::<Vec<_>>().join("\n").to_ascii_lowercase();
+    Ok(
+        lower.contains("@generated")
+            || lower.contains("code generated by")
+            || lower.contains("do not edit")
+            || lower.contains("do not modify")
+            || lower.contains("automatically generated")
+            || lower.contains("auto-generated")
+            || lower.contains("autogenerated"),
+    )
+}
+
+/// Check if `path` exceeds `max_bytes` or `max_lines`. Byte cap first
+/// (cheap), then line cap (streaming with early exit).
+pub fn is_oversized(path: &Path, max_bytes: u64, max_lines: u32) -> Result<bool> {
+    let meta = std::fs::metadata(path)?;
+    if meta.len() > max_bytes {
+        return Ok(true);
+    }
+    let reader = BufReader::new(File::open(path)?);
+    let mut count: u32 = 0;
+    for line in reader.lines() {
+        let _ = line?;
+        count = count.saturating_add(1);
+        if count > max_lines {
+            return Ok(true);
+        }
+    }
+    Ok(false)
+}

crates/kebab-parse-code/tests/lang.rs

@@ -0,0 +1,64 @@
+use kebab_parse_code::code_lang_for_path;
+use std::path::Path;
+
+#[test]
+fn known_extensions_map_to_canonical_identifiers() {
+    let cases = [
+        ("foo.rs", Some("rust")),
+        ("foo.py", Some("python")),
+        ("foo.pyi", Some("python")),
+        ("foo.ts", Some("typescript")),
+        ("foo.tsx", Some("typescript")),
+        ("foo.js", Some("javascript")),
+        ("foo.mjs", Some("javascript")),
+        ("foo.cjs", Some("javascript")),
+        ("foo.jsx", Some("javascript")),
+        ("foo.go", Some("go")),
+        ("foo.java", Some("java")),
+        ("foo.kt", Some("kotlin")),
+        ("foo.kts", Some("kotlin")),
+        ("foo.c", Some("c")),
+        ("foo.h", Some("c")),
+        ("foo.cpp", Some("cpp")),
+        ("foo.cc", Some("cpp")),
+        ("foo.cxx", Some("cpp")),
+        ("foo.hpp", Some("cpp")),
+        ("foo.hh", Some("cpp")),
+        ("foo.hxx", Some("cpp")),
+        ("foo.yaml", Some("yaml")),
+        ("foo.yml", Some("yaml")),
+        ("foo.toml", Some("toml")),
+        ("foo.json", Some("json")),
+        ("foo.sh", Some("shell")),
+        ("foo.bash", Some("shell")),
+        ("foo.zsh", Some("shell")),
+        ("foo.mk", Some("make")),
+    ];
+    for (path, expected) in cases {
+        assert_eq!(
+            code_lang_for_path(Path::new(path)),
+            expected,
+            "path = {path}"
+        );
+    }
+}
+
+#[test]
+fn special_filenames_map_to_identifiers() {
+    assert_eq!(code_lang_for_path(Path::new("Dockerfile")), Some("dockerfile"));
+    assert_eq!(code_lang_for_path(Path::new("foo.dockerfile")), Some("dockerfile"));
+    assert_eq!(code_lang_for_path(Path::new("Makefile")), Some("make"));
+}
+
+#[test]
+fn unknown_extension_returns_none() {
+    assert_eq!(code_lang_for_path(Path::new("foo.docx")), None);
+    assert_eq!(code_lang_for_path(Path::new("foo")), None);
+    assert_eq!(code_lang_for_path(Path::new("foo.unknown")), None);
+}
+
+#[test]
+fn case_insensitive() {
+    assert_eq!(code_lang_for_path(Path::new("Foo.RS")), Some("rust"));
+    assert_eq!(code_lang_for_path(Path::new("FOO.YAML")), Some("yaml"));
+}

crates/kebab-parse-code/tests/repo.rs

@@ -0,0 +1,62 @@
+use kebab_parse_code::repo::detect_repo;
+use std::fs;
+use std::process::Command;
+use tempfile::TempDir;
+
+fn init_git_repo(root: &std::path::Path) {
+    let run = |args: &[&str]| {
+        Command::new("git")
+            .args(args)
+            .current_dir(root)
+            .status()
+            .expect("git command failed");
+    };
+    run(&["init", "-q"]);
+    run(&["config", "user.email", "test@test"]);
+    run(&["config", "user.name", "test"]);
+    fs::write(root.join("README.md"), "hi").unwrap();
+    run(&["add", "README.md"]);
+    run(&["commit", "-q", "-m", "init"]);
+}
+
+#[test]
+fn detect_repo_returns_none_outside_git() {
+    let tmp = TempDir::new().unwrap();
+    let nested = tmp.path().join("a/b/c.txt");
+    fs::create_dir_all(nested.parent().unwrap()).unwrap();
+    fs::write(&nested, "x").unwrap();
+    assert!(detect_repo(&nested).is_none());
+}
+
+#[test]
+fn detect_repo_walks_up_to_git_dir() {
+    let tmp = TempDir::new().unwrap();
+    let repo_root = tmp.path().join("myrepo");
+    fs::create_dir_all(&repo_root).unwrap();
+    init_git_repo(&repo_root);
+    let nested = repo_root.join("src/deep/file.rs");
+    fs::create_dir_all(nested.parent().unwrap()).unwrap();
+    fs::write(&nested, "x").unwrap();
+
+    let meta = detect_repo(&nested).expect("should detect repo");
+    assert_eq!(meta.name, "myrepo");
+    assert!(meta.branch.is_some());
+    assert!(meta.commit.is_some());
+    assert_eq!(meta.commit.as_ref().unwrap().len(), 40);
+}
+
+#[test]
+fn detect_repo_caches_per_path_call_for_repeated_files_in_same_repo() {
+    let tmp = TempDir::new().unwrap();
+    let repo_root = tmp.path().join("myrepo");
+    fs::create_dir_all(&repo_root).unwrap();
+    init_git_repo(&repo_root);
+    let f1 = repo_root.join("a.rs");
+    let f2 = repo_root.join("b.rs");
+    fs::write(&f1, "x").unwrap();
+    fs::write(&f2, "x").unwrap();
+    let m1 = detect_repo(&f1).unwrap();
+    let m2 = detect_repo(&f2).unwrap();
+    assert_eq!(m1.name, m2.name);
+    assert_eq!(m1.commit, m2.commit);
+}

crates/kebab-parse-code/tests/skip.rs

@@ -0,0 +1,74 @@
+use kebab_parse_code::skip::{BUILTIN_BLACKLIST, is_generated_file, is_oversized};
+use std::fs;
+use tempfile::NamedTempFile;
+
+#[test]
+fn generated_header_markers_trigger_skip() {
+    let cases = [
+        "// @generated\nfn foo() {}\n",
+        "// Code generated by tonic-build. DO NOT EDIT.\nfn x() {}\n",
+        "/* DO NOT EDIT */\nfn x() {}\n",
+        "/* do not modify */\nfn x() {}\n",
+        "// AUTOMATICALLY GENERATED\nfn x() {}\n",
+        "# auto-generated\ndef x(): pass\n",
+        "// autogenerated\nfn x() {}\n",
+    ];
+    for content in cases {
+        let f = NamedTempFile::new().unwrap();
+        fs::write(f.path(), content).unwrap();
+        assert!(is_generated_file(f.path()).unwrap(), "content: {content:?}");
+    }
+}
+
+#[test]
+fn normal_code_is_not_flagged_generated() {
+    let f = NamedTempFile::new().unwrap();
+    fs::write(f.path(), "fn main() {\n    println!(\"hi\");\n}\n").unwrap();
+    assert!(!is_generated_file(f.path()).unwrap());
+}
+
+#[test]
+fn is_generated_returns_false_for_empty_file() {
+    let f = NamedTempFile::new().unwrap();
+    fs::write(f.path(), "").unwrap();
+    assert!(!is_generated_file(f.path()).unwrap());
+}
+
+#[test]
+fn oversized_by_bytes_returns_true() {
+    let f = NamedTempFile::new().unwrap();
+    let body: String = "x".repeat(300_000);
+    fs::write(f.path(), &body).unwrap();
+    assert!(is_oversized(f.path(), 262_144, 5_000).unwrap());
+}
+
+#[test]
+fn oversized_by_lines_returns_true() {
+    let f = NamedTempFile::new().unwrap();
+    let body: String = "x\n".repeat(6_000);
+    fs::write(f.path(), &body).unwrap();
+    assert!(is_oversized(f.path(), 262_144, 5_000).unwrap());
+}
+
+#[test]
+fn small_file_returns_false_for_oversize() {
+    let f = NamedTempFile::new().unwrap();
+    fs::write(f.path(), "fn foo() {}\n").unwrap();
+    assert!(!is_oversized(f.path(), 262_144, 5_000).unwrap());
+}
+
+#[test]
+fn builtin_blacklist_has_exactly_six_entries() {
+    assert_eq!(BUILTIN_BLACKLIST.len(), 6);
+    let expected = [
+        "**/node_modules/**",
+        "**/target/**",
+        "**/__pycache__/**",
+        "**/.venv/**",
+        "**/venv/**",
+        "**/env/**",
+    ];
+    for pat in expected {
+        assert!(BUILTIN_BLACKLIST.contains(&pat), "missing pattern: {pat}");
+    }
+}