Merge branch 'js/libgit-rust'

Foreign language interface for Rust into our code base has been added.

* js/libgit-rust:
  libgit: add higher-level libgit crate
  libgit-sys: also export some config_set functions
  libgit-sys: introduce Rust wrapper for libgit.a
  common-main: split init and exit code into new files

contrib/libgit-rs/Cargo.lock

@@ -0,0 +1,77 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "autocfg"
+version = "1.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ace50bade8e6234aa140d9a2f552bbee1db4d353f69b8217bc503490fc1a9f26"
+
+[[package]]
+name = "cc"
+version = "1.1.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57b6a275aa2903740dc87da01c62040406b8812552e97129a63ea8850a17c6e6"
+dependencies = [
+ "shlex",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.158"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d8adc4bb1803a324070e64a98ae98f38934d91957a99cfb3a43dcbc01bc56439"
+
+[[package]]
+name = "libgit"
+version = "0.1.0"
+dependencies = [
+ "autocfg",
+ "libgit-sys",
+]
+
+[[package]]
+name = "libgit-sys"
+version = "0.1.0"
+dependencies = [
+ "autocfg",
+ "libz-sys",
+ "make-cmd",
+]
+
+[[package]]
+name = "libz-sys"
+version = "1.1.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d2d16453e800a8cf6dd2fc3eb4bc99b786a9b90c663b8559a5b1a041bf89e472"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+ "vcpkg",
+]
+
+[[package]]
+name = "make-cmd"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a8ca8afbe8af1785e09636acb5a41e08a765f5f0340568716c18a8700ba3c0d3"
+
+[[package]]
+name = "pkg-config"
+version = "0.3.30"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d231b230927b5e4ad203db57bbcbee2802f6bce620b1e4a9024a07d94e2907ec"
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "vcpkg"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"

contrib/libgit-rs/Cargo.toml

@@ -0,0 +1,17 @@
+[package]
+name = "libgit"
+version = "0.1.0"
+edition = "2021"
+build = "build.rs"
+rust-version = "1.63" # TODO: Once we hit 1.84 or newer, we may want to remove Cargo.lock from
+                      # version control. See https://lore.kernel.org/git/Z47jgK-oMjFRSslr@tapette.crustytoothpaste.net/
+
+
+[lib]
+path = "src/lib.rs"
+
+[dependencies]
+libgit-sys = { version = "0.1.0", path = "../libgit-sys" }
+
+[build-dependencies]
+autocfg = "1.4.0"

contrib/libgit-rs/README.md

@@ -0,0 +1,13 @@
+# libgit-rs
+
+Proof-of-concept Git bindings for Rust.
+
+```toml
+[dependencies]
+libgit = "0.1.0"
+```
+
+## Rust version requirements
+
+libgit-rs should support Rust versions at least as old as the version included
+in Debian stable (currently 1.63).

contrib/libgit-rs/build.rs

@@ -0,0 +1,4 @@
+pub fn main() {
+    let ac = autocfg::new();
+    ac.emit_has_path("std::ffi::c_char");
+}

contrib/libgit-rs/src/config.rs

@@ -0,0 +1,106 @@
+use std::ffi::{c_void, CStr, CString};
+use std::path::Path;
+
+#[cfg(has_std__ffi__c_char)]
+use std::ffi::{c_char, c_int};
+
+#[cfg(not(has_std__ffi__c_char))]
+#[allow(non_camel_case_types)]
+type c_char = i8;
+
+#[cfg(not(has_std__ffi__c_char))]
+#[allow(non_camel_case_types)]
+type c_int = i32;
+
+use libgit_sys::*;
+
+/// A ConfigSet is an in-memory cache for config-like files such as `.gitmodules` or `.gitconfig`.
+/// It does not support all config directives; notably, it will not process `include` or
+/// `includeIf` directives (but it will store them so that callers can choose whether and how to
+/// handle them).
+pub struct ConfigSet(*mut libgit_config_set);
+impl ConfigSet {
+    /// Allocate a new ConfigSet
+    pub fn new() -> Self {
+        unsafe { ConfigSet(libgit_configset_alloc()) }
+    }
+
+    /// Load the given files into the ConfigSet; conflicting directives in later files will
+    /// override those given in earlier files.
+    pub fn add_files(&mut self, files: &[&Path]) {
+        for file in files {
+            let pstr = file.to_str().expect("Invalid UTF-8");
+            let rs = CString::new(pstr).expect("Couldn't convert to CString");
+            unsafe {
+                libgit_configset_add_file(self.0, rs.as_ptr());
+            }
+        }
+    }
+
+    /// Load the value for the given key and attempt to parse it as an i32. Dies with a fatal error
+    /// if the value cannot be parsed. Returns None if the key is not present.
+    pub fn get_int(&mut self, key: &str) -> Option<i32> {
+        let key = CString::new(key).expect("Couldn't convert to CString");
+        let mut val: c_int = 0;
+        unsafe {
+            if libgit_configset_get_int(self.0, key.as_ptr(), &mut val as *mut c_int) != 0 {
+                return None;
+            }
+        }
+
+        Some(val.into())
+    }
+
+    /// Clones the value for the given key. Dies with a fatal error if the value cannot be
+    /// converted to a String. Returns None if the key is not present.
+    pub fn get_string(&mut self, key: &str) -> Option<String> {
+        let key = CString::new(key).expect("Couldn't convert key to CString");
+        let mut val: *mut c_char = std::ptr::null_mut();
+        unsafe {
+            if libgit_configset_get_string(self.0, key.as_ptr(), &mut val as *mut *mut c_char) != 0
+            {
+                return None;
+            }
+            let borrowed_str = CStr::from_ptr(val);
+            let owned_str =
+                String::from(borrowed_str.to_str().expect("Couldn't convert val to str"));
+            free(val as *mut c_void); // Free the xstrdup()ed pointer from the C side
+            Some(owned_str)
+        }
+    }
+}
+
+impl Default for ConfigSet {
+    fn default() -> Self {
+        Self::new()
+    }
+}
+
+impl Drop for ConfigSet {
+    fn drop(&mut self) {
+        unsafe {
+            libgit_configset_free(self.0);
+        }
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn load_configs_via_configset() {
+        let mut cs = ConfigSet::new();
+        cs.add_files(&[
+            Path::new("testdata/config1"),
+            Path::new("testdata/config2"),
+            Path::new("testdata/config3"),
+        ]);
+        // ConfigSet retrieves correct value
+        assert_eq!(cs.get_int("trace2.eventTarget"), Some(1));
+        // ConfigSet respects last config value set
+        assert_eq!(cs.get_int("trace2.eventNesting"), Some(3));
+        // ConfigSet returns None for missing key
+        assert_eq!(cs.get_string("foo.bar"), None);
+    }
+}

contrib/libgit-rs/src/lib.rs

@@ -0,0 +1 @@
+pub mod config;

contrib/libgit-rs/testdata/config1

@@ -0,0 +1,2 @@
+[trace2]
+	eventNesting = 1

contrib/libgit-rs/testdata/config2

@@ -0,0 +1,2 @@
+[trace2]
+	eventTarget = 1

contrib/libgit-rs/testdata/config3

@@ -0,0 +1,2 @@
+[trace2]
+	eventNesting = 3

contrib/libgit-sys/Cargo.lock

@@ -0,0 +1,69 @@
+# This file is automatically @generated by Cargo.
+# It is not intended for manual editing.
+version = 3
+
+[[package]]
+name = "autocfg"
+version = "1.4.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "ace50bade8e6234aa140d9a2f552bbee1db4d353f69b8217bc503490fc1a9f26"
+
+[[package]]
+name = "cc"
+version = "1.1.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "57b6a275aa2903740dc87da01c62040406b8812552e97129a63ea8850a17c6e6"
+dependencies = [
+ "shlex",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.158"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d8adc4bb1803a324070e64a98ae98f38934d91957a99cfb3a43dcbc01bc56439"
+
+[[package]]
+name = "libgit-sys"
+version = "0.1.0"
+dependencies = [
+ "autocfg",
+ "libz-sys",
+ "make-cmd",
+]
+
+[[package]]
+name = "libz-sys"
+version = "1.1.20"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d2d16453e800a8cf6dd2fc3eb4bc99b786a9b90c663b8559a5b1a041bf89e472"
+dependencies = [
+ "cc",
+ "libc",
+ "pkg-config",
+ "vcpkg",
+]
+
+[[package]]
+name = "make-cmd"
+version = "0.1.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "a8ca8afbe8af1785e09636acb5a41e08a765f5f0340568716c18a8700ba3c0d3"
+
+[[package]]
+name = "pkg-config"
+version = "0.3.30"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d231b230927b5e4ad203db57bbcbee2802f6bce620b1e4a9024a07d94e2907ec"
+
+[[package]]
+name = "shlex"
+version = "1.3.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "0fda2ff0d084019ba4d7c6f371c95d8fd75ce3524c3cb8fb653a3023f6323e64"
+
+[[package]]
+name = "vcpkg"
+version = "0.2.15"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "accd4ea62f7bb7a82fe23066fb0957d48ef677f6eeb8215f372f52e48bb32426"

contrib/libgit-sys/Cargo.toml

@@ -0,0 +1,19 @@
+[package]
+name = "libgit-sys"
+version = "0.1.0"
+edition = "2021"
+build = "build.rs"
+links = "gitpub"
+rust-version = "1.63" # TODO: Once we hit 1.84 or newer, we may want to remove Cargo.lock from
+                      # version control. See https://lore.kernel.org/git/Z47jgK-oMjFRSslr@tapette.crustytoothpaste.net/
+description = "Native bindings to a portion of libgit"
+
+[lib]
+path = "src/lib.rs"
+
+[dependencies]
+libz-sys = "1.1.19"
+
+[build-dependencies]
+autocfg = "1.4.0"
+make-cmd = "0.1.0"

contrib/libgit-sys/README.md

@@ -0,0 +1,4 @@
+# libgit-sys
+
+A small proof-of-concept crate showing how to provide a Rust FFI to Git
+internals.

contrib/libgit-sys/build.rs

@@ -0,0 +1,35 @@
+use std::env;
+use std::path::PathBuf;
+
+pub fn main() -> std::io::Result<()> {
+    let ac = autocfg::new();
+    ac.emit_has_path("std::ffi::c_char");
+
+    let crate_root = PathBuf::from(env::var_os("CARGO_MANIFEST_DIR").unwrap());
+    let git_root = crate_root.join("../..");
+    let dst = PathBuf::from(env::var_os("OUT_DIR").unwrap());
+
+    let make_output = make_cmd::gnu_make()
+        .env("DEVELOPER", "1")
+        .env_remove("PROFILE")
+        .current_dir(git_root.clone())
+        .args([
+            "INCLUDE_LIBGIT_RS=YesPlease",
+            "contrib/libgit-sys/libgitpub.a",
+        ])
+        .output()
+        .expect("Make failed to run");
+    if !make_output.status.success() {
+        panic!(
+            "Make failed:\n  stdout = {}\n  stderr = {}\n",
+            String::from_utf8(make_output.stdout).unwrap(),
+            String::from_utf8(make_output.stderr).unwrap()
+        );
+    }
+    std::fs::copy(crate_root.join("libgitpub.a"), dst.join("libgitpub.a"))?;
+    println!("cargo:rustc-link-search=native={}", dst.display());
+    println!("cargo:rustc-link-lib=gitpub");
+    println!("cargo:rerun-if-changed={}", git_root.display());
+
+    Ok(())
+}

contrib/libgit-sys/public_symbol_export.c

@@ -0,0 +1,59 @@
+/*
+ * Shim to publicly export Git symbols. These must be renamed so that the
+ * original symbols can be hidden. Renaming these with a "libgit_" prefix also
+ * avoids conflicts with other libraries such as libgit2.
+ */
+
+#include "git-compat-util.h"
+#include "config.h"
+#include "contrib/libgit-sys/public_symbol_export.h"
+#include "version.h"
+
+#pragma GCC visibility push(default)
+
+struct libgit_config_set {
+	struct config_set cs;
+};
+
+struct libgit_config_set *libgit_configset_alloc(void)
+{
+	struct libgit_config_set *cs =
+			xmalloc(sizeof(struct libgit_config_set));
+	git_configset_init(&cs->cs);
+	return cs;
+}
+
+void libgit_configset_free(struct libgit_config_set *cs)
+{
+	git_configset_clear(&cs->cs);
+	free(cs);
+}
+
+int libgit_configset_add_file(struct libgit_config_set *cs, const char *filename)
+{
+	return git_configset_add_file(&cs->cs, filename);
+}
+
+int libgit_configset_get_int(struct libgit_config_set *cs, const char *key,
+			     int *dest)
+{
+	return git_configset_get_int(&cs->cs, key, dest);
+}
+
+int libgit_configset_get_string(struct libgit_config_set *cs, const char *key,
+				char **dest)
+{
+	return git_configset_get_string(&cs->cs, key, dest);
+}
+
+const char *libgit_user_agent(void)
+{
+	return git_user_agent();
+}
+
+const char *libgit_user_agent_sanitized(void)
+{
+	return git_user_agent_sanitized();
+}
+
+#pragma GCC visibility pop

contrib/libgit-sys/public_symbol_export.h

@@ -0,0 +1,18 @@
+#ifndef PUBLIC_SYMBOL_EXPORT_H
+#define PUBLIC_SYMBOL_EXPORT_H
+
+struct libgit_config_set *libgit_configset_alloc(void);
+
+void libgit_configset_free(struct libgit_config_set *cs);
+
+int libgit_configset_add_file(struct libgit_config_set *cs, const char *filename);
+
+int libgit_configset_get_int(struct libgit_config_set *cs, const char *key, int *dest);
+
+int libgit_configset_get_string(struct libgit_config_set *cs, const char *key, char **dest);
+
+const char *libgit_user_agent(void);
+
+const char *libgit_user_agent_sanitized(void);
+
+#endif /* PUBLIC_SYMBOL_EXPORT_H */

contrib/libgit-sys/src/lib.rs

@@ -0,0 +1,79 @@
+use std::ffi::c_void;
+
+#[cfg(has_std__ffi__c_char)]
+use std::ffi::{c_char, c_int};
+
+#[cfg(not(has_std__ffi__c_char))]
+#[allow(non_camel_case_types)]
+pub type c_char = i8;
+
+#[cfg(not(has_std__ffi__c_char))]
+#[allow(non_camel_case_types)]
+pub type c_int = i32;
+
+extern crate libz_sys;
+
+#[allow(non_camel_case_types)]
+#[repr(C)]
+pub struct libgit_config_set {
+    _data: [u8; 0],
+    _marker: core::marker::PhantomData<(*mut u8, core::marker::PhantomPinned)>,
+}
+
+extern "C" {
+    pub fn free(ptr: *mut c_void);
+
+    pub fn libgit_user_agent() -> *const c_char;
+    pub fn libgit_user_agent_sanitized() -> *const c_char;
+
+    pub fn libgit_configset_alloc() -> *mut libgit_config_set;
+    pub fn libgit_configset_free(cs: *mut libgit_config_set);
+
+    pub fn libgit_configset_add_file(cs: *mut libgit_config_set, filename: *const c_char) -> c_int;
+
+    pub fn libgit_configset_get_int(
+        cs: *mut libgit_config_set,
+        key: *const c_char,
+        int: *mut c_int,
+    ) -> c_int;
+
+    pub fn libgit_configset_get_string(
+        cs: *mut libgit_config_set,
+        key: *const c_char,
+        dest: *mut *mut c_char,
+    ) -> c_int;
+
+}
+
+#[cfg(test)]
+mod tests {
+    use std::ffi::CStr;
+
+    use super::*;
+
+    #[test]
+    fn user_agent_starts_with_git() {
+        let c_str = unsafe { CStr::from_ptr(libgit_user_agent()) };
+        let agent = c_str
+            .to_str()
+            .expect("User agent contains invalid UTF-8 data");
+        assert!(
+            agent.starts_with("git/"),
+            r#"Expected user agent to start with "git/", got: {}"#,
+            agent
+        );
+    }
+
+    #[test]
+    fn sanitized_user_agent_starts_with_git() {
+        let c_str = unsafe { CStr::from_ptr(libgit_user_agent_sanitized()) };
+        let agent = c_str
+            .to_str()
+            .expect("Sanitized user agent contains invalid UTF-8 data");
+        assert!(
+            agent.starts_with("git/"),
+            r#"Expected user agent to start with "git/", got: {}"#,
+            agent
+        );
+    }
+}