libgit-sys: introduce Rust wrapper for libgit.a

Introduce libgit-sys, a Rust wrapper crate that allows Rust code to call
functions in libgit.a. This initial patch defines build rules and an
interface that exposes user agent string getter functions as a proof of
concept. This library can be tested with `cargo test`. In later commits,
a higher-level library containing a more Rust-friendly interface will be
added at `contrib/libgit-rs`.

Symbols in libgit can collide with symbols from other libraries such as
libgit2. We avoid this by first exposing library symbols in
public_symbol_export.[ch]. These symbols are prepended with "libgit_" to
avoid collisions and set to visible using a visibility pragma. In
build.rs, Rust builds contrib/libgit-rs/libgit-sys/libgitpub.a, which also
contains libgit.a and other dependent libraries, with
-fvisibility=hidden to hide all symbols within those libraries that
haven't been exposed with a visibility pragma.

Co-authored-by: Kyle Lippincott <[email protected]>
Co-authored-by: Calvin Wan <[email protected]>
Signed-off-by: Calvin Wan <[email protected]>
Signed-off-by: Kyle Lippincott <[email protected]>
Signed-off-by: Josh Steadmon <[email protected]>
Signed-off-by: Taylor Blau <[email protected]>

Author: 3 people

.gitignore

@@ -248,3 +248,4 @@ Release/
 /git.VC.db
 *.dSYM
 /contrib/buildsystems/out
+/contrib/libgit-rs/libgit-sys/target

Makefile

@@ -653,6 +653,8 @@ CURL_CONFIG = curl-config
 GCOV = gcov
 STRIP = strip
 SPATCH = spatch
+LD = ld
+OBJCOPY = objcopy
 
 export TCL_PATH TCLTK_PATH
 
@@ -2713,6 +2715,7 @@ OBJECTS += $(XDIFF_OBJS)
 OBJECTS += $(FUZZ_OBJS)
 OBJECTS += $(REFTABLE_OBJS) $(REFTABLE_TEST_OBJS)
 OBJECTS += $(UNIT_TEST_OBJS)
+OBJECTS += contrib/libgit-rs/libgit-sys/public_symbol_export.o
 
 ifndef NO_CURL
 	OBJECTS += http.o http-walker.o remote-curl.o
@@ -3720,6 +3723,10 @@ clean: profile-clean coverage-clean cocciclean
 	$(RM) $(htmldocs).tar.gz $(manpages).tar.gz
 	$(MAKE) -C Documentation/ clean
 	$(RM) Documentation/GIT-EXCLUDED-PROGRAMS
+	$(RM) -r contrib/libgit-rs/libgit-sys/target
+	$(RM) -r contrib/libgit-rs/libgit-sys/partial_symbol_export.o
+	$(RM) -r contrib/libgit-rs/libgit-sys/hidden_symbol_export.o
+	$(RM) -r contrib/libgit-rs/libgit-sys/libgitpub.a
 ifndef NO_PERL
 	$(RM) -r perl/build/
 endif
@@ -3865,3 +3872,12 @@ $(UNIT_TEST_PROGS): $(UNIT_TEST_BIN)/%$X: $(UNIT_TEST_DIR)/%.o \
 build-unit-tests: $(UNIT_TEST_PROGS)
 unit-tests: $(UNIT_TEST_PROGS) t/helper/test-tool$X
 	$(MAKE) -C t/ unit-tests
+
+contrib/libgit-rs/libgit-sys/partial_symbol_export.o: contrib/libgit-rs/libgit-sys/public_symbol_export.o libgit.a reftable/libreftable.a xdiff/lib.a
+	$(LD) -r $^ -o $@
+
+contrib/libgit-rs/libgit-sys/hidden_symbol_export.o: contrib/libgit-rs/libgit-sys/partial_symbol_export.o
+	$(OBJCOPY) --localize-hidden $^ $@
+
+contrib/libgit-rs/libgit-sys/libgitpub.a: contrib/libgit-rs/libgit-sys/hidden_symbol_export.o
+	$(AR) $(ARFLAGS) $@ $^

contrib/libgit-rs/libgit-sys/Cargo.lock

@@ -0,0 +1,17 @@
+[package]
+name = "libgit-sys"
+version = "0.1.0"
+edition = "2021"
+build = "build.rs"
+links = "gitpub"
+rust-version = "1.63"
+
+[lib]
+path = "src/lib.rs"
+
+[dependencies]
+libz-sys = "1.1.19"
+
+[build-dependencies]
+autocfg = "1.4.0"
+make-cmd = "0.1.0"

contrib/libgit-rs/libgit-sys/Cargo.toml

@@ -0,0 +1,15 @@
+# cgit-info
+
+A small hacky proof-of-concept showing how to provide a Rust FFI for the Git
+library.
+
+## Building
+
+`cargo build` automatically builds and picks up on changes made to both
+the Rust wrapper and git.git code so there is no need to run `make`
+beforehand.
+
+## Running
+
+Assuming you don't make any changes to the Git source, you can just work from
+`contrib/cgit-rs` and use `cargo build` or `cargo run` as usual.

contrib/libgit-rs/libgit-sys/README.md

@@ -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([
+            "CFLAGS=-fvisibility=hidden",
+            "contrib/libgit-rs/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-rs/libgit-sys/build.rs

@@ -0,0 +1,21 @@
+// 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 "contrib/libgit-rs/libgit-sys/public_symbol_export.h"
+#include "version.h"
+
+#pragma GCC visibility push(default)
+
+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-rs/libgit-sys/public_symbol_export.c

@@ -0,0 +1,8 @@
+#ifndef PUBLIC_SYMBOL_EXPORT_H
+#define PUBLIC_SYMBOL_EXPORT_H
+
+const char *libgit_user_agent(void);
+
+const char *libgit_user_agent_sanitized(void);
+
+#endif /* PUBLIC_SYMBOL_EXPORT_H */

contrib/libgit-rs/libgit-sys/public_symbol_export.h

@@ -0,0 +1,46 @@
+#[cfg(has_std__ffi__c_char)]
+use std::ffi::c_char;
+
+#[cfg(not(has_std__ffi__c_char))]
+#[allow(non_camel_case_types)]
+pub type c_char = i8;
+
+extern crate libz_sys;
+
+extern "C" {
+    pub fn libgit_user_agent() -> *const c_char;
+    pub fn libgit_user_agent_sanitized() -> *const c_char;
+}
+
+#[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
+        );
+    }
+}