* Remove dependency on utf8proc
This removes the only external dependency on utf8proc for UTF-8 decoding. It does so by implementing its own UTF-8 decoder. This decoder is both faster and has a simpler API.
* .gitmodules: remove utf8proc submodule
* docs/section-2-using-parsers.md: remove requirement for utf8proc submodule
* docs/section-6-contributing.md: likewise
* lib/Cargo.toml: remove utf8proc subdirectory package include
* lib/README.md: remove utf8proc subdirectory description
* lib/binding_rust/build.rs: remove utf8proc compiler include directory
* lib/src/lexer.c: remove utf8proc dependencies and types
* lib/src/lib.c: remove utf8proc dependency
* lib/src/unicode.h: define types for Unicode decoders
* lib/src/utf16.{c,h}: implement more readable UTF-16 decoder
* lib/src/utf8.{c,h}: implement fast UTF-8 decoder
* lib/utf8proc: remove utf8proc submodule directory
* script/build-lib: remove utf8proc compiler include directory
* script/build-wasm: likewise
* Optimize ts_lexer__get_lookahead.
Try to favor non-failure code path and assign lookahead values directly to lexer
* lib/src/lexer.c: optimize for non-failure code path
* Fix some compiler errors
* lib/src/lexer.c: cast from signed to unsigned for decode_next result
* lib/src/utf16.c: fix non-constant initializers for older compilers
* Remove some missed remnants of utf8proc
* docs/section-2-using-parsers.md: only two include paths necessary now
* lib/src/lib.c: no need to define UTF8PROC_STATIC
* Use ICU's utf8 and utf16 decoding routines
* Remove unnecessary casts when calling icu macros
* Check buffer length before attempting to decode a unicode character
* Use new unicode function when parsing Queries
Co-Authored-By: Matthew Krupcale <mkrupcale@matthewkrupcale.com>
* Mark libicu files as vendored for GitHub's stats
58 lines
1.7 KiB
Rust
58 lines
1.7 KiB
Rust
extern crate cc;
|
|
|
|
use std::{env, fs};
|
|
use std::path::{Path, PathBuf};
|
|
|
|
fn main() {
|
|
println!("cargo:rerun-if-env-changed=TREE_SITTER_STATIC_ANALYSIS");
|
|
if env::var("TREE_SITTER_STATIC_ANALYSIS").is_ok() {
|
|
if let (Some(clang_path), Some(scan_build_path)) = (which("clang"), which("scan-build")) {
|
|
let clang_path = clang_path.to_str().unwrap();
|
|
let scan_build_path = scan_build_path.to_str().unwrap();
|
|
env::set_var(
|
|
"CC",
|
|
&format!(
|
|
"{} -analyze-headers --use-analyzer={} cc",
|
|
scan_build_path, clang_path
|
|
),
|
|
);
|
|
}
|
|
}
|
|
|
|
let mut config = cc::Build::new();
|
|
|
|
println!("cargo:rerun-if-env-changed=TREE_SITTER_TEST");
|
|
if env::var("TREE_SITTER_TEST").is_ok() {
|
|
config.define("TREE_SITTER_TEST", "");
|
|
}
|
|
|
|
let src_path = Path::new("src");
|
|
|
|
for entry in fs::read_dir(&src_path).unwrap() {
|
|
let entry = entry.unwrap();
|
|
let path = src_path.join(entry.file_name());
|
|
println!("cargo:rerun-if-changed={}", path.to_str().unwrap());
|
|
}
|
|
|
|
config
|
|
.flag_if_supported("-std=c99")
|
|
.flag_if_supported("-Wno-unused-parameter")
|
|
.include(src_path)
|
|
.include("include")
|
|
.file(src_path.join("lib.c"))
|
|
.file(Path::new("binding_rust").join("helper.c"))
|
|
.compile("tree-sitter");
|
|
}
|
|
|
|
fn which(exe_name: impl AsRef<Path>) -> Option<PathBuf> {
|
|
env::var_os("PATH").and_then(|paths| {
|
|
env::split_paths(&paths).find_map(|dir| {
|
|
let full_path = dir.join(&exe_name);
|
|
if full_path.is_file() {
|
|
Some(full_path)
|
|
} else {
|
|
None
|
|
}
|
|
})
|
|
})
|
|
}
|