Introduce Pheon GDSII parsing and layout review tools

Implement native GDSII reading and writing with Arrow interchange, hierarchy
scans and selective cell loading. Validate numeric packing and array pitches,
and preserve normalized REAL8 encodings exactly within the supported range.

Add standalone dump, structural diff, hierarchy, layer-name annotation and Git
diff commands. Provide scoped text and JSON reports, deterministic comparison,
and record-preserving metadata edits.

Package the shared library and optional Python Arrow readers as pheon using
CFFI ABI mode and Python-independent platform wheels. Include locked source
builds, native API checks, cross-platform artifact workflows, documentation
and regression coverage. Require Rust 1.88 or newer and Python 3.11 or newer.

Validation: 87 native tests, 14 binding tests on Python 3.11/3.13/3.14,
and 71 installed companion integration tests pass. Full, scanned and selected
Arrow layouts match the previous schemas.
This commit is contained in:
Jan Petykiewicz 2026-11-16 16:21:21 -08:00
commit b3346b40a4

157
tests/ffi_errors.rs Normal file
View file

@ -0,0 +1,157 @@
mod common;
use arrow_array::ffi::{FFI_ArrowArray, FFI_ArrowSchema};
use pheon::{last_error_message, read_path, read_cells_bytes, scan_bytes, records};
use std::{ffi::{CStr, CString}, fs, path::PathBuf, ptr};
struct TestFile(PathBuf);
impl TestFile {
fn new(name: &str, contents: &[u8]) -> Self {
let path = std::env::temp_dir().join(format!("pheon-{name}-{}.gds", std::process::id()));
fs::write(&path, contents).unwrap();
Self(path)
}
fn cpath(&self) -> CString {
CString::new(self.0.to_str().unwrap()).unwrap()
}
}
impl Drop for TestFile {
fn drop(&mut self) {
let _ = fs::remove_file(&self.0);
}
}
fn error_message() -> String {
let message = last_error_message();
assert!(!message.is_null());
unsafe { CStr::from_ptr(message) }.to_str().unwrap().to_owned()
}
#[test]
fn path_errors_preserve_outputs_and_convert_parser_panics() {
let mut array = FFI_ArrowArray::empty();
let mut schema = FFI_ArrowSchema::empty();
assert_eq!(unsafe { read_path(ptr::null(), &mut array, &mut schema) }, -1);
assert!(error_message().contains("path pointer was null"));
assert!(array.is_released());
// A mismatched timestamp size currently makes Record::read panic.
let mut bytes = Vec::new();
common::record(&mut bytes, records::RTAG_HEADER, &600_i16.to_be_bytes());
common::record(&mut bytes, records::RTAG_BGNLIB, &[0; 12]);
let file = TestFile::new("invalid-timestamps", &bytes);
assert_eq!(unsafe { read_path(file.cpath().as_ptr(), &mut array, &mut schema) }, -1);
assert!(error_message().contains("Expected record size"));
assert!(array.is_released());
let mut bytes = common::library_header();
common::record(&mut bytes, records::RTAG_ENDLIB, &[]);
let file = TestFile::new("valid-empty", &bytes);
assert_eq!(unsafe { read_path(file.cpath().as_ptr(), &mut array, &mut schema) }, 0);
assert!(!array.is_released());
assert!(last_error_message().is_null());
}
#[test]
fn other_threads_do_not_clear_or_free_error_messages() {
let mut array = FFI_ArrowArray::empty();
let mut schema = FFI_ArrowSchema::empty();
assert_eq!(unsafe { read_path(ptr::null(), &mut array, &mut schema) }, -1);
let pointer = last_error_message();
let message = error_message();
std::thread::spawn(|| {
assert!(last_error_message().is_null());
let mut bytes = common::library_header();
common::record(&mut bytes, records::RTAG_ENDLIB, &[]);
let file = TestFile::new("thread-empty", &bytes);
let mut array = FFI_ArrowArray::empty();
let mut schema = FFI_ArrowSchema::empty();
assert_eq!(unsafe { read_path(ptr::null(), &mut array, &mut schema) }, -1);
assert_eq!(unsafe { read_path(file.cpath().as_ptr(), &mut array, &mut schema) }, 0);
assert!(last_error_message().is_null());
}).join().unwrap();
assert_eq!(last_error_message(), pointer);
assert_eq!(unsafe { CStr::from_ptr(pointer) }.to_str().unwrap(), message);
}
#[test]
fn null_arrow_outputs_return_an_error() {
assert_eq!(unsafe { read_path(ptr::null(), ptr::null_mut(), ptr::null_mut()) }, -1);
assert!(error_message().contains("Arrow output pointer was null"));
}
#[test]
fn large_malformed_inputs_report_offsets_without_dumping_contents() {
let mut bytes = vec![0; 1024 * 1024 + 4];
bytes[..4].copy_from_slice(&[0, 4, 0xff, 0xff]);
let mut array = FFI_ArrowArray::empty();
let mut schema = FFI_ArrowSchema::empty();
let file = TestFile::new("large-malformed", &bytes);
assert_eq!(
unsafe { scan_bytes(bytes.as_ptr(), bytes.len(), &mut array, &mut schema) },
-1
);
let scan_message = error_message();
assert_eq!(
unsafe { read_path(file.cpath().as_ptr(), &mut array, &mut schema) },
-1
);
let read_message = error_message();
assert_eq!(
unsafe {
read_cells_bytes(
bytes.as_ptr(),
bytes.len(),
ptr::null(),
0,
&mut array,
&mut schema,
)
},
-1
);
let selected_message = error_message();
for message in [scan_message, read_message, selected_message] {
assert!(message.contains("at byte 4"), "{message}");
assert!(message.contains("Unexpected record"), "{message}");
assert!(message.len() < 256);
}
assert!(array.is_released());
}
#[test]
fn selected_cell_errors_use_file_offsets_for_bounded_ranges() {
let mut bytes = common::library_header();
let start = bytes.len() as u64;
common::record(&mut bytes, records::RTAG_BGNSTR, &[0; 24]);
common::record(&mut bytes, records::RTAG_STRNAME, b"top\0");
common::record(&mut bytes, records::RTAG_ENDSTR, &[]);
let cell_end = bytes.len();
common::record(&mut bytes, records::RTAG_ENDLIB, &[]);
let range_end = bytes.len() as u64;
bytes.resize(bytes.len() + 1024, 0);
let ranges = [start, range_end];
let mut array = FFI_ArrowArray::empty();
let mut schema = FFI_ArrowSchema::empty();
assert_eq!(
unsafe {
read_cells_bytes(
bytes.as_ptr(),
bytes.len(),
ranges.as_ptr(),
1,
&mut array,
&mut schema,
)
},
-1
);
assert!(error_message().contains(&format!(
"at byte {cell_end}: Cell byte range extends past ENDSTR"
)));
}