parse header

Cargo.lock

@@ -5,3 +5,100 @@ version = 3
 [[package]]
 name = "elven-parser"
 version = "0.1.0"
+dependencies = [
+ "memmap2",
+ "nom",
+ "thiserror",
+]
+
+[[package]]
+name = "libc"
+version = "0.2.139"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "201de327520df007757c1f0adce6e827fe8562fbc28bfd9c15571c66ca1f5f79"
+
+[[package]]
+name = "memchr"
+version = "2.5.0"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "2dffe52ecf27772e601905b7522cb4ef790d2cc203488bbd0e2fe85fcb74566d"
+
+[[package]]
+name = "memmap2"
+version = "0.5.8"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "4b182332558b18d807c4ce1ca8ca983b34c3ee32765e47b3f0f69b90355cc1dc"
+dependencies = [
+ "libc",
+]
+
+[[package]]
+name = "minimal-lexical"
+version = "0.2.1"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "68354c5c6bd36d73ff3feceb05efa59b6acb7626617f4962be322a825e61f79a"
+
+[[package]]
+name = "nom"
+version = "7.1.3"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "d273983c5a657a70a3e8f2a01329822f3b8c8172b73826411a55751e404a0a4a"
+dependencies = [
+ "memchr",
+ "minimal-lexical",
+]
+
+[[package]]
+name = "proc-macro2"
+version = "1.0.51"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "5d727cae5b39d21da60fa540906919ad737832fe0b1c165da3a34d6548c849d6"
+dependencies = [
+ "unicode-ident",
+]
+
+[[package]]
+name = "quote"
+version = "1.0.23"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "8856d8364d252a14d474036ea1358d63c9e6965c8e5c1885c18f73d70bff9c7b"
+dependencies = [
+ "proc-macro2",
+]
+
+[[package]]
+name = "syn"
+version = "1.0.107"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1f4064b5b16e03ae50984a5a8ed5d4f8803e6bc1fd170a3cda91a1be4b18e3f5"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "unicode-ident",
+]
+
+[[package]]
+name = "thiserror"
+version = "1.0.38"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "6a9cd18aa97d5c45c6603caea1da6628790b37f7a34b6ca89522331c5180fed0"
+dependencies = [
+ "thiserror-impl",
+]
+
+[[package]]
+name = "thiserror-impl"
+version = "1.0.38"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "1fb327af4685e4d03fa8cbcf1716380da910eeb2bb8be417e7f9fd3fb164f36f"
+dependencies = [
+ "proc-macro2",
+ "quote",
+ "syn",
+]
+
+[[package]]
+name = "unicode-ident"
+version = "1.0.6"
+source = "registry+https://github.com/rust-lang/crates.io-index"
+checksum = "84a22b9f218b40614adcb3f4ff08b703773ad44fa9423e4e0d346d5db86e4ebc"

elven-parser/Cargo.toml

@@ -6,3 +6,6 @@ edition = "2021"
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 
 [dependencies]
+memmap2 = "0.5.8"
+nom = "7.1.3"
+thiserror = "1.0.38"

elven-parser/src/lib.rs

@@ -1 +1 @@
-pub fn yeet() {}
+pub mod raw;

elven-parser/src/raw.rs

@@ -0,0 +1,114 @@
+//! Structures and parsers for ELF64. ELF32 can knock itself out.
+
+use std::mem;
+
+#[derive(Debug)]
+pub struct Addr(u64);
+#[derive(Debug)]
+pub struct Offset(u64);
+#[derive(Debug)]
+pub struct Section(u16);
+#[derive(Debug)]
+pub struct Versym(u16);
+
+#[derive(Debug, Clone, thiserror::Error)]
+pub enum ElfParseError {
+    #[error("The file is too small. Expected at least {0} bytes, found {1} bytes")]
+    FileTooSmall(usize, usize),
+    #[error("The input is not aligned in memory. Expected align {0}, found align {1}")]
+    UnalignedInput(usize, usize),
+    #[error("The magic of the file did not match. Maybe it's not an ELF file?. Found {0:x?}")]
+    WrongMagic([u8; 4]),
+}
+
+/// A raw ELF. Does not come with cute ears for now.
+#[derive(Debug)]
+pub struct Elf<'a> {
+    pub header: &'a ElfHeader,
+}
+
+#[derive(Debug)]
+#[repr(C)]
+pub struct ElfHeader {
+    pub ident: [u8; 16],
+    pub r#type: u16,
+    pub machine: u16,
+    pub version: u32,
+    pub entry: Addr,
+    pub phoff: Offset,
+    pub shoff: Offset,
+    pub flags: u32,
+    pub ehsize: u16,
+    pub phentsize: u16,
+    pub phnum: u16,
+    pub shentsize: u16,
+    pub shnum: u16,
+    pub shstrndex: u16,
+}
+
+impl<'a> Elf<'a> {
+    pub fn parse(input: &'a [u8]) -> Result<Self, ElfParseError> {
+        const HEADER_SIZE: usize = mem::size_of::<ElfHeader>();
+        const HEADER_ALIGN: usize = mem::align_of::<ElfHeader>();
+
+        if input.len() < HEADER_SIZE {
+            return Err(ElfParseError::FileTooSmall(HEADER_SIZE, input.len()));
+        }
+
+        let input_ptr = input as *const [u8];
+
+        let input_addr = input_ptr as *const u8 as usize;
+        let align = input_addr.trailing_zeros() as usize;
+
+        if align < HEADER_ALIGN {
+            return Err(ElfParseError::UnalignedInput(HEADER_ALIGN, align));
+        }
+
+        let header = input_ptr as *const ElfHeader;
+        // SAFETY: We checked that the size is enough. We checked that the alignment matches.
+        // ElfHeader is POD.
+        let header = unsafe { &*header };
+
+        let magic = header.ident[..4].try_into().unwrap();
+
+        if magic != [0x7f, b'E', b'L', b'F'] {
+            return Err(ElfParseError::WrongMagic(magic));
+        }
+
+        Ok(Elf { header })
+    }
+}
+
+#[cfg(test)]
+mod tests {
+    use std::{fs, path::Path};
+
+    use memmap2::Mmap;
+
+    use super::*;
+
+    fn load_test_file(file_name: impl AsRef<Path>) -> Mmap {
+        let name = file_name.as_ref();
+        let this_file_path = Path::new(env!("CARGO_MANIFEST_DIR")).join(file!());
+        let double_this_crate = this_file_path.parent().unwrap().parent().unwrap();
+        let workspace_root = double_this_crate.parent().unwrap().parent().unwrap();
+
+        let file_path = workspace_root.join("test_data").join("out").join(name);
+
+        let file = fs::File::open(&file_path).expect(&format!(
+            "Failed to open test file {} at path {}. Consider running `test_data/create_test_data.sh` to create the test data files",
+            name.display(),
+            file_path.display()
+        ));
+
+        unsafe { Mmap::map(&file).unwrap() }
+    }
+
+    #[test]
+    fn rust_hello_world_bin() {
+        let file = load_test_file("hello_world");
+        let elf = Elf::parse(&file).unwrap();
+        dbg!(elf);
+        panic!()
+    }
+}

test_data/.gitignore

@@ -0,0 +1 @@
+/out

test_data/create_test_data.sh

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+
+SCRIPT_DIR=$( cd -- "$( dirname -- "${BASH_SOURCE[0]}" )" &> /dev/null && pwd )
+
+for rust_file in $SCRIPT_DIR/*.rs; do
+    # Use -Cprefer-dynamic to keep the binary small
+    rustc --edition 2021 "$rust_file" -Cprefer-dynamic -Copt-level=3 --out-dir="$SCRIPT_DIR/out"
+done

test_data/hello_world.rs

@@ -0,0 +1,3 @@
+fn main() {
+    println!("Hello, World!");
+}