1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
//! Interface for reading object files.

use alloc::borrow::Cow;
use alloc::vec::Vec;
use core::{fmt, result};

use crate::common::*;

mod read_ref;
pub use read_ref::*;

#[cfg(feature = "std")]
mod read_cache;
#[cfg(feature = "std")]
pub use read_cache::*;

mod util;
pub use util::*;

#[cfg(any(
    feature = "coff",
    feature = "elf",
    feature = "macho",
    feature = "pe",
    feature = "wasm",
    feature = "xcoff"
))]
mod any;
#[cfg(any(
    feature = "coff",
    feature = "elf",
    feature = "macho",
    feature = "pe",
    feature = "wasm",
    feature = "xcoff"
))]
pub use any::*;

#[cfg(feature = "archive")]
pub mod archive;

#[cfg(feature = "coff")]
pub mod coff;

#[cfg(feature = "elf")]
pub mod elf;

#[cfg(feature = "macho")]
pub mod macho;

#[cfg(feature = "pe")]
pub mod pe;

#[cfg(feature = "wasm")]
pub mod wasm;

#[cfg(feature = "xcoff")]
pub mod xcoff;

mod traits;
pub use traits::*;

mod private {
    pub trait Sealed {}
}

/// The error type used within the read module.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct Error(&'static str);

impl fmt::Display for Error {
    #[inline]
    fn fmt(&self, f: &mut fmt::Formatter) -> fmt::Result {
        f.write_str(self.0)
    }
}

#[cfg(feature = "std")]
impl std::error::Error for Error {}

/// The result type used within the read module.
pub type Result<T> = result::Result<T, Error>;

trait ReadError<T> {
    fn read_error(self, error: &'static str) -> Result<T>;
}

impl<T> ReadError<T> for result::Result<T, ()> {
    fn read_error(self, error: &'static str) -> Result<T> {
        self.map_err(|()| Error(error))
    }
}

impl<T> ReadError<T> for result::Result<T, Error> {
    fn read_error(self, error: &'static str) -> Result<T> {
        self.map_err(|_| Error(error))
    }
}

impl<T> ReadError<T> for Option<T> {
    fn read_error(self, error: &'static str) -> Result<T> {
        self.ok_or(Error(error))
    }
}

/// The native executable file for the target platform.
#[cfg(all(
    unix,
    not(target_os = "macos"),
    target_pointer_width = "32",
    feature = "elf"
))]
pub type NativeFile<'data, R = &'data [u8]> = elf::ElfFile32<'data, crate::Endianness, R>;

/// The native executable file for the target platform.
#[cfg(all(
    unix,
    not(target_os = "macos"),
    target_pointer_width = "64",
    feature = "elf"
))]
pub type NativeFile<'data, R = &'data [u8]> = elf::ElfFile64<'data, crate::Endianness, R>;

/// The native executable file for the target platform.
#[cfg(all(target_os = "macos", target_pointer_width = "32", feature = "macho"))]
pub type NativeFile<'data, R = &'data [u8]> = macho::MachOFile32<'data, crate::Endianness, R>;

/// The native executable file for the target platform.
#[cfg(all(target_os = "macos", target_pointer_width = "64", feature = "macho"))]
pub type NativeFile<'data, R = &'data [u8]> = macho::MachOFile64<'data, crate::Endianness, R>;

/// The native executable file for the target platform.
#[cfg(all(target_os = "windows", target_pointer_width = "32", feature = "pe"))]
pub type NativeFile<'data, R = &'data [u8]> = pe::PeFile32<'data, R>;

/// The native executable file for the target platform.
#[cfg(all(target_os = "windows", target_pointer_width = "64", feature = "pe"))]
pub type NativeFile<'data, R = &'data [u8]> = pe::PeFile64<'data, R>;

/// The native executable file for the target platform.
#[cfg(all(feature = "wasm", target_arch = "wasm32", feature = "wasm"))]
pub type NativeFile<'data, R = &'data [u8]> = wasm::WasmFile<'data, R>;

/// A file format kind.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
#[non_exhaustive]
pub enum FileKind {
    /// A Unix archive.
    #[cfg(feature = "archive")]
    Archive,
    /// A COFF object file.
    #[cfg(feature = "coff")]
    Coff,
    /// A dyld cache file containing Mach-O images.
    #[cfg(feature = "macho")]
    DyldCache,
    /// A 32-bit ELF file.
    #[cfg(feature = "elf")]
    Elf32,
    /// A 64-bit ELF file.
    #[cfg(feature = "elf")]
    Elf64,
    /// A 32-bit Mach-O file.
    #[cfg(feature = "macho")]
    MachO32,
    /// A 64-bit Mach-O file.
    #[cfg(feature = "macho")]
    MachO64,
    /// A 32-bit Mach-O fat binary.
    #[cfg(feature = "macho")]
    MachOFat32,
    /// A 64-bit Mach-O fat binary.
    #[cfg(feature = "macho")]
    MachOFat64,
    /// A 32-bit PE file.
    #[cfg(feature = "pe")]
    Pe32,
    /// A 64-bit PE file.
    #[cfg(feature = "pe")]
    Pe64,
    /// A Wasm file.
    #[cfg(feature = "wasm")]
    Wasm,
    /// A 32-bit XCOFF file.
    #[cfg(feature = "xcoff")]
    Xcoff32,
    /// A 64-bit XCOFF file.
    #[cfg(feature = "xcoff")]
    Xcoff64,
}

impl FileKind {
    /// Determine a file kind by parsing the start of the file.
    pub fn parse<'data, R: ReadRef<'data>>(data: R) -> Result<FileKind> {
        Self::parse_at(data, 0)
    }

    /// Determine a file kind by parsing at the given offset.
    pub fn parse_at<'data, R: ReadRef<'data>>(data: R, offset: u64) -> Result<FileKind> {
        let magic = data
            .read_bytes_at(offset, 16)
            .read_error("Could not read file magic")?;
        if magic.len() < 16 {
            return Err(Error("File too short"));
        }

        let kind = match [magic[0], magic[1], magic[2], magic[3], magic[4], magic[5], magic[6], magic[7]] {
            #[cfg(feature = "archive")]
            [b'!', b'<', b'a', b'r', b'c', b'h', b'>', b'\n'] => FileKind::Archive,
            #[cfg(feature = "macho")]
            [b'd', b'y', b'l', b'd', b'_', b'v', b'1', b' '] => FileKind::DyldCache,
            #[cfg(feature = "elf")]
            [0x7f, b'E', b'L', b'F', 1, ..] => FileKind::Elf32,
            #[cfg(feature = "elf")]
            [0x7f, b'E', b'L', b'F', 2, ..] => FileKind::Elf64,
            #[cfg(feature = "macho")]
            [0xfe, 0xed, 0xfa, 0xce, ..]
            | [0xce, 0xfa, 0xed, 0xfe, ..] => FileKind::MachO32,
            #[cfg(feature = "macho")]
            | [0xfe, 0xed, 0xfa, 0xcf, ..]
            | [0xcf, 0xfa, 0xed, 0xfe, ..] => FileKind::MachO64,
            #[cfg(feature = "macho")]
            [0xca, 0xfe, 0xba, 0xbe, ..] => FileKind::MachOFat32,
            #[cfg(feature = "macho")]
            [0xca, 0xfe, 0xba, 0xbf, ..] => FileKind::MachOFat64,
            #[cfg(feature = "wasm")]
            [0x00, b'a', b's', b'm', ..] => FileKind::Wasm,
            #[cfg(feature = "pe")]
            [b'M', b'Z', ..] => {
                match pe::optional_header_magic(data) {
                    Ok(crate::pe::IMAGE_NT_OPTIONAL_HDR32_MAGIC) => {
                        FileKind::Pe32
                    }
                    Ok(crate::pe::IMAGE_NT_OPTIONAL_HDR64_MAGIC) => {
                        FileKind::Pe64
                    }
                    _ => return Err(Error("Unknown MS-DOS file")),
                }
            }
            // TODO: more COFF machines
            #[cfg(feature = "coff")]
            // COFF arm
            [0xc4, 0x01, ..]
            // COFF arm64
            | [0x64, 0xaa, ..]
            // COFF x86
            | [0x4c, 0x01, ..]
            // COFF x86-64
            | [0x64, 0x86, ..] => FileKind::Coff,
            #[cfg(feature = "xcoff")]
            [0x01, 0xDF, ..] => FileKind::Xcoff32,
            #[cfg(feature = "xcoff")]
            [0x01, 0xF7, ..] => FileKind::Xcoff64,
            _ => return Err(Error("Unknown file magic")),
        };
        Ok(kind)
    }
}

/// An object kind.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
#[non_exhaustive]
pub enum ObjectKind {
    /// The object kind is unknown.
    Unknown,
    /// Relocatable object.
    Relocatable,
    /// Executable.
    Executable,
    /// Dynamic shared object.
    Dynamic,
    /// Core.
    Core,
}

/// The index used to identify a section of a file.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
pub struct SectionIndex(pub usize);

/// The index used to identify a symbol of a file.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
pub struct SymbolIndex(pub usize);

/// The section where a symbol is defined.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
#[non_exhaustive]
pub enum SymbolSection {
    /// The section is unknown.
    Unknown,
    /// The section is not applicable for this symbol (such as file symbols).
    None,
    /// The symbol is undefined.
    Undefined,
    /// The symbol has an absolute value.
    Absolute,
    /// The symbol is a zero-initialized symbol that will be combined with duplicate definitions.
    Common,
    /// The symbol is defined in the given section.
    Section(SectionIndex),
}

impl SymbolSection {
    /// Returns the section index for the section where the symbol is defined.
    ///
    /// May return `None` if the symbol is not defined in a section.
    #[inline]
    pub fn index(self) -> Option<SectionIndex> {
        if let SymbolSection::Section(index) = self {
            Some(index)
        } else {
            None
        }
    }
}

/// An entry in a `SymbolMap`.
pub trait SymbolMapEntry {
    /// The symbol address.
    fn address(&self) -> u64;
}

/// A map from addresses to symbols.
#[derive(Debug, Default, Clone)]
pub struct SymbolMap<T: SymbolMapEntry> {
    symbols: Vec<T>,
}

impl<T: SymbolMapEntry> SymbolMap<T> {
    /// Construct a new symbol map.
    ///
    /// This function will sort the symbols by address.
    pub fn new(mut symbols: Vec<T>) -> Self {
        symbols.sort_unstable_by_key(|s| s.address());
        SymbolMap { symbols }
    }

    /// Get the symbol before the given address.
    pub fn get(&self, address: u64) -> Option<&T> {
        let index = match self
            .symbols
            .binary_search_by_key(&address, |symbol| symbol.address())
        {
            Ok(index) => index,
            Err(index) => index.checked_sub(1)?,
        };
        self.symbols.get(index)
    }

    /// Get all symbols in the map.
    #[inline]
    pub fn symbols(&self) -> &[T] {
        &self.symbols
    }
}

/// A `SymbolMap` entry for symbol names.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
pub struct SymbolMapName<'data> {
    address: u64,
    name: &'data str,
}

impl<'data> SymbolMapName<'data> {
    /// Construct a `SymbolMapName`.
    pub fn new(address: u64, name: &'data str) -> Self {
        SymbolMapName { address, name }
    }

    /// The symbol address.
    #[inline]
    pub fn address(&self) -> u64 {
        self.address
    }

    /// The symbol name.
    #[inline]
    pub fn name(&self) -> &'data str {
        self.name
    }
}

impl<'data> SymbolMapEntry for SymbolMapName<'data> {
    #[inline]
    fn address(&self) -> u64 {
        self.address
    }
}

/// A map from addresses to symbol names and object files.
///
/// This is derived from STAB entries in Mach-O files.
#[derive(Debug, Default, Clone)]
pub struct ObjectMap<'data> {
    symbols: SymbolMap<ObjectMapEntry<'data>>,
    objects: Vec<&'data [u8]>,
}

impl<'data> ObjectMap<'data> {
    /// Get the entry containing the given address.
    pub fn get(&self, address: u64) -> Option<&ObjectMapEntry<'data>> {
        self.symbols
            .get(address)
            .filter(|entry| entry.size == 0 || address.wrapping_sub(entry.address) < entry.size)
    }

    /// Get all symbols in the map.
    #[inline]
    pub fn symbols(&self) -> &[ObjectMapEntry<'data>] {
        self.symbols.symbols()
    }

    /// Get all objects in the map.
    #[inline]
    pub fn objects(&self) -> &[&'data [u8]] {
        &self.objects
    }
}

/// A `ObjectMap` entry.
#[derive(Debug, Default, Clone, Copy, PartialEq, Eq, Hash)]
pub struct ObjectMapEntry<'data> {
    address: u64,
    size: u64,
    name: &'data [u8],
    object: usize,
}

impl<'data> ObjectMapEntry<'data> {
    /// Get the symbol address.
    #[inline]
    pub fn address(&self) -> u64 {
        self.address
    }

    /// Get the symbol size.
    ///
    /// This may be 0 if the size is unknown.
    #[inline]
    pub fn size(&self) -> u64 {
        self.size
    }

    /// Get the symbol name.
    #[inline]
    pub fn name(&self) -> &'data [u8] {
        self.name
    }

    /// Get the index of the object file name.
    #[inline]
    pub fn object_index(&self) -> usize {
        self.object
    }

    /// Get the object file name.
    #[inline]
    pub fn object(&self, map: &ObjectMap<'data>) -> &'data [u8] {
        map.objects[self.object]
    }
}

impl<'data> SymbolMapEntry for ObjectMapEntry<'data> {
    #[inline]
    fn address(&self) -> u64 {
        self.address
    }
}

/// An imported symbol.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct Import<'data> {
    library: ByteString<'data>,
    // TODO: or ordinal
    name: ByteString<'data>,
}

impl<'data> Import<'data> {
    /// The symbol name.
    #[inline]
    pub fn name(&self) -> &'data [u8] {
        self.name.0
    }

    /// The name of the library to import the symbol from.
    #[inline]
    pub fn library(&self) -> &'data [u8] {
        self.library.0
    }
}

/// An exported symbol.
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct Export<'data> {
    // TODO: and ordinal?
    name: ByteString<'data>,
    address: u64,
}

impl<'data> Export<'data> {
    /// The symbol name.
    #[inline]
    pub fn name(&self) -> &'data [u8] {
        self.name.0
    }

    /// The virtual address of the symbol.
    #[inline]
    pub fn address(&self) -> u64 {
        self.address
    }
}

/// PDB Information
#[derive(Debug, Clone, Copy, PartialEq, Eq)]
pub struct CodeView<'data> {
    guid: [u8; 16],
    path: ByteString<'data>,
    age: u32,
}

impl<'data> CodeView<'data> {
    /// The path to the PDB as stored in CodeView
    #[inline]
    pub fn path(&self) -> &'data [u8] {
        self.path.0
    }

    /// The age of the PDB
    #[inline]
    pub fn age(&self) -> u32 {
        self.age
    }

    /// The GUID of the PDB.
    #[inline]
    pub fn guid(&self) -> [u8; 16] {
        self.guid
    }
}

/// The target referenced by a relocation.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
#[non_exhaustive]
pub enum RelocationTarget {
    /// The target is a symbol.
    Symbol(SymbolIndex),
    /// The target is a section.
    Section(SectionIndex),
    /// The offset is an absolute address.
    Absolute,
}

/// A relocation entry.
#[derive(Debug)]
pub struct Relocation {
    kind: RelocationKind,
    encoding: RelocationEncoding,
    size: u8,
    target: RelocationTarget,
    addend: i64,
    implicit_addend: bool,
}

impl Relocation {
    /// The operation used to calculate the result of the relocation.
    #[inline]
    pub fn kind(&self) -> RelocationKind {
        self.kind
    }

    /// Information about how the result of the relocation operation is encoded in the place.
    #[inline]
    pub fn encoding(&self) -> RelocationEncoding {
        self.encoding
    }

    /// The size in bits of the place of the relocation.
    ///
    /// If 0, then the size is determined by the relocation kind.
    #[inline]
    pub fn size(&self) -> u8 {
        self.size
    }

    /// The target of the relocation.
    #[inline]
    pub fn target(&self) -> RelocationTarget {
        self.target
    }

    /// The addend to use in the relocation calculation.
    #[inline]
    pub fn addend(&self) -> i64 {
        self.addend
    }

    /// Set the addend to use in the relocation calculation.
    #[inline]
    pub fn set_addend(&mut self, addend: i64) {
        self.addend = addend
    }

    /// Returns true if there is an implicit addend stored in the data at the offset
    /// to be relocated.
    #[inline]
    pub fn has_implicit_addend(&self) -> bool {
        self.implicit_addend
    }
}

/// A data compression format.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
#[non_exhaustive]
pub enum CompressionFormat {
    /// The data is uncompressed.
    None,
    /// The data is compressed, but the compression format is unknown.
    Unknown,
    /// ZLIB/DEFLATE.
    ///
    /// Used for ELF compression and GNU compressed debug information.
    Zlib,
}

/// A range in a file that may be compressed.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
pub struct CompressedFileRange {
    /// The data compression format.
    pub format: CompressionFormat,
    /// The file offset of the compressed data.
    pub offset: u64,
    /// The compressed data size.
    pub compressed_size: u64,
    /// The uncompressed data size.
    pub uncompressed_size: u64,
}

impl CompressedFileRange {
    /// Data that is uncompressed.
    #[inline]
    pub fn none(range: Option<(u64, u64)>) -> Self {
        if let Some((offset, size)) = range {
            CompressedFileRange {
                format: CompressionFormat::None,
                offset,
                compressed_size: size,
                uncompressed_size: size,
            }
        } else {
            CompressedFileRange {
                format: CompressionFormat::None,
                offset: 0,
                compressed_size: 0,
                uncompressed_size: 0,
            }
        }
    }

    /// Convert to `CompressedData` by reading from the file.
    pub fn data<'data, R: ReadRef<'data>>(self, file: R) -> Result<CompressedData<'data>> {
        let data = file
            .read_bytes_at(self.offset, self.compressed_size)
            .read_error("Invalid compressed data size or offset")?;
        Ok(CompressedData {
            format: self.format,
            data,
            uncompressed_size: self.uncompressed_size,
        })
    }
}

/// Data that may be compressed.
#[derive(Debug, Clone, Copy, PartialEq, Eq, Hash)]
pub struct CompressedData<'data> {
    /// The data compression format.
    pub format: CompressionFormat,
    /// The compressed data.
    pub data: &'data [u8],
    /// The uncompressed data size.
    pub uncompressed_size: u64,
}

impl<'data> CompressedData<'data> {
    /// Data that is uncompressed.
    #[inline]
    pub fn none(data: &'data [u8]) -> Self {
        CompressedData {
            format: CompressionFormat::None,
            data,
            uncompressed_size: data.len() as u64,
        }
    }

    /// Return the uncompressed data.
    ///
    /// Returns an error for invalid data or unsupported compression.
    /// This includes if the data is compressed but the `compression` feature
    /// for this crate is disabled.
    pub fn decompress(self) -> Result<Cow<'data, [u8]>> {
        match self.format {
            CompressionFormat::None => Ok(Cow::Borrowed(self.data)),
            #[cfg(feature = "compression")]
            CompressionFormat::Zlib => {
                use core::convert::TryInto;
                let size = self
                    .uncompressed_size
                    .try_into()
                    .ok()
                    .read_error("Uncompressed data size is too large.")?;
                let mut decompressed = Vec::with_capacity(size);
                let mut decompress = flate2::Decompress::new(true);
                decompress
                    .decompress_vec(
                        self.data,
                        &mut decompressed,
                        flate2::FlushDecompress::Finish,
                    )
                    .ok()
                    .read_error("Invalid zlib compressed data")?;
                Ok(Cow::Owned(decompressed))
            }
            _ => Err(Error("Unsupported compressed data.")),
        }
    }
}