Kaitai Struct YAML for COFF

coff.ksy

meta:
  id: coff
  title: Common Object Format File
  file-extension:
    - obj
  license: CC0-1.0
  ks-version: 0.9
  endian: le
doc-ref: https://wiki.osdev.org/COFF
seq:
  - id: coff_hdr
    type: coff_header
  - id: optional_hdr
    type: optional_header
    if: coff_hdr.size_of_optional_header != 0
    size: coff_hdr.size_of_optional_header
  - id: sections
    repeat: expr
    repeat-expr: coff_hdr.number_of_sections
    type: section
types:
  coff_header:
    seq:
      - id: machine
        type: u2
        enum: machine_type
      - id: number_of_sections
        type: u2
      - id: time_date_stamp
        type: u4
      - id: pointer_to_symbol_table
        type: u4
      - id: number_of_symbols
        type: u4
      - id: size_of_optional_header
        type: u2
      - id: characteristics
        type: u2
    instances:
      symbol_table_size:
        value: number_of_symbols * 18
      symbol_name_table_offset:
        value: pointer_to_symbol_table + symbol_table_size
      symbol_name_table_size:
        pos: symbol_name_table_offset
        type: u4
      symbol_table:
        pos: pointer_to_symbol_table
        type: coff_symbol
        repeat: expr
        repeat-expr: number_of_symbols
    enums:
      machine_type:
        # 3.3.1. Machine Types
        0x0: unknown
        0x1d3: am33
        0x8664: amd64
        0x1c0: arm
        0xaa64: arm64
        0x1c4: armnt
        0xebc: ebc
        0x14c: i386
        0x200: ia64
        0x9041: m32r
        0x266: mips16
        0x366: mipsfpu
        0x466: mipsfpu16
        0x1f0: powerpc
        0x1f1: powerpcfp
        0x166: r4000
        0x5032: riscv32
        0x5064: riscv64
        0x5128: riscv128
        0x1a2: sh3
        0x1a3: sh3dsp
        0x1a6: sh4
        0x1a8: sh5
        0x1c2: thumb
        0x169: wcemipsv2
        # Not mentioned in Microsoft documentation, but widely regarded
        0x184: alpha
  optional_header:
    seq:
      - id: magic
        type: u2
      - id: vstamp
        type: u2
      - id: text_size
        type: u4
      - id: data_size
        type: u4
      - id: bss_size
        type: u4
      - id: entry_point
        type: u4
      - id: text_start
        type: u4
      - id: data_start
        type: u4
  coff_symbol:
    -webide-representation: '{name_annoying.name}'
    seq:
      - id: name_annoying
        type: annoyingstring
        size: 8
      #- id: name_zeroes
      #  type: u4
      #- id: name_offset
      #  type: u4
      - id: value
        type: u4
      - id: section_number
        type: u2
      - id: type
        type: u2
      - id: storage_class
        type: u1
      - id: number_of_aux_symbols
        type: u1
    instances:
      #effective_name: 
      #  value: name_zeroes == 0 ? name_from_offset : '"fixme"'
      #name_from_offset:
      #  io: _root._io
      #  pos: name_zeroes == 0 ? _parent.symbol_name_table_offset + name_offset : 0
      #  type: str
      #  terminator: 0
      #  encoding: ascii
      section:
        value: _root.sections[section_number - 1]
      data:
        pos: section.pointer_to_raw_data + value
        size: 1
  coff_reloc:
    seq:
      - id: vaddr
        type: u4
      - id: symndx
        type: u4
      - id: type
        type: u2
  annoyingstring:
    -webide-representation: '{name}'
    instances:
      name_zeroes:
        pos: 0
        type: u4
      name_offset:
        pos: 4
        type: u4
      name_from_offset:
        io: _root._io
        pos: 'name_zeroes == 0 ? _parent._parent.symbol_name_table_offset + name_offset : 0'
        type: str
        terminator: 0
        encoding: ascii
        eos-error: false
        if: name_zeroes == 0
      name_from_short:
        pos: 0
        type: str
        terminator: 0
        encoding: ascii
        eos-error: false
        if: name_zeroes != 0
      name:
        value: 'name_zeroes == 0 ? name_from_offset : name_from_short'
  section:
    -webide-representation: "{name}"
    seq:
      - id: name
        type: str
        encoding: UTF-8
        size: 8
        pad-right: 0
      - id: virtual_size
        type: u4
      - id: virtual_address
        type: u4
      - id: size_of_raw_data
        type: u4
      - id: pointer_to_raw_data
        type: u4
      - id: pointer_to_relocations
        type: u4
      - id: pointer_to_linenumbers
        type: u4
      - id: number_of_relocations
        type: u2
      - id: number_of_linenumbers
        type: u2
      - id: characteristics
        type: u4
    instances:
      body:
        pos: pointer_to_raw_data
        size: size_of_raw_data
      relocs:
        pos: pointer_to_relocations
        repeat: expr
        repeat-expr: number_of_relocations
        type: coff_reloc