Module: MsgExtractor::Rtf::CompressedRtf
- Defined in:
- lib/msg_extractor/rtf/compressed_rtf.rb
Overview
LZFu decompression for PR_RTF_COMPRESSED per [MS-OXRTFCP].
Constant Summary collapse
- MAGIC_COMPRESSED =
“LZFu”
0x75465A4C- MAGIC_UNCOMPRESSED =
“MELA”
0x414C454D- INITIAL_DICTIONARY =
The fixed 207-byte initial dictionary defined by the spec.
("{\\rtf1\\ansi\\mac\\deff0\\deftab720{\\fonttbl;}" \ "{\\f0\\fnil \\froman \\fswiss \\fmodern \\fscript " \ "\\fdecor MS Sans SerifSymbolArialTimes New RomanCourier" \ "{\\colortbl\\red0\\green0\\blue0\r\n\\par " \ "\\pard\\plain\\f0\\fs20\\b\\i\\u\\tab\\tx").b.freeze
- CRC_TABLE =
CRC32 table (polynomial 0xEDB88320), init 0, no final XOR — per spec.
(0...256).map { |i| crc = i 8.times { crc = crc.odd? ? (0xEDB88320 ^ (crc >> 1)) : (crc >> 1) } crc }.freeze
Class Method Summary collapse
Class Method Details
.crc32(bytes) ⇒ Object
25 26 27 |
# File 'lib/msg_extractor/rtf/compressed_rtf.rb', line 25 def crc32(bytes) bytes.each_byte.reduce(0) { |crc, b| CRC_TABLE[(crc ^ b) & 0xFF] ^ (crc >> 8) } end |
.decompress(data) ⇒ Object
29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 |
# File 'lib/msg_extractor/rtf/compressed_rtf.rb', line 29 def decompress(data) raise CorruptFileError, "compressed RTF too short" if data.nil? || data.bytesize < 16 comp_size, raw_size, magic, crc = data.unpack("V4") case magic when MAGIC_UNCOMPRESSED raise CorruptFileError, "MELA RTF truncated" if data.bytesize - 16 < raw_size data.byteslice(16, raw_size) when MAGIC_COMPRESSED payload = data.byteslice(16, comp_size - 12) if comp_size >= 12 raise CorruptFileError, "compressed RTF truncated header" if payload.nil? unless crc32(payload) == crc raise CorruptFileError, "compressed RTF CRC mismatch" end lzfu(payload) else raise CorruptFileError, format("bad compressed RTF magic 0x%08x", magic) end end |
.lzfu(payload) ⇒ Object
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 |
# File 'lib/msg_extractor/rtf/compressed_rtf.rb', line 48 def lzfu(payload) dictionary = INITIAL_DICTIONARY.dup dictionary << ("\0".b * (4096 - dictionary.bytesize)) write_pos = INITIAL_DICTIONARY.bytesize # 207 out = +"".b pos = 0 while pos < payload.bytesize control = payload.getbyte(pos) pos += 1 8.times do |bit| if ((control >> bit) & 1) == 1 high = payload.getbyte(pos) low = payload.getbyte(pos + 1) return out if high.nil? || low.nil? pos += 2 reference = (high << 8) | low offset = reference >> 4 length = (reference & 0x0F) + 2 return out if offset == write_pos # end-of-stream marker length.times do byte = dictionary.getbyte(offset) offset = (offset + 1) % 4096 out << byte dictionary.setbyte(write_pos, byte) write_pos = (write_pos + 1) % 4096 end else byte = payload.getbyte(pos) return out if byte.nil? pos += 1 out << byte dictionary.setbyte(write_pos, byte) write_pos = (write_pos + 1) % 4096 end end end out end |