Prevent GC compaction and unintended sweeps for preventing checksum mismatch

[cosmo0920]

With this repro which is based on #112 (comment)

require "digest"
require "tempfile"

$LOAD_PATH.unshift File.expand_path('lib', __dir__)
require 'zstd-ruby'

puts "Zstd::VERSION=#{Zstd::VERSION}"

def compare_compressed(original:, compressed:)
  begin
    decompressed = Zstd.decompress(compressed)
  rescue => e
    decompress_error = e
  end

  if original != decompressed
    if decompress_error
      puts "Decompression error for #{original.bytesize} bytes input (#{decompress_error})"
    else
      puts "Content mismatch for #{original.bytesize} bytes input"
    end

    puts "  Original:        #{original.bytesize} bytes, #{Digest::SHA256.hexdigest(original)[0, 10]} checksum"

    if decompressed
      puts "  Zstd.decompress: #{decompressed.bytesize} bytes, #{Digest::SHA256.hexdigest(decompressed)[0, 10]} checksum"
    end

    begin
      cli_decompressed = Tempfile.create(binmode: true) do |temp_write|
        temp_write.write(compressed)
        temp_write.close
        Tempfile.create(binmode: true) do |temp_read|
          system "zstd", "--decompress", "--quiet", "--force", "-o", temp_read.path, temp_write.path, exception: true
          File.read(temp_read.path, binmode: true)
        end
      end

      puts "  zstd cli:        #{cli_decompressed.bytesize} bytes, #{Digest::SHA256.hexdigest(cli_decompressed)[0, 10]} checksum"
    rescue => e
      puts "  zstd cli error: #{e}"
    end
  end
end

def test_stream_write
  (1..256_000).each do |length|
    original = "a" * length

    stream = Zstd::StreamingCompress.new
    stream << original
    res = stream.finish

    compare_compressed(original: original, compressed: res)
  end
end

def test_stream_compress
  (1..256_000).each do |length|
    original = "a" * length

    stream = Zstd::StreamingCompress.new
    res = stream.compress(original)
    res << stream.finish

    compare_compressed(original: original, compressed: res)
  end
end

def test_compress
  (1..256_000).each do |length|
    original = "a" * length

    res = Zstd.compress(original)

    compare_compressed(original: original, compressed: res)
  end
end

def debug_specific_size(length)
  puts "=== Debugging size #{length} ==="
  original = "a" * length

  # 1. Generate the "good" stream using the working .compress method
  stream_good = Zstd::StreamingCompress.new
  good_compressed = stream_good.compress(original)
  good_compressed << stream_good.finish
  File.write("good.zst", good_compressed)
  puts "Saved working output to good.zst (#{good_compressed.bytesize} bytes)"

  # 2. Generate the "bad" stream using the failing << method
  stream_bad = Zstd::StreamingCompress.new
  stream_bad << original
  bad_compressed = stream_bad.finish
  File.write("bad.zst", bad_compressed)
  puts "Saved failing output to bad.zst (#{bad_compressed.bytesize} bytes)"
  puts
end

case ARGV[0]
when "stream_write"
  puts "=== Zstd::StreamingCompress.new with << ==="
  test_stream_write
when "stream_compress"
  puts "=== Zstd::StreamingCompress.new with .compress ==="
  test_stream_compress
when "compress"
  puts "=== Zstd.compress ==="
  test_compress
when "debug"
  size = ARGV[1].to_i
  if size <= 0
    abort "Please provide a specific size to debug, e.g., 'ruby zstd_repro.rb debug 20086'"
  end
  debug_specific_size(size)
else
  abort "Unknown test mode: #{ARGV[0].inspect}"
end

And using with rspec tests, there is no issues and checksum mismatches reported.

$ bundle exec rspec

<snip>
Finished in 15.39 seconds (files took 0.12929 seconds to load)
60 examples, 0 failures

% ruby zstd_repro.rb compress
Zstd::VERSION=2.0.0
=== Zstd.compress ===
% ruby zstd_repro.rb stream_compress
Zstd::VERSION=2.0.0
=== Zstd::StreamingCompress.new with .compress ===
% ruby zstd_repro.rb stream_write
Zstd::VERSION=2.0.0
=== Zstd::StreamingCompress.new with << ===

[SpringMT]

Thank you!

[SpringMT]

I just released v2.0.1 !