rainkinz rainkinz - 6 months ago 19
Ruby Question

Parse large JSON hash with ruby-yajl?

I have a large file (>50Mb) which contains a JSON hash. Something like:

{
"obj1": {
"key1": "val1",
"key2": "val2"
},
"obj2": {
"key1": "val1",
"key2": "val2"
}
...
}


Rather than parsing the entire file and taking say the first ten elements, I'd like to parse each item in the hash. I actually don't care about the key, i.e.
obj1
.

If I convert the above to this:

{
"key1": "val1",
"key2": "val2"
}
"obj2": {
"key1": "val1",
"key2": "val2"
}


I can easily achieve what I want using Yajl streaming:

io = File.open(path_to_file)
count = 10
Yajl::Parser.parse(io) do |obj|
puts "Parsed: #{obj}"
count -= 1
break if count == 0
end
io.close


Is there a way to do this without having to alter the file? Some sort of callback in Yajl maybe?

Answer

I ended up solving this using JSON::Stream which has callbacks for start_document, start_object etc.

I gave my 'parser' a to_enum method which emits all the 'Resource' objects as they're parsed. Note that ResourcesCollectionNode is never really used unless you completely parse the JSON stream, and the ResourceNode is a subclass of ObjectNode for naming purposes only, though I might just get rid of it:

class Parser
  METHODS = %w[start_document end_document start_object end_object start_array end_array key value]

  attr_reader :result

  def initialize(io, chunk_size = 1024)
    @io = io
    @chunk_size = chunk_size
    @parser = JSON::Stream::Parser.new

    # register callback methods
    METHODS.each do |name|
      @parser.send(name, &method(name))
    end 
  end

  def to_enum
    Enumerator.new do |yielder|
      @yielder = yielder
      begin
        while !@io.eof?
          # puts "READING CHUNK"
          chunk = @io.read(@chunk_size)
          @parser << chunk
        end
      ensure
        @yielder = nil
      end
    end
  end

  def start_document
    @stack = []
    @result = nil
  end

  def end_document
    # @result = @stack.pop.obj
  end

  def start_object
    if @stack.size == 0
      @stack.push(ResourceCollectionNode.new)
    elsif @stack.size == 1
      @stack.push(ResourceNode.new)
    else
      @stack.push(ObjectNode.new)
    end
  end

  def end_object
    if @stack.size == 2
      node = @stack.pop
      #puts "Stack depth: #{@stack.size}. Node: #{node.class}"
      @stack[-1] << node.obj

      # puts "Parsed complete resource: #{node.obj}"
      @yielder << node.obj

    elsif @stack.size == 1
      # puts "Parsed all resources"
      @result = @stack.pop.obj
    else
      node = @stack.pop
      # puts "Stack depth: #{@stack.size}. Node: #{node.class}"
      @stack[-1] << node.obj
    end
  end

  def end_array
    node = @stack.pop
    @stack[-1] << node.obj
  end

  def start_array
    @stack.push(ArrayNode.new)
  end

  def key(key)
    # puts "Stack depth: #{@stack.size} KEY: #{key}"
    @stack[-1] << key
  end

  def value(value)
    node = @stack[-1]
    node << value
  end

  class ObjectNode
    attr_reader :obj

    def initialize
      @obj, @key = {}, nil
    end

    def <<(node)
      if @key
        @obj[@key] = node
        @key = nil
      else
        @key = node
      end
      self
    end
  end

  class ResourceNode < ObjectNode
  end

  # Node that contains all the resources - a Hash keyed by url
  class ResourceCollectionNode < ObjectNode
    def <<(node)
      if @key
        @obj[@key] = node
        # puts "Completed Resource: #{@key} => #{node}"
        @key = nil
      else
        @key = node
      end
      self
    end
  end

  class ArrayNode
    attr_reader :obj

    def initialize
      @obj = []
    end

    def <<(node)
      @obj << node
      self
    end
  end

end

and an example in use:

def json
  <<-EOJ
  {
    "1": {
      "url": "url_1",
      "title": "title_1",
      "http_req": {
        "status": 200,
        "time": 10
      }
    },
    "2": {
      "url": "url_2",
      "title": "title_2",
      "http_req": {
        "status": 404,
        "time": -1
      }
    },
    "3": {
      "url": "url_1",
      "title": "title_1",
      "http_req": {
        "status": 200,
        "time": 10
      }
    },
    "4": {
      "url": "url_2",
      "title": "title_2",
      "http_req": {
        "status": 404,
        "time": -1
      }
    },
    "5": {
      "url": "url_1",
      "title": "title_1",
      "http_req": {
        "status": 200,
        "time": 10
      }
    },
    "6": {
      "url": "url_2",
      "title": "title_2",
      "http_req": {
        "status": 404,
        "time": -1
      }
    }          

  }
  EOJ
end


io = StringIO.new(json)
resource_parser = ResourceParser.new(io, 100)

count = 0
resource_parser.to_enum.each do |resource|
  count += 1
  puts "READ: #{count}"
  pp resource
  break
end

io.close

Output:

READ: 1
{"url"=>"url_1", "title"=>"title_1", "http_req"=>{"status"=>200, "time"=>10}}
Comments