json-stream 0.2.0 → 0.2.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 15b32baaa4333e97f2eae71f21a03af04e8275ea
-  data.tar.gz: ea3b178e62a46ae093e5d362abd554fa3c361241
+SHA256:
+  metadata.gz: f1db3759d432092d3f1cac4dd90fe23551f14cd33bff1fa209a4f32cb2399025
+  data.tar.gz: 5c9532adaae5591585b756686463e93e24beb371d7a78e15cf45ffe09e6b4247
 SHA512:
-  metadata.gz: c88c6208cdb0597e6ba9ad1d9a86d62605f2329176eabfc15eb43f227a61efae3c1ff66cd1efe340e73245258e325076b6ecdacf6a3f5b870d03ec03d35c986c
-  data.tar.gz: cb403d67b89ec3f609b5b9e61b9f12c6a93d654206dbed37b5e9d20a8b94ecd1bd717bfb7f72bf129e3ee923904c4ac033fc90da569879c28e9140b5aa6103bd
+  metadata.gz: 9ac6519d888a81802453b964bc36db7639728c83ad67604516045fd6756c64c34579caa16050f1df32f1b9c8e6b4723433d81db8b2c63f59a2b846d9ab00eeb5
+  data.tar.gz: 7079d8a588958e49c016cc051f27b0ce6f24a902bbe3759702d50da1329815ae1ef929d41968ad24132eb748830062070cdf58b47261d05f4528caed7ad465da

data/Gemfile

@@ -0,0 +1,2 @@
+source 'https://rubygems.org'
+gemspec

data/LICENSE

@@ -1,4 +1,4 @@
-Copyright (c) 2010-2014 David Graham
+Copyright (c) 2010-2024 David Graham
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

data/README.md

@@ -2,9 +2,10 @@
 
 JSON::Stream is a JSON parser, based on a finite state machine, that generates
 events for each state change. This allows streaming both the JSON document into
-memory and the parsed object graph out of memory to some other process. This
-is much like an XML SAX parser that generates events during parsing. There is
-no requirement for the document, or the object graph, to be fully buffered in
+memory and the parsed object graph out of memory to some other process.
+
+This is much like an XML SAX parser that generates events during parsing. There
+is no requirement for the document, or the object graph, to be fully buffered in
 memory. This is best suited for huge JSON documents that won't fit in memory.
 For example, streaming and processing large map/reduce views from Apache
 CouchDB.
@@ -39,7 +40,7 @@ Again, while JSON::Stream can be used this way, if we just need to stream the
 document from disk or the network, we're better off using the yajl-ruby gem.
 
 Huge documents arriving over the network in small chunks to an EventMachine
-receive_data loop is where JSON::Stream is really useful. Inside an
+`receive_data` loop is where JSON::Stream is really useful. Inside an
 EventMachine::Connection subclass we might have:
 
 ```ruby
@@ -51,8 +52,8 @@ def post_init
     end_object     { puts "end object" }
     start_array    { puts "start array" }
     end_array      { puts "end array" }
-    key            {|k| puts "key: #{k}" }
-    value          {|v| puts "value: #{v}" }
+    key            { |k| puts "key: #{k}" }
+    value          { |v| puts "value: #{v}" }
   end
 end
 
@@ -76,16 +77,19 @@ imagine the callbacks looking for an array named `rows` and processing sets
 of these row objects in small batches. Millions of rows, streaming over the
 network, can be processed in constant memory space this way.
 
-## Dependencies
-
-* ruby >= 1.9.2
-* jruby >= 1.7
-
 ## Alternatives
 
 * [json](https://github.com/flori/json)
 * [yajl-ruby](https://github.com/brianmario/yajl-ruby)
 * [yajl-ffi](https://github.com/dgraham/yajl-ffi)
+* [application/json-seq](http://www.rfc-editor.org/rfc/rfc7464.txt)
+
+## Development
+
+```
+$ bin/setup
+$ bin/rake test
+```
 
 ## License
 

data/json-stream.gemspec

@@ -11,10 +11,12 @@ Gem::Specification.new do |s|
   s.homepage     = 'http://dgraham.github.io/json-stream/'
   s.license      = 'MIT'
 
-  s.files        = Dir['[A-Z]*', 'json-stream.gemspec', '{lib}/**/*']
-  s.test_files   = Dir['spec/**/*']
+  s.files        = Dir['[A-Z]*', 'json-stream.gemspec', '{lib}/**/*'] - ['Gemfile.lock']
   s.require_path = 'lib'
 
-  s.add_development_dependency 'rake', '~> 10.3'
-  s.required_ruby_version = '>= 1.9.2'
+  s.add_development_dependency 'bundler', '~> 2.1'
+  s.add_development_dependency 'minitest', '~> 5.10'
+  s.add_development_dependency 'rake', '~> 12.1'
+
+  s.required_ruby_version = '>= 2.0.0'
 end

data/lib/json/stream/buffer.rb

@@ -1,5 +1,3 @@
-# encoding: UTF-8
-
 module JSON
   module Stream
     # A character buffer that expects a UTF-8 encoded stream of bytes.
@@ -14,7 +12,7 @@ module JSON
     class Buffer
       def initialize
         @state = :start
-        @buf = []
+        @buffer = []
         @need = 0
       end
 
@@ -29,6 +27,12 @@ module JSON
       #
       # Returns a UTF-8 encoded String.
       def <<(data)
+        # Avoid state machine for complete UTF-8.
+        if @buffer.empty?
+          data.force_encoding(Encoding::UTF_8)
+          return data if data.valid_encoding?
+        end
+
         bytes = []
         data.each_byte do |byte|
           case @state
@@ -37,7 +41,7 @@ module JSON
               bytes << byte
             elsif byte >= 192
               @state = :multi_byte
-              @buf << byte
+              @buffer << byte
               @need =
                 case
                 when byte >= 240 then 4
@@ -49,9 +53,9 @@ module JSON
             end
           when :multi_byte
             if byte > 127 && byte < 192
-              @buf << byte
-              if @buf.size == @need
-                bytes += @buf.slice!(0, @buf.size)
+              @buffer << byte
+              if @buffer.size == @need
+                bytes += @buffer.slice!(0, @buffer.size)
                 @state = :start
               end
             else
@@ -59,8 +63,10 @@ module JSON
             end
           end
         end
-        bytes.pack('C*').force_encoding(Encoding::UTF_8).tap do |str|
-          error('Invalid UTF-8 byte sequence') unless str.valid_encoding?
+
+        # Build UTF-8 encoded string from completed codepoints.
+        bytes.pack('C*').force_encoding(Encoding::UTF_8).tap do |text|
+          error('Invalid UTF-8 byte sequence') unless text.valid_encoding?
         end
       end
 
@@ -82,7 +88,7 @@ module JSON
       #
       # Returns true if the buffer is empty.
       def empty?
-        @buf.empty?
+        @buffer.empty?
       end
 
       private

data/lib/json/stream/builder.rb

@@ -1,5 +1,3 @@
-# encoding: UTF-8
-
 module JSON
   module Stream
     # A parser listener that builds a full, in memory, object from a JSON
@@ -38,13 +36,15 @@ module JSON
 
       def end_object
         return if @stack.size == 1
+
         node = @stack.pop
+        top = @stack[-1]
 
-        case @stack.last
+        case top
         when Hash
-          @stack.last[@keys.pop] = node
+          top[@keys.pop] = node
         when Array
-          @stack.last << node
+          top << node
         end
       end
       alias :end_array :end_object
@@ -58,11 +58,12 @@ module JSON
       end
 
       def value(value)
-        case @stack.last
+        top = @stack[-1]
+        case top
         when Hash
-          @stack.last[@keys.pop] = value
+          top[@keys.pop] = value
         when Array
-          @stack.last << value
+          top << value
         else
           @stack << value
         end

data/lib/json/stream/parser.rb

@@ -1,5 +1,3 @@
-# encoding: UTF-8
-
 module JSON
   module Stream
     # Raised on any invalid JSON text.
@@ -12,8 +10,8 @@ module JSON
     # Examples
     #
     #   parser = JSON::Stream::Parser.new
-    #   parser.key {|key| puts key }
-    #   parser.value {|value| puts value }
+    #   parser.key { |key| puts key }
+    #   parser.value { |value| puts value }
     #   parser << '{"answer":'
     #   parser << ' 42}'
     class Parser
@@ -73,46 +71,6 @@ module JSON
         stream.close
       end
 
-      # Drain any remaining buffered characters into the parser to complete
-      # the parsing of the document.
-      #
-      # This is only required when parsing a document containing a single
-      # numeric value, integer or float. The parser has no other way to
-      # detect when it should no longer expect additional characters with
-      # which to complete the parse, so it must be signaled by a call to
-      # this method.
-      #
-      # If you're parsing more typical object or array documents, there's no
-      # need to call `finish` because the parse will complete when the final
-      # closing `]` or `}` character is scanned.
-      #
-      # Raises a JSON::Stream::ParserError if the JSON data is malformed.
-      #
-      # Returns nothing.
-      def finish
-        # Partial multi-byte character waiting for completion bytes.
-        error('Unexpected end-of-file') unless @utf8.empty?
-
-        # Partial array, object, or string.
-        error('Unexpected end-of-file') unless @stack.empty?
-
-        case @state
-        when :end_document
-          # done, do nothing
-        when :in_float
-          end_value(@buf.to_f)
-        when :in_exponent
-          error('Unexpected end-of-file') unless @buf =~ DIGIT_END
-          end_value(@buf.to_f)
-        when :start_zero
-          end_value(@buf.to_i)
-        when :start_int
-          end_value(@buf.to_i)
-        else
-          error('Unexpected end-of-file')
-        end
-      end
-
       # Create a new parser with an optional initialization block where
       # we can register event callbacks.
       #
@@ -125,8 +83,8 @@ module JSON
       #     end_object     { puts "end object" }
       #     start_array    { puts "start array" }
       #     end_array      { puts "end array" }
-      #     key            {|k| puts "key: #{k}" }
-      #     value          {|v| puts "value: #{v}" }
+      #     key            { |k| puts "key: #{k}" }
+      #     value          { |v| puts "value: #{v}" }
       #   end
       def initialize(&block)
         @state = :start_document
@@ -201,11 +159,11 @@ module JSON
             start_value(ch)
           when :start_object
             case ch
-            when RIGHT_BRACE
-              end_container(:object)
             when QUOTE
               @state = :start_string
               @stack.push(:key)
+            when RIGHT_BRACE
+              end_container(:object)
             when WS
               # ignore
             else
@@ -260,12 +218,12 @@ module JSON
               if @unicode.size == 4
                 codepoint = @unicode.slice!(0, 4).hex
                 if codepoint >= 0xD800 && codepoint <= 0xDBFF
-                  error('Expected low surrogate pair half') if @stack.last.is_a?(Fixnum)
+                  error('Expected low surrogate pair half') if @stack[-1].is_a?(Integer)
                   @state = :start_surrogate_pair
                   @stack.push(codepoint)
                 elsif codepoint >= 0xDC00 && codepoint <= 0xDFFF
                   high = @stack.pop
-                  error('Expected high surrogate pair half') unless high.is_a?(Fixnum)
+                  error('Expected high surrogate pair half') unless high.is_a?(Integer)
                   pair = ((high - 0xD800) * 0x400) + (codepoint - 0xDC00) + 0x10000
                   @buf << pair
                   @state = :start_string
@@ -402,17 +360,17 @@ module JSON
             case ch
             when COMMA
               @state = :value_sep
-            when RIGHT_BRACKET
-              end_container(:array)
             when RIGHT_BRACE
               end_container(:object)
+            when RIGHT_BRACKET
+              end_container(:array)
             when WS
               # ignore
             else
               error('Expected comma or object or array close')
             end
           when :value_sep
-            if @stack.last == :object
+            if @stack[-1] == :object
               case ch
               when QUOTE
                 @state = :start_string
@@ -431,6 +389,46 @@ module JSON
         end
       end
 
+      # Drain any remaining buffered characters into the parser to complete
+      # the parsing of the document.
+      #
+      # This is only required when parsing a document containing a single
+      # numeric value, integer or float. The parser has no other way to
+      # detect when it should no longer expect additional characters with
+      # which to complete the parse, so it must be signaled by a call to
+      # this method.
+      #
+      # If you're parsing more typical object or array documents, there's no
+      # need to call `finish` because the parse will complete when the final
+      # closing `]` or `}` character is scanned.
+      #
+      # Raises a JSON::Stream::ParserError if the JSON data is malformed.
+      #
+      # Returns nothing.
+      def finish
+        # Partial multi-byte character waiting for completion bytes.
+        error('Unexpected end-of-file') unless @utf8.empty?
+
+        # Partial array, object, or string.
+        error('Unexpected end-of-file') unless @stack.empty?
+
+        case @state
+        when :end_document
+          # done, do nothing
+        when :in_float
+          end_value(@buf.to_f)
+        when :in_exponent
+          error('Unexpected end-of-file') unless @buf =~ DIGIT_END
+          end_value(@buf.to_f)
+        when :start_zero
+          end_value(@buf.to_i)
+        when :start_int
+          end_value(@buf.to_i)
+        else
+          error('Unexpected end-of-file')
+        end
+      end
+
       private
 
       # Invoke all registered observer procs for the event type.

data/lib/json/stream/version.rb

@@ -1,7 +1,5 @@
-# encoding: UTF-8
-
 module JSON
   module Stream
-    VERSION = '0.2.0'
+    VERSION = '0.2.2'
   end
 end

metadata

@@ -1,29 +1,57 @@
 --- !ruby/object:Gem::Specification
 name: json-stream
 version: !ruby/object:Gem::Version
-  version: 0.2.0
+  version: 0.2.2
 platform: ruby
 authors:
 - David Graham
-autorequire: 
+autorequire:
 bindir: bin
 cert_chain: []
-date: 2014-07-06 00:00:00.000000000 Z
+date: 2024-04-21 00:00:00.000000000 Z
 dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+- !ruby/object:Gem::Dependency
+  name: minitest
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.10'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '5.10'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.3'
+        version: '12.1'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '10.3'
+        version: '12.1'
 description: A parser best suited for huge JSON documents that don't fit in memory.
 email:
 - david.malcom.graham@gmail.com
@@ -31,6 +59,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- Gemfile
 - LICENSE
 - README.md
 - Rakefile
@@ -40,15 +69,11 @@ files:
 - lib/json/stream/builder.rb
 - lib/json/stream/parser.rb
 - lib/json/stream/version.rb
-- spec/buffer_spec.rb
-- spec/builder_spec.rb
-- spec/fixtures/repository.json
-- spec/parser_spec.rb
 homepage: http://dgraham.github.io/json-stream/
 licenses:
 - MIT
 metadata: {}
-post_install_message: 
+post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -56,20 +81,15 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: 1.9.2
+      version: 2.0.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.2.2
-signing_key: 
+rubygems_version: 3.5.4
+signing_key:
 specification_version: 4
 summary: A streaming JSON parser that generates SAX-like events.
-test_files:
-- spec/buffer_spec.rb
-- spec/builder_spec.rb
-- spec/fixtures/repository.json
-- spec/parser_spec.rb
+test_files: []

data/spec/buffer_spec.rb

@@ -1,103 +0,0 @@
-# encoding: UTF-8
-
-require 'json/stream'
-require 'minitest/autorun'
-
-describe JSON::Stream::Buffer do
-  subject { JSON::Stream::Buffer.new }
-
-  it 'accepts single byte characters' do
-    assert_equal "", subject << ""
-    assert_equal "abc", subject << "abc"
-    assert_equal "\u0000abc", subject << "\u0000abc"
-  end
-
-  # The é character can be a single codepoint \u00e9 or two codepoints
-  # \u0065\u0301. The first is encoded in 2 bytes, the second in 3 bytes.
-  # The json and yajl-ruby gems and CouchDB do not normalize unicode text
-  # so neither will we. Although, a good way to normalize is by calling
-  # ActiveSupport::Multibyte::Chars.new("é").normalize(:c).
-  it 'accepts combined characters' do
-    assert_equal "\u0065\u0301", subject << "\u0065\u0301"
-    assert_equal 3, (subject << "\u0065\u0301").bytesize
-    assert_equal 2, (subject << "\u0065\u0301").size
-
-    assert_equal "\u00e9", subject << "\u00e9"
-    assert_equal 2, (subject << "\u00e9").bytesize
-    assert_equal 1, (subject << "\u00e9").size
-  end
-
-  it 'accepts valid two byte characters' do
-    assert_equal "abcé", subject << "abcé"
-    assert_equal "a", subject << "a\xC3"
-    assert_equal "é", subject << "\xA9"
-    assert_equal "", subject << "\xC3"
-    assert_equal "é", subject << "\xA9"
-    assert_equal "é", subject << "\xC3\xA9"
-  end
-
-  it 'accepts valid three byte characters' do
-    assert_equal "abcé\u2603", subject << "abcé\u2603"
-    assert_equal "a", subject << "a\xE2"
-    assert_equal "", subject << "\x98"
-    assert_equal "\u2603", subject << "\x83"
-  end
-
-  it 'accepts valid four byte characters' do
-    assert_equal "abcé\u2603\u{10102}é", subject << "abcé\u2603\u{10102}é"
-    assert_equal "a", subject << "a\xF0"
-    assert_equal "", subject << "\x90"
-    assert_equal "", subject << "\x84"
-    assert_equal "\u{10102}", subject << "\x82"
-  end
-
-  it 'rejects invalid two byte start characters' do
-    -> { subject << "\xC3\xC3" }.must_raise JSON::Stream::ParserError
-  end
-
-  it 'rejects invalid three byte start characters' do
-    -> { subject << "\xE2\xE2" }.must_raise JSON::Stream::ParserError
-  end
-
-  it 'rejects invalid four byte start characters' do
-    -> { subject << "\xF0\xF0" }.must_raise JSON::Stream::ParserError
-  end
-
-  it 'rejects a two byte start with single byte continuation character' do
-    -> { subject << "\xC3\u0000" }.must_raise JSON::Stream::ParserError
-  end
-
-  it 'rejects a three byte start with single byte continuation character' do
-    -> { subject << "\xE2\u0010" }.must_raise JSON::Stream::ParserError
-  end
-
-  it 'rejects a four byte start with single byte continuation character' do
-    -> { subject << "\xF0a" }.must_raise JSON::Stream::ParserError
-  end
-
-  it 'rejects an invalid continuation character' do
-    -> { subject << "\xA9" }.must_raise JSON::Stream::ParserError
-  end
-
-  it 'rejects an overlong form' do
-    -> { subject << "\xC0\x80" }.must_raise JSON::Stream::ParserError
-  end
-
-  describe 'checking for empty buffers' do
-    it 'is initially empty' do
-      assert subject.empty?
-    end
-
-    it 'is empty after processing complete characters' do
-      subject << 'test'
-      assert subject.empty?
-    end
-
-    it 'is not empty after processing partial multi-byte characters' do
-      subject << "\xC3"
-      refute subject.empty?
-      subject << "\xA9"
-      assert subject.empty?
-    end
-  end
-end