json-streamer 0.3.0 → 0.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a0dc6d53af41106de2afd3c73edbe29626230388
-  data.tar.gz: 93bebbd4e33fb2eb273f849a4ffb2a1d75d9808e
+  metadata.gz: 14eacb500abba80f385b5f334b44801820cadc61
+  data.tar.gz: 5e6c6fd650b13ca12a8f541d4a80f34bc73a7e1d
 SHA512:
-  metadata.gz: a2d38100ad39aee46704ca2eb171609eea8b126c0a0f7b2cbf694b35220c479954e8a80dbba71a3136a0657e2119e0d4fe18df12975c8daa02d5ff6bcb43f8dc
-  data.tar.gz: 24b2c90609308bab883997514fc3a7ed74b1ac980a6c5ca536bc4c573bf4c3781047693ff347b63c2b7bf296549bb7deec88362e07bda27a67da56693cc61ca8
+  metadata.gz: c868d1324dd546e77eeb798df4716dc8cecea27f200643de75fe8009f4599c49c59c0a9744dbfb6f9c8e1ada67d52c46df3cc081eacb5faa8f2ddb32db0daa17
+  data.tar.gz: c762bbb47ed0f1bd0a6c8a3ea0a3b2265db28ab8f0676714a643a645e35804423a9358949994fb4c6973e7ae1a0acd33ac002f0c2bf75267854d0bb4c8527cd2

data/README.md

@@ -1,7 +1,6 @@
 # Json::Streamer
 
-Utility to support JSON streaming allowing you to get objects based on various criteria.
-Useful for e.g. streaming objects from a JSON array.
+Utility to support JSON streaming allowing you to get data based on various criteria (key, nesting level, etc).
 
 This gem will basically spare you the need to define you own callbacks when parsing JSON stream.
 Streaming is useful for
@@ -9,7 +8,8 @@ Streaming is useful for
 - files read in chunks (e.g. arriving over network)
 - cases where you expect some issue with the file (e.g. losing connection to source, invalid data at some point) but would like to get as much data as possible anyway
 
-Regarding performance:
+Performance:
+
 The gem uses JSON::Stream's events in the background. It was chosen because it's a pure Ruby parser.
 A similar implementation can be done using the ~10 times faster Yajl::FFI gem that is dependent on the native YAJL library.
 I did not measure the performance of my implementation on top of these libraries.
@@ -45,7 +45,9 @@ streamer = Json::Streamer::JsonStreamer.new(file_stream, 500)
 ```ruby
 # Get objects based on nesting level
 # First level will give you the full JSON, second level will give you objects within full JSON object, etc.
-streamer.get_objects_from_level(2)
+streamer.get(nesting_level:2).each do |object|
+    p object
+end
 ```
 
 Getting second level objects on the JSON below will yield you 2 empty objects
@@ -55,6 +57,35 @@ Getting second level objects on the JSON below will yield you 2 empty objects
     "object1": {},
     "object2": {}
 }
+=>
+{}
+{}
+```
+
+```ruby
+# Get data based on key
+streamer.get(key:'key').each do |object|
+    p object
+end
+```
+
+```json
+{
+    "obj1" : {
+        "key" : "value"
+    },
+    "key" : "value",
+    "obj2" : {
+        "key" : {
+            "key" : value"
+        }
+    }
+}
+=>
+"value"
+"value"
+"value"
+{"key"=>"value"}
 ```
 
 Check the unit tests for more examples.

data/json-streamer.gemspec

@@ -9,7 +9,7 @@ Gem::Specification.new do |spec|
   spec.authors       = ["Csaba Apagyi"]
   spec.email         = ["csapagyi@users.noreply.github.com"]
 
-  spec.summary       = %q{Utility to support JSON streaming allowing you to get objects based on various criteria. Useful for e.g. streaming objects from a JSON array.}
+  spec.summary       = %q{Utility to support JSON streaming allowing you to get data based on various criteria (key, nesting level, etc)}
   spec.homepage      = "https://github.com/csapagyi/json-streamer"
   spec.license       = "MIT"
 

data/lib/json/streamer.rb

@@ -4,13 +4,16 @@ require "json/stream"
 module Json
   module Streamer
     class JsonStreamer
+
+      attr_reader :aggregator
+
       def initialize(file_io, chunk_size = 1000)
         @parser = JSON::Stream::Parser.new
 
         @file_io = file_io
         @chunk_size = chunk_size
 
-        @object_nesting_level = 0
+        @current_nesting_level = -1
         @current_key = nil
         @aggregator = {}
         @temp_aggregator_keys = {}
@@ -18,36 +21,47 @@ module Json
         @parser.start_object {start_object}
         @parser.start_array {start_array}
         @parser.key {|k| key(k)}
-        @parser.value {|v| value(v)}
 
       end
 
-      def get_objects_from_level(yield_nesting_level)
-        @yield_nesting_level = yield_nesting_level
+      def get(nesting_level:-1, key:nil)
+        @yield_nesting_level = nesting_level
+        @wanted_key = key
+
+        @parser.value do |v|
+          if @aggregator[@current_nesting_level].kind_of? Array
+            @aggregator[@current_nesting_level] << v
+          else
+            @aggregator[@current_nesting_level][@current_key] = v
+            if yield_value?
+              yield v
+            end
+          end
+        end
 
         # Callback containing yield has be defined in the method called via block
         @parser.end_object do
-          if @object_nesting_level.eql? @yield_nesting_level
-            yield @aggregator[@object_nesting_level].clone
+          if yield_object?
+            yield @aggregator[@current_nesting_level].clone
             # TODO probably can be faster than reject!{true}
-            @aggregator[@object_nesting_level].reject!{true}
+            @aggregator[@current_nesting_level].reject!{true}
           else
             merge_up
           end
 
-          @object_nesting_level -= 1
+          @current_nesting_level -= 1
         end
 
         @parser.end_array do
-          if @object_nesting_level.eql? @yield_nesting_level
-            yield @aggregator[@object_nesting_level].clone
+          if yield_object?
+            yield @aggregator[@current_nesting_level].clone
             # TODO probably can be faster than reject!{true}
-            @aggregator[@object_nesting_level].reject!{true}
+            @aggregator[@current_nesting_level].reject!{true}
           else
             merge_up
           end
 
-          @object_nesting_level -= 1
+          @current_nesting_level -= 1
         end
 
         @file_io.each(@chunk_size) do |chunk|
@@ -55,16 +69,24 @@ module Json
         end
       end
 
+      def yield_object?
+        @current_nesting_level.eql? @yield_nesting_level or (not @wanted_key.nil? and @wanted_key == @temp_aggregator_keys[@current_nesting_level-1])
+      end
+
+      def yield_value?
+        @wanted_key == @current_key
+      end
+
       def start_object
-        @temp_aggregator_keys[@object_nesting_level] = @current_key
-        @object_nesting_level += 1
-        @aggregator[@object_nesting_level] = {}
+        @temp_aggregator_keys[@current_nesting_level] = @current_key
+        @current_nesting_level += 1
+        @aggregator[@current_nesting_level] = {}
       end
 
       def start_array
-        @temp_aggregator_keys[@object_nesting_level] = @current_key
-        @object_nesting_level += 1
-        @aggregator[@object_nesting_level] = []
+        @temp_aggregator_keys[@current_nesting_level] = @current_key
+        @current_nesting_level += 1
+        @aggregator[@current_nesting_level] = []
       end
 
       def key k
@@ -72,23 +94,19 @@ module Json
       end
 
       def value v
-        if @aggregator[@object_nesting_level].kind_of? Array
-          @aggregator[@object_nesting_level] << v
-        else
-          @aggregator[@object_nesting_level][@current_key] = v
-        end
+
       end
 
       def merge_up
-        return if @object_nesting_level == 1
-        previous_object_nesting_level = @object_nesting_level - 1
-        if @aggregator[previous_object_nesting_level].kind_of? Array
-          @aggregator[previous_object_nesting_level] << @aggregator[@object_nesting_level]
+        return if @current_nesting_level == 0
+        previous_nesting_level = @current_nesting_level - 1
+        if @aggregator[previous_nesting_level].kind_of? Array
+          @aggregator[previous_nesting_level] << @aggregator[@current_nesting_level]
         else
-          @aggregator[previous_object_nesting_level][@temp_aggregator_keys[previous_object_nesting_level]] = @aggregator[@object_nesting_level]
+          @aggregator[previous_nesting_level][@temp_aggregator_keys[previous_nesting_level]] = @aggregator[@current_nesting_level]
         end
 
-        @aggregator.delete(@object_nesting_level)
+        @aggregator.delete(@current_nesting_level)
         @aggregator
       end
     end

data/lib/json/streamer/version.rb

@@ -1,5 +1,5 @@
 module Json
   module Streamer
-    VERSION = "0.3.0"
+    VERSION = "0.4.0"
   end
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: json-streamer
 version: !ruby/object:Gem::Version
-  version: 0.3.0
+  version: 0.4.0
 platform: ruby
 authors:
 - Csaba Apagyi
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-05-28 00:00:00.000000000 Z
+date: 2016-05-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -121,6 +121,6 @@ rubyforge_project:
 rubygems_version: 2.5.1
 signing_key: 
 specification_version: 4
-summary: Utility to support JSON streaming allowing you to get objects based on various
-  criteria. Useful for e.g. streaming objects from a JSON array.
+summary: Utility to support JSON streaming allowing you to get data based on various
+  criteria (key, nesting level, etc)
 test_files: []