json-streamer 0.3.0 → 0.4.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- checksums.yaml +4 -4
- data/README.md +35 -4
- data/json-streamer.gemspec +1 -1
- data/lib/json/streamer.rb +47 -29
- data/lib/json/streamer/version.rb +1 -1
- metadata +4 -4
checksums.yaml
CHANGED
@@ -1,7 +1,7 @@
|
|
1
1
|
---
|
2
2
|
SHA1:
|
3
|
-
metadata.gz:
|
4
|
-
data.tar.gz:
|
3
|
+
metadata.gz: 14eacb500abba80f385b5f334b44801820cadc61
|
4
|
+
data.tar.gz: 5e6c6fd650b13ca12a8f541d4a80f34bc73a7e1d
|
5
5
|
SHA512:
|
6
|
-
metadata.gz:
|
7
|
-
data.tar.gz:
|
6
|
+
metadata.gz: c868d1324dd546e77eeb798df4716dc8cecea27f200643de75fe8009f4599c49c59c0a9744dbfb6f9c8e1ada67d52c46df3cc081eacb5faa8f2ddb32db0daa17
|
7
|
+
data.tar.gz: c762bbb47ed0f1bd0a6c8a3ea0a3b2265db28ab8f0676714a643a645e35804423a9358949994fb4c6973e7ae1a0acd33ac002f0c2bf75267854d0bb4c8527cd2
|
data/README.md
CHANGED
@@ -1,7 +1,6 @@
|
|
1
1
|
# Json::Streamer
|
2
2
|
|
3
|
-
Utility to support JSON streaming allowing you to get
|
4
|
-
Useful for e.g. streaming objects from a JSON array.
|
3
|
+
Utility to support JSON streaming allowing you to get data based on various criteria (key, nesting level, etc).
|
5
4
|
|
6
5
|
This gem will basically spare you the need to define you own callbacks when parsing JSON stream.
|
7
6
|
Streaming is useful for
|
@@ -9,7 +8,8 @@ Streaming is useful for
|
|
9
8
|
- files read in chunks (e.g. arriving over network)
|
10
9
|
- 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
|
11
10
|
|
12
|
-
|
11
|
+
Performance:
|
12
|
+
|
13
13
|
The gem uses JSON::Stream's events in the background. It was chosen because it's a pure Ruby parser.
|
14
14
|
A similar implementation can be done using the ~10 times faster Yajl::FFI gem that is dependent on the native YAJL library.
|
15
15
|
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)
|
|
45
45
|
```ruby
|
46
46
|
# Get objects based on nesting level
|
47
47
|
# First level will give you the full JSON, second level will give you objects within full JSON object, etc.
|
48
|
-
streamer.
|
48
|
+
streamer.get(nesting_level:2).each do |object|
|
49
|
+
p object
|
50
|
+
end
|
49
51
|
```
|
50
52
|
|
51
53
|
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
|
|
55
57
|
"object1": {},
|
56
58
|
"object2": {}
|
57
59
|
}
|
60
|
+
=>
|
61
|
+
{}
|
62
|
+
{}
|
63
|
+
```
|
64
|
+
|
65
|
+
```ruby
|
66
|
+
# Get data based on key
|
67
|
+
streamer.get(key:'key').each do |object|
|
68
|
+
p object
|
69
|
+
end
|
70
|
+
```
|
71
|
+
|
72
|
+
```json
|
73
|
+
{
|
74
|
+
"obj1" : {
|
75
|
+
"key" : "value"
|
76
|
+
},
|
77
|
+
"key" : "value",
|
78
|
+
"obj2" : {
|
79
|
+
"key" : {
|
80
|
+
"key" : value"
|
81
|
+
}
|
82
|
+
}
|
83
|
+
}
|
84
|
+
=>
|
85
|
+
"value"
|
86
|
+
"value"
|
87
|
+
"value"
|
88
|
+
{"key"=>"value"}
|
58
89
|
```
|
59
90
|
|
60
91
|
Check the unit tests for more examples.
|
data/json-streamer.gemspec
CHANGED
@@ -9,7 +9,7 @@ Gem::Specification.new do |spec|
|
|
9
9
|
spec.authors = ["Csaba Apagyi"]
|
10
10
|
spec.email = ["csapagyi@users.noreply.github.com"]
|
11
11
|
|
12
|
-
spec.summary = %q{Utility to support JSON streaming allowing you to get
|
12
|
+
spec.summary = %q{Utility to support JSON streaming allowing you to get data based on various criteria (key, nesting level, etc)}
|
13
13
|
spec.homepage = "https://github.com/csapagyi/json-streamer"
|
14
14
|
spec.license = "MIT"
|
15
15
|
|
data/lib/json/streamer.rb
CHANGED
@@ -4,13 +4,16 @@ require "json/stream"
|
|
4
4
|
module Json
|
5
5
|
module Streamer
|
6
6
|
class JsonStreamer
|
7
|
+
|
8
|
+
attr_reader :aggregator
|
9
|
+
|
7
10
|
def initialize(file_io, chunk_size = 1000)
|
8
11
|
@parser = JSON::Stream::Parser.new
|
9
12
|
|
10
13
|
@file_io = file_io
|
11
14
|
@chunk_size = chunk_size
|
12
15
|
|
13
|
-
@
|
16
|
+
@current_nesting_level = -1
|
14
17
|
@current_key = nil
|
15
18
|
@aggregator = {}
|
16
19
|
@temp_aggregator_keys = {}
|
@@ -18,36 +21,47 @@ module Json
|
|
18
21
|
@parser.start_object {start_object}
|
19
22
|
@parser.start_array {start_array}
|
20
23
|
@parser.key {|k| key(k)}
|
21
|
-
@parser.value {|v| value(v)}
|
22
24
|
|
23
25
|
end
|
24
26
|
|
25
|
-
def
|
26
|
-
@yield_nesting_level =
|
27
|
+
def get(nesting_level:-1, key:nil)
|
28
|
+
@yield_nesting_level = nesting_level
|
29
|
+
@wanted_key = key
|
30
|
+
|
31
|
+
@parser.value do |v|
|
32
|
+
if @aggregator[@current_nesting_level].kind_of? Array
|
33
|
+
@aggregator[@current_nesting_level] << v
|
34
|
+
else
|
35
|
+
@aggregator[@current_nesting_level][@current_key] = v
|
36
|
+
if yield_value?
|
37
|
+
yield v
|
38
|
+
end
|
39
|
+
end
|
40
|
+
end
|
27
41
|
|
28
42
|
# Callback containing yield has be defined in the method called via block
|
29
43
|
@parser.end_object do
|
30
|
-
if
|
31
|
-
yield @aggregator[@
|
44
|
+
if yield_object?
|
45
|
+
yield @aggregator[@current_nesting_level].clone
|
32
46
|
# TODO probably can be faster than reject!{true}
|
33
|
-
@aggregator[@
|
47
|
+
@aggregator[@current_nesting_level].reject!{true}
|
34
48
|
else
|
35
49
|
merge_up
|
36
50
|
end
|
37
51
|
|
38
|
-
@
|
52
|
+
@current_nesting_level -= 1
|
39
53
|
end
|
40
54
|
|
41
55
|
@parser.end_array do
|
42
|
-
if
|
43
|
-
yield @aggregator[@
|
56
|
+
if yield_object?
|
57
|
+
yield @aggregator[@current_nesting_level].clone
|
44
58
|
# TODO probably can be faster than reject!{true}
|
45
|
-
@aggregator[@
|
59
|
+
@aggregator[@current_nesting_level].reject!{true}
|
46
60
|
else
|
47
61
|
merge_up
|
48
62
|
end
|
49
63
|
|
50
|
-
@
|
64
|
+
@current_nesting_level -= 1
|
51
65
|
end
|
52
66
|
|
53
67
|
@file_io.each(@chunk_size) do |chunk|
|
@@ -55,16 +69,24 @@ module Json
|
|
55
69
|
end
|
56
70
|
end
|
57
71
|
|
72
|
+
def yield_object?
|
73
|
+
@current_nesting_level.eql? @yield_nesting_level or (not @wanted_key.nil? and @wanted_key == @temp_aggregator_keys[@current_nesting_level-1])
|
74
|
+
end
|
75
|
+
|
76
|
+
def yield_value?
|
77
|
+
@wanted_key == @current_key
|
78
|
+
end
|
79
|
+
|
58
80
|
def start_object
|
59
|
-
@temp_aggregator_keys[@
|
60
|
-
@
|
61
|
-
@aggregator[@
|
81
|
+
@temp_aggregator_keys[@current_nesting_level] = @current_key
|
82
|
+
@current_nesting_level += 1
|
83
|
+
@aggregator[@current_nesting_level] = {}
|
62
84
|
end
|
63
85
|
|
64
86
|
def start_array
|
65
|
-
@temp_aggregator_keys[@
|
66
|
-
@
|
67
|
-
@aggregator[@
|
87
|
+
@temp_aggregator_keys[@current_nesting_level] = @current_key
|
88
|
+
@current_nesting_level += 1
|
89
|
+
@aggregator[@current_nesting_level] = []
|
68
90
|
end
|
69
91
|
|
70
92
|
def key k
|
@@ -72,23 +94,19 @@ module Json
|
|
72
94
|
end
|
73
95
|
|
74
96
|
def value v
|
75
|
-
|
76
|
-
@aggregator[@object_nesting_level] << v
|
77
|
-
else
|
78
|
-
@aggregator[@object_nesting_level][@current_key] = v
|
79
|
-
end
|
97
|
+
|
80
98
|
end
|
81
99
|
|
82
100
|
def merge_up
|
83
|
-
return if @
|
84
|
-
|
85
|
-
if @aggregator[
|
86
|
-
@aggregator[
|
101
|
+
return if @current_nesting_level == 0
|
102
|
+
previous_nesting_level = @current_nesting_level - 1
|
103
|
+
if @aggregator[previous_nesting_level].kind_of? Array
|
104
|
+
@aggregator[previous_nesting_level] << @aggregator[@current_nesting_level]
|
87
105
|
else
|
88
|
-
@aggregator[
|
106
|
+
@aggregator[previous_nesting_level][@temp_aggregator_keys[previous_nesting_level]] = @aggregator[@current_nesting_level]
|
89
107
|
end
|
90
108
|
|
91
|
-
@aggregator.delete(@
|
109
|
+
@aggregator.delete(@current_nesting_level)
|
92
110
|
@aggregator
|
93
111
|
end
|
94
112
|
end
|
metadata
CHANGED
@@ -1,14 +1,14 @@
|
|
1
1
|
--- !ruby/object:Gem::Specification
|
2
2
|
name: json-streamer
|
3
3
|
version: !ruby/object:Gem::Version
|
4
|
-
version: 0.
|
4
|
+
version: 0.4.0
|
5
5
|
platform: ruby
|
6
6
|
authors:
|
7
7
|
- Csaba Apagyi
|
8
8
|
autorequire:
|
9
9
|
bindir: exe
|
10
10
|
cert_chain: []
|
11
|
-
date: 2016-05-
|
11
|
+
date: 2016-05-29 00:00:00.000000000 Z
|
12
12
|
dependencies:
|
13
13
|
- !ruby/object:Gem::Dependency
|
14
14
|
name: bundler
|
@@ -121,6 +121,6 @@ rubyforge_project:
|
|
121
121
|
rubygems_version: 2.5.1
|
122
122
|
signing_key:
|
123
123
|
specification_version: 4
|
124
|
-
summary: Utility to support JSON streaming allowing you to get
|
125
|
-
criteria
|
124
|
+
summary: Utility to support JSON streaming allowing you to get data based on various
|
125
|
+
criteria (key, nesting level, etc)
|
126
126
|
test_files: []
|