stream_lines 0.2.1 → 0.3.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8a5a26c4cd79ebabece359dd7bf01dc01257a7ad2762e138cc3e3a2da36ca8c3
-  data.tar.gz: 4b199714d396ba83a93119825890c2cd94a2a4b1ec8bb6da3b2fd86e634e1b96
+  metadata.gz: 5f86f4c30e240b9076fa0ede333d89a0974e48b57ca3c75c145031314b524973
+  data.tar.gz: 7ee39a6d12b3e3e54eac67f6ea1d0108ac8ecc57ad78676187fe4c3dfcfed293
 SHA512:
-  metadata.gz: 4e880b83bf7509c6b6a941922188521f214704158cc8899400e0cd7bcf26d1f34447b571ab274d53cca06a3262cfe85ce4bbfde9f96a4558d1d6deefd4ac5a4c
-  data.tar.gz: 3ce19156e1e4999ea1919daa27ffed971ddf120189a2737721d8c8e677022ebbe2186158636d80ede697035f7a1a84c3edde650ce514382b43e8a02e9d64d775
+  metadata.gz: 2edb6bdd8ebccbf8d99c9769303c132ae2016c628dec9fc7b499ea3cf95ef579f9781ac7c205cbf526a1a10062af5d14c56a4927058a9580b0b6c0636b186978
+  data.tar.gz: b56a5173a42cc761337d4d1f30116bc6e5d08f1e07ff32eb8c4edeef58a537d42949a21d696be21f3913f51413242e03a0bbe5f7e4176f8b8f63b3204722e1ee

data/Gemfile.lock

@@ -1,7 +1,7 @@
 PATH
   remote: .
   specs:
-    stream_lines (0.2.1)
+    stream_lines (0.3.0)
       httparty (~> 0.14)
 
 GEM

data/README.md

@@ -6,13 +6,15 @@ An API for streaming files from remote locations one line at a time.
 
 ## Background
 
-Some applications run in production environments without writable file system;
+Some applications run in production environments without a writable file system;
 usually this is a security measure.  Futhermore, with the proliferation of
 container-based production environments, containers may not have access to
 tremendous amounts of memory.  Thus, it can be impossible to read large files
 unless you read the file into memory in small doses.  A common pattern is to
 use a line-delimited file like [JSON Lines](http://jsonlines.org) or a CSV
 and to read the file one line at a time in order to iterate over a dataset.
+This gem aims to provide an [Enumerable](https://ruby-doc.org/core-2.7.0/Enumerable.html)
+interface for iterating over remote, line-delimited datasets.
 
 ## Installation
 
@@ -41,7 +43,7 @@ url = 'https://my.remote.file/file.txt'
 stream = StreamLines::Reading::Stream.new(url)
 
 stream.each do |line|
-  # Do something with the line of data
+  # Do something with the line of data (the line will be a String)
 end
 
 # A StreamLines::Reading::Stream object is Enumerable, so you can also use
@@ -61,14 +63,14 @@ url = 'https://my.remote.file/file.csv'
 stream = StreamLines::Reading::CSV.new(url)
 
 stream.each do |row|
-  # each row will be an array
+  # each row will be an Array
 end
 
 # Supports most Ruby CSV options (see ignored options below)
 stream = StreamLines::Reading::CSV.new(url, headers: true)
 
 stream.each do |row|
-  # each row is a CSV::Row object that you can access like row['column_name']
+  # each row will be a CSV::Row object that you can access like row['column_name']
 end
 ```
 
@@ -85,6 +87,27 @@ require additional logic in the `StreamLines::Reading::CSV#each` method.
 Rather than attempting to implement sensible solutions for these options, I am
 choosing to explicitly ignore them until there is enough outcry to support them.
 
+##### JSON Lines/Streaming JSON
+
+This gem provides first-class support for streaming
+[JSON lines](http://jsonlines.org) from a remote URL.
+
+```ruby
+url = 'https://my.remote.file/file.jsonl'
+stream = StreamLines::Reading::JSONLines.new(url)
+
+stream.each do |row|
+  # each row will be an Hash
+end
+
+# Supports all Ruby JSON::parse options
+stream = StreamLines::Reading::JSONLines.new(url, symbolize_names: true)
+
+stream.each do |row|
+  # each row will be a Hash
+end
+```
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies.

data/lib/stream_lines.rb

@@ -3,6 +3,7 @@
 require 'stream_lines/error'
 require 'stream_lines/version'
 require 'stream_lines/reading/csv'
+require 'stream_lines/reading/json_lines'
 require 'stream_lines/reading/stream'
 
 module StreamLines

data/lib/stream_lines/reading/json_lines.rb

@@ -0,0 +1,30 @@
+# frozen_string_literal: true
+
+require 'json'
+require 'stream_lines/reading/stream'
+
+module StreamLines
+  module Reading
+    class JSONLines
+      include Enumerable
+
+      def initialize(url, **json_options)
+        @url = url
+        @json_options = json_options
+        @stream = Stream.new(url)
+      end
+
+      def each(&block)
+        @stream.each { |line| block.call(parse_line(line)) }
+      end
+
+      private
+
+      attr_reader :url
+
+      def parse_line(line)
+        JSON.parse(line, **@json_options)
+      end
+    end
+  end
+end

data/lib/stream_lines/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module StreamLines
-  VERSION = '0.2.1'
+  VERSION = '0.3.0'
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: stream_lines
 version: !ruby/object:Gem::Version
-  version: 0.2.1
+  version: 0.3.0
 platform: ruby
 authors:
 - Joel Lubrano
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2020-02-13 00:00:00.000000000 Z
+date: 2020-02-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: httparty
@@ -245,6 +245,7 @@ files:
 - lib/stream_lines/error.rb
 - lib/stream_lines/reading.rb
 - lib/stream_lines/reading/csv.rb
+- lib/stream_lines/reading/json_lines.rb
 - lib/stream_lines/reading/stream.rb
 - lib/stream_lines/version.rb
 - stream_lines.gemspec