sema_api_ruby 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 5da03aaaec70b3e9e5bf3195c9c9552e348c9689
+  data.tar.gz: 3b2b8317183a67ee898ba0735bc67d569b8a8780
+SHA512:
+  metadata.gz: 5826f9f85f98f38747a69adf8981de0c70d57b1d12e7c60bb4df0856ee47fc89e9e1cce7ee224f4ac14eb86ce5f91e86ef437d2388ec5c52fc38e1b23202b8b4
+  data.tar.gz: c5a40bbacc6a83e769ee7de2489283ce3295ab4c2a49121515a182bef315c5a56c66a691a9f70354a88126b313d9e61a3355b3064f2fa4fd787a86b44ec0c8b3

data/.env.sample

@@ -0,0 +1 @@
+TEST_ACCESS_TOKEN=testaccesstoken

data/.gitignore

@@ -0,0 +1,10 @@
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+.env

data/.rspec

@@ -0,0 +1,2 @@
+--format documentation
+--color

data/Gemfile

@@ -0,0 +1,4 @@
+source 'https://rubygems.org'
+
+# Specify your gem's dependencies in sema_api_ruby.gemspec
+gemspec

data/README.md

@@ -0,0 +1,82 @@
+# SemaApiRuby
+
+Ruby client for Sema Media Data's image OCR API. Used for getting an estimated text to image ratio for validating images before being submitted to Facebook Ads.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'sema_api_ruby'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install sema_api_ruby
+
+## Usage
+
+Configure the client by providing an API token. Also tweak the configuration for any of the OCR settings.
+
+```ruby
+SemaApiRuby.configure do |config|
+  config.access_token = 'myaccesstokenhere'
+
+  #optional - below are the defaults
+  config.ocr_settings = {
+    lang: 'en',      # english language
+    outform: 'json', # output as json
+    sp: 'True',      # perform spellcheck
+    mh: 'True',      # multi-hypothesis... increases accuracy at slight performance cost
+    df: 'True',      # dictionary based word filtering
+    noempty: 'True'  # only return detected objects that are not empty
+  }
+end
+
+```
+
+Post a request to the ocr endpoint with the path to an image to get back a raw response from the api (post made using Faraday gem)
+```ruby
+client = SemaApiRuby.new
+file_path = '/path/to/your/image.jpg'
+
+client.post_ocr_image(file_path)
+# => #<Faraday::Response:0x007fcb641591e0 ...
+```
+
+Use this method to both post to the ocr endpoint and return an text to image ratio
+```ruby
+client = SemaApiRuby.new
+file_path = '/path/to/your/image.jpg'
+
+client.text_to_image_ratio(file_path)
+# => 0.2123
+```
+
+## Testing
+
+Copy the sample dotenv file to .env
+```
+$> cp .env.sample .env
+```
+
+Update it with a testing API token if you want to run specs against the live API rather than against the network stubs
+
+Run the specs
+```
+$> bundle exec rspec spec
+```
+
+This gem uses a testing gem called VCR to record and replay HTTP requests. If the actual API has changed you will need to delete all "casettes" located in ```spec/cassettes/``` so that requests will run against the live API
+
+## Contributing
+
+1. Fork it ( https://github.com/[my-github-username]/sema_api_ruby/fork )
+2. Create your feature branch (`git checkout -b my-new-feature`)
+3. Commit your changes (`git commit -am 'Add some feature'`)
+4. Push to the branch (`git push origin my-new-feature`)
+5. Create a new Pull Request

data/Rakefile

@@ -0,0 +1 @@
+require "bundler/gem_tasks"

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "sema_api_ruby"
+
+# You can add fixtures and/or initialization code here to make experimenting
+# with your gem easier. You can also use a different console, if you like.
+
+# (If you use this, don't forget to add pry to your Gemfile!)
+# require "pry"
+# Pry.start
+
+require "irb"
+IRB.start

data/bin/setup

@@ -0,0 +1,7 @@
+#!/bin/bash
+set -euo pipefail
+IFS=$'\n\t'
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/lib/sema_api_ruby/client/ocr.rb

@@ -0,0 +1,44 @@
+require 'json'
+
+module SemaApiRuby
+
+  class Client
+
+    module Ocr
+
+      def text_to_image_ratio(_file_path)
+        response = post_ocr_image(_file_path)
+
+        body = JSON.parse(response.body)
+
+        raise SemaApiRuby::Client::EmptyResponse unless body['frames']
+
+        return 0.0 if body['frames'].empty?
+
+        rectangles = body['frames'].first['results']
+
+        SemaApiRuby::GetTextToImageRatio.call(image_size(_file_path), rectangles)
+
+      # workaround for bug in sema media api where they are returning invalid json
+      # when an image does not have any text results. Remove when they start returning
+      # valid json
+      rescue JSON::ParserError => e
+        if e.message =~ /unexpected token at '\]\}'/
+          0.0
+        else
+          raise e
+        end
+      end
+
+      def post_ocr_image(_file_path)
+        post_body = ocr_settings.merge(
+          file: Faraday::UploadIO.new(_file_path, mime_type(_file_path))
+        )
+        conn_with_auth.post("/api/#{api_version}/ocr/", post_body)
+      end
+
+    end
+
+  end
+
+end

data/lib/sema_api_ruby/client.rb

@@ -0,0 +1,61 @@
+require 'faraday'
+require 'faraday_middleware'
+require 'fastimage'
+require 'sema_api_ruby/client/ocr'
+
+module SemaApiRuby
+
+  class Client
+
+    include SemaApiRuby::Client::Ocr
+
+    # setup accessors on this client for all config keys
+    attr_accessor *Configuration::VALID_CONFIG_KEYS
+
+    def initialize(options = {})
+      # Use options passed in, but fall back to config module defaults
+      merged_options = SemaApiRuby.options.merge(options)
+
+      # Copy the merged values to this client and ignore those
+      # not part of our configuration
+      SemaApiRuby::Configuration::VALID_CONFIG_KEYS.each do |key|
+        public_send("#{key}=", merged_options[key])
+      end
+
+      if access_token.nil?
+        raise NoTokenError, 'you must provide an access token'
+      end
+    end
+
+    private
+
+    def conn
+      @conn ||= Faraday.new(url: api_endpoint) do |conn|
+        conn.request :multipart
+        conn.request :url_encoded
+        #conn.response :json
+
+        conn.adapter Faraday.default_adapter
+      end
+    end
+
+    def conn_with_auth
+      @conn_with_auth ||= begin
+        conn.headers['X-api-key'] = access_token
+        conn.headers['User-Agent'] = user_agent
+        conn.headers['Content-Type'] = content_type
+        conn
+      end
+    end
+
+    def mime_type(_file_path)
+      "image/#{FastImage.type(_file_path)}"
+    end
+
+    def image_size(_file_path)
+      FastImage.size(_file_path)
+    end
+
+  end
+
+end

data/lib/sema_api_ruby/configuration.rb

@@ -0,0 +1,56 @@
+module SemaApiRuby
+
+  module Configuration
+
+    VALID_CONFIG_KEYS = [
+      :access_token,
+      :api_endpoint,
+      :api_version,
+      :user_agent,
+      :content_type,
+      :ocr_settings,
+      :debug_output
+    ]
+
+    DEFAULT_API_ENDPOINT = 'https://semamediadata.com/api'.freeze # 1.0/ocr/
+    DEFAULT_API_VERSION  = 1.0
+    DEFAULT_USER_AGENT   = "SemaApiRuby Gem #{SemaApiRuby::VERSION}".freeze
+    DEFAULT_CONTENT_TYPE = 'multipart/form-data'
+    DEFAULT_DEBUG_OUTPUT = false # $stdout
+
+    DEFAULT_OCR_SETTINGS = {
+      lang: 'en',      # english language
+      outform: 'json', # output as json
+      sp: 'True',      # perform spellcheck
+      mh: 'True',      # multi-hypothesis... increases accuracy at slight performance cost
+      df: 'True',      # dictionary based word filtering
+      noempty: 'True'  # only return detected objects that are not empty
+    }
+
+    attr_accessor *VALID_CONFIG_KEYS
+
+    def configure
+      yield self
+    end
+
+    def self.extended(base)
+      base.reset
+    end
+
+    def options
+      Hash[ *VALID_CONFIG_KEYS.map { |key| [key, public_send(key)] }.flatten ]
+    end
+
+    def reset
+      self.access_token  = nil
+      self.api_endpoint  = DEFAULT_API_ENDPOINT
+      self.api_version   = DEFAULT_API_VERSION
+      self.user_agent    = DEFAULT_USER_AGENT
+      self.content_type  = DEFAULT_CONTENT_TYPE
+      self.debug_output  = DEFAULT_DEBUG_OUTPUT
+      self.ocr_settings  = DEFAULT_OCR_SETTINGS
+    end
+
+  end
+
+end

data/lib/sema_api_ruby/exceptions.rb

@@ -0,0 +1,11 @@
+module SemaApiRuby
+
+  class Client
+
+    class NoTokenError < StandardError; end;
+
+    class EmptyResponse < StandardError; end;
+
+  end
+
+end

data/lib/sema_api_ruby/get_text_to_image_ratio.rb

@@ -0,0 +1,34 @@
+module SemaApiRuby
+
+  class GetTextToImageRatio
+
+    attr_accessor :rectangles, :image_size
+
+    def self.call(image_size, rectangles)
+      self.new(image_size, rectangles).call
+    end
+
+    def initialize(image_size, rectangles)
+      @rectangles = rectangles
+      @image_size = image_size
+    end
+
+    def call
+      return 0.0 unless rectangles.any?
+
+      text_area = rectangles.inject(0.0) do |memo, rect|
+        memo += if rect['text'].nil? || rect['text'].empty?
+          0.0
+        else
+          (rect['width'] * rect['height']).to_f
+        end
+      end
+
+      image_area = image_size[0] * image_size[1]
+
+      (text_area / image_area.to_f).round(4)
+    end
+
+  end
+
+end

data/lib/sema_api_ruby/version.rb

@@ -0,0 +1,3 @@
+module SemaApiRuby
+  VERSION = "0.1.0"
+end

data/lib/sema_api_ruby.rb

@@ -0,0 +1,30 @@
+require 'sema_api_ruby/version'
+require 'sema_api_ruby/configuration'
+require 'sema_api_ruby/exceptions'
+require 'sema_api_ruby/get_text_to_image_ratio'
+require 'sema_api_ruby/client'
+
+module SemaApiRuby
+
+  extend Configuration
+
+  def self.new(options = {})
+    SemaApiRuby::Client.new(options)
+  end
+
+  def self.root
+    File.dirname __dir__
+  end
+
+  def self.default_ocr_options
+    {
+      lang: 'en',      # english language
+      outform: 'json', # output as json
+      sp: 'True',      # perform spellcheck
+      mh: 'True',      # multi-hypothesis... increases accuracy at slight performance cost
+      df: 'True',      # dictionary based word filtering
+      noempty: 'True'  # only return detected objects that are not empty
+    }
+  end
+
+end

data/sema_api_ruby.gemspec

@@ -0,0 +1,38 @@
+# coding: utf-8
+lib = File.expand_path('../lib', __FILE__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'sema_api_ruby/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'sema_api_ruby'
+  spec.version       = SemaApiRuby::VERSION
+  spec.authors       = ['Jrod']
+  spec.email         = ['jarrod@jtms.net']
+
+  spec.summary       = %q{Ruby client for Sema Media Data image OCR API}
+  spec.description   = spec.summary
+  spec.homepage      = 'https://github.com/jspillers/sema_api_ruby'
+
+  # Prevent pushing this gem to RubyGems.org by setting 'allowed_push_host', or
+  # delete this section to allow pushing this gem to any host.
+  #if spec.respond_to?(:metadata)
+  #  spec.metadata['allowed_push_host'] = 'TODO: Set to "http://mygemserver.com"'
+  #else
+  #  raise 'RubyGems 2.0 or newer is required to protect against public gem pushes.'
+  #end
+
+  spec.files         = `git ls-files -z`.split("\x0").reject { |f| f.match(%r{^(test|spec|features)/}) }
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_dependency 'faraday', '~> 0.9.1'
+  spec.add_dependency 'faraday_middleware', '~> 0.10.0'
+  spec.add_dependency 'fastimage', '~> 1.7.0'
+  
+  spec.add_development_dependency 'bundler', '~> 1.9'
+  spec.add_development_dependency 'rake', '~> 10.0'
+  spec.add_development_dependency 'pry', '~> 0.10.1'
+  spec.add_development_dependency 'vcr', '~> 2.9.3'
+
+end

metadata

@@ -0,0 +1,157 @@
+--- !ruby/object:Gem::Specification
+name: sema_api_ruby
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Jrod
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2015-08-13 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: faraday
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.9.1
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.9.1
+- !ruby/object:Gem::Dependency
+  name: faraday_middleware
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.0
+- !ruby/object:Gem::Dependency
+  name: fastimage
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.7.0
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 1.7.0
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '10.0'
+- !ruby/object:Gem::Dependency
+  name: pry
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.1
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 0.10.1
+- !ruby/object:Gem::Dependency
+  name: vcr
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.9.3
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: 2.9.3
+description: Ruby client for Sema Media Data image OCR API
+email:
+- jarrod@jtms.net
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- ".env.sample"
+- ".gitignore"
+- ".rspec"
+- Gemfile
+- README.md
+- Rakefile
+- bin/console
+- bin/setup
+- lib/sema_api_ruby.rb
+- lib/sema_api_ruby/client.rb
+- lib/sema_api_ruby/client/ocr.rb
+- lib/sema_api_ruby/configuration.rb
+- lib/sema_api_ruby/exceptions.rb
+- lib/sema_api_ruby/get_text_to_image_ratio.rb
+- lib/sema_api_ruby/version.rb
+- sema_api_ruby.gemspec
+homepage: https://github.com/jspillers/sema_api_ruby
+licenses: []
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.4.5
+signing_key: 
+specification_version: 4
+summary: Ruby client for Sema Media Data image OCR API
+test_files: []