Add Language Detection endpoint

Close #247

Test

README.md

@@ -343,6 +343,28 @@ Response:
 
   ... PDF document body ...
 
+### Detect language
+
+This is a foreground document language detection request. The detected language
+will be returned as the response body.
+
+ POST /detect-language
+
+Params *(suggest using `multipart/form-data`)*:
+
+* `file` - the file to convert
+
+#### Example:
+
+ POST /detect-language
+  file=... foo.docx ...
+
+Response:
+
+  Content-Type: text/plain
+
+  en
+
 ## Callbacks
 
 When a document conversion is completed, an attempt will be made to POST a

config/tika.xml

@@ -0,0 +1,14 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<properties>
+ <parsers>
+ <!-- https://cwiki.apache.org/confluence/pages/viewpage.action?pageId=109454096#TikaOCR-OverridingDefaultConfiguration -->
+ <parser class="org.apache.tika.parser.DefaultParser">
+ <parser-exclude class="org.apache.tika.parser.ocr.TesseractOCRParser"/>
+ </parser>
+ <parser class="org.apache.tika.parser.ocr.TesseractOCRParser">
+ <params>
+ <param name="language" type="string">eng+ara+spa+fra+por</param>
+ </params>
+ </parser>
+ </parsers>
+</properties>

lib/app.rb

@@ -191,6 +191,30 @@ class App < Sinatra::Base
  respond_with_error e
  end
 
+ #
+ # Detect document language
+ #
+ # POST params:
+ # file - the file to detect language
+ post '/detect-language' do
+ begin
+ unless params[:file]
+ return respond 400, "missing file parameter"
+ end
+
+ unless params[:file].respond_to?(:fetch) and params[:file].fetch(:tempfile, nil).respond_to?(:read)
+ return respond 400, "invalid file parameter"
+ end
+
+ body = params[:file][:tempfile].read
+ content = Converter.new(logger: @logger).convert_file('detect-language', body)
+ content_type content.mime_type
+ content
+ rescue StandardError => e
+ respond_with_error e
+ end
+ end
+
  # Legacy method to convert files
  # Brought over from Heathen
  #

lib/heathen/processor_methods/detect_language.rb

@@ -0,0 +1,19 @@
+# frozen_string_literal: true
+
+module Heathen
+ class Processor
+ def detect_language
+ expect_mime_type 'application/pdf'
+
+ executioner.execute(
+ Colore::C_.tika_path,
+ "--config=#{File.expand_path('../../config/tika.yml', __dir__)}",
+ '--language',
+ job.content_file,
+ binary: true
+ )
+
+ job.content = executioner.stdout
+ end
+ end
+end

lib/heathen/task.rb

@@ -103,3 +103,7 @@ def task_key(action, mime_type)
 Heathen::Task.register 'doc', '.*' do
  perform_task 'msoffice'
 end
+
+Heathen::Task.register 'detect-language', '.*' do
+ perform_task 'detect_language'
+end

spec/heathen/processor_methods/detect_language_spec.rb

@@ -0,0 +1,20 @@
+# frozen_string_literal: true
+
+require 'spec_helper'
+
+describe Heathen::Processor do
+ let(:content) { File.read(fixture('heathen/quickfox.pdf')) }
+ let(:job) { Heathen::Job.new 'foo', content, 'en' }
+ let(:processor) { described_class.new job: job, logger: Logger.new($stderr) }
+
+ after do
+ processor.clean_up
+ end
+
+ context '#detect_language' do
+ it 'detects input file language' do
+ processor.detect_language
+ expect(job.content).to eq 'en'
+ end
+ end
+end