pdf_search 0.0.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 5506277019033c54c84b0aeec3deae307b304af0392f17bd7e5f1147feb07ad8
+  data.tar.gz: d0488eefb43bdd4cbba1e9bfc0656eefd3e4ff41762b70d4f1e8dc0558fd73c3
+SHA512:
+  metadata.gz: 8a20e3fffff896a967b395bae72483d99f733bf1bc1c949c3ac0f4426bd066550741c3b9e664ce71b633fb0b4e2f5c34f958123cb758deb181aaabbd5e1b8bd0
+  data.tar.gz: a2555c899aba3123f5f99b985590d75927515044111d8a7556fae92848b6a39dc335f6aa29aa1d6a3e0dada710e2e8e07e0599277240f783faff489c3b52c699

data/bin/pdf_search

@@ -0,0 +1,18 @@
+#!/usr/bin/env ruby 
+require 'pdfsearch'
+require 'webrick'
+
+`sudo service elasticsearch start`
+
+
+gemDir = [File.dirname(__FILE__), '..']
+indexPdfsScriptPath = File.expand_path(File.join(gemDir + ['lib', 'indexPdfs.rb']))
+htmlDir = File.expand_path(File.join(gemDir + ['html']))
+
+
+WEBrick::HTTPServer.new(:Port => 80, :DocumentRoot => htmlDir).start
+
+
+# PdfSearch::Indexer.startDeamon
+
+

data/lib/pdf_dir.rb

@@ -0,0 +1,33 @@
+#encoding: UTF-8
+require 'pdf-reader'
+require 'pry'
+
+module PdfSearch
+  class PdfDir
+	def initialize(dir = '.')
+		@dir = dir
+	end
+
+  	def pdf_file_paths
+            Dir.glob(File.join(File.expand_path(@dir), '*.pdf'))
+  	end
+
+	def each_pdf
+	  Enumerator.new do |e|
+	  	  pdf_file_paths.each do |pdf_file_path|
+	          	e << PDF::Reader.new(pdf_file_path)
+	  	  end
+	  end
+	end
+
+	def each_page
+	  Enumerator.new do |e|
+		each_pdf do |pdf_reader|
+			pdf_reader.pages.each do |page|
+				e << page
+			end
+		end
+	  end
+	end
+  end
+end

data/lib/pdf_index.rb

@@ -0,0 +1,5 @@
+require 'pdfiterator'
+
+PdfIterator.new.traverse_current_directory_pdf_texts do |pdf_text|
+	`echo "#{pdf_text}" >> log/indexPdfs.log`
+end

data/lib/pdf_search.rb

@@ -0,0 +1,5 @@
+require 'pdf_index'
+require 'pdf_dir'
+
+module PdfSearch
+end

metadata

@@ -0,0 +1,48 @@
+--- !ruby/object:Gem::Specification
+name: pdf_search
+version: !ruby/object:Gem::Version
+  version: 0.0.0
+platform: ruby
+authors:
+- Manuel Arno Korfmann
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2010-04-28 00:00:00.000000000 Z
+dependencies: []
+description: Run in any directory containing pdfs using `$ pdf_search`
+email: manu@korfmann.info
+executables:
+- pdf_search
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/pdf_search
+- lib/pdf_dir.rb
+- lib/pdf_index.rb
+- lib/pdf_search.rb
+homepage: https://github.com/banalBI/pdfsearch
+licenses:
+- MIT
+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: 2.7.6
+signing_key: 
+specification_version: 4
+summary: Searching pdfs by leveragin Elasticsearch
+test_files: []