arquivo 0.1.4

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 925dc8622c67a80de14421206ce7c8ab1287785421cfa218acf84b34534a55cc
+  data.tar.gz: a0f7b4964c7d85f13a95e7a9dfde0d40fb7794dd523bfd208407c399450bb05d
+SHA512:
+  metadata.gz: 4a15ce5b4d3514c7e9648fc6e73321387e93990b27f4065e8ec41d33d5643262764ed1bf4c956d969cdd730814db4be766b233d9e3b0a5729759c51ec381a3de
+  data.tar.gz: a75b8f9aa5d2da504d58770c394b8340e3c2db51c77126a10a2d20619e6080c884506758e83a18a477d6db654cb9e9e82c5f3dc35714f3e4790f6a5c6186cda2

data/.gitignore

@@ -0,0 +1,8 @@
+/.bundle/
+/.yardoc
+/_yardoc/
+/coverage/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/

data/Gemfile

@@ -0,0 +1,6 @@
+source "https://rubygems.org"
+
+git_source(:github) {|repo_name| "https://github.com/#{repo_name}" }
+
+# Specify your gem's dependencies in arquivo.gemspec
+gemspec

data/Gemfile.lock

@@ -0,0 +1,77 @@
+PATH
+  remote: .
+  specs:
+    arquivo (0.1.4)
+      fastimage (~> 2.1)
+      google-api-client (~> 0.34)
+      pdf-reader (~> 2.3)
+      thor (~> 0.1)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    Ascii85 (1.0.3)
+    addressable (2.7.0)
+      public_suffix (>= 2.0.2, < 5.0)
+    afm (0.2.2)
+    declarative (0.0.10)
+    declarative-option (0.1.0)
+    faraday (0.17.1)
+      multipart-post (>= 1.2, < 3)
+    fastimage (2.1.7)
+    google-api-client (0.36.0)
+      addressable (~> 2.5, >= 2.5.1)
+      googleauth (~> 0.9)
+      httpclient (>= 2.8.1, < 3.0)
+      mini_mime (~> 1.0)
+      representable (~> 3.0)
+      retriable (>= 2.0, < 4.0)
+      signet (~> 0.12)
+    googleauth (0.10.0)
+      faraday (~> 0.12)
+      jwt (>= 1.4, < 3.0)
+      memoist (~> 0.16)
+      multi_json (~> 1.11)
+      os (>= 0.9, < 2.0)
+      signet (~> 0.12)
+    hashery (2.1.2)
+    httpclient (2.8.3)
+    jwt (2.2.1)
+    memoist (0.16.2)
+    mini_mime (1.0.2)
+    multi_json (1.14.1)
+    multipart-post (2.1.1)
+    os (1.0.1)
+    pdf-reader (2.4.0)
+      Ascii85 (~> 1.0.0)
+      afm (~> 0.2.1)
+      hashery (~> 2.0)
+      ruby-rc4
+      ttfunk
+    public_suffix (4.0.1)
+    rake (10.5.0)
+    representable (3.0.4)
+      declarative (< 0.1.0)
+      declarative-option (< 0.2.0)
+      uber (< 0.2.0)
+    retriable (3.1.2)
+    ruby-rc4 (0.1.5)
+    signet (0.12.0)
+      addressable (~> 2.3)
+      faraday (~> 0.9)
+      jwt (>= 1.5, < 3.0)
+      multi_json (~> 1.10)
+    thor (0.20.3)
+    ttfunk (1.5.1)
+    uber (0.1.0)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  arquivo!
+  bundler (~> 1.17)
+  rake (~> 10.0)
+
+BUNDLED WITH
+   1.17.2

data/LICENSE.txt

@@ -0,0 +1,21 @@
+The MIT License (MIT)
+
+Copyright (c) 2019 TODO: Write your name
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.

data/README.md

@@ -0,0 +1,39 @@
+# Arquivo
+
+Processa documentos do condominio ph1341c118 para arquivo.
+
+## Installation
+
+Add this line to your application's Gemfile:
+
+```ruby
+gem 'arquivo'
+```
+
+And then execute:
+
+    $ bundle
+
+Or install it yourself as:
+
+    $ gem install arquivo
+
+## Usage
+
+    $ arquivo dir PASTA       # processa faturas/recibos/extratos/minutas
+    $ arquivo pdf FILE        # processa extratos ou faturas
+    $ arquivo help [COMMAND]  # Describe available commands or one specific command
+
+## Development
+
+After checking out the repo, run `bin/setup` to install dependencies. You can also run `bin/console` for an interactive prompt that will allow you to experiment.
+
+To install this gem onto your local machine, run `bundle exec rake install`. To release a new version, update the version number in `version.rb`, and then run `bundle exec rake release`, which will create a git tag for the version, push git commits and tags, and push the `.gem` file to [rubygems.org](https://rubygems.org).
+
+## Contributing
+
+Bug reports and pull requests are welcome on GitHub at https://github.com/[USERNAME]/arquivo.
+
+## License
+
+The gem is available as open source under the terms of the [MIT License](https://opensource.org/licenses/MIT).

data/Rakefile

@@ -0,0 +1,2 @@
+require "bundler/gem_tasks"
+task :default => :spec

data/arquivo.gemspec

@@ -0,0 +1,39 @@
+# frozen_string_literal: true
+
+lib = File.expand_path('lib', __dir__)
+$LOAD_PATH.unshift(lib) unless $LOAD_PATH.include?(lib)
+require 'arquivo/version'
+
+Gem::Specification.new do |spec|
+  spec.name          = 'arquivo'
+  spec.version       = Arquivo::VERSION
+  spec.authors     = ['Hernâni Rodrigues Vaz']
+  spec.email       = ['hernanirvaz@gmail.com']
+  spec.homepage    = 'https://github.com/ph1341c118/arquivo'
+
+  spec.summary       = 'Write a short summary, because RubyGems requires one.'
+  spec.description   = ' Write a longer description or delete this line.'
+  spec.license       = 'MIT'
+
+  spec.metadata['homepage_uri'] = spec.homepage
+  spec.metadata['yard.run'] = 'yard'
+
+  # Specify which files should be added to the gem when it is released.
+  # The `git ls-files -z` loads the files in the
+  # RubyGem that have been added into git.
+  spec.files = Dir.chdir(File.expand_path(__dir__)) do
+    `git ls-files -z`.split("\x0")
+                     .reject { |f| f.match(%r{^(test|spec|features)/}) }
+  end
+  spec.bindir        = 'exe'
+  spec.executables   = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
+  spec.require_paths = ['lib']
+
+  spec.add_development_dependency 'bundler', '~> 1.17'
+  spec.add_development_dependency 'rake', '~> 10.0'
+
+  spec.add_dependency 'fastimage', '~> 2.1'
+  spec.add_dependency 'google-api-client', '~> 0.34'
+  spec.add_dependency 'pdf-reader', '~> 2.3'
+  spec.add_dependency 'thor', '~> 0.1'
+end

data/bin/console

@@ -0,0 +1,14 @@
+#!/usr/bin/env ruby
+
+require "bundler/setup"
+require "arquivo"
+
+# 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(__FILE__)

data/bin/setup

@@ -0,0 +1,8 @@
+#!/usr/bin/env bash
+set -euo pipefail
+IFS=$'\n\t'
+set -vx
+
+bundle install
+
+# Do any other automated setup that you need to do here

data/exe/arquivo

@@ -0,0 +1,7 @@
+#!/usr/bin/env ruby
+# frozen_string_literal: true
+
+# require 'arquivo'
+require '/home/c118/ruby/arquivo/lib/arquivo.rb'
+
+Arquivo::CLI.start(ARGV)

data/lib/arquivo.rb

@@ -0,0 +1,56 @@
+# frozen_string_literal: true
+
+require 'thor'
+# require 'arquivo/version'
+# require 'arquivo/extrato'
+# require 'arquivo/pdf'
+# require 'arquivo/dir'
+# require 'arquivo/jpg'
+require '/home/c118/ruby/arquivo/lib/arquivo/version.rb'
+require '/home/c118/ruby/arquivo/lib/arquivo/extrato.rb'
+require '/home/c118/ruby/arquivo/lib/arquivo/pdf.rb'
+require '/home/c118/ruby/arquivo/lib/arquivo/dir.rb'
+require '/home/c118/ruby/arquivo/lib/arquivo/jpg.rb'
+
+module Arquivo
+  class Error < StandardError; end
+
+  # size limit for trim attempt
+  LT = 9000
+
+  # A4 page (8.27x11.69) inches
+  X4 = 8.27
+  Y4 = 11.69
+
+  # CLI para analisar/processar documentos c118
+  class CLI < Thor
+    desc 'pdf FILE', 'processa extratos ou faturas'
+    def pdf(file)
+      return unless File.ftype(file) == 'file'
+
+      f = C118pdf.new(file)
+      return unless f.processa_extrato?
+
+      system "mkdir -p #{f.base}"
+      # extrato contem conta c118
+      if f.extrato?
+        f.processa_extrato(0)
+      else
+        f.split
+      end
+    end
+
+    desc 'dir PASTA', 'processa faturas/recibos/extratos/minutas'
+    option :fuzz, type: :numeric, default: 29,
+                  desc: 'fuzziness para corte das imagens no pdf'
+    option :quality, type: :numeric, default: 15,
+                     desc: 'qualidade das imagens no pdf'
+    def dir(fdir)
+      return unless File.ftype(fdir) == 'directory'
+
+      system 'mkdir -p tmp/zip'
+      C118dir.new(fdir).processa_pasta(options)
+      # system 'rm -rf tmp'
+    end
+  end
+end

data/lib/arquivo/dir.rb

@@ -0,0 +1,121 @@
+# frozen_string_literal: true
+
+require 'google/apis/sheets_v4'
+require 'googleauth'
+require 'googleauth/stores/file_token_store'
+
+# ordenacao c118 dos documentos
+class Array
+  def c118_ordena
+    sort do |a, b|
+      # processa pela ordem <st2>-<st1>
+      c = File.basename(a, '.???')
+      d = File.basename(b, '.???')
+      c[/(\w+)-(\w+)/, 2] + c[/(\w+)-(\w+)/, 1] <=>
+        d[/(\w+)-(\w+)/, 2] + d[/(\w+)-(\w+)/, 1]
+    end
+  end
+end
+
+module Arquivo
+  # analisar/processar pasta
+  class C118dir < Enumerator
+    # @return [Enumerator] lista ordenada items dentro duma pasta
+    attr_reader :items
+    # @return [String] documento c118
+    attr_reader :item
+    # @return [Hash] dados (faturas/recibos) de c118-contas
+    attr_reader :dados
+
+    # @return [String] base do documento
+    attr_reader :base
+
+    # @return [C118dir] documentos c118
+    def initialize(pasta)
+      @items = Dir.glob(File.join(pasta, '*')).each
+      @base = File.basename(pasta, File.extname(pasta)).downcase +
+              Date.today.strftime('%Y%m%d')
+      obter_dados(pasta)
+    end
+
+    def obter_dados(dir)
+      return unless /factura/i.match?(dir) ||
+                    /recibo/i.match?(dir) ||
+                    dados.empty?
+
+      # obtem dados (faturas/recibos) da sheet c118-contas
+      id = '1PbiMrtTtqGztZMhe3AiJbDS6NQE9o3hXebnQEFdt954'
+      sh = (/factura/i.match?(dir) ? 'rft' : 'rrc') + '!A2:E'
+      @dados = c118_sheets.get_spreadsheet_values(id, sh).values
+                          .group_by { |k| k[0][/\w+/] }
+    rescue StandardError
+      @dados = {}
+    end
+
+    # assegura credenciais validas, obtidas dum arquivo de credencias
+    #
+    # @return [Google::Apis::SheetsV4::SheetsService] c118 sheets_v4
+    def c118_sheets
+      p = '/home/c118/c118-'
+      # file obtido console.cloud.google.com/apis OAuth 2.0 client IDs
+      i = Google::Auth::ClientId.from_file("#{p}credentials.json")
+      s = Google::Apis::SheetsV4::AUTH_SPREADSHEETS_READONLY
+      f = Google::Auth::Stores::FileTokenStore.new(file: "#{p}token.yaml")
+      z = Google::Auth::UserAuthorizer.new(i, s, f)
+
+      sheets = Google::Apis::SheetsV4::SheetsService.new
+      sheets.client_options.application_name = 'c118-arquivo'
+      sheets.authorization = z.get_credentials('default') ||
+                             new_credentials(z, 'urn:ietf:wg:oauth:2.0:oob')
+      sheets
+    end
+
+    # inicializar OAuth2 authorization abrindo URL e copiando novo codigo
+    #
+    # @return [Google::Auth::UserAuthorizer] OAuth2 credentials
+    def new_credentials(aut, oob)
+      puts 'Open URL and copy code after authorization',
+           aut.get_authorization_url(base_url: oob)
+      aut.get_and_store_credentials_from_code(user_id: 'default',
+                                              code: 'codigo aqui',
+                                              base_url: oob)
+    end
+
+    # @return [String] texto duma pagina pdf
+    def next_item
+      @item = items.next
+    rescue StopIteration
+      @item = nil
+    end
+
+    def processa_pasta(options)
+      return unless next_item
+
+      if File.ftype(item) == 'directory'
+        C118dir.new(item).processa_pasta(options)
+      else
+        processa_file(options)
+        processa_pasta(options)
+        processa_fim
+      end
+    end
+
+    def processa_fim
+      system "rm -f #{base}.*;" \
+             "pdftk tmp/stamped*.pdf cat output #{base}.pdf;cd tmp/zip;" \
+             "tar cf ../../#{base}.tar *.pdf;" \
+             "gzip --best ../../#{base}.tar;"
+      # 'rm -f *.pdf ../*.pdf'
+    end
+
+    def processa_file(options)
+      case File.extname(item).downcase
+      when '.mp3' then puts 'mp3'
+      when '.jpg' then C118jpg.new(item).processa_jpg(options, dados)
+      when '.pdf' then C118pdf.new(item).processa_pdf(options, dados)
+      else
+        puts "erro: #{item} so posso processar mp3, jpg, pdf"
+      end
+    end
+  end
+end

data/lib/arquivo/extrato.rb

@@ -0,0 +1,130 @@
+# frozen_string_literal: true
+
+require 'pdf-reader'
+
+module Arquivo
+  # analisar/processar pdf
+  class C118pdf < String
+    # @return [String] nome do documento
+    attr_reader :file
+    # @return [String] extensao do documento
+    attr_reader :ext
+    # @return [String] base do documento
+    attr_reader :base
+
+    # @return [String] texto duma pagina pdf
+    attr_reader :page
+    # @return [String] base extrato processado
+    attr_reader :nome
+    # @return [String] list paginas extrato processado
+    attr_reader :list
+
+    # @return [String] key do documento ft????/rc????/ex??0??/sc??????
+    attr_reader :key
+    # @return [Numeric] tamanho do pdf
+    attr_reader :size
+
+    # @return [C118jpg] scanned jpg em processamento
+    attr_reader :pjpg
+    # @return [C118pdf] pdf em processamento
+    attr_reader :ppdf
+
+    # @return [C118pdf] pdf c118
+    def initialize(fpdf)
+      @file = fpdf
+      @ext = File.extname(fpdf).downcase
+      @base = File.basename(fpdf, File.extname(fpdf)).downcase
+
+      @key = @base[/\w+/]
+      @size = File.size(fpdf)
+
+      @ppdf = self
+    end
+
+    def c118_gs
+      # filtrar images para scq e extratos
+      fi = /^[se]/i.match?(key.to_s) ? ' -dFILTERIMAGE' : ''
+
+      'gs -sDEVICE=pdfwrite ' \
+        '-dNOPAUSE -dBATCH -dQUIET ' \
+        '-sPAPERSIZE=a4 -dFIXEDMEDIA -dPDFFitPage ' \
+        '-dPDFSETTINGS=/screen -dDetectDuplicateImages ' \
+        '-dColorImageDownsampleThreshold=1 ' \
+        '-dGrayImageDownsampleThreshold=1 ' \
+        '-dMonoImageDownsampleThreshold=1' + fi
+    end
+
+    def processa_extrato?
+      return true if !File.exist?(base) &&
+                     File.exist?(file) && ext == '.pdf' &&
+                     first_page
+
+      if File.exist?(base)
+        puts "erro: #{base} pasta ja existe"
+      else
+        puts "erro: #{file} nao consigo obter primeira pagina do PDF"
+      end
+      false
+    end
+
+    def processa_extrato(cnt)
+      cnt += 1
+      @list += ',' + cnt.to_s if c118_conta?
+      if next_page
+        faz_extrato if extrato?
+        processa_extrato(cnt)
+      else
+        faz_extrato
+      end
+    end
+
+    def extrato?
+      c118_conta? && page.match?(/extrato +combinado/i)
+    end
+
+    def faz_extrato
+      system "#{c118_gs} " \
+        "-sOutputFile=#{base}/#{nome}-extrato.pdf " \
+        "-sPageList=#{list[1..-1]} \"#{file}\" 1>/dev/null 2>&1"
+      puts "#{nome}-extrato"
+      base_extrato
+    end
+
+    def c118_conta?
+      page.include?('45463760224')
+    end
+
+    # @return [PDF::Reader] leitor pdf
+    def rpdf
+      @rpdf ||= PDF::Reader.new(file).pages.lazy
+    rescue StandardError
+      @rpdf = nil
+    end
+
+    # @return [String] texto duma pagina pdf
+    def next_page
+      @page = rpdf.next.text
+    rescue StopIteration
+      @page = nil
+    end
+
+    def base_extrato
+      return false unless page
+
+      @list = ''
+      n = page.scan(%r{N\. *(\d+)/(\d+)}).flatten
+      @nome = "ex#{n[0].to_s[/\d{2}$/]}#{n[1]}"
+    rescue StandardError
+      @nome = nil
+    end
+
+    def first_page
+      rpdf && next_page && base_extrato
+    end
+
+    def split
+      system "pdftk #{file} burst output #{base}/pg%04d-#{base}.pdf;" \
+             "rm -f #{base}/*.txt"
+    end
+  end
+end

data/lib/arquivo/jpg.rb

@@ -0,0 +1,77 @@
+# frozen_string_literal: true
+
+require 'fastimage'
+
+module Arquivo
+  # analisar/processar pdf
+  class C118jpg < String
+    # @return [String] nome do ficheiro
+    attr_reader :file
+    # @return [String] extensao do ficheiro
+    attr_reader :ext
+    # @return [String] base do ficheiro
+    attr_reader :base
+
+    # @return [String] key do documento ft????/rc????/ex??0??/sc??????
+    attr_reader :key
+    # @return [Numeric] tamanho do jpg
+    attr_reader :size
+
+    # @return [C118jpg] jpg c118
+    def initialize(fjpg)
+      @file = fjpg
+      @ext = File.extname(fjpg).downcase
+      @base = File.basename(fjpg, File.extname(fjpg)).downcase
+
+      @key = @base[/\w+/]
+      @size = File.size(fjpg)
+    end
+
+    def processa_jpg(options, dados)
+      trim(options).jpg2pdf(options).final(dados[key])
+    end
+
+    def trim(options)
+      f = options[:fuzz]
+      h = {}
+      # obter jpg menor triming borders ao maximo
+      while f >= 1
+        system "convert \"#{file}\" -fuzz #{f}% -trim +repage " \
+               "tmp/#{base}#{f}.jpg "
+        h[f] = File.size("tmp/#{base}#{f}.jpg")
+        f -= 4
+      end
+      m = h.min_by { |_, v| v }
+      m[1].between?(LT, size) ? C118jpg.new("tmp/#{base}#{m[0]}.jpg") : self
+    end
+
+    def jpg2pdf(options)
+      o = "tmp/#{base}.pdf"
+
+      # Center image on a larger canvas (with a size given by "-extent").
+      x, y = scale_xy
+      system "convert \"#{file}\" -units PixelsPerInch " \
+             "-gravity center -extent #{x}x#{y} " \
+             "-quality #{options[:quality]}% -compress jpeg -format pdf " \
+             "#{o} 1>/dev/null 2>&1"
+
+      # devolve pdf processado a partir de jpg
+      C118pdf.new(o)
+    end
+
+    def scale_xy
+      # Determine image dimensions in pixels.
+      x, y = FastImage.size(file)
+
+      # Calculate image density (in dpi) needed to fit the image
+      # with a 5% border all around an A4 page.
+      # Factor 1.1 creates 2*5% borders,
+      # Use the higher density to prevent exceeding the required fit.
+      density = [x / X4 * 1.04, y / Y4 * 1.04].max
+
+      # Calculate canvas dimensions in pixels.
+      # (Canvas is an A4 page with the calculated density.)
+      [X4 * density, Y4 * density]
+    end
+  end
+end

data/lib/arquivo/pdf.rb

@@ -0,0 +1,118 @@
+# frozen_string_literal: true
+
+require 'i18n'
+I18n.config.available_locales = :pt
+
+module Arquivo
+  # analisar/processar pdf
+  class C118pdf < String
+    def processa_pdf(options, dados)
+      @ppdf = pjpg.trim(options).jpg2pdf(options) if jpg?
+      @ppdf = self if size < ppdf.size
+      ppdf.final(dados[key])
+    end
+
+    def marca
+      # produzir pdf com stamp
+      o = "tmp/stamped-#{base[/-(\w+)/, 1]}-#{key}.pdf"
+      t = '2 2 moveto /Ubuntu findfont 7 scalefont ' \
+           "setfont (#{base}) show"
+      system "#{c118_gs} -sOutputFile=tmp/stamp-#{key}.pdf -c \"#{t}\";\
+            pdftk tmp/zip/#{base}.pdf stamp tmp/stamp-#{key}.pdf output #{o}"
+
+      C118pdf.new(o)
+    end
+
+    def final(kda)
+      c118_stamp(kda)
+      o = "tmp/zip/#{base}.pdf"
+
+      if key[0] == 'r'
+        # google producess better && smaller pdf then c118_gs
+        system "cp \"#{file}\" #{o}"
+      else
+        system "#{c118_gs} -sOutputFile=#{o} \"#{file}\" 1>/dev/null 2>&1"
+      end
+      @ppdf = C118pdf.new(o) if File.size(o) <= size
+      ppdf.marca
+    end
+
+    def base_stamp(kda)
+      @base = key + '-' + rubrica(kda) + digest
+    end
+
+    def vnum_stamp(kda)
+      n = kda.inject(0) { |s, e| s + e[4].to_i }.abs
+      @base += '-' + format('%<valor>06d', valor: n)
+    end
+
+    def numb_stamp(kda)
+      d = kda.group_by { |e| e[0][/-(mb\d{8})/, 1] }
+             .keys.join('-')
+      @base += '-' + d unless d.size.zero?
+    end
+
+    def sfim_stamp(kda)
+      if key[0] == 'f'
+        kda.group_by { |e| e[2] }
+      else
+        kda.group_by { |e| e[2][/\d{4}-(\w{3})/, 1] }
+      end.keys.filter { |e| e }.join('-')
+    end
+
+    def c118_stamp(kda)
+      base_stamp(kda)
+      return unless kda
+
+      vnum_stamp(kda)
+      numb_stamp(kda)
+      d = sfim_stamp(kda)
+      return if d.empty?
+
+      @base += '-' + I18n.transliterate(d, locale: :pt)
+                         .gsub(/[ [[:punct:]]]/, '-')
+    end
+
+    def rubrica(kda)
+      if kda
+        # rubrica obtida da sheet arquivo
+        # isto permite fazer re-classificacoes de documentos
+        if key[0] == 'f'
+          kda.group_by { |e| e[1] }
+        else
+          kda.group_by { |e| e[3][/\w+/] }
+        end.keys.join('-')
+      else
+        base[/-(\w+)/, 1]
+      end
+    end
+
+    def digest
+      '-' + `sha256sum #{file}`[/\w+/]
+    end
+
+    def jpg?
+      return false if key[0] == 'r'
+
+      o = "tmp/#{base}.txt"
+      # teste scanned pdf (se contem texto -> not scanned)
+      system "pdftotext -q -eol unix -nopgbrk \"#{file}\" #{o}"
+      return false if File.size?(o)
+
+      @pjpg = extract_jpg
+    end
+
+    def extract_jpg
+      o = "tmp/#{base}3.jpg"
+
+      system "pdfimages -q -j #{file} tmp/#{base}2"
+      # nem sempre as imagens sao jpg
+      # somente utilizar a primeira
+      g = Dir.glob("tmp/#{base}2*.???")
+      system "convert #{g[0]} #{o} 1>/dev/null 2>&1"
+      return unless File.size(o) > LT
+
+      C118jpg.new(o)
+    end
+  end
+end

data/lib/arquivo/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module Arquivo
+  VERSION = '0.1.4'
+end

metadata

@@ -0,0 +1,146 @@
+--- !ruby/object:Gem::Specification
+name: arquivo
+version: !ruby/object:Gem::Version
+  version: 0.1.4
+platform: ruby
+authors:
+- Hernâni Rodrigues Vaz
+autorequire: 
+bindir: exe
+cert_chain: []
+date: 2019-12-14 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: bundler
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.17'
+- !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: fastimage
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.1'
+- !ruby/object:Gem::Dependency
+  name: google-api-client
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.34'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.34'
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.3'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '2.3'
+- !ruby/object:Gem::Dependency
+  name: thor
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '0.1'
+description: " Write a longer description or delete this line."
+email:
+- hernanirvaz@gmail.com
+executables:
+- arquivo
+extensions: []
+extra_rdoc_files: []
+files:
+- ".gitignore"
+- Gemfile
+- Gemfile.lock
+- LICENSE.txt
+- README.md
+- Rakefile
+- arquivo.gemspec
+- bin/console
+- bin/setup
+- exe/arquivo
+- lib/arquivo.rb
+- lib/arquivo/dir.rb
+- lib/arquivo/extrato.rb
+- lib/arquivo/jpg.rb
+- lib/arquivo/pdf.rb
+- lib/arquivo/version.rb
+homepage: https://github.com/ph1341c118/arquivo
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/ph1341c118/arquivo
+  yard.run: yard
+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: []
+rubygems_version: 3.0.3
+signing_key: 
+specification_version: 4
+summary: Write a short summary, because RubyGems requires one.
+test_files: []