nameday_vvc_pdf_extractor 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 9fe97f35bc0664cff59f3654a269aded15746d1ea09d54de83a2226cc32ef65e
+  data.tar.gz: c4bffc353a1ef7194f598bf5201c38f0e1363c2166c80cde6b7e9e6f14e3707f
+SHA512:
+  metadata.gz: 953a5af7e247352891d97af1c72090bb40465590315dec2570e2a3b11abd4ee22315de820e729eef0551b5e3745e5d7dceaef8b0f3e784bb9b7cece0b87ed4e6
+  data.tar.gz: 18088a356cd9d77766012de04b536002503412f157fbdab41dbacf31a05f3f02f0ae0369b0e77e283d8ec9304096cbcc1aeabf5fcdadda1deee9b650555069e9

data/lib/nameday_vvc_pdf_extractor.rb

@@ -0,0 +1,87 @@
+# frozen_string_literal: true
+
+require "pdf-reader"
+require "date"
+
+module Nameday
+  class VvcPdfExtractor
+    EMPTY_NAMEDAY_REGEXP = /\p{Pd}/ # Unicode category "Punctuation: Dash"
+    TEXT_ROW_DELIMITER = "\n"
+    MONTH_NAMES = %w[
+      -
+      JANVĀRIS
+      FEBRUĀRIS
+      MARTS
+      APRĪLIS
+      MAIJS
+      JŪNIJS
+      JŪLIJS
+      AUGUSTS
+      SEPTEMBRIS
+      OKTOBRIS
+      NOVEMBRIS
+      DECEMBRIS
+    ].freeze
+
+    attr_reader :output
+
+    def initialize
+      @output = {}
+    end
+
+    def read_pdf(file_name)
+      @pdf_reader = ::PDF::Reader.new(file_name)
+    end
+
+    def extract
+      raise("PDF not opened!") unless @pdf_reader
+      process_pdf
+      output
+    end
+
+    private
+
+    def prepare_output
+      @output = {}
+
+      # 2016 was leap year
+      Date.new(2016).step(Date.new(2017)) do |date|
+        @output[date.month] ||= {}
+        @output[date.month][date.day] = nil
+      end
+    end
+
+    def process_pdf
+      return unless @output == {}
+      prepare_output
+
+      @current_month_index = nil
+      @pdf_reader.pages.each do |page|
+        process_pdf_page(page)
+      end
+    end
+
+    def process_pdf_page(pdf_page)
+      text_rows = pdf_page.text.split(TEXT_ROW_DELIMITER).map!(&:strip)
+      text_rows.each do |text_row|
+        next if text_row.empty?
+
+        if (new_month_index = MONTH_NAMES.index(text_row))
+          @current_month_index = new_month_index
+        elsif text_row.match?(/^\d+\./)
+          process_nameday_value(text_row)
+        end
+      end
+    end
+
+    def process_nameday_value(text_row)
+      nameday_data = text_row.split(" ")
+      day = nameday_data[0].to_i # Ignores ending dot
+      nameday_data[1..-1].each do |name|
+        next if name.match?(EMPTY_NAMEDAY_REGEXP)
+        @output[@current_month_index][day] ||= []
+        @output[@current_month_index][day] << name.tr(",", "")
+      end
+    end
+  end
+end

metadata

@@ -0,0 +1,58 @@
+--- !ruby/object:Gem::Specification
+name: nameday_vvc_pdf_extractor
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- Aleksandrs Ļedovskis
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2018-10-06 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  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'
+description: 
+email: aleksandrs@ledovskis.lv
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- lib/nameday_vvc_pdf_extractor.rb
+homepage: https://github.com/aleksandrs-ledovskis/nameday-vvc-pdf-extractor
+licenses:
+- BSD-3-Clause
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - "~>"
+    - !ruby/object:Gem::Version
+      version: '2.0'
+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: Nameday data extraction from Valsts valodas centrs PDF
+test_files: []