nameday_vvc_pdf_extractor 0.1.1 → 0.1.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 443afb595bb2e7c47350fb02f047bdae5703fadabb3bad7b18573875ebc5ea87
-  data.tar.gz: 61d36adce7e2df9f4f66ff3d0a3e258f184c6cbba47a862558048c2cd78f360a
+  metadata.gz: d4e37438d8abad8fdd52b4cfceacb64358dc2df629ba34f5c1c3b0ebb9673e5f
+  data.tar.gz: e1c2b0e924bf98d906bca47bca2babf889dfe2992778bf372ed3a1134f8e9d1b
 SHA512:
-  metadata.gz: ba2e585871816be38ca58fcdcdce520766203b6ab20860dc280fa287761583071b1d5469ae513d2917aad8aaebab3b0095daf197453a29c9324fe55b75ad3313
-  data.tar.gz: 2284f690cdd3af7dfa87b86b0ee75383416f9700d09c8c6c5d2d57ea7ab1b155ea54c0da07706fe4de051116cb86d3b406fd0421fde743e5f97ef4b41341f494
+  metadata.gz: fcfc82617988a038a37e31495e33e74a54809dbeffe0283b326b2ac0c2feaea4348bc4899c72dd89a0d8561b4efd16980cfb9b2a97b6218157e5ad1dc9f86831
+  data.tar.gz: 1e5c09a644d3efca24b87b9f3672eb18c81ed97f8ad2d43b720b6a5025277c4f5bd539566682b1dca9469d2d8b1dc5936305d8576cbee72ac194d523015c54c2

data/lib/nameday_vvc_pdf_extractor.rb

@@ -4,6 +4,8 @@ require "pdf-reader"
 require "date"
 
 module Nameday
+  # Use this class to extract structured nameday information
+  # from pre-existing VVC PDF file
   class VvcPdfExtractor
     EMPTY_NAMEDAY_REGEXP = /\p{Pd}/ # Unicode category "Punctuation: Dash"
     TEXT_ROW_DELIMITER = "\n"
@@ -26,6 +28,7 @@ module Nameday
     attr_reader :output
 
     def initialize
+      @pdf_reader = nil
       @output = {}
     end
 
@@ -35,6 +38,7 @@ module Nameday
 
     def extract
       raise("PDF not opened!") unless @pdf_reader
+
       process_pdf
       output
     end
@@ -53,24 +57,29 @@ module Nameday
 
     def process_pdf
       return unless @output == {}
+
       prepare_output
 
       @current_month_index = nil
-      @pdf_reader.pages.each do |page|
-        process_pdf_page(page)
+      @pdf_reader.pages.each do |pdf_page|
+        process_pdf_page(pdf_page)
       end
     end
 
     def process_pdf_page(pdf_page)
-      text_rows = pdf_page.text.split(TEXT_ROW_DELIMITER).map!(&:strip)
+      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
+        process_text_row(text_row)
+      end
+    end
+
+    def process_text_row(text_row)
+      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
 
@@ -80,6 +89,7 @@ module Nameday
 
       nameday_data[1].split(",").each do |name|
         next if name.match?(EMPTY_NAMEDAY_REGEXP)
+
         @output[@current_month_index][day] ||= []
         @output[@current_month_index][day] << name.strip
       end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: nameday_vvc_pdf_extractor
 version: !ruby/object:Gem::Version
-  version: 0.1.1
+  version: 0.1.2
 platform: ruby
 authors:
 - Aleksandrs Ļedovskis