bank_statement_parser 0.0.5 → 0.0.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 2a965f6dc78b631995b0222f5a04602511720ca5
-  data.tar.gz: 662d867bdf2754e22a552824131abbdb5c800ba4
+  metadata.gz: fda2797823d21a6f4f8b438c59cd7eb1cfd994a0
+  data.tar.gz: d98654067e0e2cf05300324b8b73066ea1aad925
 SHA512:
-  metadata.gz: 58245edba68a4434c878e5ec6afbf72e4002cc7d0f79a63a6da6c34f7f04dfb7615054fd7e9f8b4004580f274727cc1899259235236ca72c3f5959967f758ca4
-  data.tar.gz: d97413e5f9611567f75b01a74ebccb38fcaf1d0a3f6f70e6248d12801a37e5120dd8a85ad59b8749bfb7d03b4c95e25cf5061d138fa476637720e8f2588949f6
+  metadata.gz: 670ac0361e50588072428059ec7c2bc20d6a53e310ed9eed4a91f4fed392acec6e5fc9627f07009b24f6d0a7b126b5e2ef15e40ebb98131b04bdd86061b3b87a
+  data.tar.gz: 8308156691543687651f998b3863bba3db5e4d875b1da7090ded53762d47efe0819250efa311a9af091f9e5516b5c6c345663cef47cce9db7da6d761a4d39378

data/lib/bank_statement_parser/base.rb

@@ -19,10 +19,14 @@ module BankStatementParser
 
   # Base class for statement parsers
   #
-  # Subclasses must implement the following instance methods
+  # Subclasses **must** implement the following instance methods
   #
-  # * void reset()
   # * bool handle_line(String line)
+  #
+  # Subclasses *may* override the following instance methods, but **must**
+  # remember to call the base class method from the override
+  #
+  # * void reset()
   class Base
 
     require 'fileutils.rb'
@@ -40,8 +44,8 @@ module BankStatementParser
 
       reset
 
-      # Grab the full text file content, and re-encode to ASCII
-      full_text = ascii_filter(File.read(path))
+      # Grab the full text file content (utf-8)
+      full_text = File.read(path)
 
       # Process each line in turn
       full_text.split("\n").each do |line|
@@ -69,38 +73,5 @@ module BankStatementParser
       @records = []
     end
 
-    private
-
-    # Filter the specified text, re-encoding to ASCII
-    def self.ascii_filter text
-      rv = text
-
-      # Squash some Unicode character categories
-      #
-      # {Zs} necessary to match statement date line
-      # {Pc} necessary to match statement record lines
-      rv.gsub!(/[\p{Zs}\p{Pc}]/, " ")
-
-      # Replace Unicode soft hyphens
-      rv.gsub!(/\u00ad/, "-")
-
-      # Replace... well, who knows just *what* this is...
-      rv.gsub!(/\u0a0c/, " ")
-
-      # Re-encode to ASCII
-      encoding_options = {
-        invalid:           :replace, # Replace invalid byte sequences
-        undef:             :replace, # Replace anything not defined in ASCII
-        replace:           '',       # Use a blank for those replacements
-        universal_newline: true      # Always break lines with \n
-      }
-      rv = rv.encode(Encoding.find('US-ASCII'), encoding_options)
-
-      # Replace ASCII form feed characters
-      rv.gsub!(/\f/, "\n")
-
-      rv
-    end
-
   end
 end

data/lib/bank_statement_parser/hsbc.rb

@@ -17,6 +17,7 @@
 
 require 'date'
 require 'bank_statement_parser/base'
+require 'bank_statement_parser/utils'
 module BankStatementParser
 
   # Parser for HSBC bank statements
@@ -27,6 +28,9 @@ module BankStatementParser
     # Returns true if parsing should continue; false to terminate the parser
     def handle_line line
 
+      # Re-encode line to ASCII
+      line = Utils.ascii_filter(line)
+
       # Skip blank lines
       return true if line =~ /\A\s*\z/
 

data/lib/bank_statement_parser/utils.rb

@@ -0,0 +1,55 @@
+# Copyright 2015 Simon Dawson <spdawson@gmail.com>
+
+# This file is part of bank_statement_parser.
+#
+# bank_statement_parser is free software: you can redistribute it and/or modify
+# it under the terms of the GNU General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+#
+# bank_statement_parser is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+# GNU General Public License for more details.
+#
+# You should have received a copy of the GNU General Public License
+# along with bank_statement_parser. If not, see <http://www.gnu.org/licenses/>.
+
+module BankStatementParser
+
+  # Utilities
+  class Utils
+
+    # Filter the specified text, re-encoding to ASCII
+    def self.ascii_filter text
+      rv = text
+
+      # Squash some Unicode character categories
+      #
+      # {Zs} necessary to match statement date line
+      # {Pc} necessary to match statement record lines
+      rv.gsub!(/[\p{Zs}\p{Pc}]/, " ")
+
+      # Replace Unicode soft hyphens
+      rv.gsub!(/\u00ad/, "-")
+
+      # Replace... well, who knows just *what* this is...
+      rv.gsub!(/\u0a0c/, " ")
+
+      # Re-encode to ASCII
+      encoding_options = {
+        invalid:           :replace, # Replace invalid byte sequences
+        undef:             :replace, # Replace anything not defined in ASCII
+        replace:           '',       # Use a blank for those replacements
+        universal_newline: true      # Always break lines with \n
+      }
+      rv = rv.encode(Encoding.find('US-ASCII'), encoding_options)
+
+      # Replace ASCII form feed characters
+      rv.gsub!(/\f/, "\n")
+
+      rv
+    end
+
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: bank_statement_parser
 version: !ruby/object:Gem::Version
-  version: 0.0.5
+  version: 0.0.6
 platform: ruby
 authors:
 - Simon Dawson
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-03-25 00:00:00.000000000 Z
+date: 2015-03-26 00:00:00.000000000 Z
 dependencies: []
 description: A gem for parsing bank statements
 email: spdawson@gmail.com
@@ -20,6 +20,7 @@ files:
 - lib/bank_statement_parser/base.rb
 - lib/bank_statement_parser/hsbc.rb
 - lib/bank_statement_parser/statement_record.rb
+- lib/bank_statement_parser/utils.rb
 homepage: http://rubygems.org/gems/bank_statement_parser
 licenses:
 - GPLv3