fixed_width_file_parser 0.1.4 → 0.1.5

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 5d247b1668e893c35afb637941e3ca01f1949a82
-  data.tar.gz: 8aed0fef1f981f2ffd7e6a257bf798f21af63e6c
+  metadata.gz: 976efbc15675621fa210269b957a18779104e541
+  data.tar.gz: b7839de06cc4b2596421c79988fe353510c199a8
 SHA512:
-  metadata.gz: 29f528e67ff45166d99ad6295f1715efddc44dfe1caa18440b444fe212dc76c3ec06b599b9da4658f1439508c0f7ea7b1617120cff69aac09c0d72a235a9bf75
-  data.tar.gz: 58d1bed56e38186e6881aba7f62fe4801b06c2c839074a002440df32c8ffd75b61091f8118276c342f698bb283295750fccff5cc20882aa8964168d6661d2ded
+  metadata.gz: de67c84d35c1c8b4927032ac2902ecab46a62f9952f241e33f3e542880222caff2b00854f1b400b7c192bf0f4cc9c68227a0e5effd0bbdafb3b287d110e1c1ce
+  data.tar.gz: 3295067dec03f267224e8781356a2f9403884cfe03cb95156d553862cf2ef1cd573f9bf63ba411888bb598cb08d7b63b37ae36a8b0d7eb835bac8a353e2644cd

data/README.md

@@ -31,14 +31,24 @@ fields = [
   { name: 'middle_initial', position: 11 },
   { name: 'last_name', position: 12..25 }
 ]
+options = {}
 
-FixedWidthFileParser.parse(filepath, fields) do |row|
+FixedWidthFileParser.parse(filepath, fields, options) do |row|
   puts row[:first_name]
   puts row[:middle_initial]
   puts row[:last_name]
 end
 ```
 
+### Tips
+If you need to parse a fixed width file that has the last field set as a variable width field, you can set the position similar to `position: 20..-1`. Setting the end of the range as `-1` will read to the end of that line.
+
+## Options
+|Name|Default Value|Description|
+|---|---|---|
+|force_utf8_encoding|true|Force UTF-8 encoding on lines being parsed. This alleviates `invalid byte sequence in UTF-8` errors thrown when trying to split a string with invalid UTF characters. For more information, view this [article](https://robots.thoughtbot.com/fight-back-utf-8-invalid-byte-sequences).|
+
+
 ## Development
 
 After checking out the repo, run `bin/setup` to install dependencies. Then, run `bin/console` for an interactive prompt that will allow you to experiment.

data/lib/fixed_width_file_parser.rb

@@ -19,7 +19,10 @@ module FixedWidthFileParser
     #   puts row
     # end
 
-  def self.parse(filepath, fields)
+  def self.parse(filepath, fields, options = {})
+    # Set options, or use default
+    force_utf8_encoding = options.fetch(:force_utf8_encoding, true)
+
     # Verify `filepath` is a String
     unless filepath.is_a?(String)
       raise '`filepath` must be a String'
@@ -53,6 +56,13 @@ module FixedWidthFileParser
       # chomp to remove "\n" and "\r\n"
       next if line.chomp.empty?
 
+      # Force UTF8 encoding if force_utf8_encoding is true (defaults to true)
+      if force_utf8_encoding
+        # Handle UTF Invalid Byte Sequence Errors
+        # e.g. https://robots.thoughtbot.com/fight-back-utf-8-invalid-byte-sequences
+        line = line.encode('UTF-8', 'binary', invalid: :replace, undef: :replace, replace: '')
+      end
+
       line_fields = {}
       fields.each do |field|
         line_fields[field[:name].to_sym] = line[ field[:position] ].nil? ? nil :  line[ field[:position] ].strip

data/lib/fixed_width_file_parser/version.rb

@@ -1,3 +1,3 @@
 module FixedWidthFileParser
-  VERSION = "0.1.4"
+  VERSION = "0.1.5"
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: fixed_width_file_parser
 version: !ruby/object:Gem::Version
-  version: 0.1.4
+  version: 0.1.5
 platform: ruby
 authors:
 - Jim Smith
 autorequire: 
 bindir: exe
 cert_chain: []
-date: 2016-07-26 00:00:00.000000000 Z
+date: 2016-07-28 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler