Merge branch 'develop'

.gitignore

@@ -1,2 +1,19 @@
 *.gem
 
+/.bundle/
+/.yardoc
+/Gemfile.lock
+/_yardoc/
+/doc/
+/pkg/
+/spec/reports/
+/tmp/
+/vendor/
+*.bundle
+*.so
+*.o
+*.a
+dockercfg.env
+
+mkmf.log
+.idea

Dockerfile

@@ -0,0 +1,8 @@
+FROM brendan6/ruby:2.2.4
+MAINTAINER Chris Sandison <chris@thinkdataworks.com>
+
+ADD . $APP_HOME
+
+RUN bundle install
+
+CMD bundle exec rspec

Gemfile

@@ -0,0 +1,7 @@
+source 'https://rubygems.org'
+
+gemspec
+
+group :development, :test do
+  gem 'pry-byebug'
+end

Gemfile.lock

@@ -0,0 +1,67 @@
+PATH
+  remote: .
+  specs:
+    csv_sniffer (0.2.1)
+
+GEM
+  remote: https://rubygems.org/
+  specs:
+    activesupport (5.2.0)
+      concurrent-ruby (~> 1.0, >= 1.0.2)
+      i18n (>= 0.7, < 2)
+      minitest (~> 5.1)
+      tzinfo (~> 1.1)
+    byebug (10.0.2)
+    coderay (1.1.2)
+    concurrent-ruby (1.0.5)
+    diff-lcs (1.3)
+    factory_girl (4.9.0)
+      activesupport (>= 3.0.0)
+    i18n (1.0.1)
+      concurrent-ruby (~> 1.0)
+    method_source (0.9.0)
+    minitest (5.11.3)
+    pry (0.11.3)
+      coderay (~> 1.1.0)
+      method_source (~> 0.9.0)
+    pry-byebug (3.6.0)
+      byebug (~> 10.0)
+      pry (~> 0.10)
+    rack (2.0.5)
+    rack-test (1.0.0)
+      rack (>= 1.0, < 3)
+    rake (10.5.0)
+    rspec (3.7.0)
+      rspec-core (~> 3.7.0)
+      rspec-expectations (~> 3.7.0)
+      rspec-mocks (~> 3.7.0)
+    rspec-core (3.7.1)
+      rspec-support (~> 3.7.0)
+    rspec-expectations (3.7.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.7.0)
+    rspec-mocks (3.7.0)
+      diff-lcs (>= 1.2.0, < 2.0)
+      rspec-support (~> 3.7.0)
+    rspec-support (3.7.1)
+    thread_safe (0.3.6)
+    tzinfo (1.2.5)
+      thread_safe (~> 0.1)
+
+PLATFORMS
+  ruby
+
+DEPENDENCIES
+  bundler (~> 1.7)
+  csv_sniffer!
+  factory_girl
+  pry-byebug
+  rack
+  rack-test
+  rake (~> 10.0)
+  rspec
+  rspec-core
+  rspec-mocks
+
+BUNDLED WITH
+   1.16.0

README.md

@@ -32,13 +32,14 @@ is_quote_enclosed = CsvSniffer.is_quote_enclosed?("/path/to/some_file.csv") #=>
 has_header = CsvSniffer.has_header?("/path/to/some_file.csv") #=> true
 ```
 
-See [`test_csv_sniffer.rb`](test/test_csv_sniffer.rb) for more examples.
+See [`csv_sniffer_spec.rb`](spec/csv_sniffer_spec.rb) for more examples.
 
 
 ## Tests
 
 ```
-$ rake test
+$ docker build -t csv_sniffer_container .
+$ docker run -t csv_sniffer_container rspec
 ```
 
 

csv_sniffer.gemspec

@@ -1,15 +1,23 @@
-Gem::Specification.new do |s|
-  s.name        = 'csv_sniffer'
-  s.version     = '0.1.2'
-  s.date        = '2015-12-28'
-  s.summary     = "CSV library for heuristic detection of CSV properties"
-  s.description = "CSV Sniffer is a set of functions that allow a user detect the delimiter character in use, whether the values in the CSV file are quote enclosed, whether the file contains a header, and more. The library is intended to detect information to be used as configuration inputs for CSV parsers."
-  s.authors     = ["Tim Ojo"]
-  s.email       = 'ojo.tim@gmail.com'
-  s.homepage    = 'https://github.com/tim-ojo/csv_sniffer'
-  s.license     = 'MIT'
+Gem::Specification.new do |spec|
+  spec.name        = 'csv_sniffer'
+  spec.version     = '0.2.0'
+  spec.date        = '2018-06-15'
+  spec.summary     = "CSV library for heuristic detection of CSV properties"
+  spec.description = "CSV Sniffer is a set of functions that allow a user detect the delimiter character in use, whether the values in the CSV file are quote enclosed, whether the file contains a header, and more. The library is intended to detect information to be used as configuration inputs for CSV parsers."
+  spec.authors     = ["Chris Sandison"]
+  spec.email       = 'chris@thinkdataworks.com'
+  spec.homepage    = 'https://github.com/thinkdataworks/csv_sniffer'
+  spec.license     = 'MIT'
 
-  s.files       = `git ls-files`.split($/)
-  s.test_files  = s.files.grep(/^test/)
-  s.add_development_dependency 'test-unit', '~> 0'
+  spec.files       = `git ls-files`.split($/)
+  spec.test_files  = spec.files.grep(/.*_spec\.rb/)
+
+  spec.add_development_dependency "bundler", "~> 1.7"
+  spec.add_development_dependency "rake", "~> 10.0"
+  spec.add_development_dependency "rspec"
+  spec.add_development_dependency "rspec-core"
+  spec.add_development_dependency "rspec-mocks"
+  spec.add_development_dependency "factory_girl"
+  spec.add_development_dependency "rack"
+  spec.add_development_dependency "rack-test"
 end

lib/csv_sniffer.rb

@@ -3,6 +3,8 @@
 # This class contains functions to heuristically decipher certain information from a CSV file
 class CsvSniffer
 
+    DEFAULT_LINES_TO_READ = 10_000
+
     # Reads the first line of the csv and returns the endline characters used
     #
     # Example:
@@ -11,12 +13,13 @@ class CsvSniffer
     #
     # Arguments:
     #   filepath: (String)
+    #   lines: (int) number of lines to read, default 10,000
 
-    def self.detect_endline(filepath)
+    def self.detect_endline(filepath, lines: DEFAULT_LINES_TO_READ)
       begin
         file = File.open(filepath, binmode: 'rt', encoding: 'bom|utf-8:utf-8')
         # Prevent large files with \r ending from reading the entire contents by limiting
-        file.readline(10_000)[/[\r\n]+/]
+        file.readline(DEFAULT_LINES_TO_READ)[/[\r\n]+/]
       rescue EOFError
         $/
       end
@@ -30,9 +33,10 @@ def self.detect_endline(filepath)
     #
     # Arguments:
     #   filepath: (String)
+    #   lines: (String) number of lines to read, default 10,000
 
-    def self.lines(filepath, &block)
-      File.foreach(filepath, detect_endline(filepath), binmode: 'rt', encoding: 'bom|utf-8:utf-8', &block)
+    def self.lines(filepath, lines: DEFAULT_LINES_TO_READ, &block)
+      File.foreach(filepath, detect_endline(filepath, lines: lines), binmode: 'rt', encoding: 'bom|utf-8:utf-8', &block)
     end
 
     # Reads the first line of the csv. Returns nil if no first line exists
@@ -67,9 +71,9 @@ def self.first_line(filepath, cleaned = true)
     # Arguments:
     #   filepath: (String)
 
-    def self.rows(filepath, &block)
+    def self.rows(filepath, lines: DEFAULT_LINES_TO_READ, &block)
       delim = detect_delimiter(filepath)
-      endline = detect_endline(filepath)
+      endline = detect_endline(filepath, lines: lines)
       CSV.foreach(filepath, row_sep: endline, col_sep: delim, encoding: 'bom|utf-8:utf-8', &block)
     end