iron-import 0.8.5 → 0.8.6

checksums.yaml

@@ -1,7 +1,7 @@
 ---
-SHA1:
-  metadata.gz: 072a67b4a7cf2c5bb215aaba838d4e5fe87395cf
-  data.tar.gz: 701d2f2a706225a8dc76c356fd130fd9335b5e2b
+SHA256:
+  metadata.gz: 31bf806c52f39edb39cbd3f7f2992ff1723c562e4c3a3859be0c341165746960
+  data.tar.gz: c140bc5f1a6affcb5e7b940a04f5a0d74c165b49ab5683815c3a63b706447c3f
 SHA512:
-  metadata.gz: 05ef313d18b1d2a9c8fe129120eab8e687ad7d7d6050e64184f2ed08e7301f89de32d89d6d65e61e320c892dc36703f969ae4d45bdf585eb9df9873cc3a2739b
-  data.tar.gz: 3cf69f77fda20624fbf0eb63d87813a2361a9eba295a89330085737ef6198ed26134dbbc30295ee1af2cddf6e6c3f77565544ac6af2f971521c77bd8dbe7fead
+  metadata.gz: 10f52ae0c423c8e9b0feb2bb560141d45a0d607be502ad74d6f1168a130e4d8932c6c28d666e94fc26344a570a6893f7828c02a854ef889018812466ac965968
+  data.tar.gz: 9f555bcf49f432cb8e3d35f3384633741280ba4853491dcaa895895d1fd00eaef1e8a33f1f780ee7efee8659b11d4f4499b9519badf7f0d9d665460a355d1aaf

data/History.txt

@@ -1,3 +1,6 @@
+== 0.8.6 / 2018-04-11
+* Add Importer#read_lines to allow reading an arbitrary number of raw rows from a file with format detection
+
 == 0.8.5 / 2018-02-14
 
 * Add simple separator char detection for CSV files, currently supporting tabs & commas

data/Version.txt

@@ -1 +1 @@
-0.8.5
+0.8.6

data/lib/iron/import/importer.rb

@@ -127,6 +127,42 @@ class Importer
     importer
   end
 
+  # Helper method for use in extracting the raw values for the first n
+  # rows in a given source.  Uses the same format options and detection code
+  # used by Importer#import.  If you are using a custom reader, you can pass in as
+  # options a lambda for :on_file or :on_stream to set the data reader to use.
+  def self.read_lines(num_lines, path_or_stream, options = {}, &block)
+    # Build a dummy importer
+    importer = Importer.build
+
+    # Get the reader for our inputs
+    custom_reader = nil
+    if options[:on_file]
+      custom_reader = Importer::CustomReader.new(importer)
+      custom_reader.set_reader(:file, options[:on_file])
+      
+    elsif options[:on_stream]
+      custom_reader = Importer::CustomReader.new(importer)
+      custom_reader.set_reader(:stream, options[:on_stream])
+    end
+    reader = importer.find_reader(path_or_stream, options[:format], custom_reader)
+
+    # Verify we got one
+    raise 'Unable to find valid reader for path' unless reader
+    
+    # What scopes (if any) should we limit our searching to?
+    scopes = options.delete(:scope)
+    if scopes && !scopes.is_a?(Array)
+      scopes = [scopes]
+    end
+
+    # Read in the data!
+    reader.load(path_or_stream, scopes) do |raw_rows|
+      return raw_rows.slice(0...num_lines)
+    end
+    raise 'Unable to load path or stream'
+  end
+
   # Ye standard constructor!
   def initialize(options = {})
     @scopes = {}
@@ -296,6 +332,29 @@ class Importer
     @custom_reader.set_reader(:stream, block)
   end
   
+  # Helper method to find the right file/stream reader given the options and
+  # params passed.
+  def find_reader(path_or_stream, format = nil, custom_reader = nil)
+    reader = nil
+    default = custom_reader ? :custom : :auto
+    format ||= default
+    if format == :custom
+      # Custom format selected, use our internal custom reader
+      reader = custom_reader
+      
+    elsif format && format != :auto
+      # Explicit format requested
+      reader = DataReader::for_format(self, format)
+      
+    else
+      # Auto select
+      reader = DataReader::for_source(self, path_or_stream)
+    end
+    
+    # What did we get?
+    reader
+  end
+  
   # First call to a freshly #build'd importer, this will read the file/stream/path supplied,
   # validate the required values, run custom validations... basically pre-parse and
   # massage the supplied data.  It will return true on success, or false if one
@@ -332,23 +391,10 @@ class Importer
   def import(path_or_stream, options = {}, &block)
     # Clear all our load-time state, including all rows, header locations... you name it
     reset
-    
-    # Get the reader for this format
-    default = @custom_reader ? :custom : :auto
-    @format = options.delete(:format) { default }
-    if @format == :custom
-      # Custom format selected, use our internal custom reader
-      @reader = @custom_reader
-      
-    elsif @format && @format != :auto
-      # Explicit format requested
-      @reader = DataReader::for_format(self, @format)
-      
-    else
-      # Auto select
-      @reader = DataReader::for_source(self, path_or_stream)
-      @format = @reader.format if @reader
-    end
+
+    # Pick a reader for this stream/file
+    @reader = find_reader(path_or_stream, options.delete(:format), @custom_reader)
+    @format = @reader.format if @reader
 
     # Verify we got one
     unless @reader

data/spec/importer/importer_spec.rb

@@ -298,4 +298,34 @@ describe Importer do
     importer.to_a.should == [{:order => '223300', :date => '1973-01-02'.to_date}]
   end
   
+  it 'should find the right reader for a given format + path/stream' do
+    importer = Importer.build
+    importer.find_reader('foo.xls').class.should == Importer::XlsReader
+    importer.find_reader('foo.text', :csv).class.should == Importer::CsvReader
+    importer.find_reader('/bob/page.html').class.should == Importer::HtmlReader
+    custom = Importer::CustomReader.new(importer)
+    importer.find_reader('foo.text', nil, custom).class.should == Importer::CustomReader
+  end
+
+  it 'should allow reading raw row values' do
+    rows = Importer.read_lines(2, SpecHelper.sample_path('2-sheets.xlsx'), :scope => 'Sheet 2')
+    rows.count.should == 2
+    rows.first.should == ['Table 1', nil]
+    rows.last.should == ['Order', 'Date']
+  end
+  
+  it 'should allow reading raw row values when using a custom reader' do
+    custom = lambda {|source|
+      File.readlines(source).collect do |line|
+        line.extract(/([A-TV-Z][0-9][A-Z0-9]{1,5})\s+(.*)/)
+      end
+    }
+    rows = Importer.read_lines(3, SpecHelper.sample_path('icd10-custom.txt'), :on_file => custom)
+    rows.should == [
+      ['A000', 'Cholera due to Vibrio cholerae 01, biovar cholerae'],
+      ['A001', 'Cholera due to Vibrio cholerae 01, biovar eltor'],
+      ['A009', 'Cholera, unspecified']
+    ]
+  end
+  
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: iron-import
 version: !ruby/object:Gem::Version
-  version: 0.8.5
+  version: 0.8.6
 platform: ruby
 authors:
 - Rob Morris
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2018-02-14 00:00:00.000000000 Z
+date: 2018-04-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: iron-extensions
@@ -157,7 +157,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.3
+rubygems_version: 2.7.6
 signing_key: 
 specification_version: 4
 summary: CSV, HTML, XLS, and XLSX import processing support