active_importer 0.0.2 → 0.0.3

data/README.md

@@ -48,6 +48,27 @@ columns declared.  Any extra columns are ignored.  Any errors while processing
 the data file does not interrupt the whole process.  Instead, errors are
 notified via some callbacks defined in the importer (see below).
 
+### Supported formats
+
+This library currently supports reading from most spreadsheet formats, thanks
+to the wonderfull [roo](https://github.com/Empact/roo) gem.  Specifically, the
+following formats are supported:
+
+* OpenOffice
+* Excel
+* Google spreadsheets
+* Excelx
+* LibreOffice
+* CSV
+
+The spreadsheet contents are scanned, row by row, until a row is found that
+matches the expect header column, which should contain header cells for all the
+columns declared in the importer.  If no such row is found, the spreadsheet
+processing fails without importing any data.
+
+If the header row is found, data is scanned from the next row on, until the end
+of the spreadsheet.
+
 ### Callbacks
 
 TODO: Document callbacks

data/lib/active_importer/base.rb

@@ -26,7 +26,7 @@ module ActiveImporter
       self.class.model_class
     end
 
-    def self.column(title, field, &block)
+    def self.column(title, field = nil, &block)
       title = title.strip
       if columns[title]
         raise "Duplicate importer column '#{title}'"
@@ -52,10 +52,9 @@ module ActiveImporter
       @context = options.delete(:context)
 
       @book = Roo::Spreadsheet.open(file, options)
-      @header = @book.row(1).map(&:strip)
-      check_header
+      load_header
 
-      @data_row_indices = (2..@book.last_row)
+      @data_row_indices = ((@header_index+1)..@book.last_row)
       @row_count = @data_row_indices.count
     rescue => e
       @book = @header = nil
@@ -111,30 +110,44 @@ module ActiveImporter
       self.class.columns
     end
 
-    def check_header
-      # Header should contain all columns declared for this importer
-      unless columns.keys.all? { |item| @header.include?(item) }
+    def find_header_index
+      (1..@book.last_row).each do |index|
+        row = @book.row(index).map(&:strip)
+        return index if columns.keys.all? { |item| row.include?(item) }
+      end
+      return nil
+    end
+
+    def load_header
+      @header_index = find_header_index
+      if @header_index
+        @header = @book.row(@header_index).map(&:strip)
+      else
         raise 'Spreadsheet does not contain all the expected columns'
       end
     end
 
     def import_row
-      @model = fetch_model
-      build_model
-      model.save!
+      begin
+        @model = fetch_model
+        build_model
+        model.save!
+      rescue => e
+        @row_errors << { row_index: row_index, error_message: e.message }
+        row_error(e.message)
+        return false
+      end
       row_success
-    rescue => e
-      @row_errors << { row_index: row_index, error_message: e.message }
-      row_error(e.message)
+      true
     end
 
     def build_model
       row.each_pair do |key, value|
         column_def = columns[key]
-        next if column_def.nil?
+        next if column_def.nil? || column_def[:field_name].nil?
         field_name = column_def[:field_name]
         transform = column_def[:transform]
-        value = transform.call(value) if transform
+        value = self.instance_exec(value, &transform) if transform
         model[field_name] = value
       end
       hook

data/lib/active_importer/version.rb

@@ -1,3 +1,3 @@
 module ActiveImporter
-  VERSION = "0.0.2"
+  VERSION = "0.0.3"
 end

data/spec/active_importer/base_spec.rb

@@ -4,7 +4,7 @@ require 'stubs/employee'
 describe ActiveImporter::Base do
   let(:spreadsheet_data) do
     [
-      [' Name ', 'Birth Date', 'Department'],
+      [' Name ', 'Birth Date', 'Department', 'Manager'],
       ['John Doe', '2013-10-25', 'IT'],
       ['Jane Doe', '2013-10-26', 'Sales'],
     ]
@@ -36,7 +36,7 @@ describe ActiveImporter::Base do
   context 'when there are rows with errors' do
     let(:spreadsheet_data) do
       [
-        ['Name', 'Birth Date', 'Department'],
+        ['Name', 'Birth Date', 'Department', 'Manager'],
         ['John Doe', '2013-10-25', 'IT'],
         ['Invalid', '2013-10-24', 'Management'],
         ['Invalid', '2013-10-24', 'Accounting'],
@@ -64,7 +64,7 @@ describe ActiveImporter::Base do
   context 'when the import fails' do
     let(:spreadsheet_data) do
       [
-        ['Name', 'Birth Date'],
+        ['Name', 'Birth Date', 'Manager'],
         ['John Doe', '2013-10-25'],
         ['Jane Doe', '2013-10-26'],
       ]
@@ -76,6 +76,23 @@ describe ActiveImporter::Base do
     end
   end
 
+  context 'when header row is not the first one' do
+    let(:spreadsheet_data) do
+      [
+        [],
+        ['List of employees', '', 'Company Name'],
+        ['Ordered by', 'Birth Date'],
+        ['Name', 'Department', 'Birth Date', 'Manager'],
+        ['John Doe', 'IT', '2013-10-25'],
+        ['Jane Doe', 'Sales', '2013-10-26'],
+      ]
+    end
+
+    it 'smartly skips any rows before the header' do
+      expect { EmployeeImporter.import('/dummy/file') }.to change(Employee, :count).by(2)
+    end
+  end
+
   describe '.fetch_model' do
     let(:model) { Employee.new }
 

data/spec/stubs/employee.rb

@@ -14,7 +14,12 @@ class EmployeeImporter < ActiveImporter::Base
 
   column 'Name', :name
   column 'Birth Date', :birth_date
+  column 'Manager'
   column '  Department ', :department_id do |value|
-    value.length # Quick dummy way to get an integer out of a string
+    find_department(value)
+  end
+
+  def find_department(name)
+    name.length # Quick dummy way to get an integer out of a string
   end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: active_importer
 version: !ruby/object:Gem::Version
-  version: 0.0.2
+  version: 0.0.3
   prerelease: 
 platform: ruby
 authors:
@@ -9,7 +9,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-11-06 00:00:00.000000000 Z
+date: 2013-11-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: roo
@@ -112,7 +112,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -3244463273596288739
+      hash: 3421867451760096133
 required_rubygems_version: !ruby/object:Gem::Requirement
   none: false
   requirements:
@@ -121,7 +121,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
       segments:
       - 0
-      hash: -3244463273596288739
+      hash: 3421867451760096133
 requirements: []
 rubyforge_project: 
 rubygems_version: 1.8.23