creek 2.4.3 → 2.5.3

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 2e0adb7a48d121c8eaf3500f58e25d2be013ce5b24b6d647443ec3dd866fee31
-  data.tar.gz: f92ee6b1dc6195d7f64c4ea189e8f47af5674ca36c31e667a5db16aa50446d58
+  metadata.gz: 0d90975898b7d260d37f6543755f8c2f4d5931d6e387a56c343bce23eee7e3b1
+  data.tar.gz: 0c381e483070a0e883f128e1a03147a5acf60c4a1095b42ef0d3106af7889f8b
 SHA512:
-  metadata.gz: 64384e3b96b50047dbad96f797ad9772dc3dbb5ba2c6f2e99467a55cf6460df883d9eb77ed2dc9eaf820ef81ebb373556328e0e48b6155f4a63180e59d2b630e
-  data.tar.gz: 5ae4f07b1eedc8ee58acaef4844f8b6abf02ef24d4e98298aa6ad842f31270ccb446908d886a55cb9b88d4e066b4c7a75cf03ab9648153243f518d6d774f7deb
+  metadata.gz: 1f23c318b54b45c2d1732c874e3f6519e7d528175a395b888e3352f302fb1f0b8625cdde965f16540081163282751dd410a712281651b9b3d3b91c9e89bec800
+  data.tar.gz: e601060be6ba35b3bc3ded42865bce8b46fc3ca92feec1439dc2e719f132bb2359d06129f1110dc6676d07f7707364fead716f8f584a5851388a1d183c6e6825

data/.gitignore

@@ -15,3 +15,6 @@ spec/reports
 test/tmp
 test/version_tmp
 tmp
+
+# Mac finder artifacts
+.DS_Store

data/README.md

@@ -100,6 +100,14 @@ remote_url = 'http://dev-builds.libreoffice.org/tmp/test.xlsx'
 Creek::Book.new remote_url, remote: true
 ```
 
+## Mapping cells with header names
+By default, Creek will map cell names with letter and number(A1, B3 and etc). To be able to get cell values by header column name use ***with_headers*** (can be used only with ***#simple_rows*** method!!!) during creation *(Note: header column is first string of sheet)*
+
+```ruby
+creek = Creek::Book.new file.path, with_headers: true
+```
+
+
 ## Contributing
 
 Contributions are welcomed. You can fork a repository, add your code changes to the forked branch, ensure all existing unit tests pass, create new unit tests which cover your new changes and finally create a pull request.
@@ -118,6 +126,12 @@ Once this is complete, you should be able to run the test suite:
 rake
 ```
 
+There are some remote tests that are excluded by default. To run those, run
+
+```
+bundle exec rspec --tag remote
+```
+
 ## Bug Reporting
 
 Please use the [Issues](https://github.com/pythonicrubyist/creek/issues) page to report bugs or suggest new enhancements.

data/creek.gemspec

@@ -20,12 +20,11 @@ Gem::Specification.new do |spec|
 
   spec.required_ruby_version = '>= 2.0.0'
 
-  spec.add_development_dependency "bundler", "~> 1.3"
+  spec.add_development_dependency "bundler", "~> 2.1.2"
   spec.add_development_dependency "rake"
   spec.add_development_dependency 'rspec', '~> 3.6.0'
-  spec.add_development_dependency 'pry'
+  spec.add_development_dependency 'pry-byebug'
 
-  spec.add_dependency 'nokogiri', '>= 1.7.0'
+  spec.add_dependency 'nokogiri', '>= 1.10.0'
   spec.add_dependency 'rubyzip', '>= 1.0.0'
-  spec.add_dependency 'http', '~> 4.0'
 end

data/lib/creek.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'creek/version'
 require 'creek/book'
 require 'creek/styles/constants'

data/lib/creek/book.rb

@@ -1,15 +1,14 @@
 require 'zip/filesystem'
 require 'nokogiri'
 require 'date'
-require 'http'
+require 'open-uri'
 
 module Creek
-
   class Creek::Book
-
     attr_reader :files,
                 :sheets,
-                :shared_strings
+                :shared_strings,
+                :with_headers
 
     DATE_1900 = Date.new(1899, 12, 30).freeze
     DATE_1904 = Date.new(1904, 1, 1).freeze
@@ -20,15 +19,10 @@ module Creek
         extension = File.extname(options[:original_filename] || path).downcase
         raise 'Not a valid file format.' unless (['.xlsx', '.xlsm'].include? extension)
       end
-      if options[:remote]
-        zipfile = Tempfile.new("file")
-        zipfile.binmode
-        zipfile.write(HTTP.get(path).to_s)
-        zipfile.close
-        path = zipfile.path
-      end
+      path = download_file(path) if options[:remote]
       @files = Zip::File.open(path)
       @shared_strings = SharedStrings.new(self)
+      @with_headers = options.fetch(:with_headers, false)
     end
 
     def sheets
@@ -47,7 +41,17 @@ module Creek
       rels = Nokogiri::XML::Document.parse(rels_doc).css("Relationship")
       @sheets = xml.css(cssPrefix+'sheet').map do |sheet|
         sheetfile = rels.find { |el| sheet.attr("r:id") == el.attr("Id") }.attr("Target")
-        Sheet.new(self, sheet.attr("name"), sheet.attr("sheetid"),  sheet.attr("state"), sheet.attr("visible"), sheet.attr("r:id"), sheetfile)
+        sheet = Sheet.new(
+          self,
+          sheet.attr("name"),
+          sheet.attr("sheetid"),
+          sheet.attr("state"),
+          sheet.attr("visible"),
+          sheet.attr("r:id"),
+          sheetfile
+        )
+        sheet.with_headers = with_headers
+        sheet
       end
     end
 
@@ -79,5 +83,20 @@ module Creek
         result
       end
     end
+
+    private
+
+    def download_file(url)
+      # OpenUri will return a StringIO if under OpenURI::Buffer::StringMax
+      # threshold, and a Tempfile if over.
+      downloaded = URI(url).open
+      if downloaded.is_a? StringIO
+        path = Tempfile.new(['creek-file', '.xlsx']).path
+        File.binwrite(path, downloaded.read)
+        path
+      else
+        downloaded.path
+      end
+    end
   end
 end

data/lib/creek/drawing.rb

@@ -83,7 +83,9 @@ module Creek
       col_to_selector = 'xdr:to/xdr:col'.freeze
 
       @drawings.xpath('//xdr:twoCellAnchor').each do |drawing|
-        embed = drawing.xpath(image_selector).first.attributes['embed']
+        # embed = drawing.xpath(image_selector).first.attributes['embed']
+        temp = drawing.xpath(image_selector).first
+        embed = temp.attributes['embed'] if temp
         next if embed.nil?
 
         rid = embed.value

data/lib/creek/sheet.rb

@@ -1,3 +1,5 @@
+# frozen_string_literal: true
+
 require 'zip/filesystem'
 require 'nokogiri'
 
@@ -5,16 +7,19 @@ module Creek
   class Creek::Sheet
     include Creek::Utils
 
+    HEADERS_ROW_NUMBER = '1'
+
+    attr_accessor :with_headers
     attr_reader :book,
                 :name,
                 :sheetid,
                 :state,
                 :visible,
                 :rid,
-                :index
-
+                :index,
+                :headers
 
-    def initialize book, name, sheetid, state, visible, rid, sheetfile
+    def initialize(book, name, sheetid, state, visible, rid, sheetfile)
       @book = book
       @name = name
       @sheetid = sheetid
@@ -46,7 +51,6 @@ module Creek
       @drawing.images_at(cell) if @images_present
     end
 
-
     ##
     # Provides an Enumerator that returns a hash representing each row.
     # The key of the hash is the column ID and the value is the value of the cell.
@@ -88,36 +92,39 @@ module Creek
         opener = Nokogiri::XML::Reader::TYPE_ELEMENT
         closer = Nokogiri::XML::Reader::TYPE_END_ELEMENT
         Enumerator.new do |y|
+          @headers = nil
           row, cells, cell = nil, {}, nil
-          cell_type  = nil
+          cell_type = nil
           cell_style_idx = nil
           @book.files.file.open(path) do |xml|
             Nokogiri::XML::Reader.from_io(xml).each do |node|
-              if (node.name.eql? 'row') and (node.node_type.eql? opener)
+              if node.name == 'row' && node.node_type == opener
                 row = node.attributes
-                row['cells'] = Hash.new
-                cells = Hash.new
+                row['cells'] = {}
+                cells = {}
                 y << (include_meta_data ? row : cells) if node.self_closing?
-              elsif (node.name.eql? 'row') and (node.node_type.eql? closer)
+              elsif node.name == 'row' && node.node_type == closer
                 processed_cells = fill_in_empty_cells(cells, row['r'], cell, use_simple_rows_format)
+                @headers = processed_cells if with_headers && row['r'] == HEADERS_ROW_NUMBER
 
                 if @images_present
                   processed_cells.each do |cell_name, cell_value|
                     next unless cell_value.nil?
+
                     processed_cells[cell_name] = images_at(cell_name)
                   end
                 end
 
                 row['cells'] = processed_cells
                 y << (include_meta_data ? row : processed_cells)
-              elsif (node.name.eql? 'c') and (node.node_type.eql? opener)
+              elsif node.name == 'c' && node.node_type == opener
                 cell_type      = node.attributes['t']
                 cell_style_idx = node.attributes['s']
                 cell           = node.attributes['r']
-              elsif (['v', 't'].include? node.name) and (node.node_type.eql? opener)
+              elsif %w[v t].include?(node.name) && node.node_type == opener
                 unless cell.nil?
                   node.read
-                  cells[(use_simple_rows_format ? cell.tr("0-9", "") : cell)] = convert(node.value, cell_type, cell_style_idx)
+                  cells[cell] = convert(node.value, cell_type, cell_style_idx)
                 end
               end
             end
@@ -142,15 +149,13 @@ module Creek
     # The unzipped XML file does not contain any node for empty cells.
     # Empty cells are being padded in using this function
     def fill_in_empty_cells(cells, row_number, last_col, use_simple_rows_format)
-      new_cells = Hash.new
+      new_cells = {}
+      return new_cells if cells.empty?
 
-      unless cells.empty?
-        last_col = last_col.gsub(row_number, '')
-
-        ("A"..last_col).to_a.each do |column|
-          id = use_simple_rows_format ? "#{column}" : "#{column}#{row_number}"
-          new_cells[id] = cells[id]
-        end
+      last_col = last_col.gsub(row_number, '')
+      ('A'..last_col).to_a.each do |column|
+        id = cell_id(column, use_simple_rows_format, row_number)
+        new_cells[id] = cells["#{column}#{row_number}"]
       end
 
       new_cells
@@ -172,5 +177,11 @@ module Creek
       sheet_rels_filepath = expand_to_rels_path(sheet_filepath)
       parse_xml(sheet_rels_filepath).css("Relationship[@Id='#{drawing_rid}']").first.attributes['Target'].value
     end
+
+    def cell_id(column, use_simple_rows_format, row_number)
+      return "#{column}#{row_number}" unless use_simple_rows_format
+
+      with_headers && headers ? headers[column] : column
+    end
   end
 end

data/lib/creek/styles/converter.rb

@@ -6,7 +6,7 @@ module Creek
       include Creek::Styles::Constants
 
       # Excel non-printable character escape sequence
-      HEX_ESCAPE_REGEXP = /_x[0-9A-Za-z]{4}_/
+      HEX_ESCAPE_REGEXP = /_x[0-9A-Fa-f]{4}_/
 
       ##
       # The heart of typecasting. The ruby type is determined either explicitly
@@ -110,7 +110,7 @@ module Creek
 
       def self.convert_bignum(value)
         if defined?(BigDecimal)
-          BigDecimal.new(value)
+          BigDecimal(value)
         else
           value.to_f
         end

data/lib/creek/version.rb

@@ -1,3 +1,3 @@
 module Creek
-  VERSION = "2.4.3"
+  VERSION = "2.5.3"
 end

data/spec/sheet_spec.rb

@@ -1,26 +1,26 @@
+# frozen_string_literal: true
+
 require './spec/spec_helper'
 
 describe 'sheet' do
   let(:book_with_images) { Creek::Book.new('spec/fixtures/sample-with-images.xlsx') }
-  let(:book_no_images) { Creek::Book.new('spec/fixtures/sample.xlsx') }
   let(:sheetfile) { 'worksheets/sheet1.xml' }
   let(:sheet_with_images) { Creek::Sheet.new(book_with_images, 'Sheet 1', 1, '', '', '1', sheetfile) }
-  let(:sheet_no_images) { Creek::Sheet.new(book_no_images, 'Sheet 1', 1, '', '', '1', sheetfile) }
 
   def load_cell(rows, cell_name)
-    cell = rows.find { |row| !row[cell_name].nil? }
+    cell = rows.find { |row| row[cell_name] }
     cell[cell_name] if cell
   end
 
   context 'escaped ampersand' do
     let(:book_escaped) { Creek::Book.new('spec/fixtures/escaped.xlsx') }
     it 'does NOT escape ampersand' do
-      expect(book_escaped.sheets[0].rows.to_enum.map(&:values)).to eq([["abc", "def"], ["ghi", "j&k"]])
+      expect(book_escaped.sheets[0].rows.to_enum.map(&:values)).to eq([%w[abc def], %w[ghi j&k]])
     end
 
     let(:book_escaped2) { Creek::Book.new('spec/fixtures/escaped2.xlsx') }
     it 'does escape ampersand' do
-      expect(book_escaped2.sheets[0].rows.to_enum.map(&:values)).to eq([["abc", "def"], ["ghi", "j&k"]])
+      expect(book_escaped2.sheets[0].rows.to_enum.map(&:values)).to eq([%w[abc def], %w[ghi j&k]])
     end
   end
 
@@ -66,6 +66,9 @@ describe 'sheet' do
     end
 
     context 'with excel without images' do
+      let(:book_no_images) { Creek::Book.new('spec/fixtures/sample.xlsx') }
+      let(:sheet_no_images) { Creek::Sheet.new(book_no_images, 'Sheet 1', 1, '', '', '1', sheetfile) }
+
       it 'does not break on with_images' do
         rows = sheet_no_images.with_images.rows.map { |r| r }
         expect(load_cell(rows, 'A10')).to eq(0.15)
@@ -94,4 +97,38 @@ describe 'sheet' do
       expect(image).to eq(nil)
     end
   end
+
+  describe '#simple_rows' do
+    let(:book_with_headers) { Creek::Book.new('spec/fixtures/sample-with-headers.xlsx') }
+    let(:sheet) { Creek::Sheet.new(book_with_headers, 'Sheet 1', 1, '', '', '1', sheetfile) }
+
+    subject { sheet.simple_rows.to_a[1] }
+
+    it 'returns values by letters' do
+      expect(subject['A']).to eq 'value1'
+      expect(subject['B']).to eq 'value2'
+    end
+
+    context 'when enable with_headers property' do
+      before { sheet.with_headers = true }
+
+      it 'returns values by headers name' do
+        expect(subject['HeaderA']).to eq 'value1'
+        expect(subject['HeaderB']).to eq 'value2'
+        expect(subject['HeaderC']).to eq 'value3'
+      end
+
+      it 'returns headers correctly when called multiple times' do
+        row = sheet.simple_rows.to_a[1]
+        expect(row['HeaderA']).to eq 'value1'
+        expect(row['HeaderB']).to eq 'value2'
+        expect(row['HeaderC']).to eq 'value3'
+
+        row = sheet.simple_rows.to_a[1]
+        expect(row['HeaderA']).to eq 'value1'
+        expect(row['HeaderB']).to eq 'value2'
+        expect(row['HeaderC']).to eq 'value3'
+      end
+    end
+  end
 end

data/spec/spec_helper.rb

@@ -1,3 +1,7 @@
 require 'creek'
 require 'pry'
+require 'time'
 
+RSpec.configure do |config|
+  config.filter_run_excluding remote: true
+end

data/spec/test_spec.rb

@@ -106,6 +106,20 @@ describe 'Creek parsing a sample XLSX file' do
     expect(@creek).not_to be_nil
   end
 
+  it 'opens small remote files successfully', remote: true do
+    url = 'https://file-examples.com/wp-content/uploads/2017/02/file_example_XLSX_10.xlsx'
+    @creek = Creek::Book.new(url, remote: true)
+
+    expect(@creek.sheets[0]).to be_a Creek::Sheet
+  end
+
+  it 'opens large remote files successfully', remote: true do
+    url = 'http://www.house.leg.state.mn.us/comm/docs/BanaianZooExample.xlsx'
+    @creek = Creek::Book.new(url, remote: true)
+
+    expect(@creek.sheets[0]).to be_a Creek::Sheet
+  end
+
   it 'find sheets successfully.' do
     expect(@creek.sheets.count).to eq(1)
     sheet = @creek.sheets.first

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: creek
 version: !ruby/object:Gem::Version
-  version: 2.4.3
+  version: 2.5.3
 platform: ruby
 authors:
 - pythonicrubyist
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2019-03-12 00:00:00.000000000 Z
+date: 2021-07-12 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: bundler
@@ -16,14 +16,14 @@ dependencies:
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: 2.1.2
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: '1.3'
+        version: 2.1.2
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
@@ -53,7 +53,7 @@ dependencies:
       - !ruby/object:Gem::Version
         version: 3.6.0
 - !ruby/object:Gem::Dependency
-  name: pry
+  name: pry-byebug
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
@@ -72,14 +72,14 @@ dependencies:
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.7.0
+        version: 1.10.0
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - ">="
       - !ruby/object:Gem::Version
-        version: 1.7.0
+        version: 1.10.0
 - !ruby/object:Gem::Dependency
   name: rubyzip
   requirement: !ruby/object:Gem::Requirement
@@ -94,20 +94,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 1.0.0
-- !ruby/object:Gem::Dependency
-  name: http
-  requirement: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '4.0'
-  type: :runtime
-  prerelease: false
-  version_requirements: !ruby/object:Gem::Requirement
-    requirements:
-    - - "~>"
-      - !ruby/object:Gem::Version
-        version: '4.0'
 description: A Ruby gem that streams and parses large Excel(xlsx and xlsm) files fast
   and efficiently.
 email:
@@ -141,6 +127,7 @@ files:
 - spec/fixtures/invalid.xls
 - spec/fixtures/large_numbers.xlsx
 - spec/fixtures/sample-as-zip.zip
+- spec/fixtures/sample-with-headers.xlsx
 - spec/fixtures/sample-with-images.xlsx
 - spec/fixtures/sample.xlsx
 - spec/fixtures/sample_dates.xlsx
@@ -175,8 +162,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubyforge_project: 
-rubygems_version: 2.7.8
+rubygems_version: 3.0.3
 signing_key: 
 specification_version: 4
 summary: A Ruby gem for parsing large Excel(xlsx and xlsm) files.
@@ -188,6 +174,7 @@ test_files:
 - spec/fixtures/invalid.xls
 - spec/fixtures/large_numbers.xlsx
 - spec/fixtures/sample-as-zip.zip
+- spec/fixtures/sample-with-headers.xlsx
 - spec/fixtures/sample-with-images.xlsx
 - spec/fixtures/sample.xlsx
 - spec/fixtures/sample_dates.xlsx