roo 2.3.2 → 2.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: a2e51de2c40930cef415563182257a853b10978e
-  data.tar.gz: 3b17c8cfb99d1a16778e20289fea7ae9b1ed88a5
+  metadata.gz: 5d2a5a56902bf60eef9028eddb5617ae403b866f
+  data.tar.gz: 3fad0f4206fd3058b3a420b63da7393b530f5f59
 SHA512:
-  metadata.gz: a8f57baddedd100e461fb350814c39dfe765a89a911f2cda0579281612cf37ca95fd9d0459f0572a2241d2e99871045dd5f4573d20364827f756b875a01484b4
-  data.tar.gz: 87012bc658fbc668b7e655de16b339034cf5887f3e0b3ceb468626e9203c22fd0d05e7d1bbea243525cb7c27e61e2af296f1804bc58def990dc4bf1f95463cd5
+  metadata.gz: 91ca5af7282631e668e104e407fb6affd40bc56792809b7129e46de4dd9e4af8133aa6c1eb18f2a9ac8fc7d9470ae51bfb304bff9d920893f1b391b40f6dd162
+  data.tar.gz: 9efee7d9ae6fec31bd965a7ce49fcd57452b0b61bb8ad0eb89a21640e4d3f0bbd5cfbb018f6f567b8475050550eb684dd6800aa80716876e2c0b747ae8adecd2

data/.github/ISSUE_TEMPLATE

@@ -0,0 +1,10 @@
+Thanks for filing an issue. Following these instructions will help us solve your problem sooner.
+
+1. Describe the issue.
+2. Create a gist for this issue (Sample gist: https://gist.github.com/stevendaniels/98a05849036e99bb8b3c)? 
+
+Here are some instructions for creating such a gist. 
+
+1. Create a gist (https://gist.github.com) with code that creates the error.
+2. Clone the gist repo locally, add a stripped down version of the offending spreadsheet to the gist repo, and push the gist's changes master.
+3. Paste the gist url here.

data/.gitignore

@@ -5,3 +5,7 @@
 .project
 *.lock
 .idea
+.buildpath
+*~
+.bundle/
+lbin/

data/CHANGELOG.md

@@ -1,3 +1,13 @@
+## [2.4.0] 2016-05-14
+### Fixed  
+- Fixed opening spreadsheets with charts [315](https://github.com/roo-rb/roo/pull/315)
+- Fixed memory issues for Roo::Utils.number_to_letter [308](https://github.com/roo-rb/roo/pull/308)
+- Fixed Roo::Excelx::Cell::Number to recognize floating point numbers [306](https://github.com/roo-rb/roo/pull/306)
+- Fixed version number in Readme.md [304](https://github.com/roo-rb/roo/pull/304)
+
+### Added
+- Added initial support for HTML formatting [278](https://github.com/roo-rb/roo/pull/278)
+
 ## [2.3.2] 2016-02-18
 ### Fixed
 - Handle url with long query params (ex. S3 secure url) [302](https://github.com/roo-rb/roo/pull/302)

data/README.md

@@ -18,7 +18,7 @@ Install as a gem
 Or add it to your Gemfile
 
 ```ruby
-gem 'roo', '~> 2.1.0'
+gem 'roo', '~> 2.4.0'
 ```
 ## Usage
 

data/lib/roo/excelx.rb

@@ -354,8 +354,10 @@ module Roo
       end
     end
 
+    # Extracts the sheets in order, but it will ignore sheets that are not
+    # worksheets.
     def extract_sheets_in_order(entries, sheet_ids, sheets, tmpdir)
-      sheet_ids.each_with_index do |id, i|
+      (sheet_ids & sheets.keys).each_with_index do |id, i|
         name = sheets[id]
         entry = entries.find { |e| e.name =~ /#{name}$/ }
         path = "#{tmpdir}/roo_sheet#{i + 1}"
@@ -414,6 +416,10 @@ module Roo
           #       ECMA-376 12.3.3 in "Ecma Office Open XML Part 1".
           nr = Regexp.last_match[1].to_i
           comments_files[nr - 1] = "#{@tmpdir}/roo_comments#{nr}"
+        when %r{chartsheets/_rels/sheet([0-9]+).xml.rels$}
+          # NOTE: Chart sheet relationship files were interfering with
+          #       worksheets.
+          nil
         when /sheet([0-9]+).xml.rels$/
           # FIXME: Roo seems to use sheet[\d].xml.rels for hyperlinks only, but
           #        it also stores the location for sharedStrings, comments,

data/lib/roo/excelx/cell/number.rb

@@ -21,7 +21,7 @@ module Roo
           when /\.0/
             Float(number)
           else
-            (number.include?('.') || (/\A\d+E[-+]\d+\z/i =~ number)) ? Float(number) : Integer(number)
+            (number.include?('.') || (/\A[-+]?\d+E[-+]\d+\z/i =~ number)) ? Float(number) : Integer(number)
           end
         end
 

data/lib/roo/excelx/shared_strings.rb

@@ -11,6 +11,16 @@ module Roo
         @array ||= extract_shared_strings
       end
 
+      def to_html
+        @html ||= extract_html
+      end
+
+      # Use to_html or to_a for html returns
+      # See what is happening with commit???
+      def use_html?(index)
+        to_html[index][/<([biu]|sup|sub)>/]
+      end
+
       private
 
       def fix_invalid_shared_strings(doc)
@@ -42,6 +52,99 @@ module Roo
           shared_string
         end
       end
-    end
-  end
-end
+
+      def extract_html
+        return [] unless doc_exists?
+        fix_invalid_shared_strings(doc)
+        # read the shared strings xml document
+        doc.xpath('/sst/si').map do |si|
+          html_string = '<html>'
+          si.children.each do |elem|
+            case elem.name
+            when 'r'
+              html_string << extract_html_r(elem)
+            when 't'
+              html_string << elem.content
+            end # case elem.name
+          end # si.children.each do |elem|
+          html_string << '</html>'
+        end # doc.xpath('/sst/si').map do |si|
+      end # def extract_html
+
+      # The goal of this function is to take the following XML code snippet and create a html tag
+      # r_elem ::: XML Element that is in sharedStrings.xml of excel_book.xlsx
+      # {code:xml}
+      # <r>
+      #   <rPr>
+      #      <i/>
+      #      <b/>
+      #      <u/>
+      #      <vertAlign val="subscript"/>
+      #      <vertAlign val="superscript"/>
+      #   </rPr>
+      #   <t>TEXT</t>
+      # </r>
+      # {code}
+      #
+      # Expected Output ::: "<html><sub|sup><b><i><u>TEXT</u></i></b></sub|/sup></html>"
+      def extract_html_r(r_elem)
+        str = ''
+        xml_elems = {
+          sub: false,
+          sup: false,
+          b:   false,
+          i:   false,
+          u:   false
+        }
+        b, i, u, sub, sup = false, false, false, false, false
+        r_elem.children.each do |elem|
+          case elem.name
+          when 'rPr'
+            elem.children.each do |rPr_elem|
+              case rPr_elem.name
+              when 'b'
+                # set formatting for Bold to true
+                xml_elems[:b] = true
+              when 'i'
+                # set formatting for Italics to true
+                xml_elems[:i] = true
+              when 'u'
+                # set formatting for Underline to true
+                xml_elems[:u] = true
+              when 'vertAlign'
+                # See if the Vertical Alignment is subscript or superscript
+                case rPr_elem.xpath('@val').first.value
+                when 'subscript'
+                  # set formatting for Subscript to true and Superscript to false ... Can't have both
+                  xml_elems[:sub] = true
+                  xml_elems[:sup] = false
+                when 'superscript'
+                  # set formatting for Superscript to true and Subscript to false ... Can't have both
+                  xml_elems[:sup] = true
+                  xml_elems[:sub] = false
+                end
+              end
+            end
+          when 't'
+            str << create_html(elem.content, xml_elems)
+          end
+        end
+        str
+      end # extract_html_r
+
+      # This will return an html string
+      def create_html(text, formatting)
+        tmp_str = ''
+        formatting.each do |elem, val|
+          tmp_str << "<#{elem}>" if val
+        end
+        tmp_str << text
+        reverse_format = Hash[formatting.to_a.reverse]
+        reverse_format.each do |elem, val|
+          tmp_str << "</#{elem}>" if val
+        end
+        tmp_str
+      end
+    end # class SharedStrings < Excelx::Extractor
+  end # class Excelx
+end # module Roo

data/lib/roo/excelx/sheet_doc.rb

@@ -119,7 +119,7 @@ module Roo
         #       3. formula
         case value_type
         when :shared
-          value = shared_strings[cell.content.to_i]
+          value = shared_strings.use_html?(cell.content.to_i) ? shared_strings.to_html[cell.content.to_i] : shared_strings[cell.content.to_i]
           Excelx::Cell.create_cell(:string, value, formula, style, hyperlink, coordinate)
         when :boolean, :string
           value = cell.content

data/lib/roo/utils.rb

@@ -2,6 +2,8 @@ module Roo
   module Utils
     extend self
 
+    LETTERS = ('A'..'Z').to_a
+
     def split_coordinate(str)
       @split_coordinate ||= {}
 
@@ -27,16 +29,14 @@ module Roo
 
     # convert a number to something like 'AB' (1 => 'A', 2 => 'B', ...)
     def number_to_letter(num)
-      results = []
-      num = num.to_i
+      result = ""
 
-      while (num > 0)
-        mod = (num - 1) % 26
-        results = [(65 + mod).chr] + results
-        num = ((num - mod) / 26)
+      until num.zero?
+        num, index = (num - 1).divmod(26)
+        result.prepend(LETTERS[index])
       end
 
-      results.join
+      result
     end
 
     def letter_to_number(letters)

data/lib/roo/version.rb

@@ -1,3 +1,3 @@
 module Roo
-  VERSION = '2.3.2'
+  VERSION = '2.4.0'
 end

data/spec/lib/roo/excelx_spec.rb

@@ -56,7 +56,6 @@ describe Roo::Excelx do
         expect(subject).to be_a(Roo::Excelx)
       end
     end
-
   end
 
   describe '#cell' do
@@ -480,10 +479,49 @@ describe Roo::Excelx do
     end
   end
 
+  describe '#html_strings' do
+    let(:path) { 'test/files/html_strings_formatting.xlsx' }
+
+    it 'returns the expected result' do
+      expect(subject.excelx_value(1, 1, "Sheet1")).to eq "This has no formatting."
+      expect(subject.excelx_value(2, 1, "Sheet1")).to eq "<html>This has<b> bold </b>formatting.</html>"
+      expect(subject.excelx_value(2, 2, "Sheet1")).to eq "<html>This has <i>italics</i> formatting.</html>"
+      expect(subject.excelx_value(2, 3, "Sheet1")).to eq "<html>This has <u>underline</u> format.</html>"
+      expect(subject.excelx_value(2, 4, "Sheet1")).to eq "<html>Superscript. x<sup>123</sup></html>"
+      expect(subject.excelx_value(2, 5, "Sheet1")).to eq "<html>SubScript.  T<sub>j</sub></html>"
+
+      expect(subject.excelx_value(3, 1, "Sheet1")).to eq "<html>Bold, italics <b><i>together</i></b>.</html>"
+      expect(subject.excelx_value(3, 2, "Sheet1")).to eq "<html>Bold, Underline <b><u>together</u></b>.</html>"
+      expect(subject.excelx_value(3, 3, "Sheet1")).to eq "<html>Bold, Superscript. <b>x</b><sup><b>N</b></sup></html>"
+      expect(subject.excelx_value(3, 4, "Sheet1")).to eq "<html>Bold, Subscript. <b>T</b><sub><b>abc</b></sub></html>"
+      expect(subject.excelx_value(3, 5, "Sheet1")).to eq "<html>Italics, Underline <i><u>together</u></i>.</html>"
+      expect(subject.excelx_value(3, 6, "Sheet1")).to eq "<html>Italics, Superscript.  <i>X</i><sup><i>abc</i></sup></html>"
+      expect(subject.excelx_value(3, 7, "Sheet1")).to eq "<html>Italics, Subscript.  <i>B</i><sub><i>efg</i></sub></html>"
+      expect(subject.excelx_value(4, 1, "Sheet1")).to eq "<html>Bold, italics underline,<b><i><u> together</u></i></b>.</html>"
+      expect(subject.excelx_value(4, 2, "Sheet1")).to eq "<html>Bold, italics, superscript. <b>X</b><sup><b><i>abc</i></b></sup><b><i>123</i></b></html>"
+      expect(subject.excelx_value(4, 3, "Sheet1")).to eq "<html>Bold, Italics, subscript. <b><i>Mg</i></b><sub><b><i>ha</i></b></sub><b><i>2</i></b></html>"
+      expect(subject.excelx_value(4, 4, "Sheet1")).to eq "<html>Bold, Underline, superscript. <b><u>AB</u></b><sup><b><u>C12</u></b></sup><b><u>3</u></b></html>"
+      expect(subject.excelx_value(4, 5, "Sheet1")).to eq "<html>Bold, Underline, subscript. <b><u>Good</u></b><sub><b><u>XYZ</u></b></sub></html>"
+      expect(subject.excelx_value(4, 6, "Sheet1")).to eq "<html>Italics, Underline, superscript. <i><u>Up</u></i><sup><i><u>swing</u></i></sup></html>"
+      expect(subject.excelx_value(4, 7, "Sheet1")).to eq "<html>Italics, Underline, subscript. <i><u>T</u></i><sub><i><u>swing</u></i></sub></html>"
+      expect(subject.excelx_value(5, 1, "Sheet1")).to eq "<html>Bold, italics, underline, superscript.  <b><i><u>GHJK</u></i></b><sup><b><i><u>190</u></i></b></sup><b><i><u>4</u></i></b></html>"
+      expect(subject.excelx_value(5, 2, "Sheet1")).to eq "<html>Bold, italics, underline, subscript. <b><i><u>Mike</u></i></b><sub><b><i><u>drop</u></i></b></sub></html>"
+      expect(subject.excelx_value(6, 1, "Sheet1")).to eq "See that regular html tags do not create html tags.\n<ol>\n  <li> Denver Broncos </li>\n  <li> Carolina Panthers </li>\n  <li> New England Patriots</li>\n  <li>Arizona Panthers</li>\n</ol>"
+      expect(subject.excelx_value(7, 1, "Sheet1")).to eq "<html>Does create html tags when formatting is used..\n<ol>\n  <li> <b>Denver Broncos</b> </li>\n  <li> <i>Carolina Panthers </i></li>\n  <li> <u>New England Patriots</u></li>\n  <li>Arizona Panthers</li>\n</ol></html>"
+    end
+  end
+
   describe '_x000D_' do
     let(:path) { 'test/files/x000D.xlsx' }
     it 'does not contain _x000D_' do
       expect(subject.cell(2, 9)).not_to include('_x000D_')
     end
   end
+
+  describe 'opening a file with a chart sheet' do
+    let(:path) { 'test/files/chart_sheet.xlsx' }
+    it 'should not raise' do
+      expect{ subject }.to_not raise_error
+    end
+  end
 end

data/spec/lib/roo/utils_spec.rb

@@ -4,7 +4,7 @@ RSpec.describe ::Roo::Utils do
   subject { described_class }
 
   context '#number_to_letter' do
-    ('A'..'Z').to_a.each_with_index do |letter, index|
+    described_class::LETTERS.each_with_index do |letter, index|
       it "should return '#{ letter }' when passed #{ index + 1 }" do
         expect(described_class.number_to_letter(index + 1)).to eq(letter)
       end

data/spec/spec_helper.rb

@@ -1,7 +1,6 @@
 require 'simplecov'
 require 'roo'
 require 'vcr'
-
 require 'helpers'
 
 RSpec.configure do |c|

data/test/excelx/cell/test_datetime.rb

@@ -1,4 +1,7 @@
 require 'test_helper'
+# require 'pry'
+# require 'active_support'
+# require 'active_support/time'
 
 class TestRooExcelxCellDateTime < Minitest::Test
   def test_cell_value_is_datetime

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: roo
 version: !ruby/object:Gem::Version
-  version: 2.3.2
+  version: 2.4.0
 platform: ruby
 authors:
 - Thomas Preymesser
@@ -12,7 +12,7 @@ authors:
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-02-19 00:00:00.000000000 Z
+date: 2016-05-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -95,6 +95,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/ISSUE_TEMPLATE"
 - ".gitignore"
 - ".simplecov"
 - ".travis.yml"
@@ -185,8 +186,9 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.5.1
+rubygems_version: 2.4.5
 signing_key: 
 specification_version: 4
 summary: Roo can access the contents of various spreadsheet files.
 test_files: []
+has_rdoc: