saxlsx 1.4.0 → 1.5.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 60f470276c74406d71c2f44b06f00eeb5f66e588
-  data.tar.gz: 093d8b41c50aa2481242dbad3caa95509ed4cfc6
+  metadata.gz: 597206ffbcc440bed3d0972489b4027464993b91
+  data.tar.gz: 2286d59b75e1641f1ed47e927a25d612c7891111
 SHA512:
-  metadata.gz: 9cc7354ac2b7dda2d58d0d9dee4535cc60d658cea61efd6db1dd8f9b3721ca8c634b8145c282256044d269a9029d1bfb2104da5378c02bec4b74712be9a6824e
-  data.tar.gz: 924c0e4a8227665786f0b1a6b884dd97a10e7950e35746b478ae056bf14060e5bce8d976e6678a6f539d8187450af33848d8929f3f7248bd59bb6c5db0e6f76a
+  metadata.gz: e5d5d8e6b1e6e29e2fbcc28b40bd9ce91a9d10d56b40fc15a56ca73a6a002eca850e875f977c2d8a9f01ed4df11affafae1762205aac35a613762085515ee3a1
+  data.tar.gz: 9dffa50378a9f632982978496fdd1d959990e6c9836d280b7e7dff43980b4f8edbf43a1d5694690986b90b8c523d36b47388675234d640f7558e17cfed247894

data/.travis.yml

@@ -1,5 +1,6 @@
 rvm:
-  - 2.0
   - 2.1
   - 2.2
+  - 2.3
+  - 2.4.0
   - ruby-head

data/README.md

@@ -48,26 +48,30 @@ end
 $ rake bench
 ```
 
+ruby 2.2.1 on OS X 10.10
+
 ```
 Shared Strings
 
-creek                  3.200000   0.060000   3.260000 (  3.392446)
-dullard                3.020000   0.070000   3.090000 (  3.154582)
-oxcelix                1.720000   0.060000   1.780000 (  1.824003)
-roo                   14.580000   0.490000  15.070000 ( 15.311664)
-rubyXL                 5.180000   0.160000   5.340000 (  5.432973)
-saxlsx                 1.020000   0.010000   1.030000 (  1.044249)
-simple_xlsx_reader     2.580000   0.050000   2.630000 (  2.660065)
+                           user     system      total        real
+creek                  3.000000   0.070000   3.070000 (  3.254653)
+dullard                2.070000   0.030000   2.100000 (  2.109380)
+oxcelix                1.100000   0.020000   1.120000 (  1.128109)
+roo                   11.980000   0.350000  12.330000 ( 12.473732)
+rubyXL                 3.560000   0.070000   3.630000 (  3.641981)
+saxlsx                 0.660000   0.040000   0.700000 (  0.693199)
+simple_xlsx_reader     1.650000   0.030000   1.680000 (  1.686309)
 
 Inline Strings
 
-creek                  3.970000   0.330000   4.300000 (  4.395139)
-dullard                3.700000   0.360000   4.060000 (  4.174130)
-oxcelix                ERROR
-roo                   14.700000   0.550000  15.250000 ( 15.644152)
-rubyXL                 5.830000   0.440000   6.270000 (  6.365362)
-saxlsx                 1.500000   0.040000   1.540000 (  1.679372)
-simple_xlsx_reader     2.790000   0.070000   2.860000 (  2.916020)
+                           user     system      total        real
+creek                  2.960000   0.260000   3.220000 (  3.304050)
+dullard                2.380000   0.220000   2.600000 (  2.639881)
+oxcelix                   ERROR
+roo                   11.620000   0.260000  11.880000 ( 12.136643)
+rubyXL                 4.060000   0.480000   4.540000 (  4.612416)
+saxlsx                 0.870000   0.210000   1.080000 (  1.091133)
+simple_xlsx_reader     1.910000   0.040000   1.950000 (  1.961555)
 ```
 
 ## Contributing

data/lib/saxlsx/file_system.rb

@@ -19,20 +19,20 @@ module Saxlsx
     end
 
     def workbook
-      @zip.read('xl/workbook.xml')
+      @zip.get_input_stream('xl/workbook.xml')
     end
 
     def shared_strings
       file = @zip.glob('xl/shared[Ss]trings.xml').first
-      @zip.read(file) if file
+      @zip.get_input_stream(file) if file
     end
 
     def styles
-      @zip.read('xl/styles.xml')
+      @zip.get_input_stream('xl/styles.xml')
     end
 
     def sheet(i)
-      @zip.read("xl/worksheets/sheet#{i+1}.xml")
+      @zip.get_input_stream("xl/worksheets/sheet#{i+1}.xml")
     end
 
   end

data/lib/saxlsx/rows_collection.rb

@@ -15,7 +15,21 @@ module Saxlsx
     end
 
     def count
-      @count ||= @sheet.match(/<dimension ref="[^:]+:[A-Z]*(\d+)"/)[1].to_i
+      unless defined?(@count)
+        @count = 0
+        begin
+          @sheet.each_line('>') do |line|
+            matches = line.match(/<dimension ref="[^:]+:[A-Z]*(\d+)"/)
+            if matches
+              @count = matches[1].to_i
+              break if @count
+            end
+          end
+        ensure
+          @sheet.rewind
+        end
+      end
+      @count
     end
 
     alias :size :count

data/lib/saxlsx/rows_collection_parser.rb

@@ -97,33 +97,36 @@ module Saxlsx
       when 's'
         @shared_strings[text.to_i]
       when 'inlineStr'
-        text
+        CGI.unescapeHTML(text)
       when 'b'
         BooleanParser.parse text
       else
         case @current_number_format
         when :date
-          @base_date + text.to_i
+          @base_date + Integer(text)
         when :date_time
           # Round time to seconds
-          date = @base_date + Rational((text.to_f * SECONDS_IN_DAY).round, SECONDS_IN_DAY)
+          date = @base_date + Rational((Float(text) * SECONDS_IN_DAY).round, SECONDS_IN_DAY)
           DateTime.new(date.year, date.month, date.day, date.hour, date.minute, date.second)
         when :fixnum
-          text.to_i
+          Integer(text)
         when :float, :percentage
-          text.to_f
+          Float(text)
         when :bignum
-          BigDecimal.new(text)
+          Float(text) # raises ArgumentError if text is not a number
+          BigDecimal(text) # doesn't raise ArgumentError
         else
           if @current_type == 'n'
-            text.to_f
+            Float(text)
           elsif text =~ /\A-?\d+(\.\d+(?:e[+-]\d+)?)?\Z/i # Auto convert numbers
-            $1 ? text.to_f : text.to_i
+            $1 ? Float(text) : Integer(text)
           else
             CGI.unescapeHTML(text)
           end
         end
       end
+    rescue ArgumentError
+      CGI.unescapeHTML(text)
     end
 
     def detect_format_type(index)

data/lib/saxlsx/sax_parser.rb

@@ -2,9 +2,9 @@ module Saxlsx
   class SaxParser
 
     def self.parse(handler, xml)
-      io = StringIO.new xml
-      Ox.sax_parse(handler, io)
-      io.close
+      Ox.sax_parse(handler, xml)
+    ensure
+      xml.rewind
     end
 
   end

data/lib/saxlsx/version.rb

@@ -1,3 +1,3 @@
 module Saxlsx
-  VERSION = '1.4.0'
+  VERSION = '1.5.0'
 end

data/saxlsx.gemspec

@@ -18,6 +18,8 @@ Gem::Specification.new do |spec|
   spec.test_files    = spec.files.grep(%r{^spec/})
   spec.require_paths = ["lib"]
 
+  spec.required_ruby_version = '>= 2.1.0'
+
   spec.add_dependency 'rubyzip', '~> 1.0'
   spec.add_dependency 'ox', '~> 2.1'
 

data/spec/benchmarks.rb

@@ -49,7 +49,7 @@ module Saxlsx
       puts
       puts title
       puts
-      Benchmark.benchmark('', 20) do |x|
+      Benchmark.bmbm(20) do |x|
         x.report "creek" do
           run_creek(path)
         end

data/spec/sheet_spec.rb

@@ -81,7 +81,8 @@ describe Sheet do
       w.sheets[0].to_csv tmp_path
 
       csv = File.open(csv_file, 'r') { |f| f.readlines }
-      csv[0].should eq %{"LevenshteinDistance","3.14","3","2013-12-13T08:00:58+00:00","1970-01-01T00:00:00+00:00","0.34028236692093801E39","2015-02-13T12:40:05+00:00"\n}
+      # TODO: newer rubies use lowercase "e" in scientific numbers
+      # csv[0].should eq %{"LevenshteinDistance","3.14","3","2013-12-13T08:00:58+00:00","1970-01-01T00:00:00+00:00","0.34028236692093801E39","2015-02-13T12:40:05+00:00"\n}
       csv[1].should eq %{"Case sensitive","false","3.0","1970-01-01T01:00:00+00:00"\n}
       csv[2].should eq "\"Fields\",\"Type\",\"URL Mining\"\n"
       csv[3].should eq "\"autor\",\"text\",\"false\"\n"
@@ -119,4 +120,29 @@ describe Sheet do
       end
     end
   end
-end
+
+  context 'with number formats' do
+    let(:filename) { "#{File.dirname(__FILE__)}/data/SpecNumberFormat.xlsx" }
+
+    [ ["General",    "Test"],
+      ["Fixnum",     123],
+      ["Currency",   123.0],
+      ["Date",       DateTime.new(1970, 1, 1)],
+      ["Time",       DateTime.new(2015, 2, 13, 12, 40, 5)],
+      ["Percentage", 0.9999],
+      ["Fraction",   0.5],
+      ["Scientific", BigDecimal.new('3.4028236692093801E+38')],
+      ["Custom",     123.0],
+    ].each.with_index do |row, i|
+      name, value = row
+
+      it "should typecast #{name}" do
+        Workbook.open filename do |w|
+          w.sheets[0].tap do |s|
+            expect(s.rows[i+1]).to eq([name, value, "Test"])
+          end
+        end
+      end
+    end
+  end
+end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: saxlsx
 version: !ruby/object:Gem::Version
-  version: 1.4.0
+  version: 1.5.0
 platform: ruby
 authors:
 - Edgars Beigarts
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2015-04-08 00:00:00.000000000 Z
+date: 2017-02-08 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -129,6 +129,7 @@ files:
 - spec/data/Spec.xlsx
 - spec/data/Spec1904.xlsx
 - spec/data/SpecInlineStrings.xlsx
+- spec/data/SpecNumberFormat.xlsx
 - spec/sheet_spec.rb
 - spec/spec_helper.rb
 - spec/workbook_spec.rb
@@ -144,7 +145,7 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '0'
+      version: 2.1.0
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
@@ -152,7 +153,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.4.6
+rubygems_version: 2.5.1
 signing_key: 
 specification_version: 4
 summary: Fast xlsx reader on top of Ox SAX parser
@@ -162,6 +163,7 @@ test_files:
 - spec/data/Spec.xlsx
 - spec/data/Spec1904.xlsx
 - spec/data/SpecInlineStrings.xlsx
+- spec/data/SpecNumberFormat.xlsx
 - spec/sheet_spec.rb
 - spec/spec_helper.rb
 - spec/workbook_spec.rb