simple_xlsx_reader 1.0.1 → 1.0.2

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 94422da0193805c579ba37c7c3e58b35a996dfbc
-  data.tar.gz: a9c5e1f01acc0c60165a13adc1af087743a60935
+  metadata.gz: d3b2fbcc0148d773ed19a266e64877600863730c
+  data.tar.gz: 61be9bbca611e49dc7ca725dd33d1560eec98018
 SHA512:
-  metadata.gz: 33338f8fcf3c180ea346548061598953842358a21acd6d97bf451c07d8655f179af0cf7b7791f7c9de1a8411578e3623faab178b3cd74893aaf6d040a7abde96
-  data.tar.gz: 50035b920f6811eed88c318c17b47bf8823aa1ac4bf114af3bc29174edcf08ebd5d16902177aa6a48b70f8e70a745249bb8494101f9f310f24d5f5d5bbc13f27
+  metadata.gz: 041cd7eb5b2ebeeb310da52c0e173ff7c04ac95b55ae1c35cc510280c7d10e9ea6af703d10f2bed1f5f5678c77465fdd5807de2d8b3e4ccf7f1a01475178f487
+  data.tar.gz: 8587c21a003e2bf4af53b2c67348102d85713e997bc15e248f2b806d4d7388b078bb7a5315c503931a0f287e1a7771d990913878d916d010c36040b6777b98ab

data/CHANGELOG.md

@@ -1,3 +1,11 @@
+### 1.0.2
+
+* Fix Ruby 1.9.3-specific bug preventing parsing most sheets [middagj, eritiro]
+* Better support for non-excel-generated xlsx files [bwlang]
+  * You don't always have a numFmtId column, and that's OK
+  * Sometimes 'sharedStrings.xml' can be 'sharedstrings.xml'
+* Fixed parsing times very close to 12/30/1899 [Valeriy Utyaganov]
+
 ### 1.0.1
 
 * Add support for the 1904 date system [zilverline]

data/lib/simple_xlsx_reader.rb

@@ -79,8 +79,9 @@ module SimpleXlsxReader
 
             # optional feature used by excel, but not often used by xlsx
             # generation libraries
-            if zip.file.file?('xl/sharedStrings.xml')
-              xml.shared_strings = Nokogiri::XML(zip.read('xl/sharedStrings.xml')).remove_namespaces!
+            ss_file =  (zip.to_a.map(&:name) & ['xl/sharedStrings.xml','xl/sharedstrings.xml'])[0]
+            if ss_file
+              xml.shared_strings = Nokogiri::XML(zip.read(ss_file)).remove_namespaces!
             end
 
             xml.sheets = []
@@ -218,11 +219,13 @@ module SimpleXlsxReader
       # 'ABA' = 26 * 26 * 1 + 26 * 2  + 1
       # 'BZA' = 26 * 26 * 2 + 26 * 26 + 1
       def column_letter_to_number(column_letter)
-        pow = -1
-        column_letter.codepoints.reverse.inject(0) do |acc, charcode|
-          pow += 1
-          acc + 26**pow * (charcode - 64)
+        pow = column_letter.length - 1
+        result = 0
+        column_letter.each_byte do |b|
+          result += 26**pow * (b - 64)
+          pow -= 1
         end
+        result
       end
 
       # Excel doesn't record types for some cells, only its display style, so
@@ -241,21 +244,32 @@ module SimpleXlsxReader
       # type.
       def style_types
         @style_types ||=
-          xml.styles.xpath('/styleSheet/cellXfs/xf').map {|xstyle|
-            style_type_by_num_fmt_id(xstyle.attributes['numFmtId'].value)}
+            xml.styles.xpath('/styleSheet/cellXfs/xf').map {|xstyle|
+              style_type_by_num_fmt_id(num_fmt_id(xstyle))}
+      end
+
+      #returns the numFmtId value if it's available
+      def num_fmt_id(xstyle)
+        if xstyle.attributes['numFmtId']
+          xstyle.attributes['numFmtId'].value
+        else
+          nil
+        end
       end
 
       # Finds the type we think a style is; For example, fmtId 14 is a date
-      # style, so this would return :date
+      # style, so this would return :date.
+      #
+      # Note, custom styles usually (are supposed to?) have a numFmtId >= 164,
+      # but in practice can sometimes be simply out of the usual "Any Language"
+      # id range that goes up to 49. For example, I have seen a numFmtId of
+      # 59 specified as a date. In Thai, 59 is a number format, so this seems
+      # like a bad idea, but we try to be flexible and just go with it.
       def style_type_by_num_fmt_id(id)
         return nil if id.nil?
 
         id = id.to_i
-        if id >= 164 # custom style, arg!
-          custom_style_types[id]
-        else # we should know this one
-          NumFmtMap[id]
-        end
+        NumFmtMap[id] || custom_style_types[id]
       end
 
       # Map of (numFmtId >= 164) (custom styles) to our best guess at the type
@@ -347,15 +361,15 @@ module SimpleXlsxReader
         # the trickiest. note that  all these formats can vary on
         # whether they actually contain a date, time, or datetime.
         when :date, :time, :date_time
-          days_since_date_system_start, fraction_of_24 = value.split('.')
+          value = value.to_f
+          days_since_date_system_start = value.to_i
+          fraction_of_24 = value - days_since_date_system_start
 
           # http://stackoverflow.com/questions/10559767/how-to-convert-ms-excel-date-from-float-to-date-format-in-ruby
-          date = options.fetch(:base_date, DATE_SYSTEM_1900) + Integer(days_since_date_system_start)
-
-          if fraction_of_24 # there is a time associated
-            fraction_of_24 = "0.#{fraction_of_24}".to_f
-            seconds        = (fraction_of_24 * 86400).round
+          date = options.fetch(:base_date, DATE_SYSTEM_1900) + days_since_date_system_start
 
+          if fraction_of_24 > 0 # there is a time associated
+            seconds = (fraction_of_24 * 86400).round
             return Time.utc(date.year, date.month, date.day) + seconds
           else
             return date

data/lib/simple_xlsx_reader/version.rb

@@ -1,3 +1,3 @@
 module SimpleXlsxReader
-  VERSION = "1.0.1"
+  VERSION = "1.0.2"
 end

data/test/date1904_test.rb

@@ -1,4 +1,4 @@
-require 'test_helper'
+require_relative 'test_helper'
 
 describe SimpleXlsxReader do
   let(:date1904_file) { File.join(File.dirname(__FILE__), 'date1904.xlsx') }

data/test/datetime_test.rb

@@ -1,4 +1,4 @@
-require 'test_helper'
+require_relative 'test_helper'
 
 describe SimpleXlsxReader do
   let(:datetimes_file) { File.join(File.dirname(__FILE__),
@@ -11,7 +11,8 @@ describe SimpleXlsxReader do
       "Datetimes" =>
         [[Time.parse("2013-08-19 18:29:59 UTC")],
          [Time.parse("2013-08-19 18:30:00 UTC")],
-         [Time.parse("2013-08-19 18:30:01 UTC")]]
+         [Time.parse("2013-08-19 18:30:01 UTC")],
+         [Time.parse("1899-12-30 00:30:00 UTC")]]
     })
   end
 

data/test/lower_case_sharedstrings_test.rb

@@ -0,0 +1,15 @@
+require_relative 'test_helper'
+
+describe SimpleXlsxReader do
+  let(:lower_case_shared_strings) { File.join(File.dirname(__FILE__),
+                                                'lower_case_sharedstrings.xlsx') }
+
+  let(:subject) { SimpleXlsxReader::Document.new(lower_case_shared_strings) }
+
+
+  describe '#to_hash' do
+    it 'should have the word Well in the first row' do
+      subject.sheets.first.rows[0].must_include('Well')
+    end
+  end
+end

data/test/performance_test.rb

@@ -1,4 +1,4 @@
-require 'test_helper'
+require_relative 'test_helper'
 require 'minitest/benchmark'
 
 describe 'SimpleXlsxReader Benchmark' do

data/test/simple_xlsx_reader_test.rb

@@ -1,4 +1,4 @@
-require 'test_helper'
+require_relative 'test_helper'
 require 'time'
 
 describe SimpleXlsxReader do
@@ -102,6 +102,13 @@ describe SimpleXlsxReader do
 
       it 'reads custom formatted styles (numFmtId >= 164)' do
         mapper.style_types[1].must_equal :date_time
+        mapper.custom_style_types[164].must_equal :date_time
+      end
+
+      # something I've seen in the wild; don't think it's correct, but let's be flexible.
+      it 'reads custom formatted styles given an id < 164, but not explicitly defined in the SpreadsheetML spec' do
+        mapper.style_types[2].must_equal :date_time
+        mapper.custom_style_types[59].must_equal :date_time
       end
     end
 
@@ -258,6 +265,45 @@ describe SimpleXlsxReader do
       end
     end
 
+    describe "missing numFmtId attributes" do
+
+      let(:xml) do
+        SimpleXlsxReader::Document::Xml.new.tap do |xml|
+          xml.sheets = [Nokogiri::XML(
+                            <<-XML
+            <worksheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
+              <dimension ref="A1:A1" />
+              <sheetData>
+                <row>
+                  <c r='A1' s='s'>
+                    <v>some content</v>
+                  </c>
+                </row>
+              </sheetData>
+            </worksheet>
+                        XML
+                        ).remove_namespaces!]
+
+          xml.styles = Nokogiri::XML(
+              <<-XML
+            <styleSheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
+
+            </styleSheet>
+          XML
+          ).remove_namespaces!
+        end
+      end
+
+      before do
+        @row = described_class.new(xml).parse_sheet('test', xml.sheets.first).rows[0]
+      end
+
+      it 'continues even when cells are missing numFmtId attributes ' do
+        @row[0].must_equal 'some content'
+      end
+
+    end
+
     describe 'parsing types' do
       let(:xml) do
         SimpleXlsxReader::Document::Xml.new.tap do |xml|

data/test/styles.xml

@@ -1,6 +1,7 @@
 <?xml version="1.0" encoding="UTF-8" standalone="yes"?>
 <styleSheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main" xmlns:mc="http://schemas.openxmlformats.org/markup-compatibility/2006" xmlns:x14ac="http://schemas.microsoft.com/office/spreadsheetml/2009/9/ac" mc:Ignorable="x14ac">
-  <numFmts count="1">
+  <numFmts count="2">
+    <numFmt numFmtId="59" formatCode="dd/mm/yyyy"/>
     <numFmt numFmtId="164" formatCode="[$-409]m/d/yy\ h:mm\ AM/PM;@"/>
   </numFmts>
   <fonts count="3" x14ac:knownFonts="1">
@@ -50,9 +51,10 @@
     <xf numFmtId="0" fontId="1" fillId="0" borderId="0" applyNumberFormat="0" applyFill="0" applyBorder="0" applyAlignment="0" applyProtection="0"/>
     <xf numFmtId="0" fontId="2" fillId="0" borderId="0" applyNumberFormat="0" applyFill="0" applyBorder="0" applyAlignment="0" applyProtection="0"/>
   </cellStyleXfs>
-  <cellXfs count="3">
+  <cellXfs count="4">
     <xf numFmtId="0" fontId="0" fillId="0" borderId="0" xfId="0"/>
     <xf numFmtId="164" fontId="0" fillId="0" borderId="0" xfId="0" applyNumberFormat="1"/>
+    <xf numFmtId="59" fontId="0" fillId="0" borderId="0" xfId="0" applyNumberFormat="1"/>
     <xf numFmtId="1" fontId="0" fillId="0" borderId="0" xfId="0" applyNumberFormat="1"/>
   </cellXfs>
   <cellStyles count="3">

data/test/test_helper.rb

@@ -2,6 +2,7 @@ gem 'minitest'
 require 'minitest/autorun'
 require 'minitest/spec'
 require 'pry'
+require 'time'
 
 $:.unshift File.expand_path("lib")
 require 'simple_xlsx_reader'

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_xlsx_reader
 version: !ruby/object:Gem::Version
-  version: 1.0.1
+  version: 1.0.2
 platform: ruby
 authors:
 - Woody Peterson
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2014-09-02 00:00:00.000000000 Z
+date: 2015-02-24 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -86,6 +86,8 @@ files:
 - test/date1904_test.rb
 - test/datetime_test.rb
 - test/datetimes.xlsx
+- test/lower_case_sharedstrings.xlsx
+- test/lower_case_sharedstrings_test.rb
 - test/performance_test.rb
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml
@@ -111,7 +113,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 2.2.0
+rubygems_version: 2.2.2
 signing_key: 
 specification_version: 4
 summary: Read xlsx data the Ruby way
@@ -120,6 +122,8 @@ test_files:
 - test/date1904_test.rb
 - test/datetime_test.rb
 - test/datetimes.xlsx
+- test/lower_case_sharedstrings.xlsx
+- test/lower_case_sharedstrings_test.rb
 - test/performance_test.rb
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml