simple_xlsx_reader 0.9.6 → 0.9.7

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 6c495d2161ffcb0fb72029aa65b3030b01761030
+  data.tar.gz: 3064fcfd2ea46a5ede489cc32faff627740b569d
+SHA512:
+  metadata.gz: 9468df9742e49b5d7c8eb830f724702b6e145dd50dc0f62e2330561091c7587364085ae850938e5853bb3ab5de744e2e87049d722e64d4989da06b5e9d0de09a
+  data.tar.gz: 029b31bff2274d01d43ff8498e76b6bdd7839621ed052af63c5348ec85fec90ce842831e5d739b39951a5807cf9ac6ff938343263709a17f826190afdc45d11d

data/CHANGELOG.md

@@ -1,3 +1,9 @@
+### 0.9.7
+
+* Fix cell parsing where cells have a type, but no content
+* Add a speed test; parsing performs in linear time, but a relatively
+  slow line :/
+
 ### 0.9.6
 
 * Fix worksheet indexes when worksheets have been deleted

data/lib/simple_xlsx_reader.rb

@@ -137,7 +137,8 @@ module SimpleXlsxReader
               xcell.at_xpath('xmlns:is/xmlns:t') : xcell.at_xpath('xmlns:v')
 
             cells << begin
-              self.class.cast(xvalue.text.strip, type, style, :shared_strings => shared_strings)
+              self.class.cast(xvalue && xvalue.text.strip, type, style,
+                              :shared_strings => shared_strings)
             rescue => e
               if !SimpleXlsxReader.configuration.catch_cell_load_errors
                 error = CellLoadError.new(

data/lib/simple_xlsx_reader/version.rb

@@ -1,3 +1,3 @@
 module SimpleXlsxReader
-  VERSION = "0.9.6"
+  VERSION = "0.9.7"
 end

data/test/performance_test.rb

@@ -0,0 +1,111 @@
+require 'test_helper'
+require 'minitest/benchmark'
+
+describe SimpleXlsxReader do
+
+  # n is 0-indexed for us, then converted to 1-indexed for excel
+  def build_row(n)
+    n += 1
+    <<-XML
+      <row>
+        <c r='A#{n}' s='0'>
+          <v>Cell A#{n}</v>
+        </c>
+        <c r='B#{n}' s='1'>
+          <v>2.4</v>
+        </c>
+        <c r='C#{n}' s='2'>
+          <v>30687</v>
+        </c>
+        <c r='D#{n}' t='inlineStr' s='0'>
+          <is><t>Cell D#{n}</t></is>
+        </c>
+
+        <c r='E#{n}' s='0'>
+          <v>Cell E#{n}</v>
+        </c>
+        <c r='F#{n}' s='1'>
+          <v>2.4</v>
+        </c>
+        <c r='G#{n}' s='2'>
+          <v>30687</v>
+        </c>
+        <c r='H#{n}' t='inlineStr' s='0'>
+          <is><t>Cell H#{n}</t></is>
+        </c>
+
+        <c r='I#{n}' s='0'>
+          <v>Cell I#{n}</v>
+        </c>
+        <c r='J#{n}' s='1'>
+          <v>2.4</v>
+        </c>
+        <c r='K#{n}' s='2'>
+          <v>30687</v>
+        </c>
+        <c r='L#{n}' t='inlineStr' s='0'>
+          <is><t>Cell L#{n}</t></is>
+        </c>
+      </row>
+    XML
+  end
+
+  before do
+    base = Nokogiri::XML(
+      <<-XML
+        <worksheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
+          <sheetData>
+          </sheetData>
+        </worksheet>
+      XML
+    )
+    base.at_xpath("/xmlns:worksheet/xmlns:sheetData").add_child(build_row(0))
+
+    @xml = SimpleXlsxReader::Document::Xml.new.tap do |xml|
+      xml.sheets = [base]
+
+      # s='0' above refers to the value of numFmtId at cellXfs index 0,
+      # which is in this case 'General' type
+      xml.styles = Nokogiri::XML(
+        <<-XML
+          <styleSheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
+            <cellXfs count="1">
+              <xf numFmtId="0" />
+              <xf numFmtId="2" />
+              <xf numFmtId="14" />
+            </cellXfs>
+          </styleSheet>
+        XML
+      )
+    end
+
+    # Every new sheet has one more row
+    self.class.bench_range.each do |range|
+      sheet = base.clone
+
+      range.times do |n|
+        sheet.xpath("/xmlns:worksheet/xmlns:sheetData/xmlns:row").last.
+          add_next_sibling(build_row(n))
+      end
+
+      @xml.sheets[range] = sheet
+    end
+  end
+
+  def self.bench_range
+    bench_exp(1,1000)
+  end
+
+  bench_performance_linear 'parses sheets in linear time', 0.9999 do |n|
+
+    raise "not enough sample data; asked for #{n}, only have #{@xml.sheets.count}"\
+      if @xml.sheets[n].nil?
+
+    sheet = SimpleXlsxReader::Document::Mapper.new(@xml).
+      parse_sheet('test', @xml.sheets[n])
+
+    raise "sheet didn't parse correctly; expected #{n + 1} rows, got #{sheet.rows.count}"\
+      if sheet.rows.count != n + 1
+  end
+
+end

data/test/simple_xlsx_reader_test.rb

@@ -18,7 +18,8 @@ describe SimpleXlsxReader do
           [["Author Name", "Title", "Body", "Created At", "Comment Count"],
            ["Big Bird", "The Number 1", "The Greatest", Time.parse("2002-01-01 11:00:00 UTC"), 1],
            ["Big Bird", "The Number 2", "Second Best", Time.parse("2002-01-02 14:00:00 UTC"), 2],
-           ["Big Bird", "Formula Dates", "Tricky tricky", Time.parse("2002-01-03 14:00:00 UTC"), 0]]
+           ["Big Bird", "Formula Dates", "Tricky tricky", Time.parse("2002-01-03 14:00:00 UTC"), 0],
+           ["Empty Eagress", nil, "The title, date, and comment have types, but no values", nil, nil]]
       })
     end
   end
@@ -239,20 +240,25 @@ describe SimpleXlsxReader do
           xml.sheets = [Nokogiri::XML(
             <<-XML
               <worksheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
-                <dimension ref="A1:C1" />
+                <dimension ref="A1:G1" />
                 <sheetData>
                   <row>
                     <c r='A1' s='0'>
                       <v>Cell A1</v>
                     </c>
+
                     <c r='C1' s='1'>
                       <v>2.4</v>
                     </c>
-                    <c r='D1' s='14'>
-                      <v>01-06-84</v>
+                    <c r='D1' s='1' />
+
+                    <c r='E1' s='2'>
+                      <v>30687</v>
                     </c>
-                    <c r='E1' t='inlineStr' s='0'>
-                      <is><t>Cell E1</t></is>
+                    <c r='F1' s='2' />
+
+                    <c r='G1' t='inlineStr' s='0'>
+                      <is><t>Cell G1</t></is>
                     </c>
                   </row>
                 </sheetData>
@@ -274,34 +280,42 @@ describe SimpleXlsxReader do
             XML
           )
         end
+      end
 
-        before do
-          @rows = described_class.new(xml).parse_sheet('test', xml.sheets.first).rows
-        end
+      before do
+        @row = described_class.new(xml).parse_sheet('test', xml.sheets.first).rows[0]
+      end
 
-        it "reads 'Generic' cells as strings" do
-          @rows[0].must_equal "Cell A1"
-        end
+      it "reads 'Generic' cells as strings" do
+        @row[0].must_equal "Cell A1"
+      end
 
-        it "reads empty 'Generic' cells as nil" do
-          @rows[1].must_equal nil
-        end
+      it "reads empty 'Generic' cells as nil" do
+        @row[1].must_equal nil
+      end
 
-        # We could expand on these type tests, but really just a couple
-        # demonstrate that it's wired together. Type-specific tests should go
-        # on #cast
+      # We could expand on these type tests, but really just a couple
+      # demonstrate that it's wired together. Type-specific tests should go
+      # on #cast
 
-        it "reads floats" do
-          @rows[2].must_equal 2.4
-        end
+      it "reads floats" do
+        @row[2].must_equal 2.4
+      end
 
-        it "reads dates" do
-          @rows[3].must_equal Date.parse('Jan 6, 1984')
-        end
+      it "reads empty floats as nil" do
+        @row[3].must_equal nil
+      end
 
-        it "reads strings formatted as inlineStr" do
-          @rows[4].must_equal 'Cell E1'
-        end
+      it "reads dates" do
+        @row[4].must_equal Date.parse('Jan 6, 1984')
+      end
+
+      it "reads empty date cells as nil" do
+        @row[5].must_equal nil
+      end
+
+      it "reads strings formatted as inlineStr" do
+        @row[6].must_equal 'Cell G1'
       end
     end
   end

metadata

@@ -1,78 +1,69 @@
 --- !ruby/object:Gem::Specification
 name: simple_xlsx_reader
 version: !ruby/object:Gem::Version
-  prerelease: 
-  version: 0.9.6
+  version: 0.9.7
 platform: ruby
 authors:
 - Woody Peterson
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2013-06-21 00:00:00.000000000 Z
+date: 2013-07-30 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
-  type: :runtime
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: rubyzip
-  type: :runtime
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
+  type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: minitest
-  type: :development
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 - !ruby/object:Gem::Dependency
   name: pry
-  type: :development
   requirement: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
+  type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
-    none: false
     requirements:
-    - - ! '>='
+    - - '>='
       - !ruby/object:Gem::Version
         version: '0'
 description: Read xlsx data the Ruby way
@@ -91,6 +82,7 @@ files:
 - lib/simple_xlsx_reader.rb
 - lib/simple_xlsx_reader/version.rb
 - simple_xlsx_reader.gemspec
+- test/performance_test.rb
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml
 - test/simple_xlsx_reader_test.rb
@@ -98,32 +90,31 @@ files:
 - test/test_helper.rb
 homepage: ''
 licenses: []
+metadata: {}
 post_install_message: 
 rdoc_options: []
 require_paths:
 - lib
 required_ruby_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 required_rubygems_version: !ruby/object:Gem::Requirement
-  none: false
   requirements:
-  - - ! '>='
+  - - '>='
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
 rubyforge_project: 
-rubygems_version: 1.8.24
+rubygems_version: 2.0.3
 signing_key: 
-specification_version: 3
+specification_version: 4
 summary: Read xlsx data the Ruby way
 test_files:
+- test/performance_test.rb
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml
 - test/simple_xlsx_reader_test.rb
 - test/styles.xml
 - test/test_helper.rb
-has_rdoc: