simple_xlsx_reader 5.0.0 → 5.1.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 8552d34f153cbdc6561c40725488d193e9aa48debcded0af24d32daf01b2f951
-  data.tar.gz: 2a0fecdec3698bb16717244fc7bf9b45b4fe0f6b216038e9823f9a5fea2ea8fa
+  metadata.gz: f779f6e272fd4b79b2da180f31eb71b40e51b25d96f50fa72180908472c56750
+  data.tar.gz: 6bd6d85c61aaede6aebbe24f88b8fcc8a4018345581a3793e6e3a89a7bc285ab
 SHA512:
-  metadata.gz: 77f99e8ad1020f0313171dcd0b14f7200fdf116e16de312146eb66a4d9347e94a0bf1cb4483f606975cd8bc776e80995473485271e05ee0a11136ef72cdeeae5
-  data.tar.gz: 7ee3ed8c37df6632981bd6eeb301de5f852df0f66534ce91593923cf1b51aa1dc0b07aed224d5d88cbd4b1f8a6901fdb17164e6e9f22fb10d4e5d90a3c24f437
+  metadata.gz: 63b52b5835fe344b7a8116c6217c6df2f1ec9e68b2876212dec1b08a22dc33549f81905079d7ccea8f2612455e70ab1719aad82229d4fbc00d6da92e4c1ca7a1
+  data.tar.gz: e9e615a600b5bd19c7510fc1b0cbd42e2a2a5494ca9da63be9de813b1bedff73045faa3d0b2f2c8c7b6a7eefecc1219fbbcf6a9f79971b30ba2f8e8c7417cdd8

data/.github/dependabot.yml

@@ -0,0 +1,6 @@
+version: 2
+updates:
+  - package-ecosystem: "github-actions"
+    directory: "/"
+    schedule:
+      interval: "weekly"

data/.github/workflows/ruby.yml

@@ -22,10 +22,10 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        ruby-version: ['2.6', '2.7', '3.0', '3.1', '3.2']
+        ruby-version: ['2.6', '2.7', '3.0', '3.1', '3.2', '3.3']
 
     steps:
-    - uses: actions/checkout@v3
+    - uses: actions/checkout@v4
     - name: Set up Ruby
       uses: ruby/setup-ruby@v1
       with:

data/CHANGELOG.md

@@ -1,3 +1,12 @@
+### 5.1.0
+
+* Parse sheets containing namespaces and no 'r' att (@skipchris)
+* Fix Zlib error when loading from string (@myabc)
+* Prevent a SimpleXlsxReader::CellLoadError (no implicit conversion of Integer
+  into String) when the casted value (friendly name) is not a string (@tsdbrown)
+* Accidental 25% perfarmance improvement while experimenting with namespace
+  support (see #53f5a9).
+
 ### 5.0.0
 
 * Change SimpleXlsxReader::Hyperlink to default to the visible cell value

data/README.md

@@ -13,7 +13,7 @@ then forgotten. We just want to get the data, and get out!
 doc = SimpleXlsxReader.open('/path/to/workbook.xlsx')
 doc.sheets # => [<#SXR::Sheet>, ...]
 doc.sheets.first.name # 'Sheet1'
-rows = doc.sheet.first.rows # <SXR::Document::RowsProxy>
+rows = doc.sheets.first.rows # <SXR::Document::RowsProxy>
 rows.each # an <Enumerator> ready to chain or stream
 rows.each {} # Streams the rows to your block
 rows.each(headers: true) {} # Streams row-hashes
@@ -44,7 +44,7 @@ SimpleXlsxReader strives to be fairly idiomatic Ruby:
 
 ```ruby
 # quick example having fun w/ ruby
-doc = SimpleXlsxReader.open(path_or_io)
+doc = SimpleXlsxReader.open(file_path) # or SimpleXlsxReader.parse(string_or_io)
 doc.sheets.first.rows.each(headers: {id: /ID/})
   .with_index.with_object({}) do |(row, index), acc|
     acc[row[:id]] = index

data/lib/simple_xlsx_reader/hyperlink.rb

@@ -21,9 +21,9 @@ module SimpleXlsxReader
     attr_reader :url
 
     def initialize(url, friendly_name = nil)
-      @friendly_name = friendly_name
       @url = url
-      super(friendly_name || url)
+      @friendly_name = friendly_name&.to_s
+      super(@friendly_name || @url)
     end
   end
 end

data/lib/simple_xlsx_reader/loader/sheet_parser.rb

@@ -33,6 +33,9 @@ module SimpleXlsxReader
         @capture = nil # silence warnings
         @captured = nil # silence warnings
         @dimension = nil # silence warnings
+        @column_index = 0
+
+        @file_io.rewind # if it's IO from IO.read, we need to rewind it
 
         # In this project this is only used for GUI-made hyperlinks (as opposed
         # to FUNCTION-based hyperlinks). Unfortunately the're needed to parse
@@ -40,30 +43,34 @@ module SimpleXlsxReader
         # to just stream-parse the file twice, first for the hyperlinks at the
         # bottom of the file, then for the file itself. In the future it would
         # be clever to use grep to extract the xml into its own smaller file.
-        if xrels_file&.grep(/hyperlink/)&.any?
-          xrels_file.rewind
-          load_gui_hyperlinks # represented as hyperlinks_by_cell
+        if xrels_file
+          if xrels_file.grep(/hyperlink/).any?
+            xrels_file.rewind
+            load_gui_hyperlinks # represented as hyperlinks_by_cell
+          end
+          @file_io.rewind # we've already parsed this once
         end
 
-        @file_io.rewind # in case we've already parsed this once
-
         Nokogiri::XML::SAX::Parser.new(self).parse(@file_io)
       end
 
       ###
       # SAX document hooks
 
-      def start_element(name, attrs = [])
+      def start_element_namespace(name, attrs = [], _prefix, _uri, _ns)
         case name
-        when 'dimension' then @dimension = attrs.last.last
+        when 'dimension'
+          @dimension = attrs.last.value
         when 'row'
-          @current_row_num = attrs.find {|(k, v)| k == 'r'}&.last&.to_i
+          @current_row_num = attrs.find {|attr| attr.localname == 'r'}&.value&.to_i
           @current_row = Array.new(column_length)
+          @column_index = 0
         when 'c'
-          attrs = attrs.inject({}) {|acc, (k, v)| acc[k] = v; acc}
-          @cell_name = attrs['r']
+          attrs = attrs.inject({}) {|acc, attr| acc[attr.localname] = attr.value; acc}
+          @cell_name = attrs['r'] || column_number_to_letter(@column_index)
           @type = attrs['t']
           @style = attrs['s'] && style_types[attrs['s'].to_i]
+          @column_index += 1
         when 'f' then @function = true
         when 'v', 't' then @capture = true
         end
@@ -114,7 +121,7 @@ module SimpleXlsxReader
         @captured = @captured ? @captured + (captured || '') : captured
       end
 
-      def end_element(name)
+      def end_element_namespace(name, _prefix, _uri)
         case name
         when 'row'
           if @headers == true # ya a little funky
@@ -208,10 +215,10 @@ module SimpleXlsxReader
           @hyperlinks_by_cell
         end
 
-        def start_element(name, attrs)
+        def start_element_namespace(name, attrs, _prefix, _uri, _ns)
           case name
           when 'hyperlink'
-            attrs = attrs.inject({}) {|acc, (k, v)| acc[k] = v; acc}
+            attrs = attrs.inject({}) {|acc, attr| acc[attr.localname] = attr.value; acc}
             id = attrs['id'] || attrs['r:id']
 
             @hyperlinks_by_cell[attrs['ref']] =
@@ -264,6 +271,16 @@ module SimpleXlsxReader
         end
         result
       end
+
+      def column_number_to_letter(n)
+        result = []
+        loop do
+          result.unshift((n % 26 + 65).chr)
+          n = (n / 26) - 1
+          break if n < 0
+        end
+        result.join
+      end
     end
   end
 end

data/lib/simple_xlsx_reader/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleXlsxReader
-  VERSION = '5.0.0'
+  VERSION = '5.1.0'
 end

data/test/namespaces_and_missing_atts_test.rb

@@ -0,0 +1,63 @@
+# frozen_string_literal: true
+
+require_relative 'test_helper'
+
+describe SimpleXlsxReader do
+  # Based on a real-world sheet possibly generated by PowerBI, where the xml
+  # has namespacing and rows are missing the 'r' attribute.
+  let(:sheet) do
+    <<~XML
+      <?xml version="1.0" encoding="utf-8"?>
+      <x:worksheet xmlns:x="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
+        <x:sheetData>
+          <x:row>
+            <x:c s="2" t="inlineStr">
+              <x:is>
+                <x:t>Salmon</x:t>
+              </x:is>
+            </x:c>
+            <x:c s="2" t="inlineStr">
+              <x:is>
+                <x:t>Trout</x:t>
+              </x:is>
+            </x:c>
+          </x:row>
+          <x:row>
+            <x:c s="2" t="inlineStr">
+              <x:is>
+                <x:t>Cat</x:t>
+              </x:is>
+            </x:c>
+            <x:c s="2" t="inlineStr">
+              <x:is>
+                <x:t>Dog</x:t>
+              </x:is>
+            </x:c>
+          </x:row>
+        </x:sheetData>
+      </x:worksheet>
+    XML
+  end
+
+  let(:styles) do
+    <<~XML
+      <?xml version="1.0" encoding="utf-8"?><x:styleSheet xmlns:x="http://schemas.openxmlformats.org/spreadsheetml/2006/main"><x:numFmts><x:numFmt numFmtId="181" formatCode="0" /><x:numFmt numFmtId="182" formatCode="m/d/yyyy h:mm:ss AM/PM" /><x:numFmt numFmtId="183" formatCode="dd MMMM yyyy" /></x:numFmts><x:fonts><x:font /><x:font><x:b /></x:font></x:fonts><x:fills><x:fill><x:patternFill patternType="none" /></x:fill><x:fill><x:patternFill patternType="gray125" /></x:fill></x:fills><x:borders><x:border /><x:border><x:bottom style="thin" /></x:border><x:border><x:right style="thin" /></x:border></x:borders><x:cellXfs><x:xf /><x:xf fontId="1" /><x:xf borderId="1" /><x:xf fontId="1" borderId="1" /><x:xf borderId="2" /><x:xf fontId="1" borderId="2" /><x:xf><x:alignment vertical="top" /></x:xf><x:xf fontId="1"><x:alignment vertical="top" /></x:xf><x:xf numFmtId="181" /><x:xf numFmtId="182" /><x:xf numFmtId="183" /><x:xf numFmtId="182" fontId="1" /><x:xf numFmtId="181" fontId="1" /><x:xf numFmtId="183" fontId="1" /></x:cellXfs></x:styleSheet>
+    XML
+  end
+
+  let(:wonky_file) do
+    TestXlsxBuilder.new(
+      sheets: [sheet],
+      styles: styles
+    )
+  end
+
+  let(:subject) { SimpleXlsxReader::Document.new(wonky_file.archive.path) }
+
+  describe '#to_hash' do
+    it 'should extract values from namespaced cells missing "r" attributes' do
+      _(subject.sheets.first.rows.to_a[0]).must_include('Salmon')
+      _(subject.sheets.first.rows.to_a[1]).must_include('Dog')
+    end
+  end
+end

data/test/simple_xlsx_reader_test.rb

@@ -56,7 +56,7 @@ describe SimpleXlsxReader do
     end
 
     describe 'load from string' do
-      let(:subject) { SimpleXlsxReader.parse(sesame_street_blog_io) }
+      let(:subject) { SimpleXlsxReader.parse(sesame_street_blog_string) }
 
       it 'reads an xlsx string into a hash of {[sheet name] => [data]}' do
         _(subject.to_hash).must_equal(expected_result)
@@ -611,6 +611,11 @@ describe SimpleXlsxReader do
           _(described_class.cast('2', 's', nil, shared_strings: %w[a b c], url: url))
             .must_equal SXR::Hyperlink.new(url, 'c')
         end
+
+        it 'creates a hyperlink with a fixnum friendly_name' do
+          _(described_class.cast('123', nil, :fixnum, url: url))
+            .must_equal SXR::Hyperlink.new(url, '123')
+        end
       end
     end
 

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_xlsx_reader
 version: !ruby/object:Gem::Version
-  version: 5.0.0
+  version: 5.1.0
 platform: ruby
 authors:
 - Woody Peterson
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-06-17 00:00:00.000000000 Z
+date: 2025-04-10 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -87,6 +87,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/dependabot.yml"
 - ".github/workflows/ruby.yml"
 - ".gitignore"
 - ".travis.yml"
@@ -115,6 +116,7 @@ files:
 - test/lower_case_sharedstrings.xlsx
 - test/lower_case_sharedstrings_test.rb
 - test/misc_numbers.xlsx
+- test/namespaces_and_missing_atts_test.rb
 - test/percentages_n_currencies.xlsx
 - test/performance_test.rb
 - test/sesame_street_blog.xlsx
@@ -142,7 +144,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.7
+rubygems_version: 3.5.22
 signing_key:
 specification_version: 4
 summary: Read xlsx data the Ruby way
@@ -157,6 +159,7 @@ test_files:
 - test/lower_case_sharedstrings.xlsx
 - test/lower_case_sharedstrings_test.rb
 - test/misc_numbers.xlsx
+- test/namespaces_and_missing_atts_test.rb
 - test/percentages_n_currencies.xlsx
 - test/performance_test.rb
 - test/sesame_street_blog.xlsx