simple_xlsx_reader 3.0.1 → 4.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1f51a4ca0ca865cc2a9ddebeb72fa3db9cc3f309ce2d1a3d34a492f09e22789c
-  data.tar.gz: 90a2b1ac9071fcef0797f5839652d919169cfcf6862de8926b7b605dcc53cd7e
+  metadata.gz: f5e0de15ab326f027127322eac9d88d752ffd2d55797df23ed525a7eea1d9833
+  data.tar.gz: 415972aaf4f77e4bdb5e60b0095cf01f6d7e24a0cd28d493c8ad8d01fa50d66b
 SHA512:
-  metadata.gz: 38f0844bfa6e30cd9af9414057a767cc3bd7cf6ed11023a7306b18686ad3cb250a70191d9b77f8cbc2a590aaa24f822cbec6c546f667fe6e820bb356ddd369f9
-  data.tar.gz: 69af022e15fa95404ab0208be1b4b6661ae14033c73477b98b78f01795712313d63952dce0674ba34ee3aecc19105ef28adfa708de738682583f3b672668a251
+  metadata.gz: cfea3adb62767bedfe6470377b54078066b1bf07e13c065160a31c260261f65a658c34c37dc850c01dd27ba7038a4261f1a6ea9c6ff42771e8113dbabc51897b
+  data.tar.gz: a4b996c3d15b2f54a61d8fc90366ba502d6bc108b1bfe5ed34b9d46f63fe7c52381f181421cc31eea46b7c73e6925d3aa3cfeb8e1b737021be93e4863ea9e703

data/CHANGELOG.md

@@ -1,3 +1,23 @@
+### 4.0.1
+
+* Fix nil error when handling some inline strings
+
+  Inline strings are almost exclusively used by non-Excel XLSX
+  implementations, but are valid, and sometimes have nil chunks.
+
+  Also, inline strings weren't preserving whitespace if Nokogiri is
+  parsing the string in chunks, as it does when encountering escaped
+  characters. Fixed.
+
+### 4.0.0
+
+* Fix percentage rounding errors. Previously we were dividing by 100, when we
+  actually don't need to, so percentage types were 100x too small. Fixes #21.
+  Major bump because workarounds might have been implemented for previous
+  incorrect behavior.
+* Fix small oddity in one currency format where round numbers would be cast
+  to an integer instead of a float.
+
 ### 3.0.1
 
 * Fix parsing "chunky" UTF-8 workbooks. Closes issues #39 and #45. See ce67f0d4.

data/lib/simple_xlsx_reader/loader/sheet_parser.rb

@@ -80,7 +80,7 @@ module SimpleXlsxReader
         captured =
           begin
             SimpleXlsxReader::Loader.cast(
-              string.strip, @type, @style,
+              string, @type, @style,
               url: @url || hyperlinks_by_cell&.[](@cell_name),
               shared_strings: shared_strings,
               base_date: base_date
@@ -99,11 +99,10 @@ module SimpleXlsxReader
             else
               @load_errors[[row_idx, col_idx]] = e.message
 
-              string.strip
+              string
             end
           end
 
-
         # For some reason I can't figure out in a reasonable timeframe,
         # SAX parsing some workbooks captures separate strings in the same cell
         # when we encounter UTF-8, although I can't get workbooks made in my
@@ -112,7 +111,7 @@ module SimpleXlsxReader
         # to make it not do this (looked, couldn't find it).
         #
         # Loading the workbook test/chunky_utf8.xlsx repros the issue.
-        @captured = @captured ? @captured + captured : captured
+        @captured = @captured ? @captured + (captured || '') : captured
       end
 
       def end_element(name)

data/lib/simple_xlsx_reader/loader/style_types_parser.rb

@@ -9,38 +9,39 @@ module SimpleXlsxReader
 
       # Map of non-custom numFmtId to casting symbol
       NumFmtMap = {
-        0 => :string,         # General
-        1 => :fixnum,         # 0
-        2 => :float,          # 0.00
-        3 => :fixnum,         # #,##0
-        4 => :float,          # #,##0.00
-        5 => :unsupported,    # $#,##0_);($#,##0)
-        6 => :unsupported,    # $#,##0_);[Red]($#,##0)
-        7 => :unsupported,    # $#,##0.00_);($#,##0.00)
-        8 => :unsupported,    # $#,##0.00_);[Red]($#,##0.00)
-        9 => :percentage,     # 0%
-        10 => :percentage,     # 0.00%
-        11 => :bignum,         # 0.00E+00
-        12 => :unsupported,    # # ?/?
-        13 => :unsupported,    # # ??/??
-        14 => :date,           # mm-dd-yy
-        15 => :date,           # d-mmm-yy
-        16 => :date,           # d-mmm
-        17 => :date,           # mmm-yy
-        18 => :time,           # h:mm AM/PM
-        19 => :time,           # h:mm:ss AM/PM
-        20 => :time,           # h:mm
-        21 => :time,           # h:mm:ss
-        22 => :date_time,      # m/d/yy h:mm
-        37 => :unsupported,    # #,##0 ;(#,##0)
-        38 => :unsupported,    # #,##0 ;[Red](#,##0)
-        39 => :unsupported,    # #,##0.00;(#,##0.00)
-        40 => :unsupported,    # #,##0.00;[Red](#,##0.00)
-        45 => :time,           # mm:ss
-        46 => :time,           # [h]:mm:ss
-        47 => :time,           # mmss.0
-        48 => :bignum,         # ##0.0E+0
-        49 => :unsupported     # @
+        0 => :string,        # General
+        1 => :fixnum,        # 0
+        2 => :float,         # 0.00
+        3 => :fixnum,        # #,##0
+        4 => :float,         # #,##0.00
+        5 => :unsupported,   # $#,##0_);($#,##0)
+        6 => :unsupported,   # $#,##0_);[Red]($#,##0)
+        7 => :unsupported,   # $#,##0.00_);($#,##0.00)
+        8 => :unsupported,   # $#,##0.00_);[Red]($#,##0.00)
+        9 => :percentage,    # 0%
+        10 => :percentage,   # 0.00%
+        11 => :bignum,       # 0.00E+00
+        12 => :unsupported,  # # ?/?
+        13 => :unsupported,  # # ??/??
+        14 => :date,         # mm-dd-yy
+        15 => :date,         # d-mmm-yy
+        16 => :date,         # d-mmm
+        17 => :date,         # mmm-yy
+        18 => :time,         # h:mm AM/PM
+        19 => :time,         # h:mm:ss AM/PM
+        20 => :time,         # h:mm
+        21 => :time,         # h:mm:ss
+        22 => :date_time,    # m/d/yy h:mm
+        37 => :unsupported,  # #,##0 ;(#,##0)
+        38 => :unsupported,  # #,##0 ;[Red](#,##0)
+        39 => :unsupported,  # #,##0.00;(#,##0.00)
+        40 => :unsupported,  # #,##0.00;[Red](#,##0.00)
+        44 => :float,        # some odd currency format ?from Office 2007?
+        45 => :time,         # mm:ss
+        46 => :time,         # [h]:mm:ss
+        47 => :time,         # mmss.0
+        48 => :bignum,       # ##0.0E+0
+        49 => :unsupported   # @
       }.freeze
 
       def parse

data/lib/simple_xlsx_reader/loader.rb

@@ -162,7 +162,7 @@ module SimpleXlsxReader
         when :float
           value.to_f
         when :percentage
-          value.to_f / 100
+          value.to_f
         # the trickiest. note that  all these formats can vary on
         # whether they actually contain a date, time, or datetime.
         when :date, :time, :date_time

data/lib/simple_xlsx_reader/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleXlsxReader
-  VERSION = '3.0.1'
+  VERSION = '4.0.1'
 end

data/test/simple_xlsx_reader_test.rb

@@ -122,6 +122,52 @@ describe SimpleXlsxReader do
 
   let(:reader) { SimpleXlsxReader.open(xlsx.archive.path) }
 
+  describe 'when parsing escaped characters' do
+    let(:escaped_content) do
+      '<a href="https://www.example.com">Link A</a> • <a href="https://www.example.com">Link B</a>'
+    end
+
+    let(:unescaped_content) do
+      '<a href="https://www.example.com">Link A</a> &bull; <a href="https://www.example.com">Link B</a>'
+    end
+
+    let(:sheet) do
+      <<~XML
+        <worksheet xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main">
+          <dimension ref="A1:B1" />
+          <sheetData>
+            <row r="1">
+              <c r="A1" s="1" t="s">
+                <v>0</v>
+              </c>
+              <c r='B1' s='0'>
+                <v>#{escaped_content}</v>
+              </c>
+            </row>
+          </sheetData>
+        </worksheet>
+      XML
+    end
+
+    let(:shared_strings) do
+      <<~XML
+        <sst xmlns="http://schemas.openxmlformats.org/spreadsheetml/2006/main" count="1" uniqueCount="1">
+          <si>
+            <t>#{escaped_content}</t>
+          </si>
+        </sst>
+      XML
+    end
+
+    it 'loads correctly using inline strings' do
+      _(reader.sheets[0].rows.slurp[0][0]).must_equal(unescaped_content)
+    end
+
+    it 'loads correctly using shared strings' do
+      _(reader.sheets[0].rows.slurp[0][1]).must_equal(unescaped_content)
+    end
+  end
+
   describe 'Sheet#rows#each(headers: true)' do
     let(:sheet) do
       <<~XML
@@ -929,7 +975,7 @@ describe SimpleXlsxReader do
         )
       )
     end
-    
+
     it "reads 'Generic' cells with numbers as numbers" do
       _(@row[9]).must_equal 1
     end
@@ -1015,4 +1061,21 @@ describe SimpleXlsxReader do
       )
     end
   end
+
+  describe 'when using percentages & currencies' do
+    let(:pnc_path) do
+      # This file provided by a GitHub user having parse errors in these fields
+      File.join(File.dirname(__FILE__), 'percentages_n_currencies.xlsx')
+    end
+
+    let(:sheet) { SimpleXlsxReader.open(pnc_path).sheets[0] }
+
+    it 'reads percentages as floats of the form 0.XX' do
+      _(sheet.rows.slurp[1][2]).must_equal(0.87)
+    end
+
+    it 'reads currencies as floats' do
+      _(sheet.rows.slurp[1][4]).must_equal(300.0)
+    end
+  end
 end

data/test/test_xlsx_builder.rb

@@ -57,7 +57,6 @@ TestXlsxBuilder = Struct.new(:shared_strings, :styles, :sheets, :workbook, :rels
     self.styles ||= DEFAULTS[:styles]
     self.sheets ||= [DEFAULTS[:sheet]]
     self.rels ||= []
-    self.shared_strings ||= []
   end
 
   def archive
@@ -76,7 +75,7 @@ TestXlsxBuilder = Struct.new(:shared_strings, :styles, :sheets, :workbook, :rels
         styles_file.write(styles)
       end
 
-      if shared_strings.any?
+      if shared_strings
         zip.get_output_stream('xl/sharedStrings.xml') do |ss_file|
           ss_file.write(shared_strings)
         end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: simple_xlsx_reader
 version: !ruby/object:Gem::Version
-  version: 3.0.1
+  version: 4.0.1
 platform: ruby
 authors:
 - Woody Peterson
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-03-05 00:00:00.000000000 Z
+date: 2023-03-06 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: nokogiri
@@ -115,6 +115,7 @@ files:
 - test/lower_case_sharedstrings.xlsx
 - test/lower_case_sharedstrings_test.rb
 - test/misc_numbers.xlsx
+- test/percentages_n_currencies.xlsx
 - test/performance_test.rb
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml
@@ -156,6 +157,7 @@ test_files:
 - test/lower_case_sharedstrings.xlsx
 - test/lower_case_sharedstrings_test.rb
 - test/misc_numbers.xlsx
+- test/percentages_n_currencies.xlsx
 - test/performance_test.rb
 - test/sesame_street_blog.xlsx
 - test/shared_strings.xml