simple_xlsx_reader 4.0.0 → 4.0.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d60e969d7d2db69578d543b6ebab36d29b3e3e88b4d62d67d00218b09b644cc5
-  data.tar.gz: 36e12c7d95b6319f8f3bb565a1bc1b8eea6d1ca44928b3188a6892bf1f0c6513
+  metadata.gz: f5e0de15ab326f027127322eac9d88d752ffd2d55797df23ed525a7eea1d9833
+  data.tar.gz: 415972aaf4f77e4bdb5e60b0095cf01f6d7e24a0cd28d493c8ad8d01fa50d66b
 SHA512:
-  metadata.gz: 6610958e6cb393e6013d303dd541f80a19d91415f6ebbe1d03162b52580ac361ad3f7e8e9fef5904a1daae72fe0774a5a83f47617c75ac185748c78e2c828e5a
-  data.tar.gz: f556a9d31d48aa7cfeb0a1a9194736f2740ae3a2c868ed6a65fc197411351b28751d9caa72fd2bbbeb7eb22acd9ba0e2d53606f414bd36843f811ccb93d80ed2
+  metadata.gz: cfea3adb62767bedfe6470377b54078066b1bf07e13c065160a31c260261f65a658c34c37dc850c01dd27ba7038a4261f1a6ea9c6ff42771e8113dbabc51897b
+  data.tar.gz: a4b996c3d15b2f54a61d8fc90366ba502d6bc108b1bfe5ed34b9d46f63fe7c52381f181421cc31eea46b7c73e6925d3aa3cfeb8e1b737021be93e4863ea9e703

data/CHANGELOG.md

@@ -1,3 +1,14 @@
+### 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

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
@@ -99,7 +99,7 @@ module SimpleXlsxReader
             else
               @load_errors[[row_idx, col_idx]] = e.message
 
-              string.strip
+              string
             end
           end
 
@@ -111,7 +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/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module SimpleXlsxReader
-  VERSION = '4.0.0'
+  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

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: 4.0.0
+  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