xsv 1.1.1 → 1.2.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b2cc530ad96a5351ea6ab8a8b9d0f2ee9df0e1827a98e4244f239b3658bc2145
-  data.tar.gz: e286d74163ea3524dfcbd92553c0c4254b667e4ea13adae7468c0d1dc4c8089b
+  metadata.gz: 5ba17dfa73b0bb77884f1f95bac715291316aa415c512b5a60b230250395f87d
+  data.tar.gz: d5c9ce6ac4b64dc854f6dd133fb139fae13b343b9e08465712d6b0e0189a6628
 SHA512:
-  metadata.gz: a89e58bc0447ecbd2eefdd81fe978a5e38438296bcce9dbf18b4dbc3fea5d5740016e35237d229fbab8201bb0e71b208ca66858c9d61e85f4d31d729e9048054
-  data.tar.gz: 45ddf90be0abe97dcd8aac6b08b9daeac2f68f7634062655efee6f59fbef50c6aad3eb69a461b4f7fcf9dd2751fa735de82e9a0821ec18d2f45cb4bada591698
+  metadata.gz: ec2f2bfd10455002aa2ebe8fe661a2b347e5831fde513d57a08fa43a58ea24a8105a2b308d504d5e65f30a5ac5a5c029daf0a6c2ac9c81ca722d6ff456d512ac
+  data.tar.gz: 232238fb39c14a4a9fb7d080b0817bd83620f9caeecd812f3058cc473d97506d8b8fbfd5ef74fc25afaf2c46674d230f2292e9b2e1b8e89b2734bb8b1540c679

data/.github/workflows/ruby.yml

@@ -19,10 +19,10 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        ruby-version: ['2.6', '2.7', '3.0', '3.1', 'jruby', 'truffleruby']
+        ruby-version: ['2.6', '2.7', '3.0', '3.1', '3.2', 'jruby', 'truffleruby']
 
     steps:
-    - uses: actions/checkout@v2
+    - uses: actions/checkout@v3
     - name: Set up Ruby
       uses: ruby/setup-ruby@v1
       with:

data/CHANGELOG.md

@@ -1,5 +1,18 @@
 # Xsv Changelog
 
+## 1.2.1 2023-05-09
+
+- Handle columns without `r` attribute (issue #48)
+- Access sheets by UTF-8 name (thanks @sebikeller)
+
+## 1.2.0 2023-01-01
+
+**This release contains the following minor breaking changes**
+
+- Raise an error when entering hash mode on a sheet with duplicate headers to prevent unintentional behaviour (fixes #44)
+- Xsv now returns frozen strings to further improve performance. This means it's no longer possible to call mutating methods on strings read from worksheets without unfreezing them first.
+- Unescape all HTML entities in XML characters (thanks @til)
+
 ## 1.1.1 2022-04-01
 
 - Improve compatibility with files generated by the Open XML SDK (#40)
@@ -119,4 +132,4 @@ Fix a Gemfile small Gemfile issue that broke the 0.3.3 and 0.3.4 releases
 
 ## 0.3.3 - 2020-03-02
 
-Intial version with a changelog and reasonably complete YARD documentation.
+Initial version with a changelog and reasonably complete YARD documentation.

data/README.md

@@ -1,7 +1,8 @@
 # Xsv .xlsx reader
 
 
-[![Test badge](https://img.shields.io/github/workflow/status/martijn/xsv/Ruby/main)](https://github.com/martijn/xsv/actions/workflows/ruby.yml)
+
+[![Test badge](https://img.shields.io/github/actions/workflow/status/martijn/xsv/ruby.yml?branch=main)](https://github.com/martijn/xsv/actions/workflows/ruby.yml)
 [![Codecov badge](https://img.shields.io/codecov/c/github/martijn/xsv/main)](https://app.codecov.io/gh/martijn/xsv)
 [![Yard Docs badge](http://img.shields.io/badge/yard-docs-blue.svg)](https://rubydoc.info/github/martijn/xsv)
 [![Gem Version badge](https://badge.fury.io/rb/xsv.svg)](https://badge.fury.io/rb/xsv)
@@ -36,10 +37,9 @@ Or install it yourself as:
 
     $ gem install xsv
 
-Xsv targets ruby >= 2.5 and has a just single dependency, `rubyzip`. It has been
-tested successfully with MRI, JRuby, and TruffleRuby. Due to the lack of
-native extensions should work well in multi-threaded environments or in Ractor
-when that becomes stable.
+Xsv targets ruby >= 2.6 and has a just single dependency, `rubyzip`. It has been
+tested successfully with MRI, JRuby, and TruffleRuby. It has no native extensions
+and is designed to be thread-safe.
 
 ## Usage
 
@@ -85,8 +85,11 @@ sheet.parse_headers!
 sheet[0] # => {"header1" => "value1", "header2" => "value2"}
 ```
 
-Be aware that hash mode will lead to unpredictable results if the worksheet
-has multiple columns with the same header. `Xsv::Sheet` implements `Enumerable` so along with `#each`
+Because of the way Ruby hashes work will raise `Xsv::DuplicateHeaders` if it detects
+duplicate values in the header row when calling `#parse_headers!` or when opening
+a workbook with `parse_headers: true`.
+
+`Xsv::Sheet` implements `Enumerable` so along with `#each`
 you can call methods like `#first`, `#filter`/`#select`, and `#map` on it.
 
 ### Opening a string or buffer instead of filename

data/lib/xsv/sax_parser.rb

@@ -1,5 +1,7 @@
 # frozen_string_literal: true
 
+require "cgi"
+
 module Xsv
   class SaxParser
     ATTR_REGEX = /((\p{Alnum}+)="(.*?)")/mn
@@ -36,14 +38,7 @@ module Xsv
             chars = pbuf.slice!(0, o + 1).chop!.force_encoding("utf-8")
 
             if responds_to_characters && !chars.empty?
-              if chars.index("&")
-                chars.gsub!("&", "&")
-                chars.gsub!("'", "'")
-                chars.gsub!(">", ">")
-                chars.gsub!("&lt;", "<")
-                chars.gsub!("&quot;", '"')
-              end
-              characters(chars)
+              characters(CGI.unescapeHTML(chars))
             end
 
             state = :look_end

data/lib/xsv/shared_strings_parser.rb

@@ -6,7 +6,7 @@ module Xsv
   class SharedStringsParser < SaxParser
     def self.parse(io)
       strings = []
-      new { |s| strings << s }.parse(io)
+      new { |s| strings << -s }.parse(io)
       strings
     end
 

data/lib/xsv/sheet.rb

@@ -83,6 +83,12 @@ module Xsv
     # @return [self]
     def parse_headers!
       @headers = parse_headers
+
+      # Check for duplicate headers, but don't care about nil columns
+      if (duplicate_header = @headers.detect { |h| @headers.count(h) > 1 })
+        raise Xsv::DuplicateHeaders, "Duplicate header '#{duplicate_header}' found, consider parsing this sheet in array mode."
+      end
+
       @mode = :hash
 
       self

data/lib/xsv/sheet_rows_handler.rb

@@ -17,6 +17,7 @@ module Xsv
       @store_characters = false
 
       @row_index = 0
+      @col_index = 0
       @current_row = {}
       @current_row_number = 0
       @current_cell = {}
@@ -33,7 +34,7 @@ module Xsv
       when "v", "is", "t"
         @store_characters = true
       when "row"
-        @current_row = @empty_row.dup
+        @current_row = @mode == :array ? []  : @empty_row.dup
         @current_row_number = attrs[:r].to_i
       end
     end
@@ -47,19 +48,22 @@ module Xsv
       when "v", "is", "t"
         @store_characters = false
       when "c"
-        col_index = column_index(@current_cell[:r])
+        col_index = @current_cell[:r] ? column_index(@current_cell[:r]) : @col_index
 
         if @mode == :array
           @current_row[col_index] = format_cell
         else
           @current_row[@headers[col_index]] = format_cell
         end
+
+        @col_index += 1
       when "row"
         return if @current_row_number <= @row_skip
 
         adjusted_row_number = @current_row_number - @row_skip
 
         @row_index += 1
+        @col_index = 0
 
         # Skip first row if we're in hash mode
         return if adjusted_row_number == 1 && @mode == :hash
@@ -72,7 +76,14 @@ module Xsv
         end
 
         # Do not return empty trailing rows
-        @block.call(@current_row) unless @row_index > @last_row
+        return if @row_index > @last_row
+
+        # Add trailing empty columns
+        if @mode == :array && @current_row.length < @empty_row.length
+          @block.call(@current_row + @empty_row[@current_row.length..])
+        else
+          @block.call(@current_row)
+        end
       end
     end
 
@@ -85,7 +96,7 @@ module Xsv
       when "s"
         @workbook.shared_strings[@current_value.to_i]
       when "str", "inlineStr"
-        @current_value.strip
+        -@current_value.strip
       when "e" # N/A
         nil
       when nil, "n"

data/lib/xsv/sheets_ids_handler.rb

@@ -9,7 +9,9 @@ module Xsv
 
       new { |sheet_ids| sheets_ids << sheet_ids }.parse(io)
 
-      sheets_ids
+      sheets_ids.each do |sheet|
+        sheet[:name].force_encoding(Encoding::UTF_8)
+      end
     end
 
     def initialize(&block)

data/lib/xsv/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Xsv
-  VERSION = "1.1.1"
+  VERSION = "1.2.1"
 end

data/lib/xsv.rb

@@ -21,6 +21,8 @@ require "xsv/workbook"
 module Xsv
   class Error < StandardError; end
 
+  class DuplicateHeaders < StandardError; end
+
   # An AssertionFailed error indicates an unexpected condition, meaning a bug
   # or misinterpreted .xlsx document
   class AssertionFailed < StandardError; end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: xsv
 version: !ruby/object:Gem::Version
-  version: 1.1.1
+  version: 1.2.1
 platform: ruby
 authors:
 - Martijn Storck
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-04-01 00:00:00.000000000 Z
+date: 2023-05-09 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip