xsv 1.1.1 → 1.2.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: b2cc530ad96a5351ea6ab8a8b9d0f2ee9df0e1827a98e4244f239b3658bc2145
-  data.tar.gz: e286d74163ea3524dfcbd92553c0c4254b667e4ea13adae7468c0d1dc4c8089b
+  metadata.gz: 58e5d405e39f42d0e5287d47dd65c65b39a0ab5a2fc7fde3fd85c7211469e6e1
+  data.tar.gz: 7100a73ce192536f81a34ffbb1b431a793edf9cb71c1612a547a64a686a8330f
 SHA512:
-  metadata.gz: a89e58bc0447ecbd2eefdd81fe978a5e38438296bcce9dbf18b4dbc3fea5d5740016e35237d229fbab8201bb0e71b208ca66858c9d61e85f4d31d729e9048054
-  data.tar.gz: 45ddf90be0abe97dcd8aac6b08b9daeac2f68f7634062655efee6f59fbef50c6aad3eb69a461b4f7fcf9dd2751fa735de82e9a0821ec18d2f45cb4bada591698
+  metadata.gz: 3b8fcbab2e2aa1f02dc0b51051a9b60dd2518b18b72007c2f3e77fa99248e864069d54b0bb43d783f8bb6ef79b6c2504c8cd05c244a2e9c85cddb882de224556
+  data.tar.gz: 3ec5120d8b6e365996985c75f4c291e3f4805e9876fd93ae2dfe071c5bd69ad751677cf71121ac23f6e9bed75ab80296b12346d79696cb6105974345d289bb7e

data/CHANGELOG.md

@@ -1,5 +1,13 @@
 # Xsv Changelog
 
+## 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 +127,4 @@ 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

@@ -85,7 +85,7 @@ 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/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Xsv
-  VERSION = "1.1.1"
+  VERSION = "1.2.0"
 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: 1.2.0
 platform: ruby
 authors:
 - Martijn Storck
 autorequire:
 bindir: exe
 cert_chain: []
-date: 2022-04-01 00:00:00.000000000 Z
+date: 2023-01-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip