xsv 1.3.1 → 1.4.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 9f753b006d8a3c230447e56b70824c7df929c5b7bd074ec82cf82acdf971073c
-  data.tar.gz: bb457169f14d259526443ff2afa47477dceb13edf13d99f089e2f843f9fa258f
+  metadata.gz: 6c27d848984359d8f492658ca2634981f6f05b66c75711ccce305f794ff04530
+  data.tar.gz: 69cb487a9c42dd09b980f3d1170f39f39f0176109bbdc332c529eab4fbc2a298
 SHA512:
-  metadata.gz: e3686372d118d3d3ca17c403e34479ab00168f0ba5b2057b624cf0b90ed4ee28caf7f9237201c5f6649a7435adc2b77e29751eeec90a71ec577acfcbca2ff0b2
-  data.tar.gz: '094d7b47e71c7ad96b1a477e672c2615203f814cc475cc6194772e8e048713d36e58780c9dbe17a2239a4a63869eea3cde8cbcc20a7dd07816cde9519ff6a2e7'
+  metadata.gz: 8001b27aec710a21ce6860bf3b7a9f37dad27ba4cef797df533df8092c3a61a3851836c8504bca3a0bff8f57dafe4ae2ea296ea7a554a9558b3d807ca9f0b62e
+  data.tar.gz: d397dc3daaccda23e5160fd6b71342fc69c57fed98276da65ef0691908afb751310c3c8f8d6ebc7b6b7b90b4e604a57e635919b7456ae64694703a7c7cf1aab4

data/.github/workflows/ruby.yml

@@ -19,7 +19,7 @@ jobs:
     runs-on: ubuntu-latest
     strategy:
       matrix:
-        ruby-version: ['2.7', '3.0', '3.1', '3.2', '3.3', 'jruby', 'truffleruby']
+        ruby-version: ['3.2', '3.3', '3.4', '4.0', 'jruby', 'truffleruby']
 
     steps:
     - uses: actions/checkout@v3

data/CHANGELOG.md

@@ -1,9 +1,24 @@
 # Xsv Changelog
 
-## 1.3.1 2023-05-06
+## 1.4.0 2026-01-29
 
-- Fix issue #56 with multiple nil headers 
-- Ignore colums with a `nil` header in hash mode
+- Ruby 2.7, 3.0, and 3.1 are no longer supported. Xsv is now compatible with Ruby 3.2 through 4.0, latest JRuby, and latest TruffleRuby
+- Add compatibility with Rubyzip 3
+- Fix UTF-8 encoding issues when parsing XML with multi-byte characters
+- Handle incomplete UTF-8 sequences at chunk boundaries in the streaming XML parser
+- Fix parsing of rows without the `r` attribute (thanks @romanbsd)
+- Performance: avoid calling `unescapeHTML` unless there are entities in the text
+- Fix typos in CHANGELOG (thanks @jdufresne)
+
+## 1.3.2 2024-12-25
+
+- Xsv is now compatible with Ruby 2.7 through 3.4, latest JRuby, and latest TruffleRuby
+- Sheet#each_row returns Enumerator when no block is given (thanks @myabc)
+
+## 1.3.1 2024-05-06
+
+- Fix issue #56 with multiple nil headers
+- Ignore columns with a `nil` header in hash mode
 
 ## 1.3.0 2023-12-16
 

data/README.md

@@ -34,8 +34,8 @@ Or install it yourself as:
 
     $ gem install xsv
 
-Xsv targets ruby >= 2.7 and has a just single dependency, `rubyzip`. It has been
-tested successfully with MRI, JRuby, and TruffleRuby. It has no native extensions
+Xsv targets Ruby >= 3.2 and has just a single dependency, `rubyzip`. It has been
+tested successfully with MRI (including Ruby 4.0), JRuby, and TruffleRuby. It has no native extensions
 and is designed to be thread-safe.
 
 ## Usage

data/lib/xsv/helpers.rb

@@ -74,7 +74,7 @@ module Xsv
       # Compensate for rounding errors
       if minutes >= 60
         hours += (minutes / 60)
-        minutes = minutes % 60
+        minutes %= 60
       end
 
       format("%02d:%02d", hours, minutes)

data/lib/xsv/sax_parser.rb

@@ -4,7 +4,48 @@ require "cgi"
 
 module Xsv
   class SaxParser
-    ATTR_REGEX = /((\p{Alnum}+)="(.*?)")/mn
+    ATTR_REGEX = /((\p{Alnum}+)="(.*?)")/m
+
+    # Returns the number of bytes to trim from the end of a UTF-8 string
+    # to avoid splitting a multi-byte character. Returns 0 if the string
+    # ends with a complete character.
+    def self.incomplete_utf8_tail_size(bytes)
+      return 0 if bytes.empty?
+
+      # Check up to 3 bytes from the end (max UTF-8 char is 4 bytes)
+      check_length = [bytes.bytesize, 3].min
+      tail = bytes.byteslice(-check_length, check_length)
+
+      tail.each_byte.with_index.reverse_each do |byte, i|
+        # Check if this is a leading byte (starts a multi-byte sequence)
+        if byte >= 0xC0 # 11000000 - start of multi-byte sequence
+          # i is position in tail, bytes after leading byte = check_length - i - 1
+          # total bytes in sequence = 1 (leading) + continuation bytes = check_length - i
+          bytes_in_sequence = check_length - i
+
+          # Determine expected length from leading byte
+          expected_length = if byte >= 0xF0 # 11110xxx - 4 byte sequence
+            4
+          elsif byte >= 0xE0 # 1110xxxx - 3 byte sequence
+            3
+          else # 110xxxxx - 2 byte sequence
+            2
+          end
+
+          # If we don't have enough bytes, this sequence is incomplete
+          return bytes_in_sequence if bytes_in_sequence < expected_length
+
+          # Sequence is complete
+          return 0
+        elsif byte < 0x80
+          # ASCII byte - string ends with complete character
+          return 0
+        end
+        # else: continuation byte (10xxxxxx), keep looking for leading byte
+      end
+
+      0
+    end
 
     def parse(io)
       responds_to_end_element = respond_to?(:end_element)
@@ -16,17 +57,36 @@ module Xsv
         eof_reached = true
         must_read = false
       else
-        pbuf = String.new(capacity: 8192)
+        pbuf = String.new(capacity: 8192, encoding: "utf-8")
         eof_reached = false
         must_read = true
       end
+      leftover = String.new(encoding: "binary")
 
       loop do
         if must_read
           begin
-            pbuf << io.sysread(2048)
-          rescue EOFError, TypeError
-            # EOFError is thrown by IO, rubyzip returns nil from sysread on EOF
+            chunk = io.sysread(2048)
+            if chunk
+              # Prepend any leftover bytes from previous incomplete UTF-8 sequence
+              chunk = leftover << chunk unless leftover.empty?
+
+              # Check if chunk ends with incomplete UTF-8 sequence
+              trim = SaxParser.incomplete_utf8_tail_size(chunk)
+              if trim > 0
+                leftover = chunk.byteslice(-trim, trim)
+                chunk = chunk.byteslice(0, chunk.bytesize - trim)
+              else
+                leftover = String.new(encoding: "binary")
+              end
+
+              pbuf << chunk.force_encoding("utf-8")
+            else
+              # rubyzip < 3 returns nil from sysread on EOF
+              eof_reached = true
+            end
+          rescue EOFError
+            # EOFError is thrown by IO and rubyzip >= 3
             eof_reached = true
           end
 
@@ -38,7 +98,11 @@ module Xsv
             chars = pbuf.slice!(0, o + 1).chop!.force_encoding("utf-8")
 
             if responds_to_characters && !chars.empty?
-              characters(CGI.unescapeHTML(chars))
+              if chars.include?("&")
+                characters(CGI.unescapeHTML(chars))
+              else
+                characters(chars)
+              end
             end
 
             state = :look_end
@@ -75,7 +139,7 @@ module Xsv
               start_element(tag_name, nil)
             else
               attribute_buffer = {}
-              attributes = args.scan(ATTR_REGEX)
+              attributes = args.force_encoding("utf-8").scan(ATTR_REGEX)
               while (attr = attributes.delete_at(0))
                 attribute_buffer[attr[1].to_sym] = attr[2]
               end

data/lib/xsv/sheet.rb

@@ -55,6 +55,8 @@ module Xsv
 
     # Iterate over rows, returning either hashes or arrays based on the current mode.
     def each_row(&block)
+      return to_enum(__method__) unless block
+
       @io.rewind
       SheetRowsHandler.new(@mode, @headers, empty_row, @workbook, @row_skip, @last_row, &block).parse(@io)
       true

data/lib/xsv/sheet_rows_handler.rb

@@ -34,7 +34,12 @@ module Xsv
         @store_characters = true
       when "row"
         @current_row = (@mode == :array) ? [] : @empty_row.dup
-        @current_row_number = attrs[:r].to_i
+        if attrs[:r]
+          @current_row_number = attrs[:r].to_i
+        else
+          # Use position-based numbering when r attribute is missing
+          @current_row_number += 1
+        end
       end
     end
 

data/lib/xsv/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Xsv
-  VERSION = "1.3.1"
+  VERSION = "1.4.0"
 end

data/xsv.gemspec

@@ -36,12 +36,12 @@ Gem::Specification.new do |spec|
   spec.executables = spec.files.grep(%r{^exe/}) { |f| File.basename(f) }
   spec.require_paths = ["lib"]
 
-  spec.required_ruby_version = ">= 2.7"
+  spec.required_ruby_version = ">= 3.2"
 
-  spec.add_dependency "rubyzip", ">= 1.3", "< 3"
+  spec.add_dependency "rubyzip", ">= 1.3", "< 4"
 
-  spec.add_development_dependency "bundler", "< 3"
-  spec.add_development_dependency "rake", "~> 13.1.0"
-  spec.add_development_dependency "minitest", "~> 5.20.0"
-  spec.add_development_dependency "standard", "~> 1.32.1"
+  spec.add_development_dependency "bundler"
+  spec.add_development_dependency "rake", "~> 13.2"
+  spec.add_development_dependency "minitest", "~> 5.24"
+  spec.add_development_dependency "standard", "~> 1.44"
 end

metadata

@@ -1,14 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: xsv
 version: !ruby/object:Gem::Version
-  version: 1.3.1
+  version: 1.4.0
 platform: ruby
 authors:
 - Martijn Storck
-autorequire:
 bindir: exe
 cert_chain: []
-date: 2024-05-06 00:00:00.000000000 Z
+date: 2026-01-29 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -19,7 +18,7 @@ dependencies:
         version: '1.3'
     - - "<"
       - !ruby/object:Gem::Version
-        version: '3'
+        version: '4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -29,63 +28,63 @@ dependencies:
         version: '1.3'
     - - "<"
       - !ruby/object:Gem::Version
-        version: '3'
+        version: '4'
 - !ruby/object:Gem::Dependency
   name: bundler
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - "<"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3'
+        version: '0'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - "<"
+    - - ">="
       - !ruby/object:Gem::Version
-        version: '3'
+        version: '0'
 - !ruby/object:Gem::Dependency
   name: rake
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 13.1.0
+        version: '13.2'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 13.1.0
+        version: '13.2'
 - !ruby/object:Gem::Dependency
   name: minitest
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 5.20.0
+        version: '5.24'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 5.20.0
+        version: '5.24'
 - !ruby/object:Gem::Dependency
   name: standard
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.32.1
+        version: '1.44'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.32.1
+        version: '1.44'
 description: |2
                               Xsv is a fast, lightweight parser for Office Open XML spreadsheet files
                               (commonly known as Excel or .xlsx files). It strives to be minimal in the
@@ -128,7 +127,6 @@ metadata:
   homepage_uri: https://github.com/martijn/xsv
   source_code_uri: https://github.com/martijn/xsv
   changelog_uri: https://raw.githubusercontent.com/martijn/xsv/main/CHANGELOG.md
-post_install_message:
 rdoc_options: []
 require_paths:
 - lib
@@ -136,15 +134,14 @@ required_ruby_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
-      version: '2.7'
+      version: '3.2'
 required_rubygems_version: !ruby/object:Gem::Requirement
   requirements:
   - - ">="
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.5.1
-signing_key:
+rubygems_version: 3.6.2
 specification_version: 4
 summary: A fast and lightweight xlsx parser that provides nothing a CSV parser wouldn't
 test_files: []