xsv 1.3.2 → 1.4.1

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: e03874b3017fd111c7b63d68bb2273f406cab5e129b4edb174c2710aed0cbab9
-  data.tar.gz: 39ebe2ffdc657efd737f62026d9cc18a531262f4722189f3d2a3012a1e0885d9
+  metadata.gz: a0fb3d682de516914c72424844559dc8ac53ef4a3ba0b906c90f44261b2411fd
+  data.tar.gz: ca269e4b84ea4c5cb865d1cd5599cf18740e840f9f26d575f2065688950b7d2a
 SHA512:
-  metadata.gz: 95e8ea84b5a39cb1158f7f1a8eb531f00f76d94eacfa370d74080b943f213dbf6d5aa9df237b54896769f4ff9e3a0a1a1393863d832e6b9cf2ceb21e2069d711
-  data.tar.gz: 9b0392cebd9f720d0c716a99f8a179a4def088e90ed79721c40fdecba518365e1e23f8fb82bbf41dbb474329d44414b1742d375a44388a2fc56cd074c870b2f3
+  metadata.gz: 2cd6b2190e84323f58e2efc1cf8ff91ae625c9febb366886d4530178d1e0c5644ca10584fe237dff8f77e8644c300b874e2feabc32116293fbd9bd63514ed272
+  data.tar.gz: f27435b037cbc53d772dd57923f9f38aa4a3becd4f8c96d4ad7f79df45fac29ee804c0c62b0a57cf69f019f04304ae95c6229f3ed8f8cb7fcb7d8caa460bfbc3

data/.github/workflows/release.yml

@@ -0,0 +1,39 @@
+name: Release
+
+on:
+  push:
+    tags:
+      - 'v*'
+
+permissions:
+  contents: write
+
+jobs:
+  release:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+        with:
+          fetch-depth: 0  # Fetch all history for changelog generation
+
+      - name: Create GitHub Release
+        env:
+          GH_TOKEN: ${{ github.token }}
+        run: |
+          # Extract version from tag
+          VERSION=${GITHUB_REF#refs/tags/}
+
+          # Generate release notes from commits since previous tag
+          PREV_TAG=$(git describe --tags --abbrev=0 ${VERSION}^ 2>/dev/null || echo "")
+
+          if [ -n "$PREV_TAG" ]; then
+            NOTES=$(git log ${PREV_TAG}..${VERSION} --pretty=format:"- %s (%h)" --no-merges)
+          else
+            NOTES="Initial release"
+          fi
+
+          # Create the release
+          gh release create ${VERSION} \
+            --title "${VERSION}" \
+            --notes "${NOTES}" \
+            --verify-tag

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', '3.4', 'jruby', 'truffleruby']
+        ruby-version: ['3.2', '3.3', '3.4', '4.0', 'jruby', 'truffleruby']
 
     steps:
     - uses: actions/checkout@v3

data/CHANGELOG.md

@@ -1,14 +1,29 @@
 # Xsv Changelog
 
+## 1.4.1 2026-04-11
+
+- Add Range support to Sheet#[] (thanks @paddor)
+- Fix SheetBoundsHandler to detect rows with inlineStr cells (thanks @kikumiyako)
+
+## 1.4.0 2026-01-29
+
+- 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 compatbile with Ruby 2.7 through 3.4, latest JRuby, and latest TruffleRuby
+- 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 colums with a `nil` header in hash mode
+- 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/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

@@ -64,14 +64,26 @@ module Xsv
 
     alias_method :each, :each_row
 
-    # Get row by number, starting at 0. Returns either a hash or an array based on the current row.
+    # Get row by number or a range of rows, starting at 0. Returns either a hash or an array
+    # based on the current mode. When called with a Range, returns an array of rows.
     # If the specified index is out of bounds an empty row is returned.
-    def [](number)
-      each_with_index do |row, i|
-        return row if i == number
+    def [](number_or_range)
+      case number_or_range
+      when Range
+        rows = []
+        each_with_index do |row, i|
+          rows << row if number_or_range.cover?(i)
+        end
+        rows
+      when Integer
+        each_with_index do |row, i|
+          return row if i == number_or_range
+        end
+
+        empty_row
+      else
+        raise ArgumentError, "Expected Integer or Range, got #{number_or_range.class}"
       end
-
-      empty_row
     end
 
     # Load headers in the top row of the worksheet. After parsing of headers

data/lib/xsv/sheet_bounds_handler.rb

@@ -40,7 +40,7 @@ module Xsv
       when "c"
         @state = name
         @cell = attrs[:r]
-      when "v"
+      when "v", "is"
         col = column_index(@cell)
         @max_column = col if col > @max_column
         @max_row = @row if @row > @max_row

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 = "1.3.2"
+  VERSION = "1.4.1"
 end

data/xsv.gemspec

@@ -36,13 +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 "bundler"
   spec.add_development_dependency "rake", "~> 13.2"
   spec.add_development_dependency "minitest", "~> 5.24"
-  # Maintain Ruby 2.7 compatibility
-  spec.add_development_dependency "standard", "1.37.0"
+  spec.add_development_dependency "standard", "~> 1.44"
 end

metadata

@@ -1,13 +1,13 @@
 --- !ruby/object:Gem::Specification
 name: xsv
 version: !ruby/object:Gem::Version
-  version: 1.3.2
+  version: 1.4.1
 platform: ruby
 authors:
 - Martijn Storck
 bindir: exe
 cert_chain: []
-date: 2024-12-25 00:00:00.000000000 Z
+date: 2026-04-11 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rubyzip
@@ -18,7 +18,7 @@ dependencies:
         version: '1.3'
     - - "<"
       - !ruby/object:Gem::Version
-        version: '3'
+        version: '4'
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -28,21 +28,21 @@ 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
@@ -75,16 +75,16 @@ dependencies:
   name: standard
   requirement: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.37.0
+        version: '1.44'
   type: :development
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
-    - - '='
+    - - "~>"
       - !ruby/object:Gem::Version
-        version: 1.37.0
+        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
@@ -96,6 +96,7 @@ executables: []
 extensions: []
 extra_rdoc_files: []
 files:
+- ".github/workflows/release.yml"
 - ".github/workflows/ruby.yml"
 - ".gitignore"
 - ".standard.yml"
@@ -134,7 +135,7 @@ 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:
   - - ">="