rika 2.0.3-java → 2.1.0-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: d1ff6f1340908e2f573ac758ded769bf4a94db0835e06a436addf6dd9408b7ba
-  data.tar.gz: 6e99972c0cf72ab44b85e11847ed6685101c8498f2cd8c1a9a51237b2cc7ede2
+  metadata.gz: b7c8161615ba58a4b172722ebff7dad84ce2c828fdaa11f93277b99ec0b73916
+  data.tar.gz: bf76b6eebc07d3eba255ac14352f6b6807e842ae1ec2b3389afd027ec85b50c8
 SHA512:
-  metadata.gz: eaf3905403a4a0f66ace5a9658f1aa0ba77f153d67e588f094fbbe426b7cd4c30640c3f21652b8312493e4ad827719d6ff1d83a613b6ae0ff9a73164b179fd4e
-  data.tar.gz: dda02d0f0377f54db2fe59535c4b59b073c5fdcae3f1f8c6e66506427e34c248b923c2b01683a6ea811ca4a1ed45305b96739611a119d7dd244895e28fe7dac4
+  metadata.gz: 3b0fd15c3f94142966fada1c952b40873de2be4d2da064859ad44ccdec2fc44bf0d8637bf05a6543b89b015fb3ca15f15f26f721c7b3d9d6ce33568fac6f5868
+  data.tar.gz: 1055d3c63959dbcbf639aff24edc0040b5a2e1c1d4f834301912ffdc0010177be633f0567664b725bcaa916babb498f8123054a438718d06446c097b252f3294

data/README.md

@@ -144,6 +144,29 @@ If you find yourself using the same options over and over again, you can put the
 variable. For example, if the default behavior of sorting keys does not work for your language, you can disable it
 for all invocations of the `rika` command by specifying `-k-` in the RIKA_OPTIONS environment variable.
 
+### Using Wildcards for File Specification
+
+Rika now supports in-app expansion of wildcard patterns for file specification. This means you can quote wildcard patterns 
+to prevent the shell from expanding them, and Rika will handle the expansion internally:
+
+```bash
+# Let Rika handle the expansion (no practical limit on number of files)
+rika '**/*.pdf'
+
+# Shell expands wildcards (limited by shell's maximum argument length)
+rika **/*.pdf
+```
+
+This is particularly useful when dealing with large numbers of files, as shell expansion may hit command line length limits.
+In-app expansion has no practical limit on the number of files that can be processed.
+
+Supported wildcard patterns:
+- `*` - Match any number of characters
+- `?` - Match a single character
+- `[abc]` - Match one character from the set
+- `{a,b,c}` - Match any of the patterns a, b, or c
+- `**` - Recursive directory matching (match all files in all subdirectories)
+
 ### Machine Readable Data Support
 
 If both metadata and text are output, and the same output format is used for both, and that format is JSON

data/RELEASE_NOTES.md

@@ -1,5 +1,14 @@
 ## Release Notes
 
+### v2.1.0
+
+* Add ability to specify quoted wildcard filespecs on command line so Ruby will expand them.
+
+### v2.0.4
+
+* Fix uninitialized constant StringIO error (issue #16).
+
+
 ### v2.0.3
 
 * Fix parsing of empty files so they do not halt parsing of all files.

data/lib/rika/cli/args_parser.rb

@@ -94,10 +94,14 @@ class ArgsParser
   end
 
   # @return [Array] the targets specified on the command line, possibly expanded by the shell,
-  #   and with any directories removed.
+  #   and with any directories removed. If a target contains a wildcard pattern (*, ?, []),
+  #   it will be expanded using Dir.glob within Ruby, which has no practical limit on the number of files.
   private def create_target_array
-    targets = args.dup.reject { |arg| File.directory?(arg) }.freeze # reject dirs to handle **/* globbing
-    targets.map(&:freeze)
+    args.each_with_object([]) do |arg, result|
+      # Expand any potential globs and reject directories
+      files = Dir.glob(arg).reject { |file| File.directory?(file) }
+      result.concat(files)
+    end.map(&:freeze).freeze
   end
 
   # Fills in the second format option character if absent, and removes any excess characters
@@ -126,6 +130,7 @@ class ArgsParser
 
   # @return [String] string containing versions of Rika and Tika, with labels
   private def versions_string
-    "Versions: Rika: #{Rika::VERSION}, Tika: #{Rika.tika_version}"
+    java_version = Java::java.lang.System.getProperty("java.version")
+    "Versions: Rika: #{Rika::VERSION}, Tika: #{Rika.tika_version}, Java: #{java_version}"
   end
 end

data/lib/rika/cli/rika_command.rb

@@ -5,6 +5,7 @@ require 'optparse'
 require 'rika'
 require 'rika/formatters'
 require 'rika/cli/args_parser'
+require 'stringio'
 
 # This command line application enables the parsing of documents on the command line.
 # Syntax is:

data/lib/rika/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Rika
-  VERSION = '2.0.3'
+  VERSION = '2.1.0'
 end

data/lib/rika.rb

@@ -40,8 +40,9 @@ module Rika
   # @param [Integer] max_content_length maximum content length to return, defaults to all
   # @param [Detector] detector Tika detector, defaults to DefaultDetector
   # @return [ParseResult]
-  def self.parse(data_source, key_sort: true, max_content_length: -1, detector: DefaultDetector.new)
+  def self.parse(data_source, key_sort: true, max_content_length: -1, detector: nil)
     init
+    detector ||= DefaultDetector.new
     parser = Parser.new(data_source, key_sort: key_sort, max_content_length: max_content_length, detector: detector)
     parser.parse
   end

data/spec/rika/cli/args_parser_spec.rb

@@ -6,6 +6,7 @@ require 'rika/cli/args_parser'
 
 describe ArgsParser do
   let(:versions_regex) { /Versions:.*Rika: (\d+\.\d+\.\d+(-\w+)?).*Tika: (\d+\.\d+\.\d+(-\w+)?)/ }
+  let(:fixtures_dir) { File.expand_path(File.join(File.dirname(__FILE__), '../../fixtures')) }
 
   specify 'returns a hash of options, a target array, and help text' do
     options, targets, help_text = described_class.call([])
@@ -114,4 +115,42 @@ describe ArgsParser do
       expect(described_class::DEFAULT_OPTIONS).to be_frozen
     end
   end
+
+  describe '#create_target_array' do
+    let(:args_parser) { described_class.new }
+    
+    it 'removes directories from the target array' do
+      allow(args_parser).to receive(:args).and_return([fixtures_dir])
+      expect(args_parser.send(:create_target_array)).to be_empty
+    end
+    
+    it 'keeps regular files in the target array' do
+      tiny_filespec = fixture_path('tiny.txt')
+      allow(args_parser).to receive(:args).and_return([tiny_filespec])
+      expect(args_parser.send(:create_target_array)).to eq([tiny_filespec])
+    end
+    
+    context 'with wildcard patterns' do
+      it 'expands wildcard patterns using Dir.glob' do
+        pattern = fixture_path('*.txt')
+        allow(args_parser).to receive(:args).and_return([pattern])
+        
+        result = args_parser.send(:create_target_array)
+        # Verify we got at least one .txt file and no directories
+        expect(result).not_to be_empty
+        expect(result.all? { |f| f.end_with?('.txt') }).to be true
+      end
+      
+      it 'removes directories from the expanded results' do
+        # Use a pattern that will match both files and the fixtures dir
+        pattern = File.join(fixtures_dir, '*')
+        allow(args_parser).to receive(:args).and_return([pattern])
+        
+        result = args_parser.send(:create_target_array)
+        # Verify we got some files but no directories
+        expect(result).not_to be_empty
+        expect(result.any? { |f| File.directory?(f) }).to be false
+      end
+    end
+  end
 end

metadata

@@ -1,17 +1,17 @@
 --- !ruby/object:Gem::Specification
 name: rika
 version: !ruby/object:Gem::Version
-  version: 2.0.3
+  version: 2.1.0
 platform: java
 authors:
 - Richard Nyström
 - Keith Bennett
-autorequire:
 bindir: bin
 cert_chain: []
-date: 2024-08-02 00:00:00.000000000 Z
+date: 2025-04-20 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
+  name: awesome_print
   requirement: !ruby/object:Gem::Requirement
     requirements:
     - - "~>"
@@ -20,7 +20,6 @@ dependencies:
     - - ">="
       - !ruby/object:Gem::Version
         version: 1.9.2
-  name: awesome_print
   type: :runtime
   prerelease: false
   version_requirements: !ruby/object:Gem::Requirement
@@ -85,6 +84,7 @@ files:
 - spec/rika/rika_spec.rb
 - spec/rika/tika_loader_spec.rb
 - spec/spec_helper.rb
+- words.txt
 homepage: https://github.com/keithrbennett/rika
 licenses:
 - MIT
@@ -111,8 +111,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.26
-signing_key:
+rubygems_version: 3.6.3
 specification_version: 4
 summary: A JRuby wrapper for Apache Tika to extract text and metadata from files of
   various formats.