rika 2.0.2-java → 2.0.4-java

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 350fd4a9478c68bea286f43ea43fe7199899fb6124115615d7e023d781845b8b
-  data.tar.gz: d9470eb7cd432acac089e1f1dc030a414096c87ab8720fa79ebd6cfe16ac4528
+  metadata.gz: 1a4cc1c56edb22131c3409bbaee3617febac8d40ba3aed28600cde997d93d465
+  data.tar.gz: 8b38c319ca598ab107762222bc0b097bcf5001aaf53fc1c33e912cff83ff7997
 SHA512:
-  metadata.gz: 82961b39e1df54bd5ef83be432a1391a021537beea8ab63e7870f41ecec56457fd87c13fcdb3b3df848b520344ccbad69fd7d58b5c4c4b4ad2590381fc4dbca2
-  data.tar.gz: 2e9edfc485e6e2f43299ac34e0bcef47e752b5a3a76d0970f84a7880612619ba41d3adab011000199728847a11f53232515a5893bf084abbd51c41bf3f8c50b6
+  metadata.gz: 1cfea7c20c8c2b294ff6a5d29877cc4670034ac6c58ac299bd5b3ac716d55bc4f1df39843d7c3a33776186ca73d7652747e8853fc914f114e2ecef16e8b26278
+  data.tar.gz: c6c5aeef86b5e9b2cba4b31f395602f94b8c1094975f5543c388175cb619c34c87258ade2043cc0faa47cff7f5bbb87f85e298179faaa4465e96e47647b1bfe0

data/Gemfile

@@ -6,11 +6,11 @@ source 'https://rubygems.org'
 gemspec
 
 group :development do
-  gem 'pry'
-  gem 'rake', '~> 13.0'
-  gem 'rspec', '~> 3.9'
-  gem 'rubocop'
-  gem 'rubocop-rspec'
-  gem 'simplecov', require: false
-  gem 'webrick', '~> 1.6'
+  gem 'pry', '~> 0.14', '>= 0.14.2'
+  gem 'rake', '~> 13.2', '>= 13.2.1'
+  gem 'rspec', '~> 3.13', '>= 3.13.0'
+  gem 'rubocop', '~> 1.65', '>= 1.65.1'
+  gem 'rubocop-rspec', '~> 3.0', '>= 3.0.3'
+  gem 'simplecov', '~>0.22', '>= 0.22.0', require: false
+  gem 'webrick', '~> 1.8', '>= 1.8.1'
 end

data/README.md

@@ -82,6 +82,10 @@ specify one or more filespecs or URL's as arguments:
 ```bash
 rika x.pdf https://github.com/keithrbennett/rika
 ```
+
+> [!NOTE]
+> If running `rika` produces an error indicating that the JRuby interpreter cannot be found, try preceding it with `jruby`, e.g. `jruby rika x.pdf`.
+
 Here is the help text:
 
 ```
@@ -245,6 +249,14 @@ rexe -in -oJ -mb 'downcase \
 This gem has been tested with JRuby managed by rvm.  It should work with other Ruby version managers and
 without any version manager at all, but those configurations have not been tested.
 
+## Using the Tika Java Jar File Directly
+
+Rika provides only the most common Tika use cases.  You may want to dig deeper than Rika does into the massive amount
+of functionality provided by the Tika library. You can do so by bypassing Rika altogether and using the Tika jar file
+directly in your own JRuby code. In addition. Tika provides its own command line application that can be called as, 
+for example, `java -jar $TIKA_JAR_FILESPEC --help`. This Tika command line application has finer grained control
+over some Tika options, but is missing some conveniences provided by the Rika command line application.
+
 ## Other Tika Resources
 
 * The Apache Tika wiki is at https://cwiki.apache.org/confluence/display/tika.
@@ -265,3 +277,8 @@ without any version manager at all, but those configurations have not been teste
 3. Commit your changes (`git commit -am 'Add some feature'`)
 4. Push to the branch (`git push origin my-new-feature`)
 5. Create new Pull Request
+
+## Acknowledgments
+
+Many thanks to the brilliant and dedicated developers who have worked to build Apache Tika since its inception many years ago.
+

data/RELEASE_NOTES.md

@@ -1,5 +1,15 @@
 ## Release Notes
 
+### 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.
+* Update gem dependencies.
+
 #### v2.0.2
 
 * Now prints source name on line with header and footer lines.

data/lib/rika/cli/args_parser.rb

@@ -126,6 +126,7 @@ 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:
@@ -32,6 +33,13 @@ class RikaCommand
       puts result_array_output
     else
       targets.each do |target|
+        # If we don't do this, Tika will raise an org.apache.tika.exception.ZeroByteFileException
+        # TODO: Do same for URL?
+        if File.file?(target) && File.zero?(target)
+          $stderr.puts("\n\nFile empty!: #{target}\n\n")
+          next
+        end
+
         result = Rika.parse(target, max_content_length: max_content_length, key_sort: options[:key_sort])
         puts single_document_output(target, result)
       end

data/lib/rika/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module Rika
-  VERSION = '2.0.2'
+  VERSION = '2.0.4'
 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/rika.gemspec

@@ -17,7 +17,7 @@ Gem::Specification.new do |gem|
   gem.files         = `git ls-files`.split($INPUT_RECORD_SEPARATOR)
   gem.executables   = gem.files.grep(%r{^bin/}).map { |f| File.basename(f) }
   gem.require_paths = ['lib']
-  gem.add_dependency 'awesome_print'
+  gem.add_dependency 'awesome_print', '~> 1.9', '>= 1.9.2'
   gem.platform = 'java'
   gem.license = 'MIT'
   gem.metadata['rubygems_mfa_required'] = 'true'

data/spec/fixtures/something.txt

@@ -0,0 +1 @@
+something

data/spec/rika/cli/rika_command_spec.rb

@@ -135,4 +135,21 @@ describe RikaCommand do
       expect(line).to match("Source: #{sample_filespec}")
     end
   end
+
+  describe 'empty file behavior' do
+    let(:empty_file_path) { fixture_path('empty.txt') }
+    let(:something_file_path) { fixture_path('something.txt') } # containts "something"
+
+    specify 'parsing an empty file outputs a message to stderr' do
+      expect {
+        described_class.new([empty_file_path]).call
+      }.to output("\n\nFile empty!: #{empty_file_path}\n\n").to_stderr
+    end
+
+    specify 'parsing an empty file does not interrupt parsing of subsequent files' do
+      expect {
+        described_class.new([empty_file_path, something_file_path]).call
+      }.to output(/something/).to_stdout
+    end
+  end
 end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: rika
 version: !ruby/object:Gem::Version
-  version: 2.0.2
+  version: 2.0.4
 platform: java
 authors:
 - Richard Nyström
@@ -9,22 +9,28 @@ authors:
 autorequire:
 bindir: bin
 cert_chain: []
-date: 2023-10-07 00:00:00.000000000 Z
+date: 2025-02-01 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   requirement: !ruby/object:Gem::Requirement
     requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.9.2
   name: awesome_print
   prerelease: false
   type: :runtime
   version_requirements: !ruby/object:Gem::Requirement
     requirements:
+    - - "~>"
+      - !ruby/object:Gem::Version
+        version: '1.9'
     - - ">="
       - !ruby/object:Gem::Version
-        version: '0'
+        version: 1.9.2
 description: A JRuby wrapper for Apache Tika to extract text and metadata from files
   of various formats.
 email:
@@ -60,6 +66,7 @@ files:
 - spec/fixtures/document.docx
 - spec/fixtures/document.pdf
 - spec/fixtures/document.txt
+- spec/fixtures/empty.txt
 - spec/fixtures/en.txt
 - spec/fixtures/es.txt
 - spec/fixtures/fr.txt
@@ -67,6 +74,7 @@ files:
 - spec/fixtures/image_jpg_without_extension
 - spec/fixtures/lang_cant_be_determined.txt
 - spec/fixtures/ru.txt
+- spec/fixtures/something.txt
 - spec/fixtures/tiny.txt
 - spec/fixtures/unknown.bin
 - spec/rika/cli/args_parser_spec.rb
@@ -77,6 +85,7 @@ 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
@@ -103,7 +112,7 @@ required_rubygems_version: !ruby/object:Gem::Requirement
     - !ruby/object:Gem::Version
       version: '0'
 requirements: []
-rubygems_version: 3.3.26
+rubygems_version: 3.1.6
 signing_key:
 specification_version: 4
 summary: A JRuby wrapper for Apache Tika to extract text and metadata from files of