hwayo 0.1.0

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA256:
+  metadata.gz: 6b649626b8aa64f7e09efcca03cbc6aaf09564fa7fedd669603f58df2cd2255e
+  data.tar.gz: d3390414f88e33b5c25d0219d9cc41a9b12674b3d52f180a225bd9eb4768364e
+SHA512:
+  metadata.gz: 83f850bf7491f9c6d0caf3b0ede1720d82b6c9c7e8644b0b2d4735622b343e07036f980eaefd115bda21a374ac8d93533efb1773c38e042226ee2b7b8a307d4b
+  data.tar.gz: 20916130d516ddd212721212ae518851b92efba543868bf49b0006c76d4ebf531b9f23493be6f262d98b74d0c06ef54d6d81b3bcf7054f9e9465329428b0fe9b

data/README.md

@@ -0,0 +1,74 @@
+# Hwayo
+
+Hwayo는 한글(HWP) 파일에서 텍스트를 추출하는 Ruby gem입니다. Java 기반의 hwplib 라이브러리를 Ruby에서 사용할 수 있도록 래핑하였습니다.
+
+## 설치
+
+Gemfile에 다음을 추가하세요:
+
+```ruby
+gem 'hwayo'
+```
+
+그리고 실행:
+
+    $ bundle install
+
+또는 직접 설치:
+
+    $ gem install hwayo
+
+## 사용법
+
+### 기본 사용법
+
+```ruby
+require 'hwayo'
+
+# HWP 파일에서 텍스트 추출
+result = Hwayo.extract_text('document.hwp')
+
+if result[:success]
+  puts result[:text]
+else
+  puts "Error: #{result[:error]}"
+end
+```
+
+### 파일로 저장
+
+```ruby
+# 추출한 텍스트를 파일로 저장
+result = Hwayo.extract_text('document.hwp', 'output.txt')
+
+if result[:success]
+  puts "Text saved to: #{result[:output_path]}"
+else
+  puts "Error: #{result[:error]}"
+end
+```
+
+## 요구사항
+
+- Ruby 2.7.0 이상
+- Java 8 이상 (JAVA_HOME 환경변수 설정 필요)
+- MRI Ruby의 경우 RJB gem 필요 (자동 설치됨)
+- JRuby의 경우 추가 설정 없이 사용 가능
+
+## 개발
+
+이 gem을 개발하려면:
+
+1. 저장소를 클론합니다
+2. `bin/setup`을 실행하여 의존성을 설치합니다
+3. `rake spec`을 실행하여 테스트를 실행합니다
+4. `bin/console`을 실행하여 대화형 프롬프트를 시작합니다
+
+## 기여
+
+버그 리포트와 풀 리퀘스트는 GitHub에서 환영합니다.
+
+## 라이선스
+
+이 gem은 [MIT License](https://opensource.org/licenses/MIT)로 제공됩니다.
+hwplib은 [Apache License 2.0](https://www.apache.org/licenses/LICENSE-2.0)으로 제공됩니다.

data/Rakefile

@@ -0,0 +1,4 @@
+# frozen_string_literal: true
+
+require "bundler/gem_tasks"
+task default: %i[]

data/lib/hwayo/extractor.rb

@@ -0,0 +1,123 @@
+# frozen_string_literal: true
+
+require 'tempfile'
+
+module Hwayo
+  class Extractor
+    def initialize
+      @java_loaded = false
+      load_java_dependencies
+    end
+    
+    def extract_text(hwp_file_path, output_path = nil)
+      raise Error, "HWP file not found: #{hwp_file_path}" unless File.exist?(hwp_file_path)
+      
+      ensure_java_loaded
+      
+      begin
+        # HWP 파일 읽기
+        hwp_file = @hwp_reader.fromFile(hwp_file_path)
+        
+        # 텍스트 추출 옵션 설정
+        option = @text_extract_option.new
+        option.setMethod(@text_extract_method.InsertControlTextBetweenParagraphText)
+        option.setWithControlChar(false)
+        option.setAppendEndingLF(true)
+        
+        # 텍스트 추출
+        extracted_text = @text_extractor.extract(hwp_file, option)
+        
+        # 결과 저장 또는 반환
+        if output_path
+          File.write(output_path, extracted_text, encoding: 'UTF-8')
+          { success: true, text: extracted_text, output_path: output_path }
+        else
+          { success: true, text: extracted_text }
+        end
+        
+      rescue => e
+        { success: false, error: "Failed to extract text: #{e.message}" }
+      end
+    end
+    
+    private
+    
+    def load_java_dependencies
+      if RUBY_PLATFORM == 'java'
+        # JRuby environment
+        require 'java'
+        load_jruby_dependencies
+      else
+        # MRI Ruby with RJB
+        begin
+          require 'rjb'
+          load_rjb_dependencies
+        rescue LoadError
+          raise Error, "RJB gem is required for Java integration. Please install it: gem install rjb"
+        end
+      end
+    end
+    
+    def load_jruby_dependencies
+      jar_path = File.expand_path('../java/hwplib-1.1.10.jar', __dir__)
+      raise Error, "hwplib JAR not found at: #{jar_path}" unless File.exist?(jar_path)
+      
+      require jar_path
+      
+      @hwp_reader = Java::KrDogfootHwplibReader::HWPReader
+      @text_extractor = Java::KrDogfootHwplibToolTextextractor::TextExtractor
+      @text_extract_option = Java::KrDogfootHwplibToolTextextractor::TextExtractOption
+      @text_extract_method = Java::KrDogfootHwplibToolTextextractor::TextExtractMethod
+      
+      @java_loaded = true
+    end
+    
+    def load_rjb_dependencies
+      return if @java_loaded
+      
+      jar_path = File.expand_path('../java/hwplib-1.1.10.jar', __dir__)
+      raise Error, "hwplib JAR not found at: #{jar_path}" unless File.exist?(jar_path)
+      
+      # Set JAVA_HOME if not set
+      ENV['JAVA_HOME'] ||= detect_java_home
+      
+      # Load RJB with the JAR file
+      Rjb::load(jar_path, ['-Xmx512m'])
+      
+      # Import Java classes
+      @hwp_reader = Rjb::import('kr.dogfoot.hwplib.reader.HWPReader')
+      @text_extractor = Rjb::import('kr.dogfoot.hwplib.tool.textextractor.TextExtractor')
+      @text_extract_option = Rjb::import('kr.dogfoot.hwplib.tool.textextractor.TextExtractOption')
+      @text_extract_method = Rjb::import('kr.dogfoot.hwplib.tool.textextractor.TextExtractMethod')
+      
+      @java_loaded = true
+    end
+    
+    def ensure_java_loaded
+      load_rjb_dependencies unless @java_loaded
+    end
+    
+    def detect_java_home
+      # Try common Java installation paths
+      possible_java_homes = [
+        '/usr/libexec/java_home -V 2>&1 | grep -E "1\.(8|11)" | head -1 | awk \'{print $NF}\'',
+        '/usr/lib/jvm/java-11-openjdk-amd64',
+        '/usr/lib/jvm/java-8-openjdk-amd64',
+        '/Library/Java/JavaVirtualMachines/jdk-11.jdk/Contents/Home',
+        '/Library/Java/JavaVirtualMachines/jdk1.8.0_*.jdk/Contents/Home'
+      ]
+      
+      if system('which java > /dev/null 2>&1')
+        java_home = `echo $(/usr/libexec/java_home 2>/dev/null)`.strip
+        return java_home unless java_home.empty?
+      end
+      
+      possible_java_homes.each do |path|
+        expanded_path = File.expand_path(path)
+        return expanded_path if File.directory?(expanded_path)
+      end
+      
+      raise Error, "Java not found. Please install Java 8 or later and set JAVA_HOME environment variable."
+    end
+  end
+end

data/lib/hwayo/simple_extractor.rb

@@ -0,0 +1,65 @@
+# frozen_string_literal: true
+
+require 'open3'
+require 'tempfile'
+
+module Hwayo
+  class SimpleExtractor
+    def extract_text(hwp_file_path, output_path = nil)
+      raise Error, "HWP file not found: #{hwp_file_path}" unless File.exist?(hwp_file_path)
+      
+      # Java 실행 가능 여부 확인
+      unless system('java -version > /dev/null 2>&1')
+        return { success: false, error: "Java is not installed. Please install Java 8 or later." }
+      end
+      
+      # JAR 파일 경로
+      jar_path = File.expand_path('../java/hwplib-1.1.10.jar', __dir__)
+      
+      # JAR 파일이 없으면 대체 경로 시도
+      unless File.exist?(jar_path)
+        # 개발 환경에서 직접 실행하는 경우
+        alt_jar_path = File.expand_path('../../../target/hwplib-1.1.10.jar', __dir__)
+        if File.exist?(alt_jar_path)
+          jar_path = alt_jar_path
+        else
+          return { success: false, error: "hwplib JAR not found" }
+        end
+      end
+      
+      # 임시 출력 파일
+      temp_output = Tempfile.new(['hwp_output', '.txt'])
+      
+      begin
+        # Java 클래스 실행
+        cmd = [
+          'java',
+          '-cp', jar_path,
+          'kr.dogfoot.hwplib.sample.Extracting_Text',
+          hwp_file_path,
+          temp_output.path
+        ]
+        
+        stdout, stderr, status = Open3.capture3(*cmd)
+        
+        if status.success?
+          extracted_text = File.read(temp_output.path, encoding: 'UTF-8')
+          
+          # 결과 저장
+          if output_path
+            File.write(output_path, extracted_text, encoding: 'UTF-8')
+            { success: true, text: extracted_text, output_path: output_path }
+          else
+            { success: true, text: extracted_text }
+          end
+        else
+          { success: false, error: "Java execution failed: #{stderr}" }
+        end
+        
+      ensure
+        temp_output.close
+        temp_output.unlink
+      end
+    end
+  end
+end

data/lib/hwayo/version.rb

@@ -0,0 +1,5 @@
+# frozen_string_literal: true
+
+module Hwayo
+  VERSION = "0.1.0"
+end

data/lib/hwayo.rb

@@ -0,0 +1,88 @@
+# frozen_string_literal: true
+
+require_relative "hwayo/version"
+require 'open3'
+require 'tempfile'
+
+module Hwayo
+  class Error < StandardError; end
+  
+  # Extract text from HWP file
+  def self.extract_text(hwp_file_path, output_path = nil)
+    raise Error, "HWP file not found: #{hwp_file_path}" unless File.exist?(hwp_file_path)
+    
+    # Java 실행 가능 여부 확인
+    unless system('java -version > /dev/null 2>&1')
+      return { success: false, error: "Java is not installed. Please install Java 8 or later." }
+    end
+    
+    # JAR 파일 경로 찾기
+    jar_path = find_jar_path
+    unless jar_path
+      return { success: false, error: "hwplib JAR not found. Please ensure hwplib-1.1.10.jar is in the gem's lib/hwayo/java directory or in the current directory." }
+    end
+    
+    # CLI 클래스 경로 찾기
+    cli_class_path = find_cli_class(jar_path)
+    unless cli_class_path
+      return { success: false, error: "HWPTextExtractorCLI.class not found" }
+    end
+    
+    # 임시 출력 파일
+    temp_output = output_path || Tempfile.new(['hwp_output', '.txt']).path
+    
+    begin
+      # Java 명령 실행
+      cmd = [
+        'java',
+        '-cp', "#{jar_path}:#{cli_class_path}",
+        'HWPTextExtractorCLI',
+        hwp_file_path,
+        temp_output
+      ]
+      
+      stdout, stderr, status = Open3.capture3(*cmd)
+      
+      if status.success? && stdout.strip == "SUCCESS"
+        extracted_text = File.read(temp_output, encoding: 'UTF-8')
+        
+        result = { success: true, text: extracted_text }
+        result[:output_path] = output_path if output_path
+        result
+      else
+        { success: false, error: "Extraction failed: #{stderr}" }
+      end
+      
+    ensure
+      # 임시 파일 정리
+      File.unlink(temp_output) if !output_path && File.exist?(temp_output)
+    end
+  end
+  
+  private
+  
+  def self.find_jar_path
+    possible_paths = [
+      # gem 내부
+      File.expand_path('../hwayo/java/hwplib-1.1.10.jar', __FILE__),
+      # 현재 디렉토리
+      'hwplib-1.1.10.jar',
+      'target/hwplib-1.1.10.jar',
+      # 환경 변수
+      ENV['HWPLIB_JAR_PATH']
+    ].compact
+    
+    possible_paths.find { |path| path && File.exist?(path) }
+  end
+  
+  def self.find_cli_class(jar_dir)
+    jar_directory = File.dirname(jar_dir)
+    possible_paths = [
+      jar_directory,
+      '.',
+      File.expand_path('../hwayo/java', __FILE__)
+    ]
+    
+    possible_paths.find { |path| File.exist?(File.join(path, 'HWPTextExtractorCLI.class')) }
+  end
+end

data/sig/hwayo.rbs

@@ -0,0 +1,4 @@
+module Hwayo
+  VERSION: String
+  # See the writing guide of rbs: https://github.com/ruby/rbs#guides
+end

metadata

@@ -0,0 +1,54 @@
+--- !ruby/object:Gem::Specification
+name: hwayo
+version: !ruby/object:Gem::Version
+  version: 0.1.0
+platform: ruby
+authors:
+- 이원섭wonsup Lee/Alfonso
+bindir: exe
+cert_chain: []
+date: 1980-01-02 00:00:00.000000000 Z
+dependencies: []
+description: Hwayo is a Ruby gem that wraps the hwplib Java library to extract text
+  from Korean HWP (Hangul Word Processor) files. It provides a simple interface to
+  extract text content from HWP documents using the Java hwplib library.
+email:
+- onesup.lee@gmail.com
+executables: []
+extensions: []
+extra_rdoc_files: []
+files:
+- README.md
+- Rakefile
+- lib/hwayo.rb
+- lib/hwayo/extractor.rb
+- lib/hwayo/java/HWPTextExtractorCLI.class
+- lib/hwayo/java/hwplib-1.1.10.jar
+- lib/hwayo/simple_extractor.rb
+- lib/hwayo/version.rb
+- sig/hwayo.rbs
+homepage: https://github.com/onesup/hwayo
+licenses:
+- MIT
+metadata:
+  homepage_uri: https://github.com/onesup/hwayo
+  source_code_uri: https://github.com/onesup/hwayo
+  changelog_uri: https://github.com/onesup/hwayo/blob/main/CHANGELOG.md
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: 2.7.0
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubygems_version: 3.6.9
+specification_version: 4
+summary: Ruby wrapper for hwplib - Extract text from HWP files
+test_files: []