RubyGems - ebook_tools - Versions diffs - 0.0.1 - Mend

ebook_tools 0.0.1

Files changed (12) hide show

data/lib/utils.rb ADDED

@@ -0,0 +1,224 @@
+# encoding: UTF-8
+require 'levenshtein'
+require 'cgi'
+require 'pathname'
+require 'fileutils'
+require 'iconv'
+class Object
+  def blank?
+    respond_to?(:empty?) ? empty? : !self
+  end
+  def present?
+    !blank?
+  end
+end
+module Utils
+  extend self
+  # fixed_page_break
+  #  修复文本中的异常中断
+  # parameters:
+  #   +page_text+   文本内容
+  def fixed_page_break(page_text,options={})
+    page_lines = []
+    length = options[:length] || guess_content_line_length(page_text)
+    page_text.each_line do |line|
+      line.gsub!("\r\n","")
+      line.gsub!("\n","")
+      line.strip!
+      page_lines << line
+    end
+    lines = []
+    flag_tag = false
+    page_lines.each do |line|
+      if line.length > 0
+        if flag_tag
+          lines[(lines.count - 1)] = merge_para_part(lines.last,line)
+        else
+          lines << line
+        end
+        if line_closed?(line,length)
+          flag_tag = false
+        else
+          flag_tag = true
+        end
+      end
+    end
+    lines.join("\n")
+  end
+  # 计算文本相似度
+  def text_similarity(text1,text2)
+    return 0 if text1.blank? || text2.blank?
+    diff = Levenshtein.distance(text1,text2)
+    count = text1.length > text2.length ? text1.length : text2.length
+    similarity = (count - diff) / count.to_f
+  rescue
+    0
+  end
+  # line_closed?
+  #   判断是否为一行的结束。如何算一行结束？
+  #    * 以句子结束符结尾的
+  #    * 非结束符结束，但长度小于猜测的行长度的
+  # parameters:
+  #   +text+  一行的文本内容
+  def line_closed?(text,length=60)
+    return true if end_mark?(text)
+    short_text = text.gsub(/[\.\-—． ]/,'')
+    if short_text =~ /\p{Han}/
+      return true if short_text.length > 80
+      return true if short_text.length < length * 2
+    else
+      return true if short_text.length > 80
+      return true if short_text.length < length
+    end
+    false
+  end
+  def end_mark?(text)
+    end_mark = [".","。",'"','!','?','！','？','…','>']
+    return true if end_mark.include?(text[-1])
+  end
+  def merge_para_part(part1,part2)
+    if part2 =~ /\p{Han}/
+      [part1,part2].join("")
+    else
+      [part1,part2].join(" ")
+    end
+  end
+  def guess_content_line_length(content)
+    line_length = 0
+    return line_length if content.blank?
+    lengths = []
+    content.each_line{|line|
+      lengths << line.length
+    }
+    while true
+      line_length = lengths.pop
+      break if line_length < 80
+    end
+    return line_length
+  end
+  # clean_text
+  #  获得干净的文本，去除两边的空格和回车，主要在txt标题转换成html时使用
+  def clean_text(text)
+    return text if text.nil?
+    text = text.strip
+    text.gsub("\n",'')
+  end
+  # escape_html
+  # 文本转义，在txt文本转html时需要使用
+  def escape_html(text)
+    CGI::escapeHTML(text)
+  end
+  def wrapper_html(content,options={})
+    <<-EOS
+    <!DOCTYPE html>
+    <HTML xmlns="http://www.w3.org/1999/xhtml" lang="" xml:lang="">
+    <HEAD>
+    <TITLE>#{options[:title]}</TITLE>
+    <META http-equiv="Content-Type" content="text/html; charset=UTF-8"/>
+    </HEAD>
+    <body>
+    #{content}
+    </body>
+    EOS
+  end
+  def to_utf8(text,encoding='GB2312')
+    doc = Iconv.iconv('UTF-8//IGNORE',"#{encoding}//IGNORE",text)
+    doc.join("")
+    #text.encode(encoding)
+  rescue
+    nil
+  end
+  def detect_utf8(content)
+    content.each_line{|line|line.strip}
+    true
+  rescue
+    false
+  end
+  # scan_file_from_dir
+  # 遍历目录下的文件
+  # parameters:
+  #   +dir+       需遍历的目录
+  #   +options+   可选参数
+  #      :format     指定需要遍历的文件后缀名，例如要遍历所有pdf文件，通过:format=>'.pdf'指定
+  def scan_file_from_dir(dir,options={})
+    files = []
+    walk_dir(dir,options) do |file|
+      files << file.to_s
+    end
+    files
+  end
+  def write_file(text, filename)
+    File.open(filename,'wb') do |file|
+      file.write text
+    end
+  end
+  # source_exists?
+  # detect source file or directory
+  # parameters:
+  #  +source+   file or directory
+  #  +dir_flag+  directory flag, default nil.
+  def source_exists?(source,dir_flag=nil)
+    if dir_flag
+      File.directory?(source)
+    else
+      File.exists?(source)
+    end
+  end
+  def make_destination_dir(destination)
+    dest_path = File.dirname(destination)
+    FileUtils.mkdir_p(dest_path) unless Dir.exists?(dest_path)
+  end
+  # 根据路径提取关键词
+  def extract_keywords_from_path(path)
+    keywords = path.split(/[\\\/]/).map{|key| key if key.strip != ''}.compact
+  end
+  def walk_dir(path_str,options={})
+    path = Pathname.new(path_str)
+    format = options[:format]
+    path.children.each do |entry|
+      if entry.directory?
+        walk_dir(entry) {|x| yield(x)}
+      elsif entry.file?
+        if format
+          if entry.extname == format
+            yield entry
+          end
+        else
+          yield entry
+        end
+      end
+    end
+  end
+  def detect_sections_from_html(html_file)
+    sections = []
+    html = Nokogiri::HTML.parse(File.open(html_file).read)
+    html.search('h2').each do |node|
+      sections << {:title=>node.text,:page_num=>node['id']}
+    end
+    sections
+  end
+end

metadata ADDED

@@ -0,0 +1,170 @@
+--- !ruby/object:Gem::Specification
+name: ebook_tools
+version: !ruby/object:Gem::Version
+  version: 0.0.1
+  prerelease:
+platform: ruby
+authors:
+- Aaron
+autorequire:
+bindir: bin
+cert_chain: []
+date: 2013-04-01 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: uuid
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: iconv
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: gepub
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: poppler
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: pdf-reader
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: nokogiri
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: levenshtein
+  requirement: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :runtime
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    none: false
+    requirements:
+    - - ! '>='
+      - !ruby/object:Gem::Version
+        version: '0'
+description: 电子书工具集.
+email: aaron@nonobo.com
+executables:
+- ebook_tools
+extensions: []
+extra_rdoc_files: []
+files:
+- README
+- CHANGELOG
+- bin/ebook_tools
+- lib/ebook_tools.rb
+- lib/extract_book_struct.rb
+- lib/header_detect.rb
+- lib/pdf.rb
+- lib/txt.rb
+- lib/epub.rb
+- lib/utils.rb
+- ebook_tools.gemspec
+homepage:
+licenses: []
+post_install_message:
+rdoc_options:
+- --charset=UTF-8
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  none: false
+  requirements:
+  - - ! '>='
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements:
+- none
+rubyforge_project:
+rubygems_version: 1.8.25
+signing_key:
+specification_version: 3
+summary: 电子书工具集.
+test_files: []