Module: EbookTools

Extended by:
EbookTools
Included in:
EbookTools
Defined in:
lib/ebook_tools.rb

Instance Method Summary collapse

Instance Method Details

#allow_extract_struct?(file) ⇒ Boolean

Returns:

  • (Boolean) 


198
199
200
201
 
# File 'lib/ebook_tools.rb', line 198

def allow_extract_struct?(file)
  extname = File.extname(file)
  ['.txt','.html','.epub'].include?(extname.downcase)
end

#batch_convert(source, destination, options = {}) ⇒ Object 



102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
 
# File 'lib/ebook_tools.rb', line 102

def batch_convert(source,destination,options={})  
  log = File.open('batch.log','a')
  success_log = File.open('success.log','a')
  error_log = File.open('error.log','a')
  scan_log = File.open('scan.log','a')
  unknown_log = File.open('unknown.log','a')

  source_path = File.absolute_path(source)
  dest_path = File.join(File.absolute_path(destination),'epub')
  scan_path = File.join(File.absolute_path(destination),'scan')
  unknown_path = File.join(File.absolute_path(destination),'unknown')
  backup_path = File.join(File.absolute_path(destination),'backup')
  
  format = options[:format]

  files = Utils.scan_file_from_dir(source_path,:format=>format)

  total_count = files.count
  scan_count = 0
  success_count = 0
  error_count = 0
  unknown_count = 0

  puts "count: #{total_count} file "
  log.puts "****batch convert****** : #{Time.now}"
  log.puts "#{source_path}  =>  #{dest_path} "
  log.puts "count: #{total_count} file "

  success_log.puts "****batch convert****** : #{Time.now}"
  success_log.puts "#{source_path}  =>  #{dest_path} "

  error_log.puts "****batch convert****** : #{Time.now}"
  error_log.puts "#{source_path}  =>  #{dest_path} "

  scan_log.puts "****batch convert****** : #{Time.now}"
  scan_log.puts "#{source_path}  =>  #{dest_path} "

  unknown_log.puts "****batch convert****** : #{Time.now}"
  unknown_log.puts "#{source_path}  =>  #{dest_path} "


  files.each do |file|
    dest_file = File.join(File.dirname(File.join(dest_path,file.gsub(source_path,''))),"#{File.basename(file,File.extname(file))}.epub")
    
    keywords = Utils.extract_keywords_from_path(File.dirname(file).gsub(source_path,''))
    puts "start convert #{file}"
    extname = File.extname(file).gsub('.','')
    method_name = "#{extname}2epub" 
    if extname == 'epub'
      FileUtils.mkdir_p(dest_path) unless Dir.exists?(dest_path)
      FileUtils.cp(file,dest_file)
      success_file = File.join(backup_path,file.gsub(source_path,''))
      FileUtils.mkdir_p(File.dirname(success_file)) unless Dir.exists?(File.dirname(success_file))
      FileUtils.mv(file,success_file,:force=>true)     
      success_count += 1
      success_log.puts "success: #{source} conversion successfully!"
    elsif EbookTools.respond_to?(method_name)
      begin
        if PDF.scan_pdf?(file)
          scan_file = File.join(scan_path,file.gsub(source_path,''))
          FileUtils.mkdir_p(File.dirname(scan_file)) unless Dir.exists?(File.dirname(scan_file))
          FileUtils.mv(file,scan_file,:force=>true)
          scan_count += 1
          scan_log.puts "warning: #{file} is scan pdf."            
        else
          EbookTools.send(method_name,file,dest_file,{:keywords=>keywords}) 
          success_file = File.join(backup_path,file.gsub(source_path,''))
          FileUtils.mkdir_p(File.dirname(success_file)) unless Dir.exists?(File.dirname(success_file))
          FileUtils.mv(file,success_file,:force=>true)        
          success_count += 1
          success_log.puts "success: #{source} conversion successfully!"
        end
      rescue Exception => e
        unknown_file = File.join(unknown_path,file.gsub(source_path,''))
        FileUtils.mkdir_p(File.dirname(unknown_file)) unless Dir.exists?(File.dirname(unknown_file))
        FileUtils.mv(file,unknown_file,:force=>true)
        error_count += 1
        error_log.puts "error: #{source} \n#{e.backtrace.join("\n")}"
      end        
    end
  end

  success_log.puts "count: #{success_count}   Time: #{Time.now} \n"
  scan_log.puts "count: #{scan_count}    Time: #{Time.now} \n"
  error_log.puts "count: #{error_count}    Time: #{Time.now} \n"
  unknown_log.puts "unknown: #{unknown_count}    Time: #{Time.now} \n"
  log.puts "success: #{success_count}   scan: #{scan_count}   error: #{error_count}    Time: #{Time.now} \n"

  ensure
    success_log.close
    error_log.close
    scan_log.close
    unknown_log.close
    log.close    
end

#batch_extract_from_dir(source, destination, options = {}) ⇒ Object

batch_extract_from_dir

batch extract book struct form dir

parameters:

+source+     source directory
+destination+   output directory
+options+        optional parameter.
   :format     指定需要提取结构的文件后缀名，例如要从所有txt文件中提取，通过:format=>'.txt'指定



242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
 
# File 'lib/ebook_tools.rb', line 242

def batch_extract_from_dir(source,destination,options={})
  format = options.delete(:format)
  source_path = File.absolute_path(source)
  dest_path = File.absolute_path(destination)

  files = Utils.scan_file_from_dir(source_path,{:format=>format})

  files.each do |file|
    extname = File.extname(file)
    basename = File.basename(file,extname)
    dest_file = File.join(File.dirname(File.join(dest_path,file.gsub(source_path,''))),"#{basename}.xml")
    if allow_extract_struct?(file)
      puts "start extract #{file} ..."          
      begin
        if extract_book_struct_to_file(file,dest_file)
          puts "success: extract book struct  successfully!"
        else
          new_file = File.join(File.dirname(file),"[err]#{basename}#{extname}")
          FileUtils.mv(file,new_file,:force=>true)
          puts "警告: 没有检测到书结构信息."
        end
      rescue Exception => e
        puts "error: #{file} \n#{e.backtrace.join("\n")}"
      end
    else
      puts "error: #{file}不是允许的文件格式: txt,html,epub"
    end
  end
end

#convert(filename, epub_file, options = {}) ⇒ Object 



10
11
12
13
14
15
16
17
18
 
# File 'lib/ebook_tools.rb', line 10

def convert(filename,epub_file,options={})
  method_name = "#{File.extname(filename).gsub('.','')}2epub" 
  if EbookTools.respond_to?(method_name)
    EbookTools.send(method_name,filename,epub_file,options) 
    return true
  else
    return nil
  end
end

#extract_book_struct_to_file(source, destination, options = {}) ⇒ Object 



203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
 
# File 'lib/ebook_tools.rb', line 203

def extract_book_struct_to_file(source,destination,options={})
  options[:title] ||= File.basename(source,File.extname(source))
  if File.extname(source) == '.epub'
    epub_book = EpubBook.new(source,options)
    docbook_xml = epub_book.to_doc_book
    if docbook_xml
      write_doc_book(destination,docbook_xml)
      puts "目录结构:"
      puts epub_book.toc_to_text
      return true
    end
  else
    content = case File.extname(source)
      when '.html'
        Utils.extract_text_from_file(source,'.html')
      when '.txt'
        File.open(source).read
    end
    txt_book = TxtBook.new(content,options)
    docbook_xml = txt_book.to_doc_book
    if docbook_xml
      write_doc_book(destination,docbook_xml)
      puts "目录结构:"
      puts txt_book.toc_to_text
      puts "共修复#{txt_book.breaklines_count}个断点."
      return true
    end
  end

  return nil
end

#html2epub(filename, epub_file, options = {}) ⇒ Object

html2epub 将HTML格式转换成EPUB格式



49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
 
# File 'lib/ebook_tools.rb', line 49

def html2epub(filename,epub_file,options={})
  basename = File.basename(filename,'.html')
  temp_dir = "#{basename}"
  FileUtils.mkdir(temp_dir) unless File.exists?(temp_dir)

  html = File.open(filename).read

  html_file = File.join([temp_dir,"#{basename}.html"].compact)
  Utils.write_file(html,html_file)
  sections = Utils.detect_sections_from_html(html_file)

  nav_file = EPUB.gen_nav_file(html_file,sections)

  EPUB.write_epub(epub_file,options.merge(:files=>[nav_file,html_file]))
  ensure
    FileUtils.remove_dir(temp_dir,true)
end

#pdf2epub(filename, epub_file, options = {}) ⇒ Object

pdf2epub 将PDF格式转换成EPUB格式



69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
 
# File 'lib/ebook_tools.rb', line 69

def pdf2epub(filename,epub_file,options={})
  basename = File.basename(filename,'.pdf')
  temp_dir = "#{basename}"
  FileUtils.mkdir(temp_dir) unless File.exists?(temp_dir)

  pages_text = PDF.extract_pdf_pages_text(filename)
  pages_text = PDF.sanitize_page_header_and_footer(pages_text,options)
  pages_text = PDF.fixed_break_with_pages_text(pages_text)

  sections = PDF.extract_sections(filename)

  illustrations = PDF.extract_illustrations(filename,{:dir=>temp_dir})

  html_content = PDF.gen_html_from_sections_and_page_texts(sections,pages_text,illustrations)
  html = Utils.wrapper_html(html_content)
  html_file = File.join([temp_dir,"#{basename}.html"].compact)
  Utils.write_file(html,html_file)

  illustrations_path = illustrations.map{|image_path| File.join(temp_dir,image_path)}

  nav_file = EPUB.gen_nav_file(html_file,sections)

  files = [html_file,nav_file,illustrations_path].flatten

  meta = PDF.extract_pdf_meta(filename)
  epub_options = options.merge(meta).merge(:files=>files)

  EPUB.write_epub(epub_file,epub_options)

  ensure
    FileUtils.remove_dir(temp_dir,true)
end

#sanitize_for_epub_text(content) ⇒ Object

sanitize_for_epub_text



287
288
289
290
291
292
293
294
295
296
297
298
 
# File 'lib/ebook_tools.rb', line 287

def sanitize_for_epub_text(content)
  return content if content.blank?
  lines = []
  content.each_line do |line|
    unless line.downcase.include?('document outline')
      lines << line
    else
      break;
    end
  end
  lines.join("")
end

#text_paras_repair(source_file, target_file, options = {}) ⇒ Object

text_paras_repair 对文本文件格式中的中断段落进行修复



279
280
281
282
283
284
 
# File 'lib/ebook_tools.rb', line 279

def text_paras_repair(source_file,target_file,options={})
  content = File.open(source_file).read
  content = Utils.to_utf8 unless Utils.detect_utf8(content)
  content = Utils.fixed_page_break(content,options)
  File.open(target_file,'w'){|file| file.write content}
end

#txt2epub(filename, epub_file, options = {}) ⇒ Object

txt2epub 将文本格式转换成EPUB格式



22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
 
# File 'lib/ebook_tools.rb', line 22

def txt2epub(filename,epub_file,options={})
  basename = File.basename(filename,'.txt')
  temp_dir = "#{basename}"
  FileUtils.mkdir(temp_dir) unless File.exists?(temp_dir)

  title,outlines, content = TXT.extract_book_part(filename)
 
  if options[:fix]
    content = Utils.fixed_page_break(content)
  end

  html_content = TXT.gen_html_from_txt_book(title,outlines,content)
  html = Utils.wrapper_html(html_content)

  html_file = File.join([temp_dir,"#{basename}.html"].compact)
  Utils.write_file(html,html_file)
  sections = Utils.detect_sections_from_html(html_file)

  nav_file = EPUB.gen_nav_file(html_file,sections)

  EPUB.write_epub(epub_file,options.merge(:files=>[nav_file,html_file]))
  ensure
    FileUtils.remove_dir(temp_dir,true)
end

#write_doc_book(destination, docbook_xml) ⇒ Object 



272
273
274
275
 
# File 'lib/ebook_tools.rb', line 272

def write_doc_book(destination, docbook_xml)
  FileUtils.mkdir_p(File.dirname(destination)) unless Dir.exists?(File.dirname(destination))
  File.open(destination,'wb'){|file|file.write docbook_xml}    
end