risbn 0.1.0 → 0.2.0

data/README.rdoc

@@ -1,9 +1,32 @@
 = risbn
 
-Description goes here.
+Minimal set of tools for working with isbns from ruby.
+
+Supports both isbn-10 and isbn-13.
+
+Provides a simple (barebones) tool for extracting isbns from pdf and chm files.
+
+== Examples:
+
+  isbn = RISBN.parse_first("Some text with and isbn: ISBN-13: 978-0393317732") # => <RISBN isbn="9780393317732">
+  isbn.valid? # => true
+
+  require 'risbn/scanner'
+  RISBN::Scanner.scan("some/file.pdf")
+  RISBN::Scanner.scan("some/file.chm")
+  RISBN::Scanner.scan("some/file.tx")
+
+== Notes
+
+Currently only works on unix like platforms.
+
+Requires the following tools for scanning files:
+
+* Poppler for pdf (pdftotext utility)
+* Archmage for chm
 
 == Note on Patches/Pull Requests
- 
+
 * Fork the project.
 * Make your feature addition or bug fix.
 * Add tests for it. This is important so I don't break it in a

data/VERSION

@@ -1 +1 @@
-0.1.0
+0.2.0

data/lib/risbn.rb

@@ -17,7 +17,7 @@ class RISBN
 
   # Provide a string with the isbn. Any non digit or X character will be removed.
   def initialize(code = "")
-    @isbn = code.to_s.upcase.gsub(/[^0-9X]/, "")
+    @isbn = (code || "").to_s.upcase.gsub(/[^0-9X]/, "")
   end
 
   def valid?

data/lib/risbn/scanner.rb

@@ -0,0 +1,55 @@
+require 'shellwords'
+require 'tmpdir'
+require 'iconv'
+
+class RISBN
+
+  # Scan a file for a isbn. Currently only text files, pdf and chm files are allowed.
+  # Uses unix 'file' command to identify the file.
+  # For pdf scanning uses poppler, for chm scanning uses archmage.
+  module Scanner
+    extend self
+
+    # provide a file path of a file to scan for the first found isbn.
+    # currently scans pdfs using poppler, chm using archmage and text files.
+    # Also, requires the unix utility "file"
+    def scan(path)
+      case identify(path)
+      when /PDF/      then scan_pdf(path)
+      when /HtmlHelp/ then scan_chm(path)
+      when /text/     then scan_txt(path)
+      end || RISBN.new
+    end
+
+    def identify(path)
+      File.file?(path) ? %x|file -F :::: #{path.to_s.shellescape}|.split("::::").last.strip : ""
+    end
+
+    def scan_chm(path)
+      Dir.mktmpdir do |dir|
+        tmp = File.join(dir, "tempfile.txt")
+        system("python -W ignore $(which archmage) -c text #{ path.to_s.shellescape } #{ tmp.to_s.shellescape } 2>&1 > /dev/null")
+        scan_txt(tmp)
+      end
+    end
+
+    def scan_pdf(path)
+      Dir.mktmpdir do |dir|
+        tmp = File.join(dir, "tempfile.txt")
+        system("pdftotext -q -f 0 -l 20 -raw -nopgbrk #{ path.to_s.shellescape } #{ tmp.to_s.shellescape }")
+        scan_txt(tmp)
+      end
+    end
+
+    def scan_txt(path)
+      IO.foreach(path) do |line|
+        isbn = RISBN.parse_first(line)
+        return isbn if isbn.valid?
+      end
+      nil
+    rescue # any problem with the text encoding
+      nil
+    end
+
+  end
+end

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification 
 name: risbn
 version: !ruby/object:Gem::Version 
-  version: 0.1.0
+  version: 0.2.0
 platform: ruby
 authors: 
 - Emmanuel Oga
@@ -39,6 +39,7 @@ files:
 - Rakefile
 - VERSION
 - lib/risbn.rb
+- lib/risbn/scanner.rb
 - spec/risbn_spec.rb
 - spec/spec_helper.rb
 has_rdoc: true