pdfmd 2.5.0 → 2.6.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA1:
-  metadata.gz: 970844407051f137b893c42e9702e1a51a7558e8
-  data.tar.gz: a0f7daf1d0fa37e297f37650b087181a3ae64402
+  metadata.gz: 4749a93bfd91007699878f1a2e3a6a98b39b7e08
+  data.tar.gz: 8c48f25ec662757a6f4b41e3ac6cb3b275deea11
 SHA512:
-  metadata.gz: 2b36151807b90b6474065900c29414b4ff95b74adb9a956ae56b1fab5439628f64994091a654ccf51d5bd255abffc072c90fed9edeb1b06e3d8043601dba905e
-  data.tar.gz: 6ee948b86f665d1ae105083fb0075d6e25cd0fde22f69d9172041da0b0e9041c57f2a90a9cec6556f2ef088f710f35f756e9e5ef907361a7f96f346aed8e07d8
+  metadata.gz: c1ca2922304b90752e324a005213823f1e2b1f39eb77f5b35749671e9c0f3c08dbd42d4e52069bb6f444a7bf07182b087b0293f97b009e54ec7825d98b3a15a8
+  data.tar.gz: 122f3d170c6a9988aa522f53d0923168766a4868098f8118045f2b37cbb6624672095651d85fe0c0f945efcd99ed3a3dbc49885dd8303f448f5a2c220e145622

data/CHANGELOG.md

@@ -1,3 +1,11 @@
+# Version 2.6.0
+- Adding stat export formats.
+- Bugfix, Abbreviations in keywords are not replaced anymore.
+- Bugfix, Files in the destination directory are now ignored while sorting and 
+  not used in the author-collision calculation any more.
+- Buxfix, Sorting now also works with directories as input.
+- Command 'stat': Added parameter to disable the percentage output.
+
 # Version 2.5.0
 - Bugfix, Removing output of debugging and empty lines.
 - Changing edit separation sign from ':' to '='.

data/TODO.mkd

@@ -6,8 +6,12 @@
 
 ### Method: _stat_
 * Parameter to ignore differences in upper and lowercase
-* Parameter to disable percentage output
-* Parameter to set output format: json,yaml, hash
+
+### Method: _rename_
+* The createdate pattern does not work with yyyy-mm-dd.
+
+### Method: _sort_
+* Author values with a slash One/two should be sorted into one/two/yyyymmdd-one_to-xxx.pdf
 
 ## pdfmdedit.rb
 

data/bin/pdfmd

@@ -8,7 +8,7 @@ require "fileutils"
 require "i18n"
 require 'pathname'
 
-VERSION = '2.5.0'
+VERSION = '2.6.0'
 NAME    = 'pdfmd'
 
 # Read the content of the long description from an external file
@@ -174,6 +174,8 @@ desc 'stat', 'Show metadata statistics of multiple files'
 long_desc readLongDesc 'pdfmd/long_desc.pdfmdstat.txt'
 option :recursive, :type => :boolean, :aliases => '-r', :desc => 'Include subdirectories recursively.', :lazy_default => true, :required => false
 option :tags, :aliases => '-t', :type => :string, :desc => 'Define Metatags to run at', :lazy_default => 'author,title,subject,createdate,keywords', :required => false
+option :format, :aliases => '-f', :type => :string, :desc => 'Define output format.', :required => false, :default => 'yaml', :enum => ['yaml', 'json', 'hash']
+option :status, :aliases => '-s', :type => :boolean, :desc => 'Show calculation status.', :required => false, :default => true
 def stat(input)
 
   filemetadata  = Hash.new
@@ -189,27 +191,34 @@ def stat(input)
 
     # Count the number of files quickly to show an overview
     # nooFiles = numberOfFiles
-    nooFiles = Dir[File.join(input.chomp, recursive, '*.pdf')].count { |file| File.file?(file) }
+    nooFiles        = Dir[File.join(input.chomp, recursive, '*.pdf')].count { |file| File.file?(file) }
     currentNooFiles = 0
     Dir.glob("#{input.chomp}#{recursive}/*.pdf").each do |filename|
 
-      # Print percentage
-      currentNooFiles = currentNooFiles + 1
-      percentage = 100 / nooFiles * currentNooFiles
-      print "\r Status: #{percentage} % of #{nooFiles} files processed.   "
+      # Print percentage if requested
+      if options[:status]
+        currentNooFiles = currentNooFiles + 1
+        percentage      = 100 / nooFiles * currentNooFiles
+        print "\r Status: #{percentage} % of #{nooFiles} files processed.   "
+      end
 
-      pdfdoc = Pdfmd.new filename
-      filemetadata = {}
+      pdfdoc                                 = Pdfmd.new filename
+      filemetadata                           = {}
       currentOutput[File.basename(filename)] = pdfdoc.metadata.to_s
-      pdfdoc = nil
+      pdfdoc                                 = nil
 
     end
-    puts ''
-    puts ''
+    # Print some linebreak if the status has been shown.
+    # This makes it a bit prettier.
+    if options[:status]
+      puts ''
+      puts ''
+    end
 
     pdfstat = Pdfmdstat.new(currentOutput)
     pdfstat.tags options[:tags]
     pdfstat.analyse_metadata
+    pdfstat.output_metadata(options[:format])
 
   end
 
@@ -229,7 +238,7 @@ method_option :typo, :aliases => '-t', :required => false, :type => :boolean, :d
 def sort(*input)
 
   input.each do |file|
-  
+
     if File.file?(file)
       pdfdoc              = Pdfmdsort.new file
       pdfdoc.copy         = pdfdoc.determineValidSetting(options[:copy], 'sort:copy')
@@ -243,8 +252,8 @@ def sort(*input)
 
     else
 
-      # Run the actions for all files
-      Dir.glob(input.chomp + '/*.pdf').each do |filename|
+      # Run the actions for all files which are in the directory
+      Dir.glob(input.join.chomp('/') + '/*.pdf').each do |filename|
         pdfdoc              = Pdfmdsort.new filename
         pdfdoc.copy         = pdfdoc.determineValidSetting(options[:copy], 'sort:copy')
         pdfdoc.interactive  = pdfdoc.determineValidSetting(options[:interactive], 'sort:interactive')

data/lib/pdfmd/long_desc.pdfmdstat.txt

@@ -14,10 +14,23 @@ Path to the directory containing PDF documents or subdirectories with PDF docume
 Example: `pdfmd stat ~/pdf`
 
 
---r --recursive
+-r --recursive
 
 If set to true, pdfmd includes all PDF documents found in subdirectories of <directory> as well.
 
 Default: false
 
 
+-f --format
+
+Sets alternativ output formats. Valid values are 'hash', 'yaml', 'json'.
+
+Default: json
+
+
+-s --status
+
+Enable/Disable the output during the statistics calculation.
+
+Default: true
+

data/lib/pdfmd/pdfmdrename.rb

@@ -152,6 +152,11 @@ class Pdfmdrename < Pdfmd
   end
 
   # Get the keywords
+  # This methods is trying in a way to intelligently handle the keywords and
+  # return them back to. While doing this, the abbreviations are also being
+  # taken into account. Wordcombinations on the other hand, that contain some
+  # keywords for the abbreviation, should not be changed.
+  # That's what makes it a bit tricky.
   def get_keywords(preface = '')
 
     if !@@metadata['keywords'].empty?
@@ -170,7 +175,7 @@ class Pdfmdrename < Pdfmd
           end
           keyvaluearray = keyvaluearray.sort_by{|size| -size.length}
           keyvaluearray.each do |keystring|
-            value = value.gsub(/#{keystring.lstrip.chomp}\s?/i, abbreviation.to_s)
+            value = value.gsub(/^#{keystring.lstrip.chomp}\s?/i, abbreviation.to_s)
           end
         end
 

data/lib/pdfmd/pdfmdsort.rb

@@ -1,6 +1,5 @@
 # == Class: pdfmdsort
 #
-# TODO: Author values with a slave One/two should be sorted into one/two/yyyymmdd-one_to-xxx.pdf
 class Pdfmdsort < Pdfmd
 
   require 'fuzzystringmatch'
@@ -80,14 +79,21 @@ class Pdfmdsort < Pdfmd
     # Get all subfolders 
     subDirectories = Dir[@destination + '/*']
     subDirectories.each do |fullPathFolder|
-       stringSimilarity = fuzzy.getDistance( 
-         fullPathFolder.gsub(@destination + '/', ''),
-         targetdir.gsub(@destination + '/', '')
-         )
-       if stringSimilarity > @stringSimBorder
-         self.log('debug', "findSimilarTargetdir: Found String value #{stringSimilarity.to_s} for target '#{fullPathFolder}'.")
-         returnValue = fullPathFolder
-       end
+
+      # Match only directories, not any files that might be in the target directory
+      if !File.directory?(fullPathFolder)
+
+        stringSimilarity = fuzzy.getDistance(
+          fullPathFolder.gsub(@destination + '/', ''),
+          targetdir.gsub(@destination + '/', '')
+          )
+        if stringSimilarity > @stringSimBorder
+          self.log('debug', "findSimilarTargetdir: Found String value #{stringSimilarity.to_s} for target '#{fullPathFolder}'.")
+          returnValue = fullPathFolder
+        end
+
+      end
+
     end
     returnValue
   end

data/lib/pdfmd/pdfmdstat.rb

@@ -11,8 +11,10 @@ class Pdfmdstat
 
   attr_accessor :metadata
 
-  @statdata   = {}
-  @hieradata  = {}
+  # Instancevariables
+  @statdata      = {}
+  @hieradata     = {}
+  @metadata_hash = {} # Keeps the metadata ones it's available
 
   def initialize(metadata)
 
@@ -110,8 +112,29 @@ class Pdfmdstat
 
     end
 
-    puts sortedOutputHash.to_yaml.gsub(/---\n/,'')
+    # Load the class variable with the metadata
+    @metadata_hash = sortedOutputHash
 
   end
 
+  # Output the metadata in multiple format
+  # Default: yaml
+  #
+  # else:
+  #   json
+  def output_metadata(format = 'yaml')
+
+    case format
+    when 'json'
+      require 'json'
+      puts @metadata_hash.to_json
+    when 'hash'
+      puts @metadata_hash
+    else
+      puts @metadata_hash.to_yaml.gsub(/---\n/,'')
+    end
+
+  end
+
+
 end

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: pdfmd
 version: !ruby/object:Gem::Version
-  version: 2.5.0
+  version: 2.6.0
 platform: ruby
 authors:
 - Daniel Roos
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2016-09-25 00:00:00.000000000 Z
+date: 2016-10-14 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: thor
@@ -174,8 +174,8 @@ homepage: https://github.com/Micronarrativ/ruby-pmd
 licenses:
 - MIT
 metadata:
-  created: '2016-09-25 20:19:06'
-  revision: '20160925201906'
+  created: '2016-10-14 21:27:32'
+  revision: '20161014212732'
 post_install_message: ". Run `pdfmd` to see the command help."
 rdoc_options: []
 require_paths: