scholar-rename 0.1

checksums.yaml

@@ -0,0 +1,7 @@
+---
+SHA1:
+  metadata.gz: 3ed79b92fcf9f579c34e3eaba52af4af7aee50e1
+  data.tar.gz: 4daa459bf18e325d1de3fb55096b652d8f600c04
+SHA512:
+  metadata.gz: 5be2495e46ce5ce2dcc299061aaa56bb598785dd1e152aaedd1922970df6b8326a285a7cc8b71412516d9d3a30763e2655355e03562502871584256dd83bd4c3
+  data.tar.gz: 4f3082e00d2e661a6b99b33e1780ff7f6a5be069ab6281d5971cc368af0fbb0abb3ea840bd94e1d9380853bdfff6ecd1c2e389e303d458a5311fc4286048de93

data/bin/scholar-rename

@@ -0,0 +1,13 @@
+#!/usr/bin/env ruby
+
+# by jeremy warner, fall 2016
+# scholar-rename, interactive pdf-namer
+# prereq: pdftotext installation for text dump
+# renames a pdf file to author-title-year.pdf
+# or other formats based on your selection
+# todo - make a suite of decent tests
+
+require_relative '../lib/selector'
+require_relative '../lib/renamer'
+
+r = Renamer.new ARGV

data/lib/renamer.rb

@@ -0,0 +1,31 @@
+class Renamer
+  def initialize(*args)
+    @file = File.join(Dir.pwd, args.first)
+
+    if @file == Dir.pwd.to_s + '/'
+      puts "scholar-rename: provide a file"
+    else
+      rename
+    end
+  end
+
+  def rename # move file based on users input
+    now = Time.now.to_i.to_s # current time, unique temp file
+    temp = File.join(Dir.pwd, "temp-scholar-rename-text-#{now}")
+    system("pdftotext -q '#{@file}' '#{temp}'")
+    content = File.read temp
+
+    # Choose pdf qualities
+    s = Selector.new(content)
+    s.select_all # choose props
+    printf "Ok? [Yn]: "
+    conf = STDIN.gets.chomp # confirm title
+
+    begin # file read in from first ARGV above
+      File.rename(@file, s.title) unless conf.match /^(n|N).*/
+    ensure # cleaning up @file cleanup from pdftotext
+      puts "Cleaning up..."
+      File.delete(temp)
+    end
+  end
+end

data/lib/selector.rb

@@ -0,0 +1,89 @@
+# Class for choosing and displaying the information from the pdf.
+# I wonder if this could be augmented with information from google scholar
+# somehow, there is probably a ruby (or at least python) api.
+
+class Selector
+  attr_reader :title
+
+  # take the first 10 lines of the pdftotext output and assign it to the
+  # context class instance variable, use later when choosing selector
+  def initialize(c)
+    @content = c.split("\n")[0..14].reject {|x| x.length < 2 }
+    @fulltxt = c.split("\n")
+  end
+
+  def select_all
+    puts "Select title line number:"
+    title = choose @content
+
+    puts "Select author line number:"
+    authors = choose @content
+
+    puts "Select author form number:"
+    author = gen_authors(authors)
+
+    year = gen_year # just read it
+
+    puts "Select desired title format:"
+    @title = choose(gen_forms year, title, author)
+  end
+
+  private
+  # Pass in an array to list and be selected, and return the element that the
+  # user selects back to the calling method. pretty sketchy way to interpret
+  # the users input as a range or integer, but seems to be working for now.
+  # requires you to check for an array and join it on the downside though
+  def choose(opts)
+    opts.each_with_index {|l, i| puts "#{i}\t#{l}" }
+    printf "Your selection [0 - #{opts.length-1}]: "
+    line = STDIN.gets.chomp
+    meta = "opts[#{line}]"
+    mout = eval meta # in theory terrible but this aint a rails app............
+    if mout.is_a? (Array)
+      mout.join ' '
+    else
+      mout
+    end
+  end
+
+  # Generate different forms for author selection, enumerating the different
+  # author that you want to save the file as. Split based on a comma.
+  def gen_authors(aline)
+    lines = aline.split(", ").map {|a| a.sub /\d$/, '' } # delete ref number.
+    if lines.is_a?(String)
+      aline # return first
+    else # its an array, augment w/ lname and choose
+      alines = lines.map {|a| a.split.last } + lines
+      choose alines
+    end
+  end
+
+  # based on the collected information, generate different forms of the title.
+  # perhaps at some point this could be autoselected from the command line,
+  # like how the date formatting works, using symbols for different features...
+  # in theory could also handle this with the eval method like above - but this
+  # would probably be better as a send call or an instance_eval method :/
+  def gen_forms(y, t, a)
+    ad = a.downcase
+    au = a.upcase
+    return [
+      "#{a}_#{y}_#{t}.pdf".gsub(" ", "_"),
+      "#{au}_#{y}_#{t}.pdf".gsub(" ", "_"),
+      "#{ad}_#{y}_#{t}.pdf".gsub(" ", "_"),
+      "#{a} #{y} #{t}.pdf",
+      "#{au} #{y} #{t}.pdf",
+      "#{ad} #{y} #{t}.pdf",
+    ]
+  end
+
+  # parse out a year from a string, for each line of the document until found.
+  # then clean it up and return it
+  def gen_year
+    @fulltxt.each do |l| # find year
+      lm = l.match(/(19|20)\d\d/)
+      return lm[0] if !lm.nil?
+    end
+
+    Time.now.year.to_s # not matched, just return current year
+  end
+end

data/lib/version.rb

@@ -0,0 +1 @@
+module SR; Version = "0.1"; end

data/readme.md

@@ -0,0 +1,9 @@
+# scholar-rename `interactive pdf-namer`
+
+- prereq: pdftotext installation for text dump
+- renames a pdf file to author-title-year.pdf
+- or other formats based on your selection
+- by jeremy warner, fall 2016
+
+You need this: https://en.wikipedia.org/wiki/Pdftotext
+

metadata

@@ -0,0 +1,77 @@
+--- !ruby/object:Gem::Specification
+name: scholar-rename
+version: !ruby/object:Gem::Version
+  version: '0.1'
+platform: ruby
+authors:
+- Jeremy Warner
+autorequire: 
+bindir: bin
+cert_chain: []
+date: 2017-01-27 00:00:00.000000000 Z
+dependencies:
+- !ruby/object:Gem::Dependency
+  name: rake
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+- !ruby/object:Gem::Dependency
+  name: rspec
+  requirement: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+  type: :development
+  prerelease: false
+  version_requirements: !ruby/object:Gem::Requirement
+    requirements:
+    - - ">="
+      - !ruby/object:Gem::Version
+        version: '0'
+description: Interactive tool to rename pdfs based on author/title/year.
+email: jeremywrnr@gmail.com
+executables:
+- scholar-rename
+extensions: []
+extra_rdoc_files: []
+files:
+- bin/scholar-rename
+- lib/renamer.rb
+- lib/selector.rb
+- lib/version.rb
+- readme.md
+homepage: http://github.com/jeremywrnr/scholar-rename
+licenses:
+- MIT
+metadata: {}
+post_install_message: 
+rdoc_options: []
+require_paths:
+- lib
+required_ruby_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+required_rubygems_version: !ruby/object:Gem::Requirement
+  requirements:
+  - - ">="
+    - !ruby/object:Gem::Version
+      version: '0'
+requirements: []
+rubyforge_project: 
+rubygems_version: 2.6.8
+signing_key: 
+specification_version: 4
+summary: Rename pdfs based on author/title/year.
+test_files: []