rbibtex 0.0.1 → 0.0.2

data/CHANGELOG

@@ -1,3 +1,12 @@
+0.0.2
+  * Simplified Grammar a bit
+  * Now parsing @comment correctly
+  * Made rbib2bib actually usefull. 
+    * Sorting of entries
+    * Sorting of fields
+    * A help 
+    * Nicer output respecting formatting.
+
 0.0.1
   * Removed unneccessary dependency on pp
   * Added rbib2bib pretty printer

data/InstalledFiles

@@ -0,0 +1,2 @@
+/home/bschroed//bin/rbib2bib
+/home/bschroed//lib/ruby/site_ruby/1.8/rbibtex/rbibtex.tab.rb

data/README

@@ -52,9 +52,13 @@ Brian
 ## ToDo
 * The binaries are only quick hacks for my specific applications right now,
   they should be rewritten and extended.
+* I should transfer functionality from rbib2bib into a library usable by all
+  programs.
 * The full bibtex format is not parsed, I only allow for a specific subset
   right now.  
 * Escaping is not implemented.
+* Create the documentation after having racc'ed the .y files, then cleanup
+  again before packaging.
   
 ## Authors
 This was implemented by Brian Schroeder.

data/bin/rbib2bib

@@ -1,76 +1,147 @@
-#! /usr/bin/ruby
-
-$:.unshift("~/lib/ruby")
-
-require "rbibtex"
-
-file = BibTeX::Parser.new.parse( ARGF.read )
-
-first = [:author, :title, :year]
-last  = [:note, :pdf, :ps, :www]
-
-puts "@comment { Pretty Printed using rbib2bib }"
-
-max_key_length = file.inject(0) { | r, entry |
-  entry.properties.inject(r) { | r, (k, _) |
-    [r, k.to_s.length].max
-  }
-}
-
-p max_key_length
+#! /home/bschroed//bin/ruby
 
+# Some string handling routines for wordwrapping and tabifying.
 class String
   def wrap(width = 78, tabwidth = 8)
     raise "Invalid width" if width < 0
     self.untabify(tabwidth).
-         gsub(/.{1,#{width}}(?:\s|\Z)/) { ($& + 5.chr).gsub(/\n\005/,"\n").gsub(/\005/,"\n") }.
-	 gsub(/\s*\Z/m, "")
+      gsub(/.{1,#{width}}(?:\s|\Z)/) { ($& + 5.chr).gsub(/\n\005/,"\n").gsub(/\005/,"\n") }.
+    gsub(/\s*\Z/m, "")
   end
 
   def indent_hanging(indent = 2)
-   self.gsub(/\n/, "\n#{" " * indent}")
+    self.gsub(/\n/, "\n#{" " * indent}")
   end
-  
+
   def indent(indent = 2)
-   self.gsub(/^/, " " * indent)
+    self.gsub(/^/, " " * indent)
   end
 
 
   def untabify(tab_width = 8)
     self.gsub(/\t/, " "*tab_width)
   end
-  
+
   def deindent_hanging(indent = [self[/^\s*/].untabify.length, self[/\n(\s*)/, 1].to_s.untabify.length].max)
     self.untabify.gsub(/^\s{0,#{indent}}/, "")
   end
-  
+
   def deindent(indent = self[/^\s*/].untabify.length)
     self.untabify.gsub(/^\s{0,#{indent}}/, "")
   end
 
   def unwrap
     self.split(/\n\n+/).map { | paragraph |
-      paragraph.gsub(/\n(?=\S)/, " ")
+      paragraph.gsub(/((?:\n|^)\S[^\n]*)\n(?=\S)/, "\\1 ")
     }.join("\n\n")
   end
 end
 
-file.each do | entry |
-  
-  p = entry.properties.dup
-  f = first.map { | k | [k, p.delete(k)] }
-  l = last.map { | k | [k, p.delete(k)] }
-  p = p.to_a.map{ | (k, v) | [k.to_s, v] }.sort
-  
-  puts "@#{entry.type}{#{entry.key},"
-  (f + p + l).each do | (k, v) |
-    next unless v
-    
-    print %(  #{k}).ljust(max_key_length+2) + " = {"  
-    print v.deindent_hanging.unwrap.wrap(78-(max_key_length+6)).indent_hanging(max_key_length+6)
-    puts "},"
+module Bib2Bib
+  VERSION = "0.0.2"
+
+  require 'optparse'
+
+  class Options < OptionParser
+    attr_reader :wrap, :sort_by, :top_fields, :bottom_fields, :output, :help, :show_version, :comment
+
+    def initialize
+      super()
+
+      # Defaults
+      @top_fields    = [:author, :title, :year]
+      @bottom_fields = [:note, :pdf, :ps, :www]    
+      @comment = true
+      @output = STDOUT
+
+      # Parser Actions
+      self.banner = "Usage: #{ __FILE__ } [-o OUTPUT] [OPTIONS] INPUT [INPUT_1 ...]"
+      self.on("-o FILENAME", "--output FILENAME", String,
+	      "Set the output filename. Writes to stdout if nothing is given")   { | v | @output   = File.open(v, 'w') }
+      self.on("-s", "--sort-by", "--sort_by Field_1,Field2,...", Array,
+	      "Specify fields that shall be used for sorting of the file")       { | v | @sort_by  = v.map { | e | e.downcase.to_sym  } }
+      self.on("-t", "--top_fields Field_1,Field2,...", Array,
+	      "Specify a list of fields that are written first in the output")   { | v | @top_fields     = v.map { | e | e.downcase.to_sym }
+											 @bottom_fields -= @top_fields }
+      self.on("-b", "--bottom_fields Field_1,Field2,...", Array,
+	      "Specify a list of fields that are written last in the output")    { | v | @bottom_fields  = v.map { | e | e.downcase.to_sym }
+		                                                                         @top_fields -= @bottom_fields }
+      self.on("-C", "--no-comment",
+	      "Suppress generation of 'Created by' comment")                     {       @comment   = false }
+      self.on("-?", "--help",
+	      "Show this help")                                                  {       @help     = true }
+      self.on("-v", "--version", 
+	      "Output version number and exit")                                  {       @show_version = true }
+    end
+
+    def parse!(*args)      
+      super
+      raise "You can't specify an empty list of fields for sorting" if @sort_by and @sort_by.empty?
+    end
   end
-  puts "}"
-  puts
-end
 
+  options = Options.new
+  begin
+    options.parse!(ARGV)
+  rescue => e
+    puts "Invalid Commandline Arguments"
+    puts e
+    puts options
+    exit
+  end
+
+  if options.show_version
+    puts VERSION 
+    exit
+  end
+
+  if options.help
+    puts options
+    exit
+  end
+
+  require "rbibtex"
+
+
+  entries = BibTeX::Parser.new.parse( ARGF.read )
+  O = options.output
+
+  if @comment
+    O.puts "@comment { Pretty Printed using rbib2bib }"
+  end
+
+  # Calculate maximum key length
+  max_key_length = entries.entries.inject(0) { | r, entry |
+    entry.properties.inject(r) { | r, (k, _) |
+      [r, k.to_s.length].max
+    }
+  }
+
+  def self.extract_properties(properties, fields)
+    fields.map    { | k | [k, properties.delete(k)] }.select { | (_, v) | v }
+  end
+
+  elements = entries.elements.select { | e | e.is_a?(BibTeX::Entry) or e.is_a?(BibTeX::Comment) }
+  if options.sort_by
+    elements = elements.sort_by { | e | e.is_a?(BibTeX::Comment) ? [] : options.sort_by.map { | k | e.properties[k] || "" } }
+  end
+  puts elements.map { | entry |
+    
+    if entry.is_a?BibTeX::Comment
+      "@comment { #{entry.to_s.deindent_hanging.unwrap.wrap(78 - 11).indent_hanging(11)} }"
+    else
+      properties = entry.properties.dup
+      top    = extract_properties(properties, options.top_fields)
+      bottom = extract_properties(properties, options.bottom_fields)
+      middle = properties.to_a.map { | (k, v) | [k.to_s, v] }.sort
+      
+      "@#{entry.type}{#{entry.key},\n" +
+      (
+	(top + middle + bottom).map { | (k, v) |
+	 %(  #{k}).ljust(max_key_length+2) + " = {#{v.deindent_hanging.unwrap.wrap(78-(max_key_length+6)).indent_hanging(max_key_length+6)}}"
+	}.join(",\n")
+      ) + "\n}"
+    end
+  }.join("\n\n\n")
+
+end

data/bin/rbib2html

@@ -1,4 +1,4 @@
-#! /usr/bin/ruby
+#! /home/bschroed//bin/ruby
 
 $:.unshift("~/lib/ruby")
 

data/bin/rbib2txt

@@ -1,4 +1,4 @@
-#! /usr/bin/ruby
+#! /home/bschroed//bin/ruby
 
 $:.unshift("~/lib/ruby")
 

data/lib/rbibtex/rbibtex.y

@@ -2,8 +2,10 @@ class BibTeX::Parser
 
 rule
 
-  file            : opt_space                         { result = val[0]    }
-                  | opt_space object_list opt_space   { result = val[1]    }
+  file            : opt_space_element                 { result = File.new(Space.new(val[0])) }
+                  | opt_space_element 
+		      object_list 
+		      opt_space_element               { result = File.new(*([val[0]] + val[1] + [val[2]]) ) }
                   ;
 
   object_list     : object                            { result = [val[0]]  }
@@ -17,7 +19,7 @@ rule
                   | entry                             { result = val[0]     }
                   ;
 
-  comment         : COMMENT opt_space value           { result = [:comment, val[2]] } 
+  comment         : COMMENT opt_space value           { result = Comment.new(val[2]) } 
                   ;
 		  
   entry           : entry_head assignment_list
@@ -60,44 +62,52 @@ rule
                   | SINGLE_ANFZ value_content_single_del SINGLE_ANFZ   { result = val[1] }
 		  | DOUBLE_ANFZ value_content_double_del DOUBLE_ANFZ   { result = val[1] }
 		  | WORD
+		  ;  
+
+  brace           : LBRACE
+                  | RBRACE
+		  ;
+		  
+  anfz            : SINGLE_ANFZ
+                  | DOUBLE_ANFZ
 		  ;
 
   value_content_single_del   :                       { result = "" }
-                  | value_content SPACE              { result << val[1] }
-                  | value_content WORD               { result << val[1] }
-                  | value_content COMMA              { result << val[1] }
-/*                  | value_content "\\" SINGLE_ANFZ   { result << val[1] << val[2]} */
+                  | value_content general_vc_token   { result << val[1] }
+                  | value_content brace              { result << val[1] }
                   | value_content DOUBLE_ANFZ        { result << val[1] }
-                  | value_content CHARACTER          { result << val[1] }
-                  | value_content AT                 { result << val[1] }
-                  | value_content LBRACE             { result << val[1] }
-                  | value_content RBRACE             { result << val[1] }
 		  ;
 
   value_content_double_del   :                       { result = "" }
-                  | value_content SPACE              { result << val[1] }
-                  | value_content WORD               { result << val[1] }
-                  | value_content COMMA              { result << val[1] }
+                  | value_content general_vc_token   { result << val[1] }
+                  | value_content brace              { result << val[1] }
                   | value_content SINGLE_ANFZ        { result << val[1] }
-/*                  | value_content "\\" DOUBLE_ANFZ   { result << val[1] << val[2] } */
-                  | value_content CHARACTER          { result << val[1] }
-                  | value_content AT                 { result << val[1] }
-                  | value_content LBRACE             { result << val[1] }
-                  | value_content RBRACE             { result << val[1] }
 		  ;
 
-  value_content   :                                   { result = "" }
-                  | value_content SPACE              { result << val[1] }
-                  | value_content WORD               { result << val[1] }
-                  | value_content COMMA              { result << val[1] }
-                  | value_content SINGLE_ANFZ        { result << val[1] }
-                  | value_content DOUBLE_ANFZ        { result << val[1] }
-                  | value_content CHARACTER          { result << val[1] }
-                  | value_content AT                 { result << val[1] }
+  value_content   :                                  { result = "" }
+                  | value_content general_vc_token   { result << val[1] }
+                  | value_content anfz               { result << val[1] }
                   | value_content 
 		         LBRACE value_content RBRACE { result << val[1] << val[2] << val[3] }
 		  ;
 
+  general_vc_token : SPACE
+                  | WORD		
+                  | COMMA		       
+                  | EQUALS                      
+                  | CHARACTER                    
+                  | AT                            
+		  ;
+
+  opt_space_element :
+                    | space_element
+		    ;
+
+  space_element   : SPACE                           { result = Space.new(val[0]) }
+
+  space           : SPACE
+                  ;
+
   opt_space       : 
                   | SPACE                             
 	          ;
@@ -109,6 +119,34 @@ end
 
 module BibTeX
   Entry = Struct.new(:type, :key, :properties)
+
+  class Space < String; end
+
+  class Comment
+    def initialize(comment)
+      @comment = comment
+    end
+
+    def to_s
+      @comment
+    end
+
+    alias :to_str :to_s
+  end  
+  
+  class File
+    def initialize(*elements)
+      @elements = elements.compact
+    end
+
+    def elements
+      @elements
+    end
+
+    def entries
+      @elements.select { | e | e.is_a?Entry }
+    end
+  end
 end
 
 ---- inner ----
@@ -120,13 +158,13 @@ end
   def parse( str )
     @q = []
 
-    @yydebug = true
+#   @yydebug = true
 
     while str.size > 0 do
       case str
       when /\A[\t\n\s]+/o
         @q.push [:SPACE, $&]
-      when /\ACOMMENT/o
+      when /\Acomment/io
         @q.push [:COMMENT, $&]
       when /\A\,/o
         @q.push [:COMMA, $&]

data/papers.bib

@@ -184,7 +184,8 @@
   pages = {70--73}, 
   year = 2005,
   Organization = {IEEE},
-  note = {A short overview of applications and methods for lip tracking, automated speech recogniton, person recogniton, etc. Pointers to databases with joint AV material and relevant Publications.}
+  note = {A short overview of applications and methods for lip tracking, automated speech recogniton, person recogniton, etc. Pointers to databases with joint AV material and relevant Publications.},
+  pdf = {}
 }
 
 @Article{seyadarabi:facial,
@@ -195,5 +196,11 @@ NUMBER = 4 ,
 year = 2004 ,
 ISSN = {1305-239X},
 Author = {Hadi Seyedarabi and Ali Aghagolzadeh and Sohrab Khanmohammadi},
-note = {Written in very bad english and does not contain too much information. They track feature points in 2D video data using optical flow and use these points to interpolate a triangle mesh. They claim to have a muscle-based model, but that shows nowhere.}
+note = {Written in very bad english and does not contain too much information. They track feature points in 2D video data using optical flow and use these points to interpolate a triangle mesh. They claim to have a muscle-based model, but that shows nowhere.},
+pdf = {}
+}
+
+@comment {
+  todo:
+    pdf = {local/blake_sparse_realtime_tracking.pdf}
 }

data/test.bib

@@ -0,0 +1,5 @@
+@comment {
+  todo:
+    pdf = {local/blake_sparse_realtime_tracking.pdf}
+  x
+}

metadata

@@ -3,7 +3,7 @@ rubygems_version: 0.8.11
 specification_version: 1
 name: rbibtex
 version: !ruby/object:Gem::Version 
-  version: 0.0.1
+  version: 0.0.2
 date: 2005-11-09 00:00:00 +01:00
 summary: A bibtex parsing library written in pure ruby
 require_paths: 
@@ -39,7 +39,9 @@ authors:
 files: 
   - papers.bib
   - README
+  - test.bib
   - CHANGELOG
+  - InstalledFiles
   - papers.html
   - setup.rb
   - bin