bibtex_parser 1.0.0 → 1.0.1

data/CHANGELOG

@@ -1,3 +1,9 @@
+*1.0.1 (March 08, 2010)*
+
+* <x@y, x=jshantz4, y=csd.uwo.ca>: Moved classes to BibTeX module and added
+                                   BibTeX::Parser.parse_bibtex() method to parse
+                                   a BibTeX string
+
 *1.0.0 (March 02, 2010)*
 
 * <x@y, x=jshantz4, y=csd.uwo.ca>: Initial release

data/README

@@ -20,12 +20,37 @@ license.  Please see LICENSE for more details
 
 == Parsing a BibTeX File
 
-A BibTeX file can be parsed using the BibTeXParser class:
+A BibTeX file can be parsed using the BibTeX::Parser class:
 
     require 'rubygems'
     require 'bibtex_parser'
 
-    entries = BibTeXParser.parse_bibtex_file('thesis.bib')
+    entries = BibTeX::Parser.parse_bibtex_file('thesis.bib')
+
+    entries.each do |entry|
+        puts entry.title
+        puts entry.year
+    end
+
+== Parsing a BibTeX string
+
+A string containing BibTeX content can be parse BibTeX file can also be parsed
+using the BibTeX::Parser class:
+
+    require 'rubygems'
+    require 'bibtex_parser'
+
+    bibtex =<<EOF
+
+    @inproceedings{shantz:2009,
+        author = "Jeffrey Shantz",
+        title = "BibTeX::Parser",
+        year = "2009"
+    }
+
+    EOF
+
+    entries = BibTeX::Parser.parse_bibtex(bibtex)
 
     entries.each do |entry|
         puts entry.title
@@ -40,7 +65,7 @@ name to get or set, or simply use "dot" notation, as shown below:
     require 'rubygems'
     require 'bibtex_parser'
 
-    entries = BibTeXParser.parse_bibtex_file('thesis.bib')
+    entries = BibTeX::Parser.parse_bibtex_file('thesis.bib')
     entry = entries[0]
 
     entry.year = 2010
@@ -52,7 +77,7 @@ name to get or set, or simply use "dot" notation, as shown below:
 == Getting author data
 
 Authors (or editors) are stored under the 'author' key as an array of
-BibTeXAuthor objects.  A BibTeXAuthor contains an author's name parsed into
+BibTeX::Author objects.  A BibTeX::Author contains an author's name parsed into
 First, Middle, and Last parts.  Unlike other BibTeX parsers currently in
 existence, this parser does not extract "von" and "jr" parts of names.  This
 may be implemented in the future, should demand arise.
@@ -60,7 +85,7 @@ may be implemented in the future, should demand arise.
     require 'rubygems'
     require 'bibtex_parser'
 
-    entries = BibTeXParser.parse_bibtex_file('thesis.bib')
+    entries = BibTeX::Parser.parse_bibtex_file('thesis.bib')
     entry = entries[0]
     first_author = entry.authors[0]
 
@@ -76,7 +101,7 @@ whether or not a citation is valid and, if not, why it is failing.
     require 'rubygems'
     require 'bibtex_parser'
 
-    entries = BibTeXParser.parse_bibtex_file('thesis.bib')
+    entries = BibTeX::Parser.parse_bibtex_file('thesis.bib')
     entry = entries[0]
 
     unless (entry.valid?)

data/Rakefile

@@ -8,7 +8,7 @@ require 'spec/rake/spectask'
 
 spec = Gem::Specification.new do |s|
   s.name = 'bibtex_parser'
-  s.version = '1.0.0'
+  s.version = '1.0.1'
   s.has_rdoc = true
   s.extra_rdoc_files = ['README', 'LICENSE','CHANGELOG']
   s.summary = 'A parser for the BibTeX citation format'

data/lib/bibtex_author.rb

@@ -4,47 +4,51 @@
 #
 # Licensed under the MIT license -- see LICENSE for more details
 
-class BibTeXAuthor
+module BibTeX
 
-  attr_accessor :first_name, :last_name, :middle_name, :raw_name
+  class Author
+
+    attr_accessor :first_name, :last_name, :middle_name, :raw_name
   
-  def initialize(name)
-    @raw_name = name.strip
-    parse
-  end
+    def initialize(name)
+      @raw_name = name.strip
+      parse
+    end
   
-  def parse
+    def parse
   
-    if @raw_name =~ /^([\w.-]+)\s*(?:(\w\.))?\s*([\w.-]+)$/ # First M. Last
-      @first_name = $1
-      @last_name = $3
-      @middle_name = $2 unless $2.nil?      
-    elsif @raw_name =~ /^([\w.-]+)\s*,\s*([\w.-]+)\s*(?:([\w]\.)?)$/ # Last, First M.
-      @first_name = $2
-      @last_name = $1
-      @middle_name = $3 unless $3.nil?
-    elsif @raw_name.index(",") # De Last, First
-      parts = @raw_name.split(/\s*,\s*/) 
-      @last_name = parts[0]
-      @first_name = parts[1]
-      @middle_name = nil
-    else # First De Last
-      parts = @raw_name.split(/\s+/) 
-      @first_name = parts.shift
-      @last_name = parts.join(" ")
-      @middle_name = nil
-    end
+      if @raw_name =~ /^([\w.-]+)\s*(?:(\w\.))?\s*([\w.-]+)$/ # First M. Last
+        @first_name = $1
+        @last_name = $3
+        @middle_name = $2 unless $2.nil?
+      elsif @raw_name =~ /^([\w.-]+)\s*,\s*([\w.-]+)\s*(?:([\w]\.)?)$/ # Last, First M.
+        @first_name = $2
+        @last_name = $1
+        @middle_name = $3 unless $3.nil?
+      elsif @raw_name.index(",") # De Last, First
+        parts = @raw_name.split(/\s*,\s*/)
+        @last_name = parts[0]
+        @first_name = parts[1]
+        @middle_name = nil
+      else # First De Last
+        parts = @raw_name.split(/\s+/)
+        @first_name = parts.shift
+        @last_name = parts.join(" ")
+        @middle_name = nil
+      end
       
-  end
+    end
   
-#  def inspect
-#
-#    s = ""
-#    s += "\t\tFIRST  : #{@first_name}\n"
-#    s += "\t\tMIDDLE : #{@middle_name}\n"
-#    s += "\t\tLAST   : #{@last_name}\n"
-#
-#    return s
-#
-#  end
+    #  def inspect
+    #
+    #    s = ""
+    #    s += "\t\tFIRST  : #{@first_name}\n"
+    #    s += "\t\tMIDDLE : #{@middle_name}\n"
+    #    s += "\t\tLAST   : #{@last_name}\n"
+    #
+    #    return s
+    #
+    #  end
+  end
+
 end

data/lib/bibtex_entry.rb

@@ -6,177 +6,181 @@ require 'bibtex_author'
 #
 # Licensed under the MIT license -- see LICENSE for more details
 
-class BibTeXEntry
+module BibTeX
 
-  attr_accessor :raw_bibtex, :valid, :type, :key, :errors, :authors
+  class Entry
+
+    attr_accessor :raw_bibtex, :valid, :type, :key, :errors, :authors
   
-  def initialize(block)
+    def initialize(block)
     
-    @raw_bibtex = block
-    @valid = true
-    @fields = {}
-    @authors = []
-    @errors = []
-    self.parse
+      @raw_bibtex = block
+      @valid = true
+      @fields = {}
+      @authors = []
+      @errors = []
+      self.parse
     
-  end
+    end
 
-  def valid?
-    @valid
-  end
+    def valid?
+      @valid
+    end
 
-  def [](key)
-    key = key.strip.downcase.to_sym if (key.is_a?(String))
-    @fields[key]
-  end
+    def [](key)
+      key = key.strip.downcase.to_sym if (key.is_a?(String))
+      @fields[key]
+    end
 
-  def []=(key, value)    
-    key = key.strip.downcase.to_sym if (key.is_a?(String))
-    @fields[key] = value
-  end
+    def []=(key, value)
+      key = key.strip.downcase.to_sym if (key.is_a?(String))
+      @fields[key] = value
+    end
 
-  def has_key?(key)
-    key = key.strip.downcase.to_sym if (key.is_a?(String))
-    @fields.has_key?(key)
-  end
+    def has_key?(key)
+      key = key.strip.downcase.to_sym if (key.is_a?(String))
+      @fields.has_key?(key)
+    end
 
-  def parse  
-    @valid = true
-    @errors = []
-    @raw_bibtex.strip!  
-    @parsed = @raw_bibtex 
+    def parse
+      @valid = true
+      @errors = []
+      @raw_bibtex.strip!
+      @parsed = @raw_bibtex
      
-    return unless parse_type
-    return unless parse_key
-    parse_fields    
-    parse_authors
+      return unless parse_type
+      return unless parse_key
+      parse_fields
+      parse_authors
     
-    if ((! self.has_key?(:year)) || (self[:year].eql?("")))
-      @errors << "Missing year field"
-      @valid = false
-    end
+      if ((! self.has_key?(:year)) || (self[:year].eql?("")))
+        @errors << "Missing year field"
+        @valid = false
+      end
     
-    if ((! self.has_key?(:title)) || (self[:title].eql?("")))
-      @errors << "Missing title field"
-      @valid = false
-    end
+      if ((! self.has_key?(:title)) || (self[:title].eql?("")))
+        @errors << "Missing title field"
+        @valid = false
+      end
     
-  end       
+    end
   
-#  def inspect
-#
-#    s =  "TYPE: #{@type}\n"
-#    s += "KEY: #{@key}\n"
-#    s += "FIELDS [#{@fields.size}]: \n"
-#    s += "VALID: #{@valid}\n"
-#
-#    @fields.each do |k,v|
-#      s += "\t#{k}\t=> #{v}\n"
-#    end
-#
-#    s += "AUTHORS [#{@authors.size}]: \n"
-#    @authors.each do |author|
-#      s+= author.inspect
-#    end
-#    s += "\n\n#{@parsed}"
-#
-#    s += "ERRORS [#{@errors.size}]: \n"
-#    @errors.each do |error|
-#      s+= "\t\t#{error}\n"
-#    end
-#
-#    return s
-#
-#  end
-
-  def method_missing(sym, *arguments)
+    #  def inspect
+    #
+    #    s =  "TYPE: #{@type}\n"
+    #    s += "KEY: #{@key}\n"
+    #    s += "FIELDS [#{@fields.size}]: \n"
+    #    s += "VALID: #{@valid}\n"
+    #
+    #    @fields.each do |k,v|
+    #      s += "\t#{k}\t=> #{v}\n"
+    #    end
+    #
+    #    s += "AUTHORS [#{@authors.size}]: \n"
+    #    @authors.each do |author|
+    #      s+= author.inspect
+    #    end
+    #    s += "\n\n#{@parsed}"
+    #
+    #    s += "ERRORS [#{@errors.size}]: \n"
+    #    @errors.each do |error|
+    #      s+= "\t\t#{error}\n"
+    #    end
+    #
+    #    return s
+    #
+    #  end
+
+    def method_missing(sym, *arguments)
     
-    if (sym.to_s =~ /=$/)      
-      self.send(:[]=, sym.to_s.chop, *arguments)
-    else
-      self.send(:[], sym)
-    end
+      if (sym.to_s =~ /=$/)
+        self.send(:[]=, sym.to_s.chop, *arguments)
+      else
+        self.send(:[], sym)
+      end
     
-  end
+    end
 
 
-  private
+    private
 
-  def parse_type
+    def parse_type
+
+      if (@parsed =~ /^(\s*@([[:alpha:]]+)\s*\{)/)
+        @type = $2
+        @parsed = @parsed[$1.length..-1]
+        @valid = true
+      else
+        @errors << "Missing citation type"
+        @valid = false
+      end
 
-    if (@parsed =~ /^(\s*@([[:alpha:]]+)\s*\{)/)
-      @type = $2
-      @parsed = @parsed[$1.length..-1]
-      @valid = true
-    else
-      @errors << "Missing citation type"
-      @valid = false
     end
 
-  end
+    def parse_key
 
-  def parse_key
+      idx = @parsed.index(",")
 
-    idx = @parsed.index(",")
+      if (idx)
 
-    if (idx)
+        key = @parsed[0...idx].strip
 
-      key = @parsed[0...idx].strip
+        # Quick sanity check to ensure the user specified a key -- don't
+        # want to treat a "KEY = VALUE," pair as the key simply because
+        # there's a comma after the pair
+        if (key =~ /=/)
+          @errors << "Missing citation key"
+          @valid = false
 
-      # Quick sanity check to ensure the user specified a key -- don't
-      # want to treat a "KEY = VALUE," pair as the key simply because
-      # there's a comma after the pair
-      if (key =~ /=/)
+        else
+          @key = key
+          @parsed = @parsed[idx+1..-1]
+        end
+      else
         @errors << "Missing citation key"
         @valid = false
-
-      else
-        @key = key
-        @parsed = @parsed[idx+1..-1]
       end
-    else
-      @errors << "Missing citation key"
-      @valid = false
     end
-  end
 
-  def parse_fields
+    def parse_fields
 
-    pairs = @parsed.scan(/(\s*[[:alpha:]]+\s*=\s*(?:\{.*\}|".*"))/)
+      pairs = @parsed.scan(/(\s*[[:alpha:]]+\s*=\s*(?:\{.*\}|".*"))/)
 
-    pairs.each do |pair|
-      parts = pair[0].split("=")
-      key = parts[0].strip.downcase
-      value = parts[1].strip
-      value.sub!(/^\{(.*)\}$/,"\\1") if value
-      value.sub!(/^"(.*)"$/,"\\1") if value
-      self[key] = value.strip
-    end
+      pairs.each do |pair|
+        parts = pair[0].split("=")
+        key = parts[0].strip.downcase
+        value = parts[1].strip
+        value.sub!(/^\{(.*)\}$/,"\\1") if value
+        value.sub!(/^"(.*)"$/,"\\1") if value
+        self[key] = value.strip
+      end
 
-  end
+    end
 
-  def parse_authors
+    def parse_authors
 
-    unless ((self.has_key?(:author)) || (self.has_key?(:editor)))
-      @errors << "Missing author or editor field"
-      @valid = false
-      return
-    end
+      unless ((self.has_key?(:author)) || (self.has_key?(:editor)))
+        @errors << "Missing author or editor field"
+        @valid = false
+        return
+      end
 
-    if ((self.has_key?(:author)) && (self[:author].length > 0))
-      authors = self[:author]
-    elsif ((self.has_key?(:editor)) && (self[:editor].length > 0))
-      authors = self[:editor]
-    else
-      @errors << "Missing author or editor field"
-      @valid = false
-      return
-    end
+      if ((self.has_key?(:author)) && (self[:author].length > 0))
+        authors = self[:author]
+      elsif ((self.has_key?(:editor)) && (self[:editor].length > 0))
+        authors = self[:editor]
+      else
+        @errors << "Missing author or editor field"
+        @valid = false
+        return
+      end
 
-    author_list = authors.split(/\s+and\s+/)
+      author_list = authors.split(/\s+and\s+/)
     
-    author_list.each do |author_name|
-      @authors << BibTeXAuthor.new(author_name)
+      author_list.each do |author_name|
+        @authors << BibTeX::Author.new(author_name)
+      end
+
     end
 
   end

data/lib/bibtex_parser.rb

@@ -1,4 +1,5 @@
 require 'bibtex_entry'
+require 'stringio'
 
 # = BibTeXParser - Simple BibTeX parsing
 #
@@ -27,7 +28,32 @@ require 'bibtex_entry'
 #    require 'rubygems'
 #    require 'bibtex_parser'
 #
-#    entries = BibTeXParser.parse_bibtex_file('thesis.bib')
+#    entries = BibTeX::Parser.parse_bibtex_file('thesis.bib')
+#
+#    entries.each do |entry|
+#        puts entry.title
+#        puts entry.year
+#    end
+#
+# == Parsing a BibTeX string
+#
+# A string containing BibTeX content can be parse BibTeX file can also be parsed
+# using the BibTeX::Parser class:
+#
+#    require 'rubygems'
+#    require 'bibtex_parser'
+#
+#    bibtex =<<EOF
+#
+#    @inproceedings{shantz:2009,
+#        author = "Jeffrey Shantz",
+#        title = "BibTeX::Parser",
+#        year = "2009"
+#    }
+#
+#    EOF
+#
+#    entries = BibTeX::Parser.parse_bibtex(bibtex)
 #
 #    entries.each do |entry|
 #        puts entry.title
@@ -42,7 +68,7 @@ require 'bibtex_entry'
 #    require 'rubygems'
 #    require 'bibtex_parser'
 #
-#    entries = BibTeXParser.parse_bibtex_file('thesis.bib')
+#    entries = BibTeX::Parser.parse_bibtex_file('thesis.bib')
 #    entry = entries[0]
 #
 #    entry.year = 2010
@@ -54,8 +80,8 @@ require 'bibtex_entry'
 # == Getting author data
 #
 # Authors (or editors) are stored under the 'author' key as an array of
-# BibTeXAuthor objects.  A BibTeXAuthor contains an author's name parsed into
-# First, Middle, and Last parts.  Unlike other BibTeX parsers currently in
+# BibTeX::Author objects.  A BibTeX::Author contains an author's name parsed
+# into First, Middle, and Last parts.  Unlike other BibTeX parsers currently in
 # existence, this parser does not extract "von" and "jr" parts of names.  This
 # may be implemented in the future, should demand arise.
 #
@@ -78,7 +104,7 @@ require 'bibtex_entry'
 #    require 'rubygems'
 #    require 'bibtex_parser'
 #
-#    entries = BibTeXParser.parse_bibtex_file('thesis.bib')
+#    entries = BibTeX::Parser.parse_bibtex_file('thesis.bib')
 #    entry = entries[0]
 #
 #    unless (entry.valid?)
@@ -89,7 +115,7 @@ require 'bibtex_entry'
 #
 # == Special entry attributes
 #
-# The following attributes of the BibTexEntry class may be of interest to you:
+# The following attributes of the BibTex::Entry class may be of interest to you:
 #
 #    * raw_bibtex    - Returns the raw BibTeX citation from which the entry was
 #                      created
@@ -108,60 +134,56 @@ require 'bibtex_entry'
 #
 # Send bug reports to: x@y, where x is equal to jshantz4, and y = csd.uwo.ca
 
-class BibTeXParser
+module BibTeX
 
-  def BibTeXParser.parse_bibtex_file(filename)
+  class Parser
 
-    f = File.open(filename)
-    blocks = []
-    entries = []
-    
-    while (!f.eof?)
-      line = f.gets
-          
-      if ((line =~ /^\s*@[[:alpha:]]+/) && (line !~ /@(string|preamble)/i))
-        blocks << extract_block(f,line)
-      end
+    def Parser.parse_bibtex(bibtex_string)
+
+      stream = StringIO.new(bibtex_string)
+      return parse_stream(stream)
       
     end
-    
-    blocks.each do |block|
-      entries << BibTeXEntry.new(block)
-    end
 
-    return entries    
+    def Parser.parse_bibtex_file(filename)
+
+      f = File.open(filename)
+      return parse_stream(f)
   
-  end
+    end
+
+    def Parser.parse_stream(stream)
+
+      blocks = []
+      entries = []
+
+      while (!stream.eof?)
+        line = stream.gets
 
-  private
+        if ((line =~ /^\s*@[[:alpha:]]+/) && (line !~ /@(string|preamble)/i))
+          blocks << extract_block(stream,line)
+        end
+
+      end
+
+      blocks.each do |block|
+        entries << BibTeX::Entry.new(block)
+      end
+
+      return entries
+
+    end
+
+    private
   
-  def BibTeXParser.extract_block(f, start_line)
+    def Parser.extract_block(f, start_line)
     
-    stack = []
-    first_brace_seen = false
-    block = ""
+      stack = []
+      first_brace_seen = false
+      block = ""
       
-    start_line.each_char do |c|
+      start_line.each_char do |c|
     
-      block += c
-
-      if (c.eql?("{"))
-        stack.push("{")
-        first_brace_seen = true
-      elsif (c.eql?("}"))
-        stack.pop()
-      end    
-      
-      return block if ((first_brace_seen) && (stack.length == 0))
-      
-    end  
-
-    while (((first_brace_seen) ^ (stack.length == 0)) && (!f.eof?))
-    
-      line = f.gets
-      
-      line.each_char do |c|
-      
         block += c
 
         if (c.eql?("{"))
@@ -169,19 +191,39 @@ class BibTeXParser
           first_brace_seen = true
         elsif (c.eql?("}"))
           stack.pop()
-        end    
+        end
+      
+        return block if ((first_brace_seen) && (stack.length == 0))
       
-        break if ((first_brace_seen) && (stack.length == 0))
       end
+
+      while (((first_brace_seen) ^ (stack.length == 0)) && (!f.eof?))
+    
+        line = f.gets
       
-    end
+        line.each_char do |c|
+      
+          block += c
+
+          if (c.eql?("{"))
+            stack.push("{")
+            first_brace_seen = true
+          elsif (c.eql?("}"))
+            stack.pop()
+          end
+      
+          break if ((first_brace_seen) && (stack.length == 0))
+        end
+      
+      end
           
-    return block
+      return block
   
-  end
+    end
   
-end
+  end
 
+end
 #entries = BibTeXParser.parse_bibtex_file('cs9544a_project.bib')
 #entries = BibTeXParser.parse_bibtex_file('test.bib')
 #entries.each do |entry|

metadata

@@ -5,8 +5,8 @@ version: !ruby/object:Gem::Version
   segments: 
   - 1
   - 0
-  - 0
-  version: 1.0.0
+  - 1
+  version: 1.0.1
 platform: ruby
 authors: 
 - Jeff Shantz
@@ -14,7 +14,7 @@ autorequire:
 bindir: bin
 cert_chain: []
 
-date: 2010-03-02 00:00:00 -05:00
+date: 2010-03-08 00:00:00 -05:00
 default_executable: 
 dependencies: []