gedcom 0.9.0

data/History.txt

@@ -0,0 +1,4 @@
+=== 0.9.0 / 2009-03-14
+
+* transcription of code from original Rails source base.
+

data/Manifest.txt

@@ -0,0 +1,74 @@
+History.txt
+Manifest.txt
+README.txt
+Rakefile
+lib/gedcom/address_record.rb
+lib/gedcom/adoption_record.rb
+lib/gedcom/cause_record.rb
+lib/gedcom/change_date_record.rb
+lib/gedcom/character_set_record.rb
+lib/gedcom/citation_data_record.rb
+lib/gedcom/citation_event_type_record.rb
+lib/gedcom/corporate_record.rb
+lib/gedcom/date_record.rb
+lib/gedcom/encoded_line_record.rb
+lib/gedcom/event_age_record.rb
+lib/gedcom/event_record.rb
+lib/gedcom/events_list_record.rb
+lib/gedcom/families_individuals.rb
+lib/gedcom/family_record.rb
+lib/gedcom/gedcom_all.rb
+lib/gedcom/gedcom_base.rb
+lib/gedcom/gedcom_record.rb
+lib/gedcom/header_data_record.rb
+lib/gedcom/header_record.rb
+lib/gedcom/header_source_record.rb
+lib/gedcom/individual_attribute_record.rb
+lib/gedcom/individual_record.rb
+lib/gedcom/association_record.rb
+lib/gedcom/multimedia_citation_record.rb
+lib/gedcom/multimedia_record.rb
+lib/gedcom/name_record.rb
+lib/gedcom/note_citation_record.rb
+lib/gedcom/note_record.rb
+lib/gedcom/place_record.rb
+lib/gedcom/refn_record.rb
+lib/gedcom/repository_caln.rb
+lib/gedcom/repository_citation_record.rb
+lib/gedcom/repository_record.rb
+lib/gedcom/source_citation_record.rb
+lib/gedcom/source_record.rb
+lib/gedcom/source_scope_record.rb
+lib/gedcom/submission_record.rb
+lib/gedcom/submitter_record.rb
+lib/gedcom/text_record.rb
+lib/gedcom/trailer_record.rb
+lib/gedcom/transmission.rb
+lib/gedcom/transmission_base.rb
+lib/gedcom.rb
+lib/parser/class_tracker.rb
+lib/parser/ged_line.rb
+lib/parser/gedcom_parser.rb
+lib/parser/instruction.rb
+lib/parser/parse_state.rb
+test/test_gedcom.rb
+test_data/Document.RTF
+test_data/Document.tex
+test_data/ImgFile.BMP
+test_data/ImgFile.GIF
+test_data/ImgFile.JPG
+test_data/ImgFile.MAC
+test_data/ImgFile.PCX
+test_data/ImgFile.PIC
+test_data/ImgFile.PNG
+test_data/ImgFile.PSD
+test_data/ImgFile.TGA
+test_data/ImgFile.TIF
+test_data/README.txt
+test_data/TGC551.ged
+test_data/TGC551LF.ged
+test_data/TGC55C.ged
+test_data/TGC55CLF.ged
+test_data/force.wav
+test_data/suntun.mov
+test_data/top.mpg

data/README.txt

@@ -0,0 +1,129 @@
+= gedcom
+
+* http://rubyforge.org/projects/gedcom/
+
+== DESCRIPTION:
+
+A Ruby GEDCOM text file parser and producer, that produces a tree of objects from each of the
+GEDCOM file types and subtypes. Understands the full GEDCOM 5.5.1 grammar, and will handle 
+unknown tags hierarchies as a Note class.
+ 
+ 
+== FEATURES/PROBLEMS:
+
+* Gedcom multicharacter ANSEL encoding is currently not understood when reading and writing, but is preserved if the file is opened as ASCII-8BIT.
+* CR line termination causes issues for systems with native LF line termination (CRLF is fine).
+* Dates are currently just strings, but I want to parse these and test their validatity. 
+  This is not as easy as it may seem at first, as dates may be in many formats, 
+  they may be partial, or may actually be strings decribing the date. 
+* For my own use, I bend the GEDCOM 5.5 standard by allowing the reading of the following types in non-standard ways. 
+  These will not affect the reading and writing of valid GEDCOM 5.5.
+* * 'NOTE' type to appear in places it is not defined to exist in GEDCOM.
+           This is necessary in order to be able to convert user defined tags into NOTE records.
+* * 'RESN' type to appear in places it is not defined to exist in GEDCOM.
+           I wanted to be able to mark any record as restricted.
+* * 'SUBM' type to appear in 'EVEN' records.
+           I wanted to be able to track where I got the event information from.
+* * 'SEX' type to appear multiple times in an 'INDI' record,
+          as a person's sex can now be changed.
+* * 'SEX' type to allow more than 'M', 'F' and 'U',  
+          to allow for the XXY, XXXY and X and other genetic anomolies associated with gender.
+* * 'NAME' type allows event details ( eg 'DATE') , 
+           as names changes are events, not just an attribute.
+* * 'ADDR' type allows a 'TYPE' entry 
+           to qualify what the address is for (e.g. home, work, ...) .
+* User defined tags are converted to the NOTE type, with sublevels being CONT lines.
+  These are recognised as any tag starting with '_'. 
+* Haven't yet merged in the code to pretty print a family tree.
+* Want to add a merge option, to take multiple transmission and make a single one from them.
+* save/load (to/from a database) is yet to be ported. GedcomBase#to_db is a dummy function.
+
+== SYNOPSIS:
+
+require 'gedcom'
+
+puts "parse TGC551LF.ged"
+g = Gedcom.file("../test_data/TGC551LF.ged", "r:ASCII-8BIT") #OK with LF line endings.
+g.transmissions[0].summary
+puts 
+puts "parse TGC55CLF.ged"
+g.file("../test_data/TGC55CLF.ged", "r:ASCII-8BIT") #Ok with CR LF line endings.
+g.transmissions[1].summary
+
+
+#print the parsed file to see if it matches the source file.
+#Note CONT and CONC breaks may end up in different places
+#Note Order of TAGS at the same level may be different
+#Note User TAGS are output as Notes.
+File.open( "../test_data/TGC551LF.out", "w:ASCII-8BIT") do |file|
+  file.print g.transmissions[0].to_gedcom
+end
+File.open( "../test_data/TGC55CLF.out", "w:ASCII-8BIT") do |file|
+  file.print g.transmissions[1].to_gedcom
+end
+puts "\nComplete"
+
+
+== REQUIREMENTS:
+
+* require 'rubygems'
+
+== INSTALL:
+
+* sudo gem install gedcom
+
+== LICENSE:
+
+Distributed under the Ruby License.
+
+Copyright (c) 2009
+
+1. You may make and give away verbatim copies of the source form of the
+   software without restriction, provided that you duplicate all of the
+   original copyright notices and associated disclaimers.
+
+2. You may modify your copy of the software in any way, provided that
+   you do at least ONE of the following:
+
+     a) place your modifications in the Public Domain or otherwise
+        make them Freely Available, such as by posting said
+  modifications to Usenet or an equivalent medium, or by allowing
+  the author to include your modifications in the software.
+
+     b) use the modified software only within your corporation or
+        organization.
+
+     c) rename any non-standard executables so the names do not conflict
+  with standard executables, which must also be provided.
+
+     d) make other distribution arrangements with the author.
+
+3. You may distribute the software in object code or executable
+   form, provided that you do at least ONE of the following:
+
+     a) distribute the executables and library files of the software,
+  together with instructions (in the manual page or equivalent)
+  on where to get the original distribution.
+
+     b) accompany the distribution with the machine-readable source of
+  the software.
+
+     c) give non-standard executables non-standard names, with
+        instructions on where to get the original software distribution.
+
+     d) make other distribution arrangements with the author.
+
+4. You may modify and include the part of the software into any other
+   software (possibly commercial).  But some files in the distribution
+   may not written by the author, so that they are not under this terms.
+
+5. The scripts and library files supplied as input to or produced as 
+   output from the software do not automatically fall under the
+   copyright of the software, but belong to whomever generated them, 
+   and may be sold commercially, and may be aggregated with this
+   software.
+
+6. THIS SOFTWARE IS PROVIDED "AS IS" AND WITHOUT ANY EXPRESS OR
+   IMPLIED WARRANTIES, INCLUDING, WITHOUT LIMITATION, THE IMPLIED
+   WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
+   PURPOSE.

data/Rakefile

@@ -0,0 +1,13 @@
+# -*- ruby -*-
+
+require 'rubygems'
+require 'hoe'
+require 'lib/gedcom.rb'
+
+Hoe.new('gedcom', Gedcom::VERSION) do |p|
+  p.rubyforge_name = "gedcom" 
+  p.developer( "Rob Burrowes","rob@burrowes.org")
+  p.remote_rdoc_dir = '' # Release to root
+end
+
+# vim: syntax=Ruby

data/lib/gedcom.rb

@@ -0,0 +1,105 @@
+#Gedcom class holds an array of GEDCOM transmissions (that is parsed GEDCOM files)
+#Each transmission relates to the loading of a GEDCOM text file, parsing it into
+#a tree, starting with a Transmission class at its root. Within the Transmission
+#class are arrays for each of the level 0 GEDCOM record types of these classes:
+#  * Header_record
+#  * Submission_record 
+#  * Submitter_record
+#  * Individual_record
+#  * Family_record
+#  * Source_record
+#  * Repository_record
+#  * Multimedia_record
+#  * Note_record
+#  * Trailer_record
+#
+#Each of these classes has arrays for each of the Level 1 Gedcom records types
+#associated with the Level 0 type. Some of these are attributes, that is they contain
+#the actual data, while others are classes that contain attributes and/or classes
+#e.g. an Individual_record class object could have any or all of these:
+#
+# * individual_ref                   ( that is individual_ref = 'I42' if the GEDCOM line is '0 INDI @I42@')
+# Then 1 level down it is possible to get local attributes for this object
+# * restriction                      (from the GEDCOM "1 RESN restriction_value" )
+# * registered_ref_id                (from the GEDCOM "1 RFN registered_ref_id" )
+# * lds_ancestral_file_no            (from the GEDCOM "1 AFN lds_ancestral_file_no" )
+# * automated_record_id              (from the GEDCOM "1 RIN automated_record_id" )
+# Also arrays of classes may exist for these:
+# * Name_record                       (from the GEDCOM "1 NAME ..." )
+# * Individual_attribute_record       (from the GEDCOM "1 [SEX | TITL | ... ] ...")
+# * Event_record                      (from the GEDCOM "1 [BIRT | DEAT | ... ] ... ")
+# * Families_individuals              (from the GEDCOM "1 [FAMC | FAMS] ...")
+# * Individuals_individuals           (from the GEDCOM "1 [ANCI | DESO | ASSO] ...")
+# * Multimedia_citation_record        (from the GEDCOM "1 OBJE ...")
+# * Source_citation_record            (from the GEDCOM "1 SOUR ...")
+# * Note_citation_record              (from the GEDCOM "1 NOTE ...")
+# * Refn_record                       (from the GEDCOM "1 REFN ...")
+# * Change_date_record                (from the GEDCOM "1 CHAN ...")
+# And References to other record types:
+# * alias_ref                         (from the GEDCOM "1 ALIA alias_ref" )
+# * submitter_ref                     (from the GEDCOM "1 SUBM submitter_ref" )
+#
+# Below say an Event object in an Individual_record object, you could get further arrays of 
+# attributes and other objects holding further levels of the GEDCOM hierarchy.
+#
+#These can all be seen in the TAGS hash in parser/gedcom_parser.rb, which defines 
+#what TAGS are valid when, and what action to take when a particular tag is encountered
+#in the input stream.
+#
+#The reverse, that is the conversion back to GEDCOM format is not a simple reversal of the
+#TAGS entries. The generation of GEDCOM from the objects is done recursively, by calling the
+#objects to_gedcom() method. This can occur at any level, from Transmission downward.
+#
+
+def path(s,fs='/')
+  last_fs = s.rindex(fs)
+  last_fs ? s[0..last_fs] : ""
+end
+
+$: << "#{path(__FILE__)}gedcom"
+$: << "#{path(__FILE__)}parser"
+
+require 'gedcom_parser.rb'
+
+class Gedcom
+  VERSION = '0.9.0'
+  attr_accessor :transmissions
+  
+  def initialize(transmission = nil)
+    @transmissions = []
+    add_transmission(transmission) if transmission != nil
+  end
+  
+  def self.file(*a)
+    g = Gedcom.new
+    g.file(*a)
+    return g
+  end
+  
+  def file(*a)
+    transmission = Transmission.new
+    gedcom_parser = GedcomParser.new(transmission)
+    
+    File.open(*a) do   |file| 
+      file.each_line("\n") do |line|
+        begin
+          gedcom_parser.parse( file.lineno, line )
+        rescue => exception
+          puts "#{file.lineno}: #{exception} - " + line
+          # raise exception
+        end
+      end
+    end
+    
+    @transmissions << transmission
+    
+  end
+  
+  def add_transmission(transmission)
+    @transmissions << transmission
+  end
+  
+  def each
+    @transmissions.each { |t| yield t }
+  end
+end

data/lib/gedcom/address_record.rb

@@ -0,0 +1,77 @@
+require 'gedcom_base.rb'
+
+#Address_record a sub-record of HEAD, REPO, SUBM and all types of Event records.
+#
+#ADDRESS_STRUCTURE:=
+#  n ADDR <ADDRESS_LINE>              {0:1}
+#    +1 CONT <ADDRESS_LINE>           {0:M}
+#    +1 ADR1 <ADDRESS_LINE1>          {0:1}
+#    +1 ADR2 <ADDRESS_LINE2>          {0:1}
+#    +1 CITY <ADDRESS_CITY>           {0:1}
+#    +1 STAE <ADDRESS_STATE>          {0:1}
+#    +1 POST <ADDRESS_POSTAL_CODE>    {0:1}
+#    +1 CTRY <ADDRESS_COUNTRY>        {0:1}
+#
+#  I have not included the Phone number from Address_record, and include it in the parent
+#  records that include ADDRESS_STRUCTURE. This is functionally equivalent, as PHON is not
+#  a sub-record of ADDR, but at the same level.
+#
+#  n PHON <PHONE_NUMBER>              {0:3}
+#
+#==ADDRESS_CITY:= {Size=1:60}
+#  The name of the city used in the address. Isolated for sorting or indexing.
+#
+#==ADDRESS_COUNTRY:= {Size=1:60}
+#  The name of the country that pertains to the associated address. Isolated by some systems for sorting
+#  or indexing. Used in most cases to facilitate automatic sorting of mail.
+#
+#==ADDRESS_LINE:= {Size=1:60}
+#  Address information that, when combined with NAME and CONTinuation lines, meets requirements
+#  for sending communications through the mail.
+#
+#==ADDRESS_LINE1:= {Size=1:60}
+#  The first line of the address used for indexing. This corresponds to the ADDRESS_LINE value of the
+#  ADDR line in the address structure.
+#
+#==ADDRESS_LINE2:= {Size=1:60}
+#  The second line of the address used for indexing. This corresponds to the ADDRESS_LINE value of
+#  the first CONT line subordinate to the ADDR tag in the address structure.
+#
+#==ADDRESS_POSTAL_CODE:= {Size=1:10}
+#  The ZIP or postal code used by the various localities in handling of mail. Isolated for sorting or
+#  indexing.
+#
+#==ADDRESS_STATE:= {Size=1:60}
+#  The name of the state used in the address. Isolated for sorting or indexing.
+#
+#  The address structure should be formed as it would appear on a mailing label using the ADDR and
+#  ADDR.CONT lines. These lines are required if an ADDRess is present. Optionally, additional
+#  structure is provided for systems that have structured their addresses for indexing and sorting.
+#
+#The attributes are all arrays for the level +1 tags/records. 
+#* Those ending in _ref are GEDCOM XREF index keys
+#* Those ending in _record are array of classes of that type.
+#* The remainder are arrays of attributes that could be present in this record.
+class Address_record < GEDCOMBase
+  attr_accessor :address,  :address_line1, :address_line2, :city, :state, :post_code, :country, :address_type
+  attr_accessor :note_citation_record
+  
+  ClassTracker <<  :Address_record
+  
+  #new sets up the state engine arrays @this_level and @sub_level, which drive the to_gedcom method generating GEDCOM output.
+  def initialize(*a)
+    super(*a)
+    @this_level = [ [:cont, "ADDR", :address] ]
+    @sub_level =  [ #level + 1
+                    [:print, "ADR1", :address_line1],
+                    [:print, "ADR2", :address_line2],
+                    [:print, "CITY", :city],
+                    [:print, "STAE", :state],
+                    [:print, "POST", :post_code],
+                    [:print, "CTRY", :country],
+                    [:print, "TYPE", :address_type], #non standard.
+                    [:walk,  nil,   :note_citation_record],
+                  ]
+  end
+                
+end

data/lib/gedcom/adoption_record.rb

@@ -0,0 +1,57 @@
+require 'gedcom_base.rb'
+
+#Adoption_record is a rarely seen sub-record of FAMC in Individual Event_record. 
+#These can occur is Event_record BIRT and ADOP event types.
+#
+#=INDIVIDUAL_EVENT_STRUCTURE:=
+#  ...
+#  -1 ADOP [Y|<NULL>]                       {1:1} (Not this ADOP record. This is the event.)
+#    ...
+#    n FAMC @<XREF:FAM>@                    {0:1} (This FAMC and its ADOP record.)
+#      +1 ADOP <ADOPTED_BY_WHICH_PARENT>    {0:1} 
+#  ...
+#    n BIRT [Y|<NULL>]                      {1:1}
+#      ...
+#      +1 FAMC @<XREF:FAM>@                 {0:1} (And this FAMC in the BIRT Event.)
+#  ...
+#
+#==ADOPTED_BY_WHICH_PARENT:= {Size=1:4}
+#  HUSB | WIFE | BOTH
+#
+#  A code which shows which parent in the associated family record adopted this person.
+#  Where:
+#    HUSB:: The HUSBand in the associated family adopted this person.
+#    WIFE:: The WIFE in the associated family adopted this person.
+#    BOTH:: Both HUSBand and WIFE adopted this person.
+#
+#  Linkage between a child and the family they belonged to at the time of an event can also optionally
+#  be shown by a FAMC pointer subordinate to the appropriate event. For example, a FAMC pointer
+#  subordinate to an adoption event would show which family adopted this individual. Biological parent
+#  or parents can be indicated by a FAMC pointer subordinate to the birth event. The FAMC tag can
+#  also optionally be used subordinate to an ADOPtion, or BIRTh event to differentiate which set of
+#  parents were related by adoption, sealing, or birth.
+#
+#The attributes are all arrays for the level +1 tags/records. 
+#* Those ending in _ref are GEDCOM XREF index keys
+#* Those ending in _record are array of classes of that type.
+#* The remainder are arrays of attributes that could be present in this record.
+class Adoption_record < GEDCOMBase
+  attr_accessor :birth_family_ref, :adopt_family_ref, :adopted_by
+  attr_accessor :note_citation_record
+
+  ClassTracker <<  :Adoption_record
+
+  #new sets up the state engine arrays @this_level and @sub_level, which drive the to_gedcom method generating GEDCOM output.
+  def initialize(*a)
+    super(*a)
+    @this_level = [ [:xref, "FAMC", :birth_family_ref ], #Only adopted family version of birth event record
+                    [:xref, "FAMC", :adopt_family_ref]   #Adopted family version of ADOP event record
+                  ]
+    @sub_level =  [ #level 1
+                    [:print, "ADOP", :adopted_by], #Only adopted family version of ADOP event record
+                    [:walk, nil,    :note_citation_record ]
+                  ]
+  end
+
+end
+