gedcom 0.9.0

data/lib/gedcom/association_record.rb

@@ -0,0 +1,79 @@
+require 'gedcom_base.rb'
+
+#Internal representation of the GEDCOM ASSO record types. 
+#
+#A relationship between an Individual_record and one of the other level 0
+#record types, as defined by the TYPE tag. The default being another 
+#a relationship with another Individual_record.
+#
+#=ASSOCIATION_STRUCTURE:=
+#  n ASSO @<XREF:TYPE>@                   {0:M}
+#    +1 TYPE <RECORD_TYPE>                {1:1}
+#    +1 RELA <RELATION_IS_DESCRIPTOR>     {1:1}
+#    +1 <<NOTE_STRUCTURE>>                {0:M}
+#    +1 <<SOURCE_CITATION>>               {0:M}
+#
+#==RECORD_TYPE:= {Size=3:4}
+#  FAM | INDI | NOTE | OBJE | REPO | SOUR | SUBM | SUBN
+#
+#  An indicator of the record type being pointed to or used. For example if in an ASSOciation, an
+#  INDIvidual record were to be ASSOciated with a FAM record then:
+#    0 INDI
+#      1 ASSO @F1@
+#        2 TYPE FAM /* ASSOCIATION is with a FAM record.
+#        2 RELA Witness at marriage
+#
+#==RELATION_IS_DESCRIPTOR:= {Size=1:25}
+#  A word or phrase that states object 1's relation is object 2. For example you would read the following
+#  as "Joe Jacob's great grandson is the submitter pointed to by the @XREF:SUBM@":
+#     0 INDI
+#       1 NAME Joe /Jacob/
+#       1 ASSO @<XREF:SUBM>@
+#        2 TYPE SUBM
+#        2 RELA great grandson
+#
+#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 Association_record < GEDCOMBase
+  attr_accessor :association_ref, :associated_record_tag, :relationship_description
+  attr_accessor :source_citation_record, :note_citation_record
+
+  ClassTracker <<  :Association_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, "ASSO", :association_ref ] ]
+    @sub_level =  [ #level 1
+                    [:print, "TYPE",    :associated_record_tag ],
+                    [:print, "RELA",    :relationship_description ],
+                    [:walk, nil,    :source_citation_record ],
+                    [:walk, nil,    :note_citation_record ],
+                  ]
+  end
+
+  protected
+  
+  #validate that the record referenced by the XREF actually exists in this transmission.
+  #Genearte a warning if it does not. It does not stop the processing of this line.
+  #Association_records default to :individual, but the TYPE field can override this.
+  def xref_check(level, tag, index, xref)
+    asso_index = case @associated_record_tag
+    when nil then index
+    when 'FAM'  then :family
+    when 'INDI' then :individual
+    when 'NOTE' then :note
+    when 'OBJE' then :multimedia
+    when 'REPO' then :repository
+    when 'SOUR' then :source
+    when 'SUBM' then :submitter
+    when 'SUBM' then :submission
+    else :individual #which will be the default individual index.
+    end
+    
+    super(level, tag, asso_index, xref)
+  end
+end
+

data/lib/gedcom/cause_record.rb

@@ -0,0 +1,45 @@
+require 'gedcom_base.rb'
+
+#Cause_record is part of Event_record, recording the cause of the event. They aren't
+#often seen in GEDCOM files.
+#
+#=EVENT_DETAIL:=
+#  ...
+#  n CAUS <CAUSE_OF_EVENT>                   {0:1}
+#  ...
+#
+#  I have added a Restriction notice, a Source_citation_record, and a NOTE. As long as
+#  you don't use these fields, the GEDCOM output will be standard. Restriction notice 
+#  tags, like NOTE and SOUR tags, should be part of every record type, but they aren't.
+#
+#    +1 RESN <RESTRICTION_NOTICE>             {0:1}
+#    +1 <<SOURCE_CITATION>>                   {0:M}
+#    +1 <<NOTE_STRUCTURE>>                    {0:M}
+#
+#==CAUSE_OF_EVENT:=                                               {Size=1:90}
+#  Used in special cases to record the reasons which precipitated an event. Normally this will be used
+#  subordinate to a death event to show cause of death, such as might be listed on a death certificate.
+#
+# 
+#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 Cause_record   < GEDCOMBase
+  attr_accessor :cause, :restriction, :source_citation_record
+  attr_accessor :note_citation_record
+
+  ClassTracker <<  :Cause_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 = [ [:print, "CAUS", :cause] ]
+    @sub_level =  [ #level + 1
+                    [:print, "RESN", :restriction],
+                    [:walk, nil,  :source_citation_record],
+                    [:walk, nil, :note_citation_record],
+                  ]
+  end
+  
+end

data/lib/gedcom/change_date_record.rb

@@ -0,0 +1,39 @@
+require 'gedcom_base.rb'
+
+
+#Change_date_record is part of many other records, recording the
+#date and time that the parent record was last altered. It also
+#allows for a comment to be added. Probably not that useful, as
+#the standard only allows for one of these in a parent record. It
+#would be more useful to have a history of changes using multiple
+#Change_records. It would also help to have them in more records.
+#
+#=CHANGE_DATE:=
+#  n CHAN                       {1:1}
+#    +1 DATE <CHANGE_DATE>      {1:1}
+#      +2 TIME <TIME_VALUE>     {0:1}
+#    +1 <<NOTE_STRUCTURE>>      {0:M}
+#
+#  The change date is intended to only record the last change to a record. Some systems may want to
+#  manage the change process with more detail, but it is sufficient for GEDCOM purposes to indicate
+#  the last time that a record was modified.
+#
+#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 Change_date_record < GEDCOMBase
+  attr_accessor :date_record, :note_citation_record
+
+  ClassTracker <<  :Change_date_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 = [ [ :nodata, "CHAN", nil] ]
+    @sub_level =  [ #level + 1
+                    [:walk, nil, :date_record],
+                    [:walk, nil, :note_citation_record]
+                  ]
+  end
+end

data/lib/gedcom/character_set_record.rb

@@ -0,0 +1,41 @@
+require 'gedcom_base.rb'
+
+#Character_set_record is part of the HEAD record, and names the
+#the character set used in this transmission.
+#
+#=HEADER:=
+#  0 HEAD                                         {1:1}
+#   ...
+#   1 CHAR <CHARACTER_SET>                        {1:1}
+#     +1 VERS <VERSION_NUMBER>                    {0:1}
+#   ...
+#
+#==CHARACTER_SET:= {Size=1:8}
+#  ANSEL | UNICODE | ASCII
+#
+#  A code value that represents the character set to be used to interpret this data. The default character
+#  set is ANSEL, which includes ASCII as a subset.
+#
+#  Note:: The IBMPC character set is not allowed. This character set cannot be interpreted properly
+#  without knowing which code page the sender was using.
+#
+#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 Character_set_record < GEDCOMBase
+  attr_accessor :char_set_id, :version
+  attr_accessor :note_citation_record
+
+  ClassTracker <<  :Character_set_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 = [ [:print, "CHAR", :char_set_id] ]
+    @sub_level =  [ #level + 1
+                    [:print, "VERS", :version],
+                    [:walk, nil,    :note_citation_record]
+                  ]
+  end
+end

data/lib/gedcom/citation_data_record.rb

@@ -0,0 +1,49 @@
+require 'gedcom_base.rb'
+
+#Citation_data_record is DATA record in a Source_citation_record.
+# 
+#=SOURCE_CITATION:= (within another record, referencing a SOURCE_RECORD)
+#  -1 SOUR @<XREF:SOUR>@                        {1:1} (pointer to source record)
+#    ...
+#    n DATA                                     {0:1}
+#      +1 DATE <ENTRY_RECORDING_DATE>           {0:1}
+#      +1 TEXT <TEXT_FROM_SOURCE>               {0:M}
+#        +2 [ CONC | CONT ] <TEXT_FROM_SOURCE>  {0:M}
+#    ...
+#
+#==ENTRY_RECORDING_DATE:=
+#  <DATE_VALUE>
+#
+#  The date that this event data was entered into the original source document.
+#
+#==TEXT_FROM_SOURCE:=                           {Size=1:248}
+#  <TEXT>
+#
+#  A verbatim copy of any description contained within the source. This indicates notes or text that are
+#  actually contained in the source document, not the submitter's opinion about the source. This should
+#  be, from the evidence point of view, "what the original record keeper said" as opposed to the
+#  researcher's interpretation. The word TEXT, in this case, means from the text which appeared in the
+#  source record including labels.
+#
+#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 Citation_data_record < GEDCOMBase
+  attr_accessor :date_record, :text_record
+  attr_accessor :note_citation_record
+
+  ClassTracker <<  :Citation_data_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 = [ [:print, "DATA", nil ] ]
+    @sub_level =  [ #level 1
+                    [:walk, nil, :date_record],
+                    [:walk, nil, :text_record ],
+                    [:walk, nil, :note_citation_record ],
+                  ]
+  end
+end
+

data/lib/gedcom/citation_event_type_record.rb

@@ -0,0 +1,42 @@
+require 'gedcom_base.rb'
+
+#Source_citation_record has an EVEN tag. This is not an Event_record, but the event
+#type that the source record records.
+#
+#=SOURCE_CITATION:= (within another record, referencing a SOURCE_RECORD)
+#  -1 SOUR @<XREF:SOUR>@                         {1:1} (pointer to source record)
+#    ...
+#    n  EVEN <EVENT_TYPE_CITED_FROM>            {0:1}
+#      +1 ROLE <ROLE_IN_EVENT>                  {0:1}
+#    ...
+#
+#==EVENT_TYPE_CITED_FROM:=                      {SIZE=1:15}
+#  <EVENT_ATTRIBUTE_TYPE>
+#
+#  A code that indicates the type of event which was responsible for the source entry being recorded. For
+#  example, if the entry was created to record a birth of a child, then the type would be BIRT regardless
+#  of the assertions made from that record, such as the mother's name or mother's birth date. This will
+#  allow a prioritized best view choice and a determination of the certainty associated with the source
+#  used in asserting the cited fact.
+#
+#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 Citation_event_type_record < GEDCOMBase
+  attr_accessor :event_type, :role
+  attr_accessor :note_citation_record
+
+  ClassTracker <<  :Citation_event_type_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 = [ [:print, "EVEN", :event_type ] ]
+    @sub_level =  [ #level 1
+                    [:print, "ROLE", :role],
+                    [:walk, nil,    :note_citation_record ],
+                  ]
+  end
+end
+

data/lib/gedcom/corporate_record.rb

@@ -0,0 +1,36 @@
+require 'gedcom_base.rb'
+
+#The Corparte_record is part of the HEAD records SOUR record.
+#
+#=HEADER:=
+#  0 HEAD                                         {1:1}
+#    1  SOUR <APPROVED_SYSTEM_ID>                 {1:1}
+#      ...
+#      n CORP <NAME_OF_BUSINESS>                  {0:1}
+#        +1 <<ADDRESS_STRUCTURE>>                 {0:1}
+#        +1 PHON <PHONE_NUMBER>                   {0:3} (defined in the Address structure)
+#
+#==NAME_OF_BUSINESS:=                             {Size=1:90}
+#  Name of the business, corporation, or person that produced or commissioned the product.
+#
+#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 Corporate_record < GEDCOMBase
+  attr_accessor :company_name, :phonenumber, :address_record
+  attr_accessor :note_citation_record
+
+  ClassTracker <<  :Corporate_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 = [ [:print, "CORP", :company_name] ]
+    @sub_level =  [  #level + 1
+                    [:print, "PHON", :phonenumber],
+                    [:walk,  nil,    :address_record],
+                    [:walk, nil,    :note_citation_record],
+                  ]
+  end
+end

data/lib/gedcom/date_record.rb

@@ -0,0 +1,206 @@
+require 'gedcom_base.rb'
+
+#Dates are stored here. In GEDCOM, they have to have the flexibility to hold
+#multiple data formats, both current and historical. Dates can be strings or
+#can have structure. At the moment, this class just stores them as strings,
+#with an optional TIME information.
+#
+#=DATE:=                                            {Size=4:35}
+#  [<DATE_CALENDAR_ESCAPE> | <NULL>] <DATE_CALENDAR>
+#
+#==DATE_CALENDAR_ESCAPE:=                              {Size=4:15}
+#  @#DHEBREW@ | @#DROMAN@ | @#DFRENCH R@ | @#DGREGORIAN@ | @#DJULIAN@ | @#DUNKNOWN@
+#
+#  The date escape determines the date interpretation by signifying which <DATE_CALENDAR> to use.
+#  The default calendar is the Gregorian calendar.
+#
+#==DATE_CALENDAR:=                                     {Size=4:35}
+#  <DATE_GREG> | <DATE_JULN> | <DATE_HEBR> | <DATE_FREN> | <DATE_FUTURE>
+#
+#  The selection is based on the <DATE_CALENDAR_ESCAPE> that precedes the
+#  <DATE_CALENDAR> value immediately to the left. If <DATE_CALENDAR_ESCAPE> doesn't
+#  appear at this point, then @#DGREGORIAN@ is assumed. No future calendar types will use words
+#  (e.g., month names) from this list: FROM, TO, BEF, AFT, BET, AND, ABT, EST, CAL, or INT.
+#  When only a day and month appears as a DATE value it is considered a date phrase and not a valid
+#  date form.
+#
+#  Date Escape         Syntax Selected
+#  -----------         -------------
+#  @#DGREGORIAN@       <DATE_GREG>
+#  @#DJULIAN@          <DATE_JULN>
+#  @#DHEBREW@          <DATE_HEBR>
+#  @#DFRENCH R@        <DATE_FREN>
+#  @#DROMAN@           for future definition
+#  @#DUNKNOWN@         calendar not known
+#
+#==DATE_APPROXIMATED:=                               {Size=4:35}
+#  ABT <DATE> | CAL <DATE> | EST <DATE>
+# 
+#  Where:
+#  ABT:: About, meaning the date is not exact.
+#  CAL:: Calculated mathematically, for example, from an event date and age.
+#  EST:: Estimated based on an algorithm using some other event date.
+#
+#==DATE_EXACT:= {Size=10:11}
+#  <DAY> <MONTH> <YEAR_GREG>
+#
+#==DATE_FREN:= {Size=4:35}
+#  <YEAR> | <MONTH_FREN> <YEAR> | <DAY> <MONTH_FREN> <YEAR>
+#===MONTH_FREN:=                                     {Size=4}
+#  VEND | BRUM | FRIM | NIVO | PLUV | VENT | GERM | FLOR | PRAI | MESS | THER | FRUC | COMP
+#  Where:
+#    VEND:: VENDEMIAIRE
+#    BRUM:: BRUMAIRE
+#    FRIM:: FRIMAIRE
+#    NIVO:: NIVOSE
+#    PLUV:: PLUVIOSE
+#    VENT:: VENTOSE
+#    GERM:: GERMINAL
+#    FLOR:: FLOREAL
+#    PRAI:: PRAIRIAL
+#    MESS:: MESSIDOR
+#    THER:; THERMIDOR
+#    FRUC:: FRUCTIDOR
+#    COMP:: JOUR_COMPLEMENTAIRS
+#
+#==DATE_GREG:= {Size=4:35}
+#  <YEAR_GREG> | <MONTH> <YEAR_GREG> | <DAY> <MONTH> <YEAR_GREG>
+#===YEAR_GREG:= {Size=3:7}
+#  [ <NUMBER> | <NUMBER>/<DIGIT><DIGIT> ]
+#
+#  The slash "/" <DIGIT><DIGIT> a year modifier which shows the possible date alternatives for pre-
+#  1752 date brought about by a changing the beginning of the year from MAR to JAN in the English
+#  calendar change of 1752, for example, 15 APR 1699/00. A (B.C.) appended to the <YEAR> indicates
+#  a date before the birth of Christ.
+#
+#
+#==DATE_HEBR:= {Size=4:35}
+#  <YEAR> | <MONTH_HEBR> <YEAR> | <DAY> <MONTH_HEBR> <YEAR>
+#===MONTH_HEBR:=                                     {Size=3}
+#  TSH | CSH | KSL | TVT | SHV | ADR | ADS | NSN | IYR | SVN | TMZ | AAV | ELL
+#  Where:
+#    TSH:: Tishri
+#    CSH:: Cheshvan
+#    KSL:: Kislev
+#    TVT:: Tevet
+#    SHV:: Shevat
+#    ADR:: Adar
+#    ADS:: Adar Sheni
+#    NSN:: Nisan
+#    IYR:: Iyar
+#    SVN:: Sivan
+#    TMZ:: Tammuz
+#    AAV:: Av
+#    ELL:: Elul
+#
+#==DATE_JULN:=                                         {Size=4:35}
+#  <YEAR> | <MONTH> <YEAR> | <DAY> <MONTH> <YEAR>
+#===MONTH:=                                          {Size=3}
+#  JAN | FEB | MAR | APR | MAY | JUN | JUL | AUG | SEP | OCT | NOV | DEC
+#  Where:
+#    JAN:: January
+#    FEB:: February
+#    MAR:: March
+#    APR:: April
+#    MAY:: May
+#    JUN:: June
+#    JUL:: July
+#    AUG:: August
+#    SEP:: September
+#    OCT:: October
+#    NOV:: November
+#    DEC:: December
+#
+#==DATE_PERIOD:=                                         {Size=7:35}
+#  FROM <DATE> | TO <DATE> | FROM <DATE> TO <DATE>
+# 
+#  Where:
+#  FROM:: Indicates the beginning of a happening or state.
+#  TO::   Indicates the ending of a happening or state.
+#
+#  Examples:
+#  FROM 1904 to 1915
+#    The state of some attribute existed from 1904 to 1915 inclusive.
+#  FROM 1904
+#    The state of the attribute began in 1904 but the end date is unknown.
+#  TO 1915
+#    The state ended in 1915 but the begin date is unknown.
+# 
+#==DATE_PHRASE:=                                         {Size=1:35}
+#  (<TEXT>)
+#
+#  Any statement offered as a date when the year is not recognizable to a date parser, but which gives
+#  information about when an event occurred. The date phrase is enclosed in matching parentheses.
+# 
+#==DATE_RANGE:=                                          {Size=8:35}
+#  BEF <DATE> | AFT <DATE> | BET <DATE> AND <DATE>
+#  
+#  Where:
+#  AFT:: Event happened after the given date.
+#  BEF:: Event happened before the given date.
+#  BET:: Event happened some time between date 1 AND date 2. For example, bet 1904 and 1915
+#        indicates that the event state (perhaps a single day) existed somewhere between 1904 and
+#        1915 inclusive.
+#
+#  The date range differs from the date period in that the date range is an estimate that an event happened
+#  on a single date somewhere in the date range specified.
+#
+#  The following are equivalent and interchangeable:
+#  Short form       Long Form
+#  ---------—       ---------—-
+#  1852             BET 1 JAN 1852 AND 31 DEC 1852
+#  1852             BET 1 JAN 1852 AND DEC 1852
+#  1852             BET JAN 1852 AND 31 DEC 1852
+#  1852             BET JAN 1852 AND DEC 1852
+#  JAN 1920         BET 1 JAN 1920 AND 31 JAN 1920
+#
+#==DATE_VALUE:=                                       {Size=1:35}
+#  <DATE> | <DATE_PERIOD> | <DATE_RANGE> | <DATE_APPROXIMATED> | INT <DATE> (<DATE_PHRASE>) | (<DATE_PHRASE>)
+# 
+#  The DATE_VALUE represents the date of an activity, attribute, or event where:
+#  INT:: Interpreted from knowledge about the associated date phrase included in parentheses.
+#
+#  An acceptable alternative to the date phrase choice is to use one of the other choices such as
+#  <DATE_APPROXIMATED> choice as the DATE line value and then include the
+#  <DATE_PHRASE> as a NOTE value subordinate to the DATE line.
+#
+#  The date value can take on the date form of just a date, an approximated date, between a date and
+#  another date, and from one date to another date. The preferred form of showing date imprecision, is
+#  to show, for example, MAY 1890 rather than ABT 12 MAY 1890. This is because limits have not
+#  been assigned to the precision of the prefixes such as ABT or EST.
+#
+#==DAY:=                                                 {Size=1:2}
+#  dd
+#
+#  Day of the month, where dd is a numeric digit whose value is within the valid range of the days for the
+#  associated calendar month.
+#
+#=TIME_VALUE:= {Size=1:12}
+#  [ hh:mm:ss.fs ]
+#
+#  The time of a specific event, usually a computer-timed event, where:
+#    hh:: hours on a 24-hour clock
+#    mm:: minutes
+#    ss:: seconds (optional)
+#    fs:: decimal fraction of a second (optional)
+#
+#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 Date_record < GEDCOMBase
+  attr_accessor :date_value, :time_value, :source_citation_record, :note_citation_record
+
+  ClassTracker <<  :Date_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 = [ [ :date, "DATE", :date_value ] ]
+    @sub_level =  [ #level + 1
+                    [ :time, "TIME", :time_value],
+                    [ :walk, nil, :source_citation_record],
+                    [ :walk,  nil, :note_citation_record]
+                  ]
+  end
+end