merge s/datatype/data type/g change and enumset change

FamilySearch · Aug 30, 2022 · c17fde2 · c17fde2
1 parent ebcbdd3
commit c17fde2
Show file tree

Hide file tree

Showing 10 changed files with 70 additions and 47 deletions.
diff --git a/build/uri-def.py b/build/uri-def.py
@@ -28,16 +28,16 @@ def get_prefixes(txt):
             pfx[abbr] = lng
     return pfx
 
-def find_datatypes(txt, g7):
+def find_data_types(txt, g7):
     """Returns datatype:uri and adds URI suffixes to g7"""
     dturi = {}
-    for section in re.finditer(r'^#+ *([^\n]*)\n+((?:[^\n]|\n+[^\n#])*[^\n]*URI for[^\n]*datatypes? is(?:[^\n]|\n+[^\n#])*)', txt, re.M):
-        for dt, uri in re.findall(r'URI[^\n]*`([^\n`]*)` datatype[^\n]*`([^`\n:]*:[^\n`]*)`', section.group(0)):
+    for section in re.finditer(r'^#+ *([^\n]*)\n+((?:[^\n]|\n+[^\n#])*[^\n]*URI for[^\n]*data types? is(?:[^\n]|\n+[^\n#])*)', txt, re.M):
+        for dt, uri in re.findall(r'URI[^\n]*`([^\n`]*)` data type[^\n]*`([^`\n:]*:[^\n`]*)`', section.group(0)):
             dturi[dt] = uri
             if uri.startswith('g7:'):
                 if '#' in uri: uri = uri[:uri.find('#')]
                 if uri[3:] not in g7:
-                    g7[uri[3:]] = ('datatype', [section.group(2).strip()])
+                    g7[uri[3:]] = ('data type', [section.group(2).strip()])
     return dturi
 
 def find_cat_tables(txt, g7, tagsets):
@@ -312,7 +312,7 @@ def expand_prefix(txt, prefixes):
     txt = get_text(specs)
 
     prefixes = get_prefixes(txt)
-    dtypes = find_datatypes(txt, g7)
+    dtypes = find_data_types(txt, g7)
     rules = parse_rules(txt)
     ssp = parse_gedstruct(txt, rules, dtypes)
     tagsets = find_descriptions(txt, g7, ssp)

diff --git a/extracted-files/grammar.gedstruct b/extracted-files/grammar.gedstruct
@@ -307,11 +307,11 @@ n MARL [Y|<NULL>]                          {1:1}  g7:MARL
   +1 TYPE <Text>                           {0:1}  g7:TYPE
   +1 <<FAMILY_EVENT_DETAIL>>               {0:1}
 |
-n MARS [Y|<NULL>]                          {1:1}  g7:MARS
+n MARR [Y|<NULL>]                          {1:1}  g7:MARR
   +1 TYPE <Text>                           {0:1}  g7:TYPE
   +1 <<FAMILY_EVENT_DETAIL>>               {0:1}
 |
-n MARR [Y|<NULL>]                          {1:1}  g7:MARR
+n MARS [Y|<NULL>]                          {1:1}  g7:MARS
   +1 TYPE <Text>                           {0:1}  g7:TYPE
   +1 <<FAMILY_EVENT_DETAIL>>               {0:1}
 |
@@ -401,6 +401,13 @@ n AGE <Age>                                {0:1}  g7:AGE
 
 INDIVIDUAL_EVENT_STRUCTURE :=
 [
+n ADOP [Y|<NULL>]                          {1:1}  g7:ADOP
+  +1 TYPE <Text>                           {0:1}  g7:TYPE
+  +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
+  +1 FAMC @<XREF:FAM>@                     {0:1}  g7:ADOP-FAMC
+     +2 ADOP <Enum>                        {0:1}  g7:FAMC-ADOP
+        +3 PHRASE <Text>                   {0:1}  g7:PHRASE
+|
 n BAPM [Y|<NULL>]                          {1:1}  g7:BAPM
   +1 TYPE <Text>                           {0:1}  g7:TYPE
   +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
@@ -413,6 +420,11 @@ n BASM [Y|<NULL>]                          {1:1}  g7:BASM
   +1 TYPE <Text>                           {0:1}  g7:TYPE
   +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
 |
+n BIRT [Y|<NULL>]                          {1:1}  g7:BIRT
+  +1 TYPE <Text>                           {0:1}  g7:TYPE
+  +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
+  +1 FAMC @<XREF:FAM>@                     {0:1}  g7:FAMC
+|
 n BLES [Y|<NULL>]                          {1:1}  g7:BLES
   +1 TYPE <Text>                           {0:1}  g7:TYPE
   +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
@@ -425,6 +437,11 @@ n CENS [Y|<NULL>]                          {1:1}  g7:INDI-CENS
   +1 TYPE <Text>                           {0:1}  g7:TYPE
   +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
 |
+n CHR [Y|<NULL>]                           {1:1}  g7:CHR
+  +1 TYPE <Text>                           {0:1}  g7:TYPE
+  +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
+  +1 FAMC @<XREF:FAM>@                     {0:1}  g7:FAMC
+|
 n CHRA [Y|<NULL>]                          {1:1}  g7:CHRA
   +1 TYPE <Text>                           {0:1}  g7:TYPE
   +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
@@ -477,23 +494,6 @@ n WILL [Y|<NULL>]                          {1:1}  g7:WILL
   +1 TYPE <Text>                           {0:1}  g7:TYPE
   +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
 |
-n ADOP [Y|<NULL>]                          {1:1}  g7:ADOP
-  +1 TYPE <Text>                           {0:1}  g7:TYPE
-  +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
-  +1 FAMC @<XREF:FAM>@                     {0:1}  g7:ADOP-FAMC
-     +2 ADOP <Enum>                        {0:1}  g7:FAMC-ADOP
-        +3 PHRASE <Text>                   {0:1}  g7:PHRASE
-|
-n BIRT [Y|<NULL>]                          {1:1}  g7:BIRT
-  +1 TYPE <Text>                           {0:1}  g7:TYPE
-  +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
-  +1 FAMC @<XREF:FAM>@                     {0:1}  g7:FAMC
-|
-n CHR [Y|<NULL>]                           {1:1}  g7:CHR
-  +1 TYPE <Text>                           {0:1}  g7:TYPE
-  +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}
-  +1 FAMC @<XREF:FAM>@                     {0:1}  g7:FAMC
-|
 n EVEN <Text>                              {1:1}  g7:INDI-EVEN
   +1 TYPE <Text>                           {1:1}  g7:TYPE
   +1 <<INDIVIDUAL_EVENT_DETAIL>>           {0:1}

diff --git a/extracted-files/tags/PHRASE b/extracted-files/tags/PHRASE
@@ -12,9 +12,9 @@ descriptions:
   - Phrase
   - |
     Textual information that cannot be expressed in the superstructure due to
-    the limitations of its datatype. A PHRASE may restate information contained
-    in the superstructure, but doing so is not recommended unless it is needed
-    for clarity.
+    the limitations of its data type. A PHRASE may restate information
+    contained in the superstructure, but doing so is not recommended unless it
+    is needed for clarity.
 
     A date interpreted from the phrase “The Feast of St John” might be
 

diff --git a/extracted-files/tags/type-Age b/extracted-files/tags/type-Age
@@ -2,7 +2,7 @@
 ---
 lang: en-US
 
-type: datatype
+type: data type
 
 uri: https://gedcom.io/terms/v7/type-Age
 
@@ -53,5 +53,5 @@ descriptions:
     Versions 5.5 and 5.5.1 allowed a few specific phrases inside Age payloads.
     Age phrases were moved to the PHRASE substructure in 7.0.
 
-    The URI for the Age datatype is https://gedcom.io/terms/v7/type-Age.
+    The URI for the Age data type is https://gedcom.io/terms/v7/type-Age.
 ...
diff --git a/extracted-files/tags/type-Date b/extracted-files/tags/type-Date
@@ -2,7 +2,7 @@
 ---
 lang: en-US
 
-type: datatype
+type: data type
 
 uri: https://gedcom.io/terms/v7/type-Date
 
@@ -12,7 +12,7 @@ descriptions:
     approximate dates, date periods, and dates expressed in different
     calendars.
 
-    Technically, there are 3 distinct date datatypes:
+    Technically, there are 3 distinct date data types:
 
     -   DateValue is a generic type that can express many kinds of dates.
     -   DateExact is used for timestamps and other fully-known dates.
@@ -103,11 +103,12 @@ descriptions:
         2 DATE
         3 PHRASE 5 January (year unknown)
 
-    The URI for the DateValue datatype is https://gedcom.io/terms/v7/type-Date.
+    The URI for the DateValue data type is
+    https://gedcom.io/terms/v7/type-Date.
 
-    The URI for the DateExact datatype is
+    The URI for the DateExact data type is
     https://gedcom.io/terms/v7/type-Date#exact.
 
-    The URI for the DatePeriod datatype is
+    The URI for the DatePeriod data type is
     https://gedcom.io/terms/v7/type-Date#period.
 ...
diff --git a/extracted-files/tags/type-Enum b/extracted-files/tags/type-Enum
@@ -2,7 +2,7 @@
 ---
 lang: en-US
 
-type: datatype
+type: data type
 
 uri: https://gedcom.io/terms/v7/type-Enum
 
@@ -22,5 +22,27 @@ descriptions:
     Each enumeration value has a distinct meaning as identified by its
     corresponding URI.
 
-    The URI for the Enum datatype is https://gedcom.io/terms/v7/type-Enum.
+    The URI of a given tag in an enumeration payload is determined by the tag
+    itself and by the structure type of the structure it is in the payload of.
+
+    The tag HUSB is used in this document to represent two enumeration values.
+    Which one is meant can be identified by the structure type it appears in as
+    follows:
+
+      ----------------------------------------------------------------------------------
+      Containing structure type              Enumeration value identified by tag HUSB
+      -------------------------------------- -------------------------------------------
+      https://gedcom.io/terms/v7/FAMC-ADOP   https://gedcom.io/terms/v7/enum-ADOP-HUSB
+
+      https://gedcom.io/terms/v7/ROLE        https://gedcom.io/terms/v7/enum-HUSB
+      ----------------------------------------------------------------------------------
+
+    An extension could also place either of these enumeration values in an
+    extension structure type; the extension authors should document which one
+    they permit.
+
+    The HUSB tag is also used to identify two different structure types,
+    https://gedcom.io/terms/v7/FAM-HUSB and https://gedcom.io/terms/v7/HUSB.
+
+    The URI for the Enum data type is https://gedcom.io/terms/v7/type-Enum.
 ...
diff --git a/extracted-files/tags/type-List b/extracted-files/tags/type-List
@@ -2,14 +2,14 @@
 ---
 lang: en-US
 
-type: datatype
+type: data type
 
 uri: https://gedcom.io/terms/v7/type-List
 
 descriptions:
   - |
-    A list is a meta-syntax representing a sequence of values with another
-    datatype. Two list datatypes are used in this document: List:Text and
+    A list is a meta-syntax representing a sequence of values with another data
+    type. Two list data types are used in this document: List:Text and
     List:Enum. Lists are serialized in a comma-separated form, delimited by a
     comma (U+002C ,) and any number of spaces (U+0020) between each item. It is
     recommended that a comma-space pair (U+002C U+0020) be used as the
@@ -33,9 +33,9 @@ descriptions:
     There is no escaping mechanism to allow lists of entries that begin or end
     with spaces or that contain comma characters.
 
-    The URI for the List:Text datatype is
+    The URI for the List:Text data type is
     https://gedcom.io/terms/v7/type-List#Text.
 
-    The URI for the List:Enum datatype is
+    The URI for the List:Enum data type is
     https://gedcom.io/terms/v7/type-List#Enum.
 ...
diff --git a/extracted-files/tags/type-Name b/extracted-files/tags/type-Name
@@ -2,7 +2,7 @@
 ---
 lang: en-US
 
-type: datatype
+type: data type
 
 uri: https://gedcom.io/terms/v7/type-Name
 
@@ -25,6 +25,6 @@ descriptions:
     specification does not provide any standard way of representing names that
     contain U+002F.
 
-    The URI for the PersonalName datatype is
+    The URI for the PersonalName data type is
     https://gedcom.io/terms/v7/type-Name.
 ...
diff --git a/extracted-files/tags/type-Time b/extracted-files/tags/type-Time
@@ -2,7 +2,7 @@
 ---
 lang: en-US
 
-type: datatype
+type: data type
 
 uri: https://gedcom.io/terms/v7/type-Time
 
@@ -24,5 +24,5 @@ descriptions:
     The above grammar prohibits end-of-day instant 24:00:00 and leap-seconds.
     It allows both 02:50 and 2:50 as the same time.
 
-    The URI for the Time datatype is https://gedcom.io/terms/v7/type-Time.
+    The URI for the Time data type is https://gedcom.io/terms/v7/type-Time.
 ...
diff --git a/specification/gedcom-01-serialization.md b/specification/gedcom-01-serialization.md
@@ -82,7 +82,7 @@ Each **structure type** is identified by a URI and defines several properties of
 - The payload type of the structure's payload, which shall be one of
     - no payload, or
     - a pointer to a record with a specific structure type, or
-    - a [datatype](#datatypes);
+    - a [data type](#datatypes);
         if an [enumeration](#enumeration) or [list of enumerations](#list), also a set of permitted enumeration values.
 - Which structure types may appear as substructures of the structure and with what **cardinality** they may appear.
     Cardinality is specified by two flags:
@@ -306,7 +306,7 @@ The recommended way to go beyond the set of standard structure types in this spe
 
 This specification also provides multiple ways for extension authors to go beyond the specification without submitting a feature request, which are described in the remainder of this section.
 
-Extensions can introduce new structure types, new enumeration values, new calendars with their associated months, and new datatypes.
+Extensions can introduce new structure types, new enumeration values, new calendars with their associated months, and new data types.
 They can also extend existing structures with new permitted substructure types and extend existing enumeration-type payloads with new permitted values.
 Extensions cannot change existing meanings, cardinalities, or calendars.