Merge main into v7.1 (excluding extracted-files)

Author: tychonievich

.github/workflows/generate-files.yml

@@ -27,7 +27,7 @@ jobs:
 
     steps:
       - name: Check out GEDCOM
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
       - name: Get the branch name
         id: extract_branch

.github/workflows/propagate-main-to-v7.1.yml

@@ -24,7 +24,7 @@ jobs:
 
     steps:
       - name: Check out GEDCOM
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
       - name: Set git config
         env:

.github/workflows/validate-yaml.yml

@@ -21,7 +21,7 @@ jobs:
 
     steps:
       - name: Checkout GEDCOM
-        uses: actions/checkout@v5
+        uses: actions/checkout@v6
 
       - name: Validate YAML
         run: yamllint .

LICENSE

@@ -186,7 +186,7 @@
       same "printed page" as the copyright notice for easier
       identification within third-party archives.
 
-   Copyright 1984-2025 Intellectual Reserve, Inc. All rights reserved. A service provided by The Church of Jesus Christ of Latter-day Saints.
+   Copyright 1984-2026 Intellectual Reserve, Inc. All rights reserved. A service provided by The Church of Jesus Christ of Latter-day Saints.
 
    Licensed under the Apache License, Version 2.0 (the "License");
    you may not use this file except in compliance with the License.

NOTICE

@@ -1,7 +1,7 @@
 NOTICE:
 
 This work comprises, is based on, or is derived from the FAMILYSEARCH GEDCOM™
-Specification, © 1984-2025 Intellectual Reserve, Inc. All rights reserved.
+Specification, © 1984-2026 Intellectual Reserve, Inc. All rights reserved.
 
 "FAMILYSEARCH GEDCOM™" and "FAMILYSEARCH®" are trademarks of Intellectual
 Reserve, Inc. and may not be used except as allowed by the Apache 2.0 license

build/hyperlink-code.py

@@ -44,7 +44,6 @@ def anchorify(m):
     return full
 
 doc = re.sub(r'<code>(g7:[^<]*)</code></h', r'<code class="uri">\1</code></h', doc)
-doc = re.sub(r'<code>(g7.1:[^<]*)</code></h', r'<code class="uri">\1</code></h', doc)
 
 chunks = re.split(r'(<pre[^>]*ged(?:struct|com)[^>]*>.*?</pre>)', doc, flags=re.DOTALL)
 

build/hyperlink.py

@@ -20,10 +20,6 @@ def slugify(bit):
         si = bit.rfind('`g7:')+4
         ei = bit.find('`', si)
         slug = bit[si:ei].replace('#','-')
-    elif '`g7.1:' in bit:
-        si = bit.rfind('`g7.1:')+6
-        ei = bit.find('`', si)
-        slug = bit[si:ei].replace('#','-')
     elif '`' in bit:
         bit = re.search('`[A-Z0-9_`.]+`', bit)
         slug = bit.group(0).replace('`','').replace('.','-')
@@ -91,7 +87,7 @@ def abnf(m):
             slug = table_tags[m.group(1)]
             return linkify(m.group(0), slug)
         return m.group(0)
-    uried = re.sub(r'(?<![\[.`])`g7(?:\.1)?:[-A-Z0-9a-z`._#]+`', repl, line)
+    uried = re.sub(r'(?<![\[.`])`g7:[-A-Z0-9a-z`._#]+`', repl, line)
     if istable: return uried
     tagged = re.sub(r'(?<![\[.`])`[A-Z0-9`._#]+`', repl, uried)
     abnfed = re.sub(r'(?<![\[.`])`([A-Za-z0-9]+)`', abnf, tagged)

build/uri-def.py

@@ -34,11 +34,9 @@ def find_data_types(txt, g7):
     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:') or uri.startswith('g7.1:'):
-                slug = uri[uri.find(':')+1:]
-                if '#' in uri: uri = uri[:uri.find('#')]
-                if slug not in g7:
-                    g7[slug] = ('data type', [section.group(2).strip()])
+            if uri.startswith('g7:'):
+                if uri[3:] not in g7:
+                    g7[uri[3:]] = ('data type', [section.group(2).strip()])
     return dturi
 
 def find_cat_tables(txt, g7, tagsets):
@@ -110,19 +108,18 @@ def find_cat_tables(txt, g7, tagsets):
                 raise Exception("unexpected enumeration URI prefix "+repr(pfx))
             if pfx not in cats:
                 cats[pfx] = meaning
-                if pfx.startswith('g7:') or pfx.startswith('g7.1:'):
-                    slug = pfx[pfx.find(':')+1:]
-                    if slug in g7:
-                        raise Exception(pfx+' defined as an enumeration and a '+g7[slug][0])
+                if pfx.startswith('g7:'):
+                    if pfx[3:] in g7:
+                        raise Exception(pfx+' defined as an enumeration and a '+g7[pfx[3:]][0])
                     if label:
-                        g7[slug] = (yamltype, meaning, None, label)
+                        g7[pfx[3:]] = (yamltype, meaning, None, label)
                     else:
-                        g7[slug] = (yamltype, meaning)
+                        g7[pfx[3:]] = (yamltype, meaning)
     return enums, calendars
 
 def find_calendars(txt, g7):
     """Looks for sections defining a `g7:cal-` URI"""
-    for bit in re.finditer(r'#+ `[^`]*`[^\n]*\n+((?:\n+(?!#)|[^\n])*is `g7(?:\.1)?:(cal-[^`]*)`(?:\n+(?!#)|[^\n#])*)', txt):
+    for bit in re.finditer(r'#+ `[^`]*`[^\n]*\n+((?:\n+(?!#)|[^\n])*is `g7:(cal-[^`]*)`(?:\n+(?!#)|[^\n#])*)', txt):
         m = re.search('The epoch markers? ([`_A-Z0-9, and]+) (is|are) permitted', bit.group(1))
         marker = [] if not m else re.findall(r'[A-Z0-9_]+', m[1])
         m = re.match(r'^The ([A-Z][A-Za-z]* )+calendar', bit.group(1))
@@ -226,27 +223,24 @@ def find_descriptions(txt, g7, ssp):
     for name,uri,desc in re.findall(r'#+ `[^`]*`[^\n]*\(([^)]*)\)[^\n]*`([^:`\n]*:[^`\n]*)`[^\n]*\n+((?:\n+(?!#)|[^\n])*)', txt):
         if uri not in ssp:
             raise Exception('Found section for '+uri+' but no gedstruct')
-        if uri.startswith('g7:') or uri.startswith('g7.1:'):
-            slug = uri[uri.find(':')+1:]
-            g7.setdefault(slug,('structure',[],ssp[uri],name.strip()))[1].extend((
+        if uri.startswith('g7:'):
+            g7.setdefault(uri[3:],('structure',[],ssp[uri],name.strip()))[1].extend((
                 name.strip(),
                 desc.strip()
             ))
             for other in re.findall(r'[Aa] type of `(\S*)`', desc):
                 m = re.search('^#+ +`'+other+r'`[^\n`]*\n((?:[^\n]+|\n+(?!#))*)', txt, re.M)
                 if m:
-                    g7[uri[uri.find(':')+1:]][1].append(m.group(1).strip())
+                    g7[uri[3:]][1].append(m.group(1).strip())
 
     # error check that gedstruct and sections align
     for uri in ssp:
         if uri.startswith('g7:') and uri[3:] not in g7:
             raise Exception('Found gedstruct for '+uri+' but no section')
-        if uri.startswith('g7.1:') and uri[5:] not in g7:
-            raise Exception('Found gedstruct for '+uri+' but no section')
 
     # gedstruct sections
     for uri, desc in re.findall(r'#+ *`[^`]*` *:=[^\n]*\n+`+[^\n]*\n+n [^\n]*\} *(\S+:\S+) *(?:\n [^\n]*)*\n`+[^\n]*\n+((?:[^\n]|\n(?!#))*)', txt):
-        g7[uri[uri.find(':')+1:]][1].append(desc.strip())
+        g7[uri[3:]][1].append(desc.strip())
 
     tagsets = {}
     # tag tables
@@ -257,11 +251,7 @@ def find_descriptions(txt, g7, ssp):
         if header.startswith('Indi'): pfx = 'INDI-'
         for tag, name, desc in re.findall(r'`([A-Z_0-9]+)` *\| *([^|\n]*?) *\| *([^|\n]*[^ |\n]) *', table.group(2)):
             if '<br' in name:
-                if '`g7:' in name:
-                    tag = name[name.find('`g7:')+4:name.rfind('`')]
-                elif '`g7.1' in name:
-                    tag = name[name.find('`g7.1')+6:name.rfind('`')]
-                else: assert False, "name without URI: "+repr(name)
+                tag = name[name.find('`g7:')+4:name.rfind('`')]
                 name = name[:name.find('<br')]
             if tag not in g7: tag = pfx+tag
             if tag not in g7:
@@ -282,7 +272,7 @@ def find_enum_by_link(txt, enums, tagsets):
             # 'g7:FAM-FACT',
         # ))         ## do not do for enumset-EVEN 
     enum_prefix = {k[k.find('enum-')+5:] for e in enums.values() for k in e }
-    for sect in re.finditer(r'# *`(g7(?:\.1)?:enumset-[^`]*)`[\s\S]*?\n#', txt):
+    for sect in re.finditer(r'# *`(g7:enumset-[^`]*)`[\s\S]*?\n#', txt):
         if '[Events]' in sect.group(0):
             key = sect.group(1).replace('`','').replace('.','-')
             for k in tagsets:
@@ -291,7 +281,7 @@ def find_enum_by_link(txt, enums, tagsets):
                     for tag in tagsets[k]:
                         if tag.startswith('INDI-') and tag[5:] in enum_prefix: tag = 'enum-'+tag[5:]
                         if tag.startswith('FAM-') and tag[4:] in enum_prefix: tag = 'enum-'+tag[4:]
-                        tag = addpfx(tag)
+                        tag = 'g7:'+tag
                         if tag in enums[key]: continue
                         enums[key].append(tag)
         if '[Attributes]' in sect.group(0):
@@ -302,22 +292,22 @@ def find_enum_by_link(txt, enums, tagsets):
                     for tag in tagsets[k]:
                         if tag.startswith('INDI-') and tag[5:] in enum_prefix: tag = 'enum-'+tag[5:]
                         if tag.startswith('FAM-') and tag[4:] in enum_prefix: tag = 'enum-'+tag[4:]
-                        tag = addpfx(tag)
+                        tag = 'g7:'+tag
                         if tag in enums[key]: continue
                         enums[key].append(tag)
                     # enums.setdefault(key, []).extend(_ for _ in ['g7:'+_2.replace('INDI-','enum-').replace('FAM-','enum-') for _2 in tagsets[k]] if _ not in enums.get(key,[]))
 
 def find_enumsets(txt):
     res = {}
-    for sect in re.finditer(r'# *[^\n]*?`(g7(?:\.1)?:[^`]*)`([\s\S]*?)\n#', txt):
-        if re.search(f'from set `g7(?:\.1)?:enumset-', sect.group(2)):
+    for sect in re.finditer(r'# *[^\n]*?`(g7:[^`]*)`([\s\S]*?)\n#', txt):
+        if 'from set `g7:enumset-' in sect.group(2):
             key = sect.group(1)
-            val = re.search(r'from set `(g7(?:\.1)?:enumset-[^`]*)`', sect.group(2)).group(1)
+            val = re.search(r'from set `(g7:enumset-[^`]*)`', sect.group(2)).group(1)
             res[key] = val
     return res
 
 def tidy_markdown(md, indent, width=79):
-    """
+    r"""
     The markdown files in the specification directory use the following Markdown dialect:
     
     Part of GFM:
@@ -351,7 +341,7 @@ def tidy_markdown(md, indent, width=79):
     import mdformat
     out = mdformat.text(md, extensions={"gfm"}, options={"number":True, "wrap":width})
 
-    return out.rstrip().replace('\n','\n'+' '*indent).replace('\[','[').replace('\]',']')
+    return out.rstrip().replace('\n','\n'+' '*indent).replace(r'\[','[').replace(r'\]',']')
 
 def yaml_str_helper(pfx, md, width=79):
     txt = tidy_markdown(md, len(pfx), width)
@@ -362,16 +352,10 @@ def yaml_str_helper(pfx, md, width=79):
     return pfx + txt
 
 def expand_prefix(txt, prefixes):
-    global prerelease
     for key in sorted(prefixes.keys(), key=lambda x:-len(x)):
         k = key+':'
         if txt.startswith(k):
-            uri = prefixes[key] + txt[len(k):]
-            if 'https://gedcom.io/terms/v7.1/' in uri:
-                prerelease = True
-            return uri
-    if 'https://gedcom.io/terms/v7.1/' in txt:
-        prerelease = True
+            return prefixes[key] + txt[len(k):]
     return txt
 
 if __name__ == '__main__':
@@ -381,24 +365,14 @@ def expand_prefix(txt, prefixes):
     txt = get_text(specs)
 
     prefixes = get_prefixes(txt)
-    prefix_of = {} # generally {tag: 'g7'} or {"record-REPO":"g7.1"} but sometimes {"month-":"g7"} for a set of values
-    for [pfx,slug] in re.findall('('+'|'.join(prefixes)+r'):([^\s`<>]+)', txt):
-        assert prefix_of.get(slug,pfx) == pfx, f"Multiple prefixes for {slug}: {prefix_of[slug]} and {pfx}"
-        prefix_of[slug] = pfx
-    def addpfx(tag):
-        if tag in prefix_of: return prefix_of[tag]+':'+tag
-        if '-' in tag:
-            lead = tag[:tag.find('-')+1]
-            if lead in prefix_of: return prefix_of[lead]+':'+tag
-        assert False, 'no prefix for '+tag+' in '+str(prefix_of)
     dtypes = find_data_types(txt, g7)
     rules = parse_rules(txt)
     ssp = parse_gedstruct(txt, rules, dtypes)
     tagsets = find_descriptions(txt, g7, ssp)
     enums, calendars = find_cat_tables(txt, g7, tagsets)
     find_enum_by_link(txt, enums, tagsets)
     for k in enums:
-        g7[k[k.find(':')+1:]] =  ('enumeration set',[]) 
+        g7[k[3:]] =  ('enumeration set',[]) 
     enumsets = find_enumsets(txt)
     find_calendars(txt, g7)
     dtypes_inv = {expand_prefix(v,prefixes):k for k,v in dtypes.items()}
@@ -411,19 +385,17 @@ def addpfx(tag):
 
     for tag in g7:
         print('outputting', tag, '...', end=' ')
-        prerelease = False
         maybe = join(dirname(specs[0]),'terms',tag)
         if exists(maybe):
             copyfile(maybe, join(dest,tag))
             print('by copying', maybe, '...', end=' ')
             continue
-        thispath = join(dest,tag.replace('#','-'))
-        with open(thispath, 'w') as fh:
+        with open(join(dest,tag.replace('#','-')), 'w') as fh:
             fh.write('%YAML 1.2\n---\n')
             print('lang: en-US', file=fh)
             print('\ntype:',g7[tag][0], file=fh)
 
-            uri = expand_prefix(addpfx(tag),prefixes)
+            uri = expand_prefix('g7:'+tag,prefixes)
             print('\nuri:', uri, file=fh)
 
             if g7[tag][0] in ('structure', 'enumeration', 'calendar', 'month'):
@@ -452,7 +424,7 @@ def addpfx(tag):
                     print('\npayload:', payload, file=fh)
                 payload_lookup.append([uri, payload if payload != 'null' else ''])
                 if d['pay'] and 'Enum' in d['pay']:
-                    setname = expand_prefix(enumsets[addpfx(tag)],prefixes)
+                    setname = expand_prefix(enumsets['g7:'+tag],prefixes)
                     print('\nenumeration set: "'+setname+'"', file=fh)
                     enum_lookup.append([uri,setname])
                     # print('\nenumeration values:', file=fh)
@@ -478,7 +450,7 @@ def addpfx(tag):
                     struct_lookup.append(['',ptag,uri])
             elif g7[tag][0] == 'calendar':
                 print('\nmonths:', file=fh)
-                for k in calendars[addpfx(tag)]:
+                for k in calendars['g7:'+tag]:
                     print('  - "'+expand_prefix(k, prefixes)+'"', file=fh)
                 if len(g7[tag][2]) == 0:
                     print('\nepochs: []', file=fh)
@@ -488,11 +460,11 @@ def addpfx(tag):
                         print('  -', epoch, file=fh)
             elif g7[tag][0] == 'month':
                 print('\ncalendars:', file=fh)
-                for k in calendars[addpfx(tag)]:
+                for k in calendars['g7:'+tag]:
                     print('  - "'+expand_prefix(k, prefixes)+'"', file=fh)
             elif g7[tag][0] == 'enumeration set':
                 print('\nenumeration values:', file=fh)
-                for k in enums[addpfx(tag)]:
+                for k in enums['g7:'+tag]:
                     valname = expand_prefix(k, prefixes)
                     print('  - "'+valname+'"', file=fh)
                     enumset_lookup.append([uri, valname])
@@ -501,20 +473,11 @@ def addpfx(tag):
             # handle use in enumerations (which can include any tag type)
             is_used_by = False
             for tag2 in sorted(enums):
-                if (addpfx(tag)) in enums[tag2]:
+                if ('g7:'+tag) in enums[tag2]:
                     if not is_used_by:
                         print('\nvalue of:', file=fh)
                         is_used_by = True
                     print('  - "'+expand_prefix(tag2,prefixes)+'"', file=fh)
-            
-            if prerelease:
-                print('\nprerelease: true', file=fh)
-            
-            # manually check for v7.1 subsuming v7.0
-            if '/v7.1/' in uri:
-                res = run(['git','show','main:'+thispath], capture_output=True)
-                if not res.returncode:
-                    print('\nsubsumes:', uri.replace('/v7.1/','/v7/'), file=fh)
 
             print('\ncontact: "https://gedcom.io/community/"', file=fh)
             fh.write('...\n')
@@ -542,4 +505,3 @@ def addpfx(tag):
             for row in data:
                 print('\t'.join(row), file=f)
         print('done')
-

changelog.md

@@ -1,3 +1,46 @@
+# Version 7.0.17
+
+- Add URI, Latitude, Longitude, and Tag definition data types.
+    
+    Previously the formats permitted for these were specified in plain text with the corresponding structure types.
+    Those definitions have been moved to the data types section to better match how other data types are defined in the specification.
+
+- Clarify the deprecation of older extensions that use non-underscore tags.
+
+    These violated the standard in both 7.0 and 5.5.1, but exist in the wild and there was unclear text "deprecating" them when they were never supported to begin with. That has been changed to be more clear about when it is an extension-defined substructure and when it violates the specification.
+
+- Clarify how file paths encode non-ASCII characters.
+
+- Clarify rules for pointer-based cycles:
+    
+    - A cycle asserting someone is their own ancestor (such as being both the `CHIL` and `FAMS` of the same person) is unlikely to be correct, but is permitted by GEDCOM.
+    
+    - A self-referential `ALIA` is (`INDI`.`AILA` pointing to the `INDI`) is meaningless and prohibited.
+    
+    - A `SOUR`-`OBJE` cycle (the source of an image is the image itself) is meaningless and prohibited.
+
+- Clarify that extension media types for notes (such as `text/markdown` that several applications are known to employ) do not require extension tags, being covered by the existing standard.
+
+- Clarify the wording of the `ELECTRONIC` enumerated value.
+
+- Clarify the wording of the `AGE` structure generally and `HUSB`.`AGE` and `WIFE`.`AGE` in particular.
+
+- Add example of `PHRASE` used with a non-`OTHER` enumeration value.
+
+- Update UUID defintion from RFC 4122 to RFC 9562
+
+- Remove redundant and confusing references to RFC 3986, which were subsumed by existing references to WHATWG URL.
+
+- Note that `FILE` payloads and GEDZIP file paths follow distinct standards, with the former using percent-escaping but the latter not.
+
+- Note that GEDZIP inherits from zip the ability to have multiple levels of compression, with some suggestions on performance implications of the chosen compression level.
+
+- Note that GEDZIP inherits from zip the ability to encrypt file contents, but not file names or sizes.
+
+- Note how `ALIA` is known to be used by existing applications and users.
+
+- Various typo corrections.
+
 # Version 7.0.16
 
 - Recommend that `ASSO` not be used to replicate other standard structures.