#11, #12: ontologia_regulam; BCP47 style extension

docs/eng-Latn/hxltm.adoc

@@ -52,6 +52,12 @@ TIP: If you perceive too many literal translations,
 
 #TODO: define a suggested language attribute for such revieened translations (2021-11-29T21:49:00Z)#
 
+
+////
+- On the issue with gender on the Core-Person-Vocabulary
+** https://github.com/SEMICeu/Core-Person-Vocabulary/issues/13
+////
+
 // TIP: One common symptom of literal translations is lack of context.
 
 // Not only this, but often means target languages have either to create new terms from bad source terms so generic that are unusable for serious work.
@@ -248,24 +254,47 @@ _TODO: this is a draft. Needs be documented later_
 
 === `+__linguam__+` (implicitum)
 
-==== `+de_linguam`
+==== `+ix_de_linguam`
 The language code of this column is stored as the value of an equivalent column with the name `+est_linguam`.
 
-==== `+de_linguam_fontem`
+==== `+ix_de_linguam_fontem`
 The language code of this column is stored as the value of an equivalent column with the name `+est_linguam_fontem`.
 
-==== `+de_linguam_objectivum`
+==== `+ix_de_linguam_objectivum`
 The language code of this column is stored as the value of an equivalent column with the name `+est_linguam_objectivum`.
 
-==== `+est_linguam`
+==== `+ix_est_linguam`
 The values of each row on this column represent the code referenced on another column with attribute `+de_linguam`.
 
-==== `+est_linguam_fontem`
+==== `+ix_est_linguam_fontem`
 The values of each row on this column represent the code referenced on another column with attribute `+de_linguam_fontem`.
 
-==== `+est_linguam_objectivum`
+==== `+ix_est_linguam_objectivum`
 The values of each row on this column represent the code referenced on another column with attribute `+de_linguam_objectivum`.
 
+=== `+ib_*`
+* BCP47
+* https://tools.ietf.org/rfc/bcp/bcp47
+
+
+=== `+ib_h_*`
+* BCP 47 Extension H - Use on HXLTM
+* https://hxltm.etica.ai/
+
+=== `+ib_t_*`
+* BCP 47 Extension T - Transformed Content
+* https://datatracker.ietf.org/doc/html/rfc6497
+
+
+=== `+ib_u_*`
+* Unicode Extensions for BCP 47
+* https://cldr.unicode.org/index/bcp47-extension
+
+
+=== `+ib_x_*`
+* BCP47 Private Use Subtags
+* https://www.rfc-editor.org/rfc/rfc4646#section-2.2.7
+
 ==== Base tags used when HXLTM on XML-like container
 
 NOTE: this section does not include other formalized specifications

docs/ontologia-regulam.html

@@ -79,14 +79,19 @@
     // var regula2 = '(?<linguam>(i.?_).*(?<etc>(\\+.?))).?'
     // var regula2 = '(?<linguam>(\\+i.?_).*(?<etc>(.?))).?'
     // var regula2 = '(?<linguam>(\\+i.?_).*(?<etc>[^\\+i](.?))).?'
-    var regula2 = '(?<linguam>(\\+i.?_).*(?<etc>[^\\+i.?](.?))).?'
+    // var regula2 = '(?<linguam>(\\+i.?_).*(?<etc>[^\\+i.?](.?))).?'
+    // var regula2 = '(?<linguam>(\\+i.?_.*))?(?<etcetera>[\\+[^i]].*)?'
+    // var regula3 = '(?<etcetera>(\\+[^i\w?_].*))'
+    var regula3 = '(?<linguam>(\\+i.?_.*))?(?<etcetera>(\\+[^i\w?_].*))'
     var subspeciem = [
       '+i_pt+i_por+ig_port1283+is_latn+rem',
+      '+i_pt+i_por+ig_port1283+is_latn+exemplo1+exemplo2+exemplo3',
       '+ix_de_linguam',
       '+ix_est_linguam',
       '+ix_est_linguam_fontem',
     ]
-    var regula_regex2 = new RegExp(regula2, "i")
+    // var regula_regex2 = new RegExp(regula2, "i")
+    var regula_regex2 = new RegExp(regula3, "i")
 
     subspeciem.forEach(element => {
       console.log(regula_regex2.exec(element))

ontologia/cor.hxltm.215.yml

@@ -3008,27 +3008,29 @@ ontologia_regulam:
   exemplum:
     hxl_caput:
       - hxl: '#item+conceptum+codicem'
-        divisionem: item
-        classem: conceptum
-        speciem: +codicem
+        divisionem: '#item'
+        classem: '+conceptum'
+        speciem: '+codicem'
       - hxl: '#meta+linguam+i_pt+i_por+ig_port1283+is_latn'
-        divisionem: meta
-        classem: linguam
+        divisionem: '#meta'
+        classem: '+linguam'
         speciem: +i_pt+i_por+ig_port1283+is_latn
 
   # Trivia: strūctūram, https://en.wiktionary.org/wiki/structura#Latin
   structuram:
     # basim -> divisionem, classem, speciem
     basim:
+      # https://regex101.com/r/XUOncM/5
       javascript: >-
-        \#(?<divisionem>(item|meta)).+?(?<classem>(conceptum|linguam|terminum))(?<speciem>.*)
+        (?<divisionem>(#item|#meta))(?<classem>(\+conceptum|\+linguam|\+terminum))((?<linguam_de>(\+ix_de_[a-z_]*))|(?<linguam_est>(\+ix_est_[a-z_]*))|(?<linguam_i2a>(\+i_\w\w))?(?<linguam_i3a>(\+i_\w\w\w))(?<linguam_ig>(\+ig_\w\w\w\w\d\d\d\d))?((?<linguam_s4a>(\+is_\w{3,4})))(?<linguam_it>(\+it_[a-z0-9_]*))?)?(?<etcetera>(\+.*))?(?<datum_vocabularium>(\+v_[a-z_]*))?
+      #  \#(?<divisionem>(item|meta)).+?(?<classem>(conceptum|linguam|terminum))(?<speciem>.*)
       python: >-
-        \#(?P<divisionem>(item|meta)).+?(?P<classem>(conceptum|linguam|terminum))(?P<speciem>.*)
+        \(?P<divisionem>(#item|#meta)).+?(?P<classem>(conceptum|linguam|terminum))(?P<speciem>.*)
     subspeciem:
       javascript: >-
-        \#(?<divisionem>(item|meta)).+?(?<classem>(conceptum|linguam|terminum))(?<speciem>.*)
+        \(?<divisionem>(#item|#meta)).+?(?<classem>(conceptum|linguam|terminum))(?<speciem>.*)
       python: >-
-        \#(?P<divisionem>(item|meta)).+?(?P<classem>(conceptum|linguam|terminum))(?P<speciem>.*)
+        \(?P<divisionem>(#item|#meta)).+?(?P<classem>(conceptum|linguam|terminum))(?P<speciem>.*)
 
   # named group:
   #  (?P<hxltag>\#[a-zA-Z_]*)(?P<hxlattrs>\+\w*){0,20}