rdf+bcp47+hxl (#41), admin-l (#39), pcodes (#2): HXL_HASHTAGS_AD_WIKI…

…DATA mappings improved
EticaAI · Jun 11, 2022 · abe808e · abe808e
1 parent 9c2922f
commit abe808e
Show file tree

Hide file tree

Showing 6 changed files with 68 additions and 57 deletions.
diff --git a/officina/999999999/0/999999999_54872.py b/officina/999999999/0/999999999_54872.py
@@ -105,7 +105,7 @@
 Temporary tests . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .
 (Debug information in JSON)
     {0} --objectivum-formato=_temp_bcp47_meta_in_json \
-999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv --rdf-bag=2
+999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv --rdf-trivio=2
 
     {0} --objectivum-formato=_temp_bcp47_meta_in_json \
 --rdf-namespaces-archivo=\
@@ -114,15 +114,15 @@
 
 (Data operations)
     {0} --objectivum-formato=_temp_bcp47 \
-999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv --rdf-bag=2
+999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv --rdf-trivio=2
 
     {0} --objectivum-formato=_temp_bcp47 --rdf-namespaces-archivo=\
 999999999/1568346/data/hxlstandard-rdf-namespaces-example.hxl.csv \
-999999999/1568346/data/unesco-thesaurus.bcp47g.tsv --rdf-bag=1
+999999999/1568346/data/unesco-thesaurus.bcp47g.tsv --rdf-trivio=1
 
     {0} --objectivum-formato=_temp_bcp47 --rdf-namespaces-archivo=\
 999999999/1568346/data/hxlstandard-rdf-namespaces-example.hxl.csv \
-999999999/1568346/data/unesco-thesaurus.bcp47g.tsv --rdf-bag=2
+999999999/1568346/data/unesco-thesaurus.bcp47g.tsv --rdf-trivio=2
 
     {0} --objectivum-formato=_temp_bcp47 --rdf-namespaces-archivo=\
 999999999/1568346/data/hxlstandard-rdf-namespaces-example.hxl.csv \
@@ -132,12 +132,12 @@
 (Data operation; example of "SKOS version" without OWL/OBO assertions)
     {0} --objectivum-formato=_temp_bcp47 \
 999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv \
---rdf-sine-spatia-nominalibus=owl,obo,devnull --rdf-bag=2
+--rdf-sine-spatia-nominalibus=owl,obo,devnull --rdf-trivio=2
 
 (Data operation; example of "OWL + OBO" without SKOS linguistic metadata)
     {0} --objectivum-formato=_temp_bcp47 \
 999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv \
---rdf-sine-spatia-nominalibus=skos,wdata,devnull --rdf-bag=2
+--rdf-sine-spatia-nominalibus=skos,wdata,devnull --rdf-trivio=2
 
 (Data operations, header conversion RDF+HXL -> RDF+BCP47)
     varbcp47=$(head -n1 \
@@ -282,7 +282,7 @@ def make_args(self, hxl_output=True):
         )
 
         parser.add_argument(
-            '--rdf-bag',
+            '--rdf-trivio',
             help='(Advanced) RDF bag; extract triples from tabular data from '
             'other groups than 1',
             dest='rdf_bag',

diff --git a/officina/999999999/0/999999999_826165.py b/officina/999999999/0/999999999_826165.py
@@ -82,7 +82,7 @@
 
     {0} --objectivum-formato=_temp_bcp47 --rdf-namespaces-archivo=\
 999999999/1568346/data/hxlstandard-rdf-namespaces-example.hxl.csv \
---rdf-bag=2 \
+--rdf-trivio=2 \
 999999999/1568346/data/unesco-thesaurus.bcp47g.tsv
 
     {0} --objectivum-formato=_temp_bcp47 --rdf-namespaces-archivo=\
@@ -209,7 +209,7 @@ def make_args(self, hxl_output=True):
         # # ex
         # # fontī, m, s, dativus, https://en.wiktionary.org/wiki/fons#Latin
         parser.add_argument(
-            '--rdf-bag',
+            '--rdf-trivio',
             help='(Advanced) RDF bag; extract triples from tabular data from '
             'other groups than 1',
             dest='rdf_bag',

diff --git a/officina/999999999/0/L999999999_0.py b/officina/999999999/0/L999999999_0.py
@@ -232,36 +232,45 @@
 # wdtaxonomy Q6256 -P P131
 HXL_HASHTAGS_AD_WIKIDATA = {
     '#country': {
-        'wdata': 'Q6256'  # country
+        'hxlattrs': HXL_ATTRIBUTES_AD_WIKIDATA['geo'],
+        'wdata': 'Q6256',  # country
+        'rdftrivio': '5000'
     },
     # Not a valid HXL hashtag, but using anyway as alias to country
     '#adm0': {
         'hxlattrs': HXL_ATTRIBUTES_AD_WIKIDATA['geo'],
-        'wdata': 'Q6256'  # country
+        'wdata': 'Q6256',  # country
+        'rdftrivio': '5000'
     },
     '#adm1': {
         'hxlattrs': HXL_ATTRIBUTES_AD_WIKIDATA['geo'],
-        'wdata': 'Q10864048'  # first-level administrative country subdivisio
+        'wdata': 'Q10864048',  # first-level administrative country subdivisio
+        'rdftrivio': '5001'
     },
     '#adm2': {
         'hxlattrs': HXL_ATTRIBUTES_AD_WIKIDATA['geo'],
-        'wdata': 'Q13220204'  # second-level administrative country subdivision
+        'wdata': 'Q13220204',  # second-level administrative country subdivision
+        'rdftrivio': '5002'
     },
     '#adm3': {
         'hxlattrs': HXL_ATTRIBUTES_AD_WIKIDATA['geo'],
-        'wdata': 'Q13221722'  # third-level administrative country subdivision
+        'wdata': 'Q13221722',  # third-level administrative country subdivision
+        'rdftrivio': '5003'
     },
     '#adm4': {
         'hxlattrs': HXL_ATTRIBUTES_AD_WIKIDATA['geo'],
-        'wdata': 'Q14757767'  # fourth-level administrative country subdivision
+        'wdata': 'Q14757767',  # fourth-level administrative country subdivision
+        'rdftrivio': '5004'
     },
     '#adm5': {
         'hxlattrs': HXL_ATTRIBUTES_AD_WIKIDATA['geo'],
-        'wdata': 'Q15640612'  # fifth-level administrative country subdivision
+        'wdata': 'Q15640612',  # fifth-level administrative country subdivision
+        'rdftrivio': '5005'
     },
     '#adm6': {
         'hxlattrs': HXL_ATTRIBUTES_AD_WIKIDATA['geo'],
-        'wdata': 'Q22927291'  # sixth-level administrative country subdivision
+        'wdata': 'Q22927291',  # sixth-level administrative country subdivision
+        'rdftrivio': '5006'
     },
 }
 
@@ -2196,7 +2205,8 @@ def _helper_aux_triple(
             triple = [triple_subject, 'a', predicate]
             result['rdf_triplis'].append(triple)
 
-        for referenced_by in bag_meta['indices_columnis']:
+        # for referenced_by in bag_meta['indices_columnis']:
+        for referenced_by in bag_meta['indices_cum_aliis']:
             if referenced_by == index_id:
                 continue
 

diff --git a/officina/999999999/1568346/README.md b/officina/999999999/1568346/README.md
@@ -64,31 +64,31 @@ for datasets that already are highly reusable, as mere suggestion:
 ### Suggested "subject group" for country, and administrative boundaries 1 to 6+
 
 - Country:
-  - Number: `500`
-  - BCP47 RDF extension part (self): `r-sU2200-s500-snop`
-  - HXL RDF attribute (self): `+rdf_s_u2200_s500`
+  - Number: `5000`
+  - BCP47 RDF extension part (self): `r-sU2200-s5000-snop`
+  - HXL RDF attribute (self): `+rdf_s_u2200_s5000`
 - #adm1:
-  - Number: `501`
-  - BCP47 RDF extension part (self): `r-sU2200-s501-snop`
-  - HXL RDF attribute (self): `+rdf_s_u2200_s501`
+  - Number: `5001`
+  - BCP47 RDF extension part (self): `r-sU2200-s5001-snop`
+  - HXL RDF attribute (self): `+rdf_s_u2200_s5001`
 - #adm2:
-  - Number: `502`
-  - BCP47 RDF extension part (self): `r-sU2200-s502-snop`
-  - HXL RDF attribute (self): `+rdf_s_u2200_s502`
+  - Number: `5002`
+  - BCP47 RDF extension part (self): `r-sU2200-s5002-snop`
+  - HXL RDF attribute (self): `+rdf_s_u2200_s5002`
 - #adm3:
-  - Number: `503`
-  - BCP47 RDF extension part (self): `r-sU2200-s503-snop`
-  - HXL RDF attribute (self): `+rdf_s_u2200_s503`
+  - Number: `5003`
+  - BCP47 RDF extension part (self): `r-sU2200-s5003-snop`
+  - HXL RDF attribute (self): `+rdf_s_u2200_s5003`
 - #adm4:
-  - Number: `504`
-  - BCP47 RDF extension part (self): `r-sU2200-s504-snop`
-  - HXL RDF attribute (self): `+rdf_s_u2200_s504`
+  - Number: `5004`
+  - BCP47 RDF extension part (self): `r-sU2200-s5004-snop`
+  - HXL RDF attribute (self): `+rdf_s_u2200_s5004`
 - #adm5:
-  - Number: `505`
-  - BCP47 RDF extension part (self): `r-sU2200-s505-snop`
-  - HXL RDF attribute (self): `+rdf_s_u2200_s505`
+  - Number: `5005`
+  - BCP47 RDF extension part (self): `r-sU2200-s5005-snop`
+  - HXL RDF attribute (self): `+rdf_s_u2200_s5005`
 - #adm6:
-  - Number: `506`
+  - Number: `5006`
   - BCP47 RDF extension part (self): `r-sU2200-s506-snop`
   - HXL RDF attribute (self): `+rdf_s_u2200_s506`
 
@@ -98,9 +98,9 @@ for datasets that already are highly reusable, as mere suggestion:
 > dataset, for a dataset that is for example about #adm3, you could:
 >
 > - #adm3:
->   - Number: `503` and `1`
->   - BCP47 RDF extension part (self): `r-sU2200-s1-snop-sU2200-s503-snop`
->   - HXL RDF attribute (self): `+rdf_s_u2200_s1+rdf_s_u2200_s503`
+>   - Number: `5003` and `1`
+>   - BCP47 RDF extension part (self): `r-sU2200-s1-snop-sU2200-s5003-snop`
+>   - HXL RDF attribute (self): `+rdf_s_u2200_s1+rdf_s_u2200_s5003`
 
 
 ## To Dos

diff --git a/officina/999999999/1568346/bcp47-to-hxl-to-rdf.sh b/officina/999999999/1568346/bcp47-to-hxl-to-rdf.sh
@@ -115,15 +115,15 @@ test_unesco_thesaurus() {
 
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47 \
-    --rdf-bag=1 \
+    --rdf-trivio=1 \
     --rdf-namespaces-archivo="${archivum__namespace}" \
     "${archivum__unesco_thesaurus_bcp47}" |
     rapper --quiet --input=turtle --output=turtle /dev/fd/0 \
       >"${archivum__resultata_bag1}"
 
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47 \
-    --rdf-bag=2 \
+    --rdf-trivio=2 \
     --rdf-namespaces-archivo="${archivum__namespace}" \
     "${archivum__unesco_thesaurus_bcp47}" |
     rapper --quiet --input=turtle --output=turtle /dev/fd/0 \
@@ -190,31 +190,31 @@ test_cod_ab() {
 
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47 \
-    --rdf-bag=1 \
+    --rdf-trivio=1 \
     --rdf-namespaces-archivo="${archivum__namespace}" \
     "${archivum__cod_ab_bcp47}" |
     rapper --quiet --input=turtle --output=turtle /dev/fd/0 \
       >"${archivum__resultata_bag1}"
 
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47 \
-    --rdf-bag=2 \
+    --rdf-trivio=2 \
     --rdf-namespaces-archivo="${archivum__namespace}" \
     "${archivum__cod_ab_bcp47}" |
     rapper --quiet --input=turtle --output=turtle /dev/fd/0 \
       >"${archivum__resultata_bag2}"
 
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47 \
-    --rdf-bag=3 \
+    --rdf-trivio=3 \
     --rdf-namespaces-archivo="${archivum__namespace}" \
     "${archivum__cod_ab_bcp47}" |
     rapper --quiet --input=turtle --output=turtle /dev/fd/0 \
       >"${archivum__resultata_bag3}"
 
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47 \
-    --rdf-bag=4 \
+    --rdf-trivio=4 \
     --rdf-namespaces-archivo="${archivum__namespace}" \
     "${archivum__cod_ab_bcp47}" |
     rapper --quiet --input=turtle --output=turtle /dev/fd/0 \
@@ -273,44 +273,45 @@ test_cod_ab__with_inferences_prebuild() {
   # officina/999999/1568346/data
 
   # @TODO: implement implicit aliases when sU2200 reference multiple subject
-  #        groups (like s500-s506 for administrative regions) but user
-  #        askis for s1 and s1 is also one of these s500-s506.
+  #        groups (like s5000-s506 for administrative regions) but user
+  #        askis for s1 and s1 is also one of these s5000-s506.
 
   set -x
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47_meta_in_json \
     --rdf-namespaces-archivo="${archivum__namespace}" \
-    --rdf-bag=500 \
+    --rdf-trivio=5000 \
     "${archivum__cod_ab_bcp47}" |
     jq >"${archivum__resultata_meta_json}"
 
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47 \
-    --rdf-bag=500 \
+    --rdf-trivio=5000 \
     --rdf-namespaces-archivo="${archivum__namespace}" \
     "${archivum__cod_ab_bcp47}" |
     rapper --quiet --input=turtle --output=turtle /dev/fd/0 \
       >"${archivum__resultata_bag1}"
 
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47 \
-    --rdf-bag=501 \
+    --rdf-trivio=5001 \
     --rdf-namespaces-archivo="${archivum__namespace}" \
     "${archivum__cod_ab_bcp47}" |
     rapper --quiet --input=turtle --output=turtle /dev/fd/0 \
       >"${archivum__resultata_bag2}"
 
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47 \
-    --rdf-bag=502 \
+    --rdf-trivio=5002 \
     --rdf-namespaces-archivo="${archivum__namespace}" \
     "${archivum__cod_ab_bcp47}" |
     rapper --quiet --input=turtle --output=turtle /dev/fd/0 \
       >"${archivum__resultata_bag3}"
 
+  # --rdf-trivio=503 is equivalent to --rdf-trivio=1
   "${ROOTDIR}/999999999/0/999999999_54872.py" \
     --objectivum-formato=_temp_bcp47 \
-    --rdf-bag=503 \
+    --rdf-trivio=1 \
     --rdf-namespaces-archivo="${archivum__namespace}" \
     "${archivum__cod_ab_bcp47}" |
     rapper --quiet --input=turtle --output=turtle /dev/fd/0 \
@@ -560,13 +561,13 @@ exit 0
 # ./999999999/0/999999999_54872.py --objectivum-formato=_temp_bcp47_meta_in_json --rdf-namespaces-archivo=999999999/1568346/data/hxlstandard-rdf-namespaces-example.hxl.csv 999999999/1568346/data/unesco-thesaurus.bcp47g.tsv | jq > 999999/1568346/data/unesco-thesaurus.meta.json
 
 
-# ./999999999/0/999999999_54872.py 999999999/1568346/data/unesco-thesaurus.bcp47g.tsv --rdf-namespaces-archivo=999999999/1568346/data/hxlstandard-rdf-namespaces-example.hxl.csv --objectivum-formato=_temp_bcp47_meta_in_json --rdf-bag=1 | jq
+# ./999999999/0/999999999_54872.py 999999999/1568346/data/unesco-thesaurus.bcp47g.tsv --rdf-namespaces-archivo=999999999/1568346/data/hxlstandard-rdf-namespaces-example.hxl.csv --objectivum-formato=_temp_bcp47_meta_in_json --rdf-trivio=1 | jq
 
-# ./999999999/0/999999999_54872.py 999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv --objectivum-formato=_temp_bcp47_meta_in_json --rdf-bag=1 | jq
+# ./999999999/0/999999999_54872.py 999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv --objectivum-formato=_temp_bcp47_meta_in_json --rdf-trivio=1 | jq
 
 # ./999999999/0/linguacodex.py --de_bcp47_simplex --de_codex=por-Latn-r-pSKOS-pprefLabel-ps4
 
-# ./999999999/0/999999999_54872.py --objectivum-formato=_temp_bcp47 999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv --rdf-bag=2 --rdf-sine-spatia-nominalibus=skos
+# ./999999999/0/999999999_54872.py --objectivum-formato=_temp_bcp47 999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv --rdf-trivio=2 --rdf-sine-spatia-nominalibus=skos
 
 #### BFO _______________________________________________________________________
 # @see https://standards.iso.org/iso-iec/21838/-2/ed-1/en/

diff --git a/officina/999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv b/officina/999999999/1568346/data/cod-ab-example1-with-inferences.bcp47.tsv
@@ -1,3 +1,3 @@
-qcc-Zxxx-r-aOBO-abfo29-anop-sU2200-s500-snop-pOBO-pbfo124-ps501	qcc-Zxxx-r-aOBO-abfo29-anop-sU2200-s501-snop-pOBO-pbfo124-ps502-pOBO-pbfo171-ps500	qcc-Zxxx-r-aOBO-abfo29-anop-sU2200-s502-snop-pOBO-pbfo124-ps502-pOBO-pbfo171-ps501	qcc-Zxxx-r-aOBO-abfo29-anop-sU2200-s1-snop-sU2200-s503-snop-pOBO-pbfo124-ps503-pOBO-pbfo171-ps502	por-Latn-r-pSKOS-pprefLabel-ps500	por-Latn-r-pSKOS-pprefLabel-ps501	por-Latn-r-pSKOS-pprefLabel-ps502	por-Latn-r-pSKOS-pprefLabel-ps503
+qcc-Zxxx-r-aOBO-abfo29-anop-sU2200-s5000-snop-pOBO-pbfo124-ps5001	qcc-Zxxx-r-aOBO-abfo29-anop-sU2200-s5001-snop-pOBO-pbfo124-ps5002-pOBO-pbfo171-ps5000	qcc-Zxxx-r-aOBO-abfo29-anop-sU2200-s5002-snop-pOBO-pbfo124-ps5002-pOBO-pbfo171-ps5001	qcc-Zxxx-r-aOBO-abfo29-anop-sU2200-s1-snop-sU2200-s5003-snop-pOBO-pbfo124-ps5003-pOBO-pbfo171-ps5002	por-Latn-r-pSKOS-pprefLabel-ps5000	por-Latn-r-pSKOS-pprefLabel-ps5001	por-Latn-r-pSKOS-pprefLabel-ps5002	por-Latn-r-pSKOS-pprefLabel-ps5003
 1603:45:16:76:0	1603:45:16:76:1:31	1603:45:16:76:2:3106200		Brasil	Minas Gerais	Belo Horizonte	
 1603:45:16:24:0	1603:45:16:24:1:7	1603:45:16:24:2:7060	1603:45:16:24:3:7060201	Angola	Cuanza Sul	Sumbe (Ngangula)	Kikombo