Skip to content

Commit

Permalink
1603_45_16.lib.sh (#45): bootstrap_1603_16_1__lsf now also generate R…
Browse files Browse the repository at this point in the history
…DF/SKOS Turtle
  • Loading branch information
fititnt committed Jul 23, 2022
1 parent d091584 commit b764406
Show file tree
Hide file tree
Showing 2 changed files with 118 additions and 1 deletion.
2 changes: 2 additions & 0 deletions officina/999999999/1568346/bcp47-to-hxl-to-rdf.sh
Original file line number Diff line number Diff line change
Expand Up @@ -187,6 +187,7 @@ test_unesco_thesaurus() {
# Not sure on this (Rocha, 2022-07-23 03:18 UTC)

# Re-save concatenated RDF/XML on RDFLib longturtle
# KNOW ISSUE: generated RDF/XML can change every run
rdfpipe --input-format=turtle --output-format=pretty-xml \
"${archivum__resultata_ttl}" \
>"${archivum__resultata_xml}"
Expand Down Expand Up @@ -329,6 +330,7 @@ test_cod_ab() {
>"${archivum__resultata_ttl}"

# Re-save concatenated RDF/XML on RDFLib longturtle
# KNOW ISSUE: generated RDF/XML can change every run
rdfpipe --input-format=turtle --output-format=pretty-xml \
"${archivum__resultata_ttl}" \
>"${archivum__resultata_xml}"
Expand Down
117 changes: 116 additions & 1 deletion officina/999999999/1603_45_16.lib.sh
Original file line number Diff line number Diff line change
Expand Up @@ -91,10 +91,21 @@ bootstrap_1603_16_1__lsf() {
fontem_archivum_temporarium_no11="${ROOTDIR}/999999/0/$_nomen.no11.tm.hxl.csv"
fontem_archivum_temporarium_no1="${ROOTDIR}/999999/0/$_nomen.no1.tm.hxl.csv"
objetivum_archivum_no1="${ROOTDIR}/1603/16/1/0/$_nomen.no1.tm.hxl.csv"
objetivum_archivum_no1_bcp47min="${ROOTDIR}/1603/16/1/0/$_nomen.no1.bcp47.csv"
objetivum_archivum_no1_owl="${ROOTDIR}/1603/16/1/0/$_nomen.no1.owl.ttl"
objetivum_archivum_no11="${ROOTDIR}/1603/16/1/0/$_nomen.no11.tm.hxl.csv"
objetivum_archivum_no11_bcp47min="${ROOTDIR}/1603/16/1/0/$_nomen.no11.bcp47.csv"
objetivum_archivum_no11_skos="${ROOTDIR}/1603/16/1/0/$_nomen.no11.skos.ttl"

opus_temporibus_temporarium="${DESTDIR}/999999/0/${_nomen}~TEMP~1.csv"
opus_temporibus_temporarium_2="${DESTDIR}/999999/0/${_nomen}~TEMP~2.csv"
opus_temporibus_temporarium_ttl_1="${DESTDIR}/999999/0/${_nomen}~TEMP~1.ttl"
opus_temporibus_temporarium_ttl_2="${DESTDIR}/999999/0/${_nomen}~TEMP~2.ttl"

set -x

# NO11 -----------------------------------------------------------------------

# This will generate a dataset with likely stale translations from Wikidata
# cached (but not commited) on main EticaAI/lexicographi-sine-finibus
"${ROOTDIR}/999999999/0/999999999_7200235.py" \
Expand All @@ -107,6 +118,33 @@ bootstrap_1603_16_1__lsf() {

frictionless validate "${fontem_archivum_temporarium_no11}"

"${ROOTDIR}/999999999/0/999999999_54872.py" \
--methodus=_temp_no1_to_no1_shortnames \
--real-infile-path="${fontem_archivum_temporarium_no11}" >"${opus_temporibus_temporarium}"

# Temporary fix: remove some generated tags with error: +ix_error
# Somewhat temporary: remove non-merget alts: +ix_alt1|+ix_alt12|+ix_alt13
# Non-temporary: remove implicit tags: +ix_hxlattrs
hxlcut \
--exclude='#*+ix_error,#*+ix_hxlattrs,#*+ix_alt1,#*+ix_alt2,#*+ix_alt3' \
"${opus_temporibus_temporarium}" >"${opus_temporibus_temporarium_2}"

# Delete first line ,,,,,
sed -i '1d' "${opus_temporibus_temporarium_2}"

frictionless validate "${opus_temporibus_temporarium_2}"

"${ROOTDIR}/999999999/0/999999999_54872.py" \
--methodus=_temp_data_hxl_to_bcp47 \
--real-infile-path="${opus_temporibus_temporarium_2}" >"${opus_temporibus_temporarium}"

frictionless validate "${opus_temporibus_temporarium}"
set +x

file_update_if_necessary "csv" "${opus_temporibus_temporarium}" "${objetivum_archivum_no11_bcp47min}"

# NO1 ------------------------------------------------------------------------
set -x
# We're removint linguistic content and Wikidata path to geojson
hxlcut \
--exclude='#meta,#item+rdf_p_skos_preflabel_s5000,#item+ix_zzgeojson,#item+ix_zzwgs84point' \
Expand All @@ -117,10 +155,87 @@ bootstrap_1603_16_1__lsf() {

frictionless validate "${fontem_archivum_temporarium_no1}"

"${ROOTDIR}/999999999/0/999999999_54872.py" \
--methodus=_temp_no1_to_no1_shortnames \
--real-infile-path="${fontem_archivum_temporarium_no1}" >"${opus_temporibus_temporarium}"

# head -n 2 "$opus_temporibus_temporarium"
# sleep 5

# Temporary fix: remove some generated tags with error: +ix_error
# Somewhat temporary: remove non-merget alts: +ix_alt1|+ix_alt12|+ix_alt13
# Non-temporary: remove implicit tags: +ix_hxlattrs
hxlcut \
--exclude='#*+ix_error,#*+ix_hxlattrs,#*+ix_alt1,#*+ix_alt2,#*+ix_alt3' \
"${opus_temporibus_temporarium}" >"${opus_temporibus_temporarium_2}"

# Delete first line ,,,,,
sed -i '1d' "${opus_temporibus_temporarium_2}"

"${ROOTDIR}/999999999/0/999999999_54872.py" \
--methodus=_temp_data_hxl_to_bcp47 \
--real-infile-path="${opus_temporibus_temporarium_2}" >"${opus_temporibus_temporarium}"

frictionless validate "${opus_temporibus_temporarium}"

set +x

# head -n 2 "$opus_temporibus_temporarium"
# sleep 5

file_update_if_necessary "csv" "${opus_temporibus_temporarium}" "${objetivum_archivum_no1_bcp47min}"
file_update_if_necessary "csv" "${fontem_archivum_temporarium_no11}" "${objetivum_archivum_no11}"
file_update_if_necessary "csv" "${fontem_archivum_temporarium_no1}" "${objetivum_archivum_no1}"

set -x

## Computational-like RDF serialization, "OWL version" --------------------
# @TODO fix generation of invalid format if
# --rdf-sine-spatia-nominalibus=skos,devnull is enabled

# "${ROOTDIR}/999999999/0/999999999_54872.py" \
# --methodus=_temp_no1 \
# --numerordinatio-cum-antecessoribus \
# --rdf-sine-spatia-nominalibus=devnull \
# --rdf-ontologia-ordinibus="${rdf_ontologia_ordinibus}" \
# --rdf-trivio="${rdf_trivio}" \
# <"${objectivum_archivum_no1}" >"${opus_temporibus_temporarium}"

# # rapper --quiet --input=turtle --output=turtle \
# # "${opus_temporibus_temporarium}" \
# # >"${objectivum_archivum_no1_owl_ttl}"

# rdfpipe --input-format=turtle --output-format=longturtle \
# "${opus_temporibus_temporarium}" \
# >"${objectivum_archivum_no1_owl_ttl}"

# riot --validate "${objectivum_archivum_no1_owl_ttl}"

## Linguistic-like RDF serialization, "SKOS version" ----------------------
# @TODO fix invalid generation if disabling OWL with
# --rdf-sine-spatia-nominalibus=owl

rdf_ontologia_ordinibus='4'
rdf_trivio='5000'

"${ROOTDIR}/999999999/0/999999999_54872.py" \
--methodus=_temp_no1 \
--numerordinatio-cum-antecessoribus \
--rdf-sine-spatia-nominalibus=obo,p,geo,wdata,devnull \
--rdf-ontologia-ordinibus="${rdf_ontologia_ordinibus}" \
--rdf-trivio="${rdf_trivio}" \
<"${objetivum_archivum_no11}" >"${opus_temporibus_temporarium_ttl_1}"

rdfpipe --input-format=turtle --output-format=longturtle \
"${opus_temporibus_temporarium_ttl_1}" \
>"${opus_temporibus_temporarium_ttl_2}"

riot --validate "${opus_temporibus_temporarium_ttl_2}"

set +x

# file_update_if_necessary "ttl" "${opus_temporibus_temporarium_ttl_2}" "${objetivum_archivum_no1_owl}"
file_update_if_necessary "ttl" "${opus_temporibus_temporarium_ttl_2}" "${objetivum_archivum_no11_skos}"
}

#######################################
Expand Down Expand Up @@ -785,7 +900,7 @@ bootstrap_1603_45_16__item_rdf() {
"${ROOTDIR}/999999999/0/999999999_54872.py" \
--methodus=_temp_no1 \
--numerordinatio-cum-antecessoribus \
--rdf-sine-spatia-nominalibus=obo,p,geo,devnull \
--rdf-sine-spatia-nominalibus=obo,p,geo,wdata,devnull \
--rdf-ontologia-ordinibus="${rdf_ontologia_ordinibus}" \
--rdf-trivio="${rdf_trivio}" \
<"${objectivum_archivum_no1}" >"${opus_temporibus_temporarium_2}"
Expand Down

0 comments on commit b764406

Please sign in to comment.