(#4): data/who-icd-crosswalk.tm.hxl.csv draft

.github/workflows/main.yml

@@ -150,6 +150,9 @@ jobs:
       - run: pip install -r .github/requirements.txt
         continue-on-error: true
 
+      - run: pip list
+        continue-on-error: true
+
       # #### Java Setup __________________________________________________________
       # # @see https://github.com/marketplace/actions/setup-java-jdk
       # - uses: actions/setup-java@v3

.gitignore

@@ -11,4 +11,9 @@ __pycache__
 node_modules
 package.json
 yarn.lock
-temp/
+temp/
+
+
+# https://github.com/EticaAI/lexicographi-sine-finibus is cloned here
+# Reasoning: use some scripts related to Wikidata data pull
+scripts/lexicographi-sine-finibus

data/who-icd-crosswalk.tm.hxl.csv

@@ -0,0 +1,11 @@
+#item+conceptum+codicem,#item+rem+i_qcc+is_zxxx+ix_wikiq,#item+rem+i_qcc+is_zxxx+ix_wdatap493,#item+rem+i_qcc+is_zxxx+ix_wdatap494,#item+rem+i_qcc+is_zxxx+ix_wdatap7329,#item+rem+i_qcc+is_zxxx+ix_wdatap7807
+5,Q5,,,XE653,301526589
+58,Q58,,,XA7QV2,435785772
+144,Q144,,,XE33Q,687129994
+146,Q146,,,XE4V0,1951749770
+152,Q152,,,XE71F,1977658261
+198,Q198,,,XE324,364444100
+497,Q497,,,XA0D34,1211030054
+499,Q499,,,XA17J1,1494375321
+553,Q553,,,XA6CZ2,1492238572
+728,Q728,,,XE4BU,1656506786

i18n/zxx/who-icd.wikidata.yml

@@ -0,0 +1,5 @@
+# - Using:
+#   - https://github.com/EticaAI/lexicographi-sine-finibus
+#   - /workspace/git/EticaAI/lexicographi-sine-finibus/officina
+
+# printf "P7329\n" | ./999999999/0/1603_3_12.py --actionem-sparql --de=P --query --ex-interlinguis --cum-interlinguis=P493,P494,P7329,P7807 | ./999999999/0/1603_3_12.py --actionem-sparql --csv --hxltm > 999999/0/P7329~P493+P494+P7329+P7807.tm.hxl.csv

scripts/common.lib.sh

@@ -35,14 +35,10 @@ BUILDTEMPDIR="${BUILDTEMPDIR:-$__BUILDTEMPDIR}"
 #### Configurable variables  - - - - - - - - - - - - - - - - - - - - - - - - - -
 # from https://apps.who.int/whocc/Search.aspx
 WHO_REGIONS=("AFRO" "AMRO" "EMRO" "EURO" "SEARO" "WPRO")
-# WHO_CSVFIELDS=(
-#   "textbox105|code"   # SOA-5 [AFRO]
-#   "textbox106|status" # Active,Pending
-#   "textbox113|name" # Active,Pending
-#   "textbox20|region" # Active,Pending
-#   "textbox19|country" # Active,Pending
-#   "textbox127|website" # Active,Pending
-# )
+LSF_REMOTE_GIT="https://github.com/EticaAI/lexicographi-sine-finibus.git"
+LSF_LOCAL_CLONED="$ROOTDIR/scripts/lexicographi-sine-finibus"
+LSF_OFFICINA="$LSF_LOCAL_CLONED/officina"
+#NUMERORDINATIO_BASIM="$LSF_OFFICINA"
 
 #### Fancy colors constants - - - - - - - - - - - - - - - - - - - - - - - - - -
 # shellcheck disable=SC2034
@@ -139,6 +135,78 @@ crawler_who_cc_fech_region() {
   printf "\t%40s\n" "${tty_green}${FUNCNAME[0]} FINISHED OKAY ${tty_normal}"
 }
 
+#######################################
+# Build local copy of crosswalk
+#
+# Globals:
+#   ROOTDIR
+#   BUILDTEMPDIR
+# Arguments:
+#   repo        Repository to fetch the data
+#   savepath    (optional) Path to store the metadata
+# Returns
+#   None
+#######################################
+crawler_wikidata_who_icd() {
+  # whoccregion="$1"
+  # output="$2"
+  printf "\n\t%40s\n" "${tty_blue}${FUNCNAME[0]} STARTED ${tty_normal}"
+  echo "TODO"
+
+  temporarium_hxltm="$BUILDTEMPDIR/P7329~P493+P494+P7329+P7807.tm.hxl.csv"
+  temporarium_hxltm_data="$ROOTDIR/data/who-icd-crosswalk.tm.hxl.csv"
+  set -x
+  # node "$ROOTDIR/scripts/etc/whocc-downloader.js" \
+  #   --who-region "$whoccregion" \
+  #   --output "$output"
+  printf "P7329\n" |
+    NUMERORDINATIO_BASIM="${LSF_OFFICINA}" "${LSF_OFFICINA}/999999999/0/1603_3_12.py" \
+      --actionem-sparql \
+      --de=P \
+      --query \
+      --ex-interlinguis \
+      --identitas-ex-wikiq \
+      --cum-interlinguis=P493,P494,P7329,P7807 |
+    NUMERORDINATIO_BASIM="${LSF_OFFICINA}" "${LSF_OFFICINA}/999999999/0/1603_3_12.py" \
+      --actionem-sparql \
+      --identitas-ex-wikiq \
+      --csv --hxltm \
+      >"$temporarium_hxltm"
+
+  frictionless validate "$temporarium_hxltm"
+
+  head -n 11 "$temporarium_hxltm" > "$temporarium_hxltm_data"
+
+  set +x
+  printf "\t%40s\n" "${tty_green}${FUNCNAME[0]} FINISHED OKAY ${tty_normal}"
+}
+
+#######################################
+# Clone remote LSF git to local path (for additional heavy build process)
+#
+# Globals:
+#   ROOTDIR
+#   LSF_REMOTE_GIT
+#   LSF_LOCAL_CLONED
+# Arguments:
+#
+# Returns
+#   None
+#######################################
+gh_clone_lsf_to_scripts() {
+  remote_git="$LSF_REMOTE_GIT"
+  local_dir="$LSF_LOCAL_CLONED"
+
+  if [ -f "${local_dir}" ]; then
+    echo "Already cached [${local_dir}]. Skiping"
+    return 0
+  fi
+
+  set -x
+  git clone "$remote_git" "$local_dir"
+  set +x
+}
+
 #######################################
 # Fetch repo statistics of one repository
 #

scripts/manual.sh → scripts/etc/manual.sh

@@ -3,7 +3,7 @@
 #
 #          FILE:  manual.sh
 #
-#         USAGE:  ./scripts/manual.sh
+#         USAGE:  ./scripts/etc/manual.sh
 #
 #   DESCRIPTION:  Generic non automated commands.
 #

scripts/via-github-action.sh

@@ -43,5 +43,17 @@ if [ "$OPERATION" = "crawler_who_cc" ]; then
   crawler_who_cc
 fi
 
+# OPERATION=gh_clone_lsf_to_scripts ./scripts/via-github-action.sh
+if [ "$OPERATION" = "gh_clone_lsf_to_scripts" ]; then
+  gh_clone_lsf_to_scripts
+  exit 0
+fi
+
+# OPERATION=crawler_wikidata_who_icd ./scripts/via-github-action.sh
+if [ "$OPERATION" = "crawler_wikidata_who_icd" ]; then
+  crawler_wikidata_who_icd
+  exit 0
+fi
+
 echo "unknow operation [$OPERATION]"
 exit 1