PICA: general changes #163

pkiraly · Jun 2, 2023 · 1a5b616 · 1a5b616
1 parent 66dc6db
commit 1a5b616
Show file tree

Hide file tree

Showing 5 changed files with 24 additions and 19 deletions.
diff --git a/Dockerfile b/Dockerfile
@@ -39,6 +39,7 @@ RUN apt-get update \
       r-cran-stringr \
       r-cran-gridextra \
       r-cran-rsqlite \
+      r-cran-httr \
       sqlite3 \
       less \
  && rm -rf /var/lib/apt/lists/*

diff --git a/INSTALL.md b/INSTALL.md
@@ -22,7 +22,7 @@ sudo apt-get install openjdk-11-jre-headless
 # Install R
 sudo apt-get install r-base
 # Install R packages from ppa:marutter
-sudo apt-get install r-cran-tidyverse r-cran-stringr r-cran-gridextra
+sudo apt-get install r-cran-tidyverse r-cran-stringr r-cran-gridextra r-cran-httr
 # Install sqlite3
 sudo apt-get install sqlite3 r-cran-rsqlite
 # Install PHP

diff --git a/scripts/sqlite/calculate-aggregated-numbers.grouped.sh b/scripts/sqlite/calculate-aggregated-numbers.grouped.sh
@@ -47,7 +47,7 @@ log "calculate numbers"
 # ${OUTPUT_DIR}/issue-grouped-types.csv
 # ${OUTPUT_DIR}/issue-grouped-categories.csv
 # ${OUTPUT_DIR}/issue-grouped-paths.csv
-Rscript scripts/sqlite/qa_catalogue.groupping.R ${OUTPUT_DIR} $SOLR_CORE
+Rscript scripts/sqlite/qa_catalogue.grouping.R ${OUTPUT_DIR} $SOLR_CORE
 
 log "import issue_grouped_types"
 tail -n +2 ${OUTPUT_DIR}/issue-grouped-types.csv > ${OUTPUT_DIR}/issue-grouped-types-noheader.csv

diff --git a/scripts/sqlite/qa_catalogue.grouped.sqlite.sql b/scripts/sqlite/qa_catalogue.grouped.sqlite.sql
@@ -20,23 +20,28 @@ CREATE TABLE IF NOT EXISTS "id_groupid" (
   "id"         TEXT,
   "groupId"    INTEGER
 );
-CREATE TABLE IF NOT EXISTS "issue_group_types" (
-  "groupId"    INTEGER,
-  "typeId"     INTEGER,
-  "records"    INTEGER,
-  "instances"  INTEGER
+DROP TABLE IF EXISTS issue_grouped_types;
+CREATE TABLE issue_grouped_types (
+  "groupId"     INTEGER,
+  "typeId"      INTEGER,
+  "record_nr"   INTEGER,
+  "instance_nr" INTEGER
 );
-CREATE TABLE IF NOT EXISTS "issue_group_categories" (
-  "groupId"    INTEGER,
-  "categoryId" INTEGER,
-  "records"    INTEGER,
-  "instances"  INTEGER
+
+DROP TABLE IF EXISTS issue_grouped_categories;
+CREATE TABLE issue_grouped_categories (
+  "groupId"     INTEGER,
+  "categoryId"  INTEGER,
+  "record_nr"   INTEGER,
+  "instance_nr" INTEGER
 );
-CREATE TABLE IF NOT EXISTS "issue_group_paths" (
-  "groupId"    INTEGER,
-  "typeId"     INTEGER,
-  "path"       TEXT,
-  "records"    INTEGER,
-  "instances"  INTEGER
+
+DROP TABLE IF EXISTS issue_grouped_paths;
+CREATE TABLE issue_grouped_paths (
+  "groupId"     INTEGER,
+  "typeId"      INTEGER,
+  "path"        VARCHAR(50),
+  "record_nr"   INTEGER,
+  "instance_nr" INTEGER
 );
 COMMIT;
diff --git a/scripts/sqlite/qa_catalogue.grouping.R b/scripts/sqlite/qa_catalogue.grouping.R
@@ -115,7 +115,6 @@ for (i in 1:len) {
                 instances = instances)
     }
   }
-
 }
 
 file <- sprintf('%s/%s', OUTPUT_DIR, 'issue-grouped-types.csv')