using PIIscanner

.github/workflows/CI.yml

@@ -0,0 +1,54 @@
+name: CI
+on:
+  push:
+    branches:
+      - main
+    tags: ['*']
+  pull_request:
+  workflow_dispatch:
+concurrency:
+  # Skip intermediate builds: always.
+  # Cancel intermediate builds: only if it is a pull request build.
+  group: ${{ github.workflow }}-${{ github.ref }}
+  cancel-in-progress: ${{ startsWith(github.ref, 'refs/pull/') }}
+jobs:
+  test:
+    name: Julia ${{ matrix.version }} - ${{ matrix.os }} - ${{ matrix.arch }}
+    runs-on: ${{ matrix.os }}
+    timeout-minutes: 60
+    permissions: # needed to allow julia-actions/cache to proactively delete old caches that it has created
+      actions: write
+      contents: read
+    strategy:
+      fail-fast: false
+      matrix:
+        version:
+          - '1.12'
+        os:
+          - ubuntu-latest
+        arch:
+          - x64
+    steps:
+      - uses: actions/checkout@v6
+      - uses: r-lib/actions/setup-r@v2
+        with:
+          use-public-rspm: true
+          r-version: 'release'
+      - name: Set LD_LIBRARY_PATH for R
+        run: echo "LD_LIBRARY_PATH=$(R RHOME)/lib:$LD_LIBRARY_PATH" >> $GITHUB_ENV
+        if: matrix.os == 'ubuntu-latest'
+      - name: Install rio from GitHub  
+        run: Rscript -e 'install.packages(c("remotes", "haven")); remotes::install_github("gesistsa/rio")'
+        env:
+          GITHUB_PAT: ${{ secrets.GITHUB_TOKEN }}
+      - name: Install all rio format handlers
+        run: Rscript -e 'rio::install_formats()'
+      - name: Install cloc
+        run: sudo apt-get update && sudo apt-get install -y cloc
+      - uses: julia-actions/setup-julia@v2
+        with:
+          version: ${{ matrix.version }}
+          arch: ${{ matrix.arch }}
+      - uses: julia-actions/cache@v2
+      - uses: julia-actions/julia-buildpkg@v1
+      - uses: julia-actions/julia-runtest@v1

.gitignore

@@ -1,154 +1 @@
-# this is from https://github.com/AEADataEditor/replication-template-development/blob/development/.gitignore
 
-# Data file extensions
-# They are duplicated in upper case and in some cases mixed case to cover all bases
-# If you want to make the parsing overall case-insensitive, you can use the following:
-#  git config core.ignorecase false
-# Version: 2025-06-06
-*.gpkg
-*.GPKG
-*.bak
-*.BAK
-*.tmp
-*.TMP
-*.aux
-*.AUX
-*.mat
-*.MAT
-*.sav
-*.SAV
-*.sas7bdat
-*.SAS7BDAT
-*.dta
-*.DTA
-*.csv
-*.CSV
-*.tsv
-*.TSV
-*.RData
-*.RDATA
-*.rdata
-*.Rdata
-*.Rds
-*.RDs
-*.RDS
-*.rds
-*.RDA
-*.Rda
-*.raw
-*.Raw
-*.RAW
-*.dbf
-*.DBF
-*.prj
-*.PRJ
-*.shp
-*.SHP
-*.shx
-*.SHX
-*.xml
-*.XML
-*.xpt
-*.XPT
-*.cpg
-*.CPG
-*.sbn
-*.SBN
-*.sbx
-*.SBX
-*.mpk
-*.MPK
-*.tfw
-*.TFW
-*.pkl
-*.PKL
-*.pbf
-*.PBF
-*.jld2
-*.JLD2
-*.dat
-*.DAT
-*.Dat
-*.feather
-*.pickle
-*.tab
-*.TAB
-# Sometimes, these are data files, too
-*.txt
-*.TXT
-*.asc
-*.ASC
-# Usually, we include images, but TIFF files can be huge
-*.tif*
-*.TIF*
-*.ovr
-*.OVR
-*.lyrx
-*.lyrx
-# Archives
-*.rar
-*.RAR
-*.zip
-*.ZIP
-*.gz
-*.tgz
-*.xz
-*.7z
-*.tar
-# Databases
-**/.*gdb/
-# Random binary formats
-*.bin
-*.BIN
-*.exe
-*.EXE
-*.dll
-*.DLL
-*.so
-*.SO
-# MacOS specific files and directories
-*.DS_Store
-*.DS_store
-*.ds_store
-__MACOSX/
-*.dmg
-*.DMG
-# Stata-specific temp files
-*.stswp
-# build-specific directories
-.rproj*
-.Rhistory
-.Rproj.user
-# test
-# .vscode
-*.npy
-__pycache__
-libraries
-# Exclusions we need for our work
-!generated/
-!generated/**
-!images/
-!images/**
-!src/
-!src/**
-!test/
-!test/**
-
-!R*.txt
-!R*.TXT
-!pii_stata_output.csv
-!package-output-map.xlsx
-
-# Exclusions we need
-TEMPLATE.html
-TEMPLATE_files/
-build/requirements.txt
-codeocean-*-live
-tmp
-cache
-# some files which should never be included
-*.lic
-*.LIC
-# Ignore all files in any directory named "data"
-**/data/*
-/.quarto/