pmd.yml

name: Source DRYness

on:
  push:
    branches: [master]
  pull_request:
  workflow_dispatch:

jobs:    
  pmd:
      name: PMD
      runs-on: "ubuntu-latest"
      env:
          pr_everything: 0
      steps:
          - name: Clone - PR
            uses: actions/checkout@v4

          - name: Set up Java
            uses: actions/setup-java@v4
            with:
              distribution: temurin
              java-version: '17'

          - name: Run CPD for Fortran
            continue-on-error: true
            run: |
              # Get latest PMD version from GitHub API
              PMD_VERSION=$(curl -s https://api.github.com/repos/pmd/pmd/releases/latest | grep '"tag_name":' | cut -d'"' -f4 | sed 's/pmd_releases\///')
              echo "Using PMD version: $PMD_VERSION"

              curl -sSL -o pmd.zip \
                "https://github.com/pmd/pmd/releases/download/pmd_releases/${PMD_VERSION}/pmd-dist-${PMD_VERSION}-bin.zip"
              unzip -q pmd.zip
              PMD_HOME="pmd-bin-${PMD_VERSION}"
          
              SOURCE_DIR="${1:-src}"
              total_files=$(find "$SOURCE_DIR" -type f \( -name "*.f" -o -name "*.f90" -o -name "*.for" -o -name "*.fpp" -o -name "*.F" -o -name "*.F90" \) | wc -l)
              processed=0

              find "$SOURCE_DIR" -type f \( -name "*.f" -o -name "*.f90" -o -name "*.for" -o -name "*.fpp" -o -name "*.F" -o -name "*.F90" \) -print0 | 
              while IFS= read -r -d $'\0' file; do
                  processed=$((processed + 1))
                  
                  # Create a temporary file with same permissions as original
                  TMP_FILE=$(mktemp)
                  if [ $? -ne 0 ]; then
                      echo -e "Failed to create temporary file for $file, skipping"
                      continue
                  fi
                  
                  # Copy permissions from original file
                  chmod --reference="$file" "$TMP_FILE"
                  
                  # More comprehensive sed command to handle different Fortran comment styles:
                  # 1. Replace lines that are entirely comments with an empty line:
                  #    - Lines starting with '!' (free form comments)
                  #    - Lines starting with 'c', 'C', '*', 'd', 'D' in column 1 (fixed form comments)
                  # 2. Remove end-of-line comments (anything after '!' that isn't in a string)
                  # 3. Preserve strings containing '!' characters                  
                  sed -E '
                    # First handle & continuation style (modern Fortran)
                    :ampersand_loop
                    /&[[:space:]]*$/ {
                      N
                      s/&[[:space:]]*\n[[:space:]]*(&)?/ /g
                      tampersand_loop
                    }
                    
                    # Handle fixed-form continuation (column 6 indicator)
                    :fixed_form_loop
                    /^[[:space:]]{0,5}[^[:space:]!&]/ {
                      N
                      s/\n[[:space:]]{5}[^[:space:]]/ /g
                      tfixed_form_loop
                    }
                    
                    # Remove any remaining continuation markers
                    s/&//g
                    
                    # Normalize spacing - replace multiple spaces with single space
                    s/[[:space:]]{2,}/ /g
                    
                    # Remove spaces around mathematical operators
                    s/[[:space:]]*\*[[:space:]]*/*/g
                    s/[[:space:]]*\+[[:space:]]*/+/g
                    s/[[:space:]]*-[[:space:]]*/-/g
                    s/[[:space:]]*\/[[:space:]]*/\//g
                    s/[[:space:]]*\*\*[[:space:]]*/\*\*/g
                    
                    # Remove spaces in common Fortran constructs (array indexing, function calls)
                    s/\([[:space:]]*([^,)[:space:]]+)[[:space:]]*,/(\1,/g      # First argument
                    s/,[[:space:]]*([^,)[:space:]]+)[[:space:]]*,/,\1,/g       # Middle arguments
                    s/,[[:space:]]*([^,)[:space:]]+)[[:space:]]*\)/,\1)/g      # Last argument
                    s/\([[:space:]]*([^,)[:space:]]+)[[:space:]]*\)/(\1)/g     # Single argument
                    
                    # Remove spaces around brackets and parentheses
                    s/\[[[:space:]]*/</g
                    s/\[[[:space:]]*/>/g
                    s/\[[[:space:]]*/</g
                    s/[[:space:]]*\]/]/g
                    s/\([[:space:]]*/(/g
                    s/[[:space:]]*\)/)/g

                    # Remove spaces around comparison operators
                    s/[[:space:]]*<=[[:space:]]*/</g
                    s/[[:space:]]*>=[[:space:]]*/>/g
                    s/[[:space:]]*<[[:space:]]*/</g
                    s/[[:space:]]*>[[:space:]]*/>/g
                    s/[[:space:]]*==[[:space:]]*/==/g

                    # Remove full-line comments
                    /^\s*!/d
                    /^[cC*dD]/d
                    /^[ \t]*[cC*dD]/d
                    /^[[:space:]]*$/d

                    # Remove end-of-line comments, preserving quoted strings
                    s/([^"'\''\\]*("[^"]*")?('\''[^'\'']*'\''?)?[^"'\''\\]*)[!].*$/\1/
                  ' "$file" > "$TMP_FILE"

                  if cmp -s "$file" "$TMP_FILE"; then
                      rm "$TMP_FILE"
                  else
                      # Overwrite the original file with the processed content
                      mv "$TMP_FILE" "$file"
                  fi
              done

              "${PMD_HOME}/bin/pmd" cpd \
                --dir src \
                --language fortran \
                --minimum-tokens=20 \
                --no-fail-on-violation \
                --no-fail-on-error