#!/bin/bash Version=0.01 Myname="${0##*/}" :<<'DOC' = pdfcat - concatenate pdf's = Synopsis pdfcat [options] filenames == Options -h,--help print short help and exit -H,--Help print full documentation and exit -V,--version print version and exit -c,--crop crop all pages of the output pdf -d,--debug do not remove temporary directory; implies --verbose -f,--font=X set font for title page and captions to X. optionally add pointsize; default: X='DejaVuSerif 12' -g,--geometry=X pdf page size for output in mm to X; default: X=210x297 -m,--margins=X left top right bottom margins in mm. default: X='0 0 0 0' if one number is given, it is used for all margins implies --crop -o,--output=X set output file to X; default: standard output -t,--toc generate subsections and toc -v,--verbose run verbosely = Description pdfcat concatenates two or more pdf's to one pdf. If a specified filename has no |.pdf| extension, it is added. If no output file is specified, standard output is used. The output pdf page size will be A4, unless the |--geometry| option is used. With the |--crop| option, every page will be cropped with zero margin, unless the |--margins| option specifies other margins. The |--margins| option implies |--crop| and specifies left, top, right, and bottom margins in mm in a space separated string, which must of course be double quoted. The value can also be a single number, which is used for all margins. If this option is not used, |--crop| will apply zero margins. Note that, if you just want to concatenate pdf's, without any of the |-- crop|, |--toc|, |--margins| or |--geometry| options, you could beter use pdfunite from the poppler-utils package. = Author [Wybo Dekker](wybodekker@me.com) = Copyright Released under the [GNU General Public License](www.gnu.org/copyleft/gpl.html) DOC REd='\e[38;5;9m' Mag='\e[38;5;5m' Nor='\e[0m' die() { local i; for i; do echo -e "$Myname: $REd$i$Nor"; done 1>&2; exit 1; } Warn() { local i; for i; do echo -e "$Myname: $Mag$i$Nor"; done 1>&2; } warn() { $verbose && Warn "$@"; } helpsrt() { sed -n '/^= Synopsis/,/^= /p' "$0"|sed '1d;$d'; exit; } helpall() { sed -n "/^:<<'DOC'$/,/^DOC/p" "$0"|sed '1d;$d'| less -P"$Myname-${Version/./·} (press h for help, q to quit)";exit; } :<<'DOC' #--------------------------------------------------------------------- = texescape synopsis: texescape varname description: escape #, _, %, & in the variable named in the argument x='50%'; texescape x; echo $x → 50\% DOC #------------------------------------------------------------------------------- texescape() { eval "$1=\${$1//#/\\\\#} $1=\${$1//%/\\\\%} $1=\${$1//&/\\\\&} $1=\${$1//_/\\\\_}" } :<<'DOC' #--------------------------------------------------------------------- = excheck synopsis: excheck executable1 [executable2...] description: check if all needed execs are there and getopt is GNU DOC #------------------------------------------------------------------------------- excheck() { local ok=true i ((BASH_VERSINFO>=4)) || die "Need bash version >= 4" for i; do command -v "$i" > /dev/null && continue Warn "Missing executable: $i" ok=false done $ok || die getopt -T [[ $? -ne 4 ]] && die "Your getopt is not GNU" } :<<'DOC' #---------------------------------------------------------------------- = handle_options synopsis: handle_options "$@" description: handle the options. globals used: Myname Version verbose toc outfile debug crop xmm ymm margins font fsize globals set: args DOC #------------------------------------------------------------------------------- handle_options() { local options options=$(getopt \ -n "$Myname" \ -o hHVdf:Ivcm:o:g:t \ -l help,Help,version,verbose,font:,margins:,output:,geometry:,crop:,debug,toc \ -- "$@" ) || exit 1 eval set -- "$options" crop=false outfile='' xmm=210 ymm=297 margins=0 toc=false verbose=false font=DejaVuSerif fsize=12 while true; do case $1 in (-h|--help) # print short help and exit helpsrt ;; (-H|--Help) # print full documentation and exit helpall ;; (-V|--version) # print version and exit echo $Version exit ;; (-c|--crop) # crop all pages of the output pdf crop=true shift ;; (-d|--debug) # do not remove temporary directory; implies --verbose verbose=true shift ;; (-f|--font) # set font for title page and captions to X. # optionally add pointsize; default: X='DejaVuSerif 12' if [[ $2 =~ ([A-Za-z_\ -]+)\ *([0-9]*)$ ]]; then font=${BASH_REMATCH[1]% } fsize=${BASH_REMATCH[2]} fi : "${fsize:=12}" shift 2 ;; (-g|--geometry) # pdf page size for output in mm to X; default: X=210x297 IFS=x read -r xmm ymm <<<"$2" shift 2 ;; (-m|--margins) # left top right bottom margins in mm. # default: X='0 0 0 0' # if one number is given, it is used for all margins # implies --crop margins="$2" crop=true shift 2 ;; (-o|--output) # set output file to X; default: standard output outfile=${2%.pdf} shift 2 ;; (-t|--toc) # generate subsections and toc toc=true shift ;; (-v|--verbose) # run verbosely verbose=true shift ;; (-I) instscript "$0" || die 'the -I option is for developers only' exit ;; (--) shift break ;; (*) break ;; esac done args=("$@") } excheck getopt pdfcrop lualatex handle_options "$@" set -- "${args[@]}" [[ -z $outfile ]] && [[ -t 1 ]] && die "if you don't specify --output, redirect the output" # do all arguments exist as pdf files? pdfs=() for i; do pdf="$i" [[ $pdf =~ \.(pdf|PDF) ]] || pdf=${i%.pdf}.pdf [[ -e $pdf ]] || die "File $pdf does not exist!" typ=$(file --mime-type -bL "$pdf") [[ $typ == 'application/pdf' ]] || die "$pdf is not a pdf file" rp=$(realpath "$pdf") warn "adding $rp" pdfs+=("$rp") done tmp=$(mktemp -dt "$Myname.XXXXXXXXXX") warn "running in temporary directory $tmp" pdf=$(realpath "${outfile%.pdf}.pdf") # absolute path to output cd "$tmp" || die "Could not cd to $tmp" cat <<-EOD >main.tex %!lualatex \\documentclass{article} \\usepackage{fontspec} \\setmainfont{$font} \\usepackage[papersize={${xmm}mm,${ymm}mm},margin=25mm]{geometry} \\usepackage{pdfpages,graphicx} \\usepackage[hidelinks]{hyperref} \\begin{document} \\fontsize{$fsize}{$((fsize+4))}\selectfont EOD $toc && cat <<-EOD >>main.tex \\tableofcontents\\newpage\\setcounter{secnumdepth}{0} EOD n=0 # copy input files (which may contain spaces or comma's) to 0.pdf, 1.pdf...: for i in "${pdfs[@]}"; do warn "copying $i" cp "$i" $n.pdf || die "error copying $i to $n.pdf" # section header = basename without extension j="${i%.pdf}" j=${j##*/} texescape j $toc && echo "\\subsection{$j}" echo "\\includepdf[pages = -]{$n}" (( n++ )) done >>main.tex echo "\\end{document}" >>main.tex warn "running lualatex" echo x | lualatex main.tex &>/dev/null || die "Errors running lualatex; inspect $tmp" [[ $toc ]] && lualatex main.tex &>/dev/null if $crop; then # convert mm to bp if [[ ! $margins == '0' ]]; then m=$margins warn "adding margins of $m mm" margins='' for i in $m; do margins+=" $(echo "$i*2.835"|bc -l)" done fi pdfcrop --margins="$margins" "main.pdf" "main.pdf" >/dev/null || die "Error running pdfcrop; try --debug" fi if [[ -z $outfile ]]; then cat "main.pdf" else mv "main.pdf" "$pdf" fi rm -r "$tmp"