path: root/project

#!/bin/sh
#
# High-level script to manage the project.
# Run `./project --help' for a description of how to use it.
#
# Copyright (C) 2019-2020 Mohammad Akhlaghi <mohammad@akhlaghi.org>
#
# This file is part of Maneage. Maneage is free software: you can
# redistribute it and/or modify it under the terms of the GNU General
# Public License as published by the Free Software Foundation, either
# version 3 of the License, or (at your option) any later version.
#
# Maneage is distributed in the hope that it will be useful, but WITHOUT
# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
# more details. See <http://www.gnu.org/licenses/>.


# Basic settings
# --------------
# Stop the script if there are any errors.
set -e





# Default option values
jobs=0     # 0 is for the default for the `configure.sh' script.
group=
debug=
host_cc=0
operation=
build_dir=
input_dir=
check_config=
make_targets=
software_dir=
clean_texdir=0
prepare_redo=0
existing_conf=0
scriptname="./project"
minmapsize=10000000000





# Parse the options
# -----------------
#
# Separate command-line arguments from options. Then put the option value
# into the respective variable.
#
# Each option has two lines because we want to process both these formats:
# `--name=value' and `--name value'. The former (with `=') is a single
# command-line argument, so we just need to shift the counter by one. The
# latter (without `=') is two arguments, so we'll need two shifts.
#
# Note on the case strings: for every option, we need three lines: one when
# the option name and value are separate. Another when there is an equal
# between them, and finally one where the value is immediately after the
# short-format. This exact order is important. Otherwise, there will be a
# conflict between them.

print_help() {
    # Print the output.
    cat <<EOF
Usage: $scriptname configure [OPTIONS]
       $scriptname make      [OPTIONS]

Top-level script to manage the reproducible project. The high-level
operation is defined by the (mandatory) second argument:

  configure    - Configure project for this machine (e.g., build software).
  make         - Run the project (do analysis and build outputs).

RECOMMENDATION: If this is the first time you are configuring this
template, please don't use the options and let the script explain each
parameter in full detail by simply running './project configure'.

Project 'make' special features.
  ./project make           Build the project on one thread
  ./project make -jN       Built the project in parallel on N threads.
  ./project make clean     Clean all files generated by 'make' (not software).
  ./project make distclean Clean everything (including compiled software).
  ./project make dist      Produce a LaTeX-ready-to-build distribution tarball
                           ('tar.gz') of the project. This is ready to be
                           uploaded to servers like 'arXiv.org'.
  ./project make dist-zip  Similar to 'dist', but compress with '.zip'.

With the options below you can modify the default behavior.
Configure options:
  -b, --build-dir=STR      Top directory to build the project in.
  -e, --existing-conf      Use (possibly existing) local configuration.
      --host-cc            Use host system's C compiler, don't build GCC.
  -i, --input-dir=STR      Directory containing input datasets (optional).
  -m, --minmapsize=INT     [Gnuastro] Minimum number of bytes to use RAM.
  -s, --software-dir=STR   Directory containing necessary software tarballs.
      --check-config       During configuration, show what is being built.
      --clean-texdir       Remove possibly existing build-time subdirectories
                           under the project's 'tex/' directory (can happen
                           when source is from arXiv for example).

Configure and Make options:
  -g, --group=STR          Build and run with write permissions for a group.
  -j, --jobs=INT           Number of threads to build/run the software.
  -?, --help               Print this help list.

Make options:
  -d, --debug=FLAGS        Print various types of debugging information.
  -p, --prepare-redo       Re-do preparation (only done automatically once).

Mandatory or optional arguments to long options are also mandatory or optional
for any corresponding short options.

Maneage URL: https://maneage.org

Report bugs to mohammad@akhlaghi.org
EOF
}

on_off_option_error() {
    if [ "x$2" = x ]; then
        echo "$scriptname: '$1' doesn't take any values."
    else
        echo "$scriptname: '$1' (or '$2') doesn't take any values."
    fi
    exit 1
}

check_v() {
    if [ x"$2" = x ]; then
        echo "$scriptname: option '$1' requires an argument."
        echo "Try '$scriptname --help' for more information."
        exit 1;
    fi
}

func_operation_set() {
    if [ x$operation = x ]; then
        operation=$1
    else
        echo "Only one operation ('configure' or 'make') may be given."
        exit 1
    fi
}

while [ $# -gt 0 ]
do
 case $1 in
  # Main operation.
  configure)    func_operation_set $1; shift;;
  make)         func_operation_set $1; shift;;


  # Configure options:
  -b|--builddir)         build_dir="$2";                             check_v "$1" "$build_dir";    shift;shift;;
  -b=*|--build-dir=*)    build_dir="${1#*=}";                        check_v "$1" "$build_dir";    shift;;
  -b*)                   build_dir=$(echo    "$1" | sed -e's/-b//'); check_v "$1" "$build_dir";    shift;;
  -e|--existing-conf)    existing_conf=1;                                                          shift;;
  -e*|--existing-conf=*) on_off_option_error --existing-conf -e;;
  --host-cc)             host_cc=1;                                                                shift;;
  --host-cc=*)           on_off_option_error --host-cc;;
  -i|--input-dir)        input_dir="$2";                             check_v "$1" "$input_dir";    shift;shift;;
  -i=*|--input-dir=*)    input_dir="${1#*=}";                        check_v "$1" "$input_dir";    shift;;
  -i*)                   input_dir=$(echo    "$1" | sed -e's/-i//'); check_v "$1" "$input_dir";    shift;;
  -m|--minmapsize)       minmapsize="$2";                            check_v "$1" "$minmapsize";   shift;shift;;
  -m=*|--minmapsize=*)   minmapsize="${1#*=}";                       check_v "$1" "$minmapsize";   shift;;
  -m*)                   minmapsize=$(echo   "$1" | sed -e's/-m//'); check_v "$1" "$minmapsize";   shift;;
  -s|--software-dir)     software_dir="$2";                          check_v "$1" "$software_dir"; shift;shift;;
  -s=*|--software-dir=*) software_dir="${1#*=}";                     check_v "$1" "$software_dir"; shift;;
  -s*)                   software_dir=$(echo "$1" | sed -e's/-s//'); check_v "$1" "$software_dir"; shift;;
  --check-config)        check_config=1;                                                           shift;;
  --check-config=*)      on_off_option_error --check-config;;
  --clean-texdir)        clean_texdir=1;                                                           shift;;
  --clean-texdir=*)      on_off_option_error --clean-texdir;;

  # Configure and Make options:
  -g|--group)             group="$2";                            check_v group "$group";   shift;shift;;
  -g=*|--group=*)         group="${1#*=}";                       check_v group "$group";   shift;;
  -g*)                    group=$(echo   "$1" | sed -e's/-g//'); check_v group "$group";   shift;;
  -j|--jobs)              jobs="$2";                             check_v jobs  "$jobs";    shift;shift;;
  -j=*|--jobs=*)          jobs="${1#*=}";                        check_v jobs  "$jobs";    shift;;
  -j*)                    jobs=$(echo "$1" | sed -e's/-j//');    check_v jobs  "$jobs";    shift;;
  -'?'|--help)            print_help; exit 0;;
  -'?'*|--help=*)         on_off_option_error --help -?;;

  # Make options
  # ------------
  #
  # Note that Make's `debug' can take values, but when called without any
  # value, it is like giving it a value of `a'):
  -d|--debug)             if [ x"$2" = x ]; then debug=a;          shift;
                          else debug="$2"; check_v debug "$debug"; shift;shift; fi;;
  -d=*|--debug=*)         debug="${1#*=}";                       check_v debug "$debug";   shift;;
  -d*)                    debug=$(echo "$1" | sed -e's/-d//');   check_v debug "$debug";   shift;;
  -p|--prepare-redo)      prepare_redo=1;                                                  shift;;
  -p=*|--prepare-redo=*)  on_off_option_error --prepare-redo;                              shift;;

  # Unrecognized option:
  -*) echo "$scriptname: unknown option '$1'"; exit 1;;

  # Not an option, an argument (so its a Make target).
  *) make_targets="$make_targets $1"; shift;;
 esac
done





# Check configuration status
# --------------------------
if ! [ x$check_config = x ]; then
    # Find the color option to pass to `ls'. Note that `--color' (for GNU
    # Coreutils `ls') should be checked first because it also has `-G', but
    # for something else.
    if   ls --color 2> /dev/null > /dev/null; then coloropt="--color=auto"
    elif ls -G      2> /dev/null > /dev/null; then coloropt="-G"
    else                               coloropt=""
    fi

    # Print a notice to let the user know what is happening.
    cat <<EOF

This is an infinite loop that will print what software are being built at
every moment. It is actually a listing ('ls' command) of the temporary
directory where software source code are unpacked while they are being
built. If the project isn't being configured, the output (every second)
will either be empty (only a date) or a with an error about a non-existant
directory. This feature is thus only useful when the project's software are
being built.

EOF

    # Run the infinite loop.
    while true; do
        echo;
        echo "$(date)    [[press CTRL-C to stop]]";
        ls $coloropt .build/software/build-tmp || junk=1;
        sleep 1;
    done
    exit 0
fi





# Basic group settings
# --------------------
if ! [ x$group = x ]; then

    # Check if group is usable.
    if ! sg "$group" "echo test &> /dev/null" &> /dev/null; then
        echo "$scriptname: '$group' is not a usable group name on this system.";
        echo "(TIP: you can use the 'groups' command to see your groups)"
        exit 1
    fi

    # Set the group option for running Make.
    gopt="reproducible_paper_group_name=$group"
fi





# Run operations in controlled environment
# ----------------------------------------
controlled_env() {
    # Get the full address of the build directory:
    bdir=`.local/bin/realpath .build`

    # Remove all existing environment variables (with `env -i') and only
    # use some pre-defined environment variables, then build the project.
    envmake=".local/bin/env -i HOME=$bdir sys_rm=$(which rm) $gopt"
    envmake="$envmake .local/bin/make --no-builtin-rules"
    envmake="$envmake --no-builtin-variables -f $1"
    if ! [ x"$debug" = x  ]; then envmake="$envmake --debug=$debug"; fi

    # Set the number of jobs. Note that for the `configure.sh' script the
    # default value has to be 0, so the default is the maximum number of
    # threads. But here, the default value is 1.
    if ! [ x"$jobs"  = x0 ]; then envmake="$envmake -j$jobs";  fi

    # Run the project
    if [ x"$group" = x ]; then
        $envmake $make_targets
    else
        # Set the group and permission flags.
        sg "$group" "umask $perms && $envmake $make_targets"
    fi
}





# Do requested operation
# ----------------------
perms="u+r,u+w,g+r,g+w,o-r,o-w,o-x"
configscript=./reproduce/software/shell/configure.sh
case $operation in

    # Build the project's software.
    configure)

        # Set executable flags
        # --------------------
        #
        # In some scenarios (for example when using a tarball from arXiv),
        # it may happen that the host server has removed the executable
        # flags of all the files. In `README.md' we instruct the readers on
        # setting the executable flag of this script. But we don't want the
        # user to have to worry about any other file that needs an
        # executable flag.
        #
        # Basically, all the files (shell scripts) in the two
        # `reproduce/*/bash' should need executable flags, so we are giving
        # them executable flags by default. If any other file in your project
        # needs such flags, add them here.
        chmod +x reproduce/software/shell/* reproduce/analysis/bash/*

        # If the user requested, clean the TeX directory from the extra
        # (to-be-built) directories that may already be there (and will not
        # allow the configuration to complete).
        if [ x"$clean_texdir" = x1 ]; then
            rm -rf tex/build tex/tikz
        fi

        # Variables to pass to the configuration script.
        export jobs=$jobs
        export host_cc=$host_cc
        export build_dir=$build_dir
        export input_dir=$input_dir
        export scriptname=$scriptname
        export minmapsize=$minmapsize
        export software_dir=$software_dir
        export existing_conf=$existing_conf
        export reproducible_paper_group_name=$group

        # Run the configuration script
        if [ x"$group" = x ]; then
            $configscript
        else
            # Set the group and permission flags.
            sg "$group" "umask $perms && $configscript"

            # Set the group writing permission for everything in the
            # installed software directory. The common build process sets
            # the writing permissions of the installed programs/libraries
            # to `755'. So group members can't write over a file. This
            # creates problems when another group member wants to update
            # the software for example. We thus need to manually add the
            # group writing flag to all installed software files.
            echo "Enabling group writing permission on all installed software..."
            .local/bin/chmod -R g+w .local/;
        fi
        ;;





    # Run the project.
    make)

        # Make sure the configure script has been completed properly
        # (`configuration-done.txt' exists).
        if ! [ -f .build/software/configuration-done.txt ]; then
            cat <<EOF

The project is either (1) not configured on this system, or (2) the
configuration wasn't successful.

(1) If it hasn't been configured at all, use the command below to configure
it (set a build directory and let it build its necessary software in it).

      $ ./project configure

(2) If it has been configured, but the configuration failed in a step, you
can re-configure it using your previous settings with the command
below. All successful steps will be skipped, allowing a fast completion.

      $ ./project configure -e

If there was a problem, please let us know by filling this online form:
      http://savannah.nongnu.org/support/?func=additem&group=reproduce

EOF
            exit 1
        fi

        # Run data preparation phase (optionally build Makefiles with
        # special values for optimizing the main `top-make.mk'). But note
        # that data preparation is only done automatically the first time
        # the project is built (when `.build/software/preparation-done.mk'
        # doesn't yet exist). After that, if the user wants to re-do the
        # preparation they have to use the `--prepare-redo' option.
        if ! [ -f .build/software/preparation-done.mk ] \
                || [ x"$prepare_redo" = x1 ]; then
            controlled_env reproduce/analysis/make/top-prepare.mk
        fi

        # Run the actual project.
        controlled_env reproduce/analysis/make/top-make.mk

        # Print the number of words (if the user has pdftotext.
        if which pdftotext &> /dev/null; then
          numwords=$(pdftotext paper.pdf && cat paper.txt | wc -w)
          echo; echo "Number of words in full PDF: $numwords"
          rm paper.txt
        fi
        ;;





    # Operation not specified.
    *)
        cat <<EOF

No operation defined!

Please run with '--help' for more information.
(TIP: available operations are: 'configure' or 'make').

EOF
        exit 1
    ;;
esac