ioccc/bin/combine_author_handle.sh

#!/usr/bin/env bash
#
# combine_author_handle.sh - output all author/author_handle.json files as single JSON file
#
# We form a single JSON file out of all author/author_handle.json files.
# We cannot simply cat the author/author_handle.json files because
# each author/author_handle.json file opens and closes the JSON.
# So this tool removes the intermediate JSON document opening "{"
# and closing "}".
#
# Because jsp open remembers the last copy of a given JSON member name.
# As such, we change the JSON member name "winning_entry_set" into
# a unique "winning_entry_set.FILENO" where FILENO is the file number.
# This the JSON member value will be preserved across all files.
#
# We also convert where FILENO is the file number and FILENAME is the filename:
#
#   "sort_word" : "data",
#
# into:
#
#   "sort_word.FILENO" : [
#	{
#	    "sort_word" : "data FILENAME"
#	}
#   ],
#
# This will allow jsp to print sort_word values.
#
# We also make sure that the last item from a given file ends in a comma (",)",
# due to the bogosity of the so-called JSON spec.
#
# NOTE: We assume that all JSON files have been formatted with the
# bin/jprint-wrapper.sh tool.  In particular the first line is just "{:,
# and the last line is just "}" and each JSON element is on its own line.
#
# Copyright (c) 2024 by Landon Curt Noll.  All Rights Reserved.
#
# Permission to use, copy, modify, and distribute this software and
# its documentation for any purpose and without fee is hereby granted,
# provided that the above copyright, this permission notice and text
# this comment, and the disclaimer below appear in all of the following:
#
#       supporting documentation
#       source copies
#       source works derived from this source
#       binaries derived from this source or from derived source
#
# LANDON CURT NOLL DISCLAIMS ALL WARRANTIES WITH REGARD TO THIS SOFTWARE,
# INCLUDING ALL IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS. IN NO
# EVENT SHALL LANDON CURT NOLL BE LIABLE FOR ANY SPECIAL, INDIRECT OR
# CONSEQUENTIAL DAMAGES OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF
# USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR
# OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR
# PERFORMANCE OF THIS SOFTWARE.
#
# chongo (Landon Curt Noll, http://www.isthe.com/chongo/index.html) /\oo/\
#
# Share and enjoy! :-)


# firewall - run only with a bash that is version 5.1.8 or later
#
# The "/usr/bin/env bash" command must result in using a bash that
# is version 5.1.8 or later.
#
# We could relax this version and insist on version 4.2 or later.  Versions
# of bash between 4.2 and 5.1.7 might work.  However, to be safe, we will require
# bash version 5.1.8 or later.
#
# WHY 5.1.8 and not 4.2?  This safely is done because macOS Homebrew bash we
# often use is "version 5.2.26(1)-release" or later, and the RHEL Linux bash we
# use often use is "version 5.1.8(1)-release" or later.  These versions are what
# we initially tested.  We recommend you either upgrade bash or install a newer
# version of bash and adjust your $PATH so that "/usr/bin/env bash" finds a bash
# that is version 5.1.8 or later.
#
# NOTE: The macOS shipped, as of 2024 March 15, a version of bash is something like
#	bash "version 3.2.57(1)-release".  That macOS shipped version of bash
#	will NOT work.  For users of macOS we recommend you install Homebrew,
#	(see https://brew.sh), and then run "brew install bash" which will
#	typically install it into /opt/homebrew/bin/bash, and then arrange your $PATH
#	so that "/usr/bin/env bash" finds "/opt/homebrew/bin" (or whatever the
#	Homebrew bash is).
#
# NOTE: And while MacPorts might work, we noticed a number of subtle differences
#	with some of their ported tools to suggest you might be better off
#	with installing Homebrew (see https://brew.sh).  No disrespect is intended
#	to the MacPorts team as they do a commendable job.  Nevertheless we ran
#	into enough differences with MacPorts environments to suggest you
#	might find a better experience with this tool under Homebrew instead.
#
if [[ -z ${BASH_VERSINFO[0]} ||
	 ${BASH_VERSINFO[0]} -lt 5 ||
	 ${BASH_VERSINFO[0]} -eq 5 && ${BASH_VERSINFO[1]} -lt 1 ||
	 ${BASH_VERSINFO[0]} -eq 5 && ${BASH_VERSINFO[1]} -eq 1 && ${BASH_VERSINFO[2]} -lt 8 ]]; then
    echo "$0: ERROR: bash version needs to be >= 5.1.8: $BASH_VERSION" 1>&2
    echo "$0: Warning: bash version >= 4.2 might work but 5.1.8 was the minimum we tested" 1>&2
    echo "$0: Notice: For macOS users: install Homebrew (see https://brew.sh), then run" \
	 ""brew install bash" and then modify your \$PATH so that \"#!/usr/bin/env bash\"" \
	 "finds the Homebrew installed (usually /opt/homebrew/bin/bash) version of bash" 1>&2
    exit 4
fi


# setup bash file matching
#
# We must declare arrays with -ag or -Ag, and we need loops to "export" modified variables.
# This requires a bash with a version 4.2 or later.  See the larger comment above about bash versions.
#
shopt -s nullglob	# enable expanded to nothing rather than remaining unexpanded
shopt -u failglob	# disable error message if no matches are found
shopt -u dotglob	# disable matching files starting with .
shopt -u nocaseglob	# disable strict case matching
shopt -u extglob	# enable extended globbing patterns
shopt -s globstar	# enable ** to match all files and zero or more directories and subdirectories


# IOCCC requires use of C locale
#
export LANG="C"
export LC_CTYPE="C"
export LC_NUMERIC="C"
export LC_TIME="C"
export LC_COLLATE="C"
export LC_MONETARY="C"
export LC_MESSAGES="C"
export LC_PAPER="C"
export LC_NAME="C"
export LC_ADDRESS="C"
export LC_TELEPHONE="C"
export LC_MEASUREMENT="C"
export LC_IDENTIFICATION="C"
export LC_ALL="C"


# set variables referenced in the usage message
#
export VERSION="2.0.0 2025-03-13"
NAME=$(basename "$0")
export NAME
export V_FLAG=0
GIT_TOOL=$(type -P git)
export GIT_TOOL
if [[ -z "$GIT_TOOL" ]]; then
    echo "$0: FATAL: git tool is not installed or not in \$PATH" 1>&2
    exit 5
fi
"$GIT_TOOL" rev-parse --is-inside-work-tree >/dev/null 2>&1
status="$?"
if [[ $status -eq 0 ]]; then
    TOPDIR=$("$GIT_TOOL" rev-parse --show-toplevel)
fi
export TOPDIR
export DOCROOT_SLASH="../../"
export TAGLINE="unspecified"
export REPO_TOP_URL="https://github.com/ioccc-src/winner"
# GitHub puts individual files under the "blob/master" sub-directory.
export REPO_URL="$REPO_TOP_URL/blob/master"
export SITE_URL="https://www.ioccc.org"
#
export NOOP=
export DO_NOT_PROCESS=
export EXIT_CODE="0"


# usage
#
export USAGE="usage: $0 [-h] [-v level] [-V] [-d topdir] [-D docroot/] [-n] [-N]

	-h		print help message and exit
	-v level	set verbosity level (def level: 0)
	-V		print version string and exit

	-d topdir	set topdir (def: $TOPDIR)
	-D docroot/	set the document root path followed by slash (def: $DOCROOT_SLASH)
			NOTE: The '-D docroot/' is passed as leading options on tool command lines.
			NOTE: 'docroot' must end in a slash

	-n		go thru the actions, but do not update any files (def: do the action)
	-N		do not process anything, just parse arguments (def: process something)

Exit codes:
     0         all OK
     1	       found unexpected \\uHexHexHexHex strings in JSON files
     2         -h and help string printed or -V and version string printed
     3         command line error
     4         bash version is too old
     5	       some internal tool is not found or not an executable file
     6	       problems found with or in the topdir or topdir/YYYY directory
     7	       problems found with or in the entry topdir/YYYY/dir directory
     8	       file.json not a readable file
 >= 10         internal error

$NAME version: $VERSION"


# parse command line
#
while getopts :hv:Vd:D:j:nN flag; do
  case "$flag" in
    h) echo "$USAGE" 1>&2
	exit 2
	;;
    v) V_FLAG="$OPTARG"
	;;
    V) echo "$VERSION"
	exit 2
	;;
    d) TOPDIR="$OPTARG"
	;;
    D) # parse -D docroot/
	case "$OPTARG" in
	*/) ;;
	*) echo "$0: ERROR: in -D docroot/, the docroot must end in /" 1>&2
	   echo 1>&2
	   echo "$USAGE" 1>&2
	   exit 3
	   ;;
	esac
	DOCROOT_SLASH="$OPTARG"
	;;
    n) NOOP="-n"
	;;
    N) DO_NOT_PROCESS="-N"
	;;
    \?) echo "$0: ERROR: invalid option: -$OPTARG" 1>&2
	echo 1>&2
	echo "$USAGE" 1>&2
	exit 3
	;;
    :) echo "$0: ERROR: option -$OPTARG requires an argument" 1>&2
	echo 1>&2
	echo "$USAGE" 1>&2
	exit 3
	;;
    *) echo "$0: ERROR: unexpected value from getopts: $flag" 1>&2
	echo 1>&2
	echo "$USAGE" 1>&2
	exit 3
	;;
  esac
done
#
# remove the options
#
shift $(( OPTIND - 1 ));
#
if [[ $V_FLAG -ge 5 ]]; then
    echo "$0: debug[5]: file argument count: $#" 1>&2
fi
if [[ $# -ne 0 ]]; then
    echo "$0: ERROR: expected 0 args, found: $#" 1>&2
    echo 1>&2
    echo "$USAGE" 1>&2
    exit 3
fi


# verify that we have a topdir directory
#
REPO_NAME=$(basename "$REPO_TOP_URL")
export REPO_NAME
if [[ -z $TOPDIR ]]; then
    echo "$0: ERROR: cannot find top of git repo directory" 1>&2
    echo "$0: Notice: if needed: $GIT_TOOL clone $REPO_TOP_URL; cd $REPO_NAME" 1>&2
    exit 6
fi
if [[ ! -e $TOPDIR ]]; then
    echo "$0: ERROR: TOPDIR does not exist: $TOPDIR" 1>&2
    echo "$0: Notice: if needed: $GIT_TOOL clone $REPO_TOP_URL; cd $REPO_NAME" 1>&2
    exit 6
fi
if [[ ! -d $TOPDIR ]]; then
    echo "$0: ERROR: TOPDIR is not a directory: $TOPDIR" 1>&2
    echo "$0: Notice: if needed: $GIT_TOOL clone $REPO_TOP_URL; cd $REPO_NAME" 1>&2
    exit 6
fi


# cd to topdir
#
if [[ ! -e $TOPDIR ]]; then
    echo "$0: ERROR: cannot cd to non-existent path: $TOPDIR" 1>&2
    exit 6
fi
if [[ ! -d $TOPDIR ]]; then
    echo "$0: ERROR: cannot cd to a non-directory: $TOPDIR" 1>&2
    exit 6
fi
export CD_FAILED
if [[ $V_FLAG -ge 5 ]]; then
    echo "$0: debug[5]: about to: cd $TOPDIR" 1>&2
fi
cd "$TOPDIR" || CD_FAILED="true"
if [[ -n $CD_FAILED ]]; then
    echo "$0: ERROR: cd $TOPDIR failed" 1>&2
    exit 6
fi
if [[ $V_FLAG -ge 3 ]]; then
    echo "$0: debug[3]: now in directory: $(/bin/pwd)" 1>&2
fi


# verify that we have an author subdirectory
#
export AUTHOR_PATH="$TOPDIR/author"
if [[ ! -d $AUTHOR_PATH ]]; then
    echo "$0: ERROR: author is not a directory under topdir: $AUTHOR_PATH" 1>&2
    exit 6
fi
export AUTHOR_DIR="author"


# verify we have a non-empty readable .top file
#
export TOP_FILE=".top"
if [[ ! -e $TOP_FILE ]]; then
    echo  "$0: ERROR: .top does not exist: $TOP_FILE" 1>&2
    exit 6
fi
if [[ ! -f $TOP_FILE ]]; then
    echo  "$0: ERROR: .top is not a regular file: $TOP_FILE" 1>&2
    exit 6
fi
if [[ ! -r $TOP_FILE ]]; then
    echo  "$0: ERROR: .top is not an readable file: $TOP_FILE" 1>&2
    exit 6
fi
if [[ ! -s $TOP_FILE ]]; then
    echo  "$0: ERROR: .top is not a non-empty readable file: $TOP_FILE" 1>&2
    exit 6
fi


# print running info if verbose
#
# If -v 3 or higher, print exported variables in order that they were exported.
#
if [[ $V_FLAG -ge 3 ]]; then
    echo "$0: debug[3]: LANG=$LANG" 1>&2
    echo "$0: debug[3]: LC_CTYPE=$LC_CTYPE" 1>&2
    echo "$0: debug[3]: LC_NUMERIC=$LC_NUMERIC" 1>&2
    echo "$0: debug[3]: LC_TIME=$LC_TIME" 1>&2
    echo "$0: debug[3]: LC_COLLATE=$LC_COLLATE" 1>&2
    echo "$0: debug[3]: LC_MONETARY=$LC_MONETARY" 1>&2
    echo "$0: debug[3]: LC_MESSAGES=$LC_MESSAGES" 1>&2
    echo "$0: debug[3]: LC_PAPER=$LC_PAPER" 1>&2
    echo "$0: debug[3]: LC_NAME=$LC_NAME" 1>&2
    echo "$0: debug[3]: LC_ADDRESS=$LC_ADDRESS" 1>&2
    echo "$0: debug[3]: LC_TELEPHONE=$LC_TELEPHONE" 1>&2
    echo "$0: debug[3]: LC_MEASUREMENT=$LC_MEASUREMENT" 1>&2
    echo "$0: debug[3]: LC_IDENTIFICATION=$LC_IDENTIFICATION" 1>&2
    echo "$0: debug[3]: LC_ALL=$LC_ALL" 1>&2
    echo "$0: debug[3]: VERSION=$VERSION" 1>&2
    echo "$0: debug[3]: NAME=$NAME" 1>&2
    echo "$0: debug[3]: V_FLAG=$V_FLAG" 1>&2
    echo "$0: debug[3]: GIT_TOOL=$GIT_TOOL" 1>&2
    echo "$0: debug[3]: TOPDIR=$TOPDIR" 1>&2
    echo "$0: debug[3]: DOCROOT_SLASH=$DOCROOT_SLASH" 1>&2
    echo "$0: debug[3]: TAGLINE=$TAGLINE" 1>&2
    echo "$0: debug[3]: REPO_TOP_URL=$REPO_TOP_URL" 1>&2
    echo "$0: debug[3]: REPO_URL=$REPO_URL" 1>&2
    echo "$0: debug[3]: SITE_URL=$SITE_URL" 1>&2
    echo "$0: debug[3]: NOOP=$NOOP" 1>&2
    echo "$0: debug[3]: DO_NOT_PROCESS=$DO_NOT_PROCESS" 1>&2
    echo "$0: debug[3]: EXIT_CODE=$EXIT_CODE" 1>&2
    echo "$0: debug[3]: REPO_NAME=$REPO_NAME" 1>&2
    echo "$0: debug[3]: CD_FAILED=$CD_FAILED" 1>&2
    echo "$0: debug[3]: AUTHOR_PATH=$AUTHOR_PATH" 1>&2
    echo "$0: debug[3]: AUTHOR_DIR=$AUTHOR_DIR" 1>&2
fi


# determine the number of author_handle.json files
#
AUTHOR_COUNT=$(find "$AUTHOR_DIR" -type f -name '*.json' -print | wc -l)
export AUTHOR_COUNT
if [[ -z $AUTHOR_COUNT || $AUTHOR_COUNT -le 0 ]]; then
    echo "$0: ERROR: found no author_handle.json files under: $AUTHOR_DIR" 1>&2
    exit 10
fi
if [[ $AUTHOR_COUNT -le 1 ]]; then
    echo "$0: ERROR: expected more than 1 author_handle.json files under: $AUTHOR_DIR" 1>&2
    exit 11
fi


# -N stops early before any processing is performed
#
if [[ -n $DO_NOT_PROCESS ]]; then
    if [[ $V_FLAG -ge 3 ]]; then
	echo "$0: debug[3]: arguments parsed, -N given, exiting 0" 1>&2
    fi
    exit 0
fi


# create a list of all author/author_handle files
#
export TMP_AUTHOR_HANDLE_LIST=".tmp.$NAME.AUTHOR_HANDLE_LIST.$$.tmp"
if [[ $V_FLAG -ge 3 ]]; then
    echo  "$0: debug[3]: list of author_handle JSON files: $TMP_AUTHOR_HANDLE_LIST" 1>&2
fi
trap 'rm -f $TMP_AUTHOR_HANDLE_LIST; exit' 0 1 2 3 15
rm -f "$TMP_AUTHOR_HANDLE_LIST"
if [[ -e $TMP_AUTHOR_HANDLE_LIST ]]; then
    echo "$0: ERROR: cannot remove list of author_handle JSON files: $TMP_AUTHOR_HANDLE_LIST" 1>&2
    exit 12
fi
find "$AUTHOR_DIR" -type f -name '*.json' -print | LC_ALL=C sort -t / -d > "$TMP_AUTHOR_HANDLE_LIST"
if [[ ! -e $TMP_AUTHOR_HANDLE_LIST ]]; then
    echo "$0: ERROR: cannot create list of author_handle JSON files: $TMP_AUTHOR_HANDLE_LIST" 1>&2
    exit 13
fi


# combine all author_handle.json files
#
export SED_PART1='s;^(\s*)("sort_word" : )"(.*)",$;\1"sort_word.'
export SED_PART2='" : [\n\1    {\n\1        \2"\3 '
export SED_PART3='"\n\1    }\n\1],;'
export count=0
echo "{"
for AUTHOR_HANDLE_JSON in $(< "$TMP_AUTHOR_HANDLE_LIST"); do

    # count file
    #
    ((++count))

    # case: not the last file
    #
    # Remove 1st and last lines, and add , (comma) to the end of the last line.
    #
    # We also replace "winning_entry_set" with "winning_entry_set.FILENO" where
    # FILENO is the file number.
    #
    # We also convert where FILENO is the file number and FILENAME is the filename:
    #
    #   "sort_word" : "data",
    #
    # into:
    #
    #   "sort_word.FILENO" : [
    #	    {
    #	        "sort_word" : "data FILENAME"
    #	    }
    #   ],
    #
    if [[ $count -lt $AUTHOR_COUNT ]]; then

	tail -n +2 "$AUTHOR_HANDLE_JSON" |
	  head -n -1 |
	  sed -E -e 's/"winning_entry_set"/"winning_entry_set.'"$count"'"/' \
		 -e "$SED_PART1$count$SED_PART2$AUTHOR_HANDLE_JSON$SED_PART3" \
	         -e '$s/$/,/'

    # case: last file
    #
    else

	tail -n +2 "$AUTHOR_HANDLE_JSON" |
	  head -n -1 |
	  sed -E -e 's/"winning_entry_set"/"winning_entry_set.'"$count"'"/' \
		 -e "$SED_PART1$count$SED_PART2$AUTHOR_HANDLE_JSON$SED_PART3"
	echo '}'

    fi
done


# All Done!!! All Done!!! -- Jessica Noll, Age 2
#
if [[ $EXIT_CODE -ne 0 ]]; then
    echo "$0: Warning: about to exit non-zero: $EXIT_CODE" 1>&2
elif [[ $V_FLAG -ge 1 ]]; then
    echo "$0: debug[1]: about to exit $EXIT_CODE" 1>&2
fi
exit "$EXIT_CODE"