#!/bin/sh
#
# anniv - generate anniversary reminders for agenda.txt
#
# SPDX-FileCopyrightText: 2023 Daniel Kalak
# SPDX-License-Identifier: GPL-3.0-or-later
#
# This program reads lines from stdin and prints lines to stdout,
# sorted. It expects the input lines to be of a format like this:
#
#     John Doe (my best friend) (* 1983-06-21)
#
# These could be the first lines of a group of text files (e.g. with
# contact information) that you could assemble with "head -qn1 *.txt".
# Then, if the current year is 2023, the output would look like this:
#
#     2023-06-21 * John Doe (my best friend) (1983, 40)
#
# If the year specified in the input is 0000 (i.e. if you had
# "0000-06-21" in the example), the last parenthesis in the output (i.e.
# " (1983, 40)" in the example) is omitted. (This is for cases where the
# year is unknown.)
#
# You can specify an arbitrary "current year" and an arbitrary symbol on
# the command line. The symbol needs to be a Basic Regular Expression as
# used by GNU sed. (For example, you could use "+" for deaths or "oo"
# for marriages, etc.) By default, the current year at invocation and
# the symbol "\*" (to symbolize a birthday) are used.
#
# The program only checks if there is a space followed by an opening
# parenthesis (i.e. " (") at some point in an input line, and if that is
# the case, it checks if there is the symbol followed by a space
# followed by an ISO date (e.g. "* 1983-06-21") at some point after that
# parenthesis (but before it is closed, if it ever is). Everything
# before the " (" is treated as the "name", and everything else (other
# than the date) is discarded. This lets you put arbitrary stuff into
# the parenthesis (e.g. multiple dates with different symbols) or after
# it.
#
# This program depends on GNU awk, the GNU coreutils, and GNU sed. It
# exits 0 on success and 1 on bad usage. If it encounters an input line
# that is not in the format specified above, it redirects it to stderr,
# along with a warning; this does not affect the other output lines (on
# stdout) and the program still exits 0.

usage_quit() {
	cat <<- EOF >&2
	Usage: $0 [YEAR [SYMBOL]]
	EOF
	exit 1
}

year="${1:-$(date +%Y)}"
symbol="${2:-\*}"
isodate='[0-9][0-9][0-9][0-9]-[0-9][0-9]-[0-9][0-9]'

case "$year" in
[0-9][0-9][0-9][0-9]) ;;
*) usage_quit ;;
esac

sed '
	s/\(.*\) ([^)]*\('"$symbol"'\) \('"$isodate"'\).*/\3 \2 \1/
	t
	s/^/ERROR/' |

# At this stage in the pipeline, the example input line given above
# would look like "1983-06-21 * John Doe (my best friend)". Faulty input
# lines have a prepended "ERROR" tag (without separators) and are left
# unchanged otherwise.

while read -r line
do
	case "$line" in
	ERROR*) printf 'Wrong input format: %s\n' "${line#ERROR}" >&2 ;;
	*) printf '%s\n' "$line"
	esac
done |

# At this stage in the pipeline, the faulty lines prepended with "ERROR"
# have been redirected to stderr.

awk -v "year=$year" '
{
	birthyear = substr($0, 1, 4)
	sub(birthyear, year)
	if (birthyear != "0000")
		$0 = $0 " (" birthyear ", " year-birthyear ")"
	print
}' |

# At this stage in the pipeline, the "birth" year at the beginning of a
# line has been replaced with the current year, and the " (1983, 40)"
# parenthesis in the example has been appended for all years that are
# not "0000". All that is left to do is to sort.

LC_ALL=C sort