lore

#!/bin/bash
#
# lore.kernel.org commit-or-search to Mutt reader
#
# Copyright (c) 2023 Vitaly Chikunov <vt@altlinux.org>
# SPDX-License-Identifier: GPL-2.0-only

set -euf -o pipefail

dedup=y
search=patchid
unset mode force_mode tags qprefix
muttrc=(-F muttrc)
curlopts=()
sort=threads
sort_aux=last-date
if type -p neomutt >/dev/null; then
	reader=neomutt
else
	reader=mutt
fi

show_help() {
	[ $# -eq 0 ] || echo 2>^1 "Error: argument required"

	cat >&2 <<"EOF"
Usage: lore [options] [commitish or query]

Default search is by patchid of referenced commitish (full threads).
If argument contains ':' it's same as --query specified (no threads).

  -s, --subject    search by commitish's subject line (no threads).
  -q, --query      raw search questy with below query language (no threads).
  -t, --thread     (force) return full threads (it's belong to).
  -r, --results    (force) return of matched results only (no threads).
  -T, --tags       Add -by tags for neomutt (works very slwoly.)
  --reverse        Reverse sort order.

Query language:

  It supports typical AND, OR, NOT, '+', '-' queries present
  in other search engines.

  We also support search prefixes to limit the scope of the
  search to certain fields.

  Prefixes supported in this installation include:

    s:        match within Subject  e.g. s:"a quick brown fox"
    d:        match date-time range, git "approxidate" formats supported
              Open-ended ranges such as `d:last.week..' and
              `d:..2.days.ago' are supported
    b:        match within message body, including text attachments
    nq:       match non-quoted text within message body
    q:        match quoted text within message body
    n:        match filename of attachment(s)
    t:        match within the To header
    c:        match within the Cc header
    f:        match within the From header
    a:        match within the To, Cc, and From headers
    tc:       match within the To and Cc headers
    l:        match contents of the List-Id header
    bs:       match within the Subject and body
    dfn:      match FILENAME from diff
    dfa:      match diff removed (-) lines
    dfb:      match diff added (+) lines
    dfhh:     match diff hunk header context (usually a FUNCTION name)
    dfctx:    match diff context lines
    dfpre:    match pre-image git blob ID
    dfpost:   match post-image git blob ID
    dfblob:   match either pre or post-image git blob ID
    patchid:  match `git patch-id --stable' output
    rt:       match received time, like `d:' if sender's clock was correct

  Most prefixes are probabilistic, meaning they support stemming
  and wildcards ('*').  Ranges (such as 'd:') and boolean prefixes
  do not support stemming or wildcards.
EOF
	exit ${1-0}
}

for opt; do
	shift
	case "$opt" in
		--reader=*) reader=${opt#*=} ;;
		--raw) unset dedup ;;
		-s | --subject | --subj) search=subject ;;
		-q | --query) search=query ;;
		-f | --file) qprefix=dfn: ;;
		-F | --fun*) qprefix=dfhh: ;;
		-t | --thr*) force_mode="x=full+threads" ;;
		-r | --res*) force_mode="z=results+only" ;;
		-T | --tags) tags=y ;;
		-h | --help) show_help ;;
		--insecure) curlopts+=(--insecure) ;;
		--no-muttrc) muttrc=() ;;
		--rev*) sort=reverse-threads ;;
		-*) echo "unknown option: $opt"; exit 1 ;;
		*) set -- "$@" "$opt" ;;
	esac
done

[ $# -ne 0 ] || show_help 1
commit=${1:?committish}

if [[ "$*" =~ : ]]; then
	search=query
elif [ -v qprefix ]; then
	search=query
else
	for dir in . \
		"$HOME/linux/torvalds" \
		"$HOME/src/linux" \
		"$HOME/linux" \
		"$HOME/src/kernel-image" \
		"$HOME/src/qemu"
	do
		cd "$dir" 2>/dev/null || continue
		git cat-file -e "$commit^{commit}" 2>/dev/null && break
	done
fi

commit_info() {
	author=$(    git log --format=%an -n1 "$commit" --)
	aemail=$(    git log --format=%ae -n1 "$commit" --)
	committer=$( git log --format=%cn -n1 "$commit" --)
	commemail=$( git log --format=%ce -n1 "$commit" --)
	subjfn=$(    git log --format=%f  -n1 "$commit" --)
	subj=$(      git log --format=%s  -n1 "$commit" --)
	subjre=${subj//[^[:alnum:]]/.}
}

case "$search" in
	patchid)
		commit_info
		patchid=$(git --no-pager show "$commit" -- | git patch-id --stable)
		patchid=${patchid% *}
		if [ -z "$patchid" ]; then
			objtype=$(git cat-file -t "$commit")
			git cat-file -t "$commit^2" >/dev/null 2>&1 && objtype="merge commit"
			echo >&2 "No patch-id for a $objtype."
			exit 1
		fi
		query="patchid:$patchid"
		mode="x=full+threads"
		;;
	subject)
		commit_info
		query="s:${subj// /+}"
		query="s:$(perl -MURI::Escape -e 'print uri_escape($ARGV[0])' "$subj")"
		query=${query//%20/+}
		mode="z=results+only"
		;;
	query)
		unset committer
		query="$(perl -MURI::Escape -e 'print uri_escape($ARGV[0])' "$*")"
		query=${qprefix-}${query//%20/+}
		mode="z=results+only"
		subjfn=${query//[^[:alnum:]]/_}
		subjre=${*#*:}
		subjre=${subjre//[^[:alnum:]]/.}
		;;
esac
[ -v force_mode ] && mode=$force_mode

tmp=$(mktemp -d --tmpdir lore.XXXXXXXXXX)
cd "$tmp"
echo "+ cd $tmp"
(set -x; curl "${curlopts[@]}" -sS -L -f "https://lore.kernel.org/all/?q=$query&x=m" -d "$mode" -o mbox.gz)
gzip -d mbox.gz
mbox="$subjfn"
if [ -v dedup ] && type -p formail >/dev/null; then
	formail -D 16384 idcache -s < mbox > "$mbox"
else
	mv -- mbox "$mbox"
fi

cat > muttrc <<EOF
set from="$(git config user.email)"
set realname="$(git config user.name)"
set reverse_name
set reverse_realname
set edit_headers
set editor=$EDITOR
set help=no
set envelope_from=yes
alternative_order text/plain text/enriched text/html
ignore *
unignore from date subject to cc message-id resent-from
EOF
if [ -v tags ]; then
	cat >> muttrc <<-EOF
	# Note: index-format-hook slows down scrolling considerably
	  index-format-hook resol "~b^fixes:"          Fixes
	  index-format-hook resol "~b^signed-off-by:"  PATCH
	  index-format-hook resol "~b^acked-by:"       Ack
	  index-format-hook resol "~b^reviewed-by:"    Review
	  index-format-hook resol "~b^tested-by:"      Tested
	set index_format="%4C %Z %[%d/%b/%y %H:%M] %-15.15n %-6@resol@ (%4l%?X?+%X&?) %H %s"
	EOF
else
	cat >> muttrc <<-EOF
	set index_format="%4C %Z %[%d/%b/%y %H:%M] %-15.15n (%4l%?X?+%X&?) %H %s"
	set index_format="%4C %Z %[%Y-%m-%d %H:%M] %-15.15n (%4l%?X?+%X&?) %H %s"
	EOF
fi
cat >> muttrc <<-EOF
set sort=$sort
set sort_aux=$sort_aux

color index_flags cyan     default ~N
color index_date blue      default "~d <1y"
color index_date cyan      default "~d <1m"
color index_date green     default "~d <1w"
color index_date yellow    default "~d <1d"

color hdrdefault brightblack black
color header   yellow      black ^(From):
color header   cyan        black ^(Subject):
color header   green       black ^(To|Cc):
color header   white       black ^(Date):
color header   magenta     black ^(X-Label|X-Maintainer|X-Reviewer):
color signature blue       black
color error    brightred   black
color status   brightwhite blue
color tree     magenta     black
color tilde    brightblack black
color message  cyan        black
color markers  cyan        black
color attachment brightgreen black
color search   black       red
color quoted   brightblue  black
color quoted1  yellow      black
color quoted2  red         black
color quoted3  green       black
color quoted4  cyan        black
color quoted5  blue        black
color quoted6  yellow      black
color quoted7  red         black
color quoted8  green       black
color quoted9  cyan        black
color body     green       default "^diff \-.*"
color body     green       default "^index [a-f0-9].*"
color body     green       default "^\-\-\- .*"
color body     green       default "^[\+]{3} .*"
color body     cyan        default "^[\+][^\+]+.*"
color body     red         default "^\-[^\-]+.*"
color body     brightblue  default "^@@ .*"
color index_subject brightyellow default "~s '$subjre'"
EOF
if [ -v committer ]; then
	cat >> muttrc <<-EOF
	color index_author  brightgreen  default "~f '$committer'"
	color index_author  brightgreen  default "~f '$commemail'"
	color index_author  brightyellow default "~f '$author'"
	color index_author  brightyellow default "~f '$aemail'"
	EOF
fi
$reader "${muttrc[@]}" -f $mbox
echo >&2 cd $tmp
exit 1
rm -rf "$tmp"