[bpt/emacs.git] / lib-src / rcs2log

#! /bin/sh

# RCS to ChangeLog generator

# Generate a change log prefix from RCS files (perhaps in the CVS repository)
# and the ChangeLog (if any).
# Output the new prefix to standard output.
# You can edit this prefix by hand, and then prepend it to ChangeLog.

# Ignore log entries that start with `#'.
# Clump together log entries that start with `{topic} ',
# where `topic' contains neither white space nor `}'.

Help='The default FILEs are the files registered under the working directory.
Options:

  -c CHANGELOG  Output a change log prefix to CHANGELOG (default ChangeLog).
  -h HOSTNAME  Use HOSTNAME in change log entries (default current host).
  -i INDENT  Indent change log lines by INDENT spaces (default 8).
  -l LENGTH  Try to limit log lines to LENGTH characters (default 79).
  -R  If no FILEs are given and RCS is used, recurse through working directory.
  -r OPTION  Pass OPTION to subsidiary log command.
  -t TABWIDTH  Tab stops are every TABWIDTH characters (default 8).
  -u "LOGIN<tab>FULLNAME<tab>MAILADDR"  Assume LOGIN has FULLNAME and MAILADDR.
  -v  Append RCS revision to file names in log lines.
  --help  Output help.
  --version  Output version number.

Report bugs to <bug-gnu-emacs@gnu.org>.'

Id='$Id: rcs2log,v 1.46 2001/01/03 12:04:06 gerd Exp $'

# Copyright 1992, 93, 94, 95, 96, 97, 1998, 2001
#  Free Software Foundation, Inc.

# This program 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 2, or (at your option)
# any later version.
#
# This program 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.
#
# You should have received a copy of the GNU General Public License
# along with this program; see the file COPYING.  If not, write to the
# Free Software Foundation, Inc., 59 Temple Place - Suite 330,
# Boston, MA 02111-1307, USA.

Copyright='Copyright 1998 Free Software Foundation, Inc.
This program comes with NO WARRANTY, to the extent permitted by law.
You may redistribute copies of this program
under the terms of the GNU General Public License.
For more information about these matters, see the files named COPYING.
Author: Paul Eggert <eggert@twinsun.com>'

tab='	'
nl='
'

# Parse options.

# defaults
: ${AWK=awk}
: ${TMPDIR=/tmp}
changelog=ChangeLog # change log file name
datearg= # rlog date option
hostname= # name of local host (if empty, will deduce it later)
indent=8 # indent of log line
length=79 # suggested max width of log line
logins= # login names for people we know fullnames and mailaddrs of
loginFullnameMailaddrs= # login<tab>fullname<tab>mailaddr triplets
logTZ= # time zone for log dates (if empty, use local time)
recursive= # t if we want recursive rlog
revision= # t if we want revision numbers
rlog_options= # options to pass to rlog
tabwidth=8 # width of horizontal tab

while :
do
	case $1 in
	-c)	changelog=${2?}; shift;;
	-i)	indent=${2?}; shift;;
	-h)	hostname=${2?}; shift;;
	-l)	length=${2?}; shift;;
	-[nu])	# -n is obsolescent; it is replaced by -u.
		case $1 in
		-n)	case ${2?}${3?}${4?} in
			*"$tab"* | *"$nl"*)
				echo >&2 "$0: -n '$2' '$3' '$4': tabs, newlines not allowed"
				exit 1
			esac
			case $loginFullnameMailaddrs in
			'') loginFullnameMailaddrs=$2$tab$3$tab$4;;
			?*) loginFullnameMailaddrs=$loginFullnameMailaddrs$nl$2$tab$3$tab$4
			esac
			shift; shift; shift;;
		-u)
			# If $2 is not tab-separated, use colon for separator.
			case ${2?} in
			*"$nl"*)
				echo >&2 "$0: -u '$2': newlines not allowed"
				exit 1;;
			*"$tab"*)
				t=$tab;;
			*)
				t=:
			esac
			case $2 in
			*"$t"*"$t"*"$t"*)
				echo >&2 "$0: -u '$2': too many fields"
				exit 1;;
			*"$t"*"$t"*)
				;;
			*)
				echo >&2 "$0: -u '$2': not enough fields"
				exit 1
			esac
			case $loginFullnameMailaddrs in
			'') loginFullnameMailaddrs=$2;;
			?*) loginFullnameMailaddrs=$loginFullnameMailaddrs$nl$2
			esac
			shift
		esac
		case $logins in
		'') logins=$login;;
		?*) logins=$logins$nl$login
		esac
		;;
	-r)
		case $rlog_options in
		'') rlog_options=${2?};;
		?*) rlog_options=$rlog_options$nl${2?}
		esac
		shift;;
	-R)	recursive=t;;
	-t)	tabwidth=${2?}; shift;;
	-v)	revision=t;;
	--version)
		set $Id
		rcs2logVersion=$3
		echo >&2 "rcs2log (GNU Emacs) $rcs2logVersion$nl$Copyright"
		exit 0;;
	-*)	echo >&2 "Usage: $0 [OPTION]... [FILE ...]$nl$Help"
		case $1 in
		--help) exit 0;;
		*) exit 1
		esac;;
	*)	break
	esac
	shift
done

month_data='
	m[0]="Jan"; m[1]="Feb"; m[2]="Mar"
	m[3]="Apr"; m[4]="May"; m[5]="Jun"
	m[6]="Jul"; m[7]="Aug"; m[8]="Sep"
	m[9]="Oct"; m[10]="Nov"; m[11]="Dec"
'


# Put rlog output into $rlogout.

# If no rlog options are given,
# log the revisions checked in since the first ChangeLog entry.
# Since ChangeLog is only by date, some of these revisions may be duplicates of
# what's already in ChangeLog; it's the user's responsibility to remove them.
case $rlog_options in
'')
	if test -s "$changelog"
	then
		e='
			/^[0-9]+-[0-9][0-9]-[0-9][0-9]/{
				# ISO 8601 date
				print $1
				exit
			}
			/^... ... [ 0-9][0-9] [ 0-9][0-9]:[0-9][0-9]:[0-9][0-9] [0-9]+ /{
				# old-fashioned date and time (Emacs 19.31 and earlier)
				'"$month_data"'
				year = $5
				for (i=0; i<=11; i++) if (m[i] == $2) break
				dd = $3
				printf "%d-%02d-%02d\n", year, i+1, dd
				exit
			}
		'
		d=`$AWK "$e" <"$changelog"` || exit
		case $d in
		?*) datearg="-d>$d"
		esac
	fi
esac

# Use TZ specified by ChangeLog local variable, if any.
if test -s "$changelog"
then
	extractTZ='
		/^.*change-log-time-zone-rule['"$tab"' ]*:['"$tab"' ]*"\([^"]*\)".*/{
			s//\1/; p; q
		}
		/^.*change-log-time-zone-rule['"$tab"' ]*:['"$tab"' ]*t.*/{
			s//UTC0/; p; q
		}
	'
	logTZ=`tail "$changelog" | sed -n "$extractTZ"`
	case $logTZ in
	?*) TZ=$logTZ; export TZ
	esac
fi

# If CVS is in use, examine its repository, not the normal RCS files.
if test ! -f CVS/Repository
then
	rlog=rlog
	repository=
else
	rlog='cvs -q log'
	repository=`sed 1q <CVS/Repository` || exit
	test ! -f CVS/Root || CVSROOT=`cat <CVS/Root` || exit
	case $CVSROOT in
	*:/*)
		# remote repository
		;;
	*)
		# local repository
		case $repository in
		/*) ;;
		*) repository=${CVSROOT?}/$repository
		esac
		if test ! -d "$repository"
		then
			echo >&2 "$0: $repository: bad repository (see CVS/Repository)"
			exit 1
		fi
	esac
fi

# Use $rlog's -zLT option, if $rlog supports it.
case `$rlog -zLT 2>&1` in
*' option'*) ;;
*)
	case $rlog_options in
	'') rlog_options=-zLT;;
	?*) rlog_options=-zLT$nl$rlog_options
	esac
esac

# With no arguments, examine all files under the RCS directory.
case $# in
0)
	case $repository in
	'')
		oldIFS=$IFS
		IFS=$nl
		case $recursive in
		t)
			RCSdirs=`find . -name RCS -type d -print`
			filesFromRCSfiles='s|,v$||; s|/RCS/|/|; s|^\./||'
			files=`
				{
					case $RCSdirs in
					?*) find $RCSdirs \
							-type f \
							! -name '*_' \
							! -name ',*,' \
							! -name '.*_' \
							! -name .rcsfreeze.log \
							! -name .rcsfreeze.ver \
							-print
					esac
					find . -name '*,v' -print
				} |
				sort -u |
				sed "$filesFromRCSfiles"
			`;;
		*)
			files=
			for file in RCS/.* RCS/* .*,v *,v
			do
				case $file in
				RCS/. | RCS/.. | RCS/,*, | RCS/*_) continue;;
				RCS/.rcsfreeze.log | RCS/.rcsfreeze.ver) continue;;
				RCS/.\* | RCS/\* | .\*,v | \*,v) test -f "$file" || continue;;
				RCS/*,v | RCS/.*,v) ;;
				RCS/* | RCS/.*) test -f "$file" || continue
				esac
				case $files in
				'') files=$file;;
				?*) files=$files$nl$file
				esac
			done
			case $files in
			'') exit 0
			esac
		esac
		set x $files
		shift
		IFS=$oldIFS
	esac
esac

logdir=$TMPDIR/rcs2log$$
llogout=$logdir/l
rlogout=$logdir/r
trap exit 1 2 13 15
trap "rm -fr $logdir 2>/dev/null" 0
(umask 077 && exec mkdir $logdir) || exit

case $datearg in
?*) $rlog $rlog_options "$datearg" ${1+"$@"} >$rlogout;;
'') $rlog $rlog_options ${1+"$@"} >$rlogout
esac || exit


# Get the full name of each author the logs mention, and set initialize_fullname
# to awk code that initializes the `fullname' awk associative array.
# Warning: foreign authors (i.e. not known in the passwd file) are mishandled;
# you have to fix the resulting output by hand.

initialize_fullname=
initialize_mailaddr=

case $loginFullnameMailaddrs in
?*)
	case $loginFullnameMailaddrs in
	*\"* | *\\*)
		sed 's/["\\]/\\&/g' >$llogout <<EOF || exit
$loginFullnameMailaddrs
EOF
		loginFullnameMailaddrs=`cat $llogout`
	esac

	oldIFS=$IFS
	IFS=$nl
	for loginFullnameMailaddr in $loginFullnameMailaddrs
	do
		case $loginFullnameMailaddr in
		*"$tab"*) IFS=$tab;;
		*) IFS=:
		esac
		set x $loginFullnameMailaddr
		login=$2
		fullname=$3
		mailaddr=$4
		initialize_fullname="$initialize_fullname
			fullname[\"$login\"] = \"$fullname\""
		initialize_mailaddr="$initialize_mailaddr
			mailaddr[\"$login\"] = \"$mailaddr\""
	done
	IFS=$oldIFS
esac

case $llogout in
?*) sort -u -o $llogout <<EOF || exit
$logins
EOF
esac
output_authors='/^date: / {
	if ($2 ~ /^[0-9]*[-\/][0-9][0-9][-\/][0-9][0-9]$/ && $3 ~ /^[0-9][0-9]:[0-9][0-9]:[0-9][0-9][-+0-9:]*;$/ && $4 == "author:" && $5 ~ /^[^;]*;$/) {
		print substr($5, 1, length($5)-1)
	}
}'
authors=`
	$AWK "$output_authors" <$rlogout |
	case $llogout in
	'') sort -u;;
	?*) sort -u | comm -23 - $llogout
	esac
`
case $authors in
?*)
	cat >$llogout <<EOF || exit
$authors
EOF
	initialize_author_script='s/["\\]/\\&/g; s/.*/author[\"&\"] = 1/'
	initialize_author=`sed -e "$initialize_author_script" <$llogout`
	awkscript='
		BEGIN {
			alphabet = "abcdefghijklmnopqrstuvwxyz"
			ALPHABET = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
			'"$initialize_author"'
		}
		{
			if (author[$1]) {
				fullname = $5
				if (fullname ~ /[0-9]+-[^(]*\([0-9]+\)$/) {
					# Remove the junk from fullnames like "0000-Admin(0000)".
					fullname = substr(fullname, index(fullname, "-") + 1)
					fullname = substr(fullname, 1, index(fullname, "(") - 1)
				}
				if (fullname ~ /,[^ ]/) {
					# Some sites put comma-separated junk after the fullname.
					# Remove it, but leave "Bill Gates, Jr" alone.
					fullname = substr(fullname, 1, index(fullname, ",") - 1)
				}
				abbr = index(fullname, "&")
				if (abbr) {
					a = substr($1, 1, 1)
					A = a
					i = index(alphabet, a)
					if (i) A = substr(ALPHABET, i, 1)
					fullname = substr(fullname, 1, abbr-1) A substr($1, 2) substr(fullname, abbr+1)
				}

				# Quote quotes and backslashes properly in full names.
				# Do not use gsub; traditional awk lacks it.
				quoted = ""
				rest = fullname
				for (;;) {
					p = index(rest, "\\")
					q = index(rest, "\"")
					if (p) {
						if (q && q<p) p = q
					} else {
						if (!q) break
						p = q
					}
					quoted = quoted substr(rest, 1, p-1) "\\" substr(rest, p, 1)
					rest = substr(rest, p+1)
				}

				printf "fullname[\"%s\"] = \"%s%s\"\n", $1, quoted, rest
				author[$1] = 0
			}
		}
	'

	initialize_fullname=`
		{
			(getent passwd $authors) ||
			(
				cat /etc/passwd
				for author in $authors
				do NIS_PATH= nismatch $author passwd.org_dir
				done
				ypmatch $authors passwd
			)
		} 2>/dev/null |
		$AWK -F: "$awkscript"
	`$initialize_fullname
esac


# Function to print a single log line.
# We don't use awk functions, to stay compatible with old awk versions.
# `Log' is the log message (with \n replaced by \001).
# `files' contains the affected files.
printlogline='{

	# Following the GNU coding standards, rewrite
	#	* file: (function): comment
	# to
	#	* file (function): comment
	if (Log ~ /^\([^)]*\): /) {
		i = index(Log, ")")
		files = files " " substr(Log, 1, i)
		Log = substr(Log, i+3)
	}

	# If "label: comment" is too long, break the line after the ":".
	sep = " "
	if ('"$length"' <= '"$indent"' + 1 + length(files) + index(Log, SOH)) sep = "\n" indent_string

	# Print the label.
	printf "%s*%s:", indent_string, files

	# Print each line of the log, transliterating \001 to \n.
	while ((i = index(Log, SOH)) != 0) {
		logline = substr(Log, 1, i-1)
		if (logline ~ /[^'"$tab"' ]/) {
			printf "%s%s\n", sep, logline
		} else {
			print ""
		}
		sep = indent_string
		Log = substr(Log, i+1)
	}
}'

# Pattern to match the `revision' line of rlog output.
rlog_revision_pattern='^revision [0-9]+\.[0-9]+(\.[0-9]+\.[0-9]+)*(['"$tab"' ]+locked by: [^'"$tab"' $,.0-9:;@]*[^'"$tab"' $,:;@][^'"$tab"' $,.0-9:;@]*;)?['"$tab"' ]*$'

case $hostname in
'')
	hostname=`(
		hostname || uname -n || uuname -l || cat /etc/whoami
	) 2>/dev/null` || {
		echo >&2 "$0: cannot deduce hostname"
		exit 1
	}

	case $hostname in
	*.*) ;;
	*)
		domainname=`(domainname) 2>/dev/null` &&
		case $domainname in
		*.*) hostname=$hostname.$domainname
		esac
	esac
esac


# Process the rlog output, generating ChangeLog style entries.

# First, reformat the rlog output so that each line contains one log entry.
# Transliterate \n to \001 so that multiline entries fit on a single line.
# Discard irrelevant rlog output.
$AWK <$rlogout '
	BEGIN { repository = "'"$repository"'" }
	/^RCS file:/ {
		if (repository != "") {
			filename = $3
			if (substr(filename, 1, length(repository) + 1) == repository "/") {
				filename = substr(filename, length(repository) + 2)
			}
			if (filename ~ /,v$/) {
				filename = substr(filename, 1, length(filename) - 2)
			}
			if (filename ~ /(^|\/)Attic\/[^\/]*$/) {
				i = length(filename)
				while (substr(filename, i, 1) != "/") i--
				filename = substr(filename, 1, i - 6) substr(filename, i + 1)
			}
		}
		rev = "?"
	}
	/^Working file:/ { if (repository == "") filename = $3 }
	/'"$rlog_revision_pattern"'/, /^(-----------*|===========*)$/ {
		line = $0
		if (line ~ /'"$rlog_revision_pattern"'/) {
			rev = $2
			next
		}
		if (line ~ /^date: [0-9][- +\/0-9:]*;/) {
			date = $2
			if (date ~ /\//) {
				# This is a traditional RCS format date YYYY/MM/DD.
				# Replace "/"s with "-"s to get ISO format.
				newdate = ""
				while ((i = index(date, "/")) != 0) {
					newdate = newdate substr(date, 1, i-1) "-"
					date = substr(date, i+1)
				}
				date = newdate date
			}
			time = substr($3, 1, length($3) - 1)
			author = substr($5, 1, length($5)-1)
			printf "%s %s %s %s %s %c", filename, rev, date, time, author, 1
			rev = "?"
			next
		}
		if (line ~ /^branches: /) { next }
		if (line ~ /^(-----------*|===========*)$/) { print ""; next }
		if (line == "Initial revision" || line ~ /^file .+ was initially added on branch .+\.$/) {
			line = "New file."
		}
		printf "%s%c", line, 1
	}
' |

# Now each line is of the form
# FILENAME REVISION YYYY-MM-DD HH:MM:SS[+-TIMEZONE] AUTHOR \001LOG
#	where \001 stands for a carriage return,
#	and each line of the log is terminated by \001 instead of \n.
# Sort the log entries, first by date+time (in reverse order),
# then by author, then by log entry, and finally by file name and revision
# (just in case).
sort +2 -4r +4 +0 |

# Finally, reformat the sorted log entries.
$AWK '
	BEGIN {
		logTZ = "'"$logTZ"'"
		revision = "'"$revision"'"

		# Some awk variants do not understand "\001", so we have to
		# put the char directly in the file.
		SOH="\ 1" # <-- There is a single SOH (octal code 001) here.

		# Initialize the fullname and mailaddr associative arrays.
		'"$initialize_fullname"'
		'"$initialize_mailaddr"'

		# Initialize indent string.
		indent_string = ""
		i = '"$indent"'
		if (0 < '"$tabwidth"')
			for (;  '"$tabwidth"' <= i;  i -= '"$tabwidth"')
				indent_string = indent_string "\t"
		while (1 <= i--)
			indent_string = indent_string " "
	}

	{
		newlog = substr($0, 1 + index($0, SOH))

		# Ignore log entries prefixed by "#".
		if (newlog ~ /^#/) { next }

		if (Log != newlog || date != $3 || author != $5) {

			# The previous log and this log differ.

			# Print the old log.
			if (date != "") '"$printlogline"'

			# Logs that begin with "{clumpname} " should be grouped together,
			# and the clumpname should be removed.
			# Extract the new clumpname from the log header,
			# and use it to decide whether to output a blank line.
			newclumpname = ""
			sep = "\n"
			if (date == "") sep = ""
			if (newlog ~ /^\{[^'"$tab"' }]*}['"$tab"' ]/) {
				i = index(newlog, "}")
				newclumpname = substr(newlog, 1, i)
				while (substr(newlog, i+1) ~ /^['"$tab"' ]/) i++
				newlog = substr(newlog, i+1)
				if (clumpname == newclumpname) sep = ""
			}
			printf sep
			clumpname = newclumpname

			# Get ready for the next log.
			Log = newlog
			if (files != "")
				for (i in filesknown)
					filesknown[i] = 0
			files = ""
		}
		if (date != $3  ||  author != $5) {
			# The previous date+author and this date+author differ.
			# Print the new one.
			date = $3
			time = $4
			author = $5

			zone = ""
			if (logTZ && ((i = index(time, "-")) || (i = index(time, "+"))))
				zone = " " substr(time, i)

			# Print "date[ timezone]  fullname  <email address>".
			# Get fullname and email address from associative arrays;
			# default to author and author@hostname if not in arrays.
			if (fullname[author])
				auth = fullname[author]
			else
				auth = author
			printf "%s%s  %s  ", date, zone, auth
			if (mailaddr[author])
				printf "<%s>\n\n", mailaddr[author]
			else
				printf "<%s@%s>\n\n", author, "'"$hostname"'"
		}
		if (! filesknown[$1]) {
			filesknown[$1] = 1
			if (files == "") files = " " $1
			else files = files ", " $1
			if (revision && $2 != "?") files = files " " $2
		}
	}
	END {
		# Print the last log.
		if (date != "") {
			'"$printlogline"'
			printf "\n"
		}
	}
' &&


# Exit successfully.

exec rm -fr $logdir

# Local Variables:
# tab-width:4
# End:
Commit	Line	Data
daecaf5d GM	1	#! /bin/sh
	2
	3	# RCS to ChangeLog generator
	4
	5	# Generate a change log prefix from RCS files (perhaps in the CVS repository)
	6	# and the ChangeLog (if any).
	7	# Output the new prefix to standard output.
	8	# You can edit this prefix by hand, and then prepend it to ChangeLog.
	9
	10	# Ignore log entries that start with `#'.
	11	# Clump together log entries that start with `{topic} ',
	12	# where `topic' contains neither white space nor `}'.
	13
	14	Help='The default FILEs are the files registered under the working directory.
	15	Options:
	16
	17	-c CHANGELOG Output a change log prefix to CHANGELOG (default ChangeLog).
	18	-h HOSTNAME Use HOSTNAME in change log entries (default current host).
	19	-i INDENT Indent change log lines by INDENT spaces (default 8).
	20	-l LENGTH Try to limit log lines to LENGTH characters (default 79).
	21	-R If no FILEs are given and RCS is used, recurse through working directory.
	22	-r OPTION Pass OPTION to subsidiary log command.
	23	-t TABWIDTH Tab stops are every TABWIDTH characters (default 8).
	24	-u "LOGIN<tab>FULLNAME<tab>MAILADDR" Assume LOGIN has FULLNAME and MAILADDR.
	25	-v Append RCS revision to file names in log lines.
	26	--help Output help.
	27	--version Output version number.
	28
	29	Report bugs to <bug-gnu-emacs@gnu.org>.'
	30
	31	Id='$Id: rcs2log,v 1.46 2001/01/03 12:04:06 gerd Exp $'
	32
	33	# Copyright 1992, 93, 94, 95, 96, 97, 1998, 2001
	34	# Free Software Foundation, Inc.
	35
	36	# This program is free software; you can redistribute it and/or modify
	37	# it under the terms of the GNU General Public License as published by
	38	# the Free Software Foundation; either version 2, or (at your option)
	39	# any later version.
	40	#
	41	# This program is distributed in the hope that it will be useful,
	42	# but WITHOUT ANY WARRANTY; without even the implied warranty of
	43	# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
	44	# GNU General Public License for more details.
	45	#
	46	# You should have received a copy of the GNU General Public License
	47	# along with this program; see the file COPYING. If not, write to the
	48	# Free Software Foundation, Inc., 59 Temple Place - Suite 330,
	49	# Boston, MA 02111-1307, USA.
	50
	51	Copyright='Copyright 1998 Free Software Foundation, Inc.
	52	This program comes with NO WARRANTY, to the extent permitted by law.
	53	You may redistribute copies of this program
	54	under the terms of the GNU General Public License.
	55	For more information about these matters, see the files named COPYING.
	56	Author: Paul Eggert <eggert@twinsun.com>'
	57
	58	tab=' '
	59	nl='
	60	'
	61
	62	# Parse options.
	63
	64	# defaults
65	: ${AWK=awk}
66	: ${TMPDIR=/tmp}
67	changelog=ChangeLog # change log file name
68	datearg= # rlog date option
69	hostname= # name of local host (if empty, will deduce it later)
70	indent=8 # indent of log line
71	length=79 # suggested max width of log line
72	logins= # login names for people we know fullnames and mailaddrs of
73	loginFullnameMailaddrs= # login<tab>fullname<tab>mailaddr triplets
74	logTZ= # time zone for log dates (if empty, use local time)
75	recursive= # t if we want recursive rlog
76	revision= # t if we want revision numbers
77	rlog_options= # options to pass to rlog
78	tabwidth=8 # width of horizontal tab
79
80	while :
81	do
82	case $1 in
83	-c) changelog=${2?}; shift;;
84	-i) indent=${2?}; shift;;
85	-h) hostname=${2?}; shift;;
86	-l) length=${2?}; shift;;
87	-[nu]) # -n is obsolescent; it is replaced by -u.
88	case $1 in
89	-n) case ${2?}${3?}${4?} in
90	"$tab" \| "$nl")
91	echo >&2 "$0: -n '$2' '$3' '$4': tabs, newlines not allowed"
92	exit 1
93	esac
94	case $loginFullnameMailaddrs in
95	'') loginFullnameMailaddrs=$2$tab$3$tab$4;;
96	?*) loginFullnameMailaddrs=$loginFullnameMailaddrs$nl$2$tab$3$tab$4
97	esac
98	shift; shift; shift;;
99	-u)
100	# If $2 is not tab-separated, use colon for separator.
101	case ${2?} in
102	"$nl")
103	echo >&2 "$0: -u '$2': newlines not allowed"
104	exit 1;;
105	"$tab")
106	t=$tab;;
107	*)
108	t=:
109	esac
110	case $2 in
111	"$t""$t""$t")
112	echo >&2 "$0: -u '$2': too many fields"
113	exit 1;;
114	"$t""$t"*)
115	;;
116	*)
117	echo >&2 "$0: -u '$2': not enough fields"
118	exit 1
119	esac
120	case $loginFullnameMailaddrs in
121	'') loginFullnameMailaddrs=$2;;
122	?*) loginFullnameMailaddrs=$loginFullnameMailaddrs$nl$2
123	esac
124	shift
125	esac
126	case $logins in
127	'') logins=$login;;
128	?*) logins=$logins$nl$login
129	esac
130	;;
131	-r)
132	case $rlog_options in
133	'') rlog_options=${2?};;
134	?*) rlog_options=$rlog_options$nl${2?}
135	esac
136	shift;;
137	-R) recursive=t;;
138	-t) tabwidth=${2?}; shift;;
139	-v) revision=t;;
140	--version)
141	set $Id
142	rcs2logVersion=$3
143	echo >&2 "rcs2log (GNU Emacs) $rcs2logVersion$nl$Copyright"
144	exit 0;;
145	-*) echo >&2 "Usage: $0 [OPTION]... [FILE ...]$nl$Help"
146	case $1 in
147	--help) exit 0;;
148	*) exit 1
149	esac;;
150	*) break
151	esac
152	shift
153	done
154
155	month_data='
156	m[0]="Jan"; m[1]="Feb"; m[2]="Mar"
157	m[3]="Apr"; m[4]="May"; m[5]="Jun"
158	m[6]="Jul"; m[7]="Aug"; m[8]="Sep"
159	m[9]="Oct"; m[10]="Nov"; m[11]="Dec"
160	'
161
162
163	# Put rlog output into $rlogout.
164
165	# If no rlog options are given,
166	# log the revisions checked in since the first ChangeLog entry.
167	# Since ChangeLog is only by date, some of these revisions may be duplicates of
168	# what's already in ChangeLog; it's the user's responsibility to remove them.
169	case $rlog_options in
170	'')
171	if test -s "$changelog"
172	then
173	e='
174	/^[0-9]+-[0-9][0-9]-[0-9][0-9]/{
175	# ISO 8601 date
176	print $1
177	exit
178	}
179	/^... ... [ 0-9][0-9] [ 0-9][0-9]:[0-9][0-9]:[0-9][0-9] [0-9]+ /{
180	# old-fashioned date and time (Emacs 19.31 and earlier)
181	'"$month_data"'
182	year = $5
183	for (i=0; i<=11; i++) if (m[i] == $2) break
184	dd = $3
185	printf "%d-%02d-%02d\n", year, i+1, dd
186	exit
187	}
188	'
189	d=`$AWK "$e" <"$changelog"` \|\| exit
190	case $d in
191	?*) datearg="-d>$d"
192	esac
193	fi
194	esac
195
196	# Use TZ specified by ChangeLog local variable, if any.
197	if test -s "$changelog"
198	then
199	extractTZ='
200	/^.change-log-time-zone-rule['"$tab"' ]:['"$tab"' ]"\([^"]\)".*/{
201	s//\1/; p; q
202	}
203	/^.change-log-time-zone-rule['"$tab"' ]:['"$tab"' ]t./{
204	s//UTC0/; p; q
205	}
206	'
207	logTZ=`tail "$changelog" \| sed -n "$extractTZ"`
208	case $logTZ in
209	?*) TZ=$logTZ; export TZ
210	esac
211	fi
212
213	# If CVS is in use, examine its repository, not the normal RCS files.
214	if test ! -f CVS/Repository
215	then
216	rlog=rlog
217	repository=
218	else
219	rlog='cvs -q log'
220	repository=`sed 1q <CVS/Repository` \|\| exit
221	test ! -f CVS/Root \|\| CVSROOT=`cat <CVS/Root` \|\| exit
222	case $CVSROOT in
223	:/)
224	# remote repository
225	;;
226	*)
227	# local repository
228	case $repository in
229	/*) ;;
230	*) repository=${CVSROOT?}/$repository
231	esac
232	if test ! -d "$repository"
233	then
234	echo >&2 "$0: $repository: bad repository (see CVS/Repository)"
235	exit 1
236	fi
237	esac
238	fi
239
240	# Use $rlog's -zLT option, if $rlog supports it.
241	case `$rlog -zLT 2>&1` in
242	' option') ;;
243	*)
244	case $rlog_options in
245	'') rlog_options=-zLT;;
246	?*) rlog_options=-zLT$nl$rlog_options
247	esac
248	esac
249
250	# With no arguments, examine all files under the RCS directory.
251	case $# in
252	0)
253	case $repository in
254	'')
255	oldIFS=$IFS
256	IFS=$nl
257	case $recursive in
258	t)
259	RCSdirs=`find . -name RCS -type d -print`
260	filesFromRCSfiles='s\|,v$\|\|; s\|/RCS/\|/\|; s\|^\./\|\|'
261	files=`
262	{
263	case $RCSdirs in
264	?*) find $RCSdirs \
265	-type f \
266	! -name '*_' \
267	! -name ',*,' \
268	! -name '.*_' \
269	! -name .rcsfreeze.log \
270	! -name .rcsfreeze.ver \
271	-print
272	esac
273	find . -name '*,v' -print
274	} \|
275	sort -u \|
276	sed "$filesFromRCSfiles"
277	`;;
278	*)
279	files=
280	for file in RCS/.* RCS/* .,v ,v
281	do
282	case $file in
283	RCS/. \| RCS/.. \| RCS/,, \| RCS/_) continue;;
284	RCS/.rcsfreeze.log \| RCS/.rcsfreeze.ver) continue;;
285	RCS/.\* \| RCS/\* \| .\,v \| \,v) test -f "$file" \|\| continue;;
286	RCS/,v \| RCS/.,v) ;;
287	RCS/* \| RCS/.*) test -f "$file" \|\| continue
288	esac
289	case $files in
290	'') files=$file;;
291	?*) files=$files$nl$file
292	esac
293	done
294	case $files in
295	'') exit 0
296	esac
297	esac
298	set x $files
299	shift
300	IFS=$oldIFS
301	esac
302	esac
303
304	logdir=$TMPDIR/rcs2log$$
305	llogout=$logdir/l
306	rlogout=$logdir/r
307	trap exit 1 2 13 15
308	trap "rm -fr $logdir 2>/dev/null" 0
309	(umask 077 && exec mkdir $logdir) \|\| exit
310
311	case $datearg in
312	?*) $rlog $rlog_options "$datearg" ${1+"$@"} >$rlogout;;
313	'') $rlog $rlog_options ${1+"$@"} >$rlogout
314	esac \|\| exit
315
316
317	# Get the full name of each author the logs mention, and set initialize_fullname
318	# to awk code that initializes the `fullname' awk associative array.
319	# Warning: foreign authors (i.e. not known in the passwd file) are mishandled;
320	# you have to fix the resulting output by hand.
321
322	initialize_fullname=
323	initialize_mailaddr=
324
325	case $loginFullnameMailaddrs in
326	?*)
327	case $loginFullnameMailaddrs in
328	\" \| \\)
329	sed 's/["\\]/\\&/g' >$llogout <<EOF \|\| exit
330	$loginFullnameMailaddrs
331	EOF
332	loginFullnameMailaddrs=`cat $llogout`
333	esac
334
335	oldIFS=$IFS
336	IFS=$nl
337	for loginFullnameMailaddr in $loginFullnameMailaddrs
338	do
339	case $loginFullnameMailaddr in
340	"$tab") IFS=$tab;;
341	*) IFS=:
342	esac
343	set x $loginFullnameMailaddr
344	login=$2
345	fullname=$3
346	mailaddr=$4
347	initialize_fullname="$initialize_fullname
348	fullname[\"$login\"] = \"$fullname\""
349	initialize_mailaddr="$initialize_mailaddr
350	mailaddr[\"$login\"] = \"$mailaddr\""
351	done
352	IFS=$oldIFS
353	esac
354
355	case $llogout in
356	?*) sort -u -o $llogout <<EOF \|\| exit
357	$logins
358	EOF
359	esac
360	output_authors='/^date: / {
361	if ($2 ~ /^[0-9][-\/][0-9][0-9][-\/][0-9][0-9]$/ && $3 ~ /^[0-9][0-9]:[0-9][0-9]:[0-9][0-9][-+0-9:];$/ && $4 == "author:" && $5 ~ /^[^;]*;$/) {
362	print substr($5, 1, length($5)-1)
363	}
364	}'
365	authors=`
366	$AWK "$output_authors" <$rlogout \|
367	case $llogout in
368	'') sort -u;;
369	?*) sort -u \| comm -23 - $llogout
370	esac
371	`
372	case $authors in
373	?*)
374	cat >$llogout <<EOF \|\| exit
375	$authors
376	EOF
377	initialize_author_script='s/["\\]/\\&/g; s/.*/author[\"&\"] = 1/'
378	initialize_author=`sed -e "$initialize_author_script" <$llogout`
379	awkscript='
380	BEGIN {
381	alphabet = "abcdefghijklmnopqrstuvwxyz"
382	ALPHABET = "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
383	'"$initialize_author"'
384	}
385	{
386	if (author[$1]) {
387	fullname = $5
388	if (fullname ~ /[0-9]+-[^(]*\([0-9]+\)$/) {
389	# Remove the junk from fullnames like "0000-Admin(0000)".
390	fullname = substr(fullname, index(fullname, "-") + 1)
391	fullname = substr(fullname, 1, index(fullname, "(") - 1)
392	}
393	if (fullname ~ /,[^ ]/) {
394	# Some sites put comma-separated junk after the fullname.
395	# Remove it, but leave "Bill Gates, Jr" alone.
396	fullname = substr(fullname, 1, index(fullname, ",") - 1)
397	}
398	abbr = index(fullname, "&")
399	if (abbr) {
400	a = substr($1, 1, 1)
401	A = a
402	i = index(alphabet, a)
403	if (i) A = substr(ALPHABET, i, 1)
404	fullname = substr(fullname, 1, abbr-1) A substr($1, 2) substr(fullname, abbr+1)
405	}
406
407	# Quote quotes and backslashes properly in full names.
408	# Do not use gsub; traditional awk lacks it.
409	quoted = ""
410	rest = fullname
411	for (;;) {
412	p = index(rest, "\\")
413	q = index(rest, "\"")
414	if (p) {
415	if (q && q<p) p = q
416	} else {
417	if (!q) break
418	p = q
419	}
420	quoted = quoted substr(rest, 1, p-1) "\\" substr(rest, p, 1)
421	rest = substr(rest, p+1)
422	}
423
424	printf "fullname[\"%s\"] = \"%s%s\"\n", $1, quoted, rest
425	author[$1] = 0
426	}
427	}
428	'
429
430	initialize_fullname=`
431	{
432	(getent passwd $authors) \|\|
433	(
434	cat /etc/passwd
435	for author in $authors
436	do NIS_PATH= nismatch $author passwd.org_dir
437	done
438	ypmatch $authors passwd
439	)
440	} 2>/dev/null \|
441	$AWK -F: "$awkscript"
442	`$initialize_fullname
443	esac
444
445
446	# Function to print a single log line.
447	# We don't use awk functions, to stay compatible with old awk versions.
448	# `Log' is the log message (with \n replaced by \001).
449	# `files' contains the affected files.
450	printlogline='{
451
452	# Following the GNU coding standards, rewrite
453	# * file: (function): comment
454	# to
455	# * file (function): comment
456	if (Log ~ /^\([^)]*\): /) {
457	i = index(Log, ")")
458	files = files " " substr(Log, 1, i)
459	Log = substr(Log, i+3)
460	}
461
462	# If "label: comment" is too long, break the line after the ":".
463	sep = " "
464	if ('"$length"' <= '"$indent"' + 1 + length(files) + index(Log, SOH)) sep = "\n" indent_string
465
466	# Print the label.
467	printf "%s*%s:", indent_string, files
468
469	# Print each line of the log, transliterating \001 to \n.
470	while ((i = index(Log, SOH)) != 0) {
471	logline = substr(Log, 1, i-1)
472	if (logline ~ /[^'"$tab"' ]/) {
473	printf "%s%s\n", sep, logline
474	} else {
475	print ""
476	}
477	sep = indent_string
478	Log = substr(Log, i+1)
479	}
480	}'
481
482	# Pattern to match the `revision' line of rlog output.
483	rlog_revision_pattern='^revision [0-9]+\.[0-9]+(\.[0-9]+\.[0-9]+)(['"$tab"' ]+locked by: [^'"$tab"' $,.0-9:;@][^'"$tab"' $,:;@][^'"$tab"' $,.0-9:;@];)?['"$tab"' ]$'
484
485	case $hostname in
486	'')
487	hostname=`(
488	hostname \|\| uname -n \|\| uuname -l \|\| cat /etc/whoami
489	) 2>/dev/null` \|\| {
490	echo >&2 "$0: cannot deduce hostname"
491	exit 1
492	}
493
494	case $hostname in
495	.) ;;
496	*)
497	domainname=`(domainname) 2>/dev/null` &&
498	case $domainname in
499	.) hostname=$hostname.$domainname
500	esac
501	esac
502	esac
503
504
505	# Process the rlog output, generating ChangeLog style entries.
506
507	# First, reformat the rlog output so that each line contains one log entry.
508	# Transliterate \n to \001 so that multiline entries fit on a single line.
509	# Discard irrelevant rlog output.
510	$AWK <$rlogout '
511	BEGIN { repository = "'"$repository"'" }
512	/^RCS file:/ {
513	if (repository != "") {
514	filename = $3
515	if (substr(filename, 1, length(repository) + 1) == repository "/") {
516	filename = substr(filename, length(repository) + 2)
517	}
518	if (filename ~ /,v$/) {
519	filename = substr(filename, 1, length(filename) - 2)
520	}
521	if (filename ~ /(^\|\/)Attic\/[^\/]*$/) {
522	i = length(filename)
523	while (substr(filename, i, 1) != "/") i--
524	filename = substr(filename, 1, i - 6) substr(filename, i + 1)
525	}
526	}
527	rev = "?"
528	}
529	/^Working file:/ { if (repository == "") filename = $3 }
530	/'"$rlog_revision_pattern"'/, /^(-----------\|===========)$/ {
531	line = $0
532	if (line ~ /'"$rlog_revision_pattern"'/) {
533	rev = $2
534	next
535	}
536	if (line ~ /^date: [0-9][- +\/0-9:]*;/) {
537	date = $2
538	if (date ~ /\//) {
539	# This is a traditional RCS format date YYYY/MM/DD.
540	# Replace "/"s with "-"s to get ISO format.
541	newdate = ""
542	while ((i = index(date, "/")) != 0) {
543	newdate = newdate substr(date, 1, i-1) "-"
544	date = substr(date, i+1)
545	}
546	date = newdate date
547	}
548	time = substr($3, 1, length($3) - 1)
549	author = substr($5, 1, length($5)-1)
550	printf "%s %s %s %s %s %c", filename, rev, date, time, author, 1
551	rev = "?"
552	next
553	}
554	if (line ~ /^branches: /) { next }
555	if (line ~ /^(-----------\|===========)$/) { print ""; next }
556	if (line == "Initial revision" \|\| line ~ /^file .+ was initially added on branch .+\.$/) {
557	line = "New file."
558	}
559	printf "%s%c", line, 1
560	}
561	' \|
562
563	# Now each line is of the form
564	# FILENAME REVISION YYYY-MM-DD HH:MM:SS[+-TIMEZONE] AUTHOR \001LOG
565	# where \001 stands for a carriage return,
566	# and each line of the log is terminated by \001 instead of \n.
567	# Sort the log entries, first by date+time (in reverse order),
568	# then by author, then by log entry, and finally by file name and revision
569	# (just in case).
570	sort +2 -4r +4 +0 \|
571
572	# Finally, reformat the sorted log entries.
573	$AWK '
574	BEGIN {
575	logTZ = "'"$logTZ"'"
576	revision = "'"$revision"'"
577
578	# Some awk variants do not understand "\001", so we have to
579	# put the char directly in the file.
580	SOH="\ 1" # <-- There is a single SOH (octal code 001) here.
581
582	# Initialize the fullname and mailaddr associative arrays.
583	'"$initialize_fullname"'
584	'"$initialize_mailaddr"'
585
586	# Initialize indent string.
587	indent_string = ""
588	i = '"$indent"'
589	if (0 < '"$tabwidth"')
590	for (; '"$tabwidth"' <= i; i -= '"$tabwidth"')
591	indent_string = indent_string "\t"
592	while (1 <= i--)
593	indent_string = indent_string " "
594	}
595
596	{
597	newlog = substr($0, 1 + index($0, SOH))
598
599	# Ignore log entries prefixed by "#".
600	if (newlog ~ /^#/) { next }
601
602	if (Log != newlog \|\| date != $3 \|\| author != $5) {
603
604	# The previous log and this log differ.
605
606	# Print the old log.
607	if (date != "") '"$printlogline"'
608
609	# Logs that begin with "{clumpname} " should be grouped together,
610	# and the clumpname should be removed.
611	# Extract the new clumpname from the log header,
612	# and use it to decide whether to output a blank line.
613	newclumpname = ""
614	sep = "\n"
615	if (date == "") sep = ""
616	if (newlog ~ /^\{[^'"$tab"' }]*}['"$tab"' ]/) {
617	i = index(newlog, "}")
618	newclumpname = substr(newlog, 1, i)
619	while (substr(newlog, i+1) ~ /^['"$tab"' ]/) i++
620	newlog = substr(newlog, i+1)
621	if (clumpname == newclumpname) sep = ""
622	}
623	printf sep
624	clumpname = newclumpname
625
626	# Get ready for the next log.
627	Log = newlog
628	if (files != "")
629	for (i in filesknown)
630	filesknown[i] = 0
631	files = ""
632	}
633	if (date != $3 \|\| author != $5) {
634	# The previous date+author and this date+author differ.
635	# Print the new one.
636	date = $3
637	time = $4
638	author = $5
639
640	zone = ""
641	if (logTZ && ((i = index(time, "-")) \|\| (i = index(time, "+"))))
642	zone = " " substr(time, i)
643
644	# Print "date[ timezone] fullname <email address>".
645	# Get fullname and email address from associative arrays;
646	# default to author and author@hostname if not in arrays.
647	if (fullname[author])
648	auth = fullname[author]
649	else
650	auth = author
651	printf "%s%s %s ", date, zone, auth
652	if (mailaddr[author])
653	printf "<%s>\n\n", mailaddr[author]
654	else
655	printf "<%s@%s>\n\n", author, "'"$hostname"'"
656	}
657	if (! filesknown[$1]) {
658	filesknown[$1] = 1
659	if (files == "") files = " " $1
660	else files = files ", " $1
661	if (revision && $2 != "?") files = files " " $2
662	}
663	}
664	END {
665	# Print the last log.
666	if (date != "") {
667	'"$printlogline"'
668	printf "\n"
669	}
670	}
671	' &&
672
673
674	# Exit successfully.
675
676	exec rm -fr $logdir
677
678	# Local Variables:
679	# tab-width:4
680	# End: