diff options
author | rgrimes <rgrimes@FreeBSD.org> | 1994-05-27 12:33:43 +0000 |
---|---|---|
committer | rgrimes <rgrimes@FreeBSD.org> | 1994-05-27 12:33:43 +0000 |
commit | f9ab90d9d6d02989a075d0f0074496d5b1045e4b (patch) | |
tree | add7e996bac5289cdc55e6935750c352505560a9 /usr.bin/sed | |
parent | be22b15ae2ff8d7fe06b6e14fddf0c5b444a95da (diff) | |
download | FreeBSD-src-f9ab90d9d6d02989a075d0f0074496d5b1045e4b.zip FreeBSD-src-f9ab90d9d6d02989a075d0f0074496d5b1045e4b.tar.gz |
BSD 4.4 Lite Usr.bin Sources
Diffstat (limited to 'usr.bin/sed')
-rw-r--r-- | usr.bin/sed/Makefile | 6 | ||||
-rw-r--r-- | usr.bin/sed/POSIX | 198 | ||||
-rw-r--r-- | usr.bin/sed/TEST/hanoi.sed | 102 | ||||
-rw-r--r-- | usr.bin/sed/TEST/math.sed | 163 | ||||
-rw-r--r-- | usr.bin/sed/TEST/sed.test | 552 | ||||
-rw-r--r-- | usr.bin/sed/compile.c | 771 | ||||
-rw-r--r-- | usr.bin/sed/defs.h | 144 | ||||
-rw-r--r-- | usr.bin/sed/extern.h | 59 | ||||
-rw-r--r-- | usr.bin/sed/main.c | 352 | ||||
-rw-r--r-- | usr.bin/sed/misc.c | 141 | ||||
-rw-r--r-- | usr.bin/sed/process.c | 629 | ||||
-rw-r--r-- | usr.bin/sed/sed.1 | 514 |
12 files changed, 3631 insertions, 0 deletions
diff --git a/usr.bin/sed/Makefile b/usr.bin/sed/Makefile new file mode 100644 index 0000000..99f860b --- /dev/null +++ b/usr.bin/sed/Makefile @@ -0,0 +1,6 @@ +# @(#)Makefile 8.1 (Berkeley) 6/6/93 + +PROG= sed +SRCS= compile.c main.c misc.c process.c + +.include <bsd.prog.mk> diff --git a/usr.bin/sed/POSIX b/usr.bin/sed/POSIX new file mode 100644 index 0000000..41955af --- /dev/null +++ b/usr.bin/sed/POSIX @@ -0,0 +1,198 @@ +# @(#)POSIX 8.1 (Berkeley) 6/6/93 + +Comments on the IEEE P1003.2 Draft 12 + Part 2: Shell and Utilities + Section 4.55: sed - Stream editor + +Diomidis Spinellis <dds@doc.ic.ac.uk> +Keith Bostic <bostic@cs.berkeley.edu> + +In the following paragraphs, "wrong" usually means "inconsistent with +historic practice", as most of the following comments refer to +undocumented inconsistencies between the historical versions of sed and +the POSIX 1003.2 standard. All the comments are notes taken while +implementing a POSIX-compatible version of sed, and should not be +interpreted as official opinions or criticism towards the POSIX committee. +All uses of "POSIX" refer to section 4.55, Draft 12 of POSIX 1003.2. + + 1. 32V and BSD derived implementations of sed strip the text + arguments of the a, c and i commands of their initial blanks, + i.e. + + #!/bin/sed -f + a\ + foo\ + \ indent\ + bar + + produces: + + foo + indent + bar + + POSIX does not specify this behavior as the System V versions of + sed do not do this stripping. The argument against stripping is + that it is difficult to write sed scripts that have leading blanks + if they are stripped. The argument for stripping is that it is + difficult to write readable sed scripts unless indentation is allowed + and ignored, and leading whitespace is obtainable by entering a + backslash in front of it. This implementation follows the BSD + historic practice. + + 2. Historical versions of sed required that the w flag be the last + flag to an s command as it takes an additional argument. This + is obvious, but not specified in POSIX. + + 3. Historical versions of sed required that whitespace follow a w + flag to an s command. This is not specified in POSIX. This + implementation permits whitespace but does not require it. + + 4. Historical versions of sed permitted any number of whitespace + characters to follow the w command. This is not specified in + POSIX. This implementation permits whitespace but does not + require it. + + 5. The rule for the l command differs from historic practice. Table + 2-15 includes the various ANSI C escape sequences, including \\ + for backslash. Some historical versions of sed displayed two + digit octal numbers, too, not three as specified by POSIX. POSIX + is a cleanup, and is followed by this implementation. + + 6. The POSIX specification for ! does not specify that for a single + command the command must not contain an address specification + whereas the command list can contain address specifications. The + specification for ! implies that "3!/hello/p" works, and it never + has, historically. Note, + + 3!{ + /hello/p + } + + does work. + + 7. POSIX does not specify what happens with consecutive ! commands + (e.g. /foo/!!!p). Historic implementations allow any number of + !'s without changing the behaviour. (It seems logical that each + one might reverse the behaviour.) This implementation follows + historic practice. + + 8. Historic versions of sed permitted commands to be separated + by semi-colons, e.g. 'sed -ne '1p;2p;3q' printed the first + three lines of a file. This is not specified by POSIX. + Note, the ; command separator is not allowed for the commands + a, c, i, w, r, :, b, t, # and at the end of a w flag in the s + command. This implementation follows historic practice and + implements the ; separator. + + 9. Historic versions of sed terminated the script if EOF was reached + during the execution of the 'n' command, i.e.: + + sed -e ' + n + i\ + hello + ' </dev/null + + did not produce any output. POSIX does not specify this behavior. + This implementation follows historic practice. + +10. Deleted. + +11. Historical implementations do not output the change text of a c + command in the case of an address range whose first line number + is greater than the second (e.g. 3,1). POSIX requires that the + text be output. Since the historic behavior doesn't seem to have + any particular purpose, this implementation follows the POSIX + behavior. + +12. POSIX does not specify whether address ranges are checked and + reset if a command is not executed due to a jump. The following + program will behave in different ways depending on whether the + 'c' command is triggered at the third line, i.e. will the text + be output even though line 3 of the input will never logically + encounter that command. + + 2,4b + 1,3c\ + text + + Historic implementations, and this implementation, do not output + the text in the above example. The general rule, therefore, + is that a range whose second address is never matched extends to + the end of the input. + +13. Historical implementations allow an output suppressing #n at the + beginning of -e arguments as well as in a script file. POSIX + does not specify this. This implementation follows historical + practice. + +14. POSIX does not explicitly specify how sed behaves if no script is + specified. Since the sed Synopsis permits this form of the command, + and the language in the Description section states that the input + is output, it seems reasonable that it behave like the cat(1) + command. Historic sed implementations behave differently for "ls | + sed", where they produce no output, and "ls | sed -e#", where they + behave like cat. This implementation behaves like cat in both cases. + +15. The POSIX requirement to open all w files at the beginning makes + sed behave nonintuitively when the w commands are preceded by + addresses or are within conditional blocks. This implementation + follows historic practice and POSIX, by default, and provides the + -a option which opens the files only when they are needed. + +16. POSIX does not specify how escape sequences other than \n and \D + (where D is the delimiter character) are to be treated. This is + reasonable, however, it also doesn't state that the backslash is + to be discarded from the output regardless. A strict reading of + POSIX would be that "echo xyz | sed s/./\a" would display "\ayz". + As historic sed implementations always discarded the backslash, + this implementation does as well. + +17. POSIX specifies that an address can be "empty". This implies + that constructs like ",d" or "1,d" and ",5d" are allowed. This + is not true for historic implementations or this implementation + of sed. + +18. The b t and : commands are documented in POSIX to ignore leading + white space, but no mention is made of trailing white space. + Historic implementations of sed assigned different locations to + the labels "x" and "x ". This is not useful, and leads to subtle + programming errors, but it is historic practice and changing it + could theoretically break working scripts. This implementation + follows historic practice. + +19. Although POSIX specifies that reading from files that do not exist + from within the script must not terminate the script, it does not + specify what happens if a write command fails. Historic practice + is to fail immediately if the file cannot be opened or written. + This implementation follows historic practice. + +20. Historic practice is that the \n construct can be used for either + string1 or string2 of the y command. This is not specified by + POSIX. This implementation follows historic practice. + +21. Deleted. + +22. Historic implementations of sed ignore the RE delimiter characters + within character classes. This is not specified in POSIX. This + implementation follows historic practice. + +23. Historic implementations handle empty RE's in a special way: the + empty RE is interpreted as if it were the last RE encountered, + whether in an address or elsewhere. POSIX does not document this + behavior. For example the command: + + sed -e /abc/s//XXX/ + + substitutes XXX for the pattern abc. The semantics of "the last + RE" can be defined in two different ways: + + 1. The last RE encountered when compiling (lexical/static scope). + 2. The last RE encountered while running (dynamic scope). + + While many historical implementations fail on programs depending + on scope differences, the SunOS version exhibited dynamic scope + behaviour. This implementation does dynamic scoping, as this seems + the most useful and in order to remain consistent with historical + practice. diff --git a/usr.bin/sed/TEST/hanoi.sed b/usr.bin/sed/TEST/hanoi.sed new file mode 100644 index 0000000..d29c648 --- /dev/null +++ b/usr.bin/sed/TEST/hanoi.sed @@ -0,0 +1,102 @@ +# Towers of Hanoi in sed. +# +# @(#)hanoi.sed 8.1 (Berkeley) 6/6/93 +# +# +# Ex: +# Run "sed -f hanoi.sed", and enter: +# +# :abcd: : :<CR><CR> +# +# note -- TWO carriage returns, a peculiarity of sed), this will output the +# sequence of states involved in moving 4 rings, the largest called "a" and +# the smallest called "d", from the first to the second of three towers, so +# that the rings on any tower at any time are in descending order of size. +# You can start with a different arrangement and a different number of rings, +# say :ce:b:ax: and it will give the shortest procedure for moving them all +# to the middle tower. The rules are: the names of the rings must all be +# lower-case letters, they must be input within 3 fields (representing the +# towers) and delimited by 4 colons, such that the letters within each field +# are in alphabetical order (i.e. rings are in descending order of size). +# +# For the benefit of anyone who wants to figure out the script, an "internal" +# line of the form +# b:0abx:1a2b3 :2 :3x2 +# has the following meaning: the material after the three markers :1, :2, +# and :3 represents the three towers; in this case the current set-up is +# ":ab : :x :". The numbers after a, b and x in these fields indicate +# that the next time it gets a chance, it will move a to tower 2, move b +# to tower 3, and move x to tower 2. The string after :0 just keeps track +# of the alphabetical order of the names of the rings. The b at the +# beginning means that it is now dealing with ring b (either about to move +# it, or re-evaluating where it should next be moved to). +# +# Although this version is "limited" to 26 rings because of the size of the +# alphabet, one could write a script using the same idea in which the rings +# were represented by arbitrary [strings][within][brackets], and in place of +# the built-in line of the script giving the order of the letters of the +# alphabet, it would accept from the user a line giving the ordering to be +# assumed, e.g. [ucbvax][decvax][hplabs][foo][bar]. +# +# George Bergman +# Math, UC Berkeley 94720 USA + +# cleaning, diagnostics +s/ *//g +/^$/d +/[^a-z:]/{a\ +Illegal characters: use only a-z and ":". Try again. +d +} +/^:[a-z]*:[a-z]*:[a-z]*:$/!{a\ +Incorrect format: use\ +\ : string1 : string2 : string3 :<CR><CR>\ +Try again. +d +} +/\([a-z]\).*\1/{a\ +Repeated letters not allowed. Try again. +d +} +# initial formatting +h +s/[a-z]/ /g +G +s/^:\( *\):\( *\):\( *\):\n:\([a-z]*\):\([a-z]*\):\([a-z]*\):$/:1\4\2\3:2\5\1\3:3\6\1\2:0/ +s/[a-z]/&2/g +s/^/abcdefghijklmnopqrstuvwxyz/ +:a +s/^\(.\).*\1.*/&\1/ +s/.// +/^[^:]/ba +s/\([^0]*\)\(:0.*\)/\2\1:/ +s/^[^0]*0\(.\)/\1&/ +:b +# outputting current state without markers +h +s/.*:1/:/ +s/[123]//gp +g +:c +# establishing destinations +/^\(.\).*\1:1/td +/^\(.\).*:1[^:]*\11/s/^\(.\)\(.*\1\([a-z]\).*\)\3./\3\2\31/ +/^\(.\).*:1[^:]*\12/s/^\(.\)\(.*\1\([a-z]\).*\)\3./\3\2\33/ +/^\(.\).*:1[^:]*\13/s/^\(.\)\(.*\1\([a-z]\).*\)\3./\3\2\32/ +/^\(.\).*:2[^:]*\11/s/^\(.\)\(.*\1\([a-z]\).*\)\3./\3\2\33/ +/^\(.\).*:2[^:]*\12/s/^\(.\)\(.*\1\([a-z]\).*\)\3./\3\2\32/ +/^\(.\).*:2[^:]*\13/s/^\(.\)\(.*\1\([a-z]\).*\)\3./\3\2\31/ +/^\(.\).*:3[^:]*\11/s/^\(.\)\(.*\1\([a-z]\).*\)\3./\3\2\32/ +/^\(.\).*:3[^:]*\12/s/^\(.\)\(.*\1\([a-z]\).*\)\3./\3\2\31/ +/^\(.\).*:3[^:]*\13/s/^\(.\)\(.*\1\([a-z]\).*\)\3./\3\2\33/ +bc +# iterate back to find smallest out-of-place ring +:d +s/^\(.\)\(:0[^:]*\([^:]\)\1.*:\([123]\)[^:]*\1\)\4/\3\2\4/ +td +# move said ring (right, resp. left) +s/^\(.\)\(.*\)\1\([23]\)\(.*:\3[^ ]*\) /\1\2 \4\1\3/ +s/^\(.\)\(.*:\([12]\)[^ ]*\) \(.*\)\1\3/\1\2\1\3\4 / +tb +s/.*/Done! Try another, or end with ^D./p +d diff --git a/usr.bin/sed/TEST/math.sed b/usr.bin/sed/TEST/math.sed new file mode 100644 index 0000000..8e7bf51 --- /dev/null +++ b/usr.bin/sed/TEST/math.sed @@ -0,0 +1,163 @@ +# +# @(#)math.sed 8.1 (Berkeley) 6/6/93 +# +# Addition and multiplication in sed. +# ++ for a limited time only do (expr) too!!! +# +# Kevin S Braunsdorf, PUCC UNIX Group, ksb@cc.purdue.edu. +# +# Ex: +# echo "4+7*3" | sed -f %f + +# make sure the expression is well formed +s/[ ]//g +/[+*\/-]$/{ + a\ + poorly formed expression, operator on the end + q +} +/^[+*\/]/{ + a\ + poorly formed expression, leading operator + q +} + +# fill hold space with done token +x +s/^.*/done/ +x + +# main loop, process operators (*, + and () ) +: loop +/^\+/{ + s/// + b loop +} +/^\(.*\)(\([^)]*\))\(.*\)$/{ + H + s//\2/ + x + s/^\(.*\)\n\(.*\)(\([^()]*\))\(.*\)$/()\2@\4@\1/ + x + b loop +} +/^[0-9]*\*/b mul +/^\([0-9]*\)\+\([0-9+*]*\*[0-9]*\)$/{ + s//\2+\1/ + b loop +} +/^[0-9]*\+/{ + s/$/=/ + b add +} +x +/^done$/{ + x + p + d +} +/^()/{ + s/// + x + G + s/\(.*\)\n\([^@]*\)@\([^@]*\)@\(.*\)/\2\1\3/ + x + s/[^@]*@[^@]*@\(.*\)/\1/ + x + b loop +} +i\ +help, stack problem +p +x +p +q + +# turn mul into add until 1*x -> x +: mul +/^0*1\*/{ + s/// + b loop +} +/^\([0-9]*\)0\*/{ + s/^\([0-9]*\)0\*\([0-9]*\)/\1*\20/ + b mul +} +s/^\([0-9]*\)1\*/\10*/ +s/^\([0-9]*\)2\*/\11*/ +s/^\([0-9]*\)3\*/\12*/ +s/^\([0-9]*\)4\*/\13*/ +s/^\([0-9]*\)5\*/\14*/ +s/^\([0-9]*\)6\*/\15*/ +s/^\([0-9]*\)7\*/\16*/ +s/^\([0-9]*\)8\*/\17*/ +s/^\([0-9]*\)9\*/\18*/ +s/\*\([0-9*]*\)/*\1+\1/ +b mul + +# get rid of a plus term until 0+x -> x +: add +/^\+\([0-9+*]*\)=/{ + s//\1/ + b loop +} +/^\([0-9*]*\)\+=/{ + s//\1/ + b loop +} +/^\([0-9]*\)\+\([0-9*+]*\)\+=/{ + s//\2+\1/ + b loop +} +/^\([0-9]*\)0\+\([0-9]*\)\([0-9]\)=/{ + s//\1+\2=\3/ + b add +} +/^\([0-9]*\)\([0-9]\)\+\([0-9]*\)0=/{ + s//\1+\3=\2/ + b add +} +/^\([0-9]*\)0\+\([0-9*+]*\)\+\([0-9]*\)\([0-9]\)=/{ + s//\1+\2+\3=\4/ + b add +} +/^\([0-9]*\)\([0-9]\)\+\([0-9*+]*\)\+\([0-9]*\)0=/{ + s//\1+\3+\4=\2/ + b add +} +s/^\([0-9]*\)1\+/\10+/ +s/^\([0-9]*\)2\+/\11+/ +s/^\([0-9]*\)3\+/\12+/ +s/^\([0-9]*\)4\+/\13+/ +s/^\([0-9]*\)5\+/\14+/ +s/^\([0-9]*\)6\+/\15+/ +s/^\([0-9]*\)7\+/\16+/ +s/^\([0-9]*\)8\+/\17+/ +s/^\([0-9]*\)9\+/\18+/ + +s/9=\([0-9]*\)$/_=\1/ +s/8=\([0-9]*\)$/9=\1/ +s/7=\([0-9]*\)$/8=\1/ +s/6=\([0-9]*\)$/7=\1/ +s/5=\([0-9]*\)$/6=\1/ +s/4=\([0-9]*\)$/5=\1/ +s/3=\([0-9]*\)$/4=\1/ +s/2=\([0-9]*\)$/3=\1/ +s/1=\([0-9]*\)$/2=\1/ +/_/{ + s//_0/ + : inc + s/9_/_0/ + s/8_/9/ + s/7_/8/ + s/6_/7/ + s/5_/6/ + s/4_/5/ + s/3_/4/ + s/2_/3/ + s/1_/2/ + s/0_/1/ + s/\+_/+1/ + /_/b inc +} +b add diff --git a/usr.bin/sed/TEST/sed.test b/usr.bin/sed/TEST/sed.test new file mode 100644 index 0000000..e91036f --- /dev/null +++ b/usr.bin/sed/TEST/sed.test @@ -0,0 +1,552 @@ +#!/bin/sh - +# +# Copyright (c) 1992 Diomidis Spinellis. +# Copyright (c) 1992, 1993 +# The Regents of the University of California. All rights reserved. +# +# Redistribution and use in source and binary forms, with or without +# modification, are permitted provided that the following conditions +# are met: +# 1. Redistributions of source code must retain the above copyright +# notice, this list of conditions and the following disclaimer. +# 2. Redistributions in binary form must reproduce the above copyright +# notice, this list of conditions and the following disclaimer in the +# documentation and/or other materials provided with the distribution. +# 3. All advertising materials mentioning features or use of this software +# must display the following acknowledgement: +# This product includes software developed by the University of +# California, Berkeley and its contributors. +# 4. Neither the name of the University nor the names of its contributors +# may be used to endorse or promote products derived from this software +# without specific prior written permission. +# +# THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +# ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +# IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +# ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +# FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +# DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +# OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +# HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +# LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +# OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +# SUCH DAMAGE. +# +# @(#)sed.test 8.1 (Berkeley) 6/6/93 +# + +# sed Regression Tests +# +# The following files are created: +# lines[1-4], script1, script2 +# Two directories *.out contain the test results + +main() +{ + BASE=/usr/old/bin/sed + BASELOG=sed.out + TEST=../obj/sed + TESTLOG=nsed.out + DICT=/usr/share/dict/words + + test_error | more + + awk 'END { for (i = 1; i < 15; i++) print "l1_" i}' </dev/null >lines1 + awk 'END { for (i = 1; i < 10; i++) print "l2_" i}' </dev/null >lines2 + + exec 4>&1 5>&2 + + # Set these flags to get messages about known problems + BSD=1 + GNU=0 + SUN=0 + tests $BASE $BASELOG + + BSD=0 + GNU=0 + SUN=0 + tests $TEST $TESTLOG + exec 1>&4 2>&5 + diff -c $BASELOG $TESTLOG | more +} + +tests() +{ + SED=$1 + DIR=$2 + rm -rf $DIR + mkdir $DIR + MARK=100 + + test_args + test_addr + echo Testing commands + test_group + test_acid + test_branch + test_pattern + test_print + test_subst +} + +mark() +{ + MARK=`expr $MARK + 1` + exec 1>&4 2>&5 + exec >"$DIR/${MARK}_$1" + echo "Test $1:$MARK" + # Uncomment this line to match tests with sed error messages + echo "Test $1:$MARK" >&5 +} + +test_args() +{ + mark '1.1' + echo Testing argument parsing + echo First type + if [ $SUN -eq 1 ] ; then + echo SunOS sed prints only with -n + else + $SED 's/^/e1_/p' lines1 + fi + mark '1.2' ; $SED -n 's/^/e1_/p' lines1 + mark '1.3' + if [ $SUN -eq 1 ] ; then + echo SunOS sed prints only with -n + else + $SED 's/^/e1_/p' <lines1 + fi + mark '1.4' ; $SED -n 's/^/e1_/p' <lines1 + echo Second type + mark '1.4.1' + if [ $SUN -eq 1 ] ; then + echo SunOS sed fails this + fi + $SED -e '' <lines1 + echo 's/^/s1_/p' >script1 + echo 's/^/s2_/p' >script2 + mark '1.5' + if [ $SUN -eq 1 ] ; then + echo SunOS sed prints only with -n + else + $SED -f script1 lines1 + fi + mark '1.6' + if [ $SUN -eq 1 ] ; then + echo SunOS sed prints only with -n + else + $SED -f script1 <lines1 + fi + mark '1.7' + if [ $SUN -eq 1 ] ; then + echo SunOS sed prints only with -n + else + $SED -e 's/^/e1_/p' lines1 + fi + mark '1.8' + if [ $SUN -eq 1 ] ; then + echo SunOS sed prints only with -n + else + $SED -e 's/^/e1_/p' <lines1 + fi + mark '1.9' ; $SED -n -f script1 lines1 + mark '1.10' ; $SED -n -f script1 <lines1 + mark '1.11' ; $SED -n -e 's/^/e1_/p' lines1 + mark '1.12' + if [ $SUN -eq 1 ] ; then + echo SunOS sed prints only with -n + else + $SED -n -e 's/^/e1_/p' <lines1 + fi + mark '1.13' + if [ $SUN -eq 1 ] ; then + echo SunOS sed prints only with -n + else + $SED -e 's/^/e1_/p' -e 's/^/e2_/p' lines1 + fi + mark '1.14' + if [ $SUN -eq 1 ] ; then + echo SunOS sed prints only with -n + else + $SED -f script1 -f script2 lines1 + fi + mark '1.15' + if [ $GNU -eq 1 -o $SUN -eq 1 ] ; then + echo GNU and SunOS sed fail this following older POSIX draft + else + $SED -e 's/^/e1_/p' -f script1 lines1 + fi + mark '1.16' + if [ $SUN -eq 1 ] ; then + echo SunOS sed prints only with -n + else + $SED -e 's/^/e1_/p' lines1 lines1 + fi + # POSIX D11.2:11251 + mark '1.17' ; $SED p <lines1 lines1 +cat >script1 <<EOF +#n +# A comment + +p +EOF + mark '1.18' ; $SED -f script1 <lines1 lines1 +} + +test_addr() +{ + echo Testing address ranges + mark '2.1' ; $SED -n -e '4p' lines1 + mark '2.2' ; $SED -n -e '20p' lines1 lines2 + mark '2.3' ; $SED -n -e '$p' lines1 + mark '2.4' ; $SED -n -e '$p' lines1 lines2 + mark '2.5' ; $SED -n -e '$a\ +hello' /dev/null + mark '2.6' ; $SED -n -e '$p' lines1 /dev/null lines2 + # Should not print anything + mark '2.7' ; $SED -n -e '20p' lines1 + mark '2.8' ; $SED -n -e '0p' lines1 + mark '2.9' ; $SED -n '/l1_7/p' lines1 + mark '2.10' ; $SED -n ' /l1_7/ p' lines1 + mark '2.11' + if [ $BSD -eq 1 ] ; then + echo BSD sed fails this test + fi + if [ $GNU -eq 1 ] ; then + echo GNU sed fails this + fi + $SED -n '\_l1\_7_p' lines1 + mark '2.12' ; $SED -n '1,4p' lines1 + mark '2.13' ; $SED -n '1,$p' lines1 lines2 + mark '2.14' ; $SED -n '1,/l2_9/p' lines1 lines2 + mark '2.15' ; $SED -n '/4/,$p' lines1 lines2 + mark '2.16' ; $SED -n '/4/,20p' lines1 lines2 + mark '2.17' ; $SED -n '/4/,/10/p' lines1 lines2 + mark '2.18' ; $SED -n '/l2_3/,/l1_8/p' lines1 lines2 + mark '2.19' + if [ $GNU -eq 1 ] ; then + echo GNU sed fails this + fi + $SED -n '12,3p' lines1 lines2 + mark '2.20' + if [ $GNU -eq 1 ] ; then + echo GNU sed fails this + fi + $SED -n '/l1_7/,3p' lines1 lines2 +} + +test_group() +{ + echo Brace and other grouping + mark '3.1' ; $SED -e ' +4,12 { + s/^/^/ + s/$/$/ + s/_/T/ +}' lines1 + mark '3.2' ; $SED -e ' +4,12 { + s/^/^/ + /6/,/10/ { + s/$/$/ + /8/ s/_/T/ + } +}' lines1 + mark '3.3' ; $SED -e ' +4,12 !{ + s/^/^/ + /6/,/10/ !{ + s/$/$/ + /8/ !s/_/T/ + } +}' lines1 + mark '3.4' ; $SED -e '4,12!s/^/^/' lines1 +} + +test_acid() +{ + echo Testing a c d and i commands + mark '4.1' ; $SED -n -e ' +s/^/before_i/p +20i\ +inserted +s/^/after_i/p +' lines1 lines2 + mark '4.2' ; $SED -n -e ' +5,12s/^/5-12/ +s/^/before_a/p +/5-12/a\ +appended +s/^/after_a/p +' lines1 lines2 + mark '4.3' + if [ $GNU -eq 1 ] ; then + echo GNU sed fails this + fi + $SED -n -e ' +s/^/^/p +/l1_/a\ +appended +8,10N +s/$/$/p +' lines1 lines2 + mark '4.4' ; $SED -n -e ' +c\ +hello +' lines1 + mark '4.5' ; $SED -n -e ' +8c\ +hello +' lines1 + mark '4.6' ; $SED -n -e ' +3,14c\ +hello +' lines1 +# SunOS and GNU sed behave differently. We follow POSIX +# mark '4.7' ; $SED -n -e ' +#8,3c\ +#hello +#' lines1 + mark '4.8' ; $SED d <lines1 +} + +test_branch() +{ + echo Testing labels and branching + mark '5.1' ; $SED -n -e ' +b label4 +:label3 +s/^/label3_/p +b end +:label4 +2,12b label1 +b label2 +:label1 +s/^/label1_/p +b +:label2 +s/^/label2_/p +b label3 +:end +' lines1 + mark '5.2' + if [ $BSD -eq 1 ] ; then + echo BSD sed fails this test + fi + $SED -n -e ' +s/l1_/l2_/ +t ok +b +:ok +s/^/tested /p +' lines1 lines2 +# SunOS sed behaves differently here. Clarification needed. +# mark '5.3' ; $SED -n -e ' +#5,8b inside +#1,5 { +# s/^/^/p +# :inside +# s/$/$/p +#} +#' lines1 +# Check that t clears the substitution done flag + mark '5.4' ; $SED -n -e ' +1,8s/^/^/ +t l1 +:l1 +t l2 +s/$/$/p +b +:l2 +s/^/ERROR/ +' lines1 +# Check that reading a line clears the substitution done flag + mark '5.5' + if [ $BSD -eq 1 ] ; then + echo BSD sed fails this test + fi + $SED -n -e ' +t l2 +1,8s/^/^/p +2,7N +b +:l2 +s/^/ERROR/p +' lines1 + mark '5.6' ; $SED 5q lines1 + mark '5.7' ; $SED -e ' +5i\ +hello +5q' lines1 +# Branch across block boundary + mark '5.8' ; $SED -e ' +{ +:b +} +s/l/m/ +tb' lines1 +} + +test_pattern() +{ +echo Pattern space commands +# Check that the pattern space is deleted + mark '6.1' ; $SED -n -e ' +c\ +changed +p +' lines1 + mark '6.2' ; $SED -n -e ' +4d +p +' lines1 +# SunOS sed refused to print here +# mark '6.3' ; $SED -e ' +#N +#N +#N +#D +#P +#4p +#' lines1 + mark '6.4' ; $SED -e ' +2h +3H +4g +5G +6x +6p +6x +6p +' lines1 + mark '6.5' ; $SED -e '4n' lines1 + mark '6.6' ; $SED -n -e '4n' lines1 +} + +test_print() +{ + echo Testing print and file routines + awk 'END {for (i = 1; i < 256; i++) printf("%c", i);print "\n"}' \ + </dev/null >lines3 + # GNU and SunOS sed behave differently here + mark '7.1' + if [ $BSD -eq 1 ] ; then + echo 'BSD sed drops core on this one; TEST SKIPPED' + else + $SED -n l lines3 + fi + mark '7.2' ; $SED -e '/l2_/=' lines1 lines2 + rm -f lines4 + mark '7.3' ; $SED -e '3,12w lines4' lines1 + echo w results + cat lines4 + mark '7.4' ; $SED -e '4r lines2' lines1 + mark '7.5' ; $SED -e '5r /dev/dds' lines1 + mark '7.6' ; $SED -e '6r /dev/null' lines1 + mark '7.7' + if [ $BSD -eq 1 -o $GNU -eq 1 -o $SUN -eq 1 ] ; then + echo BSD, GNU and SunOS cannot pass this one + else + sed '200q' $DICT | sed 's$.*$s/^/&/w tmpdir/&$' >script1 + rm -rf tmpdir + mkdir tmpdir + $SED -f script1 lines1 + cat tmpdir/* + rm -rf tmpdir + fi + mark '7.8' + if [ $BSD -eq 1 ] ; then + echo BSD sed cannot pass 7.7 + else + echo line1 > lines3 + echo "" >> lines3 + $SED -n -e '$p' lines3 /dev/null + fi + +} + +test_subst() +{ + echo Testing substitution commands + mark '8.1' ; $SED -e 's/./X/g' lines1 + mark '8.2' ; $SED -e 's,.,X,g' lines1 +# GNU and SunOS sed thinks we are escaping . as wildcard, not as separator +# mark '8.3' ; $SED -e 's.\..X.g' lines1 +# POSIX does not say that this should work +# mark '8.4' ; $SED -e 's/[/]/Q/' lines1 + mark '8.4' ; $SED -e 's/[\/]/Q/' lines1 + mark '8.5' ; $SED -e 's_\__X_' lines1 + mark '8.6' ; $SED -e 's/./(&)/g' lines1 + mark '8.7' ; $SED -e 's/./(\&)/g' lines1 + mark '8.8' ; $SED -e 's/\(.\)\(.\)\(.\)/x\3x\2x\1/g' lines1 + mark '8.9' ; $SED -e 's/_/u0\ +u1\ +u2/g' lines1 + mark '8.10' + if [ $BSD -eq 1 -o $GNU -eq 1 ] ; then + echo 'BSD/GNU sed do not understand digit flags on s commands' + fi + $SED -e 's/./X/4' lines1 + rm -f lines4 + mark '8.11' ; $SED -e 's/1/X/w lines4' lines1 + echo s wfile results + cat lines4 + mark '8.12' ; $SED -e 's/[123]/X/g' lines1 + mark '8.13' ; $SED -e 'y/0123456789/9876543210/' lines1 + mark '8.14' ; + if [ $BSD -eq 1 -o $GNU -eq 1 -o $SUN -eq 1 ] ; then + echo BSD/GNU/SUN sed fail this test + else + $SED -e 'y10\123456789198765432\101' lines1 + fi + mark '8.15' ; $SED -e '1N;2y/\n/X/' lines1 + mark '8.16' + if [ $BSD -eq 1 ] ; then + echo 'BSD sed does not handle branch defined REs' + else + echo 'eeefff' | $SED -e 'p' -e 's/e/X/p' -e ':x' \ + -e 's//Y/p' -e '/f/bx' + fi +} + +test_error() +{ + exec 0>&3 4>&1 5>&2 + exec 0</dev/null + exec 2>&1 + set -x + $TEST -x && exit 1 + $TEST -f && exit 1 + $TEST -e && exit 1 + $TEST -f /dev/dds && exit 1 + $TEST p /dev/dds && exit 1 + $TEST -f /bin/sh && exit 1 + $TEST '{' && exit 1 + $TEST '{' && exit 1 + $TEST '/hello/' && exit 1 + $TEST '1,/hello/' && exit 1 + $TEST -e '-5p' && exit 1 + $TEST '/jj' && exit 1 + $TEST 'a hello' && exit 1 + $TEST 'a \ hello' && exit 1 + $TEST 'b foo' && exit 1 + $TEST 'd hello' && exit 1 + $TEST 's/aa' && exit 1 + $TEST 's/aa/' && exit 1 + $TEST 's/a/b' && exit 1 + $TEST 's/a/b/c/d' && exit 1 + $TEST 's/a/b/ 1 2' && exit 1 + $TEST 's/a/b/ 1 g' && exit 1 + $TEST 's/a/b/w' && exit 1 + $TEST 'y/aa' && exit 1 + $TEST 'y/aa/b/' && exit 1 + $TEST 'y/aa/' && exit 1 + $TEST 'y/a/b' && exit 1 + $TEST 'y/a/b/c/d' && exit 1 + $TEST '!' && exit 1 + $TEST supercalifrangolisticexprialidociussupercalifrangolisticexcius + set +x + exec 0>&3 1>&4 2>&5 +} + +main diff --git a/usr.bin/sed/compile.c b/usr.bin/sed/compile.c new file mode 100644 index 0000000..944a226 --- /dev/null +++ b/usr.bin/sed/compile.c @@ -0,0 +1,771 @@ +/*- + * Copyright (c) 1992 Diomidis Spinellis. + * Copyright (c) 1992, 1993 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Diomidis Spinellis of Imperial College, University of London. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef lint +static char sccsid[] = "@(#)compile.c 8.1 (Berkeley) 6/6/93"; +#endif /* not lint */ + +#include <sys/types.h> +#include <sys/stat.h> + +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <regex.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "defs.h" +#include "extern.h" + +#define LHSZ 128 +#define LHMASK (LHSZ - 1) +static struct labhash { + struct labhash *lh_next; + u_int lh_hash; + struct s_command *lh_cmd; + int lh_ref; +} *labels[LHSZ]; + +static char *compile_addr __P((char *, struct s_addr *)); +static char *compile_delimited __P((char *, char *)); +static char *compile_flags __P((char *, struct s_subst *)); +static char *compile_re __P((char *, regex_t **)); +static char *compile_subst __P((char *, struct s_subst *)); +static char *compile_text __P((void)); +static char *compile_tr __P((char *, char **)); +static struct s_command + **compile_stream __P((char *, struct s_command **, char *)); +static char *duptoeol __P((char *, char *)); +static void enterlabel __P((struct s_command *)); +static struct s_command + *findlabel __P((char *)); +static void fixuplabel __P((struct s_command *, struct s_command *)); +static void uselabel __P((void)); + +/* + * Command specification. This is used to drive the command parser. + */ +struct s_format { + char code; /* Command code */ + int naddr; /* Number of address args */ + enum e_args args; /* Argument type */ +}; + +static struct s_format cmd_fmts[] = { + {'{', 2, GROUP}, + {'a', 1, TEXT}, + {'b', 2, BRANCH}, + {'c', 2, TEXT}, + {'d', 2, EMPTY}, + {'D', 2, EMPTY}, + {'g', 2, EMPTY}, + {'G', 2, EMPTY}, + {'h', 2, EMPTY}, + {'H', 2, EMPTY}, + {'i', 1, TEXT}, + {'l', 2, EMPTY}, + {'n', 2, EMPTY}, + {'N', 2, EMPTY}, + {'p', 2, EMPTY}, + {'P', 2, EMPTY}, + {'q', 1, EMPTY}, + {'r', 1, RFILE}, + {'s', 2, SUBST}, + {'t', 2, BRANCH}, + {'w', 2, WFILE}, + {'x', 2, EMPTY}, + {'y', 2, TR}, + {'!', 2, NONSEL}, + {':', 0, LABEL}, + {'#', 0, COMMENT}, + {'=', 1, EMPTY}, + {'\0', 0, COMMENT}, +}; + +/* The compiled program. */ +struct s_command *prog; + +/* + * Compile the program into prog. + * Initialise appends. + */ +void +compile() +{ + *compile_stream(NULL, &prog, NULL) = NULL; + fixuplabel(prog, NULL); + uselabel(); + appends = xmalloc(sizeof(struct s_appends) * appendnum); + match = xmalloc((maxnsub + 1) * sizeof(regmatch_t)); +} + +#define EATSPACE() do { \ + if (p) \ + while (*p && isascii(*p) && isspace(*p)) \ + p++; \ + } while (0) + +static struct s_command ** +compile_stream(terminator, link, p) + char *terminator; + struct s_command **link; + register char *p; +{ + static char lbuf[_POSIX2_LINE_MAX + 1]; /* To save stack */ + struct s_command *cmd, *cmd2; + struct s_format *fp; + int naddr; /* Number of addresses */ + + if (p != NULL) + goto semicolon; + for (;;) { + if ((p = cu_fgets(lbuf, sizeof(lbuf))) == NULL) { + if (terminator != NULL) + err(COMPILE, "unexpected EOF (pending }'s)"); + return (link); + } + +semicolon: EATSPACE(); + if (p && (*p == '#' || *p == '\0')) + continue; + if (*p == '}') { + if (terminator == NULL) + err(COMPILE, "unexpected }"); + return (link); + } + *link = cmd = xmalloc(sizeof(struct s_command)); + link = &cmd->next; + cmd->nonsel = cmd->inrange = 0; + /* First parse the addresses */ + naddr = 0; + cmd->a1 = cmd->a2 = NULL; + +/* Valid characters to start an address */ +#define addrchar(c) (strchr("0123456789/\\$", (c))) + if (addrchar(*p)) { + naddr++; + cmd->a1 = xmalloc(sizeof(struct s_addr)); + p = compile_addr(p, cmd->a1); + EATSPACE(); /* EXTENSION */ + if (*p == ',') { + naddr++; + p++; + EATSPACE(); /* EXTENSION */ + cmd->a2 = xmalloc(sizeof(struct s_addr)); + p = compile_addr(p, cmd->a2); + } + } + +nonsel: /* Now parse the command */ + EATSPACE(); + if (!*p) + err(COMPILE, "command expected"); + cmd->code = *p; + for (fp = cmd_fmts; fp->code; fp++) + if (fp->code == *p) + break; + if (!fp->code) + err(COMPILE, "invalid command code %c", *p); + if (naddr > fp->naddr) + err(COMPILE, +"command %c expects up to %d address(es), found %d", *p, fp->naddr, naddr); + switch (fp->args) { + case NONSEL: /* ! */ + cmd->nonsel = ! cmd->nonsel; + p++; + goto nonsel; + case GROUP: /* { */ + p++; + EATSPACE(); + if (!*p) + p = NULL; + cmd2 = xmalloc(sizeof(struct s_command)); + cmd2->code = '}'; + *compile_stream("}", &cmd->u.c, p) = cmd2; + cmd->next = cmd2; + link = &cmd2->next; + break; + case EMPTY: /* d D g G h H l n N p P q x = \0 */ + p++; + EATSPACE(); + if (*p == ';') { + p++; + link = &cmd->next; + goto semicolon; + } + if (*p) + err(COMPILE, +"extra characters at the end of %c command", cmd->code); + break; + case TEXT: /* a c i */ + p++; + EATSPACE(); + if (*p != '\\') + err(COMPILE, +"command %c expects \\ followed by text", cmd->code); + p++; + EATSPACE(); + if (*p) + err(COMPILE, +"extra characters after \\ at the end of %c command", cmd->code); + cmd->t = compile_text(); + break; + case COMMENT: /* \0 # */ + break; + case WFILE: /* w */ + p++; + EATSPACE(); + if (*p == '\0') + err(COMPILE, "filename expected"); + cmd->t = duptoeol(p, "w command"); + if (aflag) + cmd->u.fd = -1; + else if ((cmd->u.fd = open(p, + O_WRONLY|O_APPEND|O_CREAT|O_TRUNC, + DEFFILEMODE)) == -1) + err(FATAL, "%s: %s\n", p, strerror(errno)); + break; + case RFILE: /* r */ + p++; + EATSPACE(); + if (*p == '\0') + err(COMPILE, "filename expected"); + else + cmd->t = duptoeol(p, "read command"); + break; + case BRANCH: /* b t */ + p++; + EATSPACE(); + if (*p == '\0') + cmd->t = NULL; + else + cmd->t = duptoeol(p, "branch"); + break; + case LABEL: /* : */ + p++; + EATSPACE(); + cmd->t = duptoeol(p, "label"); + if (strlen(p) == 0) + err(COMPILE, "empty label"); + enterlabel(cmd); + break; + case SUBST: /* s */ + p++; + if (*p == '\0' || *p == '\\') + err(COMPILE, +"substitute pattern can not be delimited by newline or backslash"); + cmd->u.s = xmalloc(sizeof(struct s_subst)); + p = compile_re(p, &cmd->u.s->re); + if (p == NULL) + err(COMPILE, "unterminated substitute pattern"); + --p; + p = compile_subst(p, cmd->u.s); + p = compile_flags(p, cmd->u.s); + EATSPACE(); + if (*p == ';') { + p++; + link = &cmd->next; + goto semicolon; + } + break; + case TR: /* y */ + p++; + p = compile_tr(p, (char **)&cmd->u.y); + EATSPACE(); + if (*p == ';') { + p++; + link = &cmd->next; + goto semicolon; + } + if (*p) + err(COMPILE, +"extra text at the end of a transform command"); + break; + } + } +} + +/* + * Get a delimited string. P points to the delimeter of the string; d points + * to a buffer area. Newline and delimiter escapes are processed; other + * escapes are ignored. + * + * Returns a pointer to the first character after the final delimiter or NULL + * in the case of a non-terminated string. The character array d is filled + * with the processed string. + */ +static char * +compile_delimited(p, d) + char *p, *d; +{ + char c; + + c = *p++; + if (c == '\0') + return (NULL); + else if (c == '\\') + err(COMPILE, "\\ can not be used as a string delimiter"); + else if (c == '\n') + err(COMPILE, "newline can not be used as a string delimiter"); + while (*p) { + if (*p == '\\' && p[1] == c) + p++; + else if (*p == '\\' && p[1] == 'n') { + *d++ = '\n'; + p += 2; + continue; + } else if (*p == '\\' && p[1] == '\\') + *d++ = *p++; + else if (*p == c) { + *d = '\0'; + return (p + 1); + } + *d++ = *p++; + } + return (NULL); +} + +/* + * Get a regular expression. P points to the delimiter of the regular + * expression; repp points to the address of a regexp pointer. Newline + * and delimiter escapes are processed; other escapes are ignored. + * Returns a pointer to the first character after the final delimiter + * or NULL in the case of a non terminated regular expression. The regexp + * pointer is set to the compiled regular expression. + * Cflags are passed to regcomp. + */ +static char * +compile_re(p, repp) + char *p; + regex_t **repp; +{ + int eval; + char re[_POSIX2_LINE_MAX + 1]; + + p = compile_delimited(p, re); + if (p && strlen(re) == 0) { + *repp = NULL; + return (p); + } + *repp = xmalloc(sizeof(regex_t)); + if (p && (eval = regcomp(*repp, re, 0)) != 0) + err(COMPILE, "RE error: %s", strregerror(eval, *repp)); + if (maxnsub < (*repp)->re_nsub) + maxnsub = (*repp)->re_nsub; + return (p); +} + +/* + * Compile the substitution string of a regular expression and set res to + * point to a saved copy of it. Nsub is the number of parenthesized regular + * expressions. + */ +static char * +compile_subst(p, s) + char *p; + struct s_subst *s; +{ + static char lbuf[_POSIX2_LINE_MAX + 1]; + int asize, ref, size; + char c, *text, *op, *sp; + + c = *p++; /* Terminator character */ + if (c == '\0') + return (NULL); + + s->maxbref = 0; + s->linenum = linenum; + asize = 2 * _POSIX2_LINE_MAX + 1; + text = xmalloc(asize); + size = 0; + do { + op = sp = text + size; + for (; *p; p++) { + if (*p == '\\') { + p++; + if (strchr("123456789", *p) != NULL) { + *sp++ = '\\'; + ref = *p - '0'; + if (s->re != NULL && + ref > s->re->re_nsub) + err(COMPILE, +"\\%c not defined in the RE", *p); + if (s->maxbref < ref) + s->maxbref = ref; + } else if (*p == '&' || *p == '\\') + *sp++ = '\\'; + } else if (*p == c) { + p++; + *sp++ = '\0'; + size += sp - op; + s->new = xrealloc(text, size); + return (p); + } else if (*p == '\n') { + err(COMPILE, +"unescaped newline inside substitute pattern"); + /* NOTREACHED */ + } + *sp++ = *p; + } + size += sp - op; + if (asize - size < _POSIX2_LINE_MAX + 1) { + asize *= 2; + text = xmalloc(asize); + } + } while (cu_fgets(p = lbuf, sizeof(lbuf))); + err(COMPILE, "unterminated substitute in regular expression"); + /* NOTREACHED */ +} + +/* + * Compile the flags of the s command + */ +static char * +compile_flags(p, s) + char *p; + struct s_subst *s; +{ + int gn; /* True if we have seen g or n */ + char wfile[_POSIX2_LINE_MAX + 1], *q; + + s->n = 1; /* Default */ + s->p = 0; + s->wfile = NULL; + s->wfd = -1; + for (gn = 0;;) { + EATSPACE(); /* EXTENSION */ + switch (*p) { + case 'g': + if (gn) + err(COMPILE, +"more than one number or 'g' in substitute flags"); + gn = 1; + s->n = 0; + break; + case '\0': + case '\n': + case ';': + return (p); + case 'p': + s->p = 1; + break; + case '1': case '2': case '3': + case '4': case '5': case '6': + case '7': case '8': case '9': + if (gn) + err(COMPILE, +"more than one number or 'g' in substitute flags"); + gn = 1; + /* XXX Check for overflow */ + s->n = (int)strtol(p, &p, 10); + break; + case 'w': + p++; +#ifdef HISTORIC_PRACTICE + if (*p != ' ') { + err(WARNING, "space missing before w wfile"); + return (p); + } +#endif + EATSPACE(); + q = wfile; + while (*p) { + if (*p == '\n') + break; + *q++ = *p++; + } + *q = '\0'; + if (q == wfile) + err(COMPILE, "no wfile specified"); + s->wfile = strdup(wfile); + if (!aflag && (s->wfd = open(wfile, + O_WRONLY|O_APPEND|O_CREAT|O_TRUNC, + DEFFILEMODE)) == -1) + err(FATAL, "%s: %s\n", wfile, strerror(errno)); + return (p); + default: + err(COMPILE, + "bad flag in substitute command: '%c'", *p); + break; + } + p++; + } +} + +/* + * Compile a translation set of strings into a lookup table. + */ +static char * +compile_tr(p, transtab) + char *p; + char **transtab; +{ + int i; + char *lt, *op, *np; + char old[_POSIX2_LINE_MAX + 1]; + char new[_POSIX2_LINE_MAX + 1]; + + if (*p == '\0' || *p == '\\') + err(COMPILE, +"transform pattern can not be delimited by newline or backslash"); + p = compile_delimited(p, old); + if (p == NULL) { + err(COMPILE, "unterminated transform source string"); + return (NULL); + } + p = compile_delimited(--p, new); + if (p == NULL) { + err(COMPILE, "unterminated transform target string"); + return (NULL); + } + EATSPACE(); + if (strlen(new) != strlen(old)) { + err(COMPILE, "transform strings are not the same length"); + return (NULL); + } + /* We assume characters are 8 bits */ + lt = xmalloc(UCHAR_MAX); + for (i = 0; i <= UCHAR_MAX; i++) + lt[i] = (char)i; + for (op = old, np = new; *op; op++, np++) + lt[(u_char)*op] = *np; + *transtab = lt; + return (p); +} + +/* + * Compile the text following an a or i command. + */ +static char * +compile_text() +{ + int asize, size; + char *text, *p, *op, *s; + char lbuf[_POSIX2_LINE_MAX + 1]; + + asize = 2 * _POSIX2_LINE_MAX + 1; + text = xmalloc(asize); + size = 0; + while (cu_fgets(lbuf, sizeof(lbuf))) { + op = s = text + size; + p = lbuf; + EATSPACE(); + for (; *p; p++) { + if (*p == '\\') + p++; + *s++ = *p; + } + size += s - op; + if (p[-2] != '\\') { + *s = '\0'; + break; + } + if (asize - size < _POSIX2_LINE_MAX + 1) { + asize *= 2; + text = xmalloc(asize); + } + } + return (xrealloc(text, size + 1)); +} + +/* + * Get an address and return a pointer to the first character after + * it. Fill the structure pointed to according to the address. + */ +static char * +compile_addr(p, a) + char *p; + struct s_addr *a; +{ + char *end; + + switch (*p) { + case '\\': /* Context address */ + ++p; + /* FALLTHROUGH */ + case '/': /* Context address */ + p = compile_re(p, &a->u.r); + if (p == NULL) + err(COMPILE, "unterminated regular expression"); + a->type = AT_RE; + return (p); + + case '$': /* Last line */ + a->type = AT_LAST; + return (p + 1); + /* Line number */ + case '0': case '1': case '2': case '3': case '4': + case '5': case '6': case '7': case '8': case '9': + a->type = AT_LINE; + a->u.l = strtol(p, &end, 10); + return (end); + default: + err(COMPILE, "expected context address"); + return (NULL); + } +} + +/* + * duptoeol -- + * Return a copy of all the characters up to \n or \0. + */ +static char * +duptoeol(s, ctype) + register char *s; + char *ctype; +{ + size_t len; + int ws; + char *start; + + ws = 0; + for (start = s; *s != '\0' && *s != '\n'; ++s) + ws = isspace(*s); + *s = '\0'; + if (ws) + err(WARNING, "whitespace after %s", ctype); + len = s - start + 1; + return (memmove(xmalloc(len), start, len)); +} + +/* + * Convert goto label names to addresses, and count a and r commands, in + * the given subset of the script. Free the memory used by labels in b + * and t commands (but not by :). + * + * TODO: Remove } nodes + */ +static void +fixuplabel(cp, end) + struct s_command *cp, *end; +{ + + for (; cp != end; cp = cp->next) + switch (cp->code) { + case 'a': + case 'r': + appendnum++; + break; + case 'b': + case 't': + /* Resolve branch target. */ + if (cp->t == NULL) { + cp->u.c = NULL; + break; + } + if ((cp->u.c = findlabel(cp->t)) == NULL) + err(COMPILE2, "undefined label '%s'", cp->t); + free(cp->t); + break; + case '{': + /* Do interior commands. */ + fixuplabel(cp->u.c, cp->next); + break; + } +} + +/* + * Associate the given command label for later lookup. + */ +static void +enterlabel(cp) + struct s_command *cp; +{ + register struct labhash **lhp, *lh; + register u_char *p; + register u_int h, c; + + for (h = 0, p = (u_char *)cp->t; (c = *p) != 0; p++) + h = (h << 5) + h + c; + lhp = &labels[h & LHMASK]; + for (lh = *lhp; lh != NULL; lh = lh->lh_next) + if (lh->lh_hash == h && strcmp(cp->t, lh->lh_cmd->t) == 0) + err(COMPILE2, "duplicate label '%s'", cp->t); + lh = xmalloc(sizeof *lh); + lh->lh_next = *lhp; + lh->lh_hash = h; + lh->lh_cmd = cp; + lh->lh_ref = 0; + *lhp = lh; +} + +/* + * Find the label contained in the command l in the command linked + * list cp. L is excluded from the search. Return NULL if not found. + */ +static struct s_command * +findlabel(name) + char *name; +{ + register struct labhash *lh; + register u_char *p; + register u_int h, c; + + for (h = 0, p = (u_char *)name; (c = *p) != 0; p++) + h = (h << 5) + h + c; + for (lh = labels[h & LHMASK]; lh != NULL; lh = lh->lh_next) { + if (lh->lh_hash == h && strcmp(name, lh->lh_cmd->t) == 0) { + lh->lh_ref = 1; + return (lh->lh_cmd); + } + } + return (NULL); +} + +/* + * Warn about any unused labels. As a side effect, release the label hash + * table space. + */ +static void +uselabel() +{ + register struct labhash *lh, *next; + register int i; + + for (i = 0; i < LHSZ; i++) { + for (lh = labels[i]; lh != NULL; lh = next) { + next = lh->lh_next; + if (!lh->lh_ref) + err(WARNING, "unused label '%s'", + lh->lh_cmd->t); + free(lh); + } + } +} diff --git a/usr.bin/sed/defs.h b/usr.bin/sed/defs.h new file mode 100644 index 0000000..3cc580f --- /dev/null +++ b/usr.bin/sed/defs.h @@ -0,0 +1,144 @@ +/*- + * Copyright (c) 1992 Diomidis Spinellis. + * Copyright (c) 1992, 1993 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Diomidis Spinellis of Imperial College, University of London. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)defs.h 8.1 (Berkeley) 6/6/93 + */ + +/* + * Types of address specifications + */ +enum e_atype { + AT_RE, /* Line that match RE */ + AT_LINE, /* Specific line */ + AT_LAST, /* Last line */ +}; + +/* + * Format of an address + */ +struct s_addr { + enum e_atype type; /* Address type */ + union { + u_long l; /* Line number */ + regex_t *r; /* Regular expression */ + } u; +}; + +/* + * Substitution command + */ +struct s_subst { + int n; /* Occurrence to subst. */ + int p; /* True if p flag */ + char *wfile; /* NULL if no wfile */ + int wfd; /* Cached file descriptor */ + regex_t *re; /* Regular expression */ + int maxbref; /* Largest backreference. */ + u_long linenum; /* Line number. */ + char *new; /* Replacement text */ +}; + + +/* + * An internally compiled command. + * Initialy, label references are stored in t, on a second pass they + * are updated to pointers. + */ +struct s_command { + struct s_command *next; /* Pointer to next command */ + struct s_addr *a1, *a2; /* Start and end address */ + char *t; /* Text for : a c i r w */ + union { + struct s_command *c; /* Command(s) for b t { */ + struct s_subst *s; /* Substitute command */ + u_char *y; /* Replace command array */ + int fd; /* File descriptor for w */ + } u; + char code; /* Command code */ + u_int nonsel:1; /* True if ! */ + u_int inrange:1; /* True if in range */ +}; + +/* + * Types of command arguments recognised by the parser + */ +enum e_args { + EMPTY, /* d D g G h H l n N p P q x = \0 */ + TEXT, /* a c i */ + NONSEL, /* ! */ + GROUP, /* { */ + COMMENT, /* # */ + BRANCH, /* b t */ + LABEL, /* : */ + RFILE, /* r */ + WFILE, /* w */ + SUBST, /* s */ + TR /* y */ +}; + +/* + * Structure containing things to append before a line is read + */ +struct s_appends { + enum {AP_STRING, AP_FILE} type; + char *s; + size_t len; +}; + +enum e_spflag { + APPEND, /* Append to the contents. */ + REPLACE, /* Replace the contents. */ +}; + +/* + * Structure for a space (process, hold, otherwise). + */ +typedef struct { + char *space; /* Current space pointer. */ + size_t len; /* Current length. */ + int deleted; /* If deleted. */ + char *back; /* Backing memory. */ + size_t blen; /* Backing memory length. */ +} SPACE; + +/* + * Error severity codes: + */ +#define FATAL 0 /* Exit immediately with 1 */ +#define ERROR 1 /* Continue, but change exit value */ +#define WARNING 2 /* Just print the warning */ +#define COMPILE 3 /* Print error, count and finish script */ +#define COMPILE2 3 /* Print error, count and finish script */ diff --git a/usr.bin/sed/extern.h b/usr.bin/sed/extern.h new file mode 100644 index 0000000..54f2fb5 --- /dev/null +++ b/usr.bin/sed/extern.h @@ -0,0 +1,59 @@ +/*- + * Copyright (c) 1992 Diomidis Spinellis. + * Copyright (c) 1992, 1993 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Diomidis Spinellis of Imperial College, University of London. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + * + * @(#)extern.h 8.1 (Berkeley) 6/6/93 + */ + +extern struct s_command *prog; +extern struct s_appends *appends; +extern regmatch_t *match; +extern size_t maxnsub; +extern u_long linenum; +extern int appendnum; +extern int lastline; +extern int aflag, eflag, nflag; +extern char *fname; + +void cfclose __P((struct s_command *, struct s_command *)); +void compile __P((void)); +void cspace __P((SPACE *, char *, size_t, enum e_spflag)); +char *cu_fgets __P((char *, int)); +void err __P((int, const char *, ...)); +int mf_fgets __P((SPACE *, enum e_spflag)); +void process __P((void)); +char *strregerror __P((int, regex_t *)); +void *xmalloc __P((u_int)); +void *xrealloc __P((void *, u_int)); diff --git a/usr.bin/sed/main.c b/usr.bin/sed/main.c new file mode 100644 index 0000000..14872fd --- /dev/null +++ b/usr.bin/sed/main.c @@ -0,0 +1,352 @@ +/*- + * Copyright (c) 1992 Diomidis Spinellis. + * Copyright (c) 1992, 1993 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Diomidis Spinellis of Imperial College, University of London. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef lint +static char copyright[] = +"@(#) Copyright (c) 1992, 1993\n\ + The Regents of the University of California. All rights reserved.\n"; +#endif /* not lint */ + +#ifndef lint +static char sccsid[] = "@(#)main.c 8.2 (Berkeley) 1/3/94"; +#endif /* not lint */ + +#include <sys/types.h> + +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <regex.h> +#include <stddef.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include "defs.h" +#include "extern.h" + +/* + * Linked list of units (strings and files) to be compiled + */ +struct s_compunit { + struct s_compunit *next; + enum e_cut {CU_FILE, CU_STRING} type; + char *s; /* Pointer to string or fname */ +}; + +/* + * Linked list pointer to compilation units and pointer to current + * next pointer. + */ +static struct s_compunit *script, **cu_nextp = &script; + +/* + * Linked list of files to be processed + */ +struct s_flist { + char *fname; + struct s_flist *next; +}; + +/* + * Linked list pointer to files and pointer to current + * next pointer. + */ +static struct s_flist *files, **fl_nextp = &files; + +int aflag, eflag, nflag; + +/* + * Current file and line number; line numbers restart across compilation + * units, but span across input files. + */ +char *fname; /* File name. */ +u_long linenum; +int lastline; /* TRUE on the last line of the last file */ + +static void add_compunit __P((enum e_cut, char *)); +static void add_file __P((char *)); + +int +main(argc, argv) + int argc; + char *argv[]; +{ + int c, fflag; + + fflag = 0; + while ((c = getopt(argc, argv, "ae:f:n")) != EOF) + switch (c) { + case 'a': + aflag = 1; + break; + case 'e': + eflag = 1; + add_compunit(CU_STRING, optarg); + break; + case 'f': + fflag = 1; + add_compunit(CU_FILE, optarg); + break; + case 'n': + nflag = 1; + break; + default: + case '?': + (void)fprintf(stderr, +"usage:\tsed script [-an] [file ...]\n\tsed [-an] [-e script] ... [-f scipt_file] ... [file ...]\n"); + exit(1); + } + argc -= optind; + argv += optind; + + /* First usage case; script is the first arg */ + if (!eflag && !fflag && *argv) { + add_compunit(CU_STRING, *argv); + argv++; + } + + compile(); + + /* Continue with first and start second usage */ + if (*argv) + for (; *argv; argv++) + add_file(*argv); + else + add_file(NULL); + process(); + cfclose(prog, NULL); + if (fclose(stdout)) + err(FATAL, "stdout: %s", strerror(errno)); + exit (0); +} + +/* + * Like fgets, but go through the chain of compilation units chaining them + * together. Empty strings and files are ignored. + */ +char * +cu_fgets(buf, n) + char *buf; + int n; +{ + static enum {ST_EOF, ST_FILE, ST_STRING} state = ST_EOF; + static FILE *f; /* Current open file */ + static char *s; /* Current pointer inside string */ + static char string_ident[30]; + char *p; + +again: + switch (state) { + case ST_EOF: + if (script == NULL) + return (NULL); + linenum = 0; + switch (script->type) { + case CU_FILE: + if ((f = fopen(script->s, "r")) == NULL) + err(FATAL, + "%s: %s", script->s, strerror(errno)); + fname = script->s; + state = ST_FILE; + goto again; + case CU_STRING: + if ((snprintf(string_ident, + sizeof(string_ident), "\"%s\"", script->s)) >= + sizeof(string_ident) - 1) + (void)strcpy(string_ident + + sizeof(string_ident) - 6, " ...\""); + fname = string_ident; + s = script->s; + state = ST_STRING; + goto again; + } + case ST_FILE: + if ((p = fgets(buf, n, f)) != NULL) { + linenum++; + if (linenum == 1 && buf[0] == '#' && buf[1] == 'n') + nflag = 1; + return (p); + } + script = script->next; + (void)fclose(f); + state = ST_EOF; + goto again; + case ST_STRING: + if (linenum == 0 && s[0] == '#' && s[1] == 'n') + nflag = 1; + p = buf; + for (;;) { + if (n-- <= 1) { + *p = '\0'; + linenum++; + return (buf); + } + switch (*s) { + case '\0': + state = ST_EOF; + if (s == script->s) { + script = script->next; + goto again; + } else { + script = script->next; + *p = '\0'; + linenum++; + return (buf); + } + case '\n': + *p++ = '\n'; + *p = '\0'; + s++; + linenum++; + return (buf); + default: + *p++ = *s++; + } + } + } + /* NOTREACHED */ +} + +/* + * Like fgets, but go through the list of files chaining them together. + * Set len to the length of the line. + */ +int +mf_fgets(sp, spflag) + SPACE *sp; + enum e_spflag spflag; +{ + static FILE *f; /* Current open file */ + size_t len; + char c, *p; + + if (f == NULL) + /* Advance to first non-empty file */ + for (;;) { + if (files == NULL) { + lastline = 1; + return (0); + } + if (files->fname == NULL) { + f = stdin; + fname = "stdin"; + } else { + fname = files->fname; + if ((f = fopen(fname, "r")) == NULL) + err(FATAL, "%s: %s", + fname, strerror(errno)); + } + if ((c = getc(f)) != EOF) { + (void)ungetc(c, f); + break; + } + (void)fclose(f); + files = files->next; + } + + if (lastline) { + sp->len = 0; + return (0); + } + + /* + * Use fgetln so that we can handle essentially infinite input data. + * Can't use the pointer into the stdio buffer as the process space + * because the ungetc() can cause it to move. + */ + p = fgetln(f, &len); + if (ferror(f)) + err(FATAL, "%s: %s", fname, strerror(errno ? errno : EIO)); + cspace(sp, p, len, spflag); + + linenum++; + /* Advance to next non-empty file */ + while ((c = getc(f)) == EOF) { + (void)fclose(f); + files = files->next; + if (files == NULL) { + lastline = 1; + return (1); + } + if (files->fname == NULL) { + f = stdin; + fname = "stdin"; + } else { + fname = files->fname; + if ((f = fopen(fname, "r")) == NULL) + err(FATAL, "%s: %s", fname, strerror(errno)); + } + } + (void)ungetc(c, f); + return (1); +} + +/* + * Add a compilation unit to the linked list + */ +static void +add_compunit(type, s) + enum e_cut type; + char *s; +{ + struct s_compunit *cu; + + cu = xmalloc(sizeof(struct s_compunit)); + cu->type = type; + cu->s = s; + cu->next = NULL; + *cu_nextp = cu; + cu_nextp = &cu->next; +} + +/* + * Add a file to the linked list + */ +static void +add_file(s) + char *s; +{ + struct s_flist *fp; + + fp = xmalloc(sizeof(struct s_flist)); + fp->next = NULL; + *fl_nextp = fp; + fp->fname = s; + fl_nextp = &fp->next; +} diff --git a/usr.bin/sed/misc.c b/usr.bin/sed/misc.c new file mode 100644 index 0000000..444b7a8 --- /dev/null +++ b/usr.bin/sed/misc.c @@ -0,0 +1,141 @@ +/*- + * Copyright (c) 1992 Diomidis Spinellis. + * Copyright (c) 1992, 1993 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Diomidis Spinellis of Imperial College, University of London. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef lint +static char sccsid[] = "@(#)misc.c 8.1 (Berkeley) 6/6/93"; +#endif /* not lint */ + +#include <sys/types.h> + +#include <errno.h> +#include <regex.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> + +#include "defs.h" +#include "extern.h" + +/* + * malloc with result test + */ +void * +xmalloc(size) + u_int size; +{ + void *p; + + if ((p = malloc(size)) == NULL) + err(FATAL, "%s", strerror(errno)); + return (p); +} + +/* + * realloc with result test + */ +void * +xrealloc(p, size) + void *p; + u_int size; +{ + if (p == NULL) /* Compatibility hack. */ + return (xmalloc(size)); + + if ((p = realloc(p, size)) == NULL) + err(FATAL, "%s", strerror(errno)); + return (p); +} + +/* + * Return a string for a regular expression error passed. This is a overkill, + * because of the silly semantics of regerror (we can never know the size of + * the buffer). + */ +char * +strregerror(errcode, preg) + int errcode; + regex_t *preg; +{ + static char *oe; + size_t s; + + if (oe != NULL) + free(oe); + s = regerror(errcode, preg, "", 0); + oe = xmalloc(s); + (void)regerror(errcode, preg, oe, s); + return (oe); +} + +#if __STDC__ +#include <stdarg.h> +#else +#include <varargs.h> +#endif +/* + * Error reporting function + */ +void +#if __STDC__ +err(int severity, const char *fmt, ...) +#else +err(severity, fmt, va_alist) + int severity; + char *fmt; + va_dcl +#endif +{ + va_list ap; +#if __STDC__ + va_start(ap, fmt); +#else + va_start(ap); +#endif + (void)fprintf(stderr, "sed: "); + switch (severity) { + case WARNING: + case COMPILE: + (void)fprintf(stderr, "%lu: %s: ", linenum, fname); + } + (void)vfprintf(stderr, fmt, ap); + va_end(ap); + (void)fprintf(stderr, "\n"); + if (severity == WARNING) + return; + exit(1); + /* NOTREACHED */ +} diff --git a/usr.bin/sed/process.c b/usr.bin/sed/process.c new file mode 100644 index 0000000..2ec8aac --- /dev/null +++ b/usr.bin/sed/process.c @@ -0,0 +1,629 @@ +/*- + * Copyright (c) 1992 Diomidis Spinellis. + * Copyright (c) 1992, 1993, 1994 + * The Regents of the University of California. All rights reserved. + * + * This code is derived from software contributed to Berkeley by + * Diomidis Spinellis of Imperial College, University of London. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. All advertising materials mentioning features or use of this software + * must display the following acknowledgement: + * This product includes software developed by the University of + * California, Berkeley and its contributors. + * 4. Neither the name of the University nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * + * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND + * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE + * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL + * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS + * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) + * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT + * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY + * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef lint +static char sccsid[] = "@(#)process.c 8.6 (Berkeley) 4/20/94"; +#endif /* not lint */ + +#include <sys/types.h> +#include <sys/stat.h> +#include <sys/ioctl.h> +#include <sys/uio.h> + +#include <ctype.h> +#include <errno.h> +#include <fcntl.h> +#include <limits.h> +#include <regex.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <unistd.h> + +#include "defs.h" +#include "extern.h" + +static SPACE HS, PS, SS; +#define pd PS.deleted +#define ps PS.space +#define psl PS.len +#define hs HS.space +#define hsl HS.len + +static inline int applies __P((struct s_command *)); +static void flush_appends __P((void)); +static void lputs __P((char *)); +static inline int regexec_e __P((regex_t *, const char *, int, int, size_t)); +static void regsub __P((SPACE *, char *, char *)); +static int substitute __P((struct s_command *)); + +struct s_appends *appends; /* Array of pointers to strings to append. */ +static int appendx; /* Index into appends array. */ +int appendnum; /* Size of appends array. */ + +static int lastaddr; /* Set by applies if last address of a range. */ +static int sdone; /* If any substitutes since last line input. */ + /* Iov structure for 'w' commands. */ +static regex_t *defpreg; +size_t maxnsub; +regmatch_t *match; + +#define OUT(s) { fwrite(s, sizeof(u_char), psl, stdout); } + +void +process() +{ + struct s_command *cp; + SPACE tspace; + size_t len; + char oldc, *p; + + for (linenum = 0; mf_fgets(&PS, REPLACE);) { + pd = 0; + cp = prog; +redirect: + while (cp != NULL) { + if (!applies(cp)) { + cp = cp->next; + continue; + } + switch (cp->code) { + case '{': + cp = cp->u.c; + goto redirect; + case 'a': + if (appendx >= appendnum) + appends = xrealloc(appends, + sizeof(struct s_appends) * + (appendnum *= 2)); + appends[appendx].type = AP_STRING; + appends[appendx].s = cp->t; + appends[appendx].len = strlen(cp->t); + appendx++; + break; + case 'b': + cp = cp->u.c; + goto redirect; + case 'c': + pd = 1; + psl = 0; + if (cp->a2 == NULL || lastaddr) + (void)printf("%s", cp->t); + break; + case 'd': + pd = 1; + goto new; + case 'D': + if (pd) + goto new; + if ((p = memchr(ps, '\n', psl)) == NULL) + pd = 1; + else { + psl -= (p - ps) + 1; + memmove(ps, p + 1, psl); + } + goto new; + case 'g': + cspace(&PS, hs, hsl, REPLACE); + break; + case 'G': + cspace(&PS, hs, hsl, 0); + break; + case 'h': + cspace(&HS, ps, psl, REPLACE); + break; + case 'H': + cspace(&HS, ps, psl, 0); + break; + case 'i': + (void)printf("%s", cp->t); + break; + case 'l': + lputs(ps); + break; + case 'n': + if (!nflag && !pd) + OUT(ps) + flush_appends(); + if (!mf_fgets(&PS, REPLACE)) + exit(0); + pd = 0; + break; + case 'N': + flush_appends(); + if (!mf_fgets(&PS, 0)) { + if (!nflag && !pd) + OUT(ps) + exit(0); + } + break; + case 'p': + if (pd) + break; + OUT(ps) + break; + case 'P': + if (pd) + break; + if ((p = memchr(ps, '\n', psl)) != NULL) { + oldc = *p; + *p = '\0'; + } + OUT(ps) + if (p != NULL) + *p = oldc; + break; + case 'q': + if (!nflag && !pd) + OUT(ps) + flush_appends(); + exit(0); + case 'r': + if (appendx >= appendnum) + appends = xrealloc(appends, + sizeof(struct s_appends) * + (appendnum *= 2)); + appends[appendx].type = AP_FILE; + appends[appendx].s = cp->t; + appends[appendx].len = strlen(cp->t); + appendx++; + break; + case 's': + sdone |= substitute(cp); + break; + case 't': + if (sdone) { + sdone = 0; + cp = cp->u.c; + goto redirect; + } + break; + case 'w': + if (pd) + break; + if (cp->u.fd == -1 && (cp->u.fd = open(cp->t, + O_WRONLY|O_APPEND|O_CREAT|O_TRUNC, + DEFFILEMODE)) == -1) + err(FATAL, "%s: %s\n", + cp->t, strerror(errno)); + if (write(cp->u.fd, ps, psl) != psl) + err(FATAL, "%s: %s\n", + cp->t, strerror(errno)); + break; + case 'x': + if (hs == NULL) + cspace(&HS, "", 0, REPLACE); + tspace = PS; + PS = HS; + HS = tspace; + break; + case 'y': + if (pd) + break; + for (p = ps, len = psl; --len; ++p) + *p = cp->u.y[*p]; + break; + case ':': + case '}': + break; + case '=': + (void)printf("%lu\n", linenum); + } + cp = cp->next; + } /* for all cp */ + +new: if (!nflag && !pd) + OUT(ps) + flush_appends(); + } /* for all lines */ +} + +/* + * TRUE if the address passed matches the current program state + * (lastline, linenumber, ps). + */ +#define MATCH(a) \ + (a)->type == AT_RE ? regexec_e((a)->u.r, ps, 0, 1, psl) : \ + (a)->type == AT_LINE ? linenum == (a)->u.l : lastline + +/* + * Return TRUE if the command applies to the current line. Sets the inrange + * flag to process ranges. Interprets the non-select (``!'') flag. + */ +static inline int +applies(cp) + struct s_command *cp; +{ + int r; + + lastaddr = 0; + if (cp->a1 == NULL && cp->a2 == NULL) + r = 1; + else if (cp->a2) + if (cp->inrange) { + if (MATCH(cp->a2)) { + cp->inrange = 0; + lastaddr = 1; + } + r = 1; + } else if (MATCH(cp->a1)) { + /* + * If the second address is a number less than or + * equal to the line number first selected, only + * one line shall be selected. + * -- POSIX 1003.2 + */ + if (cp->a2->type == AT_LINE && + linenum >= cp->a2->u.l) + lastaddr = 1; + else + cp->inrange = 1; + r = 1; + } else + r = 0; + else + r = MATCH(cp->a1); + return (cp->nonsel ? ! r : r); +} + +/* + * substitute -- + * Do substitutions in the pattern space. Currently, we build a + * copy of the new pattern space in the substitute space structure + * and then swap them. + */ +static int +substitute(cp) + struct s_command *cp; +{ + SPACE tspace; + regex_t *re; + size_t re_off, slen; + int lastempty, n; + char *s; + + s = ps; + re = cp->u.s->re; + if (re == NULL) { + if (defpreg != NULL && cp->u.s->maxbref > defpreg->re_nsub) { + linenum = cp->u.s->linenum; + err(COMPILE, "\\%d not defined in the RE", + cp->u.s->maxbref); + } + } + if (!regexec_e(re, s, 0, 0, psl)) + return (0); + + SS.len = 0; /* Clean substitute space. */ + slen = psl; + n = cp->u.s->n; + lastempty = 1; + + switch (n) { + case 0: /* Global */ + do { + if (lastempty || match[0].rm_so != match[0].rm_eo) { + /* Locate start of replaced string. */ + re_off = match[0].rm_so; + /* Copy leading retained string. */ + cspace(&SS, s, re_off, APPEND); + /* Add in regular expression. */ + regsub(&SS, s, cp->u.s->new); + } + + /* Move past this match. */ + if (match[0].rm_so != match[0].rm_eo) { + s += match[0].rm_eo; + slen -= match[0].rm_eo; + lastempty = 0; + } else { + if (match[0].rm_so == 0) + cspace(&SS, + s, match[0].rm_so + 1, APPEND); + else + cspace(&SS, + s + match[0].rm_so, 1, APPEND); + s += match[0].rm_so + 1; + slen -= match[0].rm_so + 1; + lastempty = 1; + } + } while (slen > 0 && regexec_e(re, s, REG_NOTBOL, 0, slen)); + /* Copy trailing retained string. */ + if (slen > 0) + cspace(&SS, s, slen, APPEND); + break; + default: /* Nth occurrence */ + while (--n) { + s += match[0].rm_eo; + slen -= match[0].rm_eo; + if (!regexec_e(re, s, REG_NOTBOL, 0, slen)) + return (0); + } + /* FALLTHROUGH */ + case 1: /* 1st occurrence */ + /* Locate start of replaced string. */ + re_off = match[0].rm_so + (s - ps); + /* Copy leading retained string. */ + cspace(&SS, ps, re_off, APPEND); + /* Add in regular expression. */ + regsub(&SS, s, cp->u.s->new); + /* Copy trailing retained string. */ + s += match[0].rm_eo; + slen -= match[0].rm_eo; + cspace(&SS, s, slen, APPEND); + break; + } + + /* + * Swap the substitute space and the pattern space, and make sure + * that any leftover pointers into stdio memory get lost. + */ + tspace = PS; + PS = SS; + SS = tspace; + SS.space = SS.back; + + /* Handle the 'p' flag. */ + if (cp->u.s->p) + OUT(ps) + + /* Handle the 'w' flag. */ + if (cp->u.s->wfile && !pd) { + if (cp->u.s->wfd == -1 && (cp->u.s->wfd = open(cp->u.s->wfile, + O_WRONLY|O_APPEND|O_CREAT|O_TRUNC, DEFFILEMODE)) == -1) + err(FATAL, "%s: %s\n", cp->u.s->wfile, strerror(errno)); + if (write(cp->u.s->wfd, ps, psl) != psl) + err(FATAL, "%s: %s\n", cp->u.s->wfile, strerror(errno)); + } + return (1); +} + +/* + * Flush append requests. Always called before reading a line, + * therefore it also resets the substitution done (sdone) flag. + */ +static void +flush_appends() +{ + FILE *f; + int count, i; + char buf[8 * 1024]; + + for (i = 0; i < appendx; i++) + switch (appends[i].type) { + case AP_STRING: + fwrite(appends[i].s, sizeof(char), appends[i].len, + stdout); + break; + case AP_FILE: + /* + * Read files probably shouldn't be cached. Since + * it's not an error to read a non-existent file, + * it's possible that another program is interacting + * with the sed script through the file system. It + * would be truly bizarre, but possible. It's probably + * not that big a performance win, anyhow. + */ + if ((f = fopen(appends[i].s, "r")) == NULL) + break; + while (count = fread(buf, sizeof(char), sizeof(buf), f)) + (void)fwrite(buf, sizeof(char), count, stdout); + (void)fclose(f); + break; + } + if (ferror(stdout)) + err(FATAL, "stdout: %s", strerror(errno ? errno : EIO)); + appendx = sdone = 0; +} + +static void +lputs(s) + register char *s; +{ + register int count; + register char *escapes, *p; + struct winsize win; + static int termwidth = -1; + + if (termwidth == -1) + if (p = getenv("COLUMNS")) + termwidth = atoi(p); + else if (ioctl(STDOUT_FILENO, TIOCGWINSZ, &win) == 0 && + win.ws_col > 0) + termwidth = win.ws_col; + else + termwidth = 60; + + for (count = 0; *s; ++s) { + if (count >= termwidth) { + (void)printf("\\\n"); + count = 0; + } + if (isascii(*s) && isprint(*s) && *s != '\\') { + (void)putchar(*s); + count++; + } else { + escapes = "\\\a\b\f\n\r\t\v"; + (void)putchar('\\'); + if (p = strchr(escapes, *s)) { + (void)putchar("\\abfnrtv"[p - escapes]); + count += 2; + } else { + (void)printf("%03o", *(u_char *)s); + count += 4; + } + } + } + (void)putchar('$'); + (void)putchar('\n'); + if (ferror(stdout)) + err(FATAL, "stdout: %s", strerror(errno ? errno : EIO)); +} + +static inline int +regexec_e(preg, string, eflags, nomatch, slen) + regex_t *preg; + const char *string; + int eflags, nomatch; + size_t slen; +{ + int eval; + + if (preg == NULL) { + if (defpreg == NULL) + err(FATAL, "first RE may not be empty"); + } else + defpreg = preg; + + /* Set anchors, discounting trailing newline (if any). */ + if (slen > 0 && string[slen - 1] == '\n') + slen--; + match[0].rm_so = 0; + match[0].rm_eo = slen; + + eval = regexec(defpreg, string, + nomatch ? 0 : maxnsub + 1, match, eflags | REG_STARTEND); + switch(eval) { + case 0: + return (1); + case REG_NOMATCH: + return (0); + } + err(FATAL, "RE error: %s", strregerror(eval, defpreg)); + /* NOTREACHED */ +} + +/* + * regsub - perform substitutions after a regexp match + * Based on a routine by Henry Spencer + */ +static void +regsub(sp, string, src) + SPACE *sp; + char *string, *src; +{ + register int len, no; + register char c, *dst; + +#define NEEDSP(reqlen) \ + if (sp->len >= sp->blen - (reqlen) - 1) { \ + sp->blen += (reqlen) + 1024; \ + sp->space = sp->back = xrealloc(sp->back, sp->blen); \ + dst = sp->space + sp->len; \ + } + + dst = sp->space + sp->len; + while ((c = *src++) != '\0') { + if (c == '&') + no = 0; + else if (c == '\\' && isdigit(*src)) + no = *src++ - '0'; + else + no = -1; + if (no < 0) { /* Ordinary character. */ + if (c == '\\' && (*src == '\\' || *src == '&')) + c = *src++; + NEEDSP(1); + *dst++ = c; + ++sp->len; + } else if (match[no].rm_so != -1 && match[no].rm_eo != -1) { + len = match[no].rm_eo - match[no].rm_so; + NEEDSP(len); + memmove(dst, string + match[no].rm_so, len); + dst += len; + sp->len += len; + } + } + NEEDSP(1); + *dst = '\0'; +} + +/* + * aspace -- + * Append the source space to the destination space, allocating new + * space as necessary. + */ +void +cspace(sp, p, len, spflag) + SPACE *sp; + char *p; + size_t len; + enum e_spflag spflag; +{ + size_t tlen; + + /* Make sure SPACE has enough memory and ramp up quickly. */ + tlen = sp->len + len + 1; + if (tlen > sp->blen) { + sp->blen = tlen + 1024; + sp->space = sp->back = xrealloc(sp->back, sp->blen); + } + + if (spflag == REPLACE) + sp->len = 0; + + memmove(sp->space + sp->len, p, len); + + sp->space[sp->len += len] = '\0'; +} + +/* + * Close all cached opened files and report any errors + */ +void +cfclose(cp, end) + register struct s_command *cp, *end; +{ + + for (; cp != end; cp = cp->next) + switch(cp->code) { + case 's': + if (cp->u.s->wfd != -1 && close(cp->u.s->wfd)) + err(FATAL, + "%s: %s", cp->u.s->wfile, strerror(errno)); + cp->u.s->wfd = -1; + break; + case 'w': + if (cp->u.fd != -1 && close(cp->u.fd)) + err(FATAL, "%s: %s", cp->t, strerror(errno)); + cp->u.fd = -1; + break; + case '{': + cfclose(cp->u.c, cp->next); + break; + } +} diff --git a/usr.bin/sed/sed.1 b/usr.bin/sed/sed.1 new file mode 100644 index 0000000..63bcd32 --- /dev/null +++ b/usr.bin/sed/sed.1 @@ -0,0 +1,514 @@ +.\" Copyright (c) 1992, 1993 +.\" The Regents of the University of California. All rights reserved. +.\" +.\" This code is derived from software contributed to Berkeley by +.\" the Institute of Electrical and Electronics Engineers, Inc. +.\" +.\" Redistribution and use in source and binary forms, with or without +.\" modification, are permitted provided that the following conditions +.\" are met: +.\" 1. Redistributions of source code must retain the above copyright +.\" notice, this list of conditions and the following disclaimer. +.\" 2. Redistributions in binary form must reproduce the above copyright +.\" notice, this list of conditions and the following disclaimer in the +.\" documentation and/or other materials provided with the distribution. +.\" 3. All advertising materials mentioning features or use of this software +.\" must display the following acknowledgement: +.\" This product includes software developed by the University of +.\" California, Berkeley and its contributors. +.\" 4. Neither the name of the University nor the names of its contributors +.\" may be used to endorse or promote products derived from this software +.\" without specific prior written permission. +.\" +.\" THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND +.\" ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE +.\" IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE +.\" ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE +.\" FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL +.\" DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS +.\" OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) +.\" HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT +.\" LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY +.\" OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF +.\" SUCH DAMAGE. +.\" +.\" @(#)sed.1 8.2 (Berkeley) 12/30/93 +.\" +.Dd "December 30, 1993" +.Dt SED 1 +.Os +.Sh NAME +.Nm sed +.Nd stream editor +.Sh SYNOPSIS +.Nm sed +.Op Fl an +.Ar command +.Op Ar file ... +.Nm sed +.Op Fl an +.Op Fl e Ar command +.Op Fl f Ar command_file +.Op Ar file ... +.Sh DESCRIPTION +The +.Nm sed +utility reads the specified files, or the standard input if no files +are specified, modifying the input as specified by a list of commands. +The input is then written to the standard output. +.Pp +A single command may be specified as the first argument to +.Nm sed . +Multiple commands may be specified by using the +.Fl e +or +.Fl f +options. +All commands are applied to the input in the order they are specified +regardless of their origin. +.Pp +The following options are available: +.Bl -tag -width indent +.It Fl a +The files listed as parameters for the +.Dq w +functions are created (or truncated) before any processing begins, +by default. +The +.Fl a +option causes +.Nm sed +to delay opening each file until a command containing the related +.Dq w +function is applied to a line of input. +.It Fl e Ar command +Append the editing commands specified by the +.Ar command +argument +to the list of commands. +.It Fl f Ar command_file +Append the editing commands found in the file +.Ar command_file +to the list of commands. +The editing commands should each be listed on a separate line. +.It Fl n +By default, each line of input is echoed to the standard output after +all of the commands have been applied to it. +The +.Fl n +option suppresses this behavior. +.El +.Pp +The form of a +.Nm sed +command is as follows: +.sp +.Dl [address[,address]]function[arguments] +.sp +Whitespace may be inserted before the first address and the function +portions of the command. +.Pp +Normally, +.Nm sed +cyclically copies a line of input, not including its terminating newline +character, into a +.Em "pattern space" , +(unless there is something left after a +.Dq D +function), +applies all of the commands with addresses that select that pattern space, +copies the pattern space to the standard output, appending a newline, and +deletes the pattern space. +.Pp +Some of the functions use a +.Em "hold space" +to save all or part of the pattern space for subsequent retrieval. +.Sh "Sed Addresses" +An address is not required, but if specified must be a number (that counts +input lines +cumulatively across input files), a dollar +.Po +.Dq $ +.Pc +character that addresses the last line of input, or a context address +(which consists of a regular expression preceded and followed by a +delimiter). +.Pp +A command line with no addresses selects every pattern space. +.Pp +A command line with one address selects all of the pattern spaces +that match the address. +.Pp +A command line with two addresses selects the inclusive range from +the first pattern space that matches the first address through the next +pattern space that matches the second. +(If the second address is a number less than or equal to the line number +first selected, only that line is selected.) +Starting at the first line following the selected range, +.Nm sed +starts looking again for the first address. +.Pp +Editing commands can be applied to non-selected pattern spaces by use +of the exclamation character +.Po +.Dq ! +.Pc +function. +.Sh "Sed Regular Expressions" +The +.Nm sed +regular expressions are basic regular expressions (BRE's, see +.Xr regex 3 +for more information). +In addition, +.Nm sed +has the following two additions to BRE's: +.sp +.Bl -enum -compact +.It +In a context address, any character other than a backslash +.Po +.Dq \e +.Pc +or newline character may be used to delimit the regular expression. +Also, putting a backslash character before the delimiting character +causes the character to be treated literally. +For example, in the context address \exabc\exdefx, the RE delimiter +is an +.Dq x +and the second +.Dq x +stands for itself, so that the regular expression is +.Dq abcxdef . +.sp +.It +The escape sequence \en matches a newline character embedded in the +pattern space. +You can't, however, use a literal newline character in an address or +in the substitute command. +.El +.Pp +One special feature of +.Nm sed +regular expressions is that they can default to the last regular +expression used. +If a regular expression is empty, i.e. just the delimiter characters +are specified, the last regular expression encountered is used instead. +The last regular expression is defined as the last regular expression +used as part of an address or substitute command, and at run-time, not +compile-time. +For example, the command +.Dq /abc/s//XXX/ +will substitute +.Dq XXX +for the pattern +.Dq abc . +.Sh "Sed Functions" +In the following list of commands, the maximum number of permissible +addresses for each command is indicated by [0addr], [1addr], or [2addr], +representing zero, one, or two addresses. +.Pp +The argument +.Em text +consists of one or more lines. +To embed a newline in the text, precede it with a backslash. +Other backslashes in text are deleted and the following character +taken literally. +.Pp +The +.Dq r +and +.Dq w +functions take an optional file parameter, which should be separated +from the function letter by white space. +Each file given as an argument to +.Nm sed +is created (or its contents truncated) before any input processing begins. +.Pp +The +.Dq b , +.Dq r , +.Dq s , +.Dq t , +.Dq w , +.Dq y , +.Dq ! , +and +.Dq \&: +functions all accept additional arguments. +The following synopses indicate which arguments have to be separated from +the function letters by white space characters. +.Pp +Two of the functions take a function-list. +This is a list of +.Nm sed +functions separated by newlines, as follows: +.Bd -literal -offset indent +{ function + function + ... + function +} +.Ed +.Pp +The +.Dq { +can be preceded by white space and can be followed by white space. +The function can be preceded by white space. +The terminating +.Dq } +must be preceded by a newline or optional white space. +.sp +.Bl -tag -width "XXXXXX" -compact +.It [2addr] function-list +Execute function-list only when the pattern space is selected. +.sp +.It [1addr]a\e +.It text +.br +Write +.Em text +to standard output immediately before each attempt to read a line of input, +whether by executing the +.Dq N +function or by beginning a new cycle. +.sp +.It [2addr]b[lable] +Branch to the +.Dq \&: +function with the specified label. +If the label is not specified, branch to the end of the script. +.sp +.It [2addr]c\e +.It text +.br +Delete the pattern space. +With 0 or 1 address or at the end of a 2-address range, +.Em text +is written to the standard output. +.sp +.It [2addr]d +Delete the pattern space and start the next cycle. +.sp +.It [2addr]D +Delete the initial segment of the pattern space through the first +newline character and start the next cycle. +.sp +.It [2addr]g +Replace the contents of the pattern space with the contents of the +hold space. +.sp +.It [2addr]G +Append a newline character followed by the contents of the hold space +to the pattern space. +.sp +.It [2addr]h +Replace the contents of the hold space with the contents of the +pattern space. +.sp +.It [2addr]H +Append a newline character followed by the contents of the pattern space +to the hold space. +.sp +.It [1addr]i\e +.It text +.br +Write +.Em text +to the standard output. +.sp +.It [2addr]l +(The letter ell.) +Write the pattern space to the standard output in a visually unambiguous +form. +This form is as follows: +.sp +.Bl -tag -width "carriage-returnXX" -offset indent -compact +.It backslash +\e +.It alert +\ea +.It form-feed +\ef +.It newline +\en +.It carriage-return +\er +.It tab +\et +.It vertical tab +\ev +.El +.Pp +Nonprintable characters are written as three-digit octal numbers (with a +preceding backslash) for each byte in the character (most significant byte +first). +Long lines are folded, with the point of folding indicated by displaying +a backslash followed by a newline. +The end of each line is marked with a +.Dq $ . +.sp +.It [2addr]n +Write the pattern space to the standard output if the default output has +not been suppressed, and replace the pattern space with the next line of +input. +.sp +.It [2addr]N +Append the next line of input to the pattern space, using an embedded +newline character to separate the appended material from the original +contents. +Note that the current line number changes. +.sp +.It [2addr]p +Write the pattern space to standard output. +.sp +.It [2addr]P +Write the pattern space, up to the first newline character to the +standard output. +.sp +.It [1addr]q +Branch to the end of the script and quit without starting a new cycle. +.sp +.It [1addr]r file +Copy the contents of +.Em file +to the standard output immediately before the next attempt to read a +line of input. +If +.Em file +cannot be read for any reason, it is silently ignored and no error +condition is set. +.sp +.It [2addr]s/regular expression/replacement/flags +Substitute the replacement string for the first instance of the regular +expression in the pattern space. +Any character other than backslash or newline can be used instead of +a slash to delimit the RE and the replacement. +Within the RE and the replacement, the RE delimiter itself can be used as +a literal character if it is preceded by a backslash. +.Pp +An ampersand +.Po +.Dq & +.Pc +appearing in the replacement is replaced by the string matching the RE. +The special meaning of +.Dq & +in this context can be suppressed by preceding it by a backslash. +The string +.Dq \e# , +where +.Dq # +is a digit, is replaced by the text matched +by the corresponding backreference expression (see +.Xr re_format 7 ). +.Pp +A line can be split by substituting a newline character into it. +To specify a newline character in the replacement string, precede it with +a backslash. +.Pp +The value of +.Em flags +in the substitute function is zero or more of the following: +.Bl -tag -width "XXXXXX" -offset indent +.It "0 ... 9" +Make the substitution only for the N'th occurrence of the regular +expression in the pattern space. +.It g +Make the substitution for all non-overlapping matches of the +regular expression, not just the first one. +.It p +Write the pattern space to standard output if a replacement was made. +If the replacement string is identical to that which it replaces, it +is still considered to have been a replacement. +.It w Em file +Append the pattern space to +.Em file +if a replacement was made. +If the replacement string is identical to that which it replaces, it +is still considered to have been a replacement. +.El +.sp +.It [2addr]t [label] +Branch to the +.Dq : +function bearing the label if any substitutions have been made since the +most recent reading of an input line or execution of a +.Dq t +function. +If no label is specified, branch to the end of the script. +.sp +.It [2addr]w Em file +Append the pattern space to the +.Em file . +.sp +.It [2addr]x +Swap the contents of the pattern and hold spaces. +.sp +.It [2addr]y/string1/string2/ +Replace all occurrences of characters in +.Em string1 +in the pattern space with the corresponding characters from +.Em string2 . +Any character other than a backslash or newline can be used instead of +a slash to delimit the strings. +Within +.Em string1 +and +.Em string2 , +a backslash followed by any character other than a newline is that literal +character, and a backslash followed by an ``n'' is replaced by a newline +character. +.sp +.It [2addr]!function +.It [2addr]!function-list +Apply the function or function-list only to the lines that are +.Em not +selected by the address(es). +.sp +.It [0addr]:label +This function does nothing; it bears a label to which the +.Dq b +and +.Dq t +commands may branch. +.sp +.It [1addr]= +Write the line number to the standard output followed by a newline +character. +.sp +.It [0addr] +Empty lines are ignored. +.sp +.It [0addr]# +The +.Dq # +and the remainder of the line are ignored (treated as a comment), with +the single exception that if the first two characters in the file are +.Dq #n , +the default output is suppressed. +This is the same as specifying the +.Fl n +option on the command line. +.El +.Pp +The +.Nm sed +utility exits 0 on success and >0 if an error occurs. +.Sh SEE ALSO +.Xr awk 1 , +.Xr ed 1 , +.Xr grep 1 , +.Xr regex 3 , +.Xr re_format 7 +.Sh HISTORY +A +.Nm sed +command appeared in +.At v7 . +.Sh STANDARDS +The +.Nm sed +function is expected to be a superset of the +.St -p1003.2 +specification. |