t/lib-httpd: avoid using BSD's sed

Among other differences relative to GNU sed, BSD sed always ends its
output with a trailing newline, even if the input did not have such a
trailing newline.

Surprisingly, this makes three httpd-based tests fail on macOS: t5616,
t5702 and t5703. ("Surprisingly" because those tests have been around
for some time, but apparently nobody runs them on macOS with a working
Apache2 setup.)

The reason is that we use `sed` in those tests to filter the response of
the web server. Apart from the fact that we use GNU constructs (such as
using a space after the `c` command instead of a backslash and a
newline), we have another problem: BSD sed LF-only newlines while
webservers are supposed to use CR/LF ones.

Even worse, t5616 uses `sed` to replace a binary part of the response
with a new binary part (kind of hoping that the replaced binary part
does not contain a 0x0a byte which would be interpreted as a newline).

To that end, it calls on Perl to read the binary pack file and
hex-encode it, then calls on `sed` to prefix every hex digit pair with a
`\x` in order to construct the text that the `c` statement of the `sed`
invocation is supposed to insert. So we call Perl and sed to construct a
sed statement. The final nail in the coffin is that BSD sed does not
even interpret those `\x<hex>` constructs.

Let's just replace all of that by Perl snippets. With Perl, at least, we
do not have to deal with GNU vs BSD semantics, we do not have to worry
about unwanted trailing newlines, and we do not have to spawn commands
to construct arguments for other commands to be spawned (i.e. we can
avoid a whole lot of shell scripting complexity).

The upshot is that this fixes t5616, t5702 and t5703 on macOS with
Apache2.

Signed-off-by: Johannes Schindelin <[email protected]>

Author: dscho

t/lib-httpd.sh

@@ -132,7 +132,7 @@ prepare_httpd() {
 	install_script broken-smart-http.sh
 	install_script error-smart-http.sh
 	install_script error.sh
-	install_script apply-one-time-sed.sh
+	install_script apply-one-time-perl.sh
 
 	ln -s "$LIB_HTTPD_MODULE_PATH" "$HTTPD_ROOT_PATH/modules"
 

t/lib-httpd/apache.conf

@@ -113,7 +113,7 @@ Alias /auth/dumb/ www/auth/dumb/
 	SetEnv GIT_EXEC_PATH ${GIT_EXEC_PATH}
 	SetEnv GIT_HTTP_EXPORT_ALL
 </LocationMatch>
-<LocationMatch /one_time_sed/>
+<LocationMatch /one_time_perl/>
 	SetEnv GIT_EXEC_PATH ${GIT_EXEC_PATH}
 	SetEnv GIT_HTTP_EXPORT_ALL
 </LocationMatch>
@@ -122,7 +122,7 @@ ScriptAliasMatch /smart_*[^/]*/(.*) ${GIT_EXEC_PATH}/git-http-backend/$1
 ScriptAlias /broken_smart/ broken-smart-http.sh/
 ScriptAlias /error_smart/ error-smart-http.sh/
 ScriptAlias /error/ error.sh/
-ScriptAliasMatch /one_time_sed/(.*) apply-one-time-sed.sh/$1
+ScriptAliasMatch /one_time_perl/(.*) apply-one-time-perl.sh/$1
 <Directory ${GIT_EXEC_PATH}>
 	Options FollowSymlinks
 </Directory>
@@ -135,7 +135,7 @@ ScriptAliasMatch /one_time_sed/(.*) apply-one-time-sed.sh/$1
 <Files error.sh>
   Options ExecCGI
 </Files>
-<Files apply-one-time-sed.sh>
+<Files apply-one-time-perl.sh>
 	Options ExecCGI
 </Files>
 <Files ${GIT_EXEC_PATH}/git-http-backend>

t/lib-httpd/apply-one-time-perl.sh

@@ -0,0 +1,33 @@
+#!/bin/sh
+
+# If "one-time-perl" exists in $HTTPD_ROOT_PATH, run perl on the HTTP response,
+# using the contents of "one-time-perl" as the perl command to be run. If the
+# response was modified as a result, delete "one-time-perl" so that subsequent
+# HTTP responses are no longer modified.
+#
+# This can be used to simulate the effects of the repository changing in
+# between HTTP request-response pairs.
+if test -f one-time-perl
+then
+	LC_ALL=C
+	export LC_ALL
+
+	"$GIT_EXEC_PATH/git-http-backend" >out
+	perl -pe "$(cat one-time-perl)" out >out_modified
+
+echo "before applying one-time $(cat one-time-perl)" >&2
+hexdump -C out >&2
+echo "after applying one-time $(cat one-time-perl)" >&2
+hexdump -C out_modified >&2
+
+	if cmp -s out out_modified
+	then
+		cat out
+	else
+		cat out_modified
+#		rm one-time-perl
+mv one-time-perl one-time-perl.$(($(ls one-time-perl.* 2>/dev/null | wc -l | tr -dc 0-9)+1))
+	fi
+else
+	"$GIT_EXEC_PATH/git-http-backend"
+fi

t/lib-httpd/apply-one-time-sed.sh

@@ -237,7 +237,7 @@ test_expect_success 'shallow fetches check connectivity before writing shallow f
 	git -C "$REPO" config protocol.version 2 &&
 	git -C client config protocol.version 2 &&
 
-	git -C client fetch --depth=2 "$HTTPD_URL/one_time_sed/repo" master:a_branch &&
+	git -C client fetch --depth=2 "$HTTPD_URL/one_time_perl/repo" master:a_branch &&
 
 	# Craft a situation in which the server sends back an unshallow request
 	# with an empty packfile. This is done by refetching with a shorter
@@ -246,13 +246,13 @@ test_expect_success 'shallow fetches check connectivity before writing shallow f
 	printf "$(test_oid sed)" \
 	       "$(git -C "$REPO" rev-parse HEAD)" \
 	       "$(git -C "$REPO" rev-parse HEAD^)" \
-	       >"$HTTPD_ROOT_PATH/one-time-sed" &&
+	       >"$HTTPD_ROOT_PATH/one-time-perl" &&
 	test_must_fail env GIT_TEST_SIDEBAND_ALL=0 git -C client \
-		fetch --depth=1 "$HTTPD_URL/one_time_sed/repo" \
+		fetch --depth=1 "$HTTPD_URL/one_time_perl/repo" \
 		master:a_branch &&
 
-	# Ensure that the one-time-sed script was used.
-	! test -e "$HTTPD_ROOT_PATH/one-time-sed" &&
+	# Ensure that the one-time-perl script was used.
+	! test -e "$HTTPD_ROOT_PATH/one-time-perl" &&
 
 	# Ensure that the resulting repo is consistent, despite our failure to
 	# fetch.

t/t5537-fetch-shallow.sh

@@ -429,14 +429,18 @@ intersperse () {
 	sed 's/\(..\)/'$1'\1/g'
 }
 
-# Create a one-time-sed command to replace the existing packfile with $1.
+# Create a one-time-perl command to replace the existing packfile with $1.
 replace_packfile () {
 	# The protocol requires that the packfile be sent in sideband 1, hence
 	# the extra \x01 byte at the beginning.
-	printf "1,/packfile/!c %04x\\\\x01%s0000" \
-		"$(($(wc -c <$1) + 5))" \
-		"$(hex_unpack <$1 | intersperse '\\x')" \
-		>"$HTTPD_ROOT_PATH/one-time-sed"
+	cp $1 "$HTTPD_ROOT_PATH/one-time-pack" &&
+	echo 'if (/packfile/) {
+		print;
+		my $length = -s "one-time-pack";
+		printf "%04x\x01", $length + 5;
+		print `cat one-time-pack` . "0000";
+		last
+	}' >"$HTTPD_ROOT_PATH/one-time-perl"
 }
 
 test_expect_success 'upon cloning, check that all refs point to objects' '
@@ -460,16 +464,16 @@ test_expect_success 'upon cloning, check that all refs point to objects' '
 	# \x01 byte at the beginning.
 	replace_packfile incomplete.pack &&
 
-	# Use protocol v2 because the sed command looks for the "packfile"
+	# Use protocol v2 because the perl command looks for the "packfile"
 	# section header.
 	test_config -C "$SERVER" protocol.version 2 &&
 	test_must_fail git -c protocol.version=2 clone \
-		--filter=blob:none $HTTPD_URL/one_time_sed/server repo 2>err &&
+		--filter=blob:none $HTTPD_URL/one_time_perl/server repo 2>err &&
 
 	test_i18ngrep "did not send all necessary objects" err &&
 
-	# Ensure that the one-time-sed script was used.
-	! test -e "$HTTPD_ROOT_PATH/one-time-sed"
+	# Ensure that the one-time-perl script was used.
+	! test -e "$HTTPD_ROOT_PATH/one-time-perl"
 '
 
 test_expect_success 'when partial cloning, tolerate server not sending target of tag' '
@@ -500,17 +504,17 @@ test_expect_success 'when partial cloning, tolerate server not sending target of
 	# \x01 byte at the beginning.
 	replace_packfile incomplete.pack &&
 
-	# Use protocol v2 because the sed command looks for the "packfile"
+	# Use protocol v2 because the perl command looks for the "packfile"
 	# section header.
 	test_config -C "$SERVER" protocol.version 2 &&
 
 	# Exercise to make sure it works.
 	git -c protocol.version=2 clone \
-		--filter=blob:none $HTTPD_URL/one_time_sed/server repo 2> err &&
+		--filter=blob:none $HTTPD_URL/one_time_perl/server repo 2> err &&
 	! grep "missing object referenced by" err &&
 
-	# Ensure that the one-time-sed script was used.
-	! test -e "$HTTPD_ROOT_PATH/one-time-sed"
+	# Ensure that the one-time-perl script was used.
+	! test -e "$HTTPD_ROOT_PATH/one-time-perl"
 '
 
 test_expect_success 'tolerate server sending REF_DELTA against missing promisor objects' '
@@ -533,7 +537,7 @@ test_expect_success 'tolerate server sending REF_DELTA against missing promisor
 
 	# Clone. The client has deltabase_have but not deltabase_missing.
 	git -c protocol.version=2 clone --no-checkout \
-		--filter=blob:none $HTTPD_URL/one_time_sed/server repo &&
+		--filter=blob:none $HTTPD_URL/one_time_perl/server repo &&
 	git -C repo hash-object -w -- "$SERVER/have.txt" &&
 
 	# Sanity check to ensure that the client does not have
@@ -574,7 +578,7 @@ test_expect_success 'tolerate server sending REF_DELTA against missing promisor
 
 	replace_packfile thin.pack &&
 
-	# Use protocol v2 because the sed command looks for the "packfile"
+	# Use protocol v2 because the perl command looks for the "packfile"
 	# section header.
 	test_config -C "$SERVER" protocol.version 2 &&
 
@@ -587,8 +591,8 @@ test_expect_success 'tolerate server sending REF_DELTA against missing promisor
 	grep "want $(cat deltabase_missing)" trace &&
 	! grep "want $(cat deltabase_have)" trace &&
 
-	# Ensure that the one-time-sed script was used.
-	! test -e "$HTTPD_ROOT_PATH/one-time-sed"
+	# Ensure that the one-time-perl script was used.
+	! test -e "$HTTPD_ROOT_PATH/one-time-perl"
 '
 
 # DO NOT add non-httpd-specific tests here, because the last part of this

t/t5616-partial-clone.sh

@@ -712,11 +712,11 @@ test_expect_success 'when server sends "ready", expect DELIM' '
 
 	# After "ready" in the acknowledgments section, pretend that a FLUSH
 	# (0000) was sent instead of a DELIM (0001).
-	printf "/ready/,$ s/0001/0000/" \
-		>"$HTTPD_ROOT_PATH/one-time-sed" &&
+	printf "\$ready = 1 if /ready/; \$ready && s/0001/0000/" \
+		>"$HTTPD_ROOT_PATH/one-time-perl" &&
 
 	test_must_fail git -C http_child -c protocol.version=2 \
-		fetch "$HTTPD_URL/one_time_sed/http_parent" 2> err &&
+		fetch "$HTTPD_URL/one_time_perl/http_parent" 2> err &&
 	test_i18ngrep "expected packfile to be sent after .ready." err
 '
 
@@ -737,12 +737,12 @@ test_expect_success 'when server does not send "ready", expect FLUSH' '
 
 	# After the acknowledgments section, pretend that a DELIM
 	# (0001) was sent instead of a FLUSH (0000).
-	printf "/acknowledgments/,$ s/0000/0001/" \
-		>"$HTTPD_ROOT_PATH/one-time-sed" &&
+	printf "\$ack = 1 if /acknowledgments/; \$ack && s/0000/0001/" \
+		>"$HTTPD_ROOT_PATH/one-time-perl" &&
 
 	test_must_fail env GIT_TRACE_PACKET="$(pwd)/log" git -C http_child \
 		-c protocol.version=2 \
-		fetch "$HTTPD_URL/one_time_sed/http_parent" 2> err &&
+		fetch "$HTTPD_URL/one_time_perl/http_parent" 2> err &&
 	grep "fetch< .*acknowledgments" log &&
 	! grep "fetch< .*ready" log &&
 	test_i18ngrep "expected no other sections to be sent after no .ready." err

t/t5702-protocol-v2.sh

@@ -314,7 +314,7 @@ test_expect_success 'setup repos for change-while-negotiating test' '
 		test_commit m3 &&
 		git tag -d m2 m3
 	) &&
-	git -C "$LOCAL_PRISTINE" remote set-url origin "http://127.0.0.1:$LIB_HTTPD_PORT/one_time_sed/repo" &&
+	git -C "$LOCAL_PRISTINE" remote set-url origin "http://127.0.0.1:$LIB_HTTPD_PORT/one_time_perl/repo" &&
 	git -C "$LOCAL_PRISTINE" config protocol.version 2
 '
 
@@ -327,7 +327,7 @@ inconsistency () {
 	# RPCs during a single negotiation.
 	oid1=$(git -C "$REPO" rev-parse $1) &&
 	oid2=$(git -C "$REPO" rev-parse $2) &&
-	echo "s/$oid1/$oid2/" >"$HTTPD_ROOT_PATH/one-time-sed"
+	echo "s/$oid1/$oid2/" >"$HTTPD_ROOT_PATH/one-time-perl"
 }
 
 test_expect_success 'server is initially ahead - no ref in want' '
@@ -379,7 +379,7 @@ test_expect_success 'server loses a ref - ref in want' '
 	git -C "$REPO" config uploadpack.allowRefInWant true &&
 	rm -rf local &&
 	cp -r "$LOCAL_PRISTINE" local &&
-	echo "s/master/raster/" >"$HTTPD_ROOT_PATH/one-time-sed" &&
+	echo "s/master/raster/" >"$HTTPD_ROOT_PATH/one-time-perl" &&
 	test_must_fail git -C local fetch 2>err &&
 
 	test_i18ngrep "fatal: remote error: unknown ref refs/heads/raster" err