#!/bin/sh

# Regression tests from the audits of September and October 2026. Each case
# is a config, repository or request that used to crash cgit, end it inside
# git, or hand a visitor something other than what was asked for.

test_description='Check the audit regressions'
. ./setup.sh

test_expect_success 'set up a repository and a config to vary' '
	mkrepo repos/rob 3 &&
	sha=$(git -C repos/rob rev-parse HEAD~1) &&
	{
		echo "virtual-root=/" &&
		echo "cache-size=0" &&
		echo "snapshots=tar.gz" &&
		echo "repo.url=rob" &&
		echo "repo.path=$PWD/repos/rob/.git"
	} >robrc
'

robq() { CGIT_CONFIG="$PWD/robrc" QUERY_STRING="$1" cgit; }

test_expect_success 'a repository without a path answers 404' '
	{
		echo "virtual-root=/" &&
		echo "cache-size=0" &&
		echo "repo.url=nopath" &&
		echo "repo.url=emptypath" &&
		echo "repo.path="
	} >nopathrc &&
	for r in nopath emptypath
	do
		CGIT_CONFIG="$PWD/nopathrc" QUERY_STRING="url=$r/log/" cgit >tmp &&
		grep "^Status: 404 Not Found" tmp &&
		grep "Failed to open $r: Not a valid git repository" tmp || return 1
	done
'

test_expect_success 'a repository with an empty url is skipped with a warning' '
	{
		echo "virtual-root=/" &&
		echo "cache-size=0" &&
		echo "repo.url=" &&
		echo "repo.path=$PWD/repos/rob/.git" &&
		echo "repo.url=rob" &&
		echo "repo.path=$PWD/repos/rob/.git"
	} >nourlrc &&
	CGIT_CONFIG="$PWD/nourlrc" QUERY_STRING="url=rob/" cgit >tmp 2>err &&
	grep "^Status: 200" tmp &&
	grep "Ignoring repository with an empty url" err
'

test_expect_success 'a scan path that is itself a repository is named after it' '
	{
		echo "virtual-root=/" &&
		echo "cache-size=0" &&
		echo "remove-suffix=1" &&
		echo "scan-path=$PWD/repos/rob"
	} >rootrc &&
	CGIT_CONFIG="$PWD/rootrc" QUERY_STRING="url=" cgit >tmp &&
	grep "toplevel-repo.><a href=./rob/.>rob</a>" tmp
'

test_expect_success 'a repo key after scan-path is reported instead of applied' '
	{
		echo "virtual-root=/" &&
		echo "cache-size=0" &&
		echo "repo.url=first" &&
		echo "repo.path=$PWD/repos/rob/.git" &&
		echo "scan-path=$PWD/repos" &&
		echo "repo.desc=misplaced"
	} >stalerc &&
	CGIT_CONFIG="$PWD/stalerc" QUERY_STRING="url=" cgit >tmp 2>err &&
	! grep "misplaced" tmp &&
	grep "Ignoring repo.desc before any repo.url" err
'

test_expect_success 'a valueless or broken git config in a scanned repository is skipped' '
	git clone -q --bare repos/rob/.git scan/a.git &&
	printf "[cgit]\n\thide\n[cgit\n" >>scan/a.git/config &&
	{
		echo "virtual-root=/" &&
		echo "cache-size=0" &&
		echo "enable-git-config=1" &&
		echo "scan-path=$PWD/scan"
	} >gitcfgrc &&
	CGIT_CONFIG="$PWD/gitcfgrc" QUERY_STRING="url=" cgit >tmp 2>err &&
	grep "toplevel-repo.><a href=./a.git/.>" tmp &&
	grep "Ignoring unreadable config in $PWD/scan/a.git/config" err
'

test_expect_success 'only descriptive keys are taken from a scanned repository' '
	git clone -q --bare repos/rob/.git scan/b.git &&
	{
		echo "desc=from the repo" &&
		echo "readme=master:file-1" &&
		echo "head-content=<script>alert(1)</script>" &&
		echo "logo-link=javascript:alert(2)"
	} >scan/b.git/cgitrc &&
	CGIT_CONFIG="$PWD/gitcfgrc" QUERY_STRING="url=b.git/about/" cgit >tmp 2>err &&
	grep "from the repo" tmp &&
	grep "pre class=.plaintext." tmp &&
	! grep "alert(" tmp &&
	grep "Ignoring head-content in $PWD/scan/b.git/: trust-scan-config is not set" err &&
	grep "Ignoring logo-link in " err
'

test_expect_success 'a filesystem readme from a scanned repository is refused' '
	echo "readme=/etc/hosts" >scan/b.git/cgitrc &&
	CGIT_CONFIG="$PWD/gitcfgrc" QUERY_STRING="url=b.git/about/" cgit >tmp 2>err &&
	grep "Ignoring readme in " err
'

# A repository served as html runs its pages on the site's own origin, so
# the switch waits on trust like the keys that place markup. The warning has
# to name the repository, which it did not for a key read from git config.
test_expect_success 'html serving from a scanned repository waits on trust' '
	(
		cd repos/rob &&
		printf "<p>page</p>\n" >page.html &&
		git add page.html &&
		git commit -m html
	) &&
	mkdir -p scan2 &&
	git clone -q --bare repos/rob/.git scan2/c.git &&
	git -C scan2/c.git config cgit.enable-html-serving 1 &&
	{
		echo "virtual-root=/" &&
		echo "cache-size=0" &&
		echo "enable-git-config=1" &&
		echo "mimetype.html=text/html" &&
		echo "scan-path=$PWD/scan2"
	} >htmlrc &&
	CGIT_CONFIG="$PWD/htmlrc" QUERY_STRING="url=c.git/plain/page.html" cgit >tmp 2>err &&
	grep "^Content-Type: text/plain" tmp &&
	grep "^X-Content-Type-Options: nosniff" tmp &&
	grep "Ignoring enable-html-serving in $PWD/scan2/c.git/: trust-scan-config is not set" err
'

test_expect_success 'with trust-scan-config the same repository serves html' '
	{
		echo "trust-scan-config=1" &&
		cat htmlrc
	} >htmltrustrc &&
	CGIT_CONFIG="$PWD/htmltrustrc" QUERY_STRING="url=c.git/plain/page.html" cgit >tmp &&
	grep "^Content-Type: text/html" tmp &&
	! grep "^X-Content-Type-Options" tmp
'

test_expect_success SYMLINKS 'a symlink cycle under the scan path is entered once' '
	ln -s . scan/loop &&
	CGIT_CONFIG="$PWD/gitcfgrc" QUERY_STRING="url=" cgit >tmp &&
	test $(grep -c "toplevel-repo" tmp) = 2
'

test_expect_success 'a bare query parameter does not swallow the next one' '
	robq "url=rob/commit/&x&id=$sha" >tmp &&
	grep "<div class=.commit-subject.>commit 2" tmp
'

test_expect_success 'a filter that cannot run answers one error page' '
	{
		echo "commit-filter=exec:$PWD/no/such/filter" &&
		cat robrc
	} >badfilterrc &&
	CGIT_CONFIG="$PWD/badfilterrc" QUERY_STRING="url=rob/commit/" cgit >tmp 2>err &&
	test $(grep -c "^Status:" tmp) = 1 &&
	grep "Unable to complete the request" tmp &&
	grep "Unable to run filter $PWD/no/such/filter" err &&
	grep "Unable to exec filter" err
'

test_expect_success 'a filter that exits without reading does not end cgit' '
	{
		echo "email-filter=exec:/usr/bin/true" &&
		cat robrc
	} >truerc &&
	CGIT_CONFIG="$PWD/truerc" QUERY_STRING="url=rob/log/" cgit >tmp &&
	grep "^Status:" tmp
'

test_expect_success 'a commit encoding header is read without its newline' '
	(
		cd repos/rob &&
		echo more >file-1 &&
		git add file-1 &&
		git -c i18n.commitEncoding=ISO-8859-1 commit -m "$(printf "caf\351")"
	) &&
	robq "url=rob/commit/" >tmp &&
	grep "<div class=.commit-subject.>caf$(printf "\303\251")<" tmp
'

test_expect_success 'a submodule below the about path does not end the request' '
	(
		cd repos/rob &&
		git update-index --add --cacheinfo 160000,$sha,sub &&
		git commit -m gitlink
	) &&
	{
		echo "mimetype.png=image/png" &&
		cat robrc &&
		echo "repo.readme=master:file-1"
	} >aboutrc &&
	CGIT_CONFIG="$PWD/aboutrc" QUERY_STRING="url=rob/about/sub" cgit >tmp 2>err &&
	grep "^Status:" tmp &&
	! grep "fatal" err
'

test_expect_success 'a missing image on the about page errors as html' '
	CGIT_CONFIG="$PWD/aboutrc" QUERY_STRING="url=rob/about/missing.png" cgit >tmp &&
	grep "^Status: 404" tmp &&
	grep "^Content-Type: text/html" tmp
'

test_expect_success 'a snapshot name holding a slash is refused' '
	robq "url=rob/snapshot/:/../../...tar.gz" >tmp &&
	grep "^Status: 404" tmp &&
	robq "url=rob/snapshot/rob-master.tar.gz" >tmp &&
	grep "^Status: 200" tmp
'

test_expect_success 'a path opening with a colon is refused on the log and patch pages' '
	robq "url=rob/log/:%25x" >tmp &&
	grep "^Status: 400" tmp &&
	robq "url=rob/patch/:%25x" >tmp &&
	grep "^Status: 400" tmp &&
	test $(grep -c "^Status:" tmp) = 1
'

test_expect_success 'a revision spelled like an option is refused' '
	git -C repos/rob update-ref refs/heads/--stdin HEAD &&
	robq "url=rob/log/&h=--stdin" >tmp &&
	grep "^Status: 404" tmp &&
	robq "url=rob/blame/file-1&id=--stdin" >tmp &&
	grep "^Status: 400" tmp &&
	robq "url=rob/atom/&h=--stdin" >tmp &&
	grep "^Status: 404" tmp
'

test_expect_success 'the blob page reads a file through an annotated tag' '
	git -C repos/rob -c tag.gpgsign=false tag -a -m note ann HEAD &&
	robq "url=rob/blob/&h=ann&path=file-1" >tmp &&
	strip_headers <tmp >body &&
	printf "more\n" >want &&
	test_cmp want body
'

# The plain page walks a path out of whatever commit the id names, and the
# blob page used to answer such a request with the raw commit object.
test_expect_success 'the blob page walks a path out of the commit or tag the id names' '
	tip=$(git -C repos/rob rev-parse HEAD) &&
	robq "url=rob/blob/file-1&id=$tip" >tmp &&
	strip_headers <tmp >body &&
	test_cmp want body &&
	tag=$(git -C repos/rob rev-parse ann) &&
	robq "url=rob/blob/file-1&id=$tag" >tmp &&
	strip_headers <tmp >body &&
	test_cmp want body &&
	robq "url=rob/blob/missing&id=$tip" >tmp &&
	grep "^Status: 404" tmp
'

test_expect_success 'the commit page shows a message whole when text follows its trailers' '
	(
		cd repos/rob &&
		echo again >file-1 &&
		git add file-1 &&
		git commit -F - <<-\EOF
		Subject

		Body text.

		Signed-off-by: A U Thor <author@example.com>

		Conflicts:
			file-1
		EOF
	) &&
	{
		echo "enable-commit-trailers=1" &&
		cat robrc
	} >trailrc &&
	CGIT_CONFIG="$PWD/trailrc" QUERY_STRING="url=rob/commit/" cgit >tmp &&
	! grep "commit-trailers" tmp &&
	grep "Conflicts:" tmp
'

test_expect_success 'a revision expression that walks the history is refused' '
	robq "url=rob/log/&h=:/zzzz" >tmp &&
	grep "^Status: 404" tmp &&
	robq "url=rob/commit/&id=HEAD^{/zzzz}" >tmp &&
	grep "^Status: 400" tmp &&
	robq "url=rob/log/&qt=range&q=:/zzzz" >tmp &&
	grep "^Status: 400" tmp &&
	robq "url=rob/log/&qt=range&q=master~1..master" >tmp &&
	grep "^Status: 400" tmp &&
	robq "url=rob/log/&qt=range&q=$sha..master" >tmp &&
	grep "^Status: 200" tmp
'

test_expect_success 'the log search is literal' '
	robq "url=rob/log/&qt=grep&q=commit.1" >tmp &&
	! grep ">commit 1</a>" tmp &&
	robq "url=rob/log/&qt=grep&q=commit%201" >tmp &&
	grep ">commit 1</a>" tmp
'

test_expect_success 'a commit with a broken tree line does not crash the blob page' '
	git clone -q repos/rob broken &&
	(
		cd broken &&
		bad=$(git cat-file commit HEAD | sed "s/^tree .*/tree not-a-hash/" |
			git hash-object -t commit -w --stdin --literally) &&
		echo $bad >.git/refs/heads/bad
	) &&
	{
		echo "virtual-root=/" &&
		echo "cache-size=0" &&
		echo "repo.url=broken" &&
		echo "repo.path=$PWD/broken/.git" &&
		echo "repo.readme=:file-1"
	} >brokenrc &&
	CGIT_CONFIG="$PWD/brokenrc" QUERY_STRING="url=broken/blob/&h=bad&path=file-1" cgit >tmp &&
	grep "^Status: 404" tmp
'

test_expect_success 'a die inside git answers one 500 page and logs the reason' '
	printf "[core\n" >>broken/.git/config &&
	CGIT_CONFIG="$PWD/brokenrc" QUERY_STRING="url=broken/log/" cgit >tmp 2>err &&
	grep "^Status: 500" tmp &&
	test $(grep -c "^Status:" tmp) = 1 &&
	grep "bad config line" err &&
	! grep "bad config line" tmp
'

test_expect_success 'a history with a missing parent renders up to the gap' '
	git clone -q repos/rob gap &&
	older=$(git -C gap rev-parse HEAD~3) &&
	parent=$(git -C gap rev-parse HEAD~2) &&
	rm gap/.git/objects/$(echo $parent | cut -c1-2)/$(echo $parent | cut -c3-) &&
	{
		echo "virtual-root=/" &&
		echo "cache-size=0" &&
		echo "repo.url=gap" &&
		echo "repo.path=$PWD/gap/.git"
	} >gaprc &&
	CGIT_CONFIG="$PWD/gaprc" QUERY_STRING="url=gap/log/" cgit >tmp 2>err &&
	test $(grep -c "^Status:" tmp) = 1 &&
	grep "Unable to complete the request" tmp &&
	grep "Failed to traverse parents" err &&
	CGIT_CONFIG="$PWD/gaprc" QUERY_STRING="url=gap/patch/&id2=$older" cgit >tmp &&
	test $(grep -c "^Status:" tmp) = 1 &&
	grep "^Status: 500" tmp
'

test_expect_success 'a filter pipeline sees the default SIGPIPE disposition' '
	cat >pipe.sh <<-\EOF &&
	#!/bin/sh
	n=0
	while test $n -lt 20000
	do
		echo line
		n=$((n + 1))
	done | head -c 5
	EOF
	chmod +x pipe.sh &&
	{
		echo "source-filter=exec:$PWD/pipe.sh" &&
		cat robrc
	} >piperc &&
	CGIT_CONFIG="$PWD/piperc" QUERY_STRING="url=rob/tree/file-1" cgit >tmp 2>err &&
	grep "^Status: 200" tmp &&
	! grep -i "broken pipe" err
'

test_expect_success 'the fallback branch skips a name spelled like an option' '
	git -C repos/rob update-ref refs/heads/-first HEAD &&
	git -C repos/rob symbolic-ref HEAD refs/heads/gone &&
	robq "url=rob/" >tmp &&
	git -C repos/rob symbolic-ref HEAD refs/heads/master &&
	grep "^Status: 200" tmp
'

# Such a branch is refused as a head, so the switcher must not offer a
# choice that can only lead to an error page.
test_expect_success 'the branch switcher leaves out a name spelled like an option' '
	grep "<option value=.master." tmp &&
	! grep "<option value=.-first." tmp
'

test_expect_success 'a blank line in the mimetype file is skipped' '
	(
		cd repos/rob &&
		echo note >note.cgt &&
		git add note.cgt &&
		git commit -m note
	) &&
	printf "\n   \nimage/x-cgit cgt\n" >mime.types &&
	{
		echo "mimetype-file=$PWD/mime.types" &&
		cat robrc
	} >mimerc &&
	CGIT_CONFIG="$PWD/mimerc" QUERY_STRING="url=rob/plain/note.cgt" cgit >tmp &&
	grep "^Content-Type: image/x-cgit" tmp
'

test_expect_success 'a refs page named with an id is not cached for ever' '
	mkdir -p cache &&
	{
		echo "cache-size=10" &&
		echo "cache-root=$PWD/cache" &&
		echo "cache-static-ttl=-1" &&
		echo "cache-dynamic-ttl=0" &&
		echo "cache-summary-ttl=0" &&
		grep -v "^cache-size" robrc
	} >ttlrc &&
	full=$(git -C repos/rob rev-parse HEAD) &&
	CGIT_CONFIG="$PWD/ttlrc" QUERY_STRING="url=rob/refs/&id=$full" cgit >tmp &&
	git -C repos/rob tag later HEAD &&
	CGIT_CONFIG="$PWD/ttlrc" QUERY_STRING="url=rob/refs/&id=$full" cgit >tmp &&
	grep ">later<" tmp
'

test_expect_success 'the diff caps hold when the path names a directory' '
	(
		cd repos/rob &&
		mkdir -p dir &&
		for n in 1 2 3
		do
			echo $n >dir/f$n || return 1
		done &&
		git add dir &&
		git commit -m dir
	) &&
	{
		echo "max-diff-files=2" &&
		cat robrc
	} >caprc &&
	CGIT_CONFIG="$PWD/caprc" QUERY_STRING="url=rob/diff/dir" cgit >tmp &&
	grep "too large to be rendered inline" tmp &&
	CGIT_CONFIG="$PWD/caprc" QUERY_STRING="url=rob/diff/dir/f1" cgit >tmp &&
	! grep "too large to be rendered inline" tmp
'

test_expect_success 'a snapshot of a tag spelled like an option is archived' '
	git -C repos/rob update-ref refs/tags/-l HEAD &&
	robq "url=rob/snapshot/-l.tar.gz" >tmp &&
	grep "^Status: 200" tmp &&
	strip_headers <tmp | gzip -dc | tar -tf - >list &&
	grep "file-1" list
'

test -n "$CGIT_VALGRIND" || test_set_prereq NO_VALGRIND

test_expect_success NO_VALGRIND 'a snapshot format whose compressor is missing answers 500' '
	{
		echo "snapshots=tar.xz" &&
		grep -v "^snapshots" robrc
	} >xzrc &&
	cgitbin=$(command -v cgit) &&
	mkdir -p nobin &&
	PATH="$PWD/nobin" CGIT_CONFIG="$PWD/xzrc" \
		QUERY_STRING="url=rob/snapshot/rob-master.tar.xz" $cgitbin >tmp &&
	grep "^Status: 500" tmp &&
	test $(grep -c "^Status:" tmp) = 1
'

test_expect_success 'a disk readme in the repository directory serves no sibling' '
	echo hello >repos/rob/.git/README &&
	{
		cat robrc &&
		echo "repo.readme=README"
	} >diskrc &&
	CGIT_CONFIG="$PWD/diskrc" QUERY_STRING="url=rob/about/" cgit >tmp &&
	grep "hello" tmp &&
	CGIT_CONFIG="$PWD/diskrc" QUERY_STRING="url=rob/about/config" cgit >tmp &&
	! grep "repositoryformatversion" tmp
'

test_expect_success 'a tag pointing at a tag links the inner tag by id' '
	git -C repos/rob -c tag.gpgsign=false tag -a -m outer outer ann &&
	inner=$(git -C repos/rob rev-parse ann) &&
	robq "url=rob/tag/&id=$inner" >tmp &&
	grep "^Status: 200" tmp &&
	grep "tagged object" tmp
'

test_expect_success 'the dumb transport serves an empty repository' '
	git init -q --bare empty.git &&
	{
		echo "virtual-root=/" &&
		echo "cache-size=0" &&
		echo "repo.url=empty" &&
		echo "repo.path=$PWD/empty.git"
	} >emptyrc &&
	CGIT_CONFIG="$PWD/emptyrc" QUERY_STRING="url=empty/info/refs" cgit >tmp &&
	grep "^Status: 200" tmp &&
	grep "^Content-Type: text/plain" tmp &&
	CGIT_CONFIG="$PWD/emptyrc" QUERY_STRING="url=empty/objects/info" cgit >tmp &&
	grep "^Status: 404" tmp
'

# A pack is handed over as it sits on the disk, so the client can be told
# its size up front and compare what arrived against it.
test_expect_success 'the dumb transport sends a file with its size' '
	git -C repos/rob repack -q -d &&
	robq "url=rob/objects/info/packs" >tmp &&
	pack=$(strip_headers <tmp | sed -n "s/^P //p" | head -1) &&
	test -n "$pack" &&
	robq "url=rob/objects/pack/$pack" >tmp &&
	grep "^Status: 200" tmp &&
	size=$(wc -c <repos/rob/.git/objects/pack/$pack | tr -d " ") &&
	grep "^Content-Length: $size$" tmp &&
	strip_headers <tmp >body &&
	cmp body repos/rob/.git/objects/pack/$pack
'

# The alternates file lists object directories by their path on the server,
# which a client fetching over http cannot use and should not learn.
test_expect_success 'the dumb transport withholds the alternates file' '
	mkdir -p repos/rob/.git/objects/info &&
	echo "$PWD/repos/foo/.git/objects" >repos/rob/.git/objects/info/alternates &&
	robq "url=rob/objects/info/alternates" >tmp &&
	grep "^Status: 404" tmp &&
	! grep "repos/foo" tmp &&
	rm repos/rob/.git/objects/info/alternates &&
	robq "url=rob/objects/info/packs" >tmp &&
	grep "^Status: 200" tmp
'

# The about page redirects to its trailing-slash form so relative links
# resolve, and the branch asked for has to survive that hop, as does the
# hop back to the summary of a repository without a readme.
test_expect_success 'the about redirects keep the query string' '
	git -C repos/rob branch other HEAD &&
	CGIT_CONFIG="$PWD/aboutrc" QUERY_STRING="url=rob/about&h=other&x=1" cgit >tmp &&
	grep "^Status: 301" tmp &&
	grep "^Location: /rob/about/?h=other&x=1$" tmp &&
	robq "url=rob/about/&h=other" >tmp &&
	grep "^Status: 302" tmp &&
	grep "^Location: /rob/about/../?h=other$" tmp
'

test_expect_success 'a symlink whose target is a large blob is listed without it' '
	big=$(head -c 5000 /dev/zero | tr "\0" a | git -C repos/rob hash-object -w --stdin) &&
	(
		cd repos/rob &&
		git update-index --add --cacheinfo 120000,$big,biglink &&
		git commit -m biglink
	) &&
	robq "url=rob/tree/" >tmp &&
	grep "biglink" tmp &&
	! grep "aaaaaaaaaa" tmp
'

test_expect_success 'a chain of single directories is followed a bounded number of levels' '
	(
		cd repos/rob &&
		deep=$(printf "d/%.0s" $(seq 1 40))leaf &&
		mkdir -p $(dirname $deep) &&
		echo x >$deep &&
		git add d &&
		git commit -m deep
	) &&
	robq "url=rob/tree/" >tmp &&
	test $(grep -o "class=.ls-dir." tmp | wc -l) -le 17
'

test_done