[PATCH v4] test: replace notmuch_passwd_sanitize() with _libconfig_sanitize()

[PATCH v4] test: replace notmuch_passwd_sanitize() with _libconfig_sanitize()

[Tomi Ollila]

notmuch_passwd_sanitize() in test-lib.sh is too generic, it cannot
work in many cases...

The more specific version _libconfig_sanitize() replaces it in
T590-libconfig.sh and the code that uses it is modified to output
the keys (ascending numbers printed in hex) so the sanitizer knows
what to sanitize in which lines...

"@" + fqdn -> "@FQDN" replacement is used as fqdn could
-- in theory -- be substring of 'USERNAME'.

'user -> 'USER_FULL_NAME replacement to work in cases where user
is empty -- as only first ' is replaced that works as expected.

In addition to ".(none)" now also ".localdomain" is filtered from
USERNAME@FQDN.

/dev/fd/{n} is not defined in posix, but it is portable enough
(if it weren't it is easy to fix -- now code looks clearer).
---

v3 in id:20210518055443.21964-1-tomi.ollila@iki.fi

Change: using heredoc and /dev/fd/3 in in _libconfig_sanitize,
so "'" can be clearly used in the embedded python program.

 test/T590-libconfig.sh | 96 +++++++++++++++++++++++++-----------------
 test/test-lib.sh       | 20 ---------
 2 files changed, 58 insertions(+), 58 deletions(-)

diff --git a/test/T590-libconfig.sh b/test/T590-libconfig.sh
index 745e1bb4..8f775f70 100755
--- a/test/T590-libconfig.sh
+++ b/test/T590-libconfig.sh
@@ -5,6 +5,25 @@ test_description="library config API"
 
 add_email_corpus
 
+_libconfig_sanitize() {
+    ${NOTMUCH_PYTHON} /dev/fd/3 3<<'EOF'
+import os, sys, pwd, socket
+
+pw = pwd.getpwuid(os.getuid())
+user = pw.pw_name
+name = pw.pw_gecos.partition(",")[0]
+fqdn = socket.getaddrinfo(socket.gethostname(), 0, 0,
+                          socket.SOCK_STREAM, 0, socket.AI_CANONNAME)[0][3]
+for l in sys.stdin:
+    if l[:3] == "8: ":
+        l = l.replace(user, "USERNAME", 1).replace("@" + fqdn, "@FQDN", 1)
+        l = l.replace(".(none)", "", 1).replace(".localdomain", "", 1)
+    elif l[:3] == "a: ":
+        l = l.replace("'" + name, "'USER_FULL_NAME", 1)
+    sys.stdout.write(l)
+EOF
+}
+
 cat <<EOF > c_head
 #include <string.h>
 #include <stdlib.h>
@@ -380,26 +399,26 @@ cat c_head - c_tail <<'EOF' | test_C ${MAIL_DIR} '' %NULL%
 	 key < NOTMUCH_CONFIG_LAST;
 	 key = (notmuch_config_key_t)(key + 1)) {
 	const char *val = notmuch_config_get (db, key);
-        printf("%s\n", val ? val : "NULL" );
+	printf("%x: '%s'\n", key, val ? val : "NULL" );
     }
 }
 EOF
 
-notmuch_passwd_sanitize < OUTPUT > OUTPUT.clean
+_libconfig_sanitize < OUTPUT > OUTPUT.clean
 
 cat <<'EOF' >EXPECTED
 == stdout ==
-MAIL_DIR
-MAIL_DIR
-MAIL_DIR/.notmuch/hooks
-MAIL_DIR/.notmuch/backups
-
-unread;inbox
-
-true
-USERNAME@FQDN
-NULL
-USER_FULL_NAME
+0: 'MAIL_DIR'
+1: 'MAIL_DIR'
+2: 'MAIL_DIR/.notmuch/hooks'
+3: 'MAIL_DIR/.notmuch/backups'
+4: ''
+5: 'unread;inbox'
+6: ''
+7: 'true'
+8: 'USERNAME@FQDN'
+9: 'NULL'
+a: 'USER_FULL_NAME'
 == stderr ==
 EOF
 unset MAILDIR
@@ -694,23 +713,23 @@ cat c_head2 - c_tail <<'EOF' | test_C ${MAIL_DIR} %NULL% %NULL%
 	 key < NOTMUCH_CONFIG_LAST;
 	 key = (notmuch_config_key_t)(key + 1)) {
 	const char *val = notmuch_config_get (db, key);
-        printf("%s\n", val ? val : "NULL" );
+	printf("%x: '%s'\n", key, val ? val : "NULL" );
     }
 }
 EOF
 cat <<'EOF' >EXPECTED
 == stdout ==
-MAIL_DIR
-MAIL_DIR
-MAIL_DIR/.notmuch/hooks
-MAIL_DIR/.notmuch/backups
-foo;bar;fub
-unread;inbox
-sekrit_junk
-true
-test_suite@notmuchmail.org
-test_suite_other@notmuchmail.org;test_suite@otherdomain.org
-Notmuch Test Suite
+0: 'MAIL_DIR'
+1: 'MAIL_DIR'
+2: 'MAIL_DIR/.notmuch/hooks'
+3: 'MAIL_DIR/.notmuch/backups'
+4: 'foo;bar;fub'
+5: 'unread;inbox'
+6: 'sekrit_junk'
+7: 'true'
+8: 'test_suite@notmuchmail.org'
+9: 'test_suite_other@notmuchmail.org;test_suite@otherdomain.org'
+a: 'Notmuch Test Suite'
 == stderr ==
 EOF
 test_expect_equal_file EXPECTED OUTPUT
@@ -723,25 +742,26 @@ cat c_head2 - c_tail <<'EOF' | test_C ${MAIL_DIR} /nonexistent %NULL%
 	 key < NOTMUCH_CONFIG_LAST;
 	 key = (notmuch_config_key_t)(key + 1)) {
 	const char *val = notmuch_config_get (db, key);
-	printf("%s\n", val ? val : "NULL" );
+	printf("%x: '%s'\n", key, val ? val : "NULL" );
     }
 }
 EOF
 
-notmuch_passwd_sanitize < OUTPUT > OUTPUT.clean
+_libconfig_sanitize < OUTPUT > OUTPUT.clean
+
 cat <<'EOF' >EXPECTED
 == stdout ==
-MAIL_DIR
-MAIL_DIR
-MAIL_DIR/.notmuch/hooks
-MAIL_DIR/.notmuch/backups
-
-unread;inbox
-
-true
-USERNAME@FQDN
-NULL
-USER_FULL_NAME
+0: 'MAIL_DIR'
+1: 'MAIL_DIR'
+2: 'MAIL_DIR/.notmuch/hooks'
+3: 'MAIL_DIR/.notmuch/backups'
+4: ''
+5: 'unread;inbox'
+6: ''
+7: 'true'
+8: 'USERNAME@FQDN'
+9: 'NULL'
+a: 'USER_FULL_NAME'
 == stderr ==
 EOF
 test_expect_equal_file EXPECTED OUTPUT.clean
diff --git a/test/test-lib.sh b/test/test-lib.sh
index 6be5d11f..35bea097 100644
--- a/test/test-lib.sh
+++ b/test/test-lib.sh
@@ -561,26 +561,6 @@ notmuch_built_with_sanitize () {
     sed 's/^built_with[.]\(.*\)=.*$/built_with.\1=something/'
 }
 
-notmuch_passwd_sanitize () {
-    ${NOTMUCH_PYTHON} -c'
-import os, sys, pwd, socket
-
-pw = pwd.getpwuid(os.getuid())
-user = pw.pw_name
-name = pw.pw_gecos.partition(",")[0]
-fqdn = socket.getaddrinfo(socket.gethostname(), 0, 0, socket.SOCK_STREAM, 0, socket.AI_CANONNAME)[0][3]
-
-for l in sys.stdin:
-    if user:
-        l = l.replace(user, "USERNAME")
-    if fqdn:
-        l = l.replace(fqdn, "FQDN").replace(".(none)","")
-    if name:
-        l = l.replace(name, "USER_FULL_NAME")
-    sys.stdout.write(l)
-'
-}
-
 notmuch_config_sanitize () {
     notmuch_dir_sanitize | notmuch_built_with_sanitize
 }
-- 
2.25.1

Re: [PATCH v4] test: replace notmuch_passwd_sanitize() with _libconfig_sanitize()

[David Bremner]

Tomi Ollila <tomi.ollila@iki.fi> writes:
>  cat <<EOF > c_head
>  #include <string.h>
>  #include <stdlib.h>
> @@ -380,26 +399,26 @@ cat c_head - c_tail <<'EOF' | test_C ${MAIL_DIR} '' %NULL%
>  	 key < NOTMUCH_CONFIG_LAST;
>  	 key = (notmuch_config_key_t)(key + 1)) {
>  	const char *val = notmuch_config_get (db, key);
> -        printf("%s\n", val ? val : "NULL" );
> +	printf("%x: '%s'\n", key, val ? val : "NULL" );
>      }
>  }
>  EOF

It seems not that unlikely that we will hit 16 configuration keys. Would
it be better to use 2 digits 0 padded (and in that case we could
probably stick to decimal). Or maybe having different number of digits
for later keys does not matter?

d