test: normalize only message filenames in show json

[notmuch] / test / test-lib.sh

diff --git a/test/test-lib.sh b/test/test-lib.sh
index f1697856426225f2df4de7a6ca9c5c8a384333e5..6ce3b3189f25c354b471c42db1730ab8fe172e89 100644 (file)
--- a/test/test-lib.sh
+++ b/test/test-lib.sh
@@ -534,8 +534,13 @@ test_expect_equal_file ()
 # canonicalized before diff'ing.  If an argument cannot be parsed, it
 # is used unchanged so that there's something to diff against.
 test_expect_equal_json () {
-    output=$(echo "$1" | python -mjson.tool || echo "$1")
-    expected=$(echo "$2" | python -mjson.tool || echo "$2")
+    # The test suite forces LC_ALL=C, but this causes Python 3 to
+    # decode stdin as ASCII.  We need to read JSON in UTF-8, so
+    # override Python's stdio encoding defaults.
+    output=$(echo "$1" | PYTHONIOENCODING=utf-8 python -mjson.tool \
+        || echo "$1")
+    expected=$(echo "$2" | PYTHONIOENCODING=utf-8 python -mjson.tool \
+        || echo "$2")
     shift 2
     test_expect_equal "$output" "$expected" "$@"
 }
@@ -576,7 +581,7 @@ NOTMUCH_NEW ()
 
 notmuch_search_sanitize ()
 {
-    sed -r -e 's/("?thread"?: ?)("?)................("?)/\1\2XXX\3/'
+    perl -pe 's/("?thread"?: ?)("?)................("?)/\1\2XXX\3/'
 }
 
 NOTMUCH_SHOW_FILENAME_SQUELCH='s,filename:.*/mail,filename:/XXX/mail,'
@@ -595,7 +600,7 @@ notmuch_json_show_sanitize ()
 {
     sed \
        -e 's|"id": "[^"]*",|"id": "XXXXX",|g' \
-       -e 's|"filename": "[^"]*",|"filename": "YYYYY",|g'
+       -e 's|"filename": "/[^"]*",|"filename": "YYYYY",|g'
 }
 
 # End of notmuch helper functions