t9350: fix encoding test to actually test reencoding
authorElijah Newren <newren@gmail.com>
Tue, 14 May 2019 04:30:58 +0000 (21:30 -0700)
committerJunio C Hamano <gitster@pobox.com>
Tue, 14 May 2019 07:48:55 +0000 (16:48 +0900)
This test used an author with non-ascii characters in the name, but no
special commit message. It then grep'ed for those non-ascii characters,
but those are guaranteed to exist regardless of the reencoding process
since the reencoding only affects the commit message, not the author or
committer names. As such, the test would work even if the re-encoding
process simply stripped the commit message entirely. Modify the test to
actually check that the reencoding into UTF-8 worked.

Signed-off-by: Elijah Newren <newren@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>
t/t9350-fast-export.sh
t/t9350/simple-iso-8859-7-commit-message.txt [new file with mode: 0644]
index 5690fe28106624f3d666ccdda1dbcdd58673fb13..756d6a9905e6bb38e7dbf0d5a39a5d63849816e6 100755 (executable)
@@ -94,22 +94,30 @@ test_expect_success 'fast-export --show-original-ids | git fast-import' '
        test $MUSS = $(git rev-parse --verify refs/tags/muss)
 '
 
-test_expect_success 'iso-8859-1' '
+test_expect_success 'iso-8859-7' '
 
-       git config i18n.commitencoding ISO8859-1 &&
-       # use author and committer name in ISO-8859-1 to match it.
-       . "$TEST_DIRECTORY"/t3901/8859-1.txt &&
+       test_when_finished "git reset --hard HEAD~1" &&
+       test_config i18n.commitencoding iso-8859-7 &&
        test_tick &&
        echo rosten >file &&
-       git commit -s -m den file &&
-       git fast-export wer^..wer >iso8859-1.fi &&
-       sed "s/wer/i18n/" iso8859-1.fi |
+       git commit -s -F "$TEST_DIRECTORY/t9350/simple-iso-8859-7-commit-message.txt" file &&
+       git fast-export wer^..wer >iso-8859-7.fi &&
+       sed "s/wer/i18n/" iso-8859-7.fi |
                (cd new &&
                 git fast-import &&
+                # The commit object, if not re-encoded, would be 240 bytes.
+                # Removing the "encoding iso-8859-7\n" header drops 20 bytes.
+                # Re-encoding the Pi character from \xF0 (\360) in iso-8859-7
+                # to \xCF\x80 (\317\200) in UTF-8 adds a byte.  Check for
+                # the expected size.
+                test 221 -eq "$(git cat-file -s i18n)" &&
+                # ...and for the expected translation of bytes.
                 git cat-file commit i18n >actual &&
-                grep "Áéí óú" actual)
-
+                grep $(printf "\317\200") actual &&
+                # Also make sure the commit does not have the "encoding" header
+                ! grep ^encoding actual)
 '
+
 test_expect_success 'import/export-marks' '
 
        git checkout -b marks master &&
@@ -224,7 +232,6 @@ GIT_COMMITTER_NAME='C O Mitter'; export GIT_COMMITTER_NAME
 
 test_expect_success 'setup copies' '
 
-       git config --unset i18n.commitencoding &&
        git checkout -b copy rein &&
        git mv file file3 &&
        git commit -m move1 &&
diff --git a/t/t9350/simple-iso-8859-7-commit-message.txt b/t/t9350/simple-iso-8859-7-commit-message.txt
new file mode 100644 (file)
index 0000000..8b3f0c3
--- /dev/null
@@ -0,0 +1 @@
+Pi: ð
\ No newline at end of file