[PATCH v13 10/10] convert: add round trip check based on 'core.checkRoundtripEncoding'

[lars.schneider@autodesk.com]

From: Lars Schneider <larsxschneider@gmail.com>

UTF supports lossless conversion round tripping and conversions between
UTF and other encodings are mostly round trip safe as Unicode aims to be
a superset of all other character encodings. However, certain encodings
(e.g. SHIFT-JIS) are known to have round trip issues [1].

Add 'core.checkRoundtripEncoding', which contains a comma separated
list of encodings, to define for what encodings Git should check the
conversion round trip if they are used in the 'working-tree-encoding'
attribute.

Set SHIFT-JIS as default value for 'core.checkRoundtripEncoding'.

[1] https://support.microsoft.com/en-us/help/170559/prb-conversion-problem-between-shift-jis-and-unicode

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
---
 Documentation/config.txt         |  6 ++++
 Documentation/gitattributes.txt  |  8 +++++
 config.c                         |  5 +++
 convert.c                        | 77 ++++++++++++++++++++++++++++++++++++++++
 convert.h                        |  1 +
 environment.c                    |  1 +
 t/t0028-working-tree-encoding.sh | 39 ++++++++++++++++++++
 7 files changed, 137 insertions(+)

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 0e25b2c92b..7dcac9b540 100644
--- a/Documentation/config.txt
+++ b/Documentation/config.txt
@@ -530,6 +530,12 @@ core.autocrlf::
 	This variable can be set to 'input',
 	in which case no output conversion is performed.
 
+core.checkRoundtripEncoding::
+	A comma and/or whitespace separated list of encodings that Git
+	performs UTF-8 round trip checks on if they are used in an
+	`working-tree-encoding` attribute (see linkgit:gitattributes[5]).
+	The default value is `SHIFT-JIS`.
+
 core.symlinks::
 	If false, symbolic links are checked out as small plain files that
 	contain the link text. linkgit:git-update-index[1] and
diff --git a/Documentation/gitattributes.txt b/Documentation/gitattributes.txt
index 31a4f92840..aa3deae392 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -312,6 +312,14 @@ number of pitfalls:
   internal contents as UTF-8 and try to convert it to UTF-16 on checkout.
   That operation will fail and cause an error.
 
+- Reencoding content to non-UTF encodings can cause errors as the
+  conversion might not be UTF-8 round trip safe. If you suspect your
+  encoding to not be round trip safe, then add it to
+  `core.checkRoundtripEncoding` to make Git check the round trip
+  encoding (see linkgit:git-config[1]). SHIFT-JIS (Japanese character
+  set) is known to have round trip issues with UTF-8 and is checked by
+  default.
+
 - Reencoding content requires resources that might slow down certain
   Git operations (e.g 'git checkout' or 'git add').
 
diff --git a/config.c b/config.c
index 1f003fbb90..d0ada9fcd4 100644
--- a/config.c
+++ b/config.c
@@ -1172,6 +1172,11 @@ static int git_default_core_config(const char *var, const char *value)
 		return 0;
 	}
 
+	if (!strcmp(var, "core.checkroundtripencoding")) {
+		check_roundtrip_encoding = xstrdup(value);
+		return 0;
+	}
+
 	if (!strcmp(var, "core.notesref")) {
 		notes_ref_name = xstrdup(value);
 		return 0;
diff --git a/convert.c b/convert.c
index bc35c33249..1ae6301629 100644
--- a/convert.c
+++ b/convert.c
@@ -347,6 +347,42 @@ static void trace_encoding(const char *context, const char *path,
 	strbuf_release(&trace);
 }
 
+static int check_roundtrip(const char *enc_name)
+{
+	/*
+	 * check_roundtrip_encoding contains a string of comma and/or
+	 * space separated encodings (eg. "UTF-16, ASCII, CP1125").
+	 * Search for the given encoding in that string.
+	 */
+	const char *found = strcasestr(check_roundtrip_encoding, enc_name);
+	const char *next;
+	int len;
+	if (!found)
+		return 0;
+	next = found + strlen(enc_name);
+	len = strlen(check_roundtrip_encoding);
+	return (found && (
+			/*
+			 * check that the found encoding is at the
+			 * beginning of check_roundtrip_encoding or
+			 * that it is prefixed with a space or comma
+			 */
+			found == check_roundtrip_encoding || (
+				(isspace(found[-1]) || found[-1] == ',')
+			)
+		) && (
+			/*
+			 * check that the found encoding is at the
+			 * end of check_roundtrip_encoding or
+			 * that it is suffixed with a space or comma
+			 */
+			next == check_roundtrip_encoding + len || (
+				next < check_roundtrip_encoding + len &&
+				(isspace(next[0]) || next[0] == ',')
+			)
+		));
+}
+
 static const char *default_encoding = "UTF-8";
 
 static int encode_to_git(const char *path, const char *src, size_t src_len,
@@ -395,6 +431,47 @@ static int encode_to_git(const char *path, const char *src, size_t src_len,
 	}
 	trace_encoding("destination", path, default_encoding, dst, dst_len);
 
+	/*
+	 * UTF supports lossless conversion round tripping [1] and conversions
+	 * between UTF and other encodings are mostly round trip safe as
+	 * Unicode aims to be a superset of all other character encodings.
+	 * However, certain encodings (e.g. SHIFT-JIS) are known to have round
+	 * trip issues [2]. Check the round trip conversion for all encodings
+	 * listed in core.checkRoundtripEncoding.
+	 *
+	 * The round trip check is only performed if content is written to Git.
+	 * This ensures that no information is lost during conversion to/from
+	 * the internal UTF-8 representation.
+	 *
+	 * Please note, the code below is not tested because I was not able to
+	 * generate a faulty round trip without an iconv error. Iconv errors
+	 * are already caught above.
+	 *
+	 * [1] http://unicode.org/faq/utf_bom.html#gen2
+	 * [2] https://support.microsoft.com/en-us/help/170559/prb-conversion-problem-between-shift-jis-and-unicode
+	 */
+	if (die_on_error && check_roundtrip(enc)) {
+		char *re_src;
+		int re_src_len;
+
+		re_src = reencode_string_len(dst, dst_len,
+					     enc, default_encoding,
+					     &re_src_len);
+
+		trace_printf("Checking roundtrip encoding for %s...\n", enc);
+		trace_encoding("reencoded source", path, enc,
+			       re_src, re_src_len);
+
+		if (!re_src || src_len != re_src_len ||
+		    memcmp(src, re_src, src_len)) {
+			const char* msg = _("encoding '%s' from %s to %s and "
+					    "back is not the same");
+			die(msg, path, enc, default_encoding);
+		}
+
+		free(re_src);
+	}
+
 	strbuf_attach(buf, dst, dst_len, dst_len + 1);
 	return 1;
 }
diff --git a/convert.h b/convert.h
index 1d9539ed0b..765abfbd60 100644
--- a/convert.h
+++ b/convert.h
@@ -56,6 +56,7 @@ struct delayed_checkout {
 };
 
 extern enum eol core_eol;
+extern char *check_roundtrip_encoding;
 extern const char *get_cached_convert_stats_ascii(const struct index_state *istate,
 						  const char *path);
 extern const char *get_wt_convert_stats_ascii(const char *path);
diff --git a/environment.c b/environment.c
index 10a32c20ac..5bae9131ad 100644
--- a/environment.c
+++ b/environment.c
@@ -50,6 +50,7 @@ int check_replace_refs = 1;
 char *git_replace_ref_base;
 enum eol core_eol = EOL_UNSET;
 int global_conv_flags_eol = CONV_EOL_RNDTRP_WARN;
+char *check_roundtrip_encoding = "SHIFT-JIS";
 unsigned whitespace_rule_cfg = WS_DEFAULT_RULE;
 enum branch_track git_branch_track = BRANCH_TRACK_REMOTE;
 enum rebase_setup_type autorebase = AUTOREBASE_NEVER;
diff --git a/t/t0028-working-tree-encoding.sh b/t/t0028-working-tree-encoding.sh
index 026544ce09..12b8eb963a 100755
--- a/t/t0028-working-tree-encoding.sh
+++ b/t/t0028-working-tree-encoding.sh
@@ -203,4 +203,43 @@ test_expect_success 'error if encoding garbage is already in Git' '
 	test_i18ngrep "error: BOM is required" err.out
 '
 
+test_expect_success 'check roundtrip encoding' '
+	test_when_finished "rm -f roundtrip.shift roundtrip.utf16" &&
+	test_when_finished "git reset --hard HEAD" &&
+
+	text="hallo there!\nroundtrip test here!" &&
+	printf "$text" | iconv -f UTF-8 -t SHIFT-JIS >roundtrip.shift &&
+	printf "$text" | iconv -f UTF-8 -t UTF-16 >roundtrip.utf16 &&
+	echo "*.shift text working-tree-encoding=SHIFT-JIS" >>.gitattributes &&
+
+	# SHIFT-JIS encoded files are round-trip checked by default...
+	GIT_TRACE=1 git add .gitattributes roundtrip.shift 2>&1 |
+		grep "Checking roundtrip encoding for SHIFT-JIS" &&
+	git reset &&
+
+	# ... unless we overwrite the Git config!
+	! GIT_TRACE=1 git -c core.checkRoundtripEncoding=garbage \
+		add .gitattributes roundtrip.shift 2>&1 |
+		grep "Checking roundtrip encoding for SHIFT-JIS" &&
+	git reset &&
+
+	# UTF-16 encoded files should not be round-trip checked by default...
+	! GIT_TRACE=1 git add roundtrip.utf16 2>&1 |
+		grep "Checking roundtrip encoding for UTF-16" &&
+	git reset &&
+
+	# ... unless we tell Git to check it!
+	GIT_TRACE=1 git -c core.checkRoundtripEncoding="UTF-16, UTF-32" \
+		add roundtrip.utf16 2>&1 |
+		grep "Checking roundtrip encoding for utf-16" &&
+	git reset &&
+
+	# ... unless we tell Git to check it!
+	# (here we also check that the casing of the encoding is irrelevant)
+	GIT_TRACE=1 git -c core.checkRoundtripEncoding="UTF-32, utf-16" \
+		add roundtrip.utf16 2>&1 |
+		grep "Checking roundtrip encoding for utf-16" &&
+	git reset
+'
+
 test_done
-- 
2.16.2