git@vger.kernel.org mailing list mirror (one of many)
 help / color / mirror / code / Atom feed
From: lars.schneider@autodesk.com
To: git@vger.kernel.org
Cc: gitster@pobox.com, tboegi@web.de, j6t@kdbg.org,
	sunshine@sunshineco.com, peff@peff.net,
	ramsay@ramsayjones.plus.com, Johannes.Schindelin@gmx.de,
	pclouds@gmail.com, Lars Schneider <larsxschneider@gmail.com>
Subject: [PATCH v11 07/10] convert: check for detectable errors in UTF encodings
Date: Fri,  9 Mar 2018 18:35:33 +0100	[thread overview]
Message-ID: <20180309173536.62012-8-lars.schneider@autodesk.com> (raw)
In-Reply-To: <20180309173536.62012-1-lars.schneider@autodesk.com>

From: Lars Schneider <larsxschneider@gmail.com>

Check that new content is valid with respect to the user defined
'working-tree-encoding' attribute.

Signed-off-by: Lars Schneider <larsxschneider@gmail.com>
---
 convert.c                        | 48 ++++++++++++++++++++++++++++++++++
 t/t0028-working-tree-encoding.sh | 56 ++++++++++++++++++++++++++++++++++++++++
 2 files changed, 104 insertions(+)

diff --git a/convert.c b/convert.c
index aa59ecfe49..b80d666a6b 100644
--- a/convert.c
+++ b/convert.c
@@ -266,6 +266,51 @@ static int will_convert_lf_to_crlf(size_t len, struct text_stat *stats,
 
 }
 
+static int validate_encoding(const char *path, const char *enc,
+		      const char *data, size_t len, int die_on_error)
+{
+	/* We only check for UTF here as UTF?? can be an alias for UTF-?? */
+	if (istarts_with(enc, "UTF")) {
+		/*
+		 * Check for detectable errors in UTF encodings
+		 */
+		if (has_prohibited_utf_bom(enc, data, len)) {
+			const char *error_msg = _(
+				"BOM is prohibited in '%s' if encoded as %s");
+			/*
+			 * This advice is shown for UTF-??BE and UTF-??LE encodings.
+			 */
+			const char *advise_msg = _(
+				"The file '%s' contains a byte order "
+				"mark (BOM). Please use %.6s as "
+				"working-tree-encoding.");
+			advise(advise_msg, path, enc);
+			if (die_on_error)
+				die(error_msg, path, enc);
+			else {
+				return error(error_msg, path, enc);
+			}
+
+		} else if (is_missing_required_utf_bom(enc, data, len)) {
+			const char *error_msg = _(
+				"BOM is required in '%s' if encoded as %s");
+			const char *advise_msg = _(
+				"The file '%s' is missing a byte order "
+				"mark (BOM). Please use %sBE or %sLE "
+				"(depending on the byte order) as "
+				"working-tree-encoding.");
+			advise(advise_msg, path, enc, enc);
+			if (die_on_error)
+				die(error_msg, path, enc);
+			else {
+				return error(error_msg, path, enc);
+			}
+		}
+
+	}
+	return 0;
+}
+
 static const char *default_encoding = "UTF-8";
 
 static int encode_to_git(const char *path, const char *src, size_t src_len,
@@ -291,6 +336,9 @@ static int encode_to_git(const char *path, const char *src, size_t src_len,
 	if (!buf && !src)
 		return 1;
 
+	if (validate_encoding(path, enc, src, src_len, die_on_error))
+		return 0;
+
 	dst = reencode_string_len(src, src_len, default_encoding, enc,
 				  &dst_len);
 	if (!dst) {
diff --git a/t/t0028-working-tree-encoding.sh b/t/t0028-working-tree-encoding.sh
index e492945a01..e8408dfe5c 100755
--- a/t/t0028-working-tree-encoding.sh
+++ b/t/t0028-working-tree-encoding.sh
@@ -62,6 +62,46 @@ test_expect_success 'check $GIT_DIR/info/attributes support' '
 
 for i in 16 32
 do
+	test_expect_success "check prohibited UTF-${i} BOM" '
+		test_when_finished "git reset --hard HEAD" &&
+
+		echo "*.utf${i}be text working-tree-encoding=utf-${i}be" >>.gitattributes &&
+		echo "*.utf${i}le text working-tree-encoding=utf-${i}LE" >>.gitattributes &&
+
+		# Here we add a UTF-16 (resp. UTF-32) files with BOM (big/little-endian)
+		# but we tell Git to treat it as UTF-16BE/UTF-16LE (resp. UTF-32).
+		# In these cases the BOM is prohibited.
+		cp bebom.utf${i}be.raw bebom.utf${i}be &&
+		test_must_fail git add bebom.utf${i}be 2>err.out &&
+		test_i18ngrep "fatal: BOM is prohibited .* utf-${i}be" err.out &&
+
+		cp lebom.utf${i}le.raw lebom.utf${i}be &&
+		test_must_fail git add lebom.utf${i}be 2>err.out &&
+		test_i18ngrep "fatal: BOM is prohibited .* utf-${i}be" err.out &&
+
+		cp bebom.utf${i}be.raw bebom.utf${i}le &&
+		test_must_fail git add bebom.utf${i}le 2>err.out &&
+		test_i18ngrep "fatal: BOM is prohibited .* utf-${i}LE" err.out &&
+
+		cp lebom.utf${i}le.raw lebom.utf${i}le &&
+		test_must_fail git add lebom.utf${i}le 2>err.out &&
+		test_i18ngrep "fatal: BOM is prohibited .* utf-${i}LE" err.out
+	'
+
+	test_expect_success "check required UTF-${i} BOM" '
+		test_when_finished "git reset --hard HEAD" &&
+
+		echo "*.utf${i} text working-tree-encoding=utf-${i}" >>.gitattributes &&
+
+		cp nobom.utf${i}be.raw nobom.utf${i} &&
+		test_must_fail git add nobom.utf${i} 2>err.out &&
+		test_i18ngrep "fatal: BOM is required .* utf-${i}" err.out &&
+
+		cp nobom.utf${i}le.raw nobom.utf${i} &&
+		test_must_fail git add nobom.utf${i} 2>err.out &&
+		test_i18ngrep "fatal: BOM is required .* utf-${i}" err.out
+	'
+
 	test_expect_success "eol conversion for UTF-${i} encoded files on checkout" '
 		test_when_finished "rm -f crlf.utf${i}.raw lf.utf${i}.raw" &&
 		test_when_finished "git reset --hard HEAD^" &&
@@ -141,4 +181,20 @@ test_expect_success 'error if encoding round trip is not the same during refresh
 	test_i18ngrep "error: .* overwritten by checkout:" err.out
 '
 
+test_expect_success 'error if encoding garbage is already in Git' '
+	BEFORE_STATE=$(git rev-parse HEAD) &&
+	test_when_finished "git reset --hard $BEFORE_STATE" &&
+
+	# Skip the UTF-16 filter for the added file
+	# This simulates a Git version that has no checkoutEncoding support
+	cp nobom.utf16be.raw nonsense.utf16 &&
+	TEST_HASH=$(git hash-object --no-filters -w nonsense.utf16) &&
+	git update-index --add --cacheinfo 100644 $TEST_HASH nonsense.utf16 &&
+	COMMIT=$(git commit-tree -p $(git rev-parse HEAD) -m "plain commit" $(git write-tree)) &&
+	git update-ref refs/heads/master $COMMIT &&
+
+	git diff 2>err.out &&
+	test_i18ngrep "error: BOM is required" err.out
+'
+
 test_done
-- 
2.16.2


  parent reply	other threads:[~2018-03-09 17:37 UTC|newest]

Thread overview: 25+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-03-09 17:35 [PATCH v11 00/10] convert: add support for different encodings lars.schneider
2018-03-09 17:35 ` [PATCH v11 01/10] strbuf: remove unnecessary NUL assignment in xstrdup_tolower() lars.schneider
2018-03-09 17:35 ` [PATCH v11 02/10] strbuf: add xstrdup_toupper() lars.schneider
2018-03-09 17:35 ` [PATCH v11 03/10] strbuf: add a case insensitive starts_with() lars.schneider
2018-03-09 17:35 ` [PATCH v11 04/10] utf8: add function to detect prohibited UTF-16/32 BOM lars.schneider
2018-03-09 17:35 ` [PATCH v11 05/10] utf8: add function to detect a missing " lars.schneider
2018-03-09 17:35 ` [PATCH v11 06/10] convert: add 'working-tree-encoding' attribute lars.schneider
2018-03-09 19:10   ` Junio C Hamano
2018-03-15 21:23     ` Lars Schneider
2018-03-18  7:24   ` Torsten Bögershausen
2018-04-01 13:24     ` Lars Schneider
2018-04-05 16:41       ` Torsten Bögershausen
2018-04-15 16:54         ` Lars Schneider
2018-03-09 17:35 ` lars.schneider [this message]
2018-03-09 19:00   ` [PATCH v11 07/10] convert: check for detectable errors in UTF encodings Junio C Hamano
2018-03-09 19:04     ` Lars Schneider
2018-03-09 19:10   ` Junio C Hamano
2018-03-09 17:35 ` [PATCH v11 08/10] convert: advise canonical UTF encoding names lars.schneider
2018-03-09 19:11   ` Junio C Hamano
2018-03-15 22:42     ` Lars Schneider
2018-03-09 17:35 ` [PATCH v11 09/10] convert: add tracing for 'working-tree-encoding' attribute lars.schneider
2018-03-09 17:35 ` [PATCH v11 10/10] convert: add round trip check based on 'core.checkRoundtripEncoding' lars.schneider
2018-03-09 20:18   ` Eric Sunshine
2018-03-09 20:22     ` Junio C Hamano
2018-03-09 20:27       ` Eric Sunshine

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

  List information: http://vger.kernel.org/majordomo-info.html

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20180309173536.62012-8-lars.schneider@autodesk.com \
    --to=lars.schneider@autodesk.com \
    --cc=Johannes.Schindelin@gmx.de \
    --cc=git@vger.kernel.org \
    --cc=gitster@pobox.com \
    --cc=j6t@kdbg.org \
    --cc=larsxschneider@gmail.com \
    --cc=pclouds@gmail.com \
    --cc=peff@peff.net \
    --cc=ramsay@ramsayjones.plus.com \
    --cc=sunshine@sunshineco.com \
    --cc=tboegi@web.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
Code repositories for project(s) associated with this public inbox

	https://80x24.org/mirrors/git.git

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).