From: Lars Schneider <larsxschnei...@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 <larsxschnei...@gmail.com>
---
 Documentation/config.txt         |  6 ++++
 Documentation/gitattributes.txt  |  7 ++++
 config.c                         |  5 +++
 convert.c                        | 74 ++++++++++++++++++++++++++++++++++++++++
 convert.h                        |  1 +
 environment.c                    |  1 +
 t/t0028-working-tree-encoding.sh | 41 ++++++++++++++++++++++
 7 files changed, 135 insertions(+)

diff --git a/Documentation/config.txt b/Documentation/config.txt
index 0e25b2c92b..d7a56054a5 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 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 4ecdcd4859..ea5a9509c6 100644
--- a/Documentation/gitattributes.txt
+++ b/Documentation/gitattributes.txt
@@ -298,6 +298,13 @@ number of pitfalls:
   older Git versions and alternative Git implementations such as JGit
   or libgit2 (as of February 2018).
 
+- 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 5b49416ee1..71dffc7167 100644
--- a/convert.c
+++ b/convert.c
@@ -289,6 +289,39 @@ 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 space and/or
+        * comma 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 = found + strlen(enc_name);
+       int 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 || (
+                               found > check_roundtrip_encoding &&
+                               (*(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 &&
+                               (*next == ' ' || *next == ',')
+                       )
+               ));
+}
+
 static struct encoding {
        const char *name;
        struct encoding *next;
@@ -366,6 +399,47 @@ 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 ((conv_flags & CONV_WRITE_OBJECT) && check_roundtrip(enc->name)) {
+               char *re_src;
+               int re_src_len;
+
+               re_src = reencode_string_len(dst, dst_len,
+                                            enc->name, default_encoding,
+                                            &re_src_len);
+
+               trace_printf("Checking roundtrip encoding for %s...\n", 
enc->name);
+               trace_encoding("reencoded source", path, enc->name,
+                              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->name, 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 01789ae1b8..5dcdd5f899 100755
--- a/t/t0028-working-tree-encoding.sh
+++ b/t/t0028-working-tree-encoding.sh
@@ -209,4 +209,45 @@ test_expect_success 'error if encoding garbage is already 
in Git' '
        git reset --hard $BEFORE_STATE
 '
 
+test_expect_success 'check roundtrip encoding' '
+       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 >/dev/null |
+               grep "Checking roundtrip encoding for SHIFT-JIS" &&
+       git reset &&
+
+       # ... unless we overwrite the Git config!
+       test_config core.checkRoundTripEncoding "garbage" &&
+       ! GIT_TRACE=1 git add .gitattributes roundtrip.shift 2>&1 >/dev/null |
+               grep "Checking roundtrip encoding for SHIFT-JIS" &&
+       test_unconfig core.checkRoundTripEncoding &&
+       git reset &&
+
+       # UTF-16 encoded files should not be round-trip checked by default...
+       ! GIT_TRACE=1 git add roundtrip.utf16 2>&1 >/dev/null |
+               grep "Checking roundtrip encoding for UTF-16" &&
+       git reset &&
+
+       # ... unless we tell Git to check it!
+       test_config_global core.checkRoundTripEncoding "UTF-16, UTF-32" &&
+       GIT_TRACE=1 git add roundtrip.utf16 2>&1 >/dev/null |
+               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)
+       test_config_global core.checkRoundTripEncoding "UTF-32, utf-16" &&
+       GIT_TRACE=1 git add roundtrip.utf16 2>&1 >/dev/null |
+               grep "Checking roundtrip encoding for UTF-16" &&
+       git reset &&
+
+       # cleanup
+       rm roundtrip.shift roundtrip.utf16 &&
+       git reset --hard HEAD
+'
+
 test_done
-- 
2.16.1

Reply via email to