diff options
| -rw-r--r-- | commit.c | 38 | ||||
| -rwxr-xr-x | t/t3900-i18n-commit.sh | 36 |
2 files changed, 68 insertions, 6 deletions
@@ -1350,10 +1350,15 @@ int commit_tree(const struct strbuf *msg, unsigned char *tree, static int find_invalid_utf8(const char *buf, int len) { int offset = 0; + static const unsigned int max_codepoint[] = { + 0x7f, 0x7ff, 0xffff, 0x10ffff + }; while (len) { unsigned char c = *buf++; int bytes, bad_offset; + unsigned int codepoint; + unsigned int min_val, max_val; len--; offset++; @@ -1374,24 +1379,48 @@ static int find_invalid_utf8(const char *buf, int len) bytes++; } - /* Must be between 1 and 5 more bytes */ - if (bytes < 1 || bytes > 5) + /* + * Must be between 1 and 3 more bytes. Longer sequences result in + * codepoints beyond U+10FFFF, which are guaranteed never to exist. + */ + if (bytes < 1 || 3 < bytes) return bad_offset; /* Do we *have* that many bytes? */ if (len < bytes) return bad_offset; + /* + * Place the encoded bits at the bottom of the value and compute the + * valid range. + */ + codepoint = (c & 0x7f) >> bytes; + min_val = max_codepoint[bytes-1] + 1; + max_val = max_codepoint[bytes]; + offset += bytes; len -= bytes; /* And verify that they are good continuation bytes */ do { + codepoint <<= 6; + codepoint |= *buf & 0x3f; if ((*buf++ & 0xc0) != 0x80) return bad_offset; } while (--bytes); - /* We could/should check the value and length here too */ + /* Reject codepoints that are out of range for the sequence length. */ + if (codepoint < min_val || codepoint > max_val) + return bad_offset; + /* Surrogates are only for UTF-16 and cannot be encoded in UTF-8. */ + if ((codepoint & 0x1ff800) == 0xd800) + return bad_offset; + /* U+xxFFFE and U+xxFFFF are guaranteed non-characters. */ + if ((codepoint & 0xffffe) == 0xfffe) + return bad_offset; + /* So are anything in the range U+FDD0..U+FDEF. */ + if (codepoint >= 0xfdd0 && codepoint <= 0xfdef) + return bad_offset; } return -1; } @@ -1401,9 +1430,6 @@ static int find_invalid_utf8(const char *buf, int len) * * If it isn't, it assumes any non-utf8 characters are Latin1, * and does the conversion. - * - * Fixme: we should probably also disallow overlong forms and - * invalid characters. But we don't do that currently. */ static int verify_utf8(struct strbuf *buf) { diff --git a/t/t3900-i18n-commit.sh b/t/t3900-i18n-commit.sh index 37ddabba2..38b00c37b 100755 --- a/t/t3900-i18n-commit.sh +++ b/t/t3900-i18n-commit.sh @@ -39,6 +39,42 @@ test_expect_failure 'UTF-16 refused because of NULs' ' git commit -a -F "$TEST_DIRECTORY"/t3900/UTF-16.txt ' +test_expect_success 'UTF-8 invalid characters refused' ' + test_when_finished "rm -f $HOME/stderr $HOME/invalid" && + echo "UTF-8 characters" >F && + printf "Commit message\n\nInvalid surrogate:\355\240\200\n" \ + >"$HOME/invalid" && + git commit -a -F "$HOME/invalid" 2>"$HOME"/stderr && + grep "did not conform" "$HOME"/stderr +' + +test_expect_success 'UTF-8 overlong sequences rejected' ' + test_when_finished "rm -f $HOME/stderr $HOME/invalid" && + rm -f "$HOME/stderr" "$HOME/invalid" && + echo "UTF-8 overlong" >F && + printf "\340\202\251ommit message\n\nThis is not a space:\300\240\n" \ + >"$HOME/invalid" && + git commit -a -F "$HOME/invalid" 2>"$HOME"/stderr && + grep "did not conform" "$HOME"/stderr +' + +test_expect_success 'UTF-8 non-characters refused' ' + test_when_finished "rm -f $HOME/stderr $HOME/invalid" && + echo "UTF-8 non-character 1" >F && + printf "Commit message\n\nNon-character:\364\217\277\276\n" \ + >"$HOME/invalid" && + git commit -a -F "$HOME/invalid" 2>"$HOME"/stderr && + grep "did not conform" "$HOME"/stderr +' + +test_expect_success 'UTF-8 non-characters refused' ' + test_when_finished "rm -f $HOME/stderr $HOME/invalid" && + echo "UTF-8 non-character 2." >F && + printf "Commit message\n\nNon-character:\357\267\220\n" \ + >"$HOME/invalid" && + git commit -a -F "$HOME/invalid" 2>"$HOME"/stderr && + grep "did not conform" "$HOME"/stderr +' for H in ISO8859-1 eucJP ISO-2022-JP do |