diff options
author | jan.nijtmans <nijtmans@users.sourceforge.net> | 2020-04-21 09:49:19 (GMT) |
---|---|---|
committer | jan.nijtmans <nijtmans@users.sourceforge.net> | 2020-04-21 09:49:19 (GMT) |
commit | e6d30d023d0709ee78fbe25603c9ee44017b3b5c (patch) | |
tree | 7e16249fb6cd86a52a1f82d6094e8bbf09039746 | |
parent | 206022e9799361a82f91780bace269e514fb27bf (diff) | |
download | tcl-e6d30d023d0709ee78fbe25603c9ee44017b3b5c.zip tcl-e6d30d023d0709ee78fbe25603c9ee44017b3b5c.tar.gz tcl-e6d30d023d0709ee78fbe25603c9ee44017b3b5c.tar.bz2 |
More test cleanup
-rw-r--r-- | generic/tclUtf.c | 4 | ||||
-rw-r--r-- | tests/utf.test | 24 |
2 files changed, 20 insertions, 8 deletions
diff --git a/generic/tclUtf.c b/generic/tclUtf.c index c018472..d753321 100644 --- a/generic/tclUtf.c +++ b/generic/tclUtf.c @@ -563,7 +563,7 @@ Tcl_UtfToChar16( *chPtr = byte; return 1; } - + /* *--------------------------------------------------------------------------- * @@ -910,7 +910,7 @@ Tcl_UtfNext( * determine for certain in all circumstances whether the character * that begins with the returned pointer will or will not include * the byte src[-1]. In the scenario, where src points to the end of - * a buffer being filled, the returned pointer point to either the + * a buffer being filled, the returned pointer points to either the * final complete character in the string or to the earliest byte * that might start an incomplete character waiting for more bytes to * complete. diff --git a/tests/utf.test b/tests/utf.test index a12cc73..d4f45e9 100644 --- a/tests/utf.test +++ b/tests/utf.test @@ -140,10 +140,10 @@ test utf-4.10 {Tcl_NumUtfChars: #u0000, calc len, overcomplete} {testnumutfchars testnumutfchars [testbytestring "\x00"] end+1 } {2} test utf-4.11 {Tcl_NumUtfChars: 3 bytes of 4-byte UTF-8 characater} {testnumutfchars testbytestring} { - testnumutfchars [testbytestring \xf0\x9f\x92\xa9] end-1 + testnumutfchars [testbytestring \xF0\x9F\x92\xA9] end-1 } {3} test utf-4.12 {Tcl_NumUtfChars: #4-byte UTF-8 character} {testnumutfchars testbytestring tip389} { - testnumutfchars [testbytestring \xf0\x9f\x92\xa9] end + testnumutfchars [testbytestring \xF0\x9F\x92\xA9] end } {2} test utf-5.1 {Tcl_UtfFindFirst} {testfindfirst testbytestring} { @@ -246,7 +246,7 @@ test utf-6.30 {Tcl_UtfNext} testutfnext { testutfnext \xF2 } 1 test utf-6.31 {Tcl_UtfNext} testutfnext { - testutfnext \xF2A + testutfnext \xF2G } 1 test utf-6.32 {Tcl_UtfNext} testutfnext { testutfnext \xF2\xA0 @@ -369,7 +369,7 @@ test utf-6.71 {Tcl_UtfNext} testutfnext { testutfnext \xF2\xA0\xA0\xE8 } 1 test utf-6.71 {Tcl_UtfNext} testutfnext { - testutfnext \xF2\xA0\xA0\xF4 + testutfnext \xF2\xA0\xA0\xF2 } 1 test utf-6.73 {Tcl_UtfNext} testutfnext { testutfnext \xF2\xA0\xA0\xF8 @@ -434,6 +434,18 @@ test utf-6.90 {Tcl_UtfNext, validity check [493dccc2de]} testutfnext { test utf-6.91 {Tcl_UtfNext, validity check [493dccc2de]} testutfnext { testutfnext \xF4\x90\x80\x80 } 1 +test utf-6.92 {Tcl_UtfNext, pointing to 2th byte of 4-byte valid sequence} testutfnext { + testutfnext \xA0\xA0\xA0 +} 1 +test utf-6.92.1 {Tcl_UtfNext, pointing to 2th byte of 4-byte valid sequence} testutfnext { + testutfnext \xF2\xA0\xA0\xA0 1 +} 2 +test utf-6.93 {Tcl_UtfNext, pointing to 2th byte of 4-byte invalid sequence} testutfnext { + testutfnext \x80\x80\x80 +} 1 +test utf-6.93.1 {Tcl_UtfNext, pointing to 2th byte of 4-byte invalid sequence} testutfnext { + testutfnext \xF0\x80\x80\x80 1 +} 2 test utf-7.1 {Tcl_UtfPrev} testutfprev { testutfprev {} @@ -861,8 +873,8 @@ test utf-12.3 {Tcl_UtfToLower} { string tolower \xC3GH } \xE3gh test utf-12.4 {Tcl_UtfToLower} { - string tolower \u01E2AB -} \u01E3ab + string tolower \u01E2GH +} \u01E3gh test utf-12.5 {Tcl_UtfToLower Georgian (new in Unicode 11)} { string tolower \u10D0\u1C90 } \u10D0\u10D0 |