diff options
| -rw-r--r-- | .metadata.txt | 15 | ||||
| -rw-r--r-- | STUFF-2-DO.txt | 43 | ||||
| -rw-r--r-- | harness.c | 2 |
3 files changed, 52 insertions, 8 deletions
diff --git a/.metadata.txt b/.metadata.txt index b351678..bec6328 100644 --- a/.metadata.txt +++ b/.metadata.txt @@ -1,7 +1,8 @@ -CVTUTF7.C 2006-05-10 10:41 -CVTUTF7.H 2006-05-10 10:41 -ConvertUTF.c 2006-05-10 10:41 -ConvertUTF.h 2006-05-10 10:41 -ExpectedOutput.txt 2006-05-10 10:41 -harness.c 2006-05-10 10:41 -readme.txt 2006-05-10 10:41 +CVTUTF7.C 2007-05-22 17:49 +CVTUTF7.H 2007-05-22 17:49 +ConvertUTF.c 2007-05-22 17:49 +ConvertUTF.h 2007-05-22 17:49 +ExpectedOutput.txt 2007-05-22 17:49 +STUFF-2-DO.txt 2007-05-22 17:49 +harness.c 2007-05-22 17:49 +readme.txt 2007-05-22 17:49 diff --git a/STUFF-2-DO.txt b/STUFF-2-DO.txt new file mode 100644 index 0000000..2a69875 --- /dev/null +++ b/STUFF-2-DO.txt @@ -0,0 +1,43 @@ +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- + +Date/Time: Sat Apr 16 13:53:34 CST 2005 +Contact: vince@nethacker.com +Report Type: Error Report +Opt Subject: + +http://www.unicode.org/Public/PROGRAMS/CVTUTF/ConvertUTF.c + +Line: 261 +if a UTF16 surrogate pair combines to form a UTF-32 character and the strictConversion flag is set, shouldn't the function halt the conversion and return sourceIllegal? That seems to be the behavior most other places. + +Line: 438 +if the input containts an invalid UTF-32 character and the strictConversion flag is set, shouldn't the function halt the conversion and return sourceIllegal? That seems to be the behavior most other places. + + +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +(End of Report) + + +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- + +Date/Time: Wed Apr 4 09:30:06 CST 2007 +Contact: willem.dijkstra@tno.nl +Name: Willem Dijkstra +Report Type: Other Question, Problem, or Feedback +Opt Subject: harness.c + +Hello, + +I have a question about the harness.c example file at ftp://www.unicode.org/Public/PROGRAMS/CVTUTF/: +- test01 checks the following sequence: + { 1, 3, { 0xF0, 0x93, 0xB2, 0xA1, 0x00 }}, /* 5 */ +- The data should be read as 1 = good sequence, 3 = length of unicode, sequence + +Should that 3 be a 4? + +Cheers, +Willem + +-- -- -- -- -- -- -- -- -- -- -- -- -- -- -- -- +(End of Report) + @@ -79,7 +79,7 @@ struct utf8_test utf8_testData[] = { { 1, 2, { 0xDF, 0xB2, 0x00, 0x00, 0x00 }}, /* 2 */ { 1, 3, { 0xE0, 0xA1, 0x81, 0x00, 0x00 }}, /* 3 */ { 1, 3, { 0xE1, 0xAC, 0x90, 0x00, 0x00 }}, /* 4 */ - { 1, 3, { 0xF0, 0x93, 0xB2, 0xA1, 0x00 }}, /* 5 */ + { 1, 4, { 0xF0, 0x93, 0xB2, 0xA1, 0x00 }}, /* 5 */ { 1, 4, { 0xF1, 0x87, 0x9A, 0xB0, 0x00 }}, /* 6 */ { 1, 4, { 0xF3, 0x88, 0x9B, 0xAD, 0x00 }}, /* 7 */ { 1, 4, { 0xF4, 0x82, 0x89, 0x8F, 0x00 }}, /* 8 */ |