diff options
author | Nicolás Reynolds <fauno@kiwwwi.com.ar> | 2012-05-23 12:45:39 -0300 |
---|---|---|
committer | Nicolás Reynolds <fauno@kiwwwi.com.ar> | 2012-05-23 12:45:39 -0300 |
commit | 7516400a778a0a4a0668d0a2ea797a635d6d4dd2 (patch) | |
tree | 5ab321abf9f41be345f44409235b62ccb31e0d49 /extra/icu/fix_broken_regex.diff | |
parent | 1de77ff2ad96a2adfd9eb797bb2ca1bb15c2a707 (diff) | |
parent | 39c366b9fc1b83a741177d0b415a20147a18a3c0 (diff) |
Merge branch 'master' of ssh://gparabola/srv/git/abslibre-mips64el
Diffstat (limited to 'extra/icu/fix_broken_regex.diff')
-rw-r--r-- | extra/icu/fix_broken_regex.diff | 35 |
1 files changed, 35 insertions, 0 deletions
diff --git a/extra/icu/fix_broken_regex.diff b/extra/icu/fix_broken_regex.diff new file mode 100644 index 000000000..8161a1107 --- /dev/null +++ b/extra/icu/fix_broken_regex.diff @@ -0,0 +1,35 @@ +--- i18n/regexcmp.cpp ++++ i18n/regexcmp.cpp +@@ -3307,8 +3307,29 @@ + + case URX_STRING_I: +- // TODO: Is the case-folded string the longest? +- // If so we can optimize this the same as URX_STRING. +- loc++; +- currentLen = INT32_MAX; ++ // TODO: This code assumes that any user string that matches will be no longer ++ // than our compiled string, with case insensitive matching. ++ // Our compiled string has been case-folded already. ++ // ++ // Any matching user string will have no more code points than our ++ // compiled (folded) string. Folding may add code points, but ++ // not remove them. ++ // ++ // There is a potential problem if a supplemental code point ++ // case-folds to a BMP code point. In this case our compiled string ++ // could be shorter (in code units) than a matching user string. ++ // ++ // At this time (Unicode 6.1) there are no such characters, and this case ++ // is not being handled. A test, intltest regex/Bug9283, will fail if ++ // any problematic characters are added to Unicode. ++ // ++ // If this happens, we can make a set of the BMP chars that the ++ // troublesome supplementals fold to, scan our string, and bump the ++ // currentLen one extra for each that is found. ++ // ++ { ++ loc++; ++ int32_t stringLenOp = (int32_t)fRXPat->fCompiledPat->elementAti(loc); ++ currentLen = safeIncrement(currentLen, URX_VAL(stringLenOp)); ++ } + break; |