diff options
| author | Vsevolod Stakhov <vsevolod@rspamd.com> | 2022-10-03 23:16:33 +0100 |
|---|---|---|
| committer | Vsevolod Stakhov <vsevolod@rspamd.com> | 2022-10-03 23:16:33 +0100 |
| commit | e5328bd63e30aba25e20fb94a21927a5eef61e50 (patch) | |
| tree | 672adaec19d4c59a9be467283f7f16854b4cccda /src/libutil | |
| parent | 572e0b07c3cc9285b7e634d0d56172772e415efe (diff) | |
| download | rspamd-e5328bd63e30aba25e20fb94a21927a5eef61e50.tar.gz rspamd-e5328bd63e30aba25e20fb94a21927a5eef61e50.zip | |
[Fix] Fix emoji joiner FP
Issue: #4290
Diffstat (limited to 'src/libutil')
| -rw-r--r-- | src/libutil/cxx/utf8_util.cxx | 4 |
1 files changed, 3 insertions, 1 deletions
diff --git a/src/libutil/cxx/utf8_util.cxx b/src/libutil/cxx/utf8_util.cxx index 8c727e9ad..0e7cd39d7 100644 --- a/src/libutil/cxx/utf8_util.cxx +++ b/src/libutil/cxx/utf8_util.cxx @@ -85,8 +85,10 @@ rspamd_normalise_unicode_inplace(char *start, size_t *len) if (!zw_spaces.isFrozen()) { /* Add zw spaces to the set */ zw_spaces.add(0x200B); + /* TODO: ZW non joiner, it might be used for ligatures, so it should possibly be excluded as well */ zw_spaces.add(0x200C); - zw_spaces.add(0x200D); + /* See github issue #4290 for explanation. It seems that the ZWJ has many legit use cases */ + //zw_spaces.add(0x200D); zw_spaces.add(0xFEF); zw_spaces.add(0x00AD); zw_spaces.freeze(); |