Skip to content

Fix literal string matching for external annotation filter values #2526

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
sirus20x6 wants to merge 1 commit into
base: develop
Choose a base branch
from
+22 −2
Open

Fix literal string matching for external annotation filter values #2526

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 22 additions & 2 deletions filter.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2883,12 +2883,24 @@ static void cmp_vector_strings(token_t *atok, token_t *btok, token_t *rtok)
return;
}
if ( !regex )
rtok->pass_site = _match_vector_strings(atok->str_value.s, atok->str_value.l, btok->str_value.s, btok->str_value.l, logic, missing_logic);
{
// When either operand is an external value (set via filter_test_ext),
// compare as literal strings rather than splitting on commas. External
// values come from annotation file columns and may contain commas that
// are part of the value, not VCF multi-value separators. (see gh #2506)
if ( atok->iext || btok->iext )
{
int match = atok->str_value.l==btok->str_value.l && !strncmp(atok->str_value.s,btok->str_value.s,atok->str_value.l) ? 1 : 0;
if ( logic==TOK_NE ) match = match ? 0 : 1;
rtok->pass_site = match;
}
else
rtok->pass_site = _match_vector_strings(atok->str_value.s, atok->str_value.l, btok->str_value.s, btok->str_value.l, logic, missing_logic);
}
else
{
token_t *tok = atok->regex ? btok : atok;
rtok->pass_site = _regex_vector_strings(regex, tok->str_value.s, tok->str_value.l, logic, missing_logic);
fprintf(stderr,"pass=%d [%s]\n",rtok->pass_site,tok->str_value.s);
}
return;
}
Expand Down Expand Up @@ -2934,6 +2946,14 @@ static void cmp_vector_strings(token_t *atok, token_t *btok, token_t *rtok)
int match;
if ( regex )
match = _regex_vector_strings(regex, xtok->str_value.s + i*xtok->nval1, xtok->nval1, logic, missing_logic);
else if ( atok->iext || btok->iext )
{
char *xstr = xtok->str_value.s + i*xtok->nval1;
size_t xlen = 0;
while ( xlen < (size_t)xtok->nval1 && xstr[xlen] ) xlen++;
match = xlen==ytok->str_value.l && !strncmp(xstr,ytok->str_value.s,xlen) ? 1 : 0;
if ( logic==TOK_NE ) match = match ? 0 : 1;
}
else
match = _match_vector_strings(xtok->str_value.s + i*xtok->nval1, xtok->nval1, ytok->str_value.s, ytok->str_value.l, logic, missing_logic);
if ( match ) { rtok->pass_samples[i] = 1; rtok->pass_site = 1; }
Expand Down