Skip to content
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

update to fail on duplicate LN tags, with different LN values #1882

Open
wants to merge 2 commits into
base: develop
Choose a base branch
from
Open

update to fail on duplicate LN tags, with different LN values #1882

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
51253f1
update to fail on duplicate LN tags, with different LN values
vasudeva8 Jan 27, 2025
8ccc6df
review update
vasudeva8 Feb 6, 2025
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
14 changes: 12 additions & 2 deletions header.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
/*
Copyright (c) 2018-2020, 2023 Genome Research Ltd.
Copyright (c) 2018-2020, 2023, 2025 Genome Research Ltd.
Authors: James Bonfield <[email protected]>, Valeriu Ohan <[email protected]>

Redistribution and use in source and binary forms, with or without
Expand Down Expand Up @@ -145,7 +145,7 @@ static int sam_hrecs_update_hashes(sam_hrecs_t *hrecs,
const char *name = NULL;
const char *altnames = NULL;
hts_pos_t len = -1;
int r;
int r, invLN = 0;
khint_t k;

while (tag) {
Expand All @@ -154,7 +154,11 @@ static int sam_hrecs_update_hashes(sam_hrecs_t *hrecs,
name = tag->str+3;
} else if (tag->str[0] == 'L' && tag->str[1] == 'N') {
assert(tag->len >= 3);
hts_pos_t tmp = len;
len = strtoll(tag->str+3, NULL, 10);
if (tmp != -1 && tmp != len) { //duplicate and different LN
invLN = 1;
}
} else if (tag->str[0] == 'A' && tag->str[1] == 'N') {
assert(tag->len >= 3);
altnames = tag->str+3;
Expand All @@ -173,6 +177,12 @@ static int sam_hrecs_update_hashes(sam_hrecs_t *hrecs,
return -1; // LN should be present, according to spec.
}

if (invLN) {
hts_log_error("Header includes @SQ line \"%s\" with multiple LN:"
" tag with different values.", name);
return -1; // LN should not be duplicated or be same
}

// Seen already?
k = kh_get(m_s2i, hrecs->ref_hash, name);
if (k < kh_end(hrecs->ref_hash)) {
Expand Down
14 changes: 11 additions & 3 deletions sam.c
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
/* sam.c -- SAM and BAM file I/O and manipulation.

Copyright (C) 2008-2010, 2012-2024 Genome Research Ltd.
Copyright (C) 2008-2010, 2012-2025 Genome Research Ltd.
Copyright (C) 2010, 2012, 2013 Broad Institute.

Author: Heng Li <[email protected]>
Expand Down Expand Up @@ -1964,8 +1964,16 @@ static sam_hdr_t *sam_hdr_create(htsFile* fp) {
strncpy(sn, q, r - q);
q = r;
} else {
if (strncmp(q, "LN:", 3) == 0)
ln = strtoll(q + 3, (char**)&q, 10);
if (strncmp(q, "LN:", 3) == 0) {
hts_pos_t tmp = strtoll(q + 3, (char**)&q, 10);
if (ln != -1 && ln != tmp) { //duplicate & different LN
hts_log_error("Header includes @SQ line \"%s\" with"
" multiple LN: tag with different values.", sn);
goto error;
} else {
ln = tmp;
}
}
}

while (*q != '\t' && *q != '\n' && *q != '\0')
Expand Down