Drop offending space character in query -H output

The header printed by `bcftools query -H` and `bcftools +split-vep -H` contained a space after the leading hash # [1]columnName The space is unnecessary and complicates machine processing, so is dropped to produce output like #[1]columnName Resolves #1856
samtools · Feb 6, 2023 · 02a3961 · 02a3961
1 parent 9ae4fe8
commit 02a3961
Show file tree

Hide file tree

Showing 3 changed files with 9 additions and 4 deletions.
diff --git a/NEWS b/NEWS
@@ -19,12 +19,17 @@ Changes affecting the whole of bcftools, or multiple commands:
         FORMAT/AD[0:GT] > 10      .. same as above, but in the first sample
         sSUM(FORMAT/AD[GT]) > 20  .. require total sample depth bigger than 20
 
+* The commands `consensus -H` and `+split-vep -H`
+
+    - Drop unnecessary leading space in the first header column and newly print `#[1]columnName`
+      instead of the previous `# [1]columnName` (#1856)
+
 
 Changes affecting specific commands:
 
 * bcftools +allele-length
 
-    - fix overflow for indels longer than 512bp and aggregate alleles equal or larger than
+    - Fix overflow for indels longer than 512bp and aggregate alleles equal or larger than
       that in the same bin (#1837)
 
 * bcftools annotate

diff --git a/convert.c b/convert.c
@@ -1,6 +1,6 @@
 /*  convert.c -- functions for converting between VCF/BCF and related formats.
 
-    Copyright (C) 2013-2022 Genome Research Ltd.
+    Copyright (C) 2013-2023 Genome Research Ltd.
 
     Author: Petr Danecek <pd3@sanger.ac.uk>
 
@@ -1568,7 +1568,7 @@ int convert_header(convert_t *convert, kstring_t *str)
     if ( i!=convert->nfmt )
         return str->l - l_ori;
 
-    kputs("# ", str);
+    kputc('#', str);
     for (i=0; i<convert->nfmt; i++)
     {
         // Genotype fields

diff --git a/test/split-vep.12.2.out b/test/split-vep.12.2.out
@@ -1,4 +1,4 @@
-# [1]POS	[2]Allele	[3]Consequence	[4]IMPACT	[5]SYMBOL	[6]Gene	[7]Feature_type	[8]Feature	[9]BIOTYPE	[10]EXON	[11]INTRON	[12]HGVSc	[13]HGVSp	[14]cDNA_position	[15]CDS_position	[16]Protein_position	[17]Amino_acids	[18]Codons	[19]Existing_variation	[20]ALLELE_NUM	[21]DISTANCE	[22]STRAND	[23]FLAGS	[24]VARIANT_CLASS	[25]SYMBOL_SOURCE	[26]HGNC_ID	[27]CANONICAL	[28]TSL	[29]APPRIS	[30]CCDS	[31]ENSP	[32]SWISSPROT	[33]TREMBL	[34]UNIPARC	[35]SOURCE	[36]GENE_PHENO	[37]SIFT	[38]PolyPhen	[39]DOMAINS	[40]miRNA	[41]HGVS_OFFSET	[42]AF	[43]AFR_AF	[44]AMR_AF	[45]EAS_AF	[46]EUR_AF	[47]SAS_AF	[48]AA_AF	[49]EA_AF	[50]gnomAD_AF	[51]gnomAD_AFR_AF	[52]gnomAD_AMR_AF	[53]gnomAD_ASJ_AF	[54]gnomAD_EAS_AF	[55]gnomAD_FIN_AF	[56]gnomAD_NFE_AF	[57]gnomAD_OTH_AF	[58]gnomAD_SAS_AF	[59]MAX_AF	[60]MAX_AF_POPS	[61]CLIN_SIG	[62]SOMATIC	[63]PHENO	[64]PUBMED	[65]MOTIF_NAME	[66]MOTIF_POS	[67]HIGH_INF_POS	[68]MOTIF_SCORE_CHANGE	[69]LoF	[70]LoF_filter	[71]LoF_flags	[72]LoF_info	[73]CADD_PHRED	[74]CADD_RAW	[75]gnomAD2.1	[76]gnomAD2.1_AF_raw	[77]gnomAD2.1_AF_popmax	[78]gnomAD2.1_AF_afr	[79]gnomAD2.1_AF_amr	[80]gnomAD2.1_AF_asj	[81]gnomAD2.1_AF_eas	[82]gnomAD2.1_AF_fin	[83]gnomAD2.1_AF_nfe	[84]gnomAD2.1_AF_oth	[85]gnomAD2.1_AF_sas
+#[1]POS	[2]Allele	[3]Consequence	[4]IMPACT	[5]SYMBOL	[6]Gene	[7]Feature_type	[8]Feature	[9]BIOTYPE	[10]EXON	[11]INTRON	[12]HGVSc	[13]HGVSp	[14]cDNA_position	[15]CDS_position	[16]Protein_position	[17]Amino_acids	[18]Codons	[19]Existing_variation	[20]ALLELE_NUM	[21]DISTANCE	[22]STRAND	[23]FLAGS	[24]VARIANT_CLASS	[25]SYMBOL_SOURCE	[26]HGNC_ID	[27]CANONICAL	[28]TSL	[29]APPRIS	[30]CCDS	[31]ENSP	[32]SWISSPROT	[33]TREMBL	[34]UNIPARC	[35]SOURCE	[36]GENE_PHENO	[37]SIFT	[38]PolyPhen	[39]DOMAINS	[40]miRNA	[41]HGVS_OFFSET	[42]AF	[43]AFR_AF	[44]AMR_AF	[45]EAS_AF	[46]EUR_AF	[47]SAS_AF	[48]AA_AF	[49]EA_AF	[50]gnomAD_AF	[51]gnomAD_AFR_AF	[52]gnomAD_AMR_AF	[53]gnomAD_ASJ_AF	[54]gnomAD_EAS_AF	[55]gnomAD_FIN_AF	[56]gnomAD_NFE_AF	[57]gnomAD_OTH_AF	[58]gnomAD_SAS_AF	[59]MAX_AF	[60]MAX_AF_POPS	[61]CLIN_SIG	[62]SOMATIC	[63]PHENO	[64]PUBMED	[65]MOTIF_NAME	[66]MOTIF_POS	[67]HIGH_INF_POS	[68]MOTIF_SCORE_CHANGE	[69]LoF	[70]LoF_filter	[71]LoF_flags	[72]LoF_info	[73]CADD_PHRED	[74]CADD_RAW	[75]gnomAD2.1	[76]gnomAD2.1_AF_raw	[77]gnomAD2.1_AF_popmax	[78]gnomAD2.1_AF_afr	[79]gnomAD2.1_AF_amr	[80]gnomAD2.1_AF_asj	[81]gnomAD2.1_AF_eas	[82]gnomAD2.1_AF_fin	[83]gnomAD2.1_AF_nfe	[84]gnomAD2.1_AF_oth	[85]gnomAD2.1_AF_sas
 14464	T	non_coding_transcript_exon_variant	MODIFIER	WASH7P	ENSG00000227232	Transcript	ENST00000423562	unprocessed_pseudogene	10/10	.	ENST00000423562.1:n.1568T>A	.	1568	.	.	.	.	rs546169444	1	.	-1	.	SNV	HGNC	38034	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	0.0958	0.0144	0.1138	0.005	0.1859	0.1943	.	.	.	.	.	.	.	.	.	.	.	0.1943	SAS	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.
 14464	T	non_coding_transcript_exon_variant	MODIFIER	WASH7P	ENSG00000227232	Transcript	ENST00000438504	unprocessed_pseudogene	12/12	.	ENST00000438504.2:n.1682T>A	.	1682	.	.	.	.	rs546169444	1	.	-1	.	SNV	HGNC	38034	YES	.	.	.	.	.	.	.	.	.	.	.	.	.	.	0.0958	0.0144	0.1138	0.005	0.1859	0.1943	.	.	.	.	.	.	.	.	.	.	.	0.1943	SAS	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.
 14464	T	downstream_gene_variant	MODIFIER	DDX11L1	ENSG00000223972	Transcript	ENST00000456328	processed_transcript	.	.	.	.	.	.	.	.	.	rs546169444	1	55	1	.	SNV	HGNC	37102	YES	.	.	.	.	.	.	.	.	.	.	.	.	.	.	0.0958	0.0144	0.1138	0.005	0.1859	0.1943	.	.	.	.	.	.	.	.	.	.	.	0.1943	SAS	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.	.