Fix 10 assorted medium-severity bugs across multiple files

- vcffilter.c: Change max_qual from int to float to avoid truncation of
  fractional QUAL values
- vcfview.c: Guard args->ac[1] access with n_allele>=2 check for
  ALLELE_ALT1 filtering to prevent out-of-bounds on REF-only sites
- convert.c: Invert bcf_gt_is_phased() condition in process_gt_to_hap
  and process_gt_to_hap2 ('*' marks unphased, not phased)
- convert.c: Use gt_id instead of fmt->id for GT header existence check
  in process_pbinom
- convert.c: Fix off-by-one in allele bounds check (al >= n_allele,
  not al > n_allele) since allele index is 0-based
- dist.c: Fix double-counting in dist_insert_n; dist_insert already
  increments nvalues by 1, so add cnt-1 not cnt
- bin.c: Prevent bin_get_idx from returning -1 when value is below
  first bin boundary
- read_consensus.c: Fix loop condition from j<dfreq[i].len[j] to
  dfreq[i].len[j] (nonzero check) matching the pattern used elsewhere
- gff.c: Fix Mt_rRNA returning GF_MT_tRNA instead of GF_MT_rRNA
  (copy-paste error)
- gff.c: Fix strncmp length for "lncRNA" from 7 to 6

Author: sirus20x6

bin.c

@@ -101,6 +101,6 @@ int bin_get_idx(bin_t *bin, float value)
         else return i;
     }
     if ( bin->bins[imax] <= value ) return imax;
-    return imin - 1;
+    return imin > 0 ? imin - 1 : 0;
 }
 

convert.c

@@ -1014,10 +1014,10 @@ static void process_gt_to_hap(convert_t *convert, bcf1_t *line, fmt_t *fmt, int
         else
         {
             kputw(bcf_gt_allele(ptr[0]),str);
-            if ( bcf_gt_is_phased(ptr[1]) ) str->s[str->l++] = '*';
+            if ( !bcf_gt_is_phased(ptr[1]) ) str->s[str->l++] = '*';
             str->s[str->l++] = ' ';
             kputw(bcf_gt_allele(ptr[1]),str);
-            if ( bcf_gt_is_phased(ptr[1]) ) str->s[str->l++] = '*';
+            if ( !bcf_gt_is_phased(ptr[1]) ) str->s[str->l++] = '*';
             str->s[str->l++] = ' ';
         }
     }
@@ -1140,10 +1140,10 @@ static void process_gt_to_hap2(convert_t *convert, bcf1_t *line, fmt_t *fmt, int
         else
         {
             kputw(bcf_gt_allele(ptr[0]),str);
-            if ( bcf_gt_is_phased(ptr[1]) ) str->s[str->l++] = '*';
+            if ( !bcf_gt_is_phased(ptr[1]) ) str->s[str->l++] = '*';
             str->s[str->l++] = ' ';
             kputw(bcf_gt_allele(ptr[1]),str);
-            if ( bcf_gt_is_phased(ptr[1]) ) str->s[str->l++] = '*';
+            if ( !bcf_gt_is_phased(ptr[1]) ) str->s[str->l++] = '*';
             str->s[str->l++] = ' ';
         }
     }
@@ -1250,7 +1250,7 @@ static void process_pbinom(convert_t *convert, bcf1_t *line, fmt_t *fmt, int isa
 
         // Check that the first field is GT
         int gt_id = bcf_hdr_id2int(convert->header, BCF_DT_ID, "GT");
-        if ( !bcf_hdr_idinfo_exists(convert->header, BCF_HL_FMT, fmt->id)  ) error("Error: FORMAT/GT is not defined in the header\n");
+        if ( !bcf_hdr_idinfo_exists(convert->header, BCF_HL_FMT, gt_id)  ) error("Error: FORMAT/GT is not defined in the header\n");
         for (i=0; i<(int)line->n_fmt; i++)
             if ( line->d.fmt[i].id==gt_id ) { fmt->usr = &line->d.fmt[i]; break; }  // it should always be first according to VCF spec, but...
 
@@ -1268,7 +1268,7 @@ static void process_pbinom(convert_t *convert, bcf1_t *line, fmt_t *fmt, int isa
     {
         if ( bcf_gt_is_missing(gt[i]) || gt[i] == bcf_int8_vector_end ) goto invalid;
         int al = bcf_gt_allele(gt[i]);
-        if ( al > line->n_allele || al >= fmt->fmt->n ) goto invalid;
+        if ( al >= line->n_allele || al >= fmt->fmt->n ) goto invalid;
 
         #define BRANCH(type_t, convert, missing, vector_end) { \
             type_t val = convert(&fmt->fmt->p[(al + isample*fmt->fmt->n)*sizeof(type_t)]); \

dist.c

@@ -97,7 +97,7 @@ uint32_t dist_insert_n(dist_t *dist, uint32_t value, uint32_t cnt)
     if ( !cnt ) return 0;
     int ibin = dist_insert(dist, value);
     dist->bins[ibin] += cnt - 1;
-    dist->nvalues += cnt;
+    dist->nvalues += cnt - 1;
     return ibin;
 }
 

gff.c

@@ -312,12 +312,12 @@ static inline int gff_parse_biotype(char *line)
         case 'M':
             if ( !strncmp(line,"Mt_tRNA_pseudogene",18) ) return GF_MT_tRNA_PSEUDOGENE;
             else if ( !strncasecmp(line,"Mt_tRNA",7) ) return GF_MT_tRNA;
-            else if ( !strncasecmp(line,"Mt_rRNA",7) ) return GF_MT_tRNA;
+            else if ( !strncasecmp(line,"Mt_rRNA",7) ) return GF_MT_rRNA;
             else if ( !strncasecmp(line,"MRNA",4) ) return GF_PROTEIN_CODING;
             break;
         case 'l':
             if ( !strncmp(line,"lincRNA",7) ) return GF_lincRNA;
-            if ( !strncmp(line,"lncRNA",7) ) return GF_lncRNA;
+            if ( !strncmp(line,"lncRNA",6) ) return GF_lncRNA;
             break;
         case 'm':
             if ( !strncmp(line,"macro_lncRNA",12) ) return GF_macro_lncRNA;

read_consensus.c

@@ -489,7 +489,7 @@ static int select_candidate_variants(read_cns_t *rcns, const char *ref)
     // Find the longest deletion at the query position
     i = rcns->pos - rcns->beg;
     rcns->max_del = 0;
-    for (j=0; j<NI && j<dfreq[i].len[j]; j++)
+    for (j=0; j<NI && dfreq[i].len[j]; j++)
     {
         if ( rcns->max_del < dfreq[i].len[j] ) rcns->max_del = dfreq[i].len[j];
     }

vcffilter.c

@@ -310,7 +310,7 @@ static void buffered_filters(args_t *args, bcf1_t *line)
         if ( k_flush || !line )
         {
             // Select the best indel from the cluster of k_flush indels
-            int k = 0, max_ac = -1, imax_ac = -1, max_qual = -1, imax_qual = -1;
+            int k = 0, max_ac = -1, imax_ac = -1, imax_qual = -1; float max_qual = -1;
             for (i=-1; rbuf_next(&args->rbuf,&i) && k<k_flush; )
             {
                 k++;

vcfview.c

@@ -415,15 +415,15 @@ int subset_vcf(args_t *args, bcf1_t *line)
     {
         if (args->min_ac_type == ALLELE_NONREF && args->min_ac>non_ref_ac) return 0; // min AC
         else if (args->min_ac_type == ALLELE_MINOR && args->min_ac>minor_ac) return 0; // min minor AC
-        else if (args->min_ac_type == ALLELE_ALT1 && args->min_ac>args->ac[1]) return 0; // min 1st alternate AC
+        else if (args->min_ac_type == ALLELE_ALT1 && (line->n_allele<2 || args->min_ac>args->ac[1])) return 0; // min 1st alternate AC
         else if (args->min_ac_type == ALLELE_MAJOR && args->min_ac > major_ac) return 0; // min major AC
         else if (args->min_ac_type == ALLELE_NONMAJOR && args->min_ac > an-major_ac) return 0; // min non-major AC
     }
     if (args->max_ac!=-1)
     {
         if (args->max_ac_type == ALLELE_NONREF && args->max_ac<non_ref_ac) return 0; // max AC
         else if (args->max_ac_type == ALLELE_MINOR && args->max_ac<minor_ac) return 0; // max minor AC
-        else if (args->max_ac_type == ALLELE_ALT1 && args->max_ac<args->ac[1]) return 0; // max 1st alternate AC
+        else if (args->max_ac_type == ALLELE_ALT1 && line->n_allele>=2 && args->max_ac<args->ac[1]) return 0; // max 1st alternate AC
         else if (args->max_ac_type == ALLELE_MAJOR && args->max_ac < major_ac) return 0; // max major AC
         else if (args->max_ac_type == ALLELE_NONMAJOR && args->max_ac < an-major_ac) return 0; // max non-major AC
     }
@@ -432,7 +432,7 @@ int subset_vcf(args_t *args, bcf1_t *line)
         if (an == 0) return 0; // freq not defined, skip site
         if (args->min_af_type == ALLELE_NONREF && args->min_af>non_ref_ac/(double)an) return 0; // min AF
         else if (args->min_af_type == ALLELE_MINOR && args->min_af>minor_ac/(double)an) return 0; // min minor AF
-        else if (args->min_af_type == ALLELE_ALT1 && args->min_af>args->ac[1]/(double)an) return 0; // min 1st alternate AF
+        else if (args->min_af_type == ALLELE_ALT1 && (line->n_allele<2 || args->min_af>args->ac[1]/(double)an)) return 0; // min 1st alternate AF
         else if (args->min_af_type == ALLELE_MAJOR && args->min_af > major_ac/(double)an) return 0; // min major AF
         else if (args->min_af_type == ALLELE_NONMAJOR && args->min_af > (an-major_ac)/(double)an) return 0; // min non-major AF
     }
@@ -441,7 +441,7 @@ int subset_vcf(args_t *args, bcf1_t *line)
         if (an == 0) return 0; // freq not defined, skip site
         if (args->max_af_type == ALLELE_NONREF && args->max_af<non_ref_ac/(double)an) return 0; // max AF
         else if (args->max_af_type == ALLELE_MINOR && args->max_af<minor_ac/(double)an) return 0; // max minor AF
-        else if (args->max_af_type == ALLELE_ALT1 && args->max_af<args->ac[1]/(double)an) return 0; // max 1st alternate AF
+        else if (args->max_af_type == ALLELE_ALT1 && line->n_allele>=2 && args->max_af<args->ac[1]/(double)an) return 0; // max 1st alternate AF
         else if (args->max_af_type == ALLELE_MAJOR && args->max_af < major_ac/(double)an) return 0; // max major AF
         else if (args->max_af_type == ALLELE_NONMAJOR && args->max_af < (an-major_ac)/(double)an) return 0; // max non-major AF
     }