static void xml_showgthreferenceinformation(GthSA *sa,
GthInput *input,
unsigned int indentlevel,
GtFile *outfp)
{
gt_assert(gth_sa_ref_file_num(sa) != GT_UNDEF_ULONG);
gth_indent(outfp, indentlevel);
switch (gth_sa_alphatype(sa)) {
case DNA_ALPHA:
gt_file_xprintf(outfp, "<reference ref_file=\"%s\" ref_id=\"%s\" "
"ref_strand=\"%c\" ref_description=\"",
gth_input_get_reference_filename(input,
gth_sa_ref_file_num(sa)),
gth_sa_ref_id(sa),
gth_sa_ref_strand_char(sa));
break;
case PROTEIN_ALPHA:
gt_file_xprintf(outfp, "<reference ref_file=\"%s\" ref_id=\"%s\" "
"ref_description=\"",
gth_input_get_reference_filename(input,
gth_sa_ref_file_num(sa)),
gth_sa_ref_id(sa));
break;
default: gt_assert(0);
}
gth_input_echo_reference_description(input, gth_sa_ref_file_num(sa),
gth_sa_ref_seq_num(sa), outfp);
gt_file_xprintf(outfp, "\">\n");
}
static void showgthreferenceinformation(GthSA *sa, GthInput *input,
bool showseqnums,
GtFile *outfp)
{
gt_assert(gth_sa_ref_file_num(sa) != GT_UNDEF_UWORD);
switch (gth_sa_alphatype(sa)) {
case DNA_ALPHA:
gt_file_xprintf(outfp,
"EST Sequence: file=%s, strand=%c, description=",
gth_input_get_reference_filename(input,
gth_sa_ref_file_num(sa)),
gth_sa_ref_strand_char(sa));
break;
case PROTEIN_ALPHA:
gt_file_xprintf(outfp, "Protein Sequence: file=%s, description=",
gth_input_get_reference_filename(input,
gth_sa_ref_file_num(sa)));
break;
default: gt_assert(0);
}
gth_sa_echo_reference_description(sa, input, outfp);
if (showseqnums)
gt_file_xprintf(outfp, ", seqnum="GT_WU"", gth_sa_ref_seq_num(sa));
gt_file_xfputc('\n', outfp);
gt_file_xfputc('\n', outfp);
}
static void showreferencefilename(GthSA *sa,
GthInput *input,
unsigned int indentlevel, GtFile *outfp)
{
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<referencefile>\n");
indentlevel++;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<referencefilename>%s</referencefilename>\n",
gth_input_get_reference_filename(input,
gth_sa_ref_file_num(sa)));
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "<referencefilehash>%s</referencefilehash>\n",
GTH_UNDEFINED_HASH);
indentlevel--;
gth_indent(outfp, indentlevel);
gt_file_xprintf(outfp, "</referencefile>\n");
}
GtUword gth_sa_get_alignment_lines(const GthSA *sa,
unsigned char **first_line,
unsigned char **second_line,
unsigned char **third_line,
GtUword translationtable,
GthInput *input)
{
GtUword genomicstartcutoff, genomicendcutoff, genomictotalcutoff,
referencestartcutoff, referenceendcutoff, referencetotalcutoff;
GT_UNUSED bool reverse_subject_pos = false;
gt_assert(sa && first_line && second_line && third_line && input);
/* only for cosmetic reasons */
genomicstartcutoff = gth_sa_genomiccutoff_start(sa);
genomicendcutoff = gth_sa_genomiccutoff_end(sa);
genomictotalcutoff = genomicstartcutoff + genomicendcutoff;
referencestartcutoff = gth_sa_referencecutoff_start(sa);
referenceendcutoff = gth_sa_referencecutoff_end(sa);
referencetotalcutoff = referencestartcutoff + referenceendcutoff;
/* sequences */
unsigned char *gen_seq_orig, *ref_seq_orig;
GtUword cols = 0;
GthSeqCon *ref_seq_con;
/* make sure that the correct files are loaded */
gth_input_load_reference_file(input, gth_sa_ref_file_num(sa), false);
ref_seq_con = gth_input_current_ref_seq_con(input);
/* If the reverse complement of the genomic DNA is considered, this
opition is needed for correct output of the genomic sequence positions
by the function showalignmentgeneric() */
if (!gth_sa_gen_strand_forward(sa))
reverse_subject_pos = true;
/* get genomic sequence */
gen_seq_orig = (unsigned char*)
gth_input_original_genomic_sequence(input, gth_sa_gen_file_num(sa),
gth_sa_gen_strand_forward(sa))
+ gth_sa_gen_dp_start(sa);
/* get reference sequence */
if (gth_sa_ref_strand_forward(sa)) {
ref_seq_orig =
gth_seq_con_get_orig_seq(ref_seq_con, gth_sa_ref_seq_num(sa));
}
else {
ref_seq_orig =
gth_seq_con_get_orig_seq_rc(ref_seq_con, gth_sa_ref_seq_num(sa));
}
switch (gth_sa_alphatype(sa)) {
case DNA_ALPHA:
/* compute the two alignment lines */
cols = gthfillthetwoalignmentlines(first_line,
second_line,
gen_seq_orig +
genomicstartcutoff,
gth_sa_gen_dp_length(sa) -
genomictotalcutoff,
ref_seq_orig +
referencestartcutoff,
gth_sa_ref_total_length(sa) -
referencetotalcutoff,
gth_sa_get_editoperations(sa),
gth_sa_get_editoperations_length(sa),
0, /* linewidth not important here */
0, /* no short introns here */
NULL,/* therefore no shortintroninfo */
gth_sa_indelcount(sa));
*third_line = NULL;
break;
case PROTEIN_ALPHA:
/* compute the three alignment lines */
cols = gthfillthethreealignmentlines(first_line,
second_line,
third_line,
gth_sa_get_editoperations(sa),
gth_sa_get_editoperations_length(sa),
gth_sa_indelcount(sa),
gen_seq_orig +
genomicstartcutoff,
gth_sa_gen_dp_length(sa) -
genomictotalcutoff,
ref_seq_orig +
referencestartcutoff,
gth_sa_ref_total_length(sa) -
referencetotalcutoff,
translationtable);
break;
default: gt_assert(0);
}
return cols;
}
void gth_sa_echo_alignment(const GthSA *sa, GtUword showintronmaxlen,
GtUword translationtable,
bool wildcardimplosion, GthInput *input,
GtFile *outfp)
{
GtUword genomicstartcutoff, genomicendcutoff, genomictotalcutoff,
referencestartcutoff, referenceendcutoff, referencetotalcutoff;
bool reverse_subject_pos = false;
const unsigned char *gen_seq_orig, *ref_seq_orig;
GthSeqCon *ref_seq_con;
GtAlphabet *ref_alphabet;
gt_assert(sa && input);
/* only for cosmetic reasons */
genomicstartcutoff = gth_sa_genomiccutoff_start(sa);
genomicendcutoff = gth_sa_genomiccutoff_end(sa);
genomictotalcutoff = genomicstartcutoff + genomicendcutoff;
referencestartcutoff = gth_sa_referencecutoff_start(sa);
referenceendcutoff = gth_sa_referencecutoff_end(sa);
referencetotalcutoff = referencestartcutoff + referenceendcutoff;
/* make sure that the correct files are loaded */
gth_input_load_reference_file(input, gth_sa_ref_file_num(sa), false);
ref_seq_con = gth_input_current_ref_seq_con(input);
ref_alphabet = gth_input_current_ref_alphabet(input);
/* If the reverse complement of the genomic DNA is considered, this
opition is needed for correct output of the genomic sequence positions
by the function showalignmentgeneric() */
if (!gth_sa_gen_strand_forward(sa))
reverse_subject_pos = true;
/* get genomic sequence */
gen_seq_orig =
gth_input_original_genomic_sequence(input, sa->gen_file_num,
sa->gen_strand_forward)
+ gth_sa_gen_dp_start(sa);
/* get reference sequence */
if (gth_sa_ref_strand_forward(sa)) {
ref_seq_orig =
gth_seq_con_get_orig_seq(ref_seq_con, gth_sa_ref_seq_num(sa));
}
else {
ref_seq_orig =
gth_seq_con_get_orig_seq_rc(ref_seq_con, gth_sa_ref_seq_num(sa));
}
switch (gth_sa_alphatype(sa)) {
case DNA_ALPHA:
gthshowalignmentdna(outfp,ALIGNMENTLINEWIDTH,
gth_sa_get_editoperations(sa),
gth_sa_get_editoperations_length(sa),
gth_sa_indelcount(sa),
gen_seq_orig + genomicstartcutoff,
gth_sa_gen_dp_length(sa) - genomictotalcutoff,
ref_seq_orig + referencestartcutoff,
gth_sa_ref_total_length(sa) -
referencetotalcutoff,
gth_sa_gen_dp_start(sa) + genomicstartcutoff -
gth_sa_gen_offset(sa), referencestartcutoff,
gth_sa_gen_total_length(sa), showintronmaxlen,
ref_alphabet, reverse_subject_pos,
wildcardimplosion);
break;
case PROTEIN_ALPHA:
gthshowalignmentprotein(outfp, ALIGNMENTLINEWIDTH,
gth_sa_get_editoperations(sa),
gth_sa_get_editoperations_length(sa),
gth_sa_indelcount(sa),
gen_seq_orig + genomicstartcutoff,
gth_sa_gen_dp_length(sa) - genomictotalcutoff,
ref_seq_orig + referencestartcutoff,
gth_sa_ref_total_length(sa) -
referencetotalcutoff,
gth_sa_gen_dp_start(sa) + genomicstartcutoff -
gth_sa_gen_offset(sa), referencestartcutoff,
gth_sa_gen_total_length(sa), showintronmaxlen,
ref_alphabet, translationtable,
gth_input_score_matrix(input),
gth_input_score_matrix_alpha(input),
reverse_subject_pos, wildcardimplosion);
break;
default: gt_assert(0);
}
}
