#define PROG_NAME "dm_show_alignments"
#define PROG_DESC "writes the nucleotide sequence alignments for a list of candidates"
#define PROG_VERS "1.0"

/* Last edited on 2024-12-21 14:04:20 by stolfi */

#define dm_show_alignments_C_COPYRIGHT \
  "Copyright © 2013 by the State University of Campinas (UNICAMP)" \
  " and the Federal Fluminense University (UFF)"

/* !!! Fix the INFO and HELP !!! */

#define PROG_HELP \
  PROG_NAME " \\\n" \
  "    [ -maxCands {MAX} ] \\\n" \
  "    -seqA {SEQA_TAG} {SEQA_FILE} \\\n" \
  "    -seqB {SEQB_TAG} {SEQB_FILE} \\\n" \
  "    -cands {CDV_FILE} \\\n" \
  "    " argparser_help_info_HELP " \\\n"

#define PROG_INFO \
  "NAME\n" \
  "  " PROG_NAME " - " PROG_DESC "\n" \
  "\n" \
  "SYNOPSIS\n" \
  "  " PROG_HELP "\n" \
  "\n" \
  "DESCRIPTION\n" \
  "  This program reads two nucleotide sequences and a list" \
  " of candidate pairings between them, and prints the alignments" \
  " of the two sequences described by those candidates.\n" \
  "\n" \
  "  The input is assumed to be in {.cdv} format. ???\n" \
  "\n" \
  "  The output file with the alignments is written to standard output" \
  "\n" \
  "OPTIONS\n" \
  "  -cands {CDV_FILE} \n" \
  "    Specifies the file name of the candidate list.\n" \
  "\n" \
  "  -seqA {SEQA_TAG} {SEQA_FILE} \n" \
  "  -seqB {SEQB_TAG} {SEQB_FILE} \n" \
  "    Specifies the internal names (tags) of the two sequences paired by those" \
  " candidates, and the corresponding file names.\n" \
  "\n" \
   argparser_help_info_HELP_INFO "\n" \
  "SEE ALSO\n" \
  "  dm_cands_refine(1)\n" \
  "\n" \
  "AUTHOR AND HISTORY\n" \
  "  2012-10: Created by R. Saracchini, as part of {dm_analyse_cdv.c}.\n" \
  "  2013-05-05: Made into a separate program by J. Stolfi.\n" \
  "\n" \
  "WARRANTY\n" \
  argparser_help_info_NO_WARRANTY "\n" \
  "\n" \
  "RIGHTS\n" \
  "  " dm_show_alignments_C_COPYRIGHT ".\n" \
  "\n" \
  argparser_help_info_STANDARD_RIGHTS
  
#include <stdio.h>
#include <math.h>
#include <assert.h>
#include <string.h>
#include <stdlib.h>

#include <affirm.h>
#include <argparser.h>
#include <jsfile.h>
#include <jsmath.h>
#include <vec.h>

#include <msm_rung.h>
#include <msm_cand.h>
#include <msm_cand_vec.h>
#include <msm_pairing.h>

#include <dm_basic.h>
#include <dnae_seq.h>
#include <dm_cand.h>

typedef struct options_t 
  { char *cands;
    char *seqA_tag;
    char *seqA_file;
    char *seqB_tag;
    char *seqB_file;
  } options_t;

options_t *dmsa_get_options(int argc, char**argv);

int main(int argc,char** argv)
  {
    options_t* o = dmsa_get_options(argc,argv);

    /* Read the nucleic sequences: */
    dnae_seq_t seqA = dnae_seq_read_from_nucleic_file_named(o->seqA_file, "", "", 0, o->seqA_tag, FALSE);
    dnae_seq_t seqB = dnae_seq_read_from_nucleic_file_named(o->seqB_file, "", "", 1, o->seqB_tag, FALSE);

    /* Read candidate file: */
    FILE *rd = open_read(o->cands, TRUE);
    msm_cand_vec_t cdv = msm_cand_vec_read(rd);
    fclose(rd);

    int nc = cdv.ne;
    int i;

    for (i = 0; i < nc; i++)
    { msm_cand_t *cd = &(cdv.e[i]);
      demand(strcmp(cd->seq[0].name, seqA.sd.name) == 0, "wrong sequences for cand");
      demand(strcmp(cd->seq[1].name, seqB.sd.name) == 0, "wrong sequences for cand");
      dm_cand_write_with_alignment(stdout, cd, &seqA, &seqB);
    }

    fflush(stdout);
    msm_cand_vec_free(&cdv);

    return 0;
  }

options_t *dmsa_get_options(int argc, char**argv)  
  {
    options_t *o = (options_t *)notnull(malloc(sizeof(options_t)), "no mem");

    argparser_t *pp = argparser_new(stderr, argc, argv);
    argparser_set_help(pp, PROG_HELP);
    argparser_set_info(pp, PROG_INFO);
    argparser_process_help_info_options(pp);

    argparser_get_keyword(pp,"-cands");
    o->cands = argparser_get_next(pp);
    
    argparser_get_keyword(pp,"-seqA");
    o->seqA_tag = argparser_get_next(pp);
    o->seqA_file = argparser_get_next(pp);
    
    argparser_get_keyword(pp,"-seqB");
    o->seqB_tag = argparser_get_next(pp);
    o->seqB_file = argparser_get_next(pp);
    
    argparser_finish(pp);

    return o;
  }