MSF identification

[Don Gilbert]

take a look at readseq if you like -- ftp.bio.indiana.edu:/molbio/readseq
for the source.  

Here is a snippet of it's format identification routine:

  while ( !done ) {
    ReadOneLine(sp);

    /* check for mailer head & skip past if found */
    if (nlines < 4 && !done) {
      if ((strstr(sp,"From ") == sp) || (strstr(sp,"Received:") == sp)) {
        do {
          /* skip all lines until find one blank line */
          ReadOneLine(sp);
          if (!done) for (k=0; (k<splen) && (sp[k]==' '); k++) ;
          } while ((!done) && (k < splen));
        *skiplines = nlines; /* !? do we want #lines or #bytes ?? */
        }
      }

    if (sp==NULL || *sp==0)
      ; /* nada */

    /* high probability identities: */

    else if ( strstr(sp,"MSF:") && strstr(sp,"Type:") && strstr(sp,"Check:") )
      gotMSF= true;

    else if ((strstr(sp,"..") != NULL) && (strstr(sp,"Check:") != NULL))
      gotuw= true;

    else if (strstr(sp,"identity:   Data:") != NULL)
      gotolsen= true;

// and so on for more format checks...

-- 
-- d.gilbert--biocomputing--indiana u--bloomington--gilbertd at bio.indiana.edu