Commits

mchikina committed b0f7f20

Actually added PCL2Bin files

Comments (0)

Files changed (7)

 *.in
 history
 config.status
+*~

tools/PCL2Bin/Makefile.am

+bin_PROGRAMS = PCL2Bin
+AM_CPPFLAGS = $(SLEIPNIR_CFLAGS) $(LOG4CPP_CFLAGS) $(PTHREAD_CFLAGS)
+LDADD = $(SLEIPNIR_LIBS) $(LOG4CPP_LIBS) $(PTHREAD_LIBS)
+
+if WITH_GENGETOPT
+gengetopt = $(prog_gengetopt)
+BUILT_SOURCES = cmdline.c cmdline.h
+cmdline.c cmdline.h: PCL2Bin.ggo
+	$(gengetopt) -iPCL2Bin.ggo --default-optional -u -N -e
+endif
+PCL2Bin_SOURCES = PCL2Bin.cpp cmdline.c \
+	stdafx.h cmdline.h

tools/PCL2Bin/PCL2Bin.cpp

+/*****************************************************************************
+ * This file is provided under the Creative Commons Attribution 3.0 license.
+ *
+ * You are free to share, copy, distribute, transmit, or adapt this work
+ * PROVIDED THAT you attribute the work to the authors listed below.
+ * For more information, please see the following web page:
+ * http://creativecommons.org/licenses/by/3.0/
+ *
+ * This file is a component of the Sleipnir library for functional genomics,
+ * authored by:
+ * Curtis Huttenhower (chuttenh@princeton.edu)
+ * Mark Schroeder
+ * Maria D. Chikina
+ * Olga G. Troyanskaya (ogt@princeton.edu, primary contact)
+ *
+ * If you use this library, the included executable tools, or any related
+ * code in your work, please cite the following publication:
+ * Curtis Huttenhower, Mark Schroeder, Maria D. Chikina, and
+ * Olga G. Troyanskaya.
+ * "The Sleipnir library for computational functional genomics"
+ *****************************************************************************/
+#include "stdafx.h"
+#include "cmdline.h"
+#include "statistics.h"
+static const char c_szRBF[] = "rbf";
+static const char c_szPolynomial[] = "poly";
+static const char c_acDab[] = ".dab";
+static const char c_acPcl[] = ".pcl";
+
+int main(int iArgs, char** aszArgs) {
+	gengetopt_args_info sArgs;
+	CGenome Genome;
+	CGenes Genes(Genome);
+	ifstream ifsm;
+	CPCL PCL;
+	size_t i, j;
+	bool fModified;
+	char* file_ext = NULL;
+
+	if (cmdline_parser(iArgs, aszArgs, &sArgs)) {
+		cmdline_parser_print_help();
+		return 1;
+	}
+	CMeta Meta(sArgs.verbosity_arg);
+
+	if (sArgs.input_arg) {
+		if (!PCL.Open(sArgs.input_arg, sArgs.skip_arg, !!sArgs.mmap_flag)) {
+			cerr << "Could not open: " << sArgs.input_arg << endl;
+			return 1;
+		}
+	}
+	// if coming from stdin, always assume it's non binary form
+
+	else if (!PCL.Open(cin, sArgs.skip_arg)) {
+		cerr << "Could not open input" << endl;
+		return 1;
+	}
+	if (sArgs.Genes_flag) {
+		for (size_t i = 0; i < PCL.GetGenes(); i++) {
+			cout << i << '\t' << PCL.GetGene(i) << endl;
+		}
+	} else {
+		//vector<size_t> vec_iGenes;
+		ifstream ifsm;
+
+		if (sArgs.genex_given) {
+			ifsm.open(sArgs.genex_arg);
+			if (!Genes.Open(ifsm)) {
+				cerr << "Could not open: " << sArgs.genex_arg << endl;
+				return 1;
+			}
+
+			for (i = 0; i < PCL.GetGenes(); i++)
+				if (Genes.GetGene(PCL.GetGene(i)) != -1)
+					PCL.MaskGene(i, true);
+		}
+
+		else if (sArgs.genes_given) {
+			ifsm.open(sArgs.genes_arg);
+			if (!Genes.Open(ifsm)) {
+				cerr << "Could not open: " << sArgs.genes_arg << endl;
+				return 1;
+			}
+			for (i = 0; i < PCL.GetGenes(); i++)
+				if (Genes.GetGene(PCL.GetGene(i)) == -1)
+					PCL.MaskGene(i, true);
+
+		}
+		ifsm.close();
+
+		/*	if( Genes.GetGenes( ) )
+		 PCL.FilterGenes( Genes, CPCL::EFilterInclude );
+		 if( sArgs.genex_arg )
+		 PCL.FilterGenes( sArgs.genex_arg, CPCL::EFilterExclude );
+		 */
+		//Normalize Zscore
+		if (sArgs.normalize_flag)
+			PCL.Normalize(CPCL::ENormalizeMinMax);
+		if (sArgs.zrow_flag)
+					PCL.Normalize(CPCL::ENormalizeRow);
+		if (sArgs.zcol_flag)
+					PCL.Normalize(CPCL::ENormalizeColumn);
+		if (sArgs.scol_flag)
+					PCL.Normalize(CPCL::EMeanSubtractColumn);
+		else if (sArgs.normalize_flag)
+			PCL.Normalize(CPCL::ENormalizeMinMax);
+		if (sArgs.output_arg) {
+
+				PCL.Save(sArgs.output_arg);
+		} else {
+
+				PCL.Save(cout, NULL);
+			cout.flush();
+		}
+
+		return 0;
+
+	}
+}

tools/PCL2Bin/PCL2Bin.ggo

+package	"PCL2Bin"
+version	"1.0"
+purpose	"Text/binary data file interconversion"
+
+section "Main"
+option	"input"			i	"Input PCL/BIN file"
+							string	typestr="filename"
+option	"output"		o	"Output PCL/BIN file"
+							string	typestr="filename"	no
+
+section "Filtering"
+option	"genes"			g	"Process only genes from the given set"
+							string	typestr="filename" no
+option	"genex"			G	"Exclude all genes from the given set"
+							string	typestr="filename" no
+section "Optional"
+option "Genes"			E   "Only print genes and their indecies"
+							flag off
+option	"zrow"		r	"Normalize Z score row"
+						flag	off
+option	"zcol"		c	"Normalize Z score column"
+						flag	off
+option	"scol"		C	"Subtract mean per column"
+						flag	off						
+option	"normalize"		n	"Normalize 0 1 range"
+						flag	off
+						
+option	"skip"			s	"Columns to skip in input PCL"
+							int	default="0" no
+option	"verbosity"		v	"Message verbosity"
+							int	default="5" no
+option	"mmap"		m	"Memmap binary input"
+						flag	off 

tools/PCL2Bin/cmdline.c

+/*
+  File autogenerated by gengetopt version 2.22.4
+  generated with the following command:
+  /usr/bin/gengetopt -iPCL2Bin.ggo --default-optional -u -N -e 
+
+  The developers of gengetopt consider the fixed text that goes in all
+  gengetopt output files to be in the public domain:
+  we make no copyright claims on it.
+*/
+
+/* If we use autoconf.  */
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#ifndef FIX_UNUSED
+#define FIX_UNUSED(X) (void) (X) /* avoid warnings for unused params */
+#endif
+
+#include <getopt.h>
+
+#include "cmdline.h"
+
+const char *gengetopt_args_info_purpose = "Text/binary data file interconversion";
+
+const char *gengetopt_args_info_usage = "Usage: PCL2Bin [OPTIONS]... [FILES]...";
+
+const char *gengetopt_args_info_description = "";
+
+const char *gengetopt_args_info_help[] = {
+  "  -h, --help             Print help and exit",
+  "  -V, --version          Print version and exit",
+  "\nMain:",
+  "  -i, --input=filename   Input PCL/BIN file",
+  "  -o, --output=filename  Output PCL/BIN file",
+  "\nFiltering:",
+  "  -g, --genes=filename   Process only genes from the given set",
+  "  -G, --genex=filename   Exclude all genes from the given set",
+  "\nOptional:",
+  "  -E, --Genes            Only print genes and their indecies  (default=off)",
+  "  -r, --zrow             Normalize Z score row  (default=off)",
+  "  -c, --zcol             Normalize Z score column  (default=off)",
+  "  -C, --scol             Subtract mean per column  (default=off)",
+  "  -n, --normalize        Normalize 0 1 range  (default=off)",
+  "  -s, --skip=INT         Columns to skip in input PCL  (default=`0')",
+  "  -v, --verbosity=INT    Message verbosity  (default=`5')",
+  "  -m, --mmap             Memmap binary input  (default=off)",
+    0
+};
+
+typedef enum {ARG_NO
+  , ARG_FLAG
+  , ARG_STRING
+  , ARG_INT
+} cmdline_parser_arg_type;
+
+static
+void clear_given (struct gengetopt_args_info *args_info);
+static
+void clear_args (struct gengetopt_args_info *args_info);
+
+static int
+cmdline_parser_internal (int argc, char **argv, struct gengetopt_args_info *args_info,
+                        struct cmdline_parser_params *params, const char *additional_error);
+
+
+static char *
+gengetopt_strdup (const char *s);
+
+static
+void clear_given (struct gengetopt_args_info *args_info)
+{
+  args_info->help_given = 0 ;
+  args_info->version_given = 0 ;
+  args_info->input_given = 0 ;
+  args_info->output_given = 0 ;
+  args_info->genes_given = 0 ;
+  args_info->genex_given = 0 ;
+  args_info->Genes_given = 0 ;
+  args_info->zrow_given = 0 ;
+  args_info->zcol_given = 0 ;
+  args_info->scol_given = 0 ;
+  args_info->normalize_given = 0 ;
+  args_info->skip_given = 0 ;
+  args_info->verbosity_given = 0 ;
+  args_info->mmap_given = 0 ;
+}
+
+static
+void clear_args (struct gengetopt_args_info *args_info)
+{
+  FIX_UNUSED (args_info);
+  args_info->input_arg = NULL;
+  args_info->input_orig = NULL;
+  args_info->output_arg = NULL;
+  args_info->output_orig = NULL;
+  args_info->genes_arg = NULL;
+  args_info->genes_orig = NULL;
+  args_info->genex_arg = NULL;
+  args_info->genex_orig = NULL;
+  args_info->Genes_flag = 0;
+  args_info->zrow_flag = 0;
+  args_info->zcol_flag = 0;
+  args_info->scol_flag = 0;
+  args_info->normalize_flag = 0;
+  args_info->skip_arg = 0;
+  args_info->skip_orig = NULL;
+  args_info->verbosity_arg = 5;
+  args_info->verbosity_orig = NULL;
+  args_info->mmap_flag = 0;
+  
+}
+
+static
+void init_args_info(struct gengetopt_args_info *args_info)
+{
+
+
+  args_info->help_help = gengetopt_args_info_help[0] ;
+  args_info->version_help = gengetopt_args_info_help[1] ;
+  args_info->input_help = gengetopt_args_info_help[3] ;
+  args_info->output_help = gengetopt_args_info_help[4] ;
+  args_info->genes_help = gengetopt_args_info_help[6] ;
+  args_info->genex_help = gengetopt_args_info_help[7] ;
+  args_info->Genes_help = gengetopt_args_info_help[9] ;
+  args_info->zrow_help = gengetopt_args_info_help[10] ;
+  args_info->zcol_help = gengetopt_args_info_help[11] ;
+  args_info->scol_help = gengetopt_args_info_help[12] ;
+  args_info->normalize_help = gengetopt_args_info_help[13] ;
+  args_info->skip_help = gengetopt_args_info_help[14] ;
+  args_info->verbosity_help = gengetopt_args_info_help[15] ;
+  args_info->mmap_help = gengetopt_args_info_help[16] ;
+  
+}
+
+void
+cmdline_parser_print_version (void)
+{
+  printf ("%s %s\n",
+     (strlen(CMDLINE_PARSER_PACKAGE_NAME) ? CMDLINE_PARSER_PACKAGE_NAME : CMDLINE_PARSER_PACKAGE),
+     CMDLINE_PARSER_VERSION);
+}
+
+static void print_help_common(void) {
+  cmdline_parser_print_version ();
+
+  if (strlen(gengetopt_args_info_purpose) > 0)
+    printf("\n%s\n", gengetopt_args_info_purpose);
+
+  if (strlen(gengetopt_args_info_usage) > 0)
+    printf("\n%s\n", gengetopt_args_info_usage);
+
+  printf("\n");
+
+  if (strlen(gengetopt_args_info_description) > 0)
+    printf("%s\n\n", gengetopt_args_info_description);
+}
+
+void
+cmdline_parser_print_help (void)
+{
+  int i = 0;
+  print_help_common();
+  while (gengetopt_args_info_help[i])
+    printf("%s\n", gengetopt_args_info_help[i++]);
+}
+
+void
+cmdline_parser_init (struct gengetopt_args_info *args_info)
+{
+  clear_given (args_info);
+  clear_args (args_info);
+  init_args_info (args_info);
+
+  args_info->inputs = 0;
+  args_info->inputs_num = 0;
+}
+
+void
+cmdline_parser_params_init(struct cmdline_parser_params *params)
+{
+  if (params)
+    { 
+      params->override = 0;
+      params->initialize = 1;
+      params->check_required = 1;
+      params->check_ambiguity = 0;
+      params->print_errors = 1;
+    }
+}
+
+struct cmdline_parser_params *
+cmdline_parser_params_create(void)
+{
+  struct cmdline_parser_params *params = 
+    (struct cmdline_parser_params *)malloc(sizeof(struct cmdline_parser_params));
+  cmdline_parser_params_init(params);  
+  return params;
+}
+
+static void
+free_string_field (char **s)
+{
+  if (*s)
+    {
+      free (*s);
+      *s = 0;
+    }
+}
+
+
+static void
+cmdline_parser_release (struct gengetopt_args_info *args_info)
+{
+  unsigned int i;
+  free_string_field (&(args_info->input_arg));
+  free_string_field (&(args_info->input_orig));
+  free_string_field (&(args_info->output_arg));
+  free_string_field (&(args_info->output_orig));
+  free_string_field (&(args_info->genes_arg));
+  free_string_field (&(args_info->genes_orig));
+  free_string_field (&(args_info->genex_arg));
+  free_string_field (&(args_info->genex_orig));
+  free_string_field (&(args_info->skip_orig));
+  free_string_field (&(args_info->verbosity_orig));
+  
+  
+  for (i = 0; i < args_info->inputs_num; ++i)
+    free (args_info->inputs [i]);
+
+  if (args_info->inputs_num)
+    free (args_info->inputs);
+
+  clear_given (args_info);
+}
+
+
+static void
+write_into_file(FILE *outfile, const char *opt, const char *arg, const char *values[])
+{
+  FIX_UNUSED (values);
+  if (arg) {
+    fprintf(outfile, "%s=\"%s\"\n", opt, arg);
+  } else {
+    fprintf(outfile, "%s\n", opt);
+  }
+}
+
+
+int
+cmdline_parser_dump(FILE *outfile, struct gengetopt_args_info *args_info)
+{
+  int i = 0;
+
+  if (!outfile)
+    {
+      fprintf (stderr, "%s: cannot dump options to stream\n", CMDLINE_PARSER_PACKAGE);
+      return EXIT_FAILURE;
+    }
+
+  if (args_info->help_given)
+    write_into_file(outfile, "help", 0, 0 );
+  if (args_info->version_given)
+    write_into_file(outfile, "version", 0, 0 );
+  if (args_info->input_given)
+    write_into_file(outfile, "input", args_info->input_orig, 0);
+  if (args_info->output_given)
+    write_into_file(outfile, "output", args_info->output_orig, 0);
+  if (args_info->genes_given)
+    write_into_file(outfile, "genes", args_info->genes_orig, 0);
+  if (args_info->genex_given)
+    write_into_file(outfile, "genex", args_info->genex_orig, 0);
+  if (args_info->Genes_given)
+    write_into_file(outfile, "Genes", 0, 0 );
+  if (args_info->zrow_given)
+    write_into_file(outfile, "zrow", 0, 0 );
+  if (args_info->zcol_given)
+    write_into_file(outfile, "zcol", 0, 0 );
+  if (args_info->scol_given)
+    write_into_file(outfile, "scol", 0, 0 );
+  if (args_info->normalize_given)
+    write_into_file(outfile, "normalize", 0, 0 );
+  if (args_info->skip_given)
+    write_into_file(outfile, "skip", args_info->skip_orig, 0);
+  if (args_info->verbosity_given)
+    write_into_file(outfile, "verbosity", args_info->verbosity_orig, 0);
+  if (args_info->mmap_given)
+    write_into_file(outfile, "mmap", 0, 0 );
+  
+
+  i = EXIT_SUCCESS;
+  return i;
+}
+
+int
+cmdline_parser_file_save(const char *filename, struct gengetopt_args_info *args_info)
+{
+  FILE *outfile;
+  int i = 0;
+
+  outfile = fopen(filename, "w");
+
+  if (!outfile)
+    {
+      fprintf (stderr, "%s: cannot open file for writing: %s\n", CMDLINE_PARSER_PACKAGE, filename);
+      return EXIT_FAILURE;
+    }
+
+  i = cmdline_parser_dump(outfile, args_info);
+  fclose (outfile);
+
+  return i;
+}
+
+void
+cmdline_parser_free (struct gengetopt_args_info *args_info)
+{
+  cmdline_parser_release (args_info);
+}
+
+/** @brief replacement of strdup, which is not standard */
+char *
+gengetopt_strdup (const char *s)
+{
+  char *result = 0;
+  if (!s)
+    return result;
+
+  result = (char*)malloc(strlen(s) + 1);
+  if (result == (char*)0)
+    return (char*)0;
+  strcpy(result, s);
+  return result;
+}
+
+int
+cmdline_parser (int argc, char **argv, struct gengetopt_args_info *args_info)
+{
+  return cmdline_parser2 (argc, argv, args_info, 0, 1, 1);
+}
+
+int
+cmdline_parser_ext (int argc, char **argv, struct gengetopt_args_info *args_info,
+                   struct cmdline_parser_params *params)
+{
+  int result;
+  result = cmdline_parser_internal (argc, argv, args_info, params, 0);
+
+  return result;
+}
+
+int
+cmdline_parser2 (int argc, char **argv, struct gengetopt_args_info *args_info, int override, int initialize, int check_required)
+{
+  int result;
+  struct cmdline_parser_params params;
+  
+  params.override = override;
+  params.initialize = initialize;
+  params.check_required = check_required;
+  params.check_ambiguity = 0;
+  params.print_errors = 1;
+
+  result = cmdline_parser_internal (argc, argv, args_info, &params, 0);
+
+  return result;
+}
+
+int
+cmdline_parser_required (struct gengetopt_args_info *args_info, const char *prog_name)
+{
+  FIX_UNUSED (args_info);
+  FIX_UNUSED (prog_name);
+  return EXIT_SUCCESS;
+}
+
+
+static char *package_name = 0;
+
+/**
+ * @brief updates an option
+ * @param field the generic pointer to the field to update
+ * @param orig_field the pointer to the orig field
+ * @param field_given the pointer to the number of occurrence of this option
+ * @param prev_given the pointer to the number of occurrence already seen
+ * @param value the argument for this option (if null no arg was specified)
+ * @param possible_values the possible values for this option (if specified)
+ * @param default_value the default value (in case the option only accepts fixed values)
+ * @param arg_type the type of this option
+ * @param check_ambiguity @see cmdline_parser_params.check_ambiguity
+ * @param override @see cmdline_parser_params.override
+ * @param no_free whether to free a possible previous value
+ * @param multiple_option whether this is a multiple option
+ * @param long_opt the corresponding long option
+ * @param short_opt the corresponding short option (or '-' if none)
+ * @param additional_error possible further error specification
+ */
+static
+int update_arg(void *field, char **orig_field,
+               unsigned int *field_given, unsigned int *prev_given, 
+               char *value, const char *possible_values[],
+               const char *default_value,
+               cmdline_parser_arg_type arg_type,
+               int check_ambiguity, int override,
+               int no_free, int multiple_option,
+               const char *long_opt, char short_opt,
+               const char *additional_error)
+{
+  char *stop_char = 0;
+  const char *val = value;
+  int found;
+  char **string_field;
+  FIX_UNUSED (field);
+
+  stop_char = 0;
+  found = 0;
+
+  if (!multiple_option && prev_given && (*prev_given || (check_ambiguity && *field_given)))
+    {
+      if (short_opt != '-')
+        fprintf (stderr, "%s: `--%s' (`-%c') option given more than once%s\n", 
+               package_name, long_opt, short_opt,
+               (additional_error ? additional_error : ""));
+      else
+        fprintf (stderr, "%s: `--%s' option given more than once%s\n", 
+               package_name, long_opt,
+               (additional_error ? additional_error : ""));
+      return 1; /* failure */
+    }
+
+  FIX_UNUSED (default_value);
+    
+  if (field_given && *field_given && ! override)
+    return 0;
+  if (prev_given)
+    (*prev_given)++;
+  if (field_given)
+    (*field_given)++;
+  if (possible_values)
+    val = possible_values[found];
+
+  switch(arg_type) {
+  case ARG_FLAG:
+    *((int *)field) = !*((int *)field);
+    break;
+  case ARG_INT:
+    if (val) *((int *)field) = strtol (val, &stop_char, 0);
+    break;
+  case ARG_STRING:
+    if (val) {
+      string_field = (char **)field;
+      if (!no_free && *string_field)
+        free (*string_field); /* free previous string */
+      *string_field = gengetopt_strdup (val);
+    }
+    break;
+  default:
+    break;
+  };
+
+  /* check numeric conversion */
+  switch(arg_type) {
+  case ARG_INT:
+    if (val && !(stop_char && *stop_char == '\0')) {
+      fprintf(stderr, "%s: invalid numeric value: %s\n", package_name, val);
+      return 1; /* failure */
+    }
+    break;
+  default:
+    ;
+  };
+
+  /* store the original value */
+  switch(arg_type) {
+  case ARG_NO:
+  case ARG_FLAG:
+    break;
+  default:
+    if (value && orig_field) {
+      if (no_free) {
+        *orig_field = value;
+      } else {
+        if (*orig_field)
+          free (*orig_field); /* free previous string */
+        *orig_field = gengetopt_strdup (value);
+      }
+    }
+  };
+
+  return 0; /* OK */
+}
+
+
+int
+cmdline_parser_internal (
+  int argc, char **argv, struct gengetopt_args_info *args_info,
+                        struct cmdline_parser_params *params, const char *additional_error)
+{
+  int c;	/* Character of the parsed option.  */
+
+  int error = 0;
+  struct gengetopt_args_info local_args_info;
+  
+  int override;
+  int initialize;
+  int check_required;
+  int check_ambiguity;
+  
+  package_name = argv[0];
+  
+  override = params->override;
+  initialize = params->initialize;
+  check_required = params->check_required;
+  check_ambiguity = params->check_ambiguity;
+
+  if (initialize)
+    cmdline_parser_init (args_info);
+
+  cmdline_parser_init (&local_args_info);
+
+  optarg = 0;
+  optind = 0;
+  opterr = params->print_errors;
+  optopt = '?';
+
+  while (1)
+    {
+      int option_index = 0;
+
+      static struct option long_options[] = {
+        { "help",	0, NULL, 'h' },
+        { "version",	0, NULL, 'V' },
+        { "input",	1, NULL, 'i' },
+        { "output",	1, NULL, 'o' },
+        { "genes",	1, NULL, 'g' },
+        { "genex",	1, NULL, 'G' },
+        { "Genes",	0, NULL, 'E' },
+        { "zrow",	0, NULL, 'r' },
+        { "zcol",	0, NULL, 'c' },
+        { "scol",	0, NULL, 'C' },
+        { "normalize",	0, NULL, 'n' },
+        { "skip",	1, NULL, 's' },
+        { "verbosity",	1, NULL, 'v' },
+        { "mmap",	0, NULL, 'm' },
+        { 0,  0, 0, 0 }
+      };
+
+      c = getopt_long (argc, argv, "hVi:o:g:G:ErcCns:v:m", long_options, &option_index);
+
+      if (c == -1) break;	/* Exit from `while (1)' loop.  */
+
+      switch (c)
+        {
+        case 'h':	/* Print help and exit.  */
+          cmdline_parser_print_help ();
+          cmdline_parser_free (&local_args_info);
+          exit (EXIT_SUCCESS);
+
+        case 'V':	/* Print version and exit.  */
+        
+        
+          if (update_arg( 0 , 
+               0 , &(args_info->version_given),
+              &(local_args_info.version_given), optarg, 0, 0, ARG_NO,
+              check_ambiguity, override, 0, 0,
+              "version", 'V',
+              additional_error))
+            goto failure;
+          cmdline_parser_free (&local_args_info);
+          return 0;
+        
+          break;
+        case 'i':	/* Input PCL/BIN file.  */
+        
+        
+          if (update_arg( (void *)&(args_info->input_arg), 
+               &(args_info->input_orig), &(args_info->input_given),
+              &(local_args_info.input_given), optarg, 0, 0, ARG_STRING,
+              check_ambiguity, override, 0, 0,
+              "input", 'i',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 'o':	/* Output PCL/BIN file.  */
+        
+        
+          if (update_arg( (void *)&(args_info->output_arg), 
+               &(args_info->output_orig), &(args_info->output_given),
+              &(local_args_info.output_given), optarg, 0, 0, ARG_STRING,
+              check_ambiguity, override, 0, 0,
+              "output", 'o',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 'g':	/* Process only genes from the given set.  */
+        
+        
+          if (update_arg( (void *)&(args_info->genes_arg), 
+               &(args_info->genes_orig), &(args_info->genes_given),
+              &(local_args_info.genes_given), optarg, 0, 0, ARG_STRING,
+              check_ambiguity, override, 0, 0,
+              "genes", 'g',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 'G':	/* Exclude all genes from the given set.  */
+        
+        
+          if (update_arg( (void *)&(args_info->genex_arg), 
+               &(args_info->genex_orig), &(args_info->genex_given),
+              &(local_args_info.genex_given), optarg, 0, 0, ARG_STRING,
+              check_ambiguity, override, 0, 0,
+              "genex", 'G',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 'E':	/* Only print genes and their indecies.  */
+        
+        
+          if (update_arg((void *)&(args_info->Genes_flag), 0, &(args_info->Genes_given),
+              &(local_args_info.Genes_given), optarg, 0, 0, ARG_FLAG,
+              check_ambiguity, override, 1, 0, "Genes", 'E',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 'r':	/* Normalize Z score row.  */
+        
+        
+          if (update_arg((void *)&(args_info->zrow_flag), 0, &(args_info->zrow_given),
+              &(local_args_info.zrow_given), optarg, 0, 0, ARG_FLAG,
+              check_ambiguity, override, 1, 0, "zrow", 'r',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 'c':	/* Normalize Z score column.  */
+        
+        
+          if (update_arg((void *)&(args_info->zcol_flag), 0, &(args_info->zcol_given),
+              &(local_args_info.zcol_given), optarg, 0, 0, ARG_FLAG,
+              check_ambiguity, override, 1, 0, "zcol", 'c',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 'C':	/* Subtract mean per column.  */
+        
+        
+          if (update_arg((void *)&(args_info->scol_flag), 0, &(args_info->scol_given),
+              &(local_args_info.scol_given), optarg, 0, 0, ARG_FLAG,
+              check_ambiguity, override, 1, 0, "scol", 'C',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 'n':	/* Normalize 0 1 range.  */
+        
+        
+          if (update_arg((void *)&(args_info->normalize_flag), 0, &(args_info->normalize_given),
+              &(local_args_info.normalize_given), optarg, 0, 0, ARG_FLAG,
+              check_ambiguity, override, 1, 0, "normalize", 'n',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 's':	/* Columns to skip in input PCL.  */
+        
+        
+          if (update_arg( (void *)&(args_info->skip_arg), 
+               &(args_info->skip_orig), &(args_info->skip_given),
+              &(local_args_info.skip_given), optarg, 0, "0", ARG_INT,
+              check_ambiguity, override, 0, 0,
+              "skip", 's',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 'v':	/* Message verbosity.  */
+        
+        
+          if (update_arg( (void *)&(args_info->verbosity_arg), 
+               &(args_info->verbosity_orig), &(args_info->verbosity_given),
+              &(local_args_info.verbosity_given), optarg, 0, "5", ARG_INT,
+              check_ambiguity, override, 0, 0,
+              "verbosity", 'v',
+              additional_error))
+            goto failure;
+        
+          break;
+        case 'm':	/* Memmap binary input.  */
+        
+        
+          if (update_arg((void *)&(args_info->mmap_flag), 0, &(args_info->mmap_given),
+              &(local_args_info.mmap_given), optarg, 0, 0, ARG_FLAG,
+              check_ambiguity, override, 1, 0, "mmap", 'm',
+              additional_error))
+            goto failure;
+        
+          break;
+
+        case 0:	/* Long option with no short option */
+        case '?':	/* Invalid option.  */
+          /* `getopt_long' already printed an error message.  */
+          goto failure;
+
+        default:	/* bug: option not considered.  */
+          fprintf (stderr, "%s: option unknown: %c%s\n", CMDLINE_PARSER_PACKAGE, c, (additional_error ? additional_error : ""));
+          abort ();
+        } /* switch */
+    } /* while */
+
+
+
+
+  cmdline_parser_release (&local_args_info);
+
+  if ( error )
+    return (EXIT_FAILURE);
+
+  if (optind < argc)
+    {
+      int i = 0 ;
+      int found_prog_name = 0;
+      /* whether program name, i.e., argv[0], is in the remaining args
+         (this may happen with some implementations of getopt,
+          but surely not with the one included by gengetopt) */
+
+      i = optind;
+      while (i < argc)
+        if (argv[i++] == argv[0]) {
+          found_prog_name = 1;
+          break;
+        }
+      i = 0;
+
+      args_info->inputs_num = argc - optind - found_prog_name;
+      args_info->inputs =
+        (char **)(malloc ((args_info->inputs_num)*sizeof(char *))) ;
+      while (optind < argc)
+        if (argv[optind++] != argv[0])
+          args_info->inputs[ i++ ] = gengetopt_strdup (argv[optind-1]) ;
+    }
+
+  return 0;
+
+failure:
+  
+  cmdline_parser_release (&local_args_info);
+  return (EXIT_FAILURE);
+}

tools/PCL2Bin/cmdline.h

+/** @file cmdline.h
+ *  @brief The header file for the command line option parser
+ *  generated by GNU Gengetopt version 2.22.4
+ *  http://www.gnu.org/software/gengetopt.
+ *  DO NOT modify this file, since it can be overwritten
+ *  @author GNU Gengetopt by Lorenzo Bettini */
+
+#ifndef CMDLINE_H
+#define CMDLINE_H
+
+/* If we use autoconf.  */
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
+#include <stdio.h> /* for FILE */
+
+#ifdef __cplusplus
+extern "C" {
+#endif /* __cplusplus */
+
+#ifndef CMDLINE_PARSER_PACKAGE
+/** @brief the program name (used for printing errors) */
+#define CMDLINE_PARSER_PACKAGE "PCL2Bin"
+#endif
+
+#ifndef CMDLINE_PARSER_PACKAGE_NAME
+/** @brief the complete program name (used for help and version) */
+#define CMDLINE_PARSER_PACKAGE_NAME "PCL2Bin"
+#endif
+
+#ifndef CMDLINE_PARSER_VERSION
+/** @brief the program version */
+#define CMDLINE_PARSER_VERSION "1.0"
+#endif
+
+/** @brief Where the command line options are stored */
+struct gengetopt_args_info
+{
+  const char *help_help; /**< @brief Print help and exit help description.  */
+  const char *version_help; /**< @brief Print version and exit help description.  */
+  char * input_arg;	/**< @brief Input PCL/BIN file.  */
+  char * input_orig;	/**< @brief Input PCL/BIN file original value given at command line.  */
+  const char *input_help; /**< @brief Input PCL/BIN file help description.  */
+  char * output_arg;	/**< @brief Output PCL/BIN file.  */
+  char * output_orig;	/**< @brief Output PCL/BIN file original value given at command line.  */
+  const char *output_help; /**< @brief Output PCL/BIN file help description.  */
+  char * genes_arg;	/**< @brief Process only genes from the given set.  */
+  char * genes_orig;	/**< @brief Process only genes from the given set original value given at command line.  */
+  const char *genes_help; /**< @brief Process only genes from the given set help description.  */
+  char * genex_arg;	/**< @brief Exclude all genes from the given set.  */
+  char * genex_orig;	/**< @brief Exclude all genes from the given set original value given at command line.  */
+  const char *genex_help; /**< @brief Exclude all genes from the given set help description.  */
+  int Genes_flag;	/**< @brief Only print genes and their indecies (default=off).  */
+  const char *Genes_help; /**< @brief Only print genes and their indecies help description.  */
+  int zrow_flag;	/**< @brief Normalize Z score row (default=off).  */
+  const char *zrow_help; /**< @brief Normalize Z score row help description.  */
+  int zcol_flag;	/**< @brief Normalize Z score column (default=off).  */
+  const char *zcol_help; /**< @brief Normalize Z score column help description.  */
+  int scol_flag;	/**< @brief Subtract mean per column (default=off).  */
+  const char *scol_help; /**< @brief Subtract mean per column help description.  */
+  int normalize_flag;	/**< @brief Normalize 0 1 range (default=off).  */
+  const char *normalize_help; /**< @brief Normalize 0 1 range help description.  */
+  int skip_arg;	/**< @brief Columns to skip in input PCL (default='0').  */
+  char * skip_orig;	/**< @brief Columns to skip in input PCL original value given at command line.  */
+  const char *skip_help; /**< @brief Columns to skip in input PCL help description.  */
+  int verbosity_arg;	/**< @brief Message verbosity (default='5').  */
+  char * verbosity_orig;	/**< @brief Message verbosity original value given at command line.  */
+  const char *verbosity_help; /**< @brief Message verbosity help description.  */
+  int mmap_flag;	/**< @brief Memmap binary input (default=off).  */
+  const char *mmap_help; /**< @brief Memmap binary input help description.  */
+  
+  unsigned int help_given ;	/**< @brief Whether help was given.  */
+  unsigned int version_given ;	/**< @brief Whether version was given.  */
+  unsigned int input_given ;	/**< @brief Whether input was given.  */
+  unsigned int output_given ;	/**< @brief Whether output was given.  */
+  unsigned int genes_given ;	/**< @brief Whether genes was given.  */
+  unsigned int genex_given ;	/**< @brief Whether genex was given.  */
+  unsigned int Genes_given ;	/**< @brief Whether Genes was given.  */
+  unsigned int zrow_given ;	/**< @brief Whether zrow was given.  */
+  unsigned int zcol_given ;	/**< @brief Whether zcol was given.  */
+  unsigned int scol_given ;	/**< @brief Whether scol was given.  */
+  unsigned int normalize_given ;	/**< @brief Whether normalize was given.  */
+  unsigned int skip_given ;	/**< @brief Whether skip was given.  */
+  unsigned int verbosity_given ;	/**< @brief Whether verbosity was given.  */
+  unsigned int mmap_given ;	/**< @brief Whether mmap was given.  */
+
+  char **inputs ; /**< @brief unamed options (options without names) */
+  unsigned inputs_num ; /**< @brief unamed options number */
+} ;
+
+/** @brief The additional parameters to pass to parser functions */
+struct cmdline_parser_params
+{
+  int override; /**< @brief whether to override possibly already present options (default 0) */
+  int initialize; /**< @brief whether to initialize the option structure gengetopt_args_info (default 1) */
+  int check_required; /**< @brief whether to check that all required options were provided (default 1) */
+  int check_ambiguity; /**< @brief whether to check for options already specified in the option structure gengetopt_args_info (default 0) */
+  int print_errors; /**< @brief whether getopt_long should print an error message for a bad option (default 1) */
+} ;
+
+/** @brief the purpose string of the program */
+extern const char *gengetopt_args_info_purpose;
+/** @brief the usage string of the program */
+extern const char *gengetopt_args_info_usage;
+/** @brief all the lines making the help output */
+extern const char *gengetopt_args_info_help[];
+
+/**
+ * The command line parser
+ * @param argc the number of command line options
+ * @param argv the command line options
+ * @param args_info the structure where option information will be stored
+ * @return 0 if everything went fine, NON 0 if an error took place
+ */
+int cmdline_parser (int argc, char **argv,
+  struct gengetopt_args_info *args_info);
+
+/**
+ * The command line parser (version with additional parameters - deprecated)
+ * @param argc the number of command line options
+ * @param argv the command line options
+ * @param args_info the structure where option information will be stored
+ * @param override whether to override possibly already present options
+ * @param initialize whether to initialize the option structure my_args_info
+ * @param check_required whether to check that all required options were provided
+ * @return 0 if everything went fine, NON 0 if an error took place
+ * @deprecated use cmdline_parser_ext() instead
+ */
+int cmdline_parser2 (int argc, char **argv,
+  struct gengetopt_args_info *args_info,
+  int override, int initialize, int check_required);
+
+/**
+ * The command line parser (version with additional parameters)
+ * @param argc the number of command line options
+ * @param argv the command line options
+ * @param args_info the structure where option information will be stored
+ * @param params additional parameters for the parser
+ * @return 0 if everything went fine, NON 0 if an error took place
+ */
+int cmdline_parser_ext (int argc, char **argv,
+  struct gengetopt_args_info *args_info,
+  struct cmdline_parser_params *params);
+
+/**
+ * Save the contents of the option struct into an already open FILE stream.
+ * @param outfile the stream where to dump options
+ * @param args_info the option struct to dump
+ * @return 0 if everything went fine, NON 0 if an error took place
+ */
+int cmdline_parser_dump(FILE *outfile,
+  struct gengetopt_args_info *args_info);
+
+/**
+ * Save the contents of the option struct into a (text) file.
+ * This file can be read by the config file parser (if generated by gengetopt)
+ * @param filename the file where to save
+ * @param args_info the option struct to save
+ * @return 0 if everything went fine, NON 0 if an error took place
+ */
+int cmdline_parser_file_save(const char *filename,
+  struct gengetopt_args_info *args_info);
+
+/**
+ * Print the help
+ */
+void cmdline_parser_print_help(void);
+/**
+ * Print the version
+ */
+void cmdline_parser_print_version(void);
+
+/**
+ * Initializes all the fields a cmdline_parser_params structure 
+ * to their default values
+ * @param params the structure to initialize
+ */
+void cmdline_parser_params_init(struct cmdline_parser_params *params);
+
+/**
+ * Allocates dynamically a cmdline_parser_params structure and initializes
+ * all its fields to their default values
+ * @return the created and initialized cmdline_parser_params structure
+ */
+struct cmdline_parser_params *cmdline_parser_params_create(void);
+
+/**
+ * Initializes the passed gengetopt_args_info structure's fields
+ * (also set default values for options that have a default)
+ * @param args_info the structure to initialize
+ */
+void cmdline_parser_init (struct gengetopt_args_info *args_info);
+/**
+ * Deallocates the string fields of the gengetopt_args_info structure
+ * (but does not deallocate the structure itself)
+ * @param args_info the structure to deallocate
+ */
+void cmdline_parser_free (struct gengetopt_args_info *args_info);
+
+/**
+ * Checks that all the required options were specified
+ * @param args_info the structure to check
+ * @param prog_name the name of the program that will be used to print
+ *   possible errors
+ * @return
+ */
+int cmdline_parser_required (struct gengetopt_args_info *args_info,
+  const char *prog_name);
+
+
+#ifdef __cplusplus
+}
+#endif /* __cplusplus */
+#endif /* CMDLINE_H */

tools/PCL2Bin/stdafx.h

+/*****************************************************************************
+* This file is provided under the Creative Commons Attribution 3.0 license.
+*
+* You are free to share, copy, distribute, transmit, or adapt this work
+* PROVIDED THAT you attribute the work to the authors listed below.
+* For more information, please see the following web page:
+* http://creativecommons.org/licenses/by/3.0/
+*
+* This file is a component of the Sleipnir library for functional genomics,
+* authored by:
+* Curtis Huttenhower (chuttenh@princeton.edu)
+* Mark Schroeder
+* Maria D. Chikina
+* Olga G. Troyanskaya (ogt@princeton.edu, primary contact)
+*
+* If you use this library, the included executable tools, or any related
+* code in your work, please cite the following publication:
+* Curtis Huttenhower, Mark Schroeder, Maria D. Chikina, and
+* Olga G. Troyanskaya.
+* "The Sleipnir library for computational functional genomics"
+*****************************************************************************/
+#ifndef STDAFX_H
+#define STDAFX_H
+
+#include <fstream>
+using namespace std;
+
+#include "dat.h"
+#include "meta.h"
+#include "pcl.h"
+#include "genome.h"
+
+using namespace Sleipnir;
+
+#endif // STDAFX_H