Fixed a lot of warnings. Added visual studio project. Make needed changes to work with windows.

COPYING

@@ -291,7 +291,7 @@ convey the exclusion of warranty; and each file should have at least
 the "copyright" line and a pointer to where the full notice is found.
 
     <one line to give the program's name and a brief idea of what it does.>
-    Copyright (C) <year>  <name of author>
+    Copyright (C) 19yy  <name of author>
 
     This program is free software; you can redistribute it and/or modify
     it under the terms of the GNU General Public License as published by
@@ -313,7 +313,7 @@ Also add information on how to contact you by electronic and paper mail.
 If the program is interactive, make it output a short notice like this
 when it starts in an interactive mode:
 
-    Gnomovision version 69, Copyright (C) year  name of author
+    Gnomovision version 69, Copyright (C) 19yy name of author
     Gnomovision comes with ABSOLUTELY NO WARRANTY; for details type `show w'.
     This is free software, and you are welcome to redistribute it
     under certain conditions; type `show c' for details.

INSTALL

@@ -1,9 +1,3 @@
-Copyright (C) 1994, 1995, 1996, 1999, 2000, 2001, 2002 Free Software
-Foundation, Inc.
-
-   This file is free documentation; the Free Software Foundation gives
-unlimited permission to copy, distribute and modify it.
-
 Basic Installation
 ==================
 
@@ -14,27 +8,20 @@ various system-dependent variables used during compilation.  It uses
 those values to create a `Makefile' in each directory of the package.
 It may also create one or more `.h' files containing system-dependent
 definitions.  Finally, it creates a shell script `config.status' that
-you can run in the future to recreate the current configuration, and a
+you can run in the future to recreate the current configuration, a file
-file `config.log' containing compiler output (useful mainly for
+`config.cache' that saves the results of its tests to speed up
-debugging `configure').
+reconfiguring, and a file `config.log' containing compiler output
-
+(useful mainly for debugging `configure').
-   It can also use an optional file (typically called `config.cache'
-and enabled with `--cache-file=config.cache' or simply `-C') that saves
-the results of its tests to speed up reconfiguring.  (Caching is
-disabled by default to prevent problems with accidental use of stale
-cache files.)
 
    If you need to do unusual things to compile the package, please try
 to figure out how `configure' could check whether to do them, and mail
 diffs or instructions to the address given in the `README' so they can
-be considered for the next release.  If you are using the cache, and at
+be considered for the next release.  If at some point `config.cache'
-some point `config.cache' contains results you don't want to keep, you
+contains results you don't want to keep, you may remove or edit it.
-may remove or edit it.
 
-   The file `configure.ac' (or `configure.in') is used to create
+   The file `configure.in' is used to create `configure' by a program
-`configure' by a program called `autoconf'.  You only need
+called `autoconf'.  You only need `configure.in' if you want to change
-`configure.ac' if you want to change it or regenerate `configure' using
+it or regenerate `configure' using a newer version of `autoconf'.
-a newer version of `autoconf'.
 
 The simplest way to compile this package is:
 
@@ -68,16 +55,14 @@ Compilers and Options
 =====================
 
    Some systems require unusual options for compilation or linking that
-the `configure' script does not know about.  Run `./configure --help'
+the `configure' script does not know about.  You can give `configure'
-for details on some of the pertinent environment variables.
+initial values for variables by setting them in the environment.  Using
+a Bourne-compatible shell, you can do that on the command line like
+this:
+     CC=c89 CFLAGS=-O2 LIBS=-lposix ./configure
 
-   You can give `configure' initial values for configuration parameters
+Or on systems that have the `env' program, you can do it like this:
-by setting variables in the command line or in the environment.  Here
+     env CPPFLAGS=-I/usr/local/include LDFLAGS=-s ./configure
-is an example:
-
-     ./configure CC=c89 CFLAGS=-O2 LIBS=-lposix
-
-   *Note Defining Variables::, for more details.
 
 Compiling For Multiple Architectures
 ====================================
@@ -90,11 +75,11 @@ directory where you want the object files and executables to go and run
 the `configure' script.  `configure' automatically checks for the
 source code in the directory that `configure' is in and in `..'.
 
-   If you have to use a `make' that does not support the `VPATH'
+   If you have to use a `make' that does not supports the `VPATH'
-variable, you have to compile the package for one architecture at a
+variable, you have to compile the package for one architecture at a time
-time in the source code directory.  After you have installed the
+in the source code directory.  After you have installed the package for
-package for one architecture, use `make distclean' before reconfiguring
+one architecture, use `make distclean' before reconfiguring for another
-for another architecture.
+architecture.
 
 Installation Names
 ==================
@@ -138,31 +123,21 @@ Specifying the System Type
 ==========================
 
    There may be some features `configure' can not figure out
-automatically, but needs to determine by the type of machine the package
+automatically, but needs to determine by the type of host the package
-will run on.  Usually, assuming the package is built to be run on the
+will run on.  Usually `configure' can figure that out, but if it prints
-_same_ architectures, `configure' can figure that out, but if it prints
+a message saying it can not guess the host type, give it the
-a message saying it cannot guess the machine type, give it the
+`--host=TYPE' option.  TYPE can either be a short name for the system
-`--build=TYPE' option.  TYPE can either be a short name for the system
+type, such as `sun4', or a canonical name with three fields:
-type, such as `sun4', or a canonical name which has the form:
-
      CPU-COMPANY-SYSTEM
 
-where SYSTEM can have one of these forms:
-
-     OS KERNEL-OS
-
 See the file `config.sub' for the possible values of each field.  If
 `config.sub' isn't included in this package, then this package doesn't
-need to know the machine type.
+need to know the host type.
 
-   If you are _building_ compiler tools for cross-compiling, you should
+   If you are building compiler tools for cross-compiling, you can also
 use the `--target=TYPE' option to select the type of system they will
-produce code for.
+produce code for and the `--build=TYPE' option to select the type of
-
+system on which you are compiling the package.
-   If you want to _use_ a cross compiler, that generates code for a
-platform different from the build platform, you should specify the
-"host" platform (i.e., that on which the generated programs will
-eventually be run) with `--host=TYPE'.
 
 Sharing Defaults
 ================
@@ -175,43 +150,19 @@ default values for variables like `CC', `cache_file', and `prefix'.
 `CONFIG_SITE' environment variable to the location of the site script.
 A warning: not all `configure' scripts look for a site script.
 
-Defining Variables
+Operation Controls
 ==================
 
-   Variables not defined in a site shell script can be set in the
-environment passed to `configure'.  However, some packages may run
-configure again during the build, and the customized values of these
-variables may be lost.  In order to avoid this problem, you should set
-them in the `configure' command line, using `VAR=value'.  For example:
-
-     ./configure CC=/usr/local2/bin/gcc
-
-will cause the specified gcc to be used as the C compiler (unless it is
-overridden in the site shell script).
-
-`configure' Invocation
-======================
-
    `configure' recognizes the following options to control how it
 operates.
 
-`--help'
-`-h'
-     Print a summary of the options to `configure', and exit.
-
-`--version'
-`-V'
-     Print the version of Autoconf used to generate the `configure'
-     script, and exit.
-
 `--cache-file=FILE'
-     Enable the cache: use and save the results of the tests in FILE,
+     Use and save the results of the tests in FILE instead of
-     traditionally `config.cache'.  FILE defaults to `/dev/null' to
+     `./config.cache'.  Set FILE to `/dev/null' to disable caching, for
-     disable caching.
+     debugging `configure'.
 
-`--config-cache'
+`--help'
-`-C'
+     Print a summary of the options to `configure', and exit.
-     Alias for `--cache-file=config.cache'.
 
 `--quiet'
 `--silent'
@@ -224,6 +175,8 @@ operates.
      Look for the package's source code in directory DIR.  Usually
      `configure' can determine that directory automatically.
 
-`configure' also accepts some other, not widely useful, options.  Run
+`--version'
-`configure --help' for more details.
+     Print the version of Autoconf used to generate the `configure'
+     script, and exit.
 
+`configure' also accepts some other, not widely useful, options.

src/Makefile.am

@@ -18,5 +18,5 @@ libcmph_la_SOURCES = debug.h\
 
 libcmph_la_LDFLAGS = -version-info 0:0:0
 
-cmph_SOURCES = 	main.c
+cmph_SOURCES = 	main.c ../wingetopt.h ../wingetopt.c
 cmph_LDADD = libcmph.la

src/bmz.c

@@ -9,12 +9,11 @@
 #include <stdio.h>
 #include <assert.h>
 #include <string.h>
-#include <netinet/in.h>
 
 //#define DEBUG
 #include "debug.h"
 
-static uint32 UNDEFINED = UINT_MAX;
+//static uint32 UNDEFINED = UINT_MAX;
 
 static const char bitmask[8] = { 1, 1 << 1, 1 << 2, 1 << 3, 1 << 4, 1 << 5, 1 << 6, 1 << 7 };
 #define GETBIT(array, i) (array[(i) / 8] & bitmask[(i) % 8])
@@ -437,7 +436,7 @@ static int bmz_gen_edges(mph_t *mph)
 		if (h1 == h2) if (++h2 >= bmz->n) h2 = 0;
 		if (h1 == h2) 
 		{
-			if (mph->verbosity) fprintf(stderr, "Self loop for key %e\n", e);
+			if (mph->verbosity) fprintf(stderr, "Self loop for key %u\n", e);
 			mph->key_source->dispose(mph->key_source->data, key, keylen);
 			return 0;
 		}
@@ -457,7 +456,7 @@ int bmz_mphf_dump(mphf_t *mphf, FILE *fd)
 	uint32 buflen;
 	uint32 nbuflen;
 	uint32 i;
-	uint32 two = htonl(2); //number of hash functions
+	uint32 two = 2; //number of hash functions
 	bmz_mphf_data_t *data = (bmz_mphf_data_t *)mphf->data;
 	uint32 nn, nm;
 	__mphf_dump(mphf, fd);
@@ -466,28 +465,20 @@ int bmz_mphf_dump(mphf_t *mphf, FILE *fd)
 
 	hash_state_dump(data->hashes[0], &buf, &buflen);
 	DEBUGP("Dumping hash state with %u bytes to disk\n", buflen);
-	nbuflen = htonl(buflen);
+	fwrite(&buflen, sizeof(uint32), 1, fd);
-	fwrite(&nbuflen, sizeof(uint32), 1, fd);
 	fwrite(buf, buflen, 1, fd);
 	free(buf);
 
 	hash_state_dump(data->hashes[1], &buf, &buflen);
 	DEBUGP("Dumping hash state with %u bytes to disk\n", buflen);
-	nbuflen = htonl(buflen);
+	fwrite(&buflen, sizeof(uint32), 1, fd);
-	fwrite(&nbuflen, sizeof(uint32), 1, fd);
 	fwrite(buf, buflen, 1, fd);
 	free(buf);
 
-	nn = htonl(data->n);
+	fwrite(&(data->n), sizeof(uint32), 1, fd);
-	fwrite(&nn, sizeof(uint32), 1, fd);
+	fwrite(&(data->m), sizeof(uint32), 1, fd);
-	nm = htonl(data->m);
-	fwrite(&nm, sizeof(uint32), 1, fd);
 	
-	for (i = 0; i < data->n; ++i)
+	fwrite(data->g, sizeof(uint32)*(data->n), 1, fd);
-	{
-		uint32 ng = htonl(data->g[i]);
-		fwrite(&ng, sizeof(uint32), 1, fd);
-	}
 	#ifdef DEBUG
 	fprintf(stderr, "G: ");
 	for (i = 0; i < data->n; ++i) fprintf(stderr, "%u ", data->g[i]);
@@ -499,17 +490,14 @@ int bmz_mphf_dump(mphf_t *mphf, FILE *fd)
 void bmz_mphf_load(FILE *f, mphf_t *mphf)
 {
 	uint32 nhashes;
-	char fbuf[BUFSIZ];
 	char *buf = NULL;
 	uint32 buflen;
 	uint32 i;
-	hash_state_t *state;
 	bmz_mphf_data_t *bmz = (bmz_mphf_data_t *)malloc(sizeof(bmz_mphf_data_t));
 
 	DEBUGP("Loading bmz mphf\n");
 	mphf->data = bmz;
 	fread(&nhashes, sizeof(uint32), 1, f);
-	nhashes = ntohl(nhashes);
 	bmz->hashes = (hash_state_t **)malloc(sizeof(hash_state_t *)*(nhashes + 1));
 	bmz->hashes[nhashes] = NULL;
 	DEBUGP("Reading %u hashes\n", nhashes);
@@ -517,7 +505,6 @@ void bmz_mphf_load(FILE *f, mphf_t *mphf)
 	{
 		hash_state_t *state = NULL;
 		fread(&buflen, sizeof(uint32), 1, f);
-		buflen = ntohl(buflen);
 		DEBUGP("Hash state has %u bytes\n", buflen);
 		buf = (char *)malloc(buflen);
 		fread(buf, buflen, 1, f);
@@ -528,13 +515,10 @@ void bmz_mphf_load(FILE *f, mphf_t *mphf)
 
 	DEBUGP("Reading m and n\n");
 	fread(&(bmz->n), sizeof(uint32), 1, f);	
-	bmz->n = ntohl(bmz->n);
 	fread(&(bmz->m), sizeof(uint32), 1, f);	
-	bmz->m = ntohl(bmz->m);
 
 	bmz->g = (uint32 *)malloc(sizeof(uint32)*bmz->n);
 	fread(bmz->g, bmz->n*sizeof(uint32), 1, f);
-	for (i = 0; i < bmz->n; ++i) bmz->g[i] = ntohl(bmz->g[i]);
 	#ifdef DEBUG
 	fprintf(stderr, "G: ");
 	for (i = 0; i < bmz->n; ++i) fprintf(stderr, "%u ", bmz->g[i]);

src/bmz.h

@@ -14,5 +14,6 @@ mphf_t *bmz_mph_create(mph_t *mph, float bmz_c);
 
 void bmz_mphf_load(FILE *f, mphf_t *mphf);
 int bmz_mphf_dump(mphf_t *mphf, FILE *f);
+void bmz_mphf_destroy(mphf_t *mphf);
 uint32 bmz_mphf_search(mphf_t *mphf, const char *key, uint32 keylen);
 #endif

src/cmph.c

@@ -68,18 +68,26 @@ void mph_set_hashfuncs(mph_t *mph, CMPH_HASH *hashfuncs)
 	}
 	return;
 }
+void mph_set_graphsize(mph_t *mph, float c)
+{
+	mph->c = c;
+	return;
+}
 
-mphf_t *mph_create(mph_t *mph, float c)
+mphf_t *mph_create(mph_t *mph)
 {
 	mphf_t *mphf = NULL;
+	float c = mph->c;
 	switch (mph->algo)	
 	{
 		case MPH_CZECH:
 			DEBUGP("Creating czech hash\n");
+			if (c == 0) c = 2.09;
 			mphf = czech_mph_create(mph, c);
 			break;
 		case MPH_BMZ: /* included -- Fabiano */
 			DEBUGP("Creating bmz hash\n");
+			if (c == 0) c = 1.15;
 			mphf = bmz_mph_create(mph, c);
 			break;
 		default:
@@ -143,7 +151,7 @@ uint32 mphf_search(mphf_t *mphf, const char *key, uint32 keylen)
 			assert(0);
 	}
 	assert(0);
-	return;
+	return 0;
 }
 
 uint32 mphf_size(mphf_t *mphf)

src/cmph.h

@@ -27,8 +27,9 @@ typedef struct
 mph_t *mph_new(MPH_ALGO algo, key_source_t *key_source);
 void mph_set_hashfuncs(mph_t *mph, CMPH_HASH *hashfuncs);
 void mph_set_verbosity(mph_t *mph, uint32 verbosity);
+void mph_set_graphsize(mph_t *mph, float c);
 void mph_destroy(mph_t *mph);
-mphf_t *mph_create(mph_t *mph, float c);
+mphf_t *mph_create(mph_t *mph);
 
 /** Hash querying API **/
 mphf_t *mphf_load(FILE *f);

src/cmph_structs.c

@@ -13,6 +13,7 @@ mph_t *__mph_new(MPH_ALGO algo, key_source_t *key_source)
 	mph->algo = algo;
 	mph->key_source = key_source;
 	mph->verbosity = 0;
+	float c = 0;
 	return mph;
 }
 
@@ -24,7 +25,7 @@ void __mph_destroy(mph_t *mph)
 void __mphf_dump(mphf_t *mphf, FILE *fd)
 {
 	uint32 nsize = htonl(mphf->size);
-	fwrite(mph_names[mphf->algo], strlen(mph_names[mphf->algo]) + 1, 1, fd);
+	fwrite(mph_names[mphf->algo], (uint32)(strlen(mph_names[mphf->algo]) + 1), 1, fd);
 	fwrite(&nsize, sizeof(mphf->size), 1, fd);
 }
 mphf_t *__mphf_load(FILE *f) 

src/cmph_structs.h

@@ -10,6 +10,7 @@ struct __mph_t
 	MPH_ALGO algo;
 	key_source_t *key_source;
 	uint32 verbosity;
+	float c;
 	void *data; //algorithm dependent data
 };
 

src/czech.c

@@ -8,7 +8,6 @@
 #include <stdio.h>
 #include <assert.h>
 #include <string.h>
-#include <netinet/in.h>
 
 //#define DEBUG
 #include "debug.h"
@@ -68,7 +67,7 @@ mphf_t *czech_mph_create(mph_t *mph, float c)
 	char *visited = NULL;
 	czech_mph_data_t *czech = (czech_mph_data_t *)mph->data;
 	czech->m = mph->key_source->nkeys;	
-	czech->n = ceil(c * mph->key_source->nkeys);	
+	czech->n = (uint32)ceil(c * mph->key_source->nkeys);	
 	DEBUGP("m (edges): %u n (vertices): %u c: %f\n", czech->m, czech->n, c);
 	czech->graph = graph_new(czech->n, czech->m);
 	DEBUGP("Created graph\n");
@@ -197,7 +196,7 @@ static int czech_gen_edges(mph_t *mph)
 		if (h1 == h2) if (++h2 >= czech->n) h2 = 0;
 		if (h1 == h2) 
 		{
-			if (mph->verbosity) fprintf(stderr, "Self loop for key %e\n", e);
+			if (mph->verbosity) fprintf(stderr, "Self loop for key %u\n", e);
 			mph->key_source->dispose(mph->key_source->data, key, keylen);
 			return 0;
 		}
@@ -216,39 +215,29 @@ int czech_mphf_dump(mphf_t *mphf, FILE *fd)
 {
 	char *buf = NULL;
 	uint32 buflen;
-	uint32 nbuflen;
+	uint32 two = 2; //number of hash functions
-	uint32 i;
-	uint32 two = htonl(2); //number of hash functions
 	czech_mphf_data_t *data = (czech_mphf_data_t *)mphf->data;
-	uint32 nn, nm;
 	__mphf_dump(mphf, fd);
 
 	fwrite(&two, sizeof(uint32), 1, fd);
 
 	hash_state_dump(data->hashes[0], &buf, &buflen);
 	DEBUGP("Dumping hash state with %u bytes to disk\n", buflen);
-	nbuflen = htonl(buflen);
+	fwrite(&buflen, sizeof(uint32), 1, fd);
-	fwrite(&nbuflen, sizeof(uint32), 1, fd);
 	fwrite(buf, buflen, 1, fd);
 	free(buf);
 
 	hash_state_dump(data->hashes[1], &buf, &buflen);
 	DEBUGP("Dumping hash state with %u bytes to disk\n", buflen);
-	nbuflen = htonl(buflen);
+	fwrite(&buflen, sizeof(uint32), 1, fd);
-	fwrite(&nbuflen, sizeof(uint32), 1, fd);
 	fwrite(buf, buflen, 1, fd);
 	free(buf);
 
-	nn = htonl(data->n);
+	fwrite(&(data->n), sizeof(uint32), 1, fd);
-	fwrite(&nn, sizeof(uint32), 1, fd);
+	fwrite(&(data->m), sizeof(uint32), 1, fd);
-	nm = htonl(data->m);
+	
-	fwrite(&nm, sizeof(uint32), 1, fd);
+	fwrite(data->g, sizeof(uint32)*data->n, 1, fd);
 	
-	for (i = 0; i < data->n; ++i)
-	{
-		uint32 ng = htonl(data->g[i]);
-		fwrite(&ng, sizeof(uint32), 1, fd);
-	}
 	#ifdef DEBUG
 	fprintf(stderr, "G: ");
 	for (i = 0; i < data->n; ++i) fprintf(stderr, "%u ", data->g[i]);
@@ -260,17 +249,14 @@ int czech_mphf_dump(mphf_t *mphf, FILE *fd)
 void czech_mphf_load(FILE *f, mphf_t *mphf)
 {
 	uint32 nhashes;
-	char fbuf[BUFSIZ];
 	char *buf = NULL;
 	uint32 buflen;
 	uint32 i;
-	hash_state_t *state;
 	czech_mphf_data_t *czech = (czech_mphf_data_t *)malloc(sizeof(czech_mphf_data_t));
 
 	DEBUGP("Loading czech mphf\n");
 	mphf->data = czech;
 	fread(&nhashes, sizeof(uint32), 1, f);
-	nhashes = ntohl(nhashes);
 	czech->hashes = (hash_state_t **)malloc(sizeof(hash_state_t *)*(nhashes + 1));
 	czech->hashes[nhashes] = NULL;
 	DEBUGP("Reading %u hashes\n", nhashes);
@@ -278,7 +264,6 @@ void czech_mphf_load(FILE *f, mphf_t *mphf)
 	{
 		hash_state_t *state = NULL;
 		fread(&buflen, sizeof(uint32), 1, f);
-		buflen = ntohl(buflen);
 		DEBUGP("Hash state has %u bytes\n", buflen);
 		buf = (char *)malloc(buflen);
 		fread(buf, buflen, 1, f);
@@ -289,13 +274,10 @@ void czech_mphf_load(FILE *f, mphf_t *mphf)
 
 	DEBUGP("Reading m and n\n");
 	fread(&(czech->n), sizeof(uint32), 1, f);	
-	czech->n = ntohl(czech->n);
 	fread(&(czech->m), sizeof(uint32), 1, f);	
-	czech->m = ntohl(czech->m);
 	
 	czech->g = (uint32 *)malloc(sizeof(uint32)*czech->n);
 	fread(czech->g, czech->n*sizeof(uint32), 1, f);
-	for (i = 0; i < czech->n; ++i) czech->g[i] = ntohl(czech->g[i]);
 	/*
 	#ifdef DEBUG
 	fprintf(stderr, "G: ");

src/czech.h

@@ -14,5 +14,6 @@ mphf_t *czech_mph_create(mph_t *mph, float c);
 
 void czech_mphf_load(FILE *f, mphf_t *mphf);
 int czech_mphf_dump(mphf_t *mphf, FILE *f);
+void czech_mphf_destroy(mphf_t *mphf);
 uint32 czech_mphf_search(mphf_t *mphf, const char *key, uint32 keylen);
 #endif

src/debug.h

@@ -1,15 +1,53 @@
-#ifndef __MY_DEBUGC__
+#ifdef DEBUGP
-#define __MY_DEBUGC__
+#undef DEBUGP
+#endif
 
 #ifdef __cplusplus
 #include <cstdio>
+#ifdef WIN32
+#include <cstring>
+#endif
 #else
 #include <stdio.h>
+#ifdef WIN32
+#include <string.h>
 #endif
+#endif
+
+#ifdef WIN32
+#ifndef __DEBUG_H__
+#define __DEBUG_H__
+#include <stdarg.h>
+static void debugprintf(const char *format, ...)
+{
+    va_list ap;
+	char *f = NULL;
+	const char *p="%s:%d ";
+	size_t plen = strlen(p);
+    va_start(ap, format);
+	f = (char *)malloc(plen + strlen(format) + 1);
+	if (!f) return;
+	memcpy(f, p, plen);
+	memcpy(f + plen, format, strlen(format) + 1);
+    vfprintf(stderr, f, ap);
+    va_end(ap);
+	free(f);
+}
+static void dummyprintf(const char *format, ...)
+{}
+#endif
+#endif
+
 #ifdef DEBUG
+#ifdef WIN32
+#define DEBUGP debugprintf
+#else
 #define DEBUGP(args...) do { fprintf(stderr, "%s:%d ", __FILE__, __LINE__); fprintf(stderr, ## args); } while(0)
+#endif
+#else
+#ifdef WIN32
+#define DEBUGP dummyprintf
 #else
 #define DEBUGP(args...)
 #endif
-
 #endif

src/djb2_hash.c

@@ -15,9 +15,9 @@ void djb2_state_destroy(djb2_state_t *state)
 
 uint32 djb2_hash(djb2_state_t *state, const char *k, uint32 keylen)
 {
-	register unsigned int hash = 5381;
+	register uint32 hash = 5381;
 	const unsigned char *ptr = k;
-	int i = 0;
+	uint32 i = 0;
 	while (i < keylen) 
 	{
 		hash = hash*33 ^ *ptr;

src/graph.c

@@ -10,7 +10,7 @@
 //#define DEBUG
 #include "debug.h"
 
-static uint8 bitmask[8] = { 1, 1 << 1, 1 << 2, 1 << 3, 1 << 4, 1 << 5, 1 << 6, 1 << 7 };
+static const uint8 bitmask[8] = { 1, 1 << 1, 1 << 2, 1 << 3, 1 << 4, 1 << 5, 1 << 6, 1 << 7 };
 #define GETBIT(array, i) (array[(i) / 8] & bitmask[(i) % 8])
 #define SETBIT(array, i) (array[(i) / 8] |= bitmask[(i) % 8])
 #define UNSETBIT(array, i) (array[(i) / 8] &= (~(bitmask[(i) % 8])))

src/graph.h

@@ -20,9 +20,10 @@ graph_t *graph_new(uint32 nnodes, uint32 nedges);
 void graph_destroy(graph_t *graph);
 
 void graph_add_edge(graph_t *g, uint32 v1, uint32 v2);
-//void graph_del_edge(graph_t *g, uint32 v1, uint32 v2);
+void graph_del_edge(graph_t *g, uint32 v1, uint32 v2);
 void graph_clear_edges(graph_t *g);
 uint32 graph_edge_id(graph_t *g, uint32 v1, uint32 v2);
+uint8 graph_contains_edge(graph_t *g, uint32 v1, uint32 v2);
 
 graph_iterator_t graph_neighbors_it(graph_t *g, uint32 v);
 uint32 graph_next_neighbor(graph_t *g, graph_iterator_t* it);

src/hash.c

@@ -81,7 +81,7 @@ void hash_state_dump(hash_state_t *state, char **buf, uint32 *buflen)
 	memcpy(*buf, hash_names[state->hashfunc], strlen(hash_names[state->hashfunc]) + 1);
 	DEBUGP("Algobuf is %u\n", *(uint32 *)algobuf);
 	memcpy(*buf + strlen(hash_names[state->hashfunc]) + 1, algobuf, *buflen);
-	*buflen  = strlen(hash_names[state->hashfunc]) + 1 + *buflen;
+	*buflen  = (uint32)strlen(hash_names[state->hashfunc]) + 1 + *buflen;
 	free(algobuf);
 	return;
 }
@@ -100,7 +100,7 @@ hash_state_t *hash_state_load(const char *buf, uint32 buflen)
 		}
 	}
 	if (hashfunc == HASH_COUNT) return NULL;
-	offset = strlen(hash_names[hashfunc]) + 1;
+	offset = (uint32)strlen(hash_names[hashfunc]) + 1;
 	switch (hashfunc)
 	{
 		case HASH_JENKINS:

src/jenkins_hash.c

@@ -1,9 +1,11 @@
 #include "jenkins_hash.h"
 #include <stdlib.h>
+#ifdef WIN32
+#define _USE_MATH_DEFINES //For M_LOG2E
+#endif
 #include <math.h>
 #include <limits.h>
 #include <string.h>
-#include <netinet/in.h>
 
 //#define DEBUG
 #include "debug.h"
@@ -87,7 +89,7 @@ jenkins_state_t *jenkins_state_new(uint32 size) //size of hash table
 	jenkins_state_t *state = (jenkins_state_t *)malloc(sizeof(jenkins_state_t));
 	DEBUGP("Initializing jenkins hash\n");
 	state->seed = rand() % size;
-	state->nbits = ceil(log(size)/M_LOG2E);
+	state->nbits = (uint32)ceil(log(size)/M_LOG2E);
 	state->size = size;
 	DEBUGP("Initialized jenkins with size %u, nbits %u and seed %u\n", size, state->nbits, state->seed);
 	return state;
@@ -162,9 +164,6 @@ uint32 jenkins_hash(jenkins_state_t *state, const char *k, uint32 keylen)
 
 void jenkins_state_dump(jenkins_state_t *state, char **buf, uint32 *buflen)
 {
-	uint32 nseed = htonl(state->seed);
-	uint32 nnbits = htonl(state->nbits);
-	uint32 nsize = htonl(state->size);
 	*buflen = sizeof(uint32)*3;
 	*buf = malloc(*buflen);
 	if (!*buf) 
@@ -172,9 +171,9 @@ void jenkins_state_dump(jenkins_state_t *state, char **buf, uint32 *buflen)
 		*buflen = UINT_MAX;
 		return;
 	}
-	memcpy(*buf, &nseed, sizeof(uint32));
+	memcpy(*buf, &(state->seed), sizeof(uint32));
-	memcpy(*buf + sizeof(uint32), &nnbits, sizeof(uint32));
+	memcpy(*buf + sizeof(uint32), &(state->nbits), sizeof(uint32));
-	memcpy(*buf + sizeof(uint32)*2, &nsize, sizeof(uint32));
+	memcpy(*buf + sizeof(uint32)*2, &(state->size), sizeof(uint32));
 	DEBUGP("Dumped jenkins state with seed %u\n", state->seed);
 
 	return;
@@ -182,9 +181,9 @@ void jenkins_state_dump(jenkins_state_t *state, char **buf, uint32 *buflen)
 jenkins_state_t *jenkins_state_load(const char *buf, uint32 buflen)
 {
 	jenkins_state_t *state = (jenkins_state_t *)malloc(sizeof(jenkins_state_t));
-	state->seed = ntohl(*(uint32 *)buf);
+	state->seed = *(uint32 *)buf;
-	state->nbits = ntohl(*(((uint32 *)buf) + 1));
+	state->nbits = *(((uint32 *)buf) + 1);
-	state->size = ntohl(*(((uint32 *)buf) + 2));
+	state->size = *(((uint32 *)buf) + 2);
 	state->hashfunc = HASH_JENKINS;
 	DEBUGP("Loaded jenkins state with seed %u\n", state->seed);
 	return state;

src/main.c

@@ -8,7 +8,14 @@
 #include <assert.h>
 #include "cmph.h"
 #include "hash.h"
-#include "../config.h"
+#include "../wingetopt.h"
+
+#ifdef WIN32
+#define VERSION "0.2"
+#else
+#include "config.h"
+#endif
+
 
 void usage(const char *prg)
 {
@@ -47,7 +54,7 @@ static int key_read(void *data, char **key, uint32 *keylen)
 		if (feof(fd)) return -1;
 		*key = (char *)realloc(*key, *keylen + strlen(buf) + 1);
 		memcpy(*key + *keylen, buf, strlen(buf));
-		*keylen += strlen(buf);
+		*keylen += (uint32)strlen(buf);
 		if (buf[strlen(buf) - 1] != '\n') continue;
 		break;
 	}
@@ -76,7 +83,7 @@ static uint32 count_keys(FILE *fd)
 	while(1)
 	{
 		char buf[BUFSIZ];
-		char *c = fgets(buf, BUFSIZ, fd); 
+		fgets(buf, BUFSIZ, fd); 
 		if (feof(fd)) break;
 		if (buf[strlen(buf) - 1] != '\n') continue;
 		++count;
@@ -209,7 +216,7 @@ int main(int argc, char **argv)
 		return 1;
 	}
 	keys_file = argv[optind];
-	if (seed == UINT_MAX) seed = time(NULL);
+	if (seed == UINT_MAX) seed = (uint32)time(NULL);
 	srand(seed);
 
 	if (mphf_file == NULL)
@@ -219,7 +226,7 @@ int main(int argc, char **argv)
 		memcpy(mphf_file + strlen(keys_file), ".mph\0", 5);
 	}	
 
-	keys_fd = fopen64(keys_file, "r");
+	keys_fd = fopen(keys_file, "r");
 	if (keys_fd == NULL)
 	{
 		fprintf(stderr, "Unable to open file %s: %s\n", keys_file, strerror(errno));
@@ -227,7 +234,7 @@ int main(int argc, char **argv)
 	}
 
 	source.data = (void *)keys_fd;
-	if (seed == UINT_MAX) seed = time(NULL);
+	if (seed == UINT_MAX) seed = (uint32)time(NULL);
 	if(nkeys == UINT_MAX) source.nkeys = count_keys(keys_fd);
 	else source.nkeys = nkeys;
 	source.read = key_read;
@@ -242,7 +249,8 @@ int main(int argc, char **argv)
 		if (nhashes) mph_set_hashfuncs(mph, hashes);
 		mph_set_verbosity(mph, verbosity);
 		if(mph_algo == MPH_BMZ && c >= 2.0) c=1.15;
-		mphf = mph_create(mph, c);
+		if (c != 0) mph_set_graphsize(mph, c);
+		mphf = mph_create(mph);
 
 		if (mphf == NULL)
 		{

src/sdbm_hash.c

@@ -15,9 +15,9 @@ void sdbm_state_destroy(sdbm_state_t *state)
 
 uint32 sdbm_hash(sdbm_state_t *state, const char *k, uint32 keylen)
 {
-	register unsigned int hash = 0;
+	register uint32 hash = 0;
 	const unsigned char *ptr = k;
-	int i = 0;
+	uint32 i = 0;
 
 	while(i < keylen) {
 		hash = *ptr + (hash << 6) + (hash << 16) - hash;

src/vqueue.c

@@ -1,6 +1,7 @@
 #include "vqueue.h"
 #include <stdio.h>
 #include <assert.h>
+#include <stdlib.h>
 struct __vqueue_t
 {
   uint32 * values;