bool readParamsFile(char *paramsFile)
{
FILE *pFile = fopen(paramsFile, "rt");
if (pFile == NULL) {
fprintf(stderr,
"Warning: could not open %s, will try to compute parameters "
"and write them to that file\n", paramsFile);
return true;
} else {
fscanf(pFile, "%ld\n", &nRadii);
fprintf(stderr, "Using the following R-NN DS parameters (from %s):\n", paramsFile);
fprintf(stderr, "N radii = %ld, nPoints = %ld\n", nRadii, nPoints);
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
FAILIF(NULL == (algParameters = (RNNParametersT*)MALLOC(nRadii * sizeof(RNNParametersT))));
for(IntT i = 0; i < nRadii; i++){
algParameters[i] = readRNNParameters(pFile);
printRNNParameters(stderr, algParameters[i]);
nnStructs[i] = initLSH_WithDataSet(algParameters[i], nPoints, dataSetPoints);
}
pointsDimension = algParameters[0].dimension;
if (listOfRadii != NULL) FREE(listOfRadii);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++){
listOfRadii[i] = algParameters[i].parameterR;
}
return false;
}
}
/*
Creates a new R-near neighbor data structure (PRNearNeighborStructT)
from the parameters <thresholdR> and <successProbability> for the
data set <dataSet>. <nPoints> is the number of points in the data
set and <dimension> is the dimension of the points.
The set <sampleQueries> is a set with query sample points
(R-NN DS's parameters are optimized for query points from the set
<sampleQueries>). <sampleQueries> could be a sample of points from the
actual query set or from the data set. When computing the estimated
number of collisions of a sample query point <q> with the data set
points, if there is a point in the data set with the same pointer
with <q> (that is when <q> is a data set point), then the
corresponding point (<q>) is not considered in the data set (for the
purpose of computing the respective #collisions estimation).
*/
PRNearNeighborStructT initSelfTunedRNearNeighborWithDataSet(RealT thresholdR,
RealT successProbability,
Int32T nPoints,
IntT dimension,
PPointT *dataSet,
IntT nSampleQueries,
PPointT *sampleQueries,
MemVarT memoryUpperBound){
initializeLSHGlobal();
PRNearNeighborStructT nnStruct = NULL;
RNNParametersT optParameters = computeOptimalParameters(thresholdR, successProbability, nPoints, dimension, dataSet, nSampleQueries, sampleQueries, memoryUpperBound);
if (!optParameters.useUfunctions) {
DPRINTF("Used L=%d\n", optParameters.parameterL);
}else{
DPRINTF("Used m = %d\n", optParameters.parameterM);
DPRINTF("Used L = %d\n", optParameters.parameterL);
}
TimeVarT timeInit = 0;
TIMEV_START(timeInit);
// Init the R-NN data structure.
if (optParameters.typeHT != HT_HYBRID_CHAINS){
nnStruct = initLSH(optParameters, nPoints);
}else{
printRNNParameters(DEBUG_OUTPUT, optParameters);
nnStruct = initLSH_WithDataSet(optParameters, nPoints, dataSet);
}
TIMEV_END(timeInit);
DPRINTF("Time for initializing: %0.6lf\n", timeInit);
DPRINTF("Allocated memory: %lld\n", totalAllocatedMemory);
TimeVarT timeAdding = 0;
if (optParameters.typeHT != HT_HYBRID_CHAINS){
// Add the points to the LSH buckets.
TIMEV_START(timeAdding);
for(IntT i = 0; i < nPoints; i++){
addNewPointToPRNearNeighborStruct(nnStruct, dataSet[i]);
}
TIMEV_END(timeAdding);
printf("Time for adding points: %0.6lf\n", timeAdding);
DPRINTF("Allocated memory: %lld\n", totalAllocatedMemory);
}
DPRINTF("Time for creating buckets: %0.6lf\n", timeBucketCreation);
DPRINTF("Time for putting buckets into UH: %0.6lf\n", timeBucketIntoUH);
DPRINTF("Time for computing GLSH: %0.6lf\n", timeComputeULSH);
DPRINTF("NGBuckets: %d\n", nGBuckets);
return nnStruct;
}
/*
The main entry to LSH package. Depending on the command line
parameters, the function computes the R-NN data structure optimal
parameters and/or construct the R-NN data structure and runs the
queries on the data structure.
*/
int main(int argc, char *argv[]){
FAILIF(0 != regcomp(&preg[ENUM_PPROP_FILE], "FILE:([^,]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_LINE], "LINE:([0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_OFFSET], "OFFSET:([0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_NODE_KIND], "NODE_KIND:([0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_NUM_NODE], "NUM_NODE:([0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_NUM_DECL], "NUM_DECL:([0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_NUM_STMT], "NUM_STMT:([0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_NUM_EXPR], "NUM_EXPR:([0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_TBID], "TBID:([-]?[0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_TEID], "TEID:([-]?[0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_nVARs], "VARs:\\{[^}]*\\}([0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_CONTEXT_KIND], "CONTEXT_KIND:([0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_NEIGHBOR_KIND], "NEIGHBOR_KIND:([0-9]+)", REG_EXTENDED));
FAILIF(0 != regcomp(&preg[ENUM_PPROP_OIDs], "OIDs:\\{[^}]*\\}([0-9]+)", REG_EXTENDED)); // TODO, pair-wise comparision of Vars.
//initializeLSHGlobal();
availableTotalMemory = 800000000;
// Parse part of the command-line parameters.
bool computeParameters = false;
char *paramsFile = NULL;
// Parameters for filtering:
bool no_filtering = false, bug_detecting = true;
int upperBound = 0, lowerBound = 2;
int minNumNodes = 0, min_nVars = 0;
int max_num_diff_vars = 16;
float max_num_diff_nVars_diff = 0.5, max_nVars_diff = 0.35;
bool interfiles = false;
int min_lines = 0;
for (int opt; (opt = getopt(argc, argv, "ABl:v:V:e:E:a:m:N:d:p:P:R:M:cFf:b:t:")) != -1; ) {
// Needed: -p -f -R
switch (opt) {
case 'A':
fprintf(stderr, "Warning: output all clones. Takes more time...\n");
no_filtering = true; break;
case 'B':
fprintf(stderr, "Warning: no filtering for bugs now.\n");
bug_detecting = false; break;
case 'l': min_lines = atoi(optarg); break;
case 'v': min_nVars = atoi(optarg); break;
case 'V': max_num_diff_vars = atoi(optarg); break;
case 'e': max_num_diff_nVars_diff = atof(optarg); break;
case 'E': max_nVars_diff = atof(optarg); break;
case 'm': minNumNodes = atoi(optarg); break;
case 'b': lowerBound = atoi(optarg); break;
case 't': upperBound = atoi(optarg); break;
case 'N': nPoints = atol(optarg); break;
case 'd': pointsDimension = atol(optarg); break;
case 'p': paramsFile = optarg; break;
case 'P': successProbability = atof(optarg); break;
case 'M': availableTotalMemory = atol(optarg); break;
case 'a': prefetch = atol(optarg); break;
case 'c':
fprintf(stderr, "Warning: will compute parameters\n");
computeParameters = true;
break;
case 'F':
fprintf(stderr, "Warning: inter-file clone detection. Takes more time...\n");
interfiles = true; break;
case 'R':
nRadii = 1;
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
listOfRadii[0] = strtod(optarg, NULL);
memRatiosForNNStructs[0] = 1;
break;
case 'f':
readDataSetFromFile2(optarg);
DPRINTF("Allocated memory (after reading data set): %ld\n", totalAllocatedMemory);
break;
default:
fprintf(stderr, "Unknown option: -%c\n", opt);
usage(1, argv[0]);
}
}
if (optind < argc) {
fprintf(stderr, "There are unprocessed parameters left\n");
usage(1, argv[0]);
}
CHECK_INT(availableTotalMemory);
CHECK_INT(nPoints);
CHECK_INT(pointsDimension);
CHECK_INT(nRadii);
if (nPoints > MAX_N_POINTS) {
printf("Error: the structure supports at most %ld points (%ld were specified).\n", MAX_N_POINTS, nPoints);
fprintf(ERROR_OUTPUT, "Error: the structure supports at most %ld points (%ld were specified).\n", MAX_N_POINTS, nPoints);
exit(1);
}
if (computeParameters == false)
computeParameters = readParamsFile(paramsFile);
if (computeParameters) {
IntT nSampleQueries = N_SAMPLE_QUERY_POINTS;
PPointT sampleQueries[nSampleQueries];
IntT sampleQBoundaryIndeces[nSampleQueries];
// Choose several data set points for the sample query points.
for(IntT i = 0; i < nSampleQueries; i++){
sampleQueries[i] = dataSetPoints[genRandomInt(0, nPoints - 1)];
}
// Compute the array sampleQBoundaryIndeces that specifies how to
// segregate the sample query points according to their distance
// to NN.
sortQueryPointsByRadii(pointsDimension,
nSampleQueries,
sampleQueries,
nPoints,
dataSetPoints,
nRadii,
listOfRadii,
sampleQBoundaryIndeces);
// Compute the R-NN DS parameters
// if a parameter file is given, output them to that file, and continue
// otherwise, output them to stdout, and exit
FILE *fd;
if (paramsFile == NULL) {
fd = stdout;
} else {
fd = fopen(paramsFile, "wt");
if (fd == NULL) {
fprintf(stderr, "Unable to write to parameter file %s\n", paramsFile);
exit(1);
}
}
fprintf(fd, "%ld\n", nRadii);
transformMemRatios();
for(IntT i = 0; i < nRadii; i++) {
// which sample queries to use
IntT segregatedQStart = (i == 0) ? 0 : sampleQBoundaryIndeces[i - 1];
IntT segregatedQNumber = nSampleQueries - segregatedQStart;
if (segregatedQNumber == 0) {
// XXX: not the right answer
segregatedQNumber = nSampleQueries;
segregatedQStart = 0;
}
ASSERT(segregatedQStart < nSampleQueries);
ASSERT(segregatedQStart >= 0);
ASSERT(segregatedQStart + segregatedQNumber <= nSampleQueries);
ASSERT(segregatedQNumber >= 0);
RNNParametersT optParameters = computeOptimalParameters(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
segregatedQNumber,
sampleQueries + segregatedQStart,
(UnsT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
printRNNParameters(fd, optParameters);
}
if (fd == stdout) {
exit(0);
} else {
fclose(fd);
ASSERT(readParamsFile(paramsFile) == false);
}
}
// output vector clusters according to the filtering parameters.
printf("========================= Structure built =========================\n");
printf("nPoints = %ld, Dimension = %ld\n", nPoints, pointsDimension);
printf("no_filtering (0/1) = %d, inter-file (0/1) = %d, prefetch = %ld\n", no_filtering, interfiles, prefetch);
printf("*** Filtering Parameters for individual vectors ***\n");
printf("minNumNodes = %d, min_nVars = %d, min_lines = %d\n", minNumNodes, min_nVars, min_lines);
printf("*** Filtering Parameters for clusters ***\n");
printf("lowerBound = %d, upperBound = %d\n", lowerBound, upperBound);
printf("Max num of different nVars = %d, Max diff among different nVars = %g, \nMax diff among the num of different nVars = %g\n", max_num_diff_vars, max_nVars_diff, max_num_diff_nVars_diff);
IntT resultSize = nPoints;
PPointT *result = (PPointT*)MALLOC(resultSize * sizeof(*result));
PPointT queryPoint;
FAILIF(NULL == (queryPoint = (PPointT)MALLOC(sizeof(PointT))));
FAILIF(NULL == (queryPoint->coordinates = (RealT*)MALLOC(pointsDimension * sizeof(RealT))));
TimeVarT meanQueryTime = 0;
IntT nQueries = 0;
bool seen[nPoints];
IntT nBuckets = 0, nBucketedPoints = 0;
memset(seen, 0, nPoints * sizeof(bool));
for(IntT i = 0; i < nPoints; nQueries++, i++) {
// find the next unseen point
while (i < nPoints && seen[i]) i++;
if (i >= nPoints) break;
queryPoint = dataSetPoints[i];
// get the near neighbors.
IntT nNNs = 0;
for(IntT r = 0; r < nRadii; r++) { // nRadii is always 1 so far.
nNNs = getRNearNeighbors(nnStructs[r], queryPoint, result, resultSize);
//printf("Total time for R-NN query at radius %0.6lf (radius no. %ld):\t%0.6lf\n", (double)(listOfRadii[r]), r, timeRNNQuery);
meanQueryTime += timeRNNQuery;
//printf("\nQuery point %ld: found %ld NNs at distance %0.6lf (radius no. %ld). NNs are:\n",
// i, nNNs, (double)(listOfRadii[r]), r);
// sort by filename, then number of variables, then line number
qsort(result, nNNs, sizeof(*result), comparePoints);
// The result array may contain the queryPoint, so do not output it in the following.
PPointT *cur = result, *end = result + nNNs;
if ( ! no_filtering ) { // Filter out certain vectors and clusters.
while (cur < end) { // Shall we discard the rest results
// and start over for a new point? Not
// now for the sake of
// performance...TODO
ASSERT(*cur != NULL);
// Look for the first un-filtered point for the next bucket.
while ( cur < end ) {
if ( pointIsNotFiltered(cur) ) {
break;
}
seen[(*cur)->index] = true;
cur++;
}
if ( cur >= end )
break;
bool worthy = false;
int sizeBucket = 1; // 1 means the first un-filtered point
PPointT *begin = cur;
seen[(*begin)->index] = true;
cur++;
while ( cur < end &&
// look for the next point outside the current file
// if interfiles is false; that point is the end of
// current bucket (assume vectors in a bucket are
// sorted by their filenames already).
( interfiles || strcmp((*begin)->filename, (*cur)->filename)==0 ) ) {
if ( pointIsNotFiltered(cur) ) {
// prepare for filtering
sizeBucket++;
// the first heuristics for bugs AFTER filtering:
worthy = worthy || (*begin)->prop[ENUM_PPROP_nVARs-1] != (*cur)->prop[ENUM_PPROP_nVARs-1];
// the second heuristics for bugs AFTER filtering:
worthy = worthy || inconsistentIDchanges((*begin)->oids, (*cur)->oids); // TODO
}
seen[(*cur)->index] = true;
cur++;
}
// output the bucket if:
// - there are >= 2 different points
// - there are <= upperBound (default 0) && >= lowerBound (default 2) points
// - there are >= 2 different numbers of variables
// and update nBuckets and nBucketedPoints consequently
if (sizeBucket >= lowerBound && (upperBound < lowerBound || sizeBucket <= upperBound) && ( bug_detecting ? worthy : true ) ) {
nBuckets++;
printf("\n");
for (PPointT *p = begin; p < cur; p++) {
ASSERT(*p != NULL);
if ( pointIsNotFiltered(p) ) {
nBucketedPoints++;
// compute the distance to the query point (maybe useless)
RealT distance = 0.;
for (IntT i = 0; i < pointsDimension; i++) {
RealT t = (*p)->coordinates[i] - queryPoint->coordinates[i];
// L1 distance
// distance += (t >= 0) ? t : -t;
// Pi--L2 distance, LSH uses L2 by default, we should output L2 distance here.
distance += t*t;
}
// L1 distance
// printf("%09d\tdist:%0.1lf", (*p)->index, distance);
// L2 distance
printf("%09d\tdist:%0.1lf", (*p)->index, sqrt(distance));
printf("\tFILE %s LINE:%d:%d NODE_KIND:%d nVARs:%d NUM_NODE:%d TBID:%d TEID:%d\n",
(*p)->filename, (*p)->prop[ENUM_PPROP_LINE-1], (*p)->prop[ENUM_PPROP_OFFSET-1],
(*p)->prop[ENUM_PPROP_NODE_KIND-1], (*p)->prop[ENUM_PPROP_nVARs-1],
(*p)->prop[ENUM_PPROP_NUM_NODE-1], (*p)->prop[ENUM_PPROP_TBID-1], (*p)->prop[ENUM_PPROP_TEID-1]);
//CR_ASSERT(distance(pointsDimension, queryPoint, *p) <= listOfRadii[r]);
//DPRINTF("Distance: %lf\n", distance(pointsDimension, queryPoint, result[j]));
//printRealVector("NN: ", pointsDimension, result[j]->coordinates);
}
}
} // end of enumeration of a bucket
} // end of !no_filtering
}
else {
if ( nNNs>=lowerBound ) { // filter out non-clones anyway
nBuckets++;
printf("\n");
for (PPointT *p = cur; p < end; p++) {
ASSERT(*p != NULL);
nBucketedPoints++;
seen[(*p)->index] = true;
// compute the distance to the query point (maybe useless)
RealT distance = 0.;
for (IntT i = 0; i < pointsDimension; i++) {
RealT t = (*p)->coordinates[i] - queryPoint->coordinates[i];
// L1 distance
// distance += (t >= 0) ? t : -t;
// Pi--L2 distance, LSH uses L2 by default, we should output L2 distance here.
distance += t*t;
}
// L1 distance
// printf("%09d\tdist:%0.1lf", (*p)->index, distance);
// L2 distance
printf("%09d\tdist:%0.1lf", (*p)->index, sqrt(distance));
printf("\tFILE %s LINE:%d:%d NODE_KIND:%d nVARs:%d NUM_NODE:%d TBID:%d TEID:%d\n",
(*p)->filename, (*p)->prop[ENUM_PPROP_LINE-1], (*p)->prop[ENUM_PPROP_OFFSET-1],
(*p)->prop[ENUM_PPROP_NODE_KIND-1], (*p)->prop[ENUM_PPROP_nVARs-1],
(*p)->prop[ENUM_PPROP_NUM_NODE-1], (*p)->prop[ENUM_PPROP_TBID-1], (*p)->prop[ENUM_PPROP_TEID-1]);
//CR_ASSERT(distance(pointsDimension, queryPoint, *p) <= listOfRadii[r]);
//DPRINTF("Distance: %lf\n", distance(pointsDimension, queryPoint, result[j]));
//printRealVector("NN: ", pointsDimension, result[j]->coordinates);
} // end of enumeration of a bucket
} // end of nNNs>=lowerBound
} // end of no_filtering and exploration of NNs
} // for (...nRadii...)
}
// Simple statistics and finish
if (nQueries > 0) {
meanQueryTime = meanQueryTime / nQueries;
printf("\n%ld queries, Mean query time: %0.6lf\n", nQueries, (double)meanQueryTime);
printf("%ld buckets, %ld points (out of %ld, %.2f %%) in them\n",
nBuckets, nBucketedPoints, nPoints, 100*(float)nBucketedPoints/(float)nPoints);
} else {
printf("No query\n");
}
//freePRNearNeighborStruct(nnStruct);
return 0;
}
/*
The main entry to LSH package. Depending on the command line
parameters, the function computes the R-NN data structure optimal
parameters and/or construct the R-NN data structure and runs the
queries on the data structure.
*/
int main_T(int nargs, char **args)
{
//先分析参数
/* 官方lsh文件：10个参数
1000 9 784 0.9 0.6 mnist1k.dts mnist1k.q
bin/LSHMain $nDataSet $nQuerySet $dimension $successProbability "$1" "$2" "$3" $m -c*/
//算参数 bin/LSHMain 1000 9 784 0.9 "0.6" "mnist1k.dts" "mnist1k.q" 1002000000 -c
//bin/LSHMain $nDataSet $nQuerySet $dimension $successProbability 1.0 "$1" "$2" $m -p "$3"
//匹配 bin/LSHMain 1000 9 784 0.9 1.0 "mnist1k.dts" "mnist1k.q" 1002000000 -p "outputparma.txt"
if(nargs < 9)
{
usage(args[0]);
exit(1);
}
//initializeLSHGlobal();
// Parse part of the command-line parameters.
nPoints = atoi(args[1]);
IntT nQueries = atoi(args[2]);
pointsDimension = atoi(args[3]);
successProbability = atof(args[4]);
char* endPtr[1];
RealT thresholdR = strtod(args[5], endPtr);//点相邻的距离阈值
//str-to -double 将字符串转换成浮点数的函数
//endPtr 接收数字结尾后非字符串字母
//这个r阈值是什么呢？
if (thresholdR == 0 || endPtr[1] == args[5])
{//如果阈值为0，或者第一个字符就不是数字，
//表示是用文件保存的
//这大概是用于测试哪个阈值好的
// The value for R is not specified, instead there is a file
// specifying multiple R's.
thresholdR = 0;
// Read in the file
FILE *radiiFile = fopen(args[5], "rt");
FAILIF(radiiFile == NULL);
fscanf(radiiFile, "%d\n", &nRadii);
ASSERT(nRadii > 0);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++)
{
FSCANF_REAL(radiiFile, &listOfRadii[i]);
ASSERT(listOfRadii[i] > 0);
FSCANF_REAL(radiiFile, &memRatiosForNNStructs[i]);
ASSERT(memRatiosForNNStructs[i] > 0);
}
}
else
{
nRadii = 1;
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
listOfRadii[0] = thresholdR;
memRatiosForNNStructs[0] = 1;
}//对阈值R 和Radiii的处理
DPRINTF("No. radii: %d\n", nRadii);
//thresholdR = atof(args[5]);
availableTotalMemory = atoll(args[8]);//$M表示的是内存空间大小
if (nPoints > MAX_N_POINTS)
{
printf("Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
fprintf(ERROR_OUTPUT, "Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
exit(1);
}
readDataSetFromFile(args[6]);//点读到dataSetPoints
//这个totalAllocatedMemory初始化为0，但是
//#define MALLOC(amount) ((amount > 0) ? totalAllocatedMemory += amount, malloc(amount) : NULL)
//这样，每次申请内存都会统计到了
DPRINTF("Allocated memory (after reading data set): %lld\n", totalAllocatedMemory);
Int32T nSampleQueries = N_SAMPLE_QUERY_POINTS;
PPointT sampleQueries[N_SAMPLE_QUERY_POINTS];
Int32T sampleQBoundaryIndeces[N_SAMPLE_QUERY_POINTS];
// PPointT sampleQueries[nSampleQueries];
// Int32T sampleQBoundaryIndeces[nSampleQueries];
if ((nargs <= 9) || (strcmp("-c", args[9]) == 0) )
{
// In this cases, we need to generate a sample query set for
// computing the optimal parameters.
// Generate a sample query set.
FILE *queryFile = fopen(args[7], "rt");
if (strcmp(args[7], ".") == 0 || queryFile == NULL || nQueries <= 0)
{//没有查询文件，就用所有点产生随机点
// Choose several data set points for the sample query points.
for(IntT i = 0; i < nSampleQueries; i++){
sampleQueries[i] = dataSetPoints[genRandomInt(0, nPoints - 1)];
}
}
else
{
//从查询文件中选取随机的点，
// Choose several actual query points for the sample query points.
nSampleQueries = MIN(nSampleQueries, nQueries);
Int32T sampleIndeces[N_SAMPLE_QUERY_POINTS];
//Int32T sampleIndeces[nSampleQueries];
for(IntT i = 0; i < nSampleQueries; i++)
{
sampleIndeces[i] = genRandomInt(0, nQueries - 1);
}
qsort(sampleIndeces, nSampleQueries, sizeof(*sampleIndeces), compareInt32T);
//printIntVector("sampleIndeces: ", nSampleQueries, sampleIndeces);
Int32T j = 0;
for(Int32T i = 0; i < nQueries; i++)
{
if (i == sampleIndeces[j])
{
sampleQueries[j] = readPoint(queryFile);
j++;
while (i == sampleIndeces[j])
{
sampleQueries[j] = sampleQueries[j - 1];
j++;
}
}else
{
fscanf(queryFile, "%[^\n]", sBuffer);
fscanf(queryFile, "\n");
}
}
nSampleQueries = j;
fclose(queryFile);
}
//前面那么多，好像就是在申请内存，读文件，读入参数
// Compute the array sampleQBoundaryIndeces that specifies how to
// segregate the sample query points according to their distance
// to NN.
//采用遍历的方法，计算查询点的最近邻（并且距离小于listOfRadii【nRadii】）
sortQueryPointsByRadii(pointsDimension,
nSampleQueries,
sampleQueries,
nPoints,
dataSetPoints,
nRadii,
listOfRadii,
sampleQBoundaryIndeces);
}//if ((nargs < 9) || (strcmp("-c", args[9]) == 0))
RNNParametersT *algParameters = NULL;
PRNearNeighborStructT *nnStructs = NULL;
if (nargs > 9)
{/* 官方lsh文件：10个参数
bin/LSHMain $nDataSet $nQuerySet $dimension $successProbability "$1" "$2" "$3" $m -c
*/
// Additional command-line parameter is specified.
if (strcmp("-c", args[9]) == 0) //-c表示参数优化
{
// Only compute the R-NN DS parameters and output them to stdout.
printf("%d\n", nRadii);
transformMemRatios();
for(IntT i = 0; i < nRadii; i++)
{
// which sample queries to use
Int32T segregatedQStart = (i == 0) ? 0 : sampleQBoundaryIndeces[i - 1];
Int32T segregatedQNumber = nSampleQueries - segregatedQStart;
if (segregatedQNumber == 0)
{
// XXX: not the right answer
segregatedQNumber = nSampleQueries;
segregatedQStart = 0;
}
ASSERT(segregatedQStart < nSampleQueries);
ASSERT(segregatedQStart >= 0);
ASSERT(segregatedQStart + segregatedQNumber <= nSampleQueries);
ASSERT(segregatedQNumber >= 0);
//从文件读取点，然后计算优化后的参数
RNNParametersT optParameters = computeOptimalParameters(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
segregatedQNumber,
sampleQueries + segregatedQStart,
/*对内存的约束，就体现在这里，
availableTotalMemory总共的内存（传入） - totalAllocatedMemory（使用mallloc分配的）*1=内存上限
然后(L * nPoints > memoryUpperBound / 12 来约束
*/
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
printRNNParameters(stdout, optParameters);
}
exit(0);
}
else if (strcmp("-p", args[9]) == 0)
{//-p表示从文件读入参数，然后建立结构体
// Read the R-NN DS parameters from the given file and run the
// queries on the constructed data structure.
if (nargs < 10)
{
usage(args[0]);
exit(1);
}
FILE *pFile = fopen(args[10], "rt");
FAILIFWR(pFile == NULL, "Could not open the params file.");
fscanf(pFile, "%d\n", &nRadii);
DPRINTF1("Using the following R-NN DS parameters:\n");
DPRINTF("N radii = %d\n", nRadii);
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
FAILIF(NULL == (algParameters = (RNNParametersT*)MALLOC(nRadii * sizeof(RNNParametersT))));
for(IntT i = 0; i < nRadii; i++)
{//默认i=1
algParameters[i] = readRNNParameters(pFile);//从文件读参数
printRNNParameters(stderr, algParameters[i]);
nnStructs[i] = initLSH_WithDataSet(algParameters[i], nPoints, dataSetPoints);
//核心
//初始化整个数据结构 包括整体+l个hash表 +点映射到桶
}
pointsDimension = algParameters[0].dimension;
FREE(listOfRadii);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++)
{
listOfRadii[i] = algParameters[i].parameterR;
}
}
else
{
// Wrong option.
usage(args[0]);
exit(1);
}
}//if (nargs > 9)
else
{
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
// Determine the R-NN DS parameters, construct the DS and run the queries.
transformMemRatios();
for(IntT i = 0; i < nRadii; i++)
{
// XXX: segregate the sample queries...
//建立查询结构，自动优化参数
nnStructs[i] = initSelfTunedRNearNeighborWithDataSet(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
nSampleQueries,
sampleQueries,
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
}
} // if (nargs <= 9)
//上面都是根据不同配置，对参数的优化，建立查询结构
DPRINTF1("X\n");
IntT resultSize = nPoints;
PPointT *result = (PPointT*)MALLOC(resultSize * sizeof(*result));
PPointT queryPoint;
FAILIF(NULL == (queryPoint = (PPointT)MALLOC(sizeof(PointT))));
FAILIF(NULL == (queryPoint->coordinates = (RealT*)MALLOC(pointsDimension * sizeof(RealT))));
//读取查询点的文件
FILE *queryFile = fopen(args[7], "rt");
FAILIF(queryFile == NULL);
TimeVarT meanQueryTime = 0;
PPointAndRealTStructT *distToNN = NULL;
for(IntT i = 0; i < nQueries; i++)
{//对于每一个要查询的点
RealT sqrLength = 0;
// read in the query point.
for(IntT d = 0; d < pointsDimension; d++)
{
FSCANF_REAL(queryFile, &(queryPoint->coordinates[d]));
sqrLength += SQR(queryPoint->coordinates[d]);
/*//test
if (d >150 && d<160)
{
printf(" %lf ",queryPoint->coordinates[d]);
}
if ( d==160)
{
printf("原始的文件数据\n");
}
*/
}
queryPoint->sqrLength = sqrLength;
//printRealVector("Query: ", pointsDimension, queryPoint->coordinates);
// get the near neighbors.
IntT nNNs = 0;
for(IntT r = 0; r < nRadii; r++)
{//查询n个近邻点，并计算距离
//查询核心
nNNs = getRNearNeighbors(nnStructs[r], queryPoint, result, resultSize);
printf("Total time for R-NN query at radius %0.6lf (radius no. %d):\t%0.6lf\n", (double)(listOfRadii[r]), r, timeRNNQuery);
meanQueryTime += timeRNNQuery;
if (nNNs > 0)
{
printf("Query point %d: found %d NNs at distance %0.6lf (%dth radius). First %d NNs are:\n",
i, nNNs, (double)(listOfRadii[r]), r, MIN(nNNs, MAX_REPORTED_POINTS));
// compute the distances to the found NN, and sort according to the distance
//计算近邻点和查询点的距离
FAILIF(NULL == (distToNN = (PPointAndRealTStructT*)REALLOC(distToNN, nNNs * sizeof(*distToNN))));
for(IntT p = 0; p < nNNs; p++)
{
distToNN[p].ppoint = result[p];
distToNN[p].real = distance(pointsDimension, queryPoint, result[p]);
}
qsort(distToNN, nNNs, sizeof(*distToNN), comparePPointAndRealTStructT);
// Print the points
for(IntT j = 0; j < MIN(nNNs, MAX_REPORTED_POINTS); j++)
{
ASSERT(distToNN[j].ppoint != NULL);
printf("%09d\tDistance:%0.6lf\n", distToNN[j].ppoint->index, distToNN[j].real);
CR_ASSERT(distToNN[j].real <= listOfRadii[r]);
//DPRINTF("Distance: %lf\n", distance(pointsDimension, queryPoint, result[j]));
//printRealVector("NN: ", pointsDimension, result[j]->coordinates);
}
break;
}
}
if (nNNs == 0)
{
printf("Query point %d: no NNs found.\n", i);
}
}// for(IntT i = 0; i < nQueries; i++)每个点查询
//
if (nQueries > 0)
{
meanQueryTime = meanQueryTime / nQueries;
printf("Mean query time: %0.6lf\n", (double)meanQueryTime);
}
for(IntT i = 0; i < nRadii; i++)
{
freePRNearNeighborStruct(nnStructs[i]);
}
// XXX: should ideally free the other stuff as well.
return 0;
}
/*
The main entry to LSH package. Depending on the command line
parameters, the function computes the R-NN data structure optimal
parameters and/or construct the R-NN data structure and runs the
queries on the data structure.
*/
int main(int nargs, char **args){
if(nargs < 9){
usage(args[0]);
exit(1);
}
//initializeLSHGlobal();
// Parse part of the command-line parameters.
nPoints = atoi(args[1]);
IntT nQueries = atoi(args[2]);
pointsDimension = atoi(args[3]);
successProbability = atof(args[4]);
char* endPtr[1];
RealT thresholdR = strtod(args[5], endPtr);
if (thresholdR == 0 || endPtr[1] == args[5]){
// The value for R is not specified, instead there is a file
// specifying multiple R's.
thresholdR = 0;
// Read in the file
FILE *radiiFile = fopen(args[5], "rt");
FAILIF(radiiFile == NULL);
fscanf(radiiFile, "%d\n", &nRadii);
ASSERT(nRadii > 0);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++){
FSCANF_REAL(radiiFile, &listOfRadii[i]);
ASSERT(listOfRadii[i] > 0);
FSCANF_REAL(radiiFile, &memRatiosForNNStructs[i]);
ASSERT(memRatiosForNNStructs[i] > 0);
}
}else{
nRadii = 1;
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
listOfRadii[0] = thresholdR;
memRatiosForNNStructs[0] = 1;
}
DPRINTF("No. radii: %d\n", nRadii);
//thresholdR = atof(args[5]);
availableTotalMemory = atoll(args[8]);
if (nPoints > MAX_N_POINTS) { // 104w points
printf("Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
fprintf(ERROR_OUTPUT, "Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
exit(1);
}
readDataSetFromFile(args[6]); // read points into data structure
DPRINTF("Allocated memory (after reading data set): %lld\n", totalAllocatedMemory);
Int32T nSampleQueries = N_SAMPLE_QUERY_POINTS;
PPointT sampleQueries[nSampleQueries];
Int32T sampleQBoundaryIndeces[nSampleQueries];
if ((nargs < 9) || (strcmp("-c", args[9]) == 0)){
// In this cases, we need to generate a sample query set for
// computing the optimal parameters.
// Generate a sample query set.
FILE *queryFile = fopen(args[7], "rt");
if (strcmp(args[7], ".") == 0 || queryFile == NULL || nQueries <= 0){
// Choose several data set points for the sample query points.
for(IntT i = 0; i < nSampleQueries; i++){
sampleQueries[i] = dataSetPoints[genRandomInt(0, nPoints - 1)];
}
}else{
// Choose several actual query points for the sample query points.
nSampleQueries = MIN(nSampleQueries, nQueries);
Int32T sampleIndeces[nSampleQueries];
for(IntT i = 0; i < nSampleQueries; i++){
sampleIndeces[i] = genRandomInt(0, nQueries - 1);
}
qsort(sampleIndeces, nSampleQueries, sizeof(*sampleIndeces), compareInt32T);
//printIntVector("sampleIndeces: ", nSampleQueries, sampleIndeces);
Int32T j = 0;
for(Int32T i = 0; i < nQueries; i++){
if (i == sampleIndeces[j]){
sampleQueries[j] = readPoint(queryFile);
j++;
while (i == sampleIndeces[j]){
sampleQueries[j] = sampleQueries[j - 1];
j++;
}
}else{
fscanf(queryFile, "%[^\n]", sBuffer);
fscanf(queryFile, "\n");
}
}
nSampleQueries = j;
fclose(queryFile);
}
// Compute the array sampleQBoundaryIndeces that specifies how to
// segregate the sample query points according to their distance
// to NN.
sortQueryPointsByRadii(pointsDimension,
nSampleQueries,
sampleQueries,
nPoints,
dataSetPoints,
nRadii,
listOfRadii,
sampleQBoundaryIndeces);
}
RNNParametersT *algParameters = NULL;
PRNearNeighborStructT *nnStructs = NULL;
if (nargs > 9) {
// Additional command-line parameter is specified.
if (strcmp("-c", args[9]) == 0) {
// Only compute the R-NN DS parameters and output them to stdout.
printf("%d\n", nRadii);
transformMemRatios();
for(IntT i = 0; i < nRadii; i++){
// which sample queries to use
Int32T segregatedQStart = (i == 0) ? 0 : sampleQBoundaryIndeces[i - 1];
Int32T segregatedQNumber = nSampleQueries - segregatedQStart;
if (segregatedQNumber == 0) {
// XXX: not the right answer
segregatedQNumber = nSampleQueries;
segregatedQStart = 0;
}
ASSERT(segregatedQStart < nSampleQueries);
ASSERT(segregatedQStart >= 0);
ASSERT(segregatedQStart + segregatedQNumber <= nSampleQueries);
ASSERT(segregatedQNumber >= 0);
RNNParametersT optParameters = computeOptimalParameters(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
segregatedQNumber,
sampleQueries + segregatedQStart,
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
printRNNParameters(stdout, optParameters);
}
exit(0);
} else if (strcmp("-p", args[9]) == 0) {
// Read the R-NN DS parameters from the given file and run the
// queries on the constructed data structure.
if (nargs < 10){
usage(args[0]);
exit(1);
}
FILE *pFile = fopen(args[10], "rt");
FAILIFWR(pFile == NULL, "Could not open the params file.");
fscanf(pFile, "%d\n", &nRadii);
DPRINTF1("Using the following R-NN DS parameters:\n");
DPRINTF("N radii = %d\n", nRadii);
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
FAILIF(NULL == (algParameters = (RNNParametersT*)MALLOC(nRadii * sizeof(RNNParametersT))));
for(IntT i = 0; i < nRadii; i++){
algParameters[i] = readRNNParameters(pFile);
printRNNParameters(stderr, algParameters[i]);
nnStructs[i] = initLSH_WithDataSet(algParameters[i], nPoints, dataSetPoints);
}
pointsDimension = algParameters[0].dimension;
FREE(listOfRadii);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++){
listOfRadii[i] = algParameters[i].parameterR;
}
} else{
// Wrong option.
usage(args[0]);
exit(1);
}
} else {
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
// Determine the R-NN DS parameters, construct the DS and run the queries.
transformMemRatios();
for(IntT i = 0; i < nRadii; i++){
// XXX: segregate the sample queries...
nnStructs[i] = initSelfTunedRNearNeighborWithDataSet(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
nSampleQueries,
sampleQueries,
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
}
}
DPRINTF1("X\n");
IntT resultSize = nPoints;
PPointT *result = (PPointT*)MALLOC(resultSize * sizeof(*result));
PPointT queryPoint;
FAILIF(NULL == (queryPoint = (PPointT)MALLOC(sizeof(PointT))));
FAILIF(NULL == (queryPoint->coordinates = (RealT*)MALLOC(pointsDimension * sizeof(RealT))));
FILE *queryFile = fopen(args[7], "rt");
FAILIF(queryFile == NULL);
TimeVarT meanQueryTime = 0;
PPointAndRealTStructT *distToNN = NULL;
for(IntT i = 0; i < nQueries; i++){
RealT sqrLength = 0;
// read in the query point.
for(IntT d = 0; d < pointsDimension; d++){
FSCANF_REAL(queryFile, &(queryPoint->coordinates[d]));
sqrLength += SQR(queryPoint->coordinates[d]);
}
queryPoint->sqrLength = sqrLength;
//printRealVector("Query: ", pointsDimension, queryPoint->coordinates);
// get the near neighbors.
IntT nNNs = 0;
for(IntT r = 0; r < nRadii; r++){
nNNs = getRNearNeighbors(nnStructs[r], queryPoint, result, resultSize);
printf("Total time for R-NN query at radius %0.6lf (radius no. %d):\t%0.6lf\n", (double)(listOfRadii[r]), r, timeRNNQuery);
meanQueryTime += timeRNNQuery;
if (nNNs > 0){
printf("Query point %d: found %d NNs at distance %0.6lf (%dth radius). First %d NNs are:\n", i, nNNs, (double)(listOfRadii[r]), r, MIN(nNNs, MAX_REPORTED_POINTS));
// compute the distances to the found NN, and sort according to the distance
FAILIF(NULL == (distToNN = (PPointAndRealTStructT*)REALLOC(distToNN, nNNs * sizeof(*distToNN))));
for(IntT p = 0; p < nNNs; p++){
distToNN[p].ppoint = result[p];
distToNN[p].real = distance(pointsDimension, queryPoint, result[p]);
}
qsort(distToNN, nNNs, sizeof(*distToNN), comparePPointAndRealTStructT);
// Print the points
for(IntT j = 0; j < MIN(nNNs, MAX_REPORTED_POINTS); j++){
ASSERT(distToNN[j].ppoint != NULL);
printf("%09d\tDistance:%0.6lf\n", distToNN[j].ppoint->index, distToNN[j].real);
CR_ASSERT(distToNN[j].real <= listOfRadii[r]);
//DPRINTF("Distance: %lf\n", distance(pointsDimension, queryPoint, result[j]));
//printRealVector("NN: ", pointsDimension, result[j]->coordinates);
}
break;
}
}
if (nNNs == 0){
printf("Query point %d: no NNs found.\n", i);
}
}
if (nQueries > 0){
meanQueryTime = meanQueryTime / nQueries;
printf("Mean query time: %0.6lf\n", (double)meanQueryTime);
}
for(IntT i = 0; i < nRadii; i++){
freePRNearNeighborStruct(nnStructs[i]);
}
// XXX: should ideally free the other stuff as well.
return 0;
}
/*
The main entry to LSH package. Depending on the command line
parameters, the function computes the R-NN data structure optimal
parameters and/or construct the R-NN data structure and runs the
queries on the data structure.
*/
int main(int nargs, char **args){
if(nargs < 9){
usage(args[0]);
exit(1);
}
//initializeLSHGlobal();
// Parse part of the command-line parameters.
nPoints = atoi(args[1]);
IntT nQueries = atoi(args[2]);
pointsDimension = atoi(args[3]);
successProbability = atof(args[4]);
char* endPtr[1];
RealT thresholdR = strtod(args[5], endPtr); //strtod将字符串转换成浮点数 //r=0.6
//strtod()会扫描参数nptr字符串，跳过前面的空格字符，直到遇上数字或正负符号才开始做转换
//，到出现非数字或字符串结束时('')才结束转换， 并将结果返回。
//若endptr不为NULL，则会将遇到不合条件而终止的nptr中的字符指针由endptr传回。
if (thresholdR == 0 || endPtr[1] == args[5]){ //确保阈值合法
// The value for R is not specified, instead there is a file
// specifying multiple R's.
thresholdR = 0;
// Read in the file
FILE *radiiFile = fopen(args[5], "rt");
FAILIF(radiiFile == NULL);
fscanf(radiiFile, "%d\n", &nRadii);
ASSERT(nRadii > 0);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++){
FSCANF_REAL(radiiFile, &listOfRadii[i]);
ASSERT(listOfRadii[i] > 0);
FSCANF_REAL(radiiFile, &memRatiosForNNStructs[i]);
ASSERT(memRatiosForNNStructs[i] > 0);
}
}else{
nRadii = 1; //半径的个数为1个
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
FAILIF(NULL == (memRatiosForNNStructs = (RealT*)MALLOC(nRadii * sizeof(RealT))));
listOfRadii[0] = thresholdR;
memRatiosForNNStructs[0] = 1;
}
DPRINTF("No. radii: %d\n", nRadii);
//thresholdR = atof(args[5]);
availableTotalMemory = atoll(args[8]);
if (nPoints > MAX_N_POINTS) {
printf("Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
fprintf(ERROR_OUTPUT, "Error: the structure supports at most %d points (%d were specified).\n", MAX_N_POINTS, nPoints);
exit(1);
}
readDataSetFromFile(args[6]); //数据集的文件名
DPRINTF("Allocated memory (after reading data set): %lld\n", totalAllocatedMemory);
Int32T nSampleQueries = N_SAMPLE_QUERY_POINTS; //样本查询点的个数，100
PPointT sampleQueries[nSampleQueries]; //对查询点编号
Int32T sampleQBoundaryIndeces[nSampleQueries]; //第一个大于半径的点的编号，如果有多个半径的话，就会记录更多
if ((nargs < 9) || (strcmp("-c", args[9]) == 0)){ //计算最优参数
// In this cases, we need to generate a sample query set for
// computing the optimal parameters.
// Generate a sample query set.
FILE *queryFile = fopen(args[7], "rt"); //打开查询集，以只读文本方式打开
if (strcmp(args[7], ".") == 0 || queryFile == NULL || nQueries <= 0){
// Choose several data set points for the sample query points. //如果没有查询点就随机选择几个数据集点作为查询点
for(IntT i = 0; i < nSampleQueries; i++){
sampleQueries[i] = dataSetPoints[genRandomInt(0, nPoints - 1)];
}
}else{
// Choose several actual query points for the sample query points.
nSampleQueries = MIN(nSampleQueries, nQueries); //MIN（100，9）
Int32T sampleIndeces[nSampleQueries]; //定义了一个查询点样本索引数组
for(IntT i = 0; i < nSampleQueries; i++){
////为什么要对查询点索引进行随机变化？ 想把样本查询点控制在一定的范围内，如果查询点过多，则样本点最多取100个查询点。
sampleIndeces[i] = genRandomInt(0, nQueries - 1); //对查询点做了一下顺序的变化，对查询点的索引做随机处理。
}
// 根据你给的比较条件进行快速排序，通过指针的移动实验排序，排序之后的结果仍然放在原数组中，必须自己写一个比较函数
//http://www.slyar.com/blog/stdlib-qsort.html qsort(数组起始地址，数组元素大小，每个元素的大小，函数指针指向比较函数)
qsort(sampleIndeces, nSampleQueries, sizeof(*sampleIndeces), compareInt32T); //qsort，C语言标准库函数，对样本查询点的索引值进行排序
//printIntVector("sampleIndeces: ", nSampleQueries, sampleIndeces);
Int32T j = 0;
for(Int32T i = 0; i < nQueries; i++){
if (i == sampleIndeces[j]){ //如果样本查询点的索引值与实际查询点的索引值一致，读入点
sampleQueries[j] = readPoint(queryFile);
j++;
while (i == sampleIndeces[j]){ //如果样本查询点之后的索引值与实践查询点的索引值一致，则直接将此点的值赋给后面一点的值
sampleQueries[j] = sampleQueries[j - 1]; //覆盖之后索引点的值
j++; //取后面的点
}
}else{
fscanf(queryFile, "%[^\n]", sBuffer);
fscanf(queryFile, "\n");
}
}
nSampleQueries = j;
fclose(queryFile);
}
// Compute the array sampleQBoundaryIndeces that specifies how to
// segregate the sample query points according to their distance
// to NN.
//边界sampleQBoundaryIndeces只会存取一个点的索引，该点的大小为第一个大于半径点的值
sortQueryPointsByRadii(pointsDimension,
nSampleQueries, //查询集的点的个数
sampleQueries, //查询点的集合，函数运行完成后，点的值将以距离数据集合的距离由小到大的顺序排序
nPoints, //数据集点的个数
dataSetPoints, //数据集集合
nRadii, //半径的个数
listOfRadii, //半径的值
sampleQBoundaryIndeces);
}
//之前的东西-c运行的，-p是不会运行的
RNNParametersT *algParameters = NULL;
PRNearNeighborStructT *nnStructs = NULL;
if (nargs > 9) {
// Additional command-line parameter is specified.
if (strcmp("-c", args[9]) == 0) {
// Only compute the R-NN DS parameters and output them to stdout. // 如果是-c，就只计算数据集参数，然后输出
printf("%d\n", nRadii); //打印出半径的个数：1个。 将写入到参数文件中，
transformMemRatios(); //memRatiosForNNstructs,转换内存使用率。假设每个结构为1，每个半径占用的总内存的比率，用于计算内存
for(IntT i = 0; i < nRadii; i++){ //看使用哪个样本查询点
// which sample queries to use
Int32T segregatedQStart = (i == 0) ? 0 : sampleQBoundaryIndeces[i - 1]; //起始点的位置
Int32T segregatedQNumber = nSampleQueries - segregatedQStart; //查询点的个数
if (segregatedQNumber == 0) { //如果计算所得点的个数为0，就查询所有的点，从0到最后
// XXX: not the right answer
segregatedQNumber = nSampleQueries;
segregatedQStart = 0;
}
ASSERT(segregatedQStart < nSampleQueries);
ASSERT(segregatedQStart >= 0);
ASSERT(segregatedQStart + segregatedQNumber <= nSampleQueries);
ASSERT(segregatedQNumber >= 0);
RNNParametersT optParameters = computeOptimalParameters(listOfRadii[i], //计算最优的运行时间，
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
segregatedQNumber,
sampleQueries + segregatedQStart,
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i])); //比率
////memRatioForNNStructs[i]：近邻结构体每个半径所占用的内存比率，计算能用多少内存
printRNNParameters(stdout, optParameters); //将参数打印出来
}
exit(0);
} else if (strcmp("-p", args[9]) == 0) {
// Read the R-NN DS parameters from the given file and run the
// queries on the constructed data structure.
if (nargs < 10){
usage(args[0]);
exit(1);
}
FILE *pFile = fopen(args[10], "rt"); //读取参数文件，由lsh_computeParas产生
FAILIFWR(pFile == NULL, "Could not open the params file.");
fscanf(pFile, "%d\n", &nRadii); //这里只取了参数文件中的半径，那参数文件中的其他数据怎样被取用的？？
DPRINTF1("Using the following R-NN DS parameters:\n"); //使用R-NN DS(DateSet)参数
DPRINTF("N radii = %d\n", nRadii); //不知道将数据输出到哪里了？？
// printf("Using the following R-NN DS parameters:\n");
// printf("N radii=%d\n",nRadii);
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
FAILIF(NULL == (algParameters = (RNNParametersT*)MALLOC(nRadii * sizeof(RNNParametersT))));
for(IntT i = 0; i < nRadii; i++){
algParameters[i] = readRNNParameters(pFile); //将参数信息，输出到屏幕上
// printRNNParameters(stderr, algParameters[i]);@727
//printRNNParameters(stdout,algParameters[i]);
nnStructs[i] = initLSH_WithDataSet(algParameters[i], nPoints, dataSetPoints); //根据用户输入的参数，初始化结构
}
pointsDimension = algParameters[0].dimension;
FREE(listOfRadii);
FAILIF(NULL == (listOfRadii = (RealT*)MALLOC(nRadii * sizeof(RealT))));
for(IntT i = 0; i < nRadii; i++){
listOfRadii[i] = algParameters[i].parameterR;
}
} else{
// Wrong option.
usage(args[0]);
exit(1);
}
} else {
FAILIF(NULL == (nnStructs = (PRNearNeighborStructT*)MALLOC(nRadii * sizeof(PRNearNeighborStructT))));
// Determine the R-NN DS parameters, construct the DS and run the queries.
transformMemRatios();
for(IntT i = 0; i < nRadii; i++){
// XXX: segregate the sample queries...
nnStructs[i] = initSelfTunedRNearNeighborWithDataSet(listOfRadii[i],
successProbability,
nPoints,
pointsDimension,
dataSetPoints,
nSampleQueries,
sampleQueries,
(MemVarT)((availableTotalMemory - totalAllocatedMemory) * memRatiosForNNStructs[i]));
}
}
// DPRINTF1("X\n");@
printf("X\n");
IntT resultSize = nPoints;
PPointT *result = (PPointT*)MALLOC(resultSize * sizeof(*result));
PPointT queryPoint;
FAILIF(NULL == (queryPoint = (PPointT)MALLOC(sizeof(PointT))));
FAILIF(NULL == (queryPoint->coordinates = (RealT*)MALLOC(pointsDimension * sizeof(RealT))));
FILE *queryFile = fopen(args[7], "rt");
FAILIF(queryFile == NULL);
TimeVarT meanQueryTime = 0;
PPointAndRealTStructT *distToNN = NULL;
for(IntT i = 0; i < nQueries; i++){
RealT sqrLength = 0;
// read in the query point.
for(IntT d = 0; d < pointsDimension; d++){
FSCANF_REAL(queryFile, &(queryPoint->coordinates[d]));
sqrLength += SQR(queryPoint->coordinates[d]); //向量到原点的距离
}
queryPoint->sqrLength = sqrLength;
//printRealVector("Query: ", pointsDimension, queryPoint->coordinates);
// get the near neighbors.
IntT nNNs = 0;
for(IntT r = 0; r < nRadii; r++){
nNNs = getRNearNeighbors(nnStructs[r], queryPoint, result, resultSize);
printf("Total time for R-NN query at radius %0.6lf (radius no. %d):\t%0.6lf\n", (double)(listOfRadii[r]), r, timeRNNQuery);
meanQueryTime += timeRNNQuery;
if (nNNs > 0){
printf("Query point %d: found %d NNs at distance %0.6lf (%dth radius). First %d NNs are:\n", i, nNNs, (double)(listOfRadii[r]), r, MIN(nNNs, MAX_REPORTED_POINTS));
// compute the distances to the found NN, and sort according to the distance
FAILIF(NULL == (distToNN = (PPointAndRealTStructT*)REALLOC(distToNN, nNNs * sizeof(*distToNN))));
for(IntT p = 0; p < nNNs; p++){
distToNN[p].ppoint = result[p];
distToNN[p].real = distance(pointsDimension, queryPoint, result[p]);
}
qsort(distToNN, nNNs, sizeof(*distToNN), comparePPointAndRealTStructT); //C语言标准的函数
// Print the points
for(IntT j = 0; j < MIN(nNNs, MAX_REPORTED_POINTS); j++){
ASSERT(distToNN[j].ppoint != NULL);
printf("%09d\tDistance:%0.6lf\n", distToNN[j].ppoint->index, distToNN[j].real); //打印点的坐标
CR_ASSERT(distToNN[j].real <= listOfRadii[r]);
//DPRINTF("Distance: %lf\n", distance(pointsDimension, queryPoint, result[j]));
//printRealVector("NN: ", pointsDimension, result[j]->coordinates);
}
break;
}
}
if (nNNs == 0){
printf("Query point %d: no NNs found.\n", i);
}
}
if (nQueries > 0){
meanQueryTime = meanQueryTime / nQueries;
printf("Mean query time: %0.6lf\n", (double)meanQueryTime);
}
for(IntT i = 0; i < nRadii; i++){
freePRNearNeighborStruct(nnStructs[i]);
}
// XXX: should ideally free the other stuff as well.
return 0;
}