mirror of
https://github.com/zeek/zeek.git
synced 2025-10-10 02:28:21 +00:00
Reformat the world
This commit is contained in:
Tim Wojtulewicz
parent
194cb24547
commit
b2f171ec69
714 changed files with 35149 additions and 35203 deletions
|
|
@ -1,20 +1,20 @@
|
|||
// See the file "COPYING" in the main distribution directory for copyright.
|
||||
|
||||
#include "zeek/zeek-config.h"
|
||||
#include "zeek/SmithWaterman.h"
|
||||
|
||||
#include <ctype.h>
|
||||
#include <algorithm>
|
||||
|
||||
#include "zeek/SmithWaterman.h"
|
||||
#include "zeek/Var.h"
|
||||
#include "zeek/util.h"
|
||||
#include "zeek/Reporter.h"
|
||||
#include "zeek/Val.h"
|
||||
#include "zeek/Var.h"
|
||||
#include "zeek/util.h"
|
||||
#include "zeek/zeek-config.h"
|
||||
|
||||
namespace zeek::detail {
|
||||
namespace zeek::detail
|
||||
{
|
||||
|
||||
Substring::Substring(const Substring& bst)
|
||||
: String((const String&) bst), _num(), _new(bst._new)
|
||||
Substring::Substring(const Substring& bst) : String((const String&)bst), _num(), _new(bst._new)
|
||||
{
|
||||
for ( const auto& align : bst._aligns )
|
||||
_aligns.push_back(align);
|
||||
|
|
@ -51,7 +51,7 @@ bool Substring::DoesCover(const Substring* bst) const
|
|||
const BSSAlign& a = *it;
|
||||
const BSSAlign& a_bst = *it_bst;
|
||||
|
||||
if (a.index > a_bst.index || a.index + Len() < a_bst.index + bst->Len())
|
||||
if ( a.index > a_bst.index || a.index + Len() < a_bst.index + bst->Len() )
|
||||
return false;
|
||||
}
|
||||
|
||||
|
|
@ -163,19 +163,15 @@ String::IdxVec* Substring::GetOffsetsVec(const Vec* vec, unsigned int index)
|
|||
return result;
|
||||
}
|
||||
|
||||
|
||||
bool SubstringCmp::operator()(const Substring* bst1,
|
||||
const Substring* bst2) const
|
||||
bool SubstringCmp::operator()(const Substring* bst1, const Substring* bst2) const
|
||||
{
|
||||
if ( _index >= bst1->GetNumAlignments() ||
|
||||
_index >= bst2->GetNumAlignments() )
|
||||
if ( _index >= bst1->GetNumAlignments() || _index >= bst2->GetNumAlignments() )
|
||||
{
|
||||
reporter->Warning("SubstringCmp::operator(): invalid index for input strings.\n");
|
||||
return false;
|
||||
}
|
||||
|
||||
if ( bst1->GetAlignments()[_index].index <=
|
||||
bst2->GetAlignments()[_index].index )
|
||||
if ( bst1->GetAlignments()[_index].index <= bst2->GetAlignments()[_index].index )
|
||||
return true;
|
||||
|
||||
return false;
|
||||
|
|
@ -187,7 +183,8 @@ bool SubstringCmp::operator()(const Substring* bst1,
|
|||
// one up and left in case of a match, or a jump somewhere above and
|
||||
// left in case of a gap.
|
||||
//
|
||||
struct SWNode {
|
||||
struct SWNode
|
||||
{
|
||||
// ID field for the cell, for debugging purposes.
|
||||
int id;
|
||||
|
||||
|
|
@ -201,20 +198,21 @@ struct SWNode {
|
|||
|
||||
// Pointer to previous match, walking back yields subsequence.
|
||||
SWNode* swn_prev;
|
||||
};
|
||||
};
|
||||
|
||||
// A matrix of Smith-Waterman nodes.
|
||||
//
|
||||
class SWNodeMatrix {
|
||||
class SWNodeMatrix
|
||||
{
|
||||
public:
|
||||
SWNodeMatrix(const String* s1, const String* s2)
|
||||
: _s1(s1), _s2(s2), _rows(s1->Len() + 1), _cols(s2->Len() + 1)
|
||||
: _s1(s1), _s2(s2), _rows(s1->Len() + 1), _cols(s2->Len() + 1)
|
||||
{
|
||||
_nodes = new SWNode[_cols * _rows];
|
||||
memset(_nodes, 0, sizeof(SWNode) * _cols * _rows);
|
||||
}
|
||||
|
||||
~SWNodeMatrix() { delete [] _nodes; }
|
||||
~SWNodeMatrix() { delete[] _nodes; }
|
||||
|
||||
SWNode* operator()(int row, int col)
|
||||
{
|
||||
|
|
@ -227,11 +225,11 @@ public:
|
|||
return &(_nodes[row * _cols + col]);
|
||||
}
|
||||
|
||||
const String* GetRowsString() const { return _s1; }
|
||||
const String* GetColsString() const { return _s2; }
|
||||
const String* GetRowsString() const { return _s1; }
|
||||
const String* GetColsString() const { return _s2; }
|
||||
|
||||
int GetHeight() const { return _rows; }
|
||||
int GetWidth() const { return _cols; }
|
||||
int GetHeight() const { return _rows; }
|
||||
int GetWidth() const { return _cols; }
|
||||
|
||||
// Quick helper function that calculates the coordinates of a
|
||||
// node in the matrix via pointer arithmetic.
|
||||
|
|
@ -250,7 +248,7 @@ private:
|
|||
|
||||
int _rows, _cols;
|
||||
SWNode* _nodes;
|
||||
};
|
||||
};
|
||||
|
||||
// Returns the common subsequence starting from a given node.
|
||||
// @result: vector holding results on return.
|
||||
|
|
@ -258,15 +256,15 @@ private:
|
|||
// @node: starting node.
|
||||
// @params: SW parameters.
|
||||
//
|
||||
static void sw_collect_single(Substring::Vec* result, SWNodeMatrix& matrix,
|
||||
SWNode* node, SWParams& params)
|
||||
static void sw_collect_single(Substring::Vec* result, SWNodeMatrix& matrix, SWNode* node,
|
||||
SWParams& params)
|
||||
{
|
||||
std::string substring("");
|
||||
int row = 0, col = 0;
|
||||
|
||||
while ( node )
|
||||
{
|
||||
// printf("NODE: %i\n", node->id);
|
||||
// printf("NODE: %i\n", node->id);
|
||||
node->swn_visited = true;
|
||||
|
||||
// Once we hit a gap, terminate the string and prepend
|
||||
|
|
@ -277,17 +275,17 @@ static void sw_collect_single(Substring::Vec* result, SWNodeMatrix& matrix,
|
|||
{
|
||||
matrix.GetNodeIndices(node, row, col);
|
||||
substring += node->swn_byte;
|
||||
// printf("SUBSTRING: %s\n", substring.c_str());
|
||||
// printf("SUBSTRING: %s\n", substring.c_str());
|
||||
}
|
||||
else
|
||||
{
|
||||
// printf("GAP\n");
|
||||
// printf("GAP\n");
|
||||
if ( substring.size() >= params._min_toklen )
|
||||
{
|
||||
reverse(substring.begin(), substring.end());
|
||||
auto* bst = new Substring(substring);
|
||||
bst->AddAlignment(matrix.GetRowsString(), row-1);
|
||||
bst->AddAlignment(matrix.GetColsString(), col-1);
|
||||
bst->AddAlignment(matrix.GetRowsString(), row - 1);
|
||||
bst->AddAlignment(matrix.GetColsString(), col - 1);
|
||||
result->push_back(bst);
|
||||
}
|
||||
|
||||
|
|
@ -304,8 +302,8 @@ static void sw_collect_single(Substring::Vec* result, SWNodeMatrix& matrix,
|
|||
{
|
||||
reverse(substring.begin(), substring.end());
|
||||
auto* bst = new Substring(substring);
|
||||
bst->AddAlignment(matrix.GetRowsString(), row-1);
|
||||
bst->AddAlignment(matrix.GetColsString(), col-1);
|
||||
bst->AddAlignment(matrix.GetRowsString(), row - 1);
|
||||
bst->AddAlignment(matrix.GetColsString(), col - 1);
|
||||
result->push_back(bst);
|
||||
}
|
||||
|
||||
|
|
@ -322,8 +320,7 @@ static void sw_collect_single(Substring::Vec* result, SWNodeMatrix& matrix,
|
|||
// common subsequences while tracking which nodes were visited earlier and which
|
||||
// substrings are redundant (i.e., fully covered by a larger common substring).
|
||||
//
|
||||
static void sw_collect_multiple(Substring::Vec* result,
|
||||
SWNodeMatrix& matrix, SWParams& params)
|
||||
static void sw_collect_multiple(Substring::Vec* result, SWNodeMatrix& matrix, SWParams& params)
|
||||
{
|
||||
std::vector<Substring::Vec*> als;
|
||||
|
||||
|
|
@ -367,7 +364,7 @@ static void sw_collect_multiple(Substring::Vec* result,
|
|||
}
|
||||
}
|
||||
|
||||
end_loop:
|
||||
end_loop:
|
||||
if ( new_al )
|
||||
als.push_back(new_al);
|
||||
}
|
||||
|
|
@ -387,13 +384,12 @@ end_loop:
|
|||
|
||||
// The main Smith-Waterman algorithm.
|
||||
//
|
||||
Substring::Vec* smith_waterman(const String* s1, const String* s2,
|
||||
SWParams& params)
|
||||
Substring::Vec* smith_waterman(const String* s1, const String* s2, SWParams& params)
|
||||
{
|
||||
auto* result = new Substring::Vec();
|
||||
|
||||
if ( ! s1 || s1->Len() < int(params._min_toklen) ||
|
||||
! s2 || s2->Len() < int(params._min_toklen) )
|
||||
if ( ! s1 || s1->Len() < int(params._min_toklen) || ! s2 ||
|
||||
s2->Len() < int(params._min_toklen) )
|
||||
return result;
|
||||
|
||||
// Length of both strings, plus one because SW needs
|
||||
|
|
@ -407,9 +403,9 @@ Substring::Vec* smith_waterman(const String* s1, const String* s2,
|
|||
byte_vec string1 = s1->Bytes();
|
||||
byte_vec string2 = s2->Bytes();
|
||||
|
||||
SWNodeMatrix matrix(s1, s2); // dynamic programming matrix.
|
||||
SWNode* node_max = nullptr; // pointer to the best score's node
|
||||
SWNode* node_br_max = nullptr; // pointer to lowest-right matching node
|
||||
SWNodeMatrix matrix(s1, s2); // dynamic programming matrix.
|
||||
SWNode* node_max = nullptr; // pointer to the best score's node
|
||||
SWNode* node_br_max = nullptr; // pointer to lowest-right matching node
|
||||
|
||||
// The highest score in the matrix, globally. We initialize to 1
|
||||
// because we are only interested in real scores (initializing to
|
||||
|
|
@ -420,7 +416,6 @@ Substring::Vec* smith_waterman(const String* s1, const String* s2,
|
|||
int br_max_r = 0;
|
||||
int br_max_b = 0;
|
||||
|
||||
|
||||
// Matrix initialization ----------------------------------------------
|
||||
|
||||
// Assign IDs to each cell -- this is only for debugging purposes
|
||||
|
|
@ -441,9 +436,9 @@ Substring::Vec* smith_waterman(const String* s1, const String* s2,
|
|||
// Current node, top/left neighbours.
|
||||
//
|
||||
SWNode* current = matrix(i, j);
|
||||
SWNode* node_tl = matrix(i-1, j-1);
|
||||
SWNode* node_l = matrix(i, j-1);
|
||||
SWNode* node_t = matrix(i-1, j);
|
||||
SWNode* node_tl = matrix(i - 1, j - 1);
|
||||
SWNode* node_l = matrix(i, j - 1);
|
||||
SWNode* node_t = matrix(i - 1, j);
|
||||
|
||||
// Scores of neighbouring nodes.
|
||||
//
|
||||
|
|
@ -456,7 +451,7 @@ Substring::Vec* smith_waterman(const String* s1, const String* s2,
|
|||
// are necessary since matrix has one extra
|
||||
// row + column.
|
||||
//
|
||||
if ( string1[i-1] == string2[j-1] )
|
||||
if ( string1[i - 1] == string2[j - 1] )
|
||||
{
|
||||
// We have a match: improve previous score.
|
||||
//
|
||||
|
|
@ -472,7 +467,7 @@ Substring::Vec* smith_waterman(const String* s1, const String* s2,
|
|||
// Store the byte we've matched in the node for
|
||||
// easier access.
|
||||
//
|
||||
current->swn_byte = string1[i-1];
|
||||
current->swn_byte = string1[i - 1];
|
||||
current->swn_byte_assigned = true;
|
||||
}
|
||||
|
||||
|
|
@ -487,8 +482,7 @@ Substring::Vec* smith_waterman(const String* s1, const String* s2,
|
|||
// Establish predecessor chain according to neighbor
|
||||
// with best score.
|
||||
//
|
||||
if ( current->swn_score == score_tl &&
|
||||
current->swn_byte_assigned )
|
||||
if ( current->swn_score == score_tl && current->swn_byte_assigned )
|
||||
{
|
||||
// If we had matched bytes (*and* it's the
|
||||
// best neighbor), marke the node accordingly
|
||||
|
|
@ -526,7 +520,7 @@ Substring::Vec* smith_waterman(const String* s1, const String* s2,
|
|||
current->swn_prev ? current->swn_prev->id : 0,
|
||||
string1[i-1], string2[j-1]);
|
||||
#endif
|
||||
//printf("%.5i ", current->swn_score);
|
||||
// printf("%.5i ", current->swn_score);
|
||||
}
|
||||
|
||||
#if 0
|
||||
|
|
@ -554,4 +548,4 @@ Substring::Vec* smith_waterman(const String* s1, const String* s2,
|
|||
return result;
|
||||
}
|
||||
|
||||
} // namespace zeek::detail
|
||||
} // namespace zeek::detail
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue