Mirror/zeek
1
0
Fork 0
mirror of https://github.com/zeek/zeek.git synced 2025-10-06 08:38:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 2

Add new BiF for low-level Bloom filter initialization.

Browse source 
For symmetry reasons, the new Bif bloomfilter_basic_init2 also allows users to
manually specify the memory bounds and number of hash functions to use.
This commit is contained in:
Matthias Vallentin 2013-07-31 18:21:37 +02:00
parent 8ca76dd4ee
commit d50b8a147d
4 changed files with 67 additions and 12 deletions
Download patch file Download diff file Expand all files Collapse all files

1
NEWS
View file

@ -113,6 +113,7 @@ New Functionality
the frequency of elements. The corresponding functions are:
bloomfilter_basic_init(fp: double, capacity: count, name: string &default=""): opaque of bloomfilter
bloomfilter_basic_init2(k: count, cells: count, name: string &default=""): opaque of bloomfilter
bloomfilter_counting_init(k: count, cells: count, max: count, name: string &default=""): opaque of bloomfilter
bloomfilter_add(bf: opaque of bloomfilter, x: any)
bloomfilter_lookup(bf: opaque of bloomfilter, x: any): count

69
src/probabilistic/bloom-filter.bif
View file

@ -35,8 +35,8 @@ module GLOBAL;
##
## Returns: A Bloom filter handle.
##
## .. bro:see:: bloomfilter_counting_init bloomfilter_add bloomfilter_lookup
## bloomfilter_clear bloomfilter_merge
## .. bro:see:: bloomfilter_basic_init2 bloomfilter_counting_init bloomfilter_add
## bloomfilter_lookup bloomfilter_clear bloomfilter_merge
function bloomfilter_basic_init%(fp: double, capacity: count,
name: string &default=""%): opaque of bloomfilter
%{
@ -55,6 +55,47 @@ function bloomfilter_basic_init%(fp: double, capacity: count,
return new BloomFilterVal(new BasicBloomFilter(h, cells));
%}
## Creates a basic Bloom filter. This function serves as a low-level
## alternative to bloomfilter_basic_init where the user has full control over
## the number of hash functions and cells in the underlying bit vector.
##
## .. note:: A Bloom filter can have a name associated with it. In the future,
## Bloom filters with the same name will be compatible across indepedent Bro
## instances, i.e., it will be possible to merge them. Currently, however, that is
## not yet supported.
##
## k: The number of hash functions to use.
##
## cells: The number of cells of the underlying bit vector.
##
## name: A name that uniquely identifies and seeds the Bloom filter. If empty,
## the filter will remain tied to the current Bro process.
##
## Returns: A Bloom filter handle.
##
## .. bro:see:: bloom_filter_basic_init bloomfilter_counting_init bloomfilter_add
## bloomfilter_lookup bloomfilter_clear bloomfilter_merge
function bloomfilter_basic_init2%(k: count, cells: count,
name: string &default=""%): opaque of bloomfilter
%{
if ( k == 0 )
{
reporter->Error("number of hash functions must be non-negative");
return 0;
}
if ( cells == 0 )
{
reporter->Error("number of cells must be non-negative");
return 0;
}
size_t seed = Hasher::MakeSeed(name->Len() > 0 ? name->Bytes() : 0,
name->Len());
const Hasher* h = new DefaultHasher(k, seed);
return new BloomFilterVal(new BasicBloomFilter(h, cells));
%}
## Creates a counting Bloom filter.
##
## .. note:: A Bloom filter can have a name associated with it. In the future,
@ -77,8 +118,8 @@ function bloomfilter_basic_init%(fp: double, capacity: count,
##
## Returns: A Bloom filter handle.
##
## .. bro:see:: bloomfilter_basic_init bloomfilter_add bloomfilter_lookup
## bloomfilter_clear bloomfilter_merge
## .. bro:see:: bloomfilter_basic_init bloomfilter_basic_init2 bloomfilter_add
## bloomfilter_lookup bloomfilter_clear bloomfilter_merge
function bloomfilter_counting_init%(k: count, cells: count, max: count,
name: string &default=""%): opaque of bloomfilter
%{
@ -106,8 +147,9 @@ function bloomfilter_counting_init%(k: count, cells: count, max: count,
##
## x: The element to add.
##
## .. bro:see:: bloomfilter_counting_init bloomfilter_basic_init loomfilter_lookup
## bloomfilter_clear bloomfilter_merge
## .. bro:see:: bloomfilter_basic_init bloomfilter_basic_init2
## bloomfilter_counting_init bloomfilter_lookup bloomfilter_clear
## bloomfilter_merge
function bloomfilter_add%(bf: opaque of bloomfilter, x: any%): any
%{
BloomFilterVal* bfv = static_cast<BloomFilterVal*>(bf);
@ -132,8 +174,9 @@ function bloomfilter_add%(bf: opaque of bloomfilter, x: any%): any
##
## Returns: the counter associated with *x* in *bf*.
##
## .. bro:see:: bloomfilter_counting_init bloomfilter_basic_init
## bloomfilter_add bloomfilter_clear bloomfilter_merge
## .. bro:see:: bloomfilter_basic_init bloomfilter_basic_init2
## bloomfilter_counting_init bloomfilter_add bloomfilter_clear
## bloomfilter_merge
function bloomfilter_lookup%(bf: opaque of bloomfilter, x: any%): count
%{
const BloomFilterVal* bfv = static_cast<const BloomFilterVal*>(bf);
@ -159,8 +202,9 @@ function bloomfilter_lookup%(bf: opaque of bloomfilter, x: any%): count
##
## bf: The Bloom filter handle.
##
## .. bro:see:: bloomfilter_counting_init bloomfilter_basic_init
## bloomfilter_add bloomfilter_lookup bloomfilter_merge
## .. bro:see:: bloomfilter_basic_init bloomfilter_counting_init2
## bloomfilter_counting_init bloomfilter_add bloomfilter_lookup
## bloomfilter_merge
function bloomfilter_clear%(bf: opaque of bloomfilter%): any
%{
BloomFilterVal* bfv = static_cast<BloomFilterVal*>(bf);
@ -183,8 +227,9 @@ function bloomfilter_clear%(bf: opaque of bloomfilter%): any
##
## Returns: The union of *bf1* and *bf2*.
##
## .. bro:see:: bloomfilter_counting_init bloomfilter_basic_init
## bloomfilter_add bloomfilter_lookup bloomfilter_clear
## .. bro:see:: bloomfilter_basic_init bloomfilter_basic_init2
## bloomfilter_counting_init bloomfilter_add bloomfilter_lookup
## bloomfilter_clear
function bloomfilter_merge%(bf1: opaque of bloomfilter,
bf2: opaque of bloomfilter%): opaque of bloomfilter
%{

2
testing/btest/Baseline/bifs.bloomfilter/output
View file

@ -17,6 +17,8 @@ error: false-positive rate must take value between 0 and 1
1
1
1
1
1
2
3
3

7
testing/btest/bifs/bloomfilter.bro
View file

@ -15,6 +15,13 @@ function test_basic_bloom_filter()
bloomfilter_add(bf_cnt, 0.5); # Type mismatch
bloomfilter_add(bf_cnt, "foo"); # Type mismatch
# Alternative constructor.
local bf_dbl = bloomfilter_basic_init2(4, 10);
bloomfilter_add(bf_dbl, 4.2);
bloomfilter_add(bf_dbl, 3.14);
print bloomfilter_lookup(bf_dbl, 4.2);
print bloomfilter_lookup(bf_dbl, 3.14);
# Basic usage with strings.
local bf_str = bloomfilter_basic_init(0.9, 10);
bloomfilter_add(bf_str, "foo");