Skip to content

Commit a5e76e3

Browse files
committed
added test for inward edges and avoid changing test order
1 parent 686685b commit a5e76e3

17 files changed

+382
-323
lines changed

gfalibs

src/generate-tests.cpp

+4-3
Original file line numberDiff line numberDiff line change
@@ -33,9 +33,9 @@ int main(void) {
3333
};
3434

3535
const std::set<std::string> excludeExt {};
36-
const std::set<std::string> excludeFile {"random4.fasta", "random4.fastq", "random5.fasta", "random5.fastq", "random6.fastq", "random7.fastq", "random8.fastq", "random9.fastq", "random10.fastq", "random11.fasta", "random11.fastq", "to_correct.fasta", "to_correct.fastq", "decompressor1.fasta", "repeat1.fasta", "repeat1.fastq"};
36+
const std::set<std::string> excludeFile {"random4.fasta", "random4.fastq", "random5.fasta", "random5.fastq", "random6.fastq", "random7.fastq", "random8.fastq", "random9.fastq", "random10.fastq", "random11.fasta", "random11.fastq", "random12.fasta", "random12.fastq", "to_correct.fasta", "to_correct.fastq", "decompressor1.fasta", "repeat1.fasta", "repeat1.fastq"};
3737

38-
std::map<std::set<std::string>, std::vector<std::string>> file_args = {
38+
std::vector<std::pair<std::set<std::string>, std::vector<std::string>>> file_args = {
3939
{{"-f testFiles/random1.fasta"}, {"-r testFiles/random3.N.fastq", "-d testFiles/test1.kreeq", "-d testFiles/test2.kreeq"}},
4040
{{"-f testFiles/random4.fasta"}, {"-r testFiles/random4.fastq -k3"}},
4141
{{"-f testFiles/to_correct.fasta"}, {"-r testFiles/to_correct.fastq", "-r testFiles/to_correct.fastq -o gfa", "-r testFiles/to_correct.fastq -o vcf", "-r testFiles/to_correct.fastq -o vcf -p testFiles/random1.anomalies.bed"}}
@@ -90,7 +90,8 @@ int main(void) {
9090
{{"-d testFiles/random10.kreeq -f testFiles/random5.fasta --search-depth 15 --traversal-algorithm traversal"}, {""}},
9191
{{"-d testFiles/random10.kreeq -f testFiles/random5.fasta --search-depth 16 --traversal-algorithm traversal"}, {""}},
9292
{{"-d testFiles/random10.kreeq -f testFiles/random5.fasta --search-depth 32 --traversal-algorithm best-first"}, {""}},
93-
{{"-d testFiles/random11.kreeq -f testFiles/random11.fasta --search-depth 32 --traversal-algorithm best-first --no-collapse"}, {""}}
93+
{{"-d testFiles/random11.kreeq -f testFiles/random11.fasta --search-depth 32 --traversal-algorithm best-first --no-collapse"}, {""}},
94+
{{"-d testFiles/random12.kreeq -f testFiles/random12.fasta --search-depth 21 --traversal-algorithm best-first --no-collapse"}, {""}}
9495
// {{set of test inputs}, {list of command line args to run with}}
9596
};
9697
for(const auto &pair : file_args) {

src/kreeq.cpp

+1-1
Original file line numberDiff line numberDiff line change
@@ -887,7 +887,7 @@ void DBG::nextKmerFromString(uint8_t *nextKmer, std::string *sequence, uint64_t
887887

888888
}
889889

890-
bool DBG::isKeyFw(uint64_t key) {
890+
bool DBG::isKeyFw(uint64_t key) { // this doesn't make any sense
891891
bool isFw;
892892
std::string kmer = reverseHash(key);
893893
uint8_t thisKmer[k];

validateFiles/test.36.tst

+18-18
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,11 @@
1-
kreeq subgraph -d testFiles/random10.kreeq -f testFiles/random5.fasta --search-depth 15 --traversal-algorithm traversal
1+
kreeq subgraph -d testFiles/test1.kreeq -f testFiles/random1.fasta --search-depth 0 --no-collapse
22
embedded
33
Subgraph summary statistics:
4-
Total kmers: 157
5-
Unique kmers: 61
6-
Distinct kmers: 109
7-
Missing kmers: 4398046510995
8-
Total edges: 184
4+
Total kmers: 1156
5+
Unique kmers: 168
6+
Distinct kmers: 260
7+
Missing kmers: 4398046510844
8+
Total edges: 446
99
+++Assembly summary+++:
1010
# scaffolds: 0
1111
Total scaffold length: 0
@@ -34,25 +34,25 @@ Smallest gap in scaffolds: 0
3434
Base composition (A:C:G:T): 0:0:0:0
3535
GC content %: nan
3636
# soft-masked bases: 0
37-
# segments: 5
38-
Total segment length: 209
39-
Average segment length: 41.80
37+
# segments: 260
38+
Total segment length: 5460
39+
Average segment length: 21.00
4040
# gaps: 0
4141
# paths: 0
42-
# edges: 4
43-
Average degree: 0.80
42+
# edges: 520
43+
Average degree: 2.00
4444
# connected components: 1
45-
Largest connected component length: 209
46-
# dead ends: 4
45+
Largest connected component length: 5460
46+
# dead ends: 2
4747
# disconnected components: 0
4848
Total length disconnected components: 0
4949
# separated components: 1
5050
# bubbles: 0
5151
# circular segments: 0
5252
# circular paths: 0
5353
DBG Summary statistics:
54-
Total kmers: 158
55-
Unique kmers: 62
56-
Distinct kmers: 110
57-
Missing kmers: 4398046510994
58-
Total edges: 188
54+
Total kmers: 172
55+
Unique kmers: 25
56+
Distinct kmers: 96
57+
Missing kmers: 4398046511008
58+
Total edges: 160

validateFiles/test.37.tst

+15-15
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,11 @@
1-
kreeq subgraph -d testFiles/random10.kreeq -f testFiles/random5.fasta --search-depth 16 --traversal-algorithm traversal
1+
kreeq subgraph -d testFiles/random5.kreeq -f testFiles/random5.fasta --no-collapse
22
embedded
33
Subgraph summary statistics:
44
Total kmers: 158
5-
Unique kmers: 62
6-
Distinct kmers: 110
7-
Missing kmers: 4398046510994
8-
Total edges: 188
5+
Unique kmers: 84
6+
Distinct kmers: 121
7+
Missing kmers: 4398046510983
8+
Total edges: 203
99
+++Assembly summary+++:
1010
# scaffolds: 0
1111
Total scaffold length: 0
@@ -34,15 +34,15 @@ Smallest gap in scaffolds: 0
3434
Base composition (A:C:G:T): 0:0:0:0
3535
GC content %: nan
3636
# soft-masked bases: 0
37-
# segments: 4
38-
Total segment length: 190
39-
Average segment length: 47.50
37+
# segments: 121
38+
Total segment length: 2541
39+
Average segment length: 21.00
4040
# gaps: 0
4141
# paths: 0
42-
# edges: 4
43-
Average degree: 1.00
42+
# edges: 244
43+
Average degree: 2.02
4444
# connected components: 1
45-
Largest connected component length: 190
45+
Largest connected component length: 2541
4646
# dead ends: 2
4747
# disconnected components: 0
4848
Total length disconnected components: 0
@@ -52,7 +52,7 @@ Total length disconnected components: 0
5252
# circular paths: 0
5353
DBG Summary statistics:
5454
Total kmers: 158
55-
Unique kmers: 62
56-
Distinct kmers: 110
57-
Missing kmers: 4398046510994
58-
Total edges: 188
55+
Unique kmers: 84
56+
Distinct kmers: 121
57+
Missing kmers: 4398046510983
58+
Total edges: 203

validateFiles/test.38.tst

+16-16
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,11 @@
1-
kreeq subgraph -d testFiles/random10.kreeq -f testFiles/random5.fasta --search-depth 32 --traversal-algorithm best-first
1+
kreeq subgraph -d testFiles/random5.kreeq -f testFiles/random5.fasta
22
embedded
33
Subgraph summary statistics:
44
Total kmers: 158
5-
Unique kmers: 62
6-
Distinct kmers: 110
7-
Missing kmers: 4398046510994
8-
Total edges: 188
5+
Unique kmers: 84
6+
Distinct kmers: 121
7+
Missing kmers: 4398046510983
8+
Total edges: 203
99
+++Assembly summary+++:
1010
# scaffolds: 0
1111
Total scaffold length: 0
@@ -34,25 +34,25 @@ Smallest gap in scaffolds: 0
3434
Base composition (A:C:G:T): 0:0:0:0
3535
GC content %: nan
3636
# soft-masked bases: 0
37-
# segments: 4
38-
Total segment length: 190
39-
Average segment length: 47.50
37+
# segments: 7
38+
Total segment length: 261
39+
Average segment length: 37.29
4040
# gaps: 0
4141
# paths: 0
42-
# edges: 4
43-
Average degree: 1.00
42+
# edges: 8
43+
Average degree: 1.14
4444
# connected components: 1
45-
Largest connected component length: 190
45+
Largest connected component length: 261
4646
# dead ends: 2
4747
# disconnected components: 0
4848
Total length disconnected components: 0
4949
# separated components: 1
50-
# bubbles: 0
50+
# bubbles: 2
5151
# circular segments: 0
5252
# circular paths: 0
5353
DBG Summary statistics:
5454
Total kmers: 158
55-
Unique kmers: 62
56-
Distinct kmers: 110
57-
Missing kmers: 4398046510994
58-
Total edges: 188
55+
Unique kmers: 84
56+
Distinct kmers: 121
57+
Missing kmers: 4398046510983
58+
Total edges: 203

validateFiles/test.39.tst

+17-17
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,11 @@
1-
kreeq subgraph -d testFiles/random11.kreeq -f testFiles/random11.fasta --search-depth 32 --traversal-algorithm best-first --no-collapse
1+
kreeq subgraph -d testFiles/random6.kreeq -f testFiles/random5.fasta
22
embedded
33
Subgraph summary statistics:
4-
Total kmers: 110
5-
Unique kmers: 110
6-
Distinct kmers: 110
7-
Missing kmers: 4398046510994
8-
Total edges: 186
4+
Total kmers: 159
5+
Unique kmers: 41
6+
Distinct kmers: 100
7+
Missing kmers: 4398046511004
8+
Total edges: 173
99
+++Assembly summary+++:
1010
# scaffolds: 0
1111
Total scaffold length: 0
@@ -34,15 +34,15 @@ Smallest gap in scaffolds: 0
3434
Base composition (A:C:G:T): 0:0:0:0
3535
GC content %: nan
3636
# soft-masked bases: 0
37-
# segments: 110
38-
Total segment length: 2310
39-
Average segment length: 21.00
37+
# segments: 4
38+
Total segment length: 180
39+
Average segment length: 45.00
4040
# gaps: 0
4141
# paths: 0
42-
# edges: 218
43-
Average degree: 1.98
42+
# edges: 4
43+
Average degree: 1.00
4444
# connected components: 1
45-
Largest connected component length: 2310
45+
Largest connected component length: 180
4646
# dead ends: 2
4747
# disconnected components: 0
4848
Total length disconnected components: 0
@@ -51,8 +51,8 @@ Total length disconnected components: 0
5151
# circular segments: 0
5252
# circular paths: 0
5353
DBG Summary statistics:
54-
Total kmers: 79
55-
Unique kmers: 79
56-
Distinct kmers: 79
57-
Missing kmers: 4398046511025
58-
Total edges: 132
54+
Total kmers: 159
55+
Unique kmers: 41
56+
Distinct kmers: 100
57+
Missing kmers: 4398046511004
58+
Total edges: 173

validateFiles/test.40.tst

+18-18
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,11 @@
1-
kreeq subgraph -d testFiles/random5.kreeq -f testFiles/random5.fasta
1+
kreeq subgraph -d testFiles/random7.kreeq -f testFiles/random5.fasta
22
embedded
33
Subgraph summary statistics:
4-
Total kmers: 158
5-
Unique kmers: 84
6-
Distinct kmers: 121
7-
Missing kmers: 4398046510983
8-
Total edges: 203
4+
Total kmers: 157
5+
Unique kmers: 41
6+
Distinct kmers: 99
7+
Missing kmers: 4398046511005
8+
Total edges: 170
99
+++Assembly summary+++:
1010
# scaffolds: 0
1111
Total scaffold length: 0
@@ -34,25 +34,25 @@ Smallest gap in scaffolds: 0
3434
Base composition (A:C:G:T): 0:0:0:0
3535
GC content %: nan
3636
# soft-masked bases: 0
37-
# segments: 7
38-
Total segment length: 261
39-
Average segment length: 37.29
37+
# segments: 4
38+
Total segment length: 179
39+
Average segment length: 44.75
4040
# gaps: 0
4141
# paths: 0
42-
# edges: 8
43-
Average degree: 1.14
42+
# edges: 4
43+
Average degree: 1.00
4444
# connected components: 1
45-
Largest connected component length: 261
45+
Largest connected component length: 179
4646
# dead ends: 2
4747
# disconnected components: 0
4848
Total length disconnected components: 0
4949
# separated components: 1
50-
# bubbles: 2
50+
# bubbles: 0
5151
# circular segments: 0
5252
# circular paths: 0
5353
DBG Summary statistics:
54-
Total kmers: 158
55-
Unique kmers: 84
56-
Distinct kmers: 121
57-
Missing kmers: 4398046510983
58-
Total edges: 203
54+
Total kmers: 157
55+
Unique kmers: 41
56+
Distinct kmers: 99
57+
Missing kmers: 4398046511005
58+
Total edges: 170

validateFiles/test.41.tst

+17-17
Original file line numberDiff line numberDiff line change
@@ -1,11 +1,11 @@
1-
kreeq subgraph -d testFiles/random5.kreeq -f testFiles/random5.fasta --no-collapse
1+
kreeq subgraph -d testFiles/random8.kreeq -f testFiles/random5.fasta
22
embedded
33
Subgraph summary statistics:
4-
Total kmers: 158
5-
Unique kmers: 84
6-
Distinct kmers: 121
7-
Missing kmers: 4398046510983
8-
Total edges: 203
4+
Total kmers: 159
5+
Unique kmers: 35
6+
Distinct kmers: 97
7+
Missing kmers: 4398046511007
8+
Total edges: 165
99
+++Assembly summary+++:
1010
# scaffolds: 0
1111
Total scaffold length: 0
@@ -34,15 +34,15 @@ Smallest gap in scaffolds: 0
3434
Base composition (A:C:G:T): 0:0:0:0
3535
GC content %: nan
3636
# soft-masked bases: 0
37-
# segments: 121
38-
Total segment length: 2541
39-
Average segment length: 21.00
37+
# segments: 4
38+
Total segment length: 177
39+
Average segment length: 44.25
4040
# gaps: 0
4141
# paths: 0
42-
# edges: 244
43-
Average degree: 2.02
42+
# edges: 4
43+
Average degree: 1.00
4444
# connected components: 1
45-
Largest connected component length: 2541
45+
Largest connected component length: 177
4646
# dead ends: 2
4747
# disconnected components: 0
4848
Total length disconnected components: 0
@@ -51,8 +51,8 @@ Total length disconnected components: 0
5151
# circular segments: 0
5252
# circular paths: 0
5353
DBG Summary statistics:
54-
Total kmers: 158
55-
Unique kmers: 84
56-
Distinct kmers: 121
57-
Missing kmers: 4398046510983
58-
Total edges: 203
54+
Total kmers: 159
55+
Unique kmers: 35
56+
Distinct kmers: 97
57+
Missing kmers: 4398046511007
58+
Total edges: 165

0 commit comments

Comments
 (0)