Skip to content

Commit bbf7dd8

Browse files
viig99viig99
committed
Formatting + Version fixes.
1 parent b7b20dd commit bbf7dd8

File tree

2 files changed

+90
-75
lines changed

2 files changed

+90
-75
lines changed

‎CMakeLists.txt‎

Lines changed: 2 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -19,7 +19,7 @@ if (BUILD_FOR_PYTHON)
1919
FetchContent_Declare(
2020
pybind11
2121
GIT_REPOSITORY https://github.com/pybind/pybind11.git
22-
GIT_TAG v2.10.1)
22+
GIT_TAG v2.10.4)
2323
FetchContent_MakeAvailable(pybind11)
2424
pybind11_add_module(SymSpellCppPy MODULE SymSpellCppPy.cpp)
2525
target_sources(SymSpellCppPy PRIVATE library.cpp library.h)
@@ -34,7 +34,7 @@ else ()
3434
FetchContent_Declare(
3535
Catch2
3636
GIT_REPOSITORY https://github.com/catchorg/Catch2.git
37-
GIT_TAG v2.13.1)
37+
GIT_TAG v2.13.10)
3838
FetchContent_MakeAvailable(Catch2)
3939

4040
add_executable(Catch2Test tests/CatchMain.cpp library.cpp library.h)

‎tests/CatchMain.cpp‎

Lines changed: 88 additions & 73 deletions
Original file line numberDiff line numberDiff line change
@@ -5,132 +5,140 @@
55

66
using namespace symspellcpppy;
77

8-
TEST_CASE("Testing English", "[english]") {
8+
TEST_CASE("Testing English", "[english]")
9+
{
910
const int maxEditDistance = 2;
1011
const int prefixLength = 3;
1112

12-
SECTION("Do Word Segmentation") {
13+
SECTION("Do Word Segmentation")
14+
{
1315
SymSpell symSpell(maxEditDistance, prefixLength);
1416
symSpell.LoadDictionary("../resources/frequency_dictionary_en_82_765.txt", 0, 1, XL(' '));
1517
std::unordered_map<xstring, xstring> sentences = {
16-
{XL("thequickbrownfoxjumpsoverthelazydog"), XL("the quick brown fox jumps over the lazy dog")},
17-
{XL("itwasabrightcolddayinaprilandtheclockswerestrikingthirteen"), XL("it was bright holiday in april and the clocks were striking thirteen")},
18-
{XL("itwasthebestoftimesitwastheworstoftimesitwastheageofwisdomitwastheageoffoolishness"), XL("iowa the best of times it waste worst of times it was thereof wisdom it was thereof foolishness")}
19-
};
18+
{XL("thequickbrownfoxjumpsoverthelazydog"), XL("the quick brown fox jumps over the lazy dog")},
19+
{XL("itwasabrightcolddayinaprilandtheclockswerestrikingthirteen"), XL("it was bright holiday in april and the clocks were striking thirteen")},
20+
{XL("itwasthebestoftimesitwastheworstoftimesitwastheageofwisdomitwastheageoffoolishness"), XL("iowa the best of times it waste worst of times it was thereof wisdom it was thereof foolishness")}};
2021

21-
for (auto &sentence : sentences) {
22+
for (auto &sentence : sentences)
23+
{
2224
auto results = symSpell.WordSegmentation(sentence.first);
2325
REQUIRE(results.getCorrected() == sentence.second);
2426
}
2527
}
2628

27-
// SECTION("Test 6.7 Changes") {
28-
// xstring input =
29-
// XL("AbstractHowdoesauser’spriorexperiencewithdeeplearningimpactaccuracy?Wepresentaninitialstudybased"
30-
// "on31participantswithdifferentlevelsofexperience.Theirtaskistoperformhyperparameteroptimizationfor"
31-
// "agivendeeplearningarchitecture.There-sultsshowastrongpositivecorrelationbetweentheparticipant’sexperience"
32-
// "andthefinalperformance.Theyadditionallyindicatethatanexperiencedparticipantfindsbettersolu-tions"
33-
// "usingfewerresourcesonaverage.Thedatasuggestsfurthermorethatparticipantswithnopriorexperiencefollow"
34-
// "randomstrategiesintheirpursuitofoptimalhyperpa-rameters.Ourstudyinvestigatesthesubjectivehumanfactor"
35-
// "incomparisonsofstateoftheartresultsandscientificreproducibilityindeeplearning.1IntroductionThepopularity"
36-
// "ofdeeplearninginvariousfieldssuchasimagerecognition[9,19],speech[11,30],bioinformatics[21,24],"
37-
// "questionanswering[3]etc.stemsfromtheseeminglyfavorabletrade-offbetweentherecognitionaccuracy"
38-
// "andtheiroptimizationburdenlecunetal20attributetheirsuccess");
39-
// XL("AbstractHowdoesauser’spriorexperience?");
40-
41-
// xstring output =
42-
// XL("Abstract How does a user’s prior experience with deep learning impact accuracy? We present an initial "
43-
// "study based on 31 participants with different levels of experience. Their task is to perform hyper "
44-
// "parameter optimization for a given deep learning architecture. The results show a strong positive "
45-
// "correlation between the participant’s experience and the final performance. They additionally indicate "
46-
// "that an experienced participant finds better solutions using fewer resources on average. The data "
47-
// "suggests furthermore that participants with no prior experience follow random strategies in their "
48-
// "pursuit of optimal hyper parameters. Our study investigates the subjective human factor in comparisons "
49-
// "of state of the art results and scientific reproducibility in deep learning. 1 Introduction The "
50-
// "popularity of deep learning in various fields such as image recognition [9,19], speech [11,30], bio "
51-
// "informatics [21,24], question answering [3] etc. stems from the seemingly favorable trade off between "
52-
// "the recognition accuracy and their optimization burden l ecu net al 20 attribute their success");
53-
// XL("Abstract How does a user’s prior experience?");
54-
//
55-
// SymSpell symSpell(maxEditDistance, prefixLength);
56-
// symSpell.LoadDictionary("../resources/frequency_dictionary_en_82_765.txt", 0, 1, XL(' '));
57-
//
58-
// auto results = symSpell.WordSegmentation(input, 2, 28);
59-
// REQUIRE(results.getSegmented() == output);
60-
// }
61-
62-
SECTION("Do Spell Correction") {
29+
// SECTION("Test 6.7 Changes") {
30+
// xstring input =
31+
// XL("AbstractHowdoesauser’spriorexperiencewithdeeplearningimpactaccuracy?Wepresentaninitialstudybased"
32+
// "on31participantswithdifferentlevelsofexperience.Theirtaskistoperformhyperparameteroptimizationfor"
33+
// "agivendeeplearningarchitecture.There-sultsshowastrongpositivecorrelationbetweentheparticipant’sexperience"
34+
// "andthefinalperformance.Theyadditionallyindicatethatanexperiencedparticipantfindsbettersolu-tions"
35+
// "usingfewerresourcesonaverage.Thedatasuggestsfurthermorethatparticipantswithnopriorexperiencefollow"
36+
// "randomstrategiesintheirpursuitofoptimalhyperpa-rameters.Ourstudyinvestigatesthesubjectivehumanfactor"
37+
// "incomparisonsofstateoftheartresultsandscientificreproducibilityindeeplearning.1IntroductionThepopularity"
38+
// "ofdeeplearninginvariousfieldssuchasimagerecognition[9,19],speech[11,30],bioinformatics[21,24],"
39+
// "questionanswering[3]etc.stemsfromtheseeminglyfavorabletrade-offbetweentherecognitionaccuracy"
40+
// "andtheiroptimizationburdenlecunetal20attributetheirsuccess");
41+
// XL("AbstractHowdoesauser’spriorexperience?");
42+
43+
// xstring output =
44+
// XL("Abstract How does a user’s prior experience with deep learning impact accuracy? We present an initial "
45+
// "study based on 31 participants with different levels of experience. Their task is to perform hyper "
46+
// "parameter optimization for a given deep learning architecture. The results show a strong positive "
47+
// "correlation between the participant’s experience and the final performance. They additionally indicate "
48+
// "that an experienced participant finds better solutions using fewer resources on average. The data "
49+
// "suggests furthermore that participants with no prior experience follow random strategies in their "
50+
// "pursuit of optimal hyper parameters. Our study investigates the subjective human factor in comparisons "
51+
// "of state of the art results and scientific reproducibility in deep learning. 1 Introduction The "
52+
// "popularity of deep learning in various fields such as image recognition [9,19], speech [11,30], bio "
53+
// "informatics [21,24], question answering [3] etc. stems from the seemingly favorable trade off between "
54+
// "the recognition accuracy and their optimization burden l ecu net al 20 attribute their success");
55+
// XL("Abstract How does a user’s prior experience?");
56+
//
57+
// SymSpell symSpell(maxEditDistance, prefixLength);
58+
// symSpell.LoadDictionary("../resources/frequency_dictionary_en_82_765.txt", 0, 1, XL(' '));
59+
//
60+
// auto results = symSpell.WordSegmentation(input, 2, 28);
61+
// REQUIRE(results.getSegmented() == output);
62+
// }
63+
64+
SECTION("Do Spell Correction")
65+
{
6366
SymSpell symSpell(maxEditDistance, prefixLength);
6467
symSpell.LoadDictionary("../resources/frequency_dictionary_en_82_765.txt", 0, 1, XL(' '));
6568
std::unordered_map<xstring, xstring> words = {
66-
{XL("tke"), XL("the")},
67-
{XL("abolution"), XL("abolition")},
68-
{XL("intermedaite"), XL("intermediate")}
69-
};
69+
{XL("tke"), XL("the")},
70+
{XL("abolution"), XL("abolition")},
71+
{XL("intermedaite"), XL("intermediate")}};
7072

71-
for (auto &word : words) {
73+
for (auto &word : words)
74+
{
7275
auto results = symSpell.Lookup(word.first, Verbosity::Closest);
7376
REQUIRE(results[0].term == word.second);
7477
}
7578
}
7679

77-
SECTION("Do Spell Correction With MaxEditDistance=2") {
80+
SECTION("Do Spell Correction With MaxEditDistance=2")
81+
{
7882
SymSpell symSpell(maxEditDistance, prefixLength);
7983
symSpell.LoadDictionary("../resources/frequency_dictionary_en_82_765.txt", 0, 1, XL(' '));
8084
std::unordered_map<xstring, xstring> words_within_distance = {
81-
{XL("tke"), XL("the")},
82-
{XL("extrine"), XL("extreme")}
83-
};
85+
{XL("tke"), XL("the")},
86+
{XL("extrine"), XL("extreme")}};
8487

8588
std::unordered_map<xstring, xstring> words_far_distance = {
86-
{XL("elipnaht"), XL("elephant")},
87-
{XL("aotocrasie"), XL("autocracy")}
88-
};
89+
{XL("elipnaht"), XL("elephant")},
90+
{XL("aotocrasie"), XL("autocracy")}};
8991

90-
for (auto &word : words_within_distance) {
92+
for (auto &word : words_within_distance)
93+
{
9194
auto results = symSpell.Lookup(word.first, Verbosity::Closest, 2);
9295
REQUIRE(results[0].term == word.second);
9396
}
9497

95-
for (auto &word : words_far_distance) {
98+
for (auto &word : words_far_distance)
99+
{
96100
auto results = symSpell.Lookup(word.first, Verbosity::Closest, 2);
97101
REQUIRE(results.empty());
98102
}
99103
}
100104

101-
SECTION("Correct Compound Mistakes") {
105+
SECTION("Correct Compound Mistakes")
106+
{
102107
SymSpell symSpell(maxEditDistance, prefixLength);
103108
symSpell.LoadDictionary("../resources/frequency_dictionary_en_82_765.txt", 0, 1, XL(' '));
104109
symSpell.LoadBigramDictionary("../resources/frequency_bigramdictionary_en_243_342.txt", 0, 2, XL(' '));
105110
std::unordered_map<xstring, xstring> compunded_sentences = {
106-
{XL("whereis th elove"), XL("where is the love")},
107-
{XL("whereis th elove hehad dated forImuch of thepast who couqdn'tread in sixthgrade and ins pired him"), XL("where is the love he had dated for much of the past who couldn't read in sixth grade and inspired him")},
108-
{XL("in te dhird qarter oflast jear he hadlearned ofca sekretplan"), XL("in the third quarter of last year he had learned of a secret plan")},
109-
{XL("the bigjest playrs in te strogsommer film slatew ith plety of funn"), XL("the biggest players in the strong summer film slate with plenty of fun")}
110-
};
111+
{XL("whereis th elove"), XL("where is the love")},
112+
{XL("whereis th elove hehad dated forImuch of thepast who couqdn'tread in sixthgrade and ins pired him"), XL("where is the love he had dated for much of the past who couldn't read in sixth grade and inspired him")},
113+
{XL("in te dhird qarter oflast jear he hadlearned ofca sekretplan"), XL("in the third quarter of last year he had learned of a secret plan")},
114+
{XL("the bigjest playrs in te strogsommer film slatew ith plety of funn"), XL("the biggest players in the strong summer film slate with plenty of fun")}};
111115

112-
for (auto &sentence : compunded_sentences) {
116+
for (auto &sentence : compunded_sentences)
117+
{
113118
auto results = symSpell.LookupCompound(sentence.first);
114119
REQUIRE(results[0].term == sentence.second);
115120
}
116121
}
117122

118-
SECTION("Check top verbosity") {
123+
SECTION("Check top verbosity")
124+
{
119125
SymSpell symSpellcustom(maxEditDistance, prefixLength);
120126
symSpellcustom.LoadDictionary("../resources/frequency_dictionary_en_test_verbosity.txt", 0, 1, XL(' '));
121127
auto results = symSpellcustom.Lookup(XL("stream"), Verbosity::Top, 2);
122128
REQUIRE(1 == results.size());
123129
REQUIRE(XL("streamc") == results[0].term);
124130
}
125131

126-
SECTION("Check all verbosity") {
132+
SECTION("Check all verbosity")
133+
{
127134
SymSpell symSpellcustom(maxEditDistance, prefixLength);
128135
symSpellcustom.LoadDictionary("../resources/frequency_dictionary_en_test_verbosity.txt", 0, 1, XL(' '));
129136
auto results = symSpellcustom.Lookup(XL("stream"), Verbosity::All, 2);
130137
REQUIRE(2 == results.size());
131138
}
132139

133-
SECTION("check custom entry of dictionary") {
140+
SECTION("check custom entry of dictionary")
141+
{
134142
SymSpell symSpellcustom(maxEditDistance, prefixLength, DEFAULT_COUNT_THRESHOLD, DEFAULT_INITIAL_CAPACITY,
135143
DEFAULT_COMPACT_LEVEL);
136144
auto staging = std::make_shared<SuggestionStage>(100);
@@ -140,22 +148,27 @@ TEST_CASE("Testing English", "[english]") {
140148
REQUIRE(XL("take") == results[0].term);
141149
}
142150

143-
SECTION("check save works fine.") {
151+
SECTION("check save works fine.")
152+
{
144153
SymSpell symSpellcustom(maxEditDistance, prefixLength, DEFAULT_COUNT_THRESHOLD, DEFAULT_INITIAL_CAPACITY,
145154
DEFAULT_COMPACT_LEVEL);
146155
symSpellcustom.LoadDictionary("../resources/frequency_dictionary_en_test_verbosity.txt", 0, 1, XL(' '));
147156
auto filepath = "../resources/model.bin";
148157
std::ofstream binary_path(filepath, std::ios::out | std::ios::app | std::ios::binary);
149-
if (binary_path.is_open()) {
158+
if (binary_path.is_open())
159+
{
150160
cereal::BinaryOutputArchive oarchive(binary_path);
151161
oarchive(symSpellcustom);
152-
} else {
162+
}
163+
else
164+
{
153165
throw std::invalid_argument("Cannot save to file");
154166
}
155167
std::remove(filepath);
156168
}
157169

158-
SECTION("Compund mistakes distance") {
170+
SECTION("Compund mistakes distance")
171+
{
159172
SymSpell symSpell(maxEditDistance, prefixLength);
160173
symSpell.LoadDictionary("../resources/frequency_dictionary_en_82_765.txt", 0, 1, XL(' '));
161174
symSpell.LoadBigramDictionary("../resources/frequency_bigramdictionary_en_243_342.txt", 0, 2, XL(' '));
@@ -165,7 +178,8 @@ TEST_CASE("Testing English", "[english]") {
165178
REQUIRE(results[0].distance == 2);
166179
}
167180

168-
SECTION("Compund mistakes capitals") {
181+
SECTION("Compund mistakes capitals")
182+
{
169183
SymSpell symSpell(maxEditDistance, prefixLength);
170184
symSpell.LoadDictionary("../resources/frequency_dictionary_en_82_765.txt", 0, 1, XL(' '));
171185
xstring typo = XL("can yu readthis");
@@ -174,7 +188,8 @@ TEST_CASE("Testing English", "[english]") {
174188
REQUIRE(results[0].term == correction);
175189
}
176190

177-
SECTION("Lookup transfer casing") {
191+
SECTION("Lookup transfer casing")
192+
{
178193
SymSpell symSpell(maxEditDistance, prefixLength);
179194
symSpell.LoadDictionary("../resources/frequency_dictionary_en_82_765.txt", 0, 1, XL(' '));
180195
xstring typo = XL("meMberSa");

0 commit comments

Comments
 (0)