8000 Feature/ngram similarity function by Dronplane · Pull Request #11276 · arangodb/arangodb · GitHub
[go: up one dir, main page]
Skip to content

Feature/ngram similarity function #11276

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 11 commits into from
Mar 16, 2020
Merged

Feature/ngram similarity function #11276

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
5f104d8
Implemented similarity functions
Dronplane Mar 10, 2020
c1b493a
WIP
Dronplane Mar 11, 2020
d4e15c1
added NGRAM_MATCH implementation
Dronplane Mar 11, 2020
a9c0330
WIP
Dronplane Mar 13, 2020
2d58031
Merge branch 'devel' into feature/ngram-similarity-function
Dronplane Mar 13, 2020
7011243
Added tests and code cleanup
Dronplane Mar 16, 2020
5aaffa3
Merge branch 'devel' into feature/ngram-similarity-function
Dronplane Mar 16, 2020
9059513
Added constants container
Dronplane Mar 16, 2020
8b49deb
cleanup
Dronplane Mar 16, 2020
69cb161
Adressed review comments
Dronplane Mar 16, 2020
8398298
more cleanup
Dronplane Mar 16, 2020
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
Added constants container
  • Loading branch information
@Dronplane
Dronplane committed Mar 16, 2020
commit 905951350f09a1faaadb953c93047f040f6008a6
3 changes: 2 additions & 1 deletion arangod/Aql/Functions.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,6 +61,7 @@
#include "IResearch/VelocyPackHelper.h"
#include "IResearch/IResearchPDP.h"
#include "IResearch/IResearchAnalyzerFeature.h"
#include "IResearch/IResearchFilterFactory.h"
#include "Random/UniformCharacter.h"
#include "Rest/Version.h"
#include "RestServer/SystemDatabaseFeature.h"
Expand Down Expand Up @@ -1681,7 +1682,7 @@ AqlValue Functions::NgramMatch(ExpressionContext* ctx, transaction::Methods* trx
}
auto const targetValue = iresearch::getStringRef(target.slice());

double_t threshold = 0.7;//!!!! to constants!
auto threshold = arangodb::iresearch::FilterConstants::DefaultNgramMatchThreshold;
size_t analyzerPosition = 2;
if (argc > 3) {// 4 args given. 3rd is threshold
auto const& thresholdArg = extractFunctionParameterValue(args, 2);
Expand Down
8 changes: 4 additions & 4 deletions arangod/IResearch/IResearchFilterFactory.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2237,7 +2237,7 @@ arangodb::Result getLevenshteinArguments(char const* funcName, bool isFilter,
};
}

scoringLimit = 128; // FIXME make configurable
scoringLimit = FilterConstants::DefaultScoringTermsLimit;

return {};
}
Expand Down Expand Up @@ -2623,7 +2623,7 @@ arangodb::Result fromFuncNgramMatch(
}
}

double_t threshold = 0.7;
auto threshold = FilterConstants::DefaultNgramMatchThreshold;
TRI_ASSERT(filterCtx.analyzer);
auto analyzerPool = filterCtx.analyzer;

Expand Down Expand Up @@ -2769,7 +2769,7 @@ arangodb::Result fromFuncStartsWith(
return rv;
}

size_t scoringLimit = 128; // FIXME make configurable
size_t scoringLimit = FilterConstants::DefaultScoringTermsLimit;

if (argc > 2) {
// 3rd (optional) argument defines a number of scored terms
Expand Down Expand Up @@ -2915,7 +2915,7 @@ arangodb::Result fromFuncLike(
return res;
}

const size_t scoringLimit = 128; // FIXME make configurable
const auto scoringLimit = FilterConstants::DefaultScoringTermsLimit;

if (filter) {
std::string name;
Expand Down
9 changes: 9 additions & 0 deletions arangod/IResearch/IResearchFilterFactory.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,15 @@ struct FilterFactory {
arangodb::aql::AstNode const& node);
}; // FilterFactory


class FilterConstants {
FilterConstants() = delete;
public:
// Defaults
static constexpr size_t DefaultScoringTermsLimit { 128 };
static constexpr double_t DefaultNgramMatchThreshold { 0.7 };
};

} // namespace iresearch
} // namespace arangodb

Expand Down
0