Skip to content

Add support for inlined user dictionary in the Kuromoji plugin #4138

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.

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 1 commit into from
Oct 15, 2019
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
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
18 changes: 17 additions & 1 deletion src/Nest/Analysis/Plugins/Kuromoji/KuromojiTokenizer.cs
Original file line number Diff line number Diff line change
@@ -1,4 +1,5 @@
using System.Runtime.Serialization;
using System.Collections.Generic;
using System.Runtime.Serialization;
using Elasticsearch.Net.Utf8Json;

namespace Nest
Expand Down Expand Up @@ -44,6 +45,11 @@ public interface IKuromojiTokenizer : ITokenizer
/// </summary>
[DataMember(Name ="user_dictionary")]
string UserDictionary { get; set; }

/// <summary> Inline rule version of <see cref="UserDictionary"/> </summary>
[DataMember(Name ="user_dictionary_rules")]
IEnumerable<string> UserDictionaryRules { get; set; }

}

/// <inheritdoc />
Expand All @@ -65,6 +71,9 @@ public class KuromojiTokenizer : TokenizerBase, IKuromojiTokenizer

/// <inheritdoc />
public string UserDictionary { get; set; }

/// <inheritdoc />
public IEnumerable<string> UserDictionaryRules { get; set; }
}

/// <inheritdoc />
Expand All @@ -78,6 +87,7 @@ public class KuromojiTokenizerDescriptor
int? IKuromojiTokenizer.NBestCost { get; set; }
string IKuromojiTokenizer.NBestExamples { get; set; }
string IKuromojiTokenizer.UserDictionary { get; set; }
IEnumerable<string> IKuromojiTokenizer.UserDictionaryRules { get; set; }

/// <inheritdoc />
public KuromojiTokenizerDescriptor Mode(KuromojiTokenizationMode? mode) => Assign(mode, (a, v) => a.Mode = v);
Expand All @@ -93,5 +103,11 @@ public class KuromojiTokenizerDescriptor

/// <inheritdoc />
public KuromojiTokenizerDescriptor NBestCost(int? cost) => Assign(cost, (a, v) => a.NBestCost = v);

/// <inheritdoc />
public KuromojiTokenizerDescriptor UserDictionaryRules(IEnumerable<string> rules) => Assign(rules, (a, v) => a.UserDictionaryRules = rules);

/// <inheritdoc />
public KuromojiTokenizerDescriptor UserDictionaryRules(params string[] rules) => Assign(rules, (a, v) => a.UserDictionaryRules = rules);
}
}
9 changes: 7 additions & 2 deletions src/Tests/Tests/Analysis/Tokenizers/TokenizerTests.cs
Original file line number Diff line number Diff line change
Expand Up @@ -114,23 +114,27 @@ public class IcuTests : TokenizerAssertionBase<IcuTests>
public override string Name => "icu";
}

[SkipVersion("<7.4.0", "not all options available before this version")]
public class KuromojiTests : TokenizerAssertionBase<KuromojiTests>
{
private const string Example = "/箱根山-箱根/成田空港-成田/";
private const string Inline = "東京スカイツリー,東京 スカイツリー,トウキョウ スカイツリー,カスタム名詞";

public override FuncTokenizer Fluent => (n, t) => t.Kuromoji(n, e => e
.Mode(KuromojiTokenizationMode.Extended)
.DiscardPunctuation()
.NBestExamples(Example)
.NBestCost(1000)
.UserDictionaryRules(Inline)
);

public override ITokenizer Initializer => new KuromojiTokenizer
{
Mode = KuromojiTokenizationMode.Extended,
DiscardPunctuation = true,
NBestExamples = Example,
NBestCost = 1000
NBestCost = 1000,
UserDictionaryRules = new [] { Inline }
};

public override object Json => new
Expand All @@ -139,7 +143,8 @@ public class KuromojiTests : TokenizerAssertionBase<KuromojiTests>
mode = "extended",
nbest_cost = 1000,
nbest_examples = Example,
type = "kuromoji_tokenizer"
type = "kuromoji_tokenizer",
user_dictionary_rules = new [] { Inline }
};

public override string Name => "kuro";
Expand Down