Skip to content

Add discard_compound_token to kuromoji tokenizer #4912

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 2 commits into from
Aug 4, 2020
Merged

Add discard_compound_token to kuromoji tokenizer #4912

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f0b326d
Add discard_compound_token to kuromoji tokenizer
russcam Jul 31, 2020
dd8c2d0
Add version comment
russcam Jul 31, 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
32 changes: 24 additions & 8 deletions src/Nest/Analysis/Plugins/Kuromoji/KuromojiTokenizer.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,16 @@ public interface IKuromojiTokenizer : ITokenizer
[JsonFormatter(typeof(NullableStringBooleanFormatter))]
bool? DiscardPunctuation { get; set; }

/// <summary>
/// Whether original compound tokens should be discarded from the output with
/// <see cref="KuromojiTokenizationMode.Search"/> <see cref="Mode"/>. Defaults to `false`.
/// <para />
/// Valid in Elasticsearch 7.9.0+
/// </summary>
[DataMember(Name ="discard_compound_token")]
[JsonFormatter(typeof(NullableStringBooleanFormatter))]
bool? DiscardCompoundToken { get; set; }

/// <summary>
/// The tokenization mode determines how the tokenizer handles compound and unknown words.
/// </summary>
Expand Down Expand Up @@ -64,6 +74,9 @@ public class KuromojiTokenizer : TokenizerBase, IKuromojiTokenizer
/// <inheritdoc />
public bool? DiscardPunctuation { get; set; }

/// <inheritdoc />
public bool? DiscardCompoundToken { get; set; }

/// <inheritdoc />
public KuromojiTokenizationMode? Mode { get; set; }

Expand All @@ -86,32 +99,35 @@ public class KuromojiTokenizerDescriptor
{
protected override string Type => "kuromoji_tokenizer";
bool? IKuromojiTokenizer.DiscardPunctuation { get; set; }

bool? IKuromojiTokenizer.DiscardCompoundToken { get; set; }
KuromojiTokenizationMode? IKuromojiTokenizer.Mode { get; set; }
int? IKuromojiTokenizer.NBestCost { get; set; }
string IKuromojiTokenizer.NBestExamples { get; set; }
string IKuromojiTokenizer.UserDictionary { get; set; }
IEnumerable<string> IKuromojiTokenizer.UserDictionaryRules { get; set; }

/// <inheritdoc />
/// <inheritdoc cref="IKuromojiTokenizer.Mode" />
public KuromojiTokenizerDescriptor Mode(KuromojiTokenizationMode? mode) => Assign(mode, (a, v) => a.Mode = v);

/// <inheritdoc />
/// <inheritdoc cref="IKuromojiTokenizer.DiscardPunctuation" />
public KuromojiTokenizerDescriptor DiscardPunctuation(bool? discard = true) => Assign(discard, (a, v) => a.DiscardPunctuation = v);

/// <inheritdoc />
/// <inheritdoc cref="IKuromojiTokenizer.DiscardCompoundToken" />
public KuromojiTokenizerDescriptor DiscardCompoundToken(bool? discard = true) => Assign(discard, (a, v) => a.DiscardCompoundToken = v);

/// <inheritdoc cref="IKuromojiTokenizer.UserDictionary" />
public KuromojiTokenizerDescriptor UserDictionary(string userDictionary) => Assign(userDictionary, (a, v) => a.UserDictionary = v);

/// <inheritdoc />
/// <inheritdoc cref="IKuromojiTokenizer.NBestExamples" />
public KuromojiTokenizerDescriptor NBestExamples(string examples) => Assign(examples, (a, v) => a.NBestExamples = v);

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

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

/// <inheritdoc />
/// <inheritdoc cref="IKuromojiTokenizer.UserDictionaryRules" />
public KuromojiTokenizerDescriptor UserDictionaryRules(params string[] rules) => Assign(rules, (a, v) => a.UserDictionaryRules = rules);
}
}
28 changes: 28 additions & 0 deletions tests/Tests/Analysis/Tokenizers/TokenizerTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -214,6 +214,34 @@ public class KuromojiTests : TokenizerAssertionBase<KuromojiTests>
public override string Name => "kuro";
}

[SkipVersion("<7.9.0", "discard_compound_token introduced in 7.9.0")]
public class KuromojiDiscardCompoundTokenTests : TokenizerAssertionBase<KuromojiDiscardCompoundTokenTests>
{
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.Search)
.DiscardCompoundToken()
);

public override ITokenizer Initializer => new KuromojiTokenizer
{
Mode = KuromojiTokenizationMode.Search,
DiscardCompoundToken = true,
};

public override object Json => new
{
discard_compound_token = true,
mode = "search",
type = "kuromoji_tokenizer",
};

public override string Name => "kuro_discard_compound_token";
}

public class UaxTests : TokenizerAssertionBase<UaxTests>
{
public override FuncTokenizer Fluent => (n, t) => t.UaxEmailUrl(n, e => e
Expand Down