Skip to content

[Backport master] Add ignore_keywords flag to word delimiter graph #5129

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 1 commit into from
Nov 30, 2020
Merged

[Backport master] Add ignore_keywords flag to word delimiter graph #5129

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
20 changes: 19 additions & 1 deletion src/Nest/Analysis/TokenFilters/WordDelimiterGraph/WordDelimiterGraphTokenFilter.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,13 @@ public interface IWordDelimiterGraphTokenFilter : ITokenFilter
[JsonFormatter(typeof(NullableStringBooleanFormatter))]
bool? GenerateWordParts { get; set; }

/// <summary>
/// If true, the filter skips tokens with a keyword attribute of true. Defaults to false.
/// </summary>
[DataMember(Name = "ignore_keywords")]
[JsonFormatter(typeof(NullableStringBooleanFormatter))]
bool? IgnoreKeywords { get; set; }

/// <summary>
/// If true includes original words in subwords: "500-42" ⇒ "500-42" "500" "42". Defaults to false.
/// </summary>
Expand Down Expand Up @@ -133,6 +140,9 @@ public WordDelimiterGraphTokenFilter() : base("word_delimiter_graph") { }
/// <inheritdoc />
public bool? GenerateWordParts { get; set; }

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

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

Expand Down Expand Up @@ -169,8 +179,8 @@ public class WordDelimiterGraphTokenFilterDescriptor
bool? IWordDelimiterGraphTokenFilter.CatenateWords { get; set; }
bool? IWordDelimiterGraphTokenFilter.GenerateNumberParts { get; set; }
bool? IWordDelimiterGraphTokenFilter.GenerateWordParts { get; set; }
bool? IWordDelimiterGraphTokenFilter.IgnoreKeywords { get; set; }
bool? IWordDelimiterGraphTokenFilter.PreserveOriginal { get; set; }

IEnumerable<string> IWordDelimiterGraphTokenFilter.ProtectedWords { get; set; }
string IWordDelimiterGraphTokenFilter.ProtectedWordsPath { get; set; }
bool? IWordDelimiterGraphTokenFilter.SplitOnCaseChange { get; set; }
Expand All @@ -187,6 +197,14 @@ public WordDelimiterGraphTokenFilterDescriptor GenerateWordParts(bool? generateW
public WordDelimiterGraphTokenFilterDescriptor GenerateNumberParts(bool? generateNumberParts = true) =>
Assign(generateNumberParts, (a, v) => a.GenerateNumberParts = v);

/// <summary>
/// <para>Configure whether the filter will skip tokens with a keyword attribute of true.</para>
/// <para>(Optional) When not configured, this defaults to false in Elasticsearch.</para>
/// </summary>
/// <param name="ignoreKeywords">If true, the filter skips tokens with a keyword attribute of true.</param>
public WordDelimiterGraphTokenFilterDescriptor IgnoreKeywords(bool? ignoreKeywords = true) =>
Assign(ignoreKeywords, (a, v) => a.IgnoreKeywords = v);

/// <inheritdoc />
public WordDelimiterGraphTokenFilterDescriptor CatenateWords(bool? catenateWords = true) => Assign(catenateWords, (a, v) => a.CatenateWords = v);

Expand Down
3 changes: 3 additions & 0 deletions tests/Tests/Analysis/TokenFilters/TokenFilterTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -923,6 +923,7 @@ public class WordDelimiterGraphTests : TokenFilterAssertionBase<WordDelimiterGra
.CatenateWords()
.GenerateNumberParts()
.GenerateWordParts()
.IgnoreKeywords()
.PreserveOriginal()
.ProtectedWords("x", "y", "z")
.SplitOnCaseChange()
Expand All @@ -939,6 +940,7 @@ public class WordDelimiterGraphTests : TokenFilterAssertionBase<WordDelimiterGra
CatenateWords = true,
GenerateNumberParts = true,
GenerateWordParts = true,
IgnoreKeywords = true,
PreserveOriginal = true,
ProtectedWords = new[] { "x", "y", "z" },
SplitOnCaseChange = true,
Expand All @@ -952,6 +954,7 @@ public class WordDelimiterGraphTests : TokenFilterAssertionBase<WordDelimiterGra
adjust_offsets = true,
generate_word_parts = true,
generate_number_parts = true,
ignore_keywords = true,
catenate_words = true,
catenate_numbers = true,
catenate_all = true,
Expand Down
3 changes: 3 additions & 0 deletions tests/Tests/Analysis/TokenFilters/TokenFilterUsageTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -141,6 +141,7 @@ public class TokenFilterUsageTests : PromiseUsageTestBase<IIndexSettings, IndexS
.CatenateWords()
.GenerateNumberParts()
.GenerateWordParts()
.IgnoreKeywords()
.PreserveOriginal()
.ProtectedWords("x", "y", "z")
.SplitOnCaseChange()
Expand Down Expand Up @@ -301,6 +302,7 @@ public class TokenFilterUsageTests : PromiseUsageTestBase<IIndexSettings, IndexS
CatenateWords = true,
GenerateNumberParts = true,
GenerateWordParts = true,
IgnoreKeywords = true,
PreserveOriginal = true,
ProtectedWords = new[] { "x", "y", "z" },
SplitOnCaseChange = true,
Expand Down Expand Up @@ -624,6 +626,7 @@ public class TokenFilterUsageTests : PromiseUsageTestBase<IIndexSettings, IndexS
type = "word_delimiter_graph",
generate_word_parts = true,
generate_number_parts = true,
ignore_keywords = true,
catenate_words = true,
catenate_numbers = true,
catenate_all = true,
Expand Down