added custom analyzer structs (#224)

* added custom analyzer structs

* fix lint issues

Author: abner-dou

mongodbatlas/search.go

@@ -28,13 +28,13 @@ const (
 //
 // See more: https://docs.atlas.mongodb.com/reference/api/atlas-search/
 type SearchService interface {
-	ListIndexes(context.Context, string, string, string, string, *ListOptions) ([]*SearchIndex, *Response, error)
-	GetIndex(context.Context, string, string, string) (*SearchIndex, *Response, error)
-	CreateIndex(context.Context, string, string, *SearchIndex) (*SearchIndex, *Response, error)
-	UpdateIndex(context.Context, string, string, string, *SearchIndex) (*SearchIndex, *Response, error)
-	DeleteIndex(context.Context, string, string, string) (*Response, error)
-	ListAnalyzers(context.Context, string, string, *ListOptions) ([]*SearchAnalyzer, *Response, error)
-	UpdateAllAnalyzers(context.Context, string, string, []*SearchAnalyzer) ([]*SearchAnalyzer, *Response, error)
+	ListIndexes(ctx context.Context, groupID string, clusterName string, databaseName string, collectionName string, opts *ListOptions) ([]*SearchIndex, *Response, error)
+	GetIndex(ctx context.Context, groupID, clusterName, indexID string) (*SearchIndex, *Response, error)
+	CreateIndex(ctx context.Context, projectID, clusterName string, r *SearchIndex) (*SearchIndex, *Response, error)
+	UpdateIndex(ctx context.Context, projectID, clusterName, indexID string, r *SearchIndex) (*SearchIndex, *Response, error)
+	DeleteIndex(ctx context.Context, projectID, clusterName, indexID string) (*Response, error)
+	ListAnalyzers(ctx context.Context, groupID, clusterName string, listOptions *ListOptions) ([]*SearchAnalyzer, *Response, error)
+	UpdateAllAnalyzers(ctx context.Context, groupID, clusterName string, analyzers []*SearchAnalyzer) ([]*SearchAnalyzer, *Response, error)
 }
 
 // SearchServiceOp provides an implementation of the SearchService interface.
@@ -242,15 +242,15 @@ func (s *SearchServiceOp) UpdateAllAnalyzers(ctx context.Context, groupID, clust
 
 // SearchIndex index definition.
 type SearchIndex struct {
-	Analyzer       string                 `json:"analyzer,omitempty"`
-	Analyzers      map[string]interface{} `json:"analyzers,omitempty"` // Custom analyzers
-	CollectionName string                 `json:"collectionName"`
-	Database       string                 `json:"database"`
-	IndexID        string                 `json:"indexID,omitempty"`
-	Mappings       *IndexMapping          `json:"mappings,omitempty"`
-	Name           string                 `json:"name"`
-	SearchAnalyzer string                 `json:"searchAnalyzer,omitempty"`
-	Status         string                 `json:"status,omitempty"`
+	Analyzer       string            `json:"analyzer,omitempty"`
+	Analyzers      []*CustomAnalyzer `json:"analyzers,omitempty"` // Custom analyzers
+	CollectionName string            `json:"collectionName"`
+	Database       string            `json:"database"`
+	IndexID        string            `json:"indexID,omitempty"`
+	Mappings       *IndexMapping     `json:"mappings,omitempty"`
+	Name           string            `json:"name"`
+	SearchAnalyzer string            `json:"searchAnalyzer,omitempty"`
+	Status         string            `json:"status,omitempty"`
 }
 
 // IndexMapping containing index specifications for the collection fields.
@@ -280,7 +280,7 @@ type IndexField struct {
 	IndexShapes    *bool                  `json:"indexShapes,omitempty"`
 }
 
-// SearchAnalyzer custom analyzer definition.
+// SearchAnalyzer search analyzer definition.
 type SearchAnalyzer struct {
 	BaseAnalyzer     string   `json:"baseAnalyzer"`
 	MaxTokenLength   *int     `json:"maxTokenLength,omitempty"`
@@ -289,3 +289,126 @@ type SearchAnalyzer struct {
 	StemExclusionSet []string `json:"stemExclusionSet,omitempty"`
 	Stopwords        []string `json:"stopwords,omitempty"`
 }
+
+// CustomAnalyzer custom analyzer for index.
+type CustomAnalyzer struct {
+	// Name of the custom analyzer. Names must be unique within an index, and may not start with any of the following strings: lucene, builtin, mongodb
+	Name string `json:"name"`
+
+	// CharFilters Array containing zero or more character filters.
+	CharFilters []*AnalyzerCharFilter `json:"charFilters,omitempty"`
+
+	// Tokenizer to use.
+	Tokenizer *AnalyzerTokenizer `json:"tokenizer"`
+
+	// TokenFilters Array containing zero or more token filters
+	TokenFilters []*AnalyzerTokenFilters `json:"tokenFilters,omitempty"`
+}
+
+// AnalyzerCharFilter Characters filters for custom analyzer. For further information, go to
+// https://docs.atlas.mongodb.com/reference/atlas-search/analyzers/custom/#std-label-char-filters-ref
+type AnalyzerCharFilter struct {
+	// Type The type of this character filter, supports: htmlStrip, icuNormalize, mapping, persian
+	Type string `json:"type"`
+
+	// IgnoreTags A list of HTML tags to exclude from filtering. Apply for type: htmlStrip
+	IgnoreTags []string `json:"IgnoreTags,omitempty"`
+
+	// Mappings An object containing a comma-separated list of mappings. A mapping indicates that one character
+	// or group of characters should be substituted for another, in the format <original> : <replacement>
+	// apply for type: mapping
+	Mappings *map[string]string `json:"mappings,omitempty"`
+}
+
+// AnalyzerTokenizer tokenizer for custom analyzer, for further information, go to
+// https://docs.atlas.mongodb.com/reference/atlas-search/analyzers/custom/#std-label-tokenizers-ref
+type AnalyzerTokenizer struct {
+	// Type The type of this tokenizer. Supports standard, keyword, whitespace, nGram, edgeGram, regexCaptureGroup,
+	// regexSplit, uaxUrEmail
+	Type string `json:"type"`
+
+	// MaxTokenLength Maximum length for a single token. Tokens greater than this length are split at maxTokenLength
+	// into multiple tokens. Apply for type: standard, whitespace, uaxUrlEmail
+	MaxTokenLength *int `json:"maxTokenLength,omitempty"`
+
+	// MinGram Number of characters to include in the shortest token created. Apply for type: nGram, edgeGram
+	MinGram *int `json:"minGram,omitempty"`
+
+	// MaxGram Number of characters to include in the longest token created. Apply for type: nGram, edgeGram
+	MaxGram *int `json:"maxGram,omitempty"`
+
+	// Pattern A regular expression to match against. Apply for type: regexCaptureGroup, regexSplit
+	Pattern string `json:"pattern,omitempty"`
+
+	// Group Index of the character group within the matching expression to extract into tokens. Use 0 to extract all
+	// character groups. Apply for type: regexCaptureGroup
+	Group *int `json:"group,omitempty"`
+}
+
+// AnalyzerTokenFilters token filter for custom analyzer. To get more information, go to
+// https://docs.atlas.mongodb.com/reference/atlas-search/analyzers/custom/#std-label-token-filters-ref
+type AnalyzerTokenFilters struct {
+	// Type The type of this token filter. Supports: daitchMokotoffSoundex, lowercase, length, icuFolding, icuNormalize
+	// nGram, edgeGram, shingle, regex, snowballStemming, stopword, trim
+	Type string `json:"type"`
+
+	// OriginalTokens Specifies whether to include or omit the original tokens in the output of the token filter. Value can
+	// be one of the following: include - to include the original tokens with the encoded tokens in the output of the token
+	// filter. We recommend this value if you want queries on both the original tokens as well as the encoded forms.
+	// omit - to omit the original tokens and include only the encoded tokens in the output of the token filter.
+	// Use this value if you want to only query on the encoded forms of the original tokens. Apply for type: daitchMokotoffSoundex
+	OriginalTokens string `json:"originalTokens,omitempty"`
+
+	// Min The minimum length of a token. Must be less than or equal to max. Apply for type: length
+	Min *int `json:"min,omitempty"`
+
+	// Max The maximum length of a token. Must be greater than or equal to min.
+	Max *int `json:"max,omitempty"`
+
+	// NormalizationForm Normalization form to apply. Accepted values are:
+	// nfd (Canonical Decomposition)
+	// nfc (Canonical Decomposition, followed by Canonical Composition)
+	// nfkd (Compatibility Decomposition)
+	// nfkc (Compatibility Decomposition, followed by Canonical Composition).
+	// Apply for type: icuNormalize
+	NormalizationForm string `json:"normalizationForm,omitempty"`
+
+	// MinGram The minimum length of generated n-grams. Must be less than or equal to maxGram. Apply for type: nGram, edgeGram
+	MinGram *int `json:"minGram,omitempty"`
+
+	// MaxGram The maximum length of generated n-grams. Must be greater than or equal to minGram. Apply for type: nGram, edgeGram
+	MaxGram *int `json:"maxGram,omitempty"`
+
+	// TermsNotInBounds Accepted values are: include, omit
+	// If include is specified, tokens shorter than minGram or longer than maxGram are indexed as-is. If omit is specified,
+	// those tokens are not indexed. Apply for type: nGram, edgeGram
+	TermsNotInBounds string `json:"termsNotInBounds,omitempty"`
+
+	// MinShingleSize Minimum number of tokens per shingle. Must be less than or equal to maxShingleSize. Apply for type: shingle
+	MinShingleSize *int `json:"minShingleSize,omitempty"`
+
+	// MaxShingleSize Maximum number of tokens per shingle. Must be greater than or equal to minShingleSize. Apply for type: shingle
+	MaxShingleSize *int `json:"maxShingleSize,omitempty"`
+
+	// Pattern Regular expression pattern to apply to each token. Apply for type: regex
+	Pattern string `json:"pattern,omitempty"`
+
+	// Replacement Replacement string to substitute wherever a matching pattern occurs. Apply for type: regex
+	Replacement string `json:"replacement,omitempty"`
+
+	// Matches Acceptable values are: all, first
+	// If matches is set to all, replace all matching patterns. Otherwise, replace only the first matching pattern. Apply for type: regex
+	Matches string `json:"matches,omitempty"`
+
+	// StemmerName Apply for type: snowballStemming
+	StemmerName string `json:"stemmerName,omitempty"`
+
+	// Tokens The list of stop words that correspond to the tokens to remove. Value must be one or more stop words. Apply for type: stopword
+	Tokens []string `json:"tokens,omitempty"`
+
+	// IgnoreCase The flag that indicates whether or not to ignore case of stop words when filtering the tokens to remove. The value can be one of the following:
+	// true - to ignore case and remove all tokens that match the specified stop words
+	// false - to be case-sensitive and remove only tokens that exactly match the specified case
+	// If omitted, defaults to true. Apply for type: stopword
+	IgnoreCase *bool `json:"ignoreCase,omitempty"`
+}