expose length again (Azure#18505)

jongio · Feb 9, 2021 · 4d27fd1 · 4d27fd1
1 parent d94939e
commit 4d27fd1
Show file tree

Hide file tree

Showing 30 changed files with 104 additions and 31 deletions.
diff --git a/sdk/textanalytics/Azure.AI.TextAnalytics/CHANGELOG.md b/sdk/textanalytics/Azure.AI.TextAnalytics/CHANGELOG.md
@@ -1,6 +1,9 @@
 # Release History
 
 ## 5.1.0-beta.4 (Unreleased)
+### New features
+- Added property `Length` to `CategorizedEntity`, `SentenceSentiment`, `LinkedEntityMatch`, `AspectSentiment`, `OpinionSentiment`, and `PiiEntity`.
+- `StringIndexType` has been added to all endpoints as a new option to control how the `Offset` and `Length` are calculated by the service.
 
 ### Breaking changes
 - Renamed `RecognizeHealthcareEntitiesResultCollection` to `AnalyzeHealthcareEntitiesResultCollection`.

diff --git a/sdk/textanalytics/Azure.AI.TextAnalytics/README.md b/sdk/textanalytics/Azure.AI.TextAnalytics/README.md
@@ -252,6 +252,7 @@ try
     {
         Console.WriteLine($"  Text: {entity.Text}");
         Console.WriteLine($"  Offset: {entity.Offset}");
+        Console.WriteLine($"  Length: {entity.Length}");
         Console.WriteLine($"  Category: {entity.Category}");
         if (!string.IsNullOrEmpty(entity.SubCategory))
             Console.WriteLine($"  SubCategory: {entity.SubCategory}");
@@ -333,6 +334,7 @@ try
         {
             Console.WriteLine($"    Match Text: {match.Text}");
             Console.WriteLine($"    Offset: {match.Offset}");
+            Console.WriteLine($"    Length: {match.Length}");
             Console.WriteLine($"    Confidence score: {match.ConfidenceScore}");
         }
         Console.WriteLine("");
@@ -394,6 +396,7 @@ try
     {
         Console.WriteLine($"    Text: {entity.Text}");
         Console.WriteLine($"    Offset: {entity.Offset}");
+        Console.WriteLine($"  Length: {entity.Length}");
         Console.WriteLine($"    Category: {entity.Category}");
         if (!string.IsNullOrEmpty(entity.SubCategory))
             Console.WriteLine($"    SubCategory: {entity.SubCategory}");

diff --git a/sdk/textanalytics/Azure.AI.TextAnalytics/api/Azure.AI.TextAnalytics.netstandard2.0.cs b/sdk/textanalytics/Azure.AI.TextAnalytics/api/Azure.AI.TextAnalytics.netstandard2.0.cs
@@ -103,6 +103,7 @@ public readonly partial struct AspectSentiment
         private readonly object _dummy;
         private readonly int _dummyPrimitive;
         public Azure.AI.TextAnalytics.SentimentConfidenceScores ConfidenceScores { get { throw null; } }
+        public int Length { get { throw null; } }
         public int Offset { get { throw null; } }
         public Azure.AI.TextAnalytics.TextSentiment Sentiment { get { throw null; } }
         public string Text { get { throw null; } }
@@ -114,6 +115,7 @@ public readonly partial struct CategorizedEntity
         private readonly int _dummyPrimitive;
         public Azure.AI.TextAnalytics.EntityCategory Category { get { throw null; } }
         public double ConfidenceScore { get { throw null; } }
+        public int Length { get { throw null; } }
         public int Offset { get { throw null; } }
         public string SubCategory { get { throw null; } }
         public string Text { get { throw null; } }
@@ -310,6 +312,7 @@ public readonly partial struct LinkedEntityMatch
         private readonly object _dummy;
         private readonly int _dummyPrimitive;
         public double ConfidenceScore { get { throw null; } }
+        public int Length { get { throw null; } }
         public int Offset { get { throw null; } }
         public string Text { get { throw null; } }
     }
@@ -328,6 +331,7 @@ public readonly partial struct OpinionSentiment
         private readonly int _dummyPrimitive;
         public Azure.AI.TextAnalytics.SentimentConfidenceScores ConfidenceScores { get { throw null; } }
         public bool IsNegated { get { throw null; } }
+        public int Length { get { throw null; } }
         public int Offset { get { throw null; } }
         public Azure.AI.TextAnalytics.TextSentiment Sentiment { get { throw null; } }
         public string Text { get { throw null; } }
@@ -346,6 +350,7 @@ public readonly partial struct PiiEntity
         private readonly int _dummyPrimitive;
         public Azure.AI.TextAnalytics.EntityCategory Category { get { throw null; } }
         public double ConfidenceScore { get { throw null; } }
+        public int Length { get { throw null; } }
         public int Offset { get { throw null; } }
         public string SubCategory { get { throw null; } }
         public string Text { get { throw null; } }
@@ -434,6 +439,7 @@ public readonly partial struct SentenceSentiment
         private readonly object _dummy;
         private readonly int _dummyPrimitive;
         public Azure.AI.TextAnalytics.SentimentConfidenceScores ConfidenceScores { get { throw null; } }
+        public int Length { get { throw null; } }
         public System.Collections.Generic.IReadOnlyCollection<Azure.AI.TextAnalytics.MinedOpinion> MinedOpinions { get { throw null; } }
         public int Offset { get { throw null; } }
         public Azure.AI.TextAnalytics.TextSentiment Sentiment { get { throw null; } }
@@ -607,7 +613,7 @@ public static partial class TextAnalyticsModelFactory
         public static Azure.AI.TextAnalytics.AnalyzeSentimentResult AnalyzeSentimentResult(string id, Azure.AI.TextAnalytics.TextAnalyticsError error) { throw null; }
         public static Azure.AI.TextAnalytics.AnalyzeSentimentResult AnalyzeSentimentResult(string id, Azure.AI.TextAnalytics.TextDocumentStatistics statistics, Azure.AI.TextAnalytics.DocumentSentiment documentSentiment) { throw null; }
         public static Azure.AI.TextAnalytics.AnalyzeSentimentResultCollection AnalyzeSentimentResultCollection(System.Collections.Generic.IEnumerable<Azure.AI.TextAnalytics.AnalyzeSentimentResult> list, Azure.AI.TextAnalytics.TextDocumentBatchStatistics statistics, string modelVersion) { throw null; }
-        public static Azure.AI.TextAnalytics.AspectSentiment AspectSentiment(Azure.AI.TextAnalytics.TextSentiment sentiment, string text, double positiveScore, double negativeScore, int offset) { throw null; }
+        public static Azure.AI.TextAnalytics.AspectSentiment AspectSentiment(Azure.AI.TextAnalytics.TextSentiment sentiment, string text, double positiveScore, double negativeScore, int offset, int length) { throw null; }
         [System.ComponentModel.EditorBrowsableAttribute(System.ComponentModel.EditorBrowsableState.Never)]
         public static Azure.AI.TextAnalytics.CategorizedEntity CategorizedEntity(string text, string category, string subCategory, double score) { throw null; }
         public static Azure.AI.TextAnalytics.CategorizedEntity CategorizedEntity(string text, string category, string subCategory, double score, int offset) { throw null; }
@@ -627,9 +633,9 @@ public static partial class TextAnalyticsModelFactory
         public static Azure.AI.TextAnalytics.LinkedEntityCollection LinkedEntityCollection(System.Collections.Generic.IList<Azure.AI.TextAnalytics.LinkedEntity> entities, System.Collections.Generic.IList<Azure.AI.TextAnalytics.TextAnalyticsWarning> warnings = null) { throw null; }
         [System.ComponentModel.EditorBrowsableAttribute(System.ComponentModel.EditorBrowsableState.Never)]
         public static Azure.AI.TextAnalytics.LinkedEntityMatch LinkedEntityMatch(string text, double score) { throw null; }
-        public static Azure.AI.TextAnalytics.LinkedEntityMatch LinkedEntityMatch(string text, double score, int offset) { throw null; }
+        public static Azure.AI.TextAnalytics.LinkedEntityMatch LinkedEntityMatch(string text, double score, int offset, int length) { throw null; }
         public static Azure.AI.TextAnalytics.MinedOpinion MinedOpinion(Azure.AI.TextAnalytics.AspectSentiment aspect, System.Collections.Generic.IReadOnlyList<Azure.AI.TextAnalytics.OpinionSentiment> opinions) { throw null; }
-        public static Azure.AI.TextAnalytics.OpinionSentiment OpinionSentiment(Azure.AI.TextAnalytics.TextSentiment sentiment, double positiveScore, double negativeScore, string text, bool isNegated, int offset) { throw null; }
+        public static Azure.AI.TextAnalytics.OpinionSentiment OpinionSentiment(Azure.AI.TextAnalytics.TextSentiment sentiment, double positiveScore, double negativeScore, string text, bool isNegated, int offset, int length) { throw null; }
         public static Azure.AI.TextAnalytics.PiiEntity PiiEntity(string text, string category, string subCategory, double score, int offset) { throw null; }
         public static Azure.AI.TextAnalytics.PiiEntityCollection PiiEntityCollection(System.Collections.Generic.IList<Azure.AI.TextAnalytics.PiiEntity> entities, string redactedText, System.Collections.Generic.IList<Azure.AI.TextAnalytics.TextAnalyticsWarning> warnings = null) { throw null; }
         public static Azure.AI.TextAnalytics.RecognizeEntitiesResult RecognizeEntitiesResult(string id, Azure.AI.TextAnalytics.TextAnalyticsError error) { throw null; }
@@ -643,7 +649,7 @@ public static partial class TextAnalyticsModelFactory
         public static Azure.AI.TextAnalytics.RecognizePiiEntitiesResultCollection RecognizePiiEntitiesResultCollection(System.Collections.Generic.IEnumerable<Azure.AI.TextAnalytics.RecognizePiiEntitiesResult> list, Azure.AI.TextAnalytics.TextDocumentBatchStatistics statistics, string modelVersion) { throw null; }
         [System.ComponentModel.EditorBrowsableAttribute(System.ComponentModel.EditorBrowsableState.Never)]
         public static Azure.AI.TextAnalytics.SentenceSentiment SentenceSentiment(Azure.AI.TextAnalytics.TextSentiment sentiment, string text, double positiveScore, double neutralScore, double negativeScore) { throw null; }
-        public static Azure.AI.TextAnalytics.SentenceSentiment SentenceSentiment(Azure.AI.TextAnalytics.TextSentiment sentiment, string text, double positiveScore, double neutralScore, double negativeScore, int offset, System.Collections.Generic.IReadOnlyList<Azure.AI.TextAnalytics.MinedOpinion> minedOpinions) { throw null; }
+        public static Azure.AI.TextAnalytics.SentenceSentiment SentenceSentiment(Azure.AI.TextAnalytics.TextSentiment sentiment, string text, double positiveScore, double neutralScore, double negativeScore, int offset, int length, System.Collections.Generic.IReadOnlyList<Azure.AI.TextAnalytics.MinedOpinion> minedOpinions) { throw null; }
         public static Azure.AI.TextAnalytics.SentimentConfidenceScores SentimentConfidenceScores(double positiveScore, double neutralScore, double negativeScore) { throw null; }
         public static Azure.AI.TextAnalytics.TextAnalyticsError TextAnalyticsError(string code, string message, string target = null) { throw null; }
         public static Azure.AI.TextAnalytics.TextAnalyticsWarning TextAnalyticsWarning(string code, string message) { throw null; }

diff --git a/sdk/textanalytics/Azure.AI.TextAnalytics/samples/Sample4_RecognizeEntities.md b/sdk/textanalytics/Azure.AI.TextAnalytics/samples/Sample4_RecognizeEntities.md
@@ -35,6 +35,7 @@ try
     {
         Console.WriteLine($"  Text: {entity.Text}");
         Console.WriteLine($"  Offset: {entity.Offset}");
+        Console.WriteLine($"  Length: {entity.Length}");
         Console.WriteLine($"  Category: {entity.Category}");
         if (!string.IsNullOrEmpty(entity.SubCategory))
             Console.WriteLine($"  SubCategory: {entity.SubCategory}");
@@ -107,6 +108,7 @@ foreach (RecognizeEntitiesResult entitiesInDocument in entititesPerDocuments)
         {
             Console.WriteLine($"    Text: {entity.Text}");
             Console.WriteLine($"    Offset: {entity.Offset}");
+            Console.WriteLine($"    Length: {entity.Length}");
             Console.WriteLine($"    Category: {entity.Category}");
             if (!string.IsNullOrEmpty(entity.SubCategory))
                 Console.WriteLine($"    SubCategory: {entity.SubCategory}");
@@ -184,6 +186,7 @@ foreach (RecognizeEntitiesResult entitiesInDocument in entitiesInDocuments)
         {
             Console.WriteLine($"    Text: {entity.Text}");
             Console.WriteLine($"    Offset: {entity.Offset}");
+            Console.WriteLine($"    Length: {entity.Length}");
             Console.WriteLine($"    Category: {entity.Category}");
             if (!string.IsNullOrEmpty(entity.SubCategory))
                 Console.WriteLine($"    SubCategory: {entity.SubCategory}");

diff --git a/...textanalytics/Azure.AI.TextAnalytics/samples/Sample6_RecognizeLinkedEntities.md b/...textanalytics/Azure.AI.TextAnalytics/samples/Sample6_RecognizeLinkedEntities.md
@@ -41,6 +41,7 @@ try
         {
             Console.WriteLine($"    Match Text: {match.Text}");
             Console.WriteLine($"    Offset: {match.Offset}");
+            Console.WriteLine($"    Length: {match.Length}");
             Console.WriteLine($"    Confidence score: {match.ConfidenceScore}");
         }
         Console.WriteLine("");
@@ -110,6 +111,7 @@ foreach (RecognizeLinkedEntitiesResult entitiesInDocument in entitiesInDocuments
             {
                 Console.WriteLine($"    Match Text: {match.Text}");
                 Console.WriteLine($"    Offset: {match.Offset}");
+                Console.WriteLine($"    Length: {match.Length}");
                 Console.WriteLine($"    Confidence score: {match.ConfidenceScore}");
             }
             Console.WriteLine("");
@@ -187,6 +189,7 @@ foreach (RecognizeLinkedEntitiesResult entitiesInDocument in entitiesPerDocument
             {
                 Console.WriteLine($"    Match Text: {match.Text}");
                 Console.WriteLine($"    Offset: {match.Offset}");
+                Console.WriteLine($"    Length: {match.Length}");
                 Console.WriteLine($"    Confidence score: {match.ConfidenceScore}");
             }
             Console.WriteLine("");

diff --git a/sdk/textanalytics/Azure.AI.TextAnalytics/src/AspectSentiment.cs b/sdk/textanalytics/Azure.AI.TextAnalytics/src/AspectSentiment.cs
@@ -17,12 +17,13 @@ public readonly struct AspectSentiment
     {
         private const double _neutralValue = 0d;
 
-        internal AspectSentiment(TextSentiment sentiment, string text, double positiveScore, double negativeScore, int offset)
+        internal AspectSentiment(TextSentiment sentiment, string text, double positiveScore, double negativeScore, int offset, int length)
         {
             Sentiment = sentiment;
             Text = text;
             ConfidenceScores = new SentimentConfidenceScores(positiveScore, _neutralValue, negativeScore);
             Offset = offset;
+            Length = length;
         }
 
         internal AspectSentiment(SentenceAspect sentenceAspect)
@@ -33,6 +34,7 @@ internal AspectSentiment(SentenceAspect sentenceAspect)
             ConfidenceScores = new SentimentConfidenceScores(sentenceAspect.ConfidenceScores.Positive, _neutralValue, sentenceAspect.ConfidenceScores.Negative);
             Sentiment = (TextSentiment)Enum.Parse(typeof(TextSentiment), sentenceAspect.Sentiment, ignoreCase: true);
             Offset = sentenceAspect.Offset;
+            Length = sentenceAspect.Length;
         }
 
         /// <summary>
@@ -57,8 +59,13 @@ internal AspectSentiment(SentenceAspect sentenceAspect)
         public SentimentConfidenceScores ConfidenceScores { get; }
 
         /// <summary>
-        /// Gets the starting position (in UTF-16 code units) for the aspect text.
+        /// Gets the starting position for the aspect text.
         /// </summary>
         public int Offset { get; }
+
+        /// <summary>
+        /// Gets the length of the aspect text.
+        /// </summary>
+        public int Length { get; }
     }
 }
diff --git a/sdk/textanalytics/Azure.AI.TextAnalytics/src/CategorizedEntity.cs b/sdk/textanalytics/Azure.AI.TextAnalytics/src/CategorizedEntity.cs
@@ -22,6 +22,7 @@ internal CategorizedEntity(Entity entity)
             SubCategory = entity.Subcategory;
             ConfidenceScore = entity.ConfidenceScore;
             Offset = entity.Offset;
+            Length = entity.Length;
         }
 
         /// <summary>
@@ -53,8 +54,13 @@ internal CategorizedEntity(Entity entity)
         public double ConfidenceScore { get; }
 
         /// <summary>
-        /// Gets the starting position (in UTF-16 code units) for the matching text in the input document.
+        /// Gets the starting position for the matching text in the input document.
         /// </summary>
         public int Offset { get; }
+
+        /// <summary>
+        /// Gets the length of the matching text in the input document.
+        /// </summary>
+        public int Length { get; }
     }
 }
diff --git a/sdk/textanalytics/Azure.AI.TextAnalytics/src/HealthcareEntity.cs b/sdk/textanalytics/Azure.AI.TextAnalytics/src/HealthcareEntity.cs
@@ -50,7 +50,7 @@ internal HealthcareEntity(HealthcareEntityInternal entity)
         public double ConfidenceScore { get; }
 
         /// <summary>
-        /// Gets the starting position (in UTF-16 code units) for the matching text in the input document.
+        /// Gets the starting position for the matching text in the input document.
         /// </summary>
         public int Offset { get; }
 

diff --git a/sdk/textanalytics/Azure.AI.TextAnalytics/src/LinkedEntityMatch.cs b/sdk/textanalytics/Azure.AI.TextAnalytics/src/LinkedEntityMatch.cs
@@ -13,18 +13,14 @@ namespace Azure.AI.TextAnalytics
     [CodeGenModel("Match")]
     public readonly partial struct LinkedEntityMatch
     {
-        // use for deserialization
         internal LinkedEntityMatch(double confidenceScore, string text, int offset, int length)
-            : this(confidenceScore, text, offset) => Length = length;
-
-        internal LinkedEntityMatch(double confidenceScore, string text, int offset)
         {
             // We shipped TA 5.0.0 Text == string.Empty if the service returned a null value for Text.
             // Because we don't want to introduce a breaking change, we are transforming that null to string.Empty
             Text = text ?? string.Empty;
             ConfidenceScore = confidenceScore;
             Offset = offset;
-            Length = default;
+            Length = length;
         }
 
         /// <summary>
@@ -39,13 +35,13 @@ internal LinkedEntityMatch(double confidenceScore, string text, int offset)
         public double ConfidenceScore { get; }
 
         /// <summary>
-        /// Gets the starting position (in UTF-16 code units) for the matching text in the document.
+        /// Gets the starting position for the matching text in the document.
         /// </summary>
         public int Offset { get; }
 
         /// <summary>
-        /// Gets the length (in UTF-16 code units) of the matching text in the sentence.
+        /// Gets the length of the matching text in the sentence.
         /// </summary>
-        private int Length { get; }
+        public int Length { get; }
     }
 }
diff --git a/sdk/textanalytics/Azure.AI.TextAnalytics/src/OpinionSentiment.cs b/sdk/textanalytics/Azure.AI.TextAnalytics/src/OpinionSentiment.cs
@@ -15,13 +15,14 @@ public readonly struct OpinionSentiment
     {
         private const double _neutralValue = 0d;
 
-        internal OpinionSentiment(TextSentiment sentiment, double positiveScore, double negativeScore, string text, bool isNegated, int offset)
+        internal OpinionSentiment(TextSentiment sentiment, double positiveScore, double negativeScore, string text, bool isNegated, int offset, int length)
         {
             Sentiment = sentiment;
             ConfidenceScores = new SentimentConfidenceScores(positiveScore, _neutralValue, negativeScore);
             Text = text;
             IsNegated = isNegated;
             Offset = offset;
+            Length = length;
         }
 
         internal OpinionSentiment(SentenceOpinion opinion)
@@ -33,6 +34,7 @@ internal OpinionSentiment(SentenceOpinion opinion)
             Sentiment = (TextSentiment)Enum.Parse(typeof(TextSentiment), opinion.Sentiment, ignoreCase: true);
             IsNegated = opinion.IsNegated;
             Offset = opinion.Offset;
+            Length = opinion.Length;
         }
 
         /// <summary>
@@ -63,8 +65,13 @@ internal OpinionSentiment(SentenceOpinion opinion)
         public bool IsNegated { get; }
 
         /// <summary>
-        /// Gets the starting position (in UTF-16 code units) for the opinion text.
+        /// Gets the starting position for the opinion text.
         /// </summary>
         public int Offset { get; }
+
+        /// <summary>
+        /// Gets the length of the opinion text.
+        /// </summary>
+        public int Length { get; }
     }
 }
diff --git a/sdk/textanalytics/Azure.AI.TextAnalytics/src/PiiEntity.cs b/sdk/textanalytics/Azure.AI.TextAnalytics/src/PiiEntity.cs
@@ -20,6 +20,7 @@ internal PiiEntity(Entity entity)
             SubCategory = entity.Subcategory;
             ConfidenceScore = entity.ConfidenceScore;
             Offset = entity.Offset;
+            Length = entity.Length;
         }
 
         /// <summary>
@@ -51,8 +52,13 @@ internal PiiEntity(Entity entity)
         public double ConfidenceScore { get; }
 
         /// <summary>
-        /// Gets the starting position (in UTF-16 code units) for the matching text in the input document.
+        /// Gets the starting position for the matching text in the input document.
         /// </summary>
         public int Offset { get; }
+
+        /// <summary>
+        /// Gets the length of the matching text in the input document.
+        /// </summary>
+        public int Length { get; }
     }
 }