Porting quoted text recognizer into project - v0 (#2528)

* Add QuotedText recognizer skeleton

* Add structure to support multi-language

* Add English and Chinese quoted recognizer

* Add initial test spec cases

* Refinements according to code review

* Add NotSupportedByDesign annotations to test specs

* Update text model and fix code style issues

* Add multi-language quoted text recognizers

* Update QuotedText recognizer to expose models

* Filter French frequent false positive in Currency

* Fix build break

* Add NotSupportedByDesign attributes in specs for all non-dotnet platforms


Co-authored-by: Tom Laird-McConnell <[email protected]>

.NET/Microsoft.Recognizers.Definitions.Common/BaseQuotedText.cs

@@ -0,0 +1,26 @@
+//------------------------------------------------------------------------------
+// <auto-generated>
+//     This code was generated by a tool.
+//     Changes to this file may cause incorrect behavior and will be lost if
+//     the code is regenerated.
+//
+//     Generation parameters:
+//     - DataFilename: Patterns\Base-QuotedText.yaml
+//     - Language: NULL
+//     - ClassName: BaseQuotedText
+// </auto-generated>
+//
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License.
+// ------------------------------------------------------------------------------
+
+namespace Microsoft.Recognizers.Definitions
+{
+    using System;
+    using System.Collections.Generic;
+
+    public static class BaseQuotedText
+    {
+      public const string QuotedTextRegex = @"('([a-zA-Z0-9_]+)')";
+    }
+}

.NET/Microsoft.Recognizers.Definitions.Common/BaseQuotedText.tt

@@ -0,0 +1,7 @@
+<#@ template debug="true" hostspecific="true" language="C#" #>
+<#
+	this.DataFilename = @"Patterns\Base-QuotedText.yaml";
+	this.Language = null;
+	this.ClassName = "BaseQuotedText";
+#>
+<#@ include file=".\CommonDefinitions.ttinclude"#>

.NET/Microsoft.Recognizers.Definitions.Common/Chinese/QuotedTextDefinitions.cs

@@ -0,0 +1,35 @@
+//------------------------------------------------------------------------------
+// <auto-generated>
+//     This code was generated by a tool.
+//     Changes to this file may cause incorrect behavior and will be lost if
+//     the code is regenerated.
+//
+//     Generation parameters:
+//     - DataFilename: Patterns\Chinese\Chinese-QuotedText.yaml
+//     - Language: Chinese
+//     - ClassName: QuotedTextDefinitions
+// </auto-generated>
+//
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License.
+// ------------------------------------------------------------------------------
+
+namespace Microsoft.Recognizers.Definitions.Chinese
+{
+    using System;
+    using System.Collections.Generic;
+
+    public static class QuotedTextDefinitions
+    {
+      public const string LangMarker = @"Chs";
+      public const string QuotedTextRegex1 = @"(“([^“”]+)”)";
+      public const string QuotedTextRegex2 = @"(‘([^‘’]+)’)";
+      public const string QuotedTextRegex3 = @"(『([^『』]+)』)";
+      public const string QuotedTextRegex4 = @"(「([^「」]+)」)";
+      public const string QuotedTextRegex5 = @"(﹃([^﹃﹄]+)﹄)";
+      public const string QuotedTextRegex6 = @"(﹁([^﹁﹂]+)﹂)";
+      public const string QuotedTextRegex7 = @"(""([^""]+)"")";
+      public const string QuotedTextRegex8 = @"(\\'([^\']+)\\')";
+      public const string QuotedTextRegex9 = @"(`([^`]+)`)";
+    }
+}

.NET/Microsoft.Recognizers.Definitions.Common/Chinese/QuotedTextDefinitions.tt

@@ -0,0 +1,7 @@
+<#@ template debug="true" hostspecific="true" language="C#" #>
+<#
+	this.DataFilename = @"Patterns\Chinese\Chinese-QuotedText.yaml";
+	this.Language = "Chinese";
+	this.ClassName = "QuotedTextDefinitions";
+#>
+<#@ include file="..\CommonDefinitions.ttinclude"#>

.NET/Microsoft.Recognizers.Definitions.Common/Dutch/QuotedTextDefinitions.cs

@@ -0,0 +1,35 @@
+//------------------------------------------------------------------------------
+// <auto-generated>
+//     This code was generated by a tool.
+//     Changes to this file may cause incorrect behavior and will be lost if
+//     the code is regenerated.
+//
+//     Generation parameters:
+//     - DataFilename: Patterns\Dutch\Dutch-QuotedText.yaml
+//     - Language: Dutch
+//     - ClassName: QuotedTextDefinitions
+// </auto-generated>
+//
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License.
+// ------------------------------------------------------------------------------
+
+namespace Microsoft.Recognizers.Definitions.Dutch
+{
+    using System;
+    using System.Collections.Generic;
+
+    public static class QuotedTextDefinitions
+    {
+      public const string LangMarker = @"Dut";
+      public const string QuotedTextRegex1 = @"(“([^“”]+)”)";
+      public const string QuotedTextRegex2 = @"(‘([^‘’]+)’)";
+      public const string QuotedTextRegex3 = @"(„([^„”]+)”)";
+      public const string QuotedTextRegex4 = @"(,([^,’']+)[’'])";
+      public const string QuotedTextRegex5 = @"(""([^""]+)"")";
+      public const string QuotedTextRegex6 = @"(\\'([^\']+)\\')";
+      public const string QuotedTextRegex7 = @"(`([^`]+)`)";
+      public const string QuotedTextRegex8 = @"(123456)";
+      public const string QuotedTextRegex9 = @"(123456)";
+    }
+}

.NET/Microsoft.Recognizers.Definitions.Common/Dutch/QuotedTextDefinitions.tt

@@ -0,0 +1,7 @@
+<#@ template debug="true" hostspecific="true" language="C#" #>
+<#
+	this.DataFilename = @"Patterns\Dutch\Dutch-QuotedText.yaml";
+	this.Language = "Dutch";
+	this.ClassName = "QuotedTextDefinitions";
+#>
+<#@ include file="..\CommonDefinitions.ttinclude"#>

.NET/Microsoft.Recognizers.Definitions.Common/English/QuotedTextDefinitions.cs

@@ -0,0 +1,35 @@
+//------------------------------------------------------------------------------
+// <auto-generated>
+//     This code was generated by a tool.
+//     Changes to this file may cause incorrect behavior and will be lost if
+//     the code is regenerated.
+//
+//     Generation parameters:
+//     - DataFilename: Patterns\English\English-QuotedText.yaml
+//     - Language: English
+//     - ClassName: QuotedTextDefinitions
+// </auto-generated>
+//
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License.
+// ------------------------------------------------------------------------------
+
+namespace Microsoft.Recognizers.Definitions.English
+{
+    using System;
+    using System.Collections.Generic;
+
+    public static class QuotedTextDefinitions
+    {
+      public const string LangMarker = @"Eng";
+      public const string QuotedTextRegex1 = @"(“([^“”]+)”)";
+      public const string QuotedTextRegex2 = @"(‘([^‘’]+)’)";
+      public const string QuotedTextRegex3 = @"(""([^""]+)"")";
+      public const string QuotedTextRegex4 = @"(\\'([^\']+)\\')";
+      public const string QuotedTextRegex5 = @"(`([^`]+)`)";
+      public const string QuotedTextRegex6 = @"(123456)";
+      public const string QuotedTextRegex7 = @"(123456)";
+      public const string QuotedTextRegex8 = @"(123456)";
+      public const string QuotedTextRegex9 = @"(123456)";
+    }
+}

.NET/Microsoft.Recognizers.Definitions.Common/English/QuotedTextDefinitions.tt

@@ -0,0 +1,7 @@
+<#@ template debug="true" hostspecific="true" language="C#" #>
+<#
+	this.DataFilename = @"Patterns\English\English-QuotedText.yaml";
+	this.Language = "English";
+	this.ClassName = "QuotedTextDefinitions";
+#>
+<#@ include file="..\CommonDefinitions.ttinclude"#>

.NET/Microsoft.Recognizers.Definitions.Common/French/NumbersWithUnitDefinitions.cs

@@ -604,7 +604,8 @@ public static class NumbersWithUnitDefinitions
             @"sos",
             @"std",
             @"try",
-            @"yer"
+            @"yer",
+            @"livre"
         };
       public static readonly Dictionary<string, string> InformationSuffixList = new Dictionary<string, string>
         {

.NET/Microsoft.Recognizers.Definitions.Common/French/QuotedTextDefinitions.cs

@@ -0,0 +1,35 @@
+//------------------------------------------------------------------------------
+// <auto-generated>
+//     This code was generated by a tool.
+//     Changes to this file may cause incorrect behavior and will be lost if
+//     the code is regenerated.
+//
+//     Generation parameters:
+//     - DataFilename: Patterns\French\French-QuotedText.yaml
+//     - Language: French
+//     - ClassName: QuotedTextDefinitions
+// </auto-generated>
+//
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License.
+// ------------------------------------------------------------------------------
+
+namespace Microsoft.Recognizers.Definitions.French
+{
+    using System;
+    using System.Collections.Generic;
+
+    public static class QuotedTextDefinitions
+    {
+      public const string LangMarker = @"Fr";
+      public const string QuotedTextRegex1 = @"(“([^“”]+)”)";
+      public const string QuotedTextRegex2 = @"(‘([^‘’]+)’)";
+      public const string QuotedTextRegex3 = @"(""([^""]+)"")";
+      public const string QuotedTextRegex4 = @"(\\'([^\']+)\\')";
+      public const string QuotedTextRegex5 = @"(`([^`]+)`)";
+      public const string QuotedTextRegex6 = @"(«([^«»]+)»)";
+      public const string QuotedTextRegex7 = @"(‹([^‹›]+)›)";
+      public const string QuotedTextRegex8 = @"(123456)";
+      public const string QuotedTextRegex9 = @"(123456)---";
+    }
+}

.NET/Microsoft.Recognizers.Definitions.Common/French/QuotedTextDefinitions.tt

@@ -0,0 +1,7 @@
+<#@ template debug="true" hostspecific="true" language="C#" #>
+<#
+	this.DataFilename = @"Patterns\French\French-QuotedText.yaml";
+	this.Language = "French";
+	this.ClassName = "QuotedTextDefinitions";
+#>
+<#@ include file="..\CommonDefinitions.ttinclude"#>

.NET/Microsoft.Recognizers.Definitions.Common/German/QuotedTextDefinitions.cs

@@ -0,0 +1,35 @@
+//------------------------------------------------------------------------------
+// <auto-generated>
+//     This code was generated by a tool.
+//     Changes to this file may cause incorrect behavior and will be lost if
+//     the code is regenerated.
+//
+//     Generation parameters:
+//     - DataFilename: Patterns\German\German-QuotedText.yaml
+//     - Language: German
+//     - ClassName: QuotedTextDefinitions
+// </auto-generated>
+//
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License.
+// ------------------------------------------------------------------------------
+
+namespace Microsoft.Recognizers.Definitions.German
+{
+    using System;
+    using System.Collections.Generic;
+
+    public static class QuotedTextDefinitions
+    {
+      public const string LangMarker = @"Ger";
+      public const string QuotedTextRegex1 = @"(„([^„“]+)“)";
+      public const string QuotedTextRegex2 = @"(‚([^‚‘]+)‘)";
+      public const string QuotedTextRegex3 = @"(""([^""]+)"")";
+      public const string QuotedTextRegex4 = @"(\\'([^\']+)\\')";
+      public const string QuotedTextRegex5 = @"(`([^`]+)`)";
+      public const string QuotedTextRegex6 = @"(«([^«»]+)»)";
+      public const string QuotedTextRegex7 = @"(‹([^‹›]+)›)";
+      public const string QuotedTextRegex8 = @"(»([^»«]+)«)";
+      public const string QuotedTextRegex9 = @"(›([^›‹]+)‹)";
+    }
+}

.NET/Microsoft.Recognizers.Definitions.Common/German/QuotedTextDefinitions.tt

@@ -0,0 +1,7 @@
+<#@ template debug="true" hostspecific="true" language="C#" #>
+<#
+	this.DataFilename = @"Patterns\German\German-QuotedText.yaml";
+	this.Language = "German";
+	this.ClassName = "QuotedTextDefinitions";
+#>
+<#@ include file="..\CommonDefinitions.ttinclude"#>

.NET/Microsoft.Recognizers.Definitions.Common/Hindi/QuotedTextDefinitions.cs

@@ -0,0 +1,35 @@
+//------------------------------------------------------------------------------
+// <auto-generated>
+//     This code was generated by a tool.
+//     Changes to this file may cause incorrect behavior and will be lost if
+//     the code is regenerated.
+//
+//     Generation parameters:
+//     - DataFilename: Patterns\Hindi\Hindi-QuotedText.yaml
+//     - Language: Hindi
+//     - ClassName: QuotedTextDefinitions
+// </auto-generated>
+//
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License.
+// ------------------------------------------------------------------------------
+
+namespace Microsoft.Recognizers.Definitions.Hindi
+{
+    using System;
+    using System.Collections.Generic;
+
+    public static class QuotedTextDefinitions
+    {
+      public const string LangMarker = @"Hin";
+      public const string QuotedTextRegex1 = @"(“([^“”]+)”)";
+      public const string QuotedTextRegex2 = @"(‘([^‘’]+)’)";
+      public const string QuotedTextRegex3 = @"(""([^""]+)"")";
+      public const string QuotedTextRegex4 = @"(\\'([^\']+)\\')";
+      public const string QuotedTextRegex5 = @"(`([^`]+)`)";
+      public const string QuotedTextRegex6 = @"(123456)";
+      public const string QuotedTextRegex7 = @"(123456)";
+      public const string QuotedTextRegex8 = @"(123456)";
+      public const string QuotedTextRegex9 = @"(123456)";
+    }
+}

.NET/Microsoft.Recognizers.Definitions.Common/Hindi/QuotedTextDefinitions.tt

@@ -0,0 +1,7 @@
+<#@ template debug="true" hostspecific="true" language="C#" #>
+<#
+	this.DataFilename = @"Patterns\Hindi\Hindi-QuotedText.yaml";
+	this.Language = "Hindi";
+	this.ClassName = "QuotedTextDefinitions";
+#>
+<#@ include file="..\CommonDefinitions.ttinclude"#>

.NET/Microsoft.Recognizers.Definitions.Common/Italian/QuotedTextDefinitions.cs

@@ -0,0 +1,35 @@
+//------------------------------------------------------------------------------
+// <auto-generated>
+//     This code was generated by a tool.
+//     Changes to this file may cause incorrect behavior and will be lost if
+//     the code is regenerated.
+//
+//     Generation parameters:
+//     - DataFilename: Patterns\Italian\Italian-QuotedText.yaml
+//     - Language: Italian
+//     - ClassName: QuotedTextDefinitions
+// </auto-generated>
+//
+// Copyright (c) Microsoft Corporation. All rights reserved.
+// Licensed under the MIT License.
+// ------------------------------------------------------------------------------
+
+namespace Microsoft.Recognizers.Definitions.Italian
+{
+    using System;
+    using System.Collections.Generic;
+
+    public static class QuotedTextDefinitions
+    {
+      public const string LangMarker = @"Ita";
+      public const string QuotedTextRegex1 = @"(“([^“”]+)”)";
+      public const string QuotedTextRegex2 = @"(‘([^‘’]+)’)";
+      public const string QuotedTextRegex3 = @"(""([^""]+)"")";
+      public const string QuotedTextRegex4 = @"(\\'([^\']+)\\')";
+      public const string QuotedTextRegex5 = @"(`([^`]+)`)";
+      public const string QuotedTextRegex6 = @"(«([^«»]+)»)";
+      public const string QuotedTextRegex7 = @"(‹([^‹›]+)›)";
+      public const string QuotedTextRegex8 = @"(123456)";
+      public const string QuotedTextRegex9 = @"(123456)";
+    }
+}

.NET/Microsoft.Recognizers.Definitions.Common/Italian/QuotedTextDefinitions.tt

@@ -0,0 +1,7 @@
+<#@ template debug="true" hostspecific="true" language="C#" #>
+<#
+	this.DataFilename = @"Patterns\Italian\Italian-QuotedText.yaml";
+	this.Language = "Italian";
+	this.ClassName = "QuotedTextDefinitions";
+#>
+<#@ include file="..\CommonDefinitions.ttinclude"#>