Automatic code arrangement (#157)

* Some automatic code arrangement, removed a ton of useless whitespace.

* More whitespace removed.

* Added editorconfig.

* Unused usings and whitespace removal

.editorconfig

@@ -0,0 +1,160 @@
+# To learn more about .editorconfig see https://aka.ms/editorconfigdocs
+###############################
+# Core EditorConfig Options   #
+###############################
+# All files
+[*]
+indent_style = space
+insert_final_newline = false
+
+# XML project files
+[*.{csproj,proj,projitems,shproj}]
+indent_size = 2
+
+# XML config files
+[*.{props,targets,ruleset,config,nuspec,resx,vsixmanifest,vsct}]
+indent_size = 2
+
+# Code files
+[*.{cs,csx,vb,vbx}]
+indent_size = 4
+insert_final_newline = true
+charset = utf-8-bom
+###############################
+# .NET Coding Conventions     #
+###############################
+[*.{cs,vb}]
+# Organize usings
+dotnet_sort_system_directives_first = true
+# this. preferences
+dotnet_style_qualification_for_field = false:silent
+dotnet_style_qualification_for_property = false:silent
+dotnet_style_qualification_for_method = false:silent
+dotnet_style_qualification_for_event = false:silent
+# Language keywords vs BCL types preferences
+dotnet_style_predefined_type_for_locals_parameters_members = true:silent
+dotnet_style_predefined_type_for_member_access = true:silent
+# Parentheses preferences
+dotnet_style_parentheses_in_arithmetic_binary_operators = always_for_clarity:silent
+dotnet_style_parentheses_in_relational_binary_operators = always_for_clarity:silent
+dotnet_style_parentheses_in_other_binary_operators = always_for_clarity:silent
+dotnet_style_parentheses_in_other_operators = never_if_unnecessary:silent
+# Modifier preferences
+dotnet_style_require_accessibility_modifiers = for_non_interface_members:silent
+dotnet_style_readonly_field = true:suggestion
+# Expression-level preferences
+dotnet_style_object_initializer = true:suggestion
+dotnet_style_collection_initializer = true:suggestion
+dotnet_style_explicit_tuple_names = true:suggestion
+dotnet_style_null_propagation = true:suggestion
+dotnet_style_coalesce_expression = true:suggestion
+dotnet_style_prefer_is_null_check_over_reference_equality_method = true:silent
+dotnet_style_prefer_inferred_tuple_names = true:suggestion
+dotnet_style_prefer_inferred_anonymous_type_member_names = true:suggestion
+dotnet_style_prefer_auto_properties = true:silent
+dotnet_style_prefer_conditional_expression_over_assignment = true:silent
+dotnet_style_prefer_conditional_expression_over_return = true:silent
+###############################
+# Naming Conventions          #
+###############################
+# Style Definitions
+dotnet_naming_style.pascal_case_style.capitalization             = pascal_case
+# Use PascalCase for constant fields
+dotnet_naming_rule.constant_fields_should_be_pascal_case.severity = suggestion
+dotnet_naming_rule.constant_fields_should_be_pascal_case.symbols  = constant_fields
+dotnet_naming_rule.constant_fields_should_be_pascal_case.style = pascal_case_style
+dotnet_naming_symbols.constant_fields.applicable_kinds            = field
+dotnet_naming_symbols.constant_fields.applicable_accessibilities  = *
+dotnet_naming_symbols.constant_fields.required_modifiers          = const
+dotnet_style_prefer_simplified_boolean_expressions = true:suggestion
+dotnet_style_prefer_compound_assignment = true:suggestion
+dotnet_style_prefer_simplified_interpolation = true:suggestion
+dotnet_style_namespace_match_folder = true:suggestion
+dotnet_style_operator_placement_when_wrapping = beginning_of_line
+tab_width = 4
+end_of_line = crlf
+dotnet_style_allow_multiple_blank_lines_experimental = true:silent
+dotnet_style_allow_statement_immediately_after_block_experimental = true:silent
+dotnet_code_quality_unused_parameters = all:suggestion
+###############################
+# C# Coding Conventions       #
+###############################
+[*.cs]
+# var preferences
+csharp_style_var_for_built_in_types = true:silent
+csharp_style_var_when_type_is_apparent = true:silent
+csharp_style_var_elsewhere = true:silent
+# Expression-bodied members
+csharp_style_expression_bodied_methods = false:silent
+csharp_style_expression_bodied_constructors = false:silent
+csharp_style_expression_bodied_operators = false:silent
+csharp_style_expression_bodied_properties = true:silent
+csharp_style_expression_bodied_indexers = true:silent
+csharp_style_expression_bodied_accessors = true:silent
+# Pattern matching preferences
+csharp_style_pattern_matching_over_is_with_cast_check = true:suggestion
+csharp_style_pattern_matching_over_as_with_null_check = true:suggestion
+# Null-checking preferences
+csharp_style_throw_expression = true:suggestion
+csharp_style_conditional_delegate_call = true:suggestion
+# Modifier preferences
+csharp_preferred_modifier_order = public,private,protected,internal,static,extern,new,virtual,abstract,sealed,override,readonly,unsafe,volatile,async:suggestion
+# Expression-level preferences
+csharp_prefer_braces = true:silent
+csharp_style_deconstructed_variable_declaration = true:suggestion
+csharp_prefer_simple_default_expression = true:suggestion
+csharp_style_pattern_local_over_anonymous_function = true:suggestion
+csharp_style_inlined_variable_declaration = true:suggestion
+###############################
+# C# Formatting Rules         #
+###############################
+# New line preferences
+csharp_new_line_before_open_brace = all
+csharp_new_line_before_else = true
+csharp_new_line_before_catch = true
+csharp_new_line_before_finally = true
+csharp_new_line_before_members_in_object_initializers = true
+csharp_new_line_before_members_in_anonymous_types = true
+csharp_new_line_between_query_expression_clauses = true
+# Indentation preferences
+csharp_indent_case_contents = true
+csharp_indent_switch_labels = true
+csharp_indent_labels = flush_left
+# Space preferences
+csharp_space_after_cast = false
+csharp_space_after_keywords_in_control_flow_statements = true
+csharp_space_between_method_call_parameter_list_parentheses = false
+csharp_space_between_method_declaration_parameter_list_parentheses = false
+csharp_space_between_parentheses = false
+csharp_space_before_colon_in_inheritance_clause = true
+csharp_space_after_colon_in_inheritance_clause = true
+csharp_space_around_binary_operators = before_and_after
+csharp_space_between_method_declaration_empty_parameter_list_parentheses = false
+csharp_space_between_method_call_name_and_opening_parenthesis = false
+csharp_space_between_method_call_empty_parameter_list_parentheses = false
+# Wrapping preferences
+csharp_preserve_single_line_statements = true
+csharp_preserve_single_line_blocks = true
+csharp_using_directive_placement = outside_namespace:silent
+csharp_prefer_simple_using_statement = true:suggestion
+csharp_style_namespace_declarations = block_scoped:silent
+csharp_style_prefer_method_group_conversion = true:silent
+csharp_style_expression_bodied_lambdas = true:silent
+csharp_style_expression_bodied_local_functions = false:silent
+csharp_style_prefer_extended_property_pattern = true:suggestion
+csharp_style_prefer_null_check_over_type_check = true:suggestion
+csharp_style_prefer_local_over_anonymous_function = true:suggestion
+csharp_style_prefer_range_operator = true:suggestion
+csharp_style_prefer_index_operator = true:suggestion
+csharp_style_prefer_tuple_swap = true:suggestion
+csharp_style_implicit_object_creation_when_type_is_apparent = true:suggestion
+csharp_style_unused_value_expression_statement_preference = discard_variable:silent
+csharp_style_unused_value_assignment_preference = discard_variable:suggestion
+csharp_prefer_static_local_function = true:suggestion
+csharp_style_allow_embedded_statements_on_same_line_experimental = true:silent
+csharp_style_allow_blank_line_after_colon_in_constructor_initializer_experimental = true:silent
+csharp_style_allow_blank_lines_between_consecutive_braces_experimental = true:silent
+csharp_style_prefer_parameter_null_checking = true:suggestion
+csharp_style_prefer_switch_expression = true:suggestion
+csharp_style_prefer_pattern_matching = true:silent
+csharp_style_prefer_not_pattern = true:suggestion

UTF-unknown.sln

@@ -1,13 +1,18 @@
 
 Microsoft Visual Studio Solution File, Format Version 12.00
-# Visual Studio 15
-VisualStudioVersion = 15.0.26228.9
+# Visual Studio Version 17
+VisualStudioVersion = 17.2.32616.157
 MinimumVisualStudioVersion = 10.0.40219.1
-Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "UTF-unknown", "src\UTF-unknown.csproj", "{64CA7BA7-EFD9-4475-BB66-40B187622A73}"
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "UTF-unknown", "src\UTF-unknown.csproj", "{64CA7BA7-EFD9-4475-BB66-40B187622A73}"
 EndProject
-Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "ConsoleExample", "example\ConsoleExample.csproj", "{386C6ABF-44EA-4418-B90E-E8D21E4C2475}"
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "ConsoleExample", "example\ConsoleExample.csproj", "{386C6ABF-44EA-4418-B90E-E8D21E4C2475}"
 EndProject
-Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "UTF-unknown.Tests", "Tests\UTF-unknown.Tests.csproj", "{1922DCC9-A45F-4627-9087-CD492BBF7F38}"
+Project("{9A19103F-16F7-4668-BE54-9A1E7A4F7556}") = "UTF-unknown.Tests", "Tests\UTF-unknown.Tests.csproj", "{1922DCC9-A45F-4627-9087-CD492BBF7F38}"
+EndProject
+Project("{2150E333-8FDC-42A3-9474-1A3956D46DE8}") = "Solution Items", "Solution Items", "{052846B2-CA56-482F-B477-6E33523C091E}"
+	ProjectSection(SolutionItems) = preProject
+		.editorconfig = .editorconfig
+	EndProjectSection
 EndProject
 Global
 	GlobalSection(SolutionConfigurationPlatforms) = preSolution
@@ -31,4 +36,7 @@ Global
 	GlobalSection(SolutionProperties) = preSolution
 		HideSolutionNode = FALSE
 	EndGlobalSection
+	GlobalSection(ExtensibilityGlobals) = postSolution
+		SolutionGuid = {0C7AF656-EF20-4880-8EB9-9BF101340A03}
+	EndGlobalSection
 EndGlobal

src/CharsetDetector.cs

@@ -48,9 +48,9 @@
 namespace UtfUnknown
 {
     /// <summary>
-    /// Default implementation of charset detection interface. 
+    /// Default implementation of charset detection interface.
     /// The detector can be fed by a System.IO.Stream:
-    /// </summary>                
+    /// </summary>
     public class CharsetDetector
     {
         internal InputState InputState;
@@ -135,7 +135,7 @@ public static DetectionResult DetectFromBytes(byte[] bytes)
         }
 
         /// <summary>
-        /// Detect the character encoding form this byte array. 
+        /// Detect the character encoding form this byte array.
         /// It searchs for BOM from bytes[offset].
         /// </summary>
         /// <param name="bytes">The byte array containing the text</param>
@@ -170,7 +170,7 @@ public static DetectionResult DetectFromBytes(byte[] bytes, int offset, int len)
 
         /// <summary>
         /// Detect the character encoding by reading the stream.
-        /// 
+        ///
         /// Note: stream position is not reset before and after.
         /// </summary>
         /// <param name="stream">The steam. </param>
@@ -186,7 +186,7 @@ public static DetectionResult DetectFromStream(Stream stream)
 
         /// <summary>
         /// Detect the character encoding by reading the stream.
-        /// 
+        ///
         /// Note: stream position is not reset before and after.
         /// </summary>
         /// <param name="stream">The steam. </param>
@@ -403,10 +403,10 @@ private static string FindCharSetByBom(byte[] buf, int offset, int len)
 
             if (buf0 == 0xEF && buf1 == 0xBB && buf[offset + 2] == 0xBF)
                 return CodepageName.UTF8;
-            
+
             if (len < 4)
                 return null;
-            
+
             //Here, because anyway further more than 3 positions are checked.
             if (buf0 == 0x00 && buf1 == 0x00)
             {
@@ -422,24 +422,24 @@ private static string FindCharSetByBom(byte[] buf, int offset, int len)
             if (buf0 == 0x2B && buf1 == 0x2F && buf[offset + 2] == 0x76)
                 if (buf[offset + 3] == 0x38 || buf[offset + 3] == 0x39 || buf[offset + 3] == 0x2B || buf[offset + 3] == 0x2F)
                     return CodepageName.UTF7;
-            
+
             // Detect GB18030 with bom (see table in https://en.wikipedia.org/wiki/Byte_order_mark)
             // TODO: If you remove this check, GB18030Prober will still be defined as GB18030 -- It's feature or bug?
             if (buf0 == 0x84 && buf1 == 0x31 && buf[offset + 2] == 0x95 && buf[offset + 3] == 0x33)
                 return CodepageName.GB18030;
-            
+
             return null;
         }
 
         /// <summary>
-        /// Notify detector that no further data is available. 
+        /// Notify detector that no further data is available.
         /// </summary>
         private DetectionResult DataEnd()
         {
             if (!_gotData)
             {
-                // we haven't got any data yet, return immediately 
-                // caller program sometimes call DataEnd before anything has 
+                // we haven't got any data yet, return immediately
+                // caller program sometimes call DataEnd before anything has
                 // been sent to detector
                 return new DetectionResult();
             }
@@ -499,5 +499,4 @@ internal IList<CharsetProber> GetNewProbers()
             }
         }
     }
-}
-
+}

src/Core/Analyzers/CharDistributionAnalyser.cs

@@ -1,4 +1,4 @@
-/* ***** BEGIN LICENSE BLOCK *****
+/* ***** BEGIN LICENSE BLOCK *****
  * Version: MPL 1.1/GPL 2.0/LGPL 2.1
  *
  * The contents of this file are subject to the Mozilla Public License Version
@@ -38,7 +38,7 @@
 namespace UtfUnknown.Core.Analyzers
 {
     /// <summary>
-    /// Base class for the Character Distribution Method, used for 
+    /// Base class for the Character Distribution Method, used for
     /// the CJK encodings
     /// </summary>
     public abstract class CharDistributionAnalyser
@@ -60,7 +60,7 @@ public abstract class CharDistributionAnalyser
         // Mapping table to get frequency order from char order (get from GetOrder())
         protected int[] charToFreqOrder;
 
-        // This constant value varies from language to language. It is used in calculating confidence. 
+        // This constant value varies from language to language. It is used in calculating confidence.
         protected float typicalDistributionRatio;
 
         public CharDistributionAnalyser()
@@ -72,7 +72,7 @@ public CharDistributionAnalyser()
         /// Feed a block of data and do distribution analysis
         /// </summary>
         /// <remarks>
-        /// we do not handle character base on its original encoding string, but 
+        /// we do not handle character base on its original encoding string, but
         /// convert this encoding string to a number, here called order.
         /// This allow multiple encoding of a language to share one frequency table
         /// </remarks>
@@ -82,7 +82,7 @@ public CharDistributionAnalyser()
         public abstract int GetOrder(byte[] buf, int offset);
 
         /// <summary>
-        /// Feed a character with known length 
+        /// Feed a character with known length
         /// </summary>
         /// <param name="buf">A <see cref="System.Byte"/></param>
         /// <param name="offset">buf offset</param>

src/Core/Analyzers/MultiByte/Chinese/BIG5DistributionAnalyser.cs

@@ -3,7 +3,7 @@ namespace UtfUnknown.Core.Analyzers.Chinese
     public class BIG5DistributionAnalyser : CharDistributionAnalyser
     {
         // Big5 frequency table
-        // by Taiwan's Mandarin Promotion Council 
+        // by Taiwan's Mandarin Promotion Council
         // <http://www.edu.tw:81/mandr/>
         /******************************************************************************
          * 128  --> 0.42261
@@ -902,28 +902,28 @@ public class BIG5DistributionAnalyser : CharDistributionAnalyser
         13968,13969,13970,13971,13972, //13973
         ****************************************************************************************/
         };
-        
+
         public BIG5DistributionAnalyser()
         {
             charToFreqOrder = BIG5_CHAR2FREQ_ORDER;
-            typicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO;        
+            typicalDistributionRatio = BIG5_TYPICAL_DISTRIBUTION_RATIO;
         }
-        
+
         /// <summary>
         /// first  byte range: 0xa4 -- 0xfe
         ///  second byte range: 0x40 -- 0x7e , 0xa1 -- 0xfe
         /// no validation needed here. State machine has done that
         /// </summary>
-        public override int GetOrder(byte[] buf, int offset) 
-        { 
+        public override int GetOrder(byte[] buf, int offset)
+        {
             if (buf[offset] >= 0xA4) {
                 if (buf[offset+1] >= 0xA1)
                     return 157 * (buf[offset] - 0xA4) + buf[offset+1] - 0xA1 + 63;
                 else
                     return 157 * (buf[offset] - 0xA4) + buf[offset+1] - 0x40;
             } else {
-                return -1;            
-            }  
+                return -1;
+            }
         }
     }
 }

src/Core/Analyzers/MultiByte/Chinese/EUCTWDistributionAnalyser.cs

@@ -3,8 +3,8 @@ namespace UtfUnknown.Core.Analyzers.Chinese
     public class EUCTWDistributionAnalyser : CharDistributionAnalyser
     {
         // EUCTW frequency table
-        // Converted from big5 work 
-        // by Taiwan's Mandarin Promotion Council 
+        // Converted from big5 work
+        // by Taiwan's Mandarin Promotion Council
         // <http://www.edu.tw:81/mandr/>
         /******************************************************************************
          * 128  --> 0.42261
@@ -417,9 +417,9 @@ public EUCTWDistributionAnalyser()
         ///  second byte range: 0xa1 -- 0xfe
         /// no validation needed here. State machine has done that
         /// </summary>
-        public override int GetOrder(byte[] buf, int offset) 
-        { 
-            if (buf[offset] >= 0xC4)  
+        public override int GetOrder(byte[] buf, int offset)
+        {
+            if (buf[offset] >= 0xC4)
                 return 94 * (buf[offset] - 0xC4) + buf[offset+1] - 0xA1;
             else
                 return -1;