Mercurial > hg > orthanc

changeset 1090:e494ceb8d763

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
support more encodings
author Sebastien Jodogne <s.jodogne@gmail.com>
date Tue, 05 Aug 2014 12:04:23 +0200
parents 5ea0b56e850d
children a66224eec125
files Core/Enumerations.cpp Core/Enumerations.h Core/Toolbox.cpp OrthancServer/FromDcmtkBridge.cpp OrthancServer/ParsedDicomFile.cpp OrthancServer/ParsedDicomFile.h Resources/Configuration.json Resources/EncodingTests.h Resources/EncodingTests.py UnitTestsSources/FromDcmtkTests.cpp UnitTestsSources/UnitTestsMain.cpp
diffstat 11 files changed, 367 insertions(+), 90 deletions(-) [+]
line wrap: on
line diff
--- a/Core/Enumerations.cpp	Tue Aug 05 08:49:25 2014 +0200
+++ b/Core/Enumerations.cpp	Tue Aug 05 12:04:23 2014 +0200
@@ -298,6 +298,15 @@
       case Encoding_Hebrew:
         return "Hebrew";
 
+      case Encoding_Thai:
+        return "Thai";
+
+      case Encoding_Japanese:
+        return "Japanese";
+
+      case Encoding_Chinese:
+        return "Chinese";
+
       default:
         throw OrthancException(ErrorCode_ParameterOutOfRange);
     }
@@ -364,6 +373,21 @@
       return Encoding_Hebrew;
     }
 
+    if (s == "THAI")
+    {
+      return Encoding_Thai;
+    }
+
+    if (s == "JAPANESE")
+    {
+      return Encoding_Japanese;
+    }
+
+    if (s == "CHINESE")
+    {
+      return Encoding_Chinese;
+    }
+
     throw OrthancException(ErrorCode_ParameterOutOfRange);
   }
 
@@ -430,4 +454,99 @@
         throw OrthancException(ErrorCode_ParameterOutOfRange);
     }
   }
+
+
+  bool GetDicomEncoding(Encoding& encoding,
+                        const char* specificCharacterSet)
+  {
+    std::string s = specificCharacterSet;
+    Toolbox::ToUpperCase(s);
+
+    // http://www.dabsoft.ch/dicom/3/C.12.1.1.2/
+    // https://github.com/dcm4che/dcm4che/blob/master/dcm4che-core/src/main/java/org/dcm4che3/data/SpecificCharacterSet.java
+    if (s == "ISO_IR 6" ||
+        s == "ISO_IR 192" ||
+        s == "ISO 2022 IR 6")
+    {
+      encoding = Encoding_Utf8;
+    }
+    else if (s == "ISO_IR 100" ||
+             s == "ISO 2022 IR 100")
+    {
+      encoding = Encoding_Latin1;
+    }
+    else if (s == "ISO_IR 101" ||
+             s == "ISO 2022 IR 101")
+    {
+      encoding = Encoding_Latin2;
+    }
+    else if (s == "ISO_IR 109" ||
+             s == "ISO 2022 IR 109")
+    {
+      encoding = Encoding_Latin3;
+    }
+    else if (s == "ISO_IR 110" ||
+             s == "ISO 2022 IR 110")
+    {
+      encoding = Encoding_Latin4;
+    }
+    else if (s == "ISO_IR 148" ||
+             s == "ISO 2022 IR 148")
+    {
+      encoding = Encoding_Latin5;
+    }
+    else if (s == "ISO_IR 144" ||
+             s == "ISO 2022 IR 144")
+    {
+      encoding = Encoding_Cyrillic;
+    }
+    else if (s == "ISO_IR 127" ||
+             s == "ISO 2022 IR 127")
+    {
+      encoding = Encoding_Arabic;
+    }
+    else if (s == "ISO_IR 126" ||
+             s == "ISO 2022 IR 126")
+    {
+      encoding = Encoding_Greek;
+    }
+    else if (s == "ISO_IR 138" ||
+             s == "ISO 2022 IR 138")
+    {
+      encoding = Encoding_Hebrew;
+    }
+    else if (s == "ISO_IR 166" || s == "ISO 2022 IR 166")
+    {
+      encoding = Encoding_Thai;
+    }
+    else if (s == "ISO_IR 13" || s == "ISO 2022 IR 13")
+    {
+      encoding = Encoding_Japanese;
+    }
+    else if (s == "GB18030")
+    {
+      encoding = Encoding_Chinese;
+    }
+    /*
+      else if (s == "ISO 2022 IR 149")
+      {
+      TODO
+      }
+      else if (s == "ISO 2022 IR 159")
+      {
+      TODO
+      }
+      else if (s == "ISO 2022 IR 87")
+      {
+      TODO
+      }
+    */
+    else
+    {
+      return false;
+    }
+
+    // The encoding was properly detected
+    return true;
+  }
 }
--- a/Core/Enumerations.h	Tue Aug 05 08:49:25 2014 +0200
+++ b/Core/Enumerations.h	Tue Aug 05 12:04:23 2014 +0200
@@ -230,6 +230,7 @@
   };
 
 
+  // http://www.dabsoft.ch/dicom/3/C.12.1.1.2/
   enum Encoding
   {
     Encoding_Ascii,
@@ -238,11 +239,17 @@
     Encoding_Latin2,
     Encoding_Latin3,
     Encoding_Latin4,
-    Encoding_Latin5,
+    Encoding_Latin5,                        // Turkish
     Encoding_Cyrillic,
     Encoding_Arabic,
     Encoding_Greek,
-    Encoding_Hebrew
+    Encoding_Hebrew,
+    Encoding_Thai,                          // TIS 620-2533
+    Encoding_Japanese,                      // JIS X 0201 (Shift JIS): Katakana
+    Encoding_Chinese                        // GB18030 - Chinese simplified
+    //Encoding_JapaneseKanji,               // Multibyte - JIS X 0208: Kanji
+    //Encoding_JapaneseSupplementaryKanji,  // Multibyte - JIS X 0212: Supplementary Kanji set
+    //Encoding_Korean,                      // Multibyte - KS X 1001: Hangul and Hanja
   };
 
 
@@ -294,4 +301,7 @@
   ImageFormat StringToImageFormat(const char* format);
 
   unsigned int GetBytesPerPixel(PixelFormat format);
+
+  bool GetDicomEncoding(Encoding& encoding,
+                        const char* specificCharacterSet);
 }
--- a/Core/Toolbox.cpp	Tue Aug 05 08:49:25 2014 +0200
+++ b/Core/Toolbox.cpp	Tue Aug 05 12:04:23 2014 +0200
@@ -532,6 +532,8 @@
   {
     const char* encoding;
 
+
+    // http://bradleyross.users.sourceforge.net/docs/dicom/doc/src-html/org/dcm4che2/data/SpecificCharacterSet.html
     switch (sourceEncoding)
     {
       case Encoding_Utf8:
@@ -576,6 +578,18 @@
       case Encoding_Hebrew:
         encoding = "ISO-8859-8";
         break;
+        
+      case Encoding_Japanese:
+        encoding = "SHIFT-JIS";
+        break;
+
+      case Encoding_Chinese:
+        encoding = "GB18030";
+        break;
+
+      case Encoding_Thai:
+        encoding = "TIS620.2533-0";
+        break;
 
       default:
         throw OrthancException(ErrorCode_NotImplemented);
--- a/OrthancServer/FromDcmtkBridge.cpp	Tue Aug 05 08:49:25 2014 +0200
+++ b/OrthancServer/FromDcmtkBridge.cpp	Tue Aug 05 12:04:23 2014 +0200
@@ -128,56 +128,26 @@
     if (dataset.findAndGetOFString(DCM_SpecificCharacterSet, tmp).good())
     {
       std::string characterSet = Toolbox::StripSpaces(std::string(tmp.c_str()));
-      Toolbox::ToUpperCase(characterSet);
 
-      if (characterSet == "ISO_IR 6" ||
-          characterSet == "ISO_IR 192")
-      {
-        encoding = Encoding_Utf8;
-      }
-      else if (characterSet == "ISO_IR 100")
+      if (characterSet.empty())
       {
-        encoding = Encoding_Latin1;
-      }
-      else if (characterSet == "ISO_IR 101")
-      {
-        encoding = Encoding_Latin2;
-      }
-      else if (characterSet == "ISO_IR 109")
-      {
-        encoding = Encoding_Latin3;
-      }
-      else if (characterSet == "ISO_IR 110")
-      {
-        encoding = Encoding_Latin4;
+        // Empty specific character set tag: Use the default encoding
       }
-      else if (characterSet == "ISO_IR 148")
-      {
-        encoding = Encoding_Latin5;
-      }
-      else if (characterSet == "ISO_IR 144")
+      else if (GetDicomEncoding(encoding, characterSet.c_str()))
       {
-        encoding = Encoding_Cyrillic;
-      }
-      else if (characterSet == "ISO_IR 127")
-      {
-        encoding = Encoding_Arabic;
+        // The specific character set is supported by the Orthanc core
       }
-      else if (characterSet == "ISO_IR 126")
-      {
-        encoding = Encoding_Greek;
-      }
-      else if (characterSet == "ISO_IR 138")
+      else
       {
-        encoding = Encoding_Hebrew;
-      }
-      else if (!characterSet.empty())
-      {
-        LOG(WARNING) << "Value of Specific Character Set (0008,0005) is not supported: " << characterSet;
-        // Fallback to ASCII (remove all special characters)
+        LOG(WARNING) << "Value of Specific Character Set (0008,0005) is not supported: " << characterSet
+                     << ", fallback to ASCII (remove all special characters)";
         encoding = Encoding_Ascii;
       }
     }
+    else
+    {
+      // No specific character set tag: Use the default encoding
+    }
 
     return encoding;
   }
--- a/OrthancServer/ParsedDicomFile.cpp	Tue Aug 05 08:49:25 2014 +0200
+++ b/OrthancServer/ParsedDicomFile.cpp	Tue Aug 05 12:04:23 2014 +0200
@@ -1215,4 +1215,71 @@
   {
     return pimpl_->encoding_;
   }
+
+
+  void ParsedDicomFile::SetEncoding(Encoding encoding)
+  {
+    std::string s;
+
+    // http://www.dabsoft.ch/dicom/3/C.12.1.1.2/
+    switch (encoding)
+    {
+      case Encoding_Utf8:
+      case Encoding_Ascii:
+        s = "ISO_IR 192";
+        break;
+
+      case Encoding_Latin1:
+        s = "ISO_IR 100";
+        break;
+
+      case Encoding_Latin2:
+        s = "ISO_IR 101";
+        break;
+
+      case Encoding_Latin3:
+        s = "ISO_IR 109";
+        break;
+
+      case Encoding_Latin4:
+        s = "ISO_IR 110";
+        break;
+
+      case Encoding_Latin5:
+        s = "ISO_IR 148";
+        break;
+
+      case Encoding_Cyrillic:
+        s = "ISO_IR 144";
+        break;
+
+      case Encoding_Arabic:
+        s = "ISO_IR 127";
+        break;
+
+      case Encoding_Greek:
+        s = "ISO_IR 126";
+        break;
+
+      case Encoding_Hebrew:
+        s = "ISO_IR 138";
+        break;
+
+        /*
+          case Encoding_Japanese:
+          s = "ISO_IR 13";
+          break;
+        */
+
+      case Encoding_Thai:
+        s = "ISO_IR 166";
+        break;
+
+      default:
+        throw OrthancException(ErrorCode_ParameterOutOfRange);
+    }
+
+    Replace(DICOM_TAG_SPECIFIC_CHARACTER_SET, "", DicomReplaceMode_InsertIfAbsent);
+  }
+
 }
--- a/OrthancServer/ParsedDicomFile.h	Tue Aug 05 08:49:25 2014 +0200
+++ b/OrthancServer/ParsedDicomFile.h	Tue Aug 05 12:04:23 2014 +0200
@@ -116,6 +116,8 @@
                          ImageExtractionMode mode);
 
     Encoding GetEncoding() const;
+
+    void SetEncoding(Encoding encoding);
   };
 
 }
--- a/Resources/Configuration.json	Tue Aug 05 08:49:25 2014 +0200
+++ b/Resources/Configuration.json	Tue Aug 05 12:04:23 2014 +0200
@@ -183,7 +183,9 @@
   "LimitJobs" : 10,
 
   // The default encoding that is assumed for DICOM files without
-  // "SpecificCharacterSet" DICOM tag. The allowed values are
-  // currently "Latin1", "Utf8" and "Ascii".
+  // "SpecificCharacterSet" DICOM tag. The allowed values are "Ascii",
+  // "Utf8", "Latin1", "Latin2", "Latin3", "Latin4", "Latin5",
+  // "Cyrillic", "Arabic", "Greek", "Hebrew", "Thai", "Japanese",
+  // and "Chinese".
   "DefaultEncoding" : "Latin1"
 }
--- a/Resources/EncodingTests.h	Tue Aug 05 08:49:25 2014 +0200
+++ b/Resources/EncodingTests.h	Tue Aug 05 12:04:23 2014 +0200
@@ -1,40 +1,49 @@
-static const unsigned int testEncodingsCount = 11;
-static const Orthanc::Encoding testEncodings[] = {
-  Orthanc::Encoding_Latin5,
-  Orthanc::Encoding_Hebrew,
-  Orthanc::Encoding_Greek,
-  Orthanc::Encoding_Arabic,
-  Orthanc::Encoding_Cyrillic,
-  Orthanc::Encoding_Latin4,
-  Orthanc::Encoding_Latin3,
-  Orthanc::Encoding_Latin2,
-  Orthanc::Encoding_Latin1,
-  Orthanc::Encoding_Utf8,
-  Orthanc::Encoding_Ascii
+static const unsigned int testEncodingsCount = 14;
+static const ::Orthanc::Encoding testEncodings[] = {
+  ::Orthanc::Encoding_Latin5,
+  ::Orthanc::Encoding_Hebrew,
+  ::Orthanc::Encoding_Greek,
+  ::Orthanc::Encoding_Arabic,
+  ::Orthanc::Encoding_Cyrillic,
+  ::Orthanc::Encoding_Latin4,
+  ::Orthanc::Encoding_Latin3,
+  ::Orthanc::Encoding_Latin2,
+  ::Orthanc::Encoding_Latin1,
+  ::Orthanc::Encoding_Utf8,
+  ::Orthanc::Encoding_Thai,
+  ::Orthanc::Encoding_Japanese,
+  ::Orthanc::Encoding_Ascii,
+  ::Orthanc::Encoding_Chinese
 };
-static const char *testEncodingsEncoded[11] = {
-  "\xe9\xe4\xf6\xf2\x3f\x3f\x3f\x3f\x3f\x3f\x3f",
-  "\x3f\x3f\x3f\x3f\x3f\x3f\x3f\xe3\x3f\x3f\x3f",
-  "\x3f\x3f\x3f\x3f\x3f\xc8\x3f\x3f\x3f\x3f\x3f",
-  "\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f\xd5\x3f\x3f",
-  "\x3f\x3f\x3f\x3f\xb4\x3f\x3f\x3f\x3f\x3f\xfb",
-  "\xe9\xe4\xf6\x3f\x3f\x3f\x3f\x3f\x3f\xf3\x3f",
-  "\xe9\xe4\xf6\xf2\x3f\x3f\xf8\x3f\x3f\x3f\x3f",
-  "\xe9\xe4\xf6\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f",
-  "\xe9\xe4\xf6\xf2\x3f\x3f\x3f\x3f\x3f\x3f\x3f",
-  "\xc3\xa9\xc3\xa4\xc3\xb6\xc3\xb2\xd0\x94\xce\x98\xc4\x9d\xd7\x93\xd8\xb5\xc4\xb7\xd1\x9b",
-  "\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f"
+static const char *testEncodingsEncoded[14] = {
+  "\xe9\xe4\xf6\xf2\xdd",
+  "\xe3",
+  "\xc8",
+  "\xd5",
+  "\xb4\xfb",
+  "\xe9\xe4\xf6\xf3",
+  "\xe9\xe4\xf6\xf2\xf8\xa9",
+  "\xe9\xe4\xf6",
+  "\xe9\xe4\xf6\xf2",
+  "\xc3\xa9\xc3\xa4\xc3\xb6\xc3\xb2\xd0\x94\xce\x98\xc4\x9d\xd7\x93\xd8\xb5\xc4\xb7\xd1\x9b\xe0\xb9\x9b\xef\xbe\x88\xc4\xb0",
+  "\xfb",
+  "\x84\x44\x83\xa6\xc8",
+  "",
+  "\x81\x30\x89\x37\x81\x30\x89\x38\xA8\xA4\xA8\xA2\x81\x30\x89\x39\x81\x30\x8A\x30"
 };
-static const char *testEncodingsExpected[11] = {
-  "\xc3\xa9\xc3\xa4\xc3\xb6\xc3\xb2\x3f\x3f\x3f\x3f\x3f\x3f\x3f",
-  "\x3f\x3f\x3f\x3f\x3f\x3f\x3f\xd7\x93\x3f\x3f\x3f",
-  "\x3f\x3f\x3f\x3f\x3f\xce\x98\x3f\x3f\x3f\x3f\x3f",
-  "\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f\xd8\xb5\x3f\x3f",
-  "\x3f\x3f\x3f\x3f\xd0\x94\x3f\x3f\x3f\x3f\x3f\xd1\x9b",
-  "\xc3\xa9\xc3\xa4\xc3\xb6\x3f\x3f\x3f\x3f\x3f\x3f\xc4\xb7\x3f",
-  "\xc3\xa9\xc3\xa4\xc3\xb6\xc3\xb2\x3f\x3f\xc4\x9d\x3f\x3f\x3f\x3f",
-  "\xc3\xa9\xc3\xa4\xc3\xb6\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f",
-  "\xc3\xa9\xc3\xa4\xc3\xb6\xc3\xb2\x3f\x3f\x3f\x3f\x3f\x3f\x3f",
-  "\xc3\xa9\xc3\xa4\xc3\xb6\xc3\xb2\xd0\x94\xce\x98\xc4\x9d\xd7\x93\xd8\xb5\xc4\xb7\xd1\x9b",
-  "\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f\x3f"
+static const char *testEncodingsExpected[14] = {
+  "\xc3\xa9\xc3\xa4\xc3\xb6\xc3\xb2\xc4\xb0",
+  "\xd7\x93",
+  "\xce\x98",
+  "\xd8\xb5",
+  "\xd0\x94\xd1\x9b",
+  "\xc3\xa9\xc3\xa4\xc3\xb6\xc4\xb7",
+  "\xc3\xa9\xc3\xa4\xc3\xb6\xc3\xb2\xc4\x9d\xc4\xb0",
+  "\xc3\xa9\xc3\xa4\xc3\xb6",
+  "\xc3\xa9\xc3\xa4\xc3\xb6\xc3\xb2",
+  "\xc3\xa9\xc3\xa4\xc3\xb6\xc3\xb2\xd0\x94\xce\x98\xc4\x9d\xd7\x93\xd8\xb5\xc4\xb7\xd1\x9b\xe0\xb9\x9b\xef\xbe\x88\xc4\xb0",
+  "\xe0\xb9\x9b",
+  "\xd0\x94\xce\x98\xef\xbe\x88",
+  "",
+  "\xc3\x9e\xc3\x9f\xc3\xa0\xc3\xa1\xc3\xa2\xc3\xa3"
 };
--- a/Resources/EncodingTests.py	Tue Aug 05 08:49:25 2014 +0200
+++ b/Resources/EncodingTests.py	Tue Aug 05 12:04:23 2014 +0200
@@ -1,7 +1,7 @@
 #!/usr/bin/python
 # -*- coding: utf-8 -*-
 
-source = u'éäöòДΘĝדصķћ'
+source = u'éäöòДΘĝדصķћ๛ﾈİ'
 
 encodings = {
     'UTF-8' : 'Utf8',
@@ -15,8 +15,16 @@
     'ISO-8859-6' : 'Arabic',
     'ISO-8859-7' : 'Greek',
     'ISO-8859-8' : 'Hebrew',
+    'TIS-620' : 'Thai',
+    'SHIFT-JIS' : 'Japanese',
+    #'GB18030' : 'Chinese',
 }
 
+#from encodings.aliases import aliases
+#for a, b in aliases.iteritems():
+#    print '%s : %s' % (a, b)
+
+
 # "63" corresponds to "?"
 l = []
 encoded = []
@@ -30,12 +38,24 @@
     
 
 for encoding, orthancEnumeration in encodings.iteritems():
-    l.append('Orthanc::Encoding_%s' % orthancEnumeration)
-    s = source.encode(encoding, 'replace')
+    l.append('::Orthanc::Encoding_%s' % orthancEnumeration)
+    s = source.encode(encoding, 'ignore')
     encoded.append(ToArray(s))
     expected.append(ToArray(s.decode(encoding).encode('utf-8')))
 
-print 'static const unsigned int testEncodingsCount = %d;' % len(encodings)
-print 'static const Orthanc::Encoding testEncodings[] = {\n  %s\n};' % (',\n  '.join(l))
-print 'static const char *testEncodingsEncoded[%d] = {\n  %s\n};' % (len(encodings), ',\n  '.join(encoded))
-print 'static const char *testEncodingsExpected[%d] = {\n  %s\n};' % (len(encodings), ',\n  '.join(expected))
+
+# https://en.wikipedia.org/wiki/GB_18030#Technical_details
+l.append('::Orthanc::Encoding_Chinese')
+expected.append(ToArray('Þßàáâã'))
+encoded.append('"\\x81\\x30\\x89\\x37\\x81\\x30\\x89\\x38\\xA8\\xA4\\xA8\\xA2\\x81\\x30\\x89\\x39\\x81\\x30\\x8A\\x30"')
+
+
+if True:
+    print 'static const unsigned int testEncodingsCount = %d;' % len(l)
+    print 'static const ::Orthanc::Encoding testEncodings[] = {\n  %s\n};' % (',\n  '.join(l))
+    print 'static const char *testEncodingsEncoded[%d] = {\n  %s\n};' % (len(l), ',\n  '.join(encoded))
+    print 'static const char *testEncodingsExpected[%d] = {\n  %s\n};' % (len(l), ',\n  '.join(expected))
+else:
+    for i in range(len(expected)):
+        print expected[i]
+        #print '%s: %s' % (expected[i], l[i])
--- a/UnitTestsSources/FromDcmtkTests.cpp	Tue Aug 05 08:49:25 2014 +0200
+++ b/UnitTestsSources/FromDcmtkTests.cpp	Tue Aug 05 12:04:23 2014 +0200
@@ -179,7 +179,7 @@
 }
 
 
-TEST(Toolbox, Encodings1)
+TEST(FromDcmtkBridge, Encodings1)
 {
   for (unsigned int i = 0; i < testEncodingsCount; i++)
   {
@@ -190,3 +190,64 @@
     EXPECT_EQ(expected, s);
   }
 }
+
+
+TEST(FromDcmtkBridge, Enumerations)
+{
+  Encoding e;
+
+  ASSERT_FALSE(GetDicomEncoding(e, ""));
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 6"));  ASSERT_EQ(Encoding_Utf8, e);
+
+  // http://www.dabsoft.ch/dicom/3/C.12.1.1.2/ - Table C.12-2
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 100"));  ASSERT_EQ(Encoding_Latin1, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 101"));  ASSERT_EQ(Encoding_Latin2, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 109"));  ASSERT_EQ(Encoding_Latin3, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 110"));  ASSERT_EQ(Encoding_Latin4, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 144"));  ASSERT_EQ(Encoding_Cyrillic, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 127"));  ASSERT_EQ(Encoding_Arabic, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 126"));  ASSERT_EQ(Encoding_Greek, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 138"));  ASSERT_EQ(Encoding_Hebrew, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 148"));  ASSERT_EQ(Encoding_Latin5, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 13"));  ASSERT_EQ(Encoding_Japanese, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 166"));  ASSERT_EQ(Encoding_Thai, e);
+
+  // http://www.dabsoft.ch/dicom/3/C.12.1.1.2/ - Table C.12-3
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 6"));  ASSERT_EQ(Encoding_Utf8, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 100"));  ASSERT_EQ(Encoding_Latin1, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 101"));  ASSERT_EQ(Encoding_Latin2, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 109"));  ASSERT_EQ(Encoding_Latin3, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 110"));  ASSERT_EQ(Encoding_Latin4, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 144"));  ASSERT_EQ(Encoding_Cyrillic, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 127"));  ASSERT_EQ(Encoding_Arabic, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 126"));  ASSERT_EQ(Encoding_Greek, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 138"));  ASSERT_EQ(Encoding_Hebrew, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 148"));  ASSERT_EQ(Encoding_Latin5, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 13"));  ASSERT_EQ(Encoding_Japanese, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO 2022 IR 166"));  ASSERT_EQ(Encoding_Thai, e);
+
+  // http://www.dabsoft.ch/dicom/3/C.12.1.1.2/ - Table C.12-4
+  ASSERT_FALSE(GetDicomEncoding(e, "ISO 2022 IR 87"));  //ASSERT_EQ(Encoding_JapaneseKanji, e);
+  ASSERT_FALSE(GetDicomEncoding(e, "ISO 2022 IR 159"));  //ASSERT_EQ(Encoding_JapaneseKanjiSupplementary, e);
+  ASSERT_FALSE(GetDicomEncoding(e, "ISO 2022 IR 149"));  //ASSERT_EQ(Encoding_Korean, e);
+
+  // http://www.dabsoft.ch/dicom/3/C.12.1.1.2/ - Table C.12-5
+  ASSERT_TRUE(GetDicomEncoding(e, "ISO_IR 192"));  ASSERT_EQ(Encoding_Utf8, e);
+  ASSERT_TRUE(GetDicomEncoding(e, "GB18030")); ASSERT_EQ(Encoding_Chinese, e);
+}
+
+
+TEST(FromDcmtkBridge, DISABLED_Encodings3)
+{
+  for (unsigned int i = 0; i < testEncodingsCount; i++)
+  {
+    ParsedDicomFile f;
+    f.SetEncoding(testEncodings[i]);
+
+    std::string source(testEncodingsEncoded[i]);
+    std::string expected(testEncodingsExpected[i]);
+    std::string s = Toolbox::ConvertToUtf8(source, testEncodings[i]);
+    std::cout << EnumerationToString(testEncodings[i]) << std::endl;
+    EXPECT_EQ(expected, s);
+  }
+}
--- a/UnitTestsSources/UnitTestsMain.cpp	Tue Aug 05 08:49:25 2014 +0200
+++ b/UnitTestsSources/UnitTestsMain.cpp	Tue Aug 05 12:04:23 2014 +0200
@@ -652,6 +652,9 @@
   ASSERT_EQ(Encoding_Arabic, StringToEncoding(EnumerationToString(Encoding_Arabic)));
   ASSERT_EQ(Encoding_Greek, StringToEncoding(EnumerationToString(Encoding_Greek)));
   ASSERT_EQ(Encoding_Hebrew, StringToEncoding(EnumerationToString(Encoding_Hebrew)));
+  ASSERT_EQ(Encoding_Japanese, StringToEncoding(EnumerationToString(Encoding_Japanese)));
+  ASSERT_EQ(Encoding_Chinese, StringToEncoding(EnumerationToString(Encoding_Chinese)));
+  ASSERT_EQ(Encoding_Thai, StringToEncoding(EnumerationToString(Encoding_Thai)));
 
   ASSERT_EQ(ResourceType_Patient, StringToResourceType(EnumerationToString(ResourceType_Patient)));
   ASSERT_EQ(ResourceType_Study, StringToResourceType(EnumerationToString(ResourceType_Study)));