#1619 Import/export of variant monomers from IDT

Add import/export of standard variant ID monomers.
Add UTs

api/c/indigo/indigo.h

@@ -198,6 +198,12 @@ CEXPORT int indigoLoadSmartsFromBuffer(const char* buffer, int size);
 CEXPORT int indigoLoadMonomerLibrary(int source);
 CEXPORT int indigoLoadMonomerLibraryFromString(const char* string);
 CEXPORT int indigoLoadMonomerLibraryFromFile(const char* filename);
+CEXPORT int indigoLoadMonomerLibraryFromBuffer(const char* buffer, int size);
+
+CEXPORT int indigoLoadKetDocument(int source);
+CEXPORT int indigoLoadKetDocumentFromString(const char* string);
+CEXPORT int indigoLoadKetDocumentFromFile(const char* filename);
+CEXPORT int indigoLoadKetDocumentFromBuffer(const char* buffer, int size);
 
 CEXPORT int indigoLoadSequence(int source, const char* seq_type, int library);
 CEXPORT int indigoLoadSequenceFromString(const char* string, const char* seq_type, int library);

api/c/indigo/src/indigo_macros.c

@@ -84,6 +84,14 @@ WRAPPER_LOAD_FROM_STRING(indigoLoadReactionSmarts)
 WRAPPER_LOAD_FROM_FILE(indigoLoadReactionSmarts)
 WRAPPER_LOAD_FROM_BUFFER(indigoLoadReactionSmarts)
 
+WRAPPER_LOAD_FROM_STRING(indigoLoadMonomerLibrary)
+WRAPPER_LOAD_FROM_FILE(indigoLoadMonomerLibrary)
+WRAPPER_LOAD_FROM_BUFFER(indigoLoadMonomerLibrary)
+
+WRAPPER_LOAD_FROM_STRING(indigoLoadKetDocument)
+WRAPPER_LOAD_FROM_FILE(indigoLoadKetDocument)
+WRAPPER_LOAD_FROM_BUFFER(indigoLoadKetDocument)
+
 CEXPORT int indigoSaveMolfileToFile(int molecule, const char* filename)
 {
     int f = indigoWriteFile(filename);

api/c/indigo/src/indigo_molecule.cpp

@@ -28,6 +28,7 @@
 #include "molecule/canonical_smiles_saver.h"
 #include "molecule/elements.h"
 #include "molecule/hybridization.h"
+#include "molecule/ket_document_json_loader.h"
 #include "molecule/molecule_auto_loader.h"
 #include "molecule/molecule_automorphism_search.h"
 #include "molecule/molecule_fingerprint.h"
@@ -543,36 +544,18 @@ CEXPORT int indigoLoadMonomerLibrary(int source)
     INDIGO_END(-1);
 }
 
-CEXPORT int indigoLoadMonomerLibraryFromString(const char* string)
+CEXPORT int indigoLoadKetDocument(int source)
 {
     INDIGO_BEGIN
     {
-        int source = indigoReadString(string);
-        int result;
-
-        if (source <= 0)
-            return -1;
-
-        result = indigoLoadMonomerLibrary(source);
-        indigoFree(source);
-        return result;
-    }
-    INDIGO_END(-1);
-}
-
-CEXPORT int indigoLoadMonomerLibraryFromFile(const char* filename)
-{
-    INDIGO_BEGIN
-    {
-        int source = indigoReadFile(filename);
-        int result;
-
-        if (source < 0)
-            return -1;
-
-        result = indigoLoadMonomerLibrary(source);
-        indigoFree(source);
-        return result;
+        IndigoObject& obj = self.getObject(source);
+        auto& scanner = IndigoScanner::get(obj);
+        std::string json_str;
+        scanner.readAll(json_str);
+        std::unique_ptr<IndigoKetDocument> docptr = std::make_unique<IndigoKetDocument>();
+        KetDocumentJsonLoader loader{};
+        loader.parseJson(json_str, docptr->get());
+        return self.addObject(docptr.release());
     }
     INDIGO_END(-1);
 }

api/c/indigo/src/indigo_savers.cpp

@@ -639,6 +639,14 @@ CEXPORT int indigoSaveIdt(int item, int output, int library)
             out.flush();
             return 1;
         }
+        else if (IndigoKetDocument::is(obj))
+        {
+            IndigoObject& lib_obj = self.getObject(library);
+            SequenceSaver saver(out, IndigoMonomerLibrary::get(lib_obj));
+            saver.saveKetDocument(static_cast<IndigoKetDocument&>(obj).get(), SequenceSaver::SeqFormat::IDT);
+            out.flush();
+            return 1;
+        }
         throw IndigoError("indigoSaveIdt(): expected molecule, got %s", obj.debugInfo());
     }
     INDIGO_END(-1);

api/c/tests/unit/tests/formats.cpp

@@ -24,6 +24,8 @@
 
 #include "common.h"
 
+#include <fstream>
+
 using namespace std;
 using namespace indigo;
 
@@ -282,3 +284,29 @@ TEST_F(IndigoApiFormatsTest, noFile)
         },
         Exception);
 }
+
+TEST_F(IndigoApiFormatsTest, idt_to_ket)
+{
+    int obj = -1;
+    int library = indigoLoadMonomerLibraryFromFile(dataPath("molecules/basic/monomer_library.ket").c_str());
+    obj = indigoLoadIdtFromString("ARAS", library);
+    indigoSetOptionBool("json-saving-pretty", true);
+    const char* res = indigoJson(obj);
+    // printf("res=%s", res);
+    std::ifstream is(dataPath("molecules/basic/idt_mixed_std.ket"), std::ios::binary | std::ios::ate);
+    auto size = is.tellg();
+    std::string str(size, '\0'); // construct string to stream size
+    is.seekg(0);
+    is.read(&str[0], size);
+    ASSERT_STREQ(res, str.c_str());
+}
+
+TEST_F(IndigoApiFormatsTest, ket_to_idt)
+{
+    int obj = -1;
+    int library = indigoLoadMonomerLibraryFromFile(dataPath("molecules/basic/monomer_library.ket").c_str());
+    obj = indigoLoadKetDocumentFromFile(dataPath("molecules/basic/idt_mixed_std.ket").c_str());
+    const char* res = indigoIdt(obj, library);
+    // printf("res=%s", res);
+    ASSERT_STREQ("ARAS", res);
+}

api/python/indigo/indigo/indigo.py

@@ -548,6 +548,46 @@ def loadMonomerLibraryFromFile(self, filename):
             ),
         )
 
+    def loadKetDocument(self, string):
+        """Loads ket document from ket string
+
+        Args:
+            string (str): ket
+
+        Returns:
+            IndigoObject: loaded ket document
+
+        Raises:
+            IndigoException: Exception if structure format is incorrect
+        """
+
+        return IndigoObject(
+            self,
+            IndigoLib.checkResult(
+                self._lib().indigoLoadKetDocumentFromString(string.encode())
+            ),
+        )
+
+    def loadKetDocumentFromFile(self, filename):
+        """Loads ket document from from file in ket format
+
+        Args:
+            string (str): full path to the file with ket
+
+        Returns:
+            IndigoObject: loaded ket document
+
+        Raises:
+            IndigoException: Exception if structure format is incorrect
+        """
+
+        return IndigoObject(
+            self,
+            IndigoLib.checkResult(
+                self._lib().indigoLoadKetDocumentFromFile(filename.encode())
+            ),
+        )
+
     def loadSequence(self, string, seq_type, library):
         """Loads molecule from DNA/RNA/PEPTIDE sequence string
 

api/python/indigo/indigo/indigo_lib.py

@@ -136,6 +136,10 @@ def __init__(self) -> None:
         IndigoLib.lib.indigoLoadMonomerLibraryFromString.argtypes = [c_char_p]
         IndigoLib.lib.indigoLoadMonomerLibraryFromFile.restype = c_int
         IndigoLib.lib.indigoLoadMonomerLibraryFromFile.argtypes = [c_char_p]
+        IndigoLib.lib.indigoLoadKetDocumentFromString.restype = c_int
+        IndigoLib.lib.indigoLoadKetDocumentFromString.argtypes = [c_char_p]
+        IndigoLib.lib.indigoLoadKetDocumentFromFile.restype = c_int
+        IndigoLib.lib.indigoLoadKetDocumentFromFile.argtypes = [c_char_p]
         IndigoLib.lib.indigoLoadSequenceFromString.restype = c_int
         IndigoLib.lib.indigoLoadSequenceFromString.argtypes = [
             c_char_p,

api/tests/integration/ref/formats/ket_to_idt.py.out

@@ -17,6 +17,7 @@ idt_i2moera_sp_32moera.ket:SUCCEED
 idt_i2moera_t.ket:SUCCEED
 idt_many_molecules.ket:SUCCEED
 idt_mixed.ket:SUCCEED
+idt_mixed_std.ket:SUCCEED
 idt_mod_phosphates.ket:SUCCEED
 idt_modifications.ket:SUCCEED
 idt_more_than_80_chars.ket:SUCCEED

api/tests/integration/tests/formats/ket_to_idt.py

@@ -61,10 +61,11 @@ def find_diff(a, b):
     "idt_52moera_sp_i2moera_sp": "/52MOErA/*/i2MOErA/*",
     "idt_unsplit": "/5UNSPLIT/A",
     "idt_more_than_80_chars": "/52MOErA//i2MOErA//i2MOErA//i2MOErA//i2MOErA//i2MOErA//i2MOErA//i2MOErA//i2MOErA//i2MOErA//i2MOErA//i2MOErA//3Phos/",
+    "idt_mixed_std": "ARAS",
 }
 
 for filename in sorted(idt_data.keys()):
-    mol = indigo.loadMoleculeFromFile(os.path.join(ref, filename + ".ket"))
+    mol = indigo.loadKetDocumentFromFile(os.path.join(ref, filename + ".ket"))
     idt = mol.idt(lib)
     idt_ref = idt_data[filename]
     if idt_ref == idt: