From 2bedb2a82fd9418ea5302fb6d39acf6dda786a72 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Luk=C3=A1=C5=A1=20Pleva=C4=8D?= <lukas@plevac.eu>
Date: Mon, 27 Nov 2023 19:43:09 +0100
Subject: [PATCH] Added support for decode

---
 src/SIMDDNA/assembly.py | 19 ++++++++++++-------
 src/SIMDDNA/molecule.py | 40 +++++++++++++++++++++++++++++++++++++++-
 src/main.py             |  7 ++++++-
 3 files changed, 57 insertions(+), 9 deletions(-)

diff --git a/src/SIMDDNA/assembly.py b/src/SIMDDNA/assembly.py
index 71ccb97..2fcfdb8 100644
--- a/src/SIMDDNA/assembly.py
+++ b/src/SIMDDNA/assembly.py
@@ -60,15 +60,10 @@ class Assembly:
             elif ":" in ins and is_in:
                 break
             elif is_in:
-                reg = ins.split(" ")
-
-                if len(reg) > 1:
-                    print("WARNING: ASM parsing data molecule with space. All after space is ignored!")
-
-                reg = reg[0]
+                reg = self.useMacros(ins).replace(" ", "")
 
                 if not reg.isspace() and len(reg) > 0:
-                    datas.append(molecule.parse(self.useMacros(reg)))
+                    datas.append(molecule.parse(reg))
 
         return datas        
 
@@ -97,4 +92,14 @@ class Assembly:
                     gins.append(DNAInsArray)
 
         return gins     
+    
+    def decode(self, reg):
+        mol = molecule.encode(reg.mol)
+
+        for macro in self.macros:
+            mol = mol.replace(macro[1], macro[0])
+            
+        return mol
+
+
 
diff --git a/src/SIMDDNA/molecule.py b/src/SIMDDNA/molecule.py
index dc949f6..4227e65 100644
--- a/src/SIMDDNA/molecule.py
+++ b/src/SIMDDNA/molecule.py
@@ -326,4 +326,42 @@ def parse(notationStr):
 
     newMolecule.endPad()
 
-    return newMolecule
\ No newline at end of file
+    return newMolecule
+
+##
+# Encode molecule to ASCII reprezentation
+# @param mol moleculte to encode
+# @retun STR of ascii reprezentation
+# @todo support for overhangs
+#
+def encode(mol):
+    outstr = ""
+    lastClose = ""
+    lastChain = -1
+    lastBounded = None
+    
+    for basePos in range(len(mol)):
+        bounded = False
+        for chainID in range(1, mol.chainsCount()):
+            if isComplementary(mol.getBase(chainID, basePos), mol.getBase(0, basePos)):
+                if not lastBounded or lastBounded is None or lastChain != chainID:
+                    lastBounded  = True
+                    lastChain    = chainID
+                    outstr      += lastClose + "["
+                    lastClose    = "]"
+
+                bounded = True
+                break
+
+        if (not bounded and lastBounded) or lastBounded is None:
+            lastBounded = False
+            outstr     += lastClose + "{"
+            lastClose   = "}"
+
+        if mol.getBase(0, basePos) == nothing:
+            break
+
+        outstr += mol.getBase(0, basePos)
+
+    return (outstr + lastClose).replace("{}", "").replace("[]", "")
+                
\ No newline at end of file
diff --git a/src/main.py b/src/main.py
index 4cf7a11..b283684 100755
--- a/src/main.py
+++ b/src/main.py
@@ -69,4 +69,9 @@ for reg in regs:
 
 if args.decode:
     # todo: implement it
-    pass
\ No newline at end of file
+    print()
+    print("Decoded")
+    print("--------------------------------")
+    print()
+    for reg in regs:
+        print(asm.decode(reg))
\ No newline at end of file