Feature/sina/hdf5 output support

src/axom/sina/core/Document.cpp

@@ -22,6 +22,10 @@
 #include <utility>
 #include <sstream>
 #include <stdexcept>
+#include <algorithm>
+#include "conduit.hpp"
+#include "conduit_relay.hpp"
+#include "conduit_relay_io.hpp"
 
 namespace axom
 {
@@ -33,7 +37,124 @@ namespace
 char const RECORDS_KEY[] = "records";
 char const RELATIONSHIPS_KEY[] = "relationships";
 char const SAVE_TMP_FILE_EXTENSION[] = ".sina.tmp";
-}  // namespace
+}
+
+void protocol_warn(std::string protocol, std::string const &name) {
+  size_t pos = name.rfind('.');
+
+  if (pos != std::string::npos) {
+        std::string found = name.substr(pos+1);
+
+        if (("." + found) != protocol && protocol == ".json") {
+          std::cout << ".json extension not found, did you mean to save to this format?";
+        } else if (("." + found) != protocol && protocol == ".hdf5") {
+          std::cout << ".hdf5 extension not found, did you use one of its other supported types? (h5, hdf, ...)";
+        } else {
+          return;
+        }
+  } else {
+    std::cout << "No file extension found, did you mean to use one of " << protocol << "'s supported types?";
+  }
+}
+
+void removeSlashes(const conduit::Node& originalNode, conduit::Node& modifiedNode)
+{
+    for (auto it = originalNode.children(); it.has_next();)
+    {
+        it.next();
+        std::string key = it.name();
+        std::string modifiedKey = key;
+
+        std::string toReplace = "/";
+
+        size_t pos = 0;
+        // Find and replace all occurrences of "/"
+        while ((pos = modifiedKey.find(toReplace, pos)) != std::string::npos) {
+          modifiedKey.replace(pos, toReplace.length(), slashSubstitute);
+          pos += slashSubstitute.length(); // Move past the replaced substring
+        }
+
+        modifiedNode[modifiedKey] = it.node();
+
+        if (it.node().dtype().is_object())
+        {
+            conduit::Node nestedNode;
+            removeSlashes(it.node(), nestedNode);
+            modifiedNode[modifiedKey].set(nestedNode); 
+        }
+    }
+}
+
+void restoreSlashes(const conduit::Node& modifiedNode, conduit::Node& restoredNode)
+{
+    // Check if List or Object, if its a list the else statement would turn it into an object
+    // which breaks the Document
+
+    if (modifiedNode.dtype().is_list())
+    {
+        // If its empty with no children it's the end of a tree
+
+        for (auto it = modifiedNode.children(); it.has_next();)
+        {
+            it.next();
+            conduit::Node& newChild = restoredNode.append();
+
+            // Leaves empty nodes empty, if null data is set the
+            // Document breaks
+
+            if (it.node().dtype().is_string() || it.node().dtype().is_number())
+            {
+                newChild.set(it.node()); // Lists need .set
+            }
+
+            // Recursive Call
+            if (it.node().number_of_children() > 0)
+            {
+                restoreSlashes(it.node(), newChild);
+            }
+        }
+    }
+    else
+    {
+        for (auto it = modifiedNode.children(); it.has_next();)
+        {
+            it.next();
+            std::string key = it.name();
+            std::string restoredKey = key;
+            std::string replacement = "/";
+
+            size_t pos = 0;
+            // Find and replace all occurrences of "__SLASH__"
+
+            while ((pos = restoredKey.find(slashSubstitute, pos)) != std::string::npos) {
+                restoredKey.replace(pos, toReplace.length(), replacement);
+                pos += replacement.length();
+            }
+
+
+            // Initialize a new node for the restored key
+            conduit::Node& newChild = restoredNode.add_child(restoredKey);
+
+            // Leaves empty keys empty but continues recursive call if its a list
+            if (it.node().dtype().is_string() || it.node().dtype().is_number() || it.node().dtype().is_object())
+            {
+                newChild.set(it.node());
+            }
+            else if (it.node().dtype().is_list())
+            {
+                restoreSlashes(it.node(), newChild);  // Handle nested lists
+            }
+
+            // If the node has children, recursively restore them
+            if (it.node().number_of_children() > 0)
+            {
+                conduit::Node nestedNode;
+                restoreSlashes(it.node(), nestedNode);
+                newChild.set(nestedNode);
+            }
+        }
+    }
+}
 
 void Document::add(std::unique_ptr<Record> record)
 {
@@ -87,26 +208,27 @@ void Document::createFromNode(conduit::Node const &asNode,
     }
   }
 
-  if(asNode.has_child(RELATIONSHIPS_KEY))
-  {
-    conduit::Node relationship_nodes = asNode[RELATIONSHIPS_KEY];
-    if(relationship_nodes.dtype().is_list())
-    {
-      auto relationshipsIter = relationship_nodes.children();
-      while(relationshipsIter.has_next())
-      {
-        auto &relationship = relationshipsIter.next();
-        add(Relationship {relationship});
-      }
-    }
-    else
+  if (asNode.has_child(RELATIONSHIPS_KEY))
     {
-      std::ostringstream message;
-      message << "The '" << RELATIONSHIPS_KEY
-              << "' element of a document must be an array";
-      throw std::invalid_argument(message.str());
+        conduit::Node relationship_nodes = asNode[RELATIONSHIPS_KEY];
+        if (relationship_nodes.number_of_children() == 0)
+        {
+            relationship_nodes.set(conduit::DataType::list());
+        }
+        else if (!relationship_nodes.dtype().is_list())
+        {
+            std::ostringstream message;
+            message << "The '" << RELATIONSHIPS_KEY << "' element of a document must be an array";
+            throw std::invalid_argument(message.str());
+        }
+
+        auto relationshipsIter = relationship_nodes.children();
+        while (relationshipsIter.has_next())
+        {
+            auto &relationship = relationshipsIter.next();
+            add(Relationship{relationship});
+        }
     }
-  }
 }
 
 Document::Document(conduit::Node const &asNode, RecordLoader const &recordLoader)
@@ -121,6 +243,37 @@ Document::Document(std::string const &asJson, RecordLoader const &recordLoader)
   this->createFromNode(asNode, recordLoader);
 }
 
+void Document::toHDF5(const std::string &filename) const 
+{
+    conduit::Node node;
+    conduit::Node &recordsNode = node["records"];
+    conduit::Node &relationshipsNode = node["relationships"];
+
+    for (const auto& record : getRecords())
+    {
+        conduit::Node recordNode = record->toNode();
+        conduit::Node modifiedRecordNode;
+
+        removeSlashes(recordNode, modifiedRecordNode);
+
+        recordsNode.append() = modifiedRecordNode; 
+    }
+
+    // Process relationships
+    for (const auto& relationship : getRelationships())
+    {
+        conduit::Node relationshipNode = relationship.toNode();
+        conduit::Node modifiedRelationshipsNode;
+
+        removeSlashes(relationshipNode, modifiedRelationshipsNode);
+        relationshipsNode.append() = modifiedRelationshipsNode;
+    }
+
+    conduit::relay::io::save(node, filename, "hdf5");
+}
+
+//
+
 std::string Document::toJson(conduit::index_t indent,
                              conduit::index_t depth,
                              const std::string &pad,
@@ -129,7 +282,7 @@ std::string Document::toJson(conduit::index_t indent,
   return this->toNode().to_json("json", indent, depth, pad, eoe);
 }
 
-void saveDocument(Document const &document, std::string const &fileName)
+void saveDocument(Document const &document, std::string const &fileName, Protocol protocol)
 {
   // It is a common use case for users to want to overwrite their files as
   // the simulation progresses. However, this operation should be atomic so
@@ -138,37 +291,63 @@ void saveDocument(Document const &document, std::string const &fileName)
   // file is in the same directory to ensure that it is part of the same
   // file system as the destination file so that the move operation is
   // atomic.
+
   std::string tmpFileName = fileName + SAVE_TMP_FILE_EXTENSION;
-  auto asJson = document.toJson();
-  std::ofstream fout {tmpFileName};
-  fout.exceptions(std::ostream::failbit | std::ostream::badbit);
-  fout << asJson;
-  fout.close();
 
-  if(rename(tmpFileName.c_str(), fileName.c_str()) != 0)
+  if (protocol == Protocol::JSON)
   {
-    std::string message {"Could not save to '"};
-    message += fileName;
-    message += "'";
-    throw std::ios::failure {message};
+      protocol_warn(".json", fileName);
+      auto asJson = document.toJson();
+      std::ofstream fout {tmpFileName};
+      fout.exceptions(std::ostream::failbit | std::ostream::badbit);
+      fout << asJson;
+      fout.close();
+  }
+  else if (protocol == Protocol::HDF5)
+  {
+      protocol_warn(".hdf5", fileName);
+      document.toHDF5(tmpFileName);
+  }
+  else
+  {
+      throw std::invalid_argument("Invalid format choice. Please enter 'json' or 'hdf5'.");
+  }
+
+  if (rename(tmpFileName.c_str(), fileName.c_str()) != 0)
+  {
+      std::string message {"Could not save to '"};
+      message += fileName;
+      message += "'";
+      throw std::ios::failure {message};
   }
 }
 
-Document loadDocument(std::string const &path)
+Document loadDocument(std::string const &path, Protocol protocol)
 {
-  return loadDocument(path, createRecordLoaderWithAllKnownTypes());
+  return loadDocument(path, createRecordLoaderWithAllKnownTypes(), protocol);
 }
 
-Document loadDocument(std::string const &path, RecordLoader const &recordLoader)
+Document loadDocument(std::string const &path, RecordLoader const &recordLoader, Protocol protocol)
 {
-  conduit::Node nodeFromJson;
-  std::ifstream file_in {path};
-  std::ostringstream file_contents;
-  file_contents << file_in.rdbuf();
-  file_in.close();
-  nodeFromJson.parse(file_contents.str(), "json");
-  return Document {nodeFromJson, recordLoader};
+    conduit::Node node;
+
+    // Load the file depending on the protocol
+    if (protocol == Protocol::JSON) {
+        std::ifstream file_in {path};
+        std::ostringstream file_contents;
+        file_contents << file_in.rdbuf();
+        file_in.close();
+        node.parse(file_contents.str(), "json");
+        return Document {node, recordLoader};
+    } else if (protocol == Protocol::HDF5) {
+        conduit::Node modifiedNode;
+        conduit::relay::io::load(path, "hdf5", node);
+        restoreSlashes(node, modifiedNode);
+        return Document {modifiedNode, recordLoader};
+    }
+
+    // Finally, use the node to create the Document object (existing logic)
 }
 
 }  // namespace sina
-}  // namespace axom
+}  // namespace axom