From 6746da6edd7d9d50efe374eabbb79a3cac882d81 Mon Sep 17 00:00:00 2001
From: Kelly Rauchenberger <fefferburbia@gmail.com>
Date: Mon, 16 Jan 2017 18:02:50 -0500
Subject: Started structural rewrite

The new object structure was designed to build on the existing WordNet
structure, while also adding in all of the data that we get from other sources.
More information about this can be found on the project wiki.

The generator has already been completely rewritten to generate a
datafile that uses the new structure. In addition, a number of indexes
are created, which does double the size of the datafile, but also allows
for much faster lookups. Finally, the new generator is written modularly
and is a lot more readable than the old one.

The verbly interface to the new object structure has mostly been
completed, but has not been tested fully. There is a completely new
search API which utilizes a lot of operator overloading; documentation
on how to use it should go up at some point.

Token processing and verb frames are currently unimplemented. Source for
these have been left in the repository for now.
---
 generator/notion.cpp | 85 ++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 85 insertions(+)
 create mode 100644 generator/notion.cpp

(limited to 'generator/notion.cpp')

diff --git a/generator/notion.cpp b/generator/notion.cpp
new file mode 100644
index 0000000..290d982
--- /dev/null
+++ b/generator/notion.cpp
@@ -0,0 +1,85 @@
+#include "notion.h"
+#include <string>
+#include <list>
+#include "database.h"
+#include "field.h"
+
+namespace verbly {
+  namespace generator {
+
+    int notion::nextId_ = 0;
+
+    notion::notion(
+      part_of_speech partOfSpeech) :
+        id_(nextId_++),
+        partOfSpeech_(partOfSpeech)
+    {
+    }
+
+    notion::notion(
+      part_of_speech partOfSpeech,
+      int wnid) :
+        id_(nextId_++),
+        partOfSpeech_(partOfSpeech),
+        wnid_(wnid),
+        hasWnid_(true)
+    {
+    }
+
+    void notion::incrementNumOfImages()
+    {
+      // Calling code should always call hasWnid and check that the notion is a noun first.
+      assert(hasWnid_ && (partOfSpeech_ == part_of_speech::noun));
+      
+      numOfImages_++;
+    }
+    
+    void notion::setPrepositionGroups(std::list<std::string> groups)
+    {
+      // Calling code should always check that the notion is a preposition first.
+      assert(partOfSpeech_ == part_of_speech::preposition);
+      
+      prepositionGroups_ = groups;
+    }
+
+    database& operator<<(database& db, const notion& arg)
+    {
+      // First, serialize the notion
+      {
+        std::list<field> fields;
+
+        fields.emplace_back("notion_id", arg.getId());
+        fields.emplace_back("part_of_speech", static_cast<int>(arg.getPartOfSpeech()));
+
+        if (arg.hasWnid())
+        {
+          fields.emplace_back("wnid", arg.getWnid());
+        
+          if (arg.getPartOfSpeech() == part_of_speech::noun)
+          {
+            fields.emplace_back("images", arg.getNumOfImages());
+          }
+        }
+
+        db.insertIntoTable("notions", std::move(fields));
+      }
+      
+      // Next, serialize the is_a relationship if this is a preposition
+      if (arg.getPartOfSpeech() == part_of_speech::preposition)
+      {
+        for (std::string group : arg.getPrepositionGroups())
+        {
+          std::list<field> fields;
+          
+          fields.emplace_back("notion_id", arg.getId());
+          fields.emplace_back("groupname", group);
+          
+          db.insertIntoTable("is_a", std::move(fields));
+        }
+      }
+
+      return db;
+    }
+
+  };
+};
-- 
cgit 1.4.1