From 6613f3fd45b4ecf6821ee7bb07c95f86f43b0db2 Mon Sep 17 00:00:00 2001
From: John Fultz <jfultz@wolfram.com>
Date: Thu, 20 Aug 2015 04:59:36 -0500
Subject: Move DAWG generation into quackleio.

Same thing I just did for the gaddag code I'm now doing
for the dawg code.  While I was at it, I made some
improvements to the dawg code...

* Instead of adding multiple cross-checks for various
kinds of node metadata, there's now only one cross-
check...a hash applied to each node.
* Some useless variables/members have been excised.
* Add ability to do a word count (cryptohash coming soon).
* Make it possible to call generate() and writeIndex()
multiple times without corrupting the dictionary.
---
 makeminidawg/makeminidawgmain.cpp | 124 ++++++++++++++++++++++++++++++++++++--
 1 file changed, 119 insertions(+), 5 deletions(-)

(limited to 'makeminidawg/makeminidawgmain.cpp')

diff --git a/makeminidawg/makeminidawgmain.cpp b/makeminidawg/makeminidawgmain.cpp
index 82871be..89afb68 100644
--- a/makeminidawg/makeminidawgmain.cpp
+++ b/makeminidawg/makeminidawgmain.cpp
@@ -16,16 +16,130 @@
  *  along with this program. If not, see <http://www.gnu.org/licenses/>.
  */
 
-#include <QCoreApplication>
-#include <QStringList>
+#include <map>
+#include <QtCore>
 
-#include "minidawgmaker.h"
+#include "quackleio/dawgfactory.h"
+#include "quackleio/froggetopt.h"
+#include "quackleio/util.h"
+
+std::map< QString, bool> smallerMap;
+std::map< QString, int> playabilityMap;
 
 int main(int argc, char **argv)
 {
 	QCoreApplication a(argc, argv);
 
-	MiniDawgMaker maker;
-	return maker.executeFromArguments();
+	GetOpt opts;
+	QString alphabet;
+	opts.addOption('a', "alphabet", &alphabet);
+	if (!opts.parse())
+		return 1;
+
+	if (alphabet.isNull())
+		alphabet = "english";
+
+	QString alphabetFile = QString("../data/alphabets/%1.quackle_alphabet").arg(alphabet);
+	UVcout << "Using alphabet file: " << QuackleIO::Util::qstringToString(alphabetFile) << endl;
+
+	DawgFactory factory(alphabetFile);
+
+
+	QString smallerDictFilename = "smaller.raw";
+	QFile smallerDict(smallerDictFilename);
+	if (!smallerDict.exists())
+	{
+		UVcout << "smaller dictionary does not exist: " << QuackleIO::Util::qstringToString(smallerDictFilename) << endl;
+		return false;
+	}
+
+	if (!smallerDict.open(QIODevice::ReadOnly | QIODevice::Text))
+	{
+		UVcout << "Could not open " << QuackleIO::Util::qstringToString(smallerDictFilename) << endl;
+		return false;
+	}
+
+	QTextStream smallerStream(&smallerDict);
+	smallerStream.setCodec(QTextCodec::codecForName("UTF-8"));
+	
+	while (!smallerStream.atEnd())
+	{
+		QString originalQString;
+		smallerStream >> originalQString;
+		//UVcout << "this word is in the smaller dictionary: " << QuackleIO::Util::qstringToString(originalQString) << endl;
+		smallerMap[originalQString] = true;
+	}
+
+	QString playabilityFilename = "playabilities.raw";
+	QFile playability(playabilityFilename);
+	if (!playability.exists())
+	{
+		UVcout << "playability does not exist: " << QuackleIO::Util::qstringToString(playabilityFilename) << endl;
+		return false;
+	}
+
+	if (!playability.open(QIODevice::ReadOnly | QIODevice::Text))
+	{
+		UVcout << "Could not open " << QuackleIO::Util::qstringToString(playabilityFilename) << endl;
+		return false;
+	}
+
+	QTextStream playabilityStream(&playability);
+	playabilityStream.setCodec(QTextCodec::codecForName("UTF-8"));
+	
+	while (!playabilityStream.atEnd())
+	{
+		int pb;
+		playabilityStream >> pb;
+		QString originalQString;
+		playabilityStream >> originalQString;
+		//UVcout << "playability: " << QuackleIO::Util::qstringToString(originalQString) << " " << pb << endl;
+		playabilityMap[originalQString] = pb;
+	}
+
+	QString dawgFilename = "dawginput.raw";
+	QFile file(dawgFilename);
+	if (!file.exists())
+	{
+		UVcout << "dawg does not exist: " << QuackleIO::Util::qstringToString(dawgFilename) << endl;
+		return false;
+	}
+
+	if (!file.open(QIODevice::ReadOnly | QIODevice::Text))
+	{
+		UVcout << "Could not open " << QuackleIO::Util::qstringToString(dawgFilename) << endl;
+		return false;
+	}
+
+	QTextStream stream(&file);
+	stream.setCodec(QTextCodec::codecForName("UTF-8"));
+
+	while (!stream.atEnd())
+	{
+		QString word;
+		stream >> word;
+
+		bool inSmaller = smallerMap[word];
+		int pb = playabilityMap[word];
+
+		if (stream.atEnd())
+			break;
+
+		if (!factory.pushWord(word, inSmaller, pb))
+			UVcout << "not encodable without leftover: " << QuackleIO::Util::qstringToString(word) << endl;
+	}
+
+	file.close();
+
+	UVcout << "encodable words: " << factory.encodableWords() << ", unencodable words: " << factory.unencodableWords() << endl;
+
+	UVcout << "nodelist.size(): " << factory.nodeCount() << endl;
+
+	factory.generate();
+	UVcout << "Compressed nodelist.size(): " << factory.nodeCount() << endl;
+
+	factory.writeIndex("output.dawg");
+
+	return 0;
 }
 
-- 
cgit v1.2.3