private void SaveIndexTableItem(BinaryWriter writer, IndexTableItem item)
{
writer.Write(item.nCount);
for (int i = 0; i < item.nCount; i++)
{
SaveWordItem(writer, item.WordItems[i]);
}
}
//====================================================================
// Func Name : Load
// Description: Load the dictionary from the file .dct
// Parameters : sFilename: the file name
// Returns : success or fail
//====================================================================
public bool Load(string sFilename, bool bReset)
{
int frequency, wordLength, pos; //频率、词长、读取词性
bool isSuccess = true;
FileStream fileStream = null;
BinaryReader binReader = null;
try
{
fileStream = new FileStream(sFilename, FileMode.Open, FileAccess.Read);
if (fileStream == null)
{
return(false);
}
binReader = new BinaryReader(fileStream, Encoding.GetEncoding("gb2312"));
indexTable = new IndexTableItem[Predefine.CC_NUM];
bReleased = false;
for (int i = 0; i < Predefine.CC_NUM; i++)
{
//读取以该汉字打头的词有多少个
indexTable[i] = new IndexTableItem();
indexTable[i].nCount = binReader.ReadInt32();
if (indexTable[i].nCount <= 0)
{
continue;
}
indexTable[i].WordItems = new WordItem[indexTable[i].nCount];
for (int j = 0; j < indexTable[i].nCount; j++)
{
indexTable[i].WordItems[j] = new WordItem();
frequency = binReader.ReadInt32(); //读取频率
wordLength = binReader.ReadInt32(); //读取词长
pos = binReader.ReadInt32(); //读取词性
if (wordLength > 0)
{
indexTable[i].WordItems[j].sWord = Utility.ByteArray2String(binReader.ReadBytes(wordLength));
}
else
{
indexTable[i].WordItems[j].sWord = "";
}
//Reset the frequency
if (bReset)
{
indexTable[i].WordItems[j].nFrequency = 0;
}
else
{
indexTable[i].WordItems[j].nFrequency = frequency;
}
indexTable[i].WordItems[j].nWordLen = wordLength;
indexTable[i].WordItems[j].nPOS = pos;
}
}
}
catch (Exception e)
{
Console.WriteLine(e.Message);
isSuccess = false;
}
finally
{
if (binReader != null)
{
binReader.Close();
}
if (fileStream != null)
{
fileStream.Close();
}
}
return(isSuccess);
}
private void MergeAndSaveIndexTableItem(BinaryWriter writer, IndexTableItem item, ModifyTableItem modifyItem)
{
int j, nCount; //频率、词长、读取词性
WordChain pCur;
//计算修改后有效词块的数目
nCount = item.nCount + modifyItem.nCount - modifyItem.nDelete;
writer.Write(nCount);
pCur = modifyItem.pWordItemHead;
j = 0;
//对原表中的词块和修改表中的词块进行遍历,并把修改后的添加到原表中
while (pCur != null && j < item.nCount)
{
//如果修改表中的词小于原表中对应位置的词或者长度相等但nHandle值比原表中的小,则把修改表中的写入到词典文件当中.
if (Utility.CCStringCompare(pCur.data.sWord, item.WordItems[j].sWord) < 0 ||
((pCur.data.sWord == item.WordItems[j].sWord) &&
(pCur.data.nPOS < item.WordItems[j].nPOS)))
{
//Output the modified data to the file
SaveWordItem(writer, pCur.data);
pCur = pCur.next;
}
//频度nFrequecy等于-1说明该词已被删除,跳过它
else if (item.WordItems[j].nFrequency == -1)
{
j++;
}
//如果修改表中的词长度比原表中的长度大或 长度相等但句柄值要多,就把原表的词写入的词典文件中
else if (Utility.CCStringCompare(pCur.data.sWord, item.WordItems[j].sWord) > 0 ||
((pCur.data.sWord == item.WordItems[j].sWord) &&
(pCur.data.nPOS > item.WordItems[j].nPOS)))
{
//Output the index table data to the file
SaveWordItem(writer, item.WordItems[j]);
j++;
}
}
//如果归并结束后indexTable有剩余，则继续写完indexTable中的数据
if (j < item.nCount)
{
for (int i = j; i < item.nCount; i++)
{
if (item.WordItems[j].nFrequency != -1)
{
SaveWordItem(writer, item.WordItems[i]);
}
}
}
//否则继续写完modifyTable中的数据
else
{
while (pCur != null)
{
//Output the modified data to the file
SaveWordItem(writer, pCur.data);
pCur = pCur.next;
}
}
}
//====================================================================
// Func Name : Load
// Description: Load the dictionary from the file .dct
// Parameters : sFilename: the file name
// Returns : success or fail
//====================================================================
public bool Load(string sFilename, bool bReset)
{
int frequency, wordLength, pos; //频率、词长、读取词性
bool isSuccess = true;
FileStream fileStream = null;
BinaryReader binReader = null;
try
{
fileStream = new FileStream(sFilename, FileMode.Open, FileAccess.Read);
if (fileStream == null)
return false;
binReader = new BinaryReader(fileStream, Encoding.GetEncoding("gb2312"));
indexTable = new IndexTableItem[Predefine.CC_NUM];
bReleased = false;
for (int i = 0; i < Predefine.CC_NUM; i++)
{
//读取以该汉字打头的词有多少个
indexTable[i] = new IndexTableItem();
indexTable[i].nCount = binReader.ReadInt32();
if (indexTable[i].nCount <= 0)
continue;
indexTable[i].WordItems = new WordItem[indexTable[i].nCount];
for (int j = 0; j < indexTable[i].nCount; j++)
{
indexTable[i].WordItems[j] = new WordItem();
frequency = binReader.ReadInt32(); //读取频率
wordLength = binReader.ReadInt32(); //读取词长
pos = binReader.ReadInt32(); //读取词性
if (wordLength > 0)
indexTable[i].WordItems[j].sWord = Utility.ByteArray2String(binReader.ReadBytes(wordLength));
else
indexTable[i].WordItems[j].sWord = "";
//Reset the frequency
if (bReset)
indexTable[i].WordItems[j].nFrequency = 0;
else
indexTable[i].WordItems[j].nFrequency = frequency;
indexTable[i].WordItems[j].nWordLen = wordLength;
indexTable[i].WordItems[j].nPOS = pos;
}
}
}
catch (Exception e)
{
Console.WriteLine(e.Message);
isSuccess = false;
}
finally
{
if (binReader != null)
binReader.Close();
if (fileStream != null)
fileStream.Close();
}
return isSuccess;
}
private void SaveIndexTableItem(BinaryWriter writer, IndexTableItem item)
{
writer.Write(item.nCount);
for (int i = 0; i < item.nCount; i++)
SaveWordItem(writer, item.WordItems[i]);
}
private void MergeAndSaveIndexTableItem(BinaryWriter writer, IndexTableItem item, ModifyTableItem modifyItem)
{
int j, nCount; //频率、词长、读取词性
WordChain pCur;
//计算修改后有效词块的数目
nCount = item.nCount + modifyItem.nCount - modifyItem.nDelete;
writer.Write(nCount);
pCur = modifyItem.pWordItemHead;
j = 0;
//对原表中的词块和修改表中的词块进行遍历,并把修改后的添加到原表中
while (pCur != null && j < item.nCount)
{
//如果修改表中的词小于原表中对应位置的词或者长度相等但nHandle值比原表中的小,则把修改表中的写入到词典文件当中.
if (Utility.CCStringCompare(pCur.data.sWord, item.WordItems[j].sWord) < 0 ||
((pCur.data.sWord == item.WordItems[j].sWord) &&
(pCur.data.nPOS < item.WordItems[j].nPOS)))
{
//Output the modified data to the file
SaveWordItem(writer, pCur.data);
pCur = pCur.next;
}
//频度nFrequecy等于-1说明该词已被删除,跳过它
else if (item.WordItems[j].nFrequency == -1)
j++;
//如果修改表中的词长度比原表中的长度大或 长度相等但句柄值要多,就把原表的词写入的词典文件中
else if (Utility.CCStringCompare(pCur.data.sWord, item.WordItems[j].sWord) > 0 ||
((pCur.data.sWord == item.WordItems[j].sWord) &&
(pCur.data.nPOS > item.WordItems[j].nPOS)))
{
//Output the index table data to the file
SaveWordItem(writer, item.WordItems[j]);
j++;
}
}
//如果归并结束后indexTable有剩余，则继续写完indexTable中的数据
if (j < item.nCount)
{
for (int i = j; i < item.nCount; i++)
if (item.WordItems[j].nFrequency != -1)
SaveWordItem(writer, item.WordItems[i]);
}
//否则继续写完modifyTable中的数据
else
while (pCur != null)
{
//Output the modified data to the file
SaveWordItem(writer, pCur.data);
pCur = pCur.next;
}
}
private void MergeAndSaveIndexTableItem(BinaryWriter writer, IndexTableItem item, ModifyTableItem modifyItem)
{
int j, nCount; //Ƶ�ʡ��ʳ�����ȡ����
WordChain pCur;
//�����ĺ���Ч�ʿ����Ŀ
nCount = item.nCount + modifyItem.nCount - modifyItem.nDelete;
writer.Write(nCount);
pCur = modifyItem.pWordItemHead;
j = 0;
//��ԭ���еĴʿ���ı��еĴʿ���б���,�����ĺ����ӵ�ԭ����
while (pCur != null && j < item.nCount)
{
//����ı��еĴ�С��ԭ���ж�Ӧλ�õĴʻ��߳�����ȵ�nHandleֵ��ԭ���е�С,����ı��е�д�뵽�ʵ��ļ�����.
if (Utility.CCStringCompare(pCur.data.sWord, item.WordItems[j].sWord) < 0 ||
((pCur.data.sWord == item.WordItems[j].sWord) &&
(pCur.data.nPOS < item.WordItems[j].nPOS)))
{
//Output the modified data to the file
SaveWordItem(writer, pCur.data);
pCur = pCur.next;
}
//Ƶ��nFrequecy����-1˵���ô��ѱ�ɾ��,������
else if (item.WordItems[j].nFrequency == -1)
j++;
//����ı��еĴʳ��ȱ�ԭ���еij��ȴ�� ������ȵ����ֵҪ��,�Ͱ�ԭ��Ĵ�д��Ĵʵ��ļ���
else if (Utility.CCStringCompare(pCur.data.sWord, item.WordItems[j].sWord) > 0 ||
((pCur.data.sWord == item.WordItems[j].sWord) &&
(pCur.data.nPOS > item.WordItems[j].nPOS)))
{
//Output the index table data to the file
SaveWordItem(writer, item.WordItems[j]);
j++;
}
}
//����鲢������indexTable��ʣ�࣬�����д��indexTable�е�����
if (j < item.nCount)
{
for (int i = j; i < item.nCount; i++)
if (item.WordItems[j].nFrequency != -1)
SaveWordItem(writer, item.WordItems[i]);
}
//��������modifyTable�����
else
while (pCur != null)
{
//Output the modified data to the file
SaveWordItem(writer, pCur.data);
pCur = pCur.next;
}
}
