//Read each line from strTextFileName, and verify wether terms in every line are in strDictFileName
public static void Match(string strTextFileName, DictMatch match)
{
List <Lemma> dm_r = new List <Lemma>();
List <int> offsetList = new List <int>();
StreamReader sr = new StreamReader(strTextFileName);
while (sr.EndOfStream == false)
{
string strLine = sr.ReadLine();
if (strLine.Length == 0)
{
continue;
}
dm_r.Clear();
offsetList.Clear();
match.Search(strLine, ref dm_r, ref offsetList, DictMatch.DM_OUT_FMM);
//if dm_r.Count > 0, it means some contigous terms in strLine have matched terms in the dictionary.
for (int i = 0; i < dm_r.Count; i++)
{
uint len = dm_r[i].len;
int offset = offsetList[i];
string strProp = dm_r[i].strProp;
string strTerm = strLine.Substring(offset, (int)len);
Console.WriteLine("Matched term: {0}[offset:{1}, len:{2}, prop:{3}]", strTerm, offset, len, strProp);
}
}
sr.Close();
}
//Read each line from strTextFileName, and verify wether terms in every line are in strDictFileName
public static void Match(string inputFilePath, string outputFilePath, DictMatch match)
{
List <Lemma> dm_r = new List <Lemma>();
List <int> offsetList = new List <int>();
StreamReader sr = new StreamReader(inputFilePath);
StreamWriter sw = new StreamWriter(outputFilePath);
while (sr.EndOfStream == false)
{
string?line = sr.ReadLine();
if (line == null || line.Length == 0)
{
continue;
}
dm_r.Clear();
offsetList.Clear();
match.Search(line, ref dm_r, ref offsetList, DictMatch.DM_OUT_FMM);
//if dm_r.Count > 0, it means some contigous terms in strLine have matched terms in the dictionary.
StringBuilder sb = new StringBuilder();
int currOffset = 0;
for (int i = 0; i < dm_r.Count; i++)
{
uint len = dm_r[i].len;
int offset = offsetList[i];
string strProp = dm_r[i].strProp;
string strTerm = line.Substring(offset, (int)len);
if (offset > currOffset)
{
sb.Append(line.Substring(currOffset, offset - currOffset));
}
sb.Append($" <{strProp}> {strTerm} </{strProp}> ");
currOffset = (int)(offset + len);
}
if (currOffset < line.Length)
{
sb.Append(line.Substring(currOffset));
}
sw.WriteLine(sb.ToString().Replace(" ", " "));
}
sr.Close();
sw.Close();
}
public List <List <string> > GenerateFeature(string strText)
{
var rstListList = new List <List <string> >();
if (dictmatch == null)
{
return(rstListList);
}
dm_r.Clear();
dm_offsetList.Clear();
dictmatch.Search(strText, ref dm_r, ref dm_offsetList, DictMatch.DM_OUT_FMM);
string [] astrDictMatch;
astrDictMatch = new string[strText.Length];
for (var i = 0; i < dm_r.Count; i++)
{
var offset = dm_offsetList[i];
var len = (int)dm_r[i].len;
for (var j = offset; j < offset + len; j++)
{
astrDictMatch[j] = dm_r[i].strProp;
}
}
for (var i = 0; i < strText.Length; i++)
{
rstListList.Add(new List <string>());
rstListList[i].Add(strText[i].ToString());
if (astrDictMatch[i] != null)
{
rstListList[i].Add(astrDictMatch[i]);
}
else
{
rstListList[i].Add("NOR");
}
}
return(rstListList);
}
