commit 082a7299dc6194fe8291f37c6c12e962167d3f5b
Author: vivekvardhanadepu <vivekvicky839@gmail.com>
Date:   Sat Jul 31 20:31:23 2021 +0530

    removing additional ^ and $

diff --git a/src/tagger_output_processor.cc b/src/tagger_output_processor.cc
index 859aae3..e9e65a4 100644
--- a/src/tagger_output_processor.cc
+++ b/src/tagger_output_processor.cc
@@ -2,53 +2,71 @@
 #include <lttoolbox/string_utils.h>
 #include <lttoolbox/input_file.h>
 
-int TaggerOutputProcessor::find(vector<UString> xs, UString x) {
-	for (size_t i = 0; i < xs.size(); ++i) {
+int TaggerOutputProcessor::find(vector<UString> xs, UString x)
+{
+	for (size_t i = 0; i < xs.size(); ++i)
+	{
 		if (xs[i] == x)
 			return i;
 	}
 	return -1;
 }
 
-TaggerToken TaggerOutputProcessor::parseTaggerToken(UString str) {
+TaggerToken TaggerOutputProcessor::parseTaggerToken(UString str)
+{
 	TaggerToken token;
 	int state = 0; // lemma;
 	UString buffer;
-	for (auto& c : str) {
-		if(c == '<' && state == 0) {
+	for (auto &c : str)
+	{
+		if (c == '<' && state == 0)
+		{
 			state = 1;
 			token.lemma = buffer;
 			buffer.clear();
 		}
 
-		if (c == '>') {
+		if (c == '>')
+		{
 			token.tags.push_back(buffer);
 			buffer.clear();
-		} else if (c != '<') {
+		}
+		else if (c != '<')
+		{
 			buffer += c;
 		}
 	}
-	if(state == 0) {
+	if (state == 0)
+	{
 		token.lemma = buffer;
 	}
 	return token;
 }
 
-vector<UString> TaggerOutputProcessor::parseTags(UString token) {
+vector<UString> TaggerOutputProcessor::parseTags(UString token)
+{
 	int state = 0; // outside
 	vector<UString> tags;
 	UString buffer;
-	for (auto& c : token) {
-		if (state == 0) {
-			if (c == '<') {
+	for (auto &c : token)
+	{
+		if (state == 0)
+		{
+			if (c == '<')
+			{
 				state = 1;
 			}
-		} else if (state == 1) {
-			if (c == '>') {
+		}
+		else if (state == 1)
+		{
+			if (c == '>')
+			{
 				tags.push_back(buffer);
 				buffer.clear();
 				state = 0;
-			} else {
+			}
+			else
+			{
 				buffer += c;
 			}
 		}
@@ -56,50 +74,69 @@ vector<UString> TaggerOutputProcessor::parseTags(UString token) {
 	return tags;
 }
 
-vector<UString> TaggerOutputProcessor::wsplit(UString wstr, UChar delim) {
+vector<UString> TaggerOutputProcessor::wsplit(UString wstr, UChar delim)
+{
 	vector<UString> tokens;
 	UString buffer;
 
-	for(size_t i = 0; i < wstr.size(); ++i) {
-		if(wstr[i] == delim && (i == 0 || wstr[i-1] != '\\')) {
+	for (size_t i = 0; i < wstr.size(); ++i)
+	{
+		if (wstr[i] == delim && (i == 0 || wstr[i - 1] != '\\'))
+		{
 			tokens.push_back(buffer);
 			buffer.clear();
-		} else {
+		}
+		else
+		{
 			buffer += wstr[i];
 		}
 	}
-	if(!buffer.empty()) {
+	if (!buffer.empty())
+	{
 		tokens.push_back(buffer);
 	}
 	return tokens;
 }
 
-UString TaggerOutputProcessor::getLemma(UString token) {
+UString TaggerOutputProcessor::getLemma(UString token)
+{
 	UString buffer;
-	for (auto& c : token) {
-		if(c != '<') {
+	for (auto &c : token)
+	{
+		if (c != '<')
+		{
 			buffer += c;
-		} else {
+		}
+		else
+		{
 			break;
 		}
 	}
 	return buffer;
 }
 
-void TaggerOutputProcessor::processTaggerOutput(bool nullFlush) {
+void TaggerOutputProcessor::processTaggerOutput(bool nullFlush)
+{
 	vector<TaggerToken> sentence;
 	UChar32 c;
-  InputFile in;
-	while (!in.eof()) {
-    c = in.get();
+	InputFile in;
+	while (!in.eof())
+	{
+		c = in.get();
 
-		if ((c == '\n') || (nullFlush && c == '\0')) {
-		  processSentence(sentence);
-		  sentence.clear();
-		} else if (c == '\\') {
-      in.get();
-    } else if (c == '^') {
-      sentence.push_back(parseTaggerToken(in.readBlock('^', '$')));
+		if ((c == '\n') || (nullFlush && c == '\0'))
+		{
+			processSentence(sentence);
+			sentence.clear();
+		}
+		else if (c == '\\')
+		{
+			in.get();
+		}
+		else if (c == '^')
+		{
+			UString temp = in.readBlock('^', '$');
+			sentence.push_back(parseTaggerToken(temp.substr(1, temp.size() - 2)));
 		}
 	}
 }