fix the split functions.

include/LightGBM/utils/common.h

@@ -44,6 +44,7 @@ inline static std::string& RemoveQuotationSymbol(std::string& str) {
   str.erase(0, str.find_first_not_of("'\""));
   return str;
 }
+
 inline static bool StartsWith(const std::string& str, const std::string prefix) {
   if (str.substr(0, prefix.size()) == prefix) {
     return true;
@@ -51,32 +52,79 @@ inline static bool StartsWith(const std::string& str, const std::string prefix)
     return false;
   }
 }
+
 inline static std::vector<std::string> Split(const char* c_str, char delimiter) {
   std::vector<std::string> ret;
   std::string str(c_str);
   size_t i = 0;
-  size_t pos = str.find(delimiter);
-  while (pos != std::string::npos) {
-    ret.push_back(str.substr(i, pos - i));
-    i = ++pos;
-    pos = str.find(delimiter, pos);
+  size_t pos = 0;
+  while (pos < str.length()) {
+    if (str[pos] == delimiter) {
+      if (i < pos) {
+        ret.push_back(str.substr(i, pos - i));
+      }
+      ++pos;
+      i = pos;
+    } else {
+      ++pos;
+    }
+  }
+  if (i < pos) {
+    ret.push_back(str.substr(i));
+  }
+  return ret;
+}
+
+inline static std::vector<std::string> SplitLines(const char* c_str) {
+  std::vector<std::string> ret;
+  std::string str(c_str);
+  size_t i = 0;
+  size_t pos = 0;
+  while (pos < str.length()) {
+    if (str[pos] == '\n' || str[pos] == '\r') {
+      if (i < pos) {
+        ret.push_back(str.substr(i, pos - i));
+      }
+      // skip the line endings
+      while (str[pos] == '\n' || str[pos] == '\r') ++pos;
+      // new begin
+      i = pos;
+    } else {
+      ++pos;
+    }
+  }
+  if (i < pos) {
+    ret.push_back(str.substr(i));
   }
-  ret.push_back(str.substr(i));
   return ret;
 }
 
 inline static std::vector<std::string> Split(const char* c_str, const char* delimiters) {
-  // will split when met any chars in delimiters
   std::vector<std::string> ret;
   std::string str(c_str);
   size_t i = 0;
-  size_t pos = str.find_first_of(delimiters);
-  while (pos != std::string::npos) {
-    ret.push_back(str.substr(i, pos - i));
-    i = ++pos;
-    pos = str.find_first_of(delimiters, pos);
+  size_t pos = 0;
+  while (pos < str.length()) {
+    bool met_delimiters = false;
+    for (int j = 0; delimiters[j] != '\0'; ++j) {
+      if (str[pos] == delimiters[j]) {
+        met_delimiters = true;
+        break;
+      }
+    }
+    if (met_delimiters) {
+      if (i < pos) {
+        ret.push_back(str.substr(i, pos - i));
+      }
+      ++pos;
+      i = pos;
+    } else {
+      ++pos;
+    }
+  }
+  if (i < pos) {
+    ret.push_back(str.substr(i));
   }
-  ret.push_back(str.substr(i));
   return ret;
 }
 

src/boosting/gbdt.cpp

@@ -875,7 +875,7 @@ bool GBDT::SaveModelToFile(int num_iteration, const char* filename) const {
 bool GBDT::LoadModelFromString(const std::string& model_str) {
   // use serialized string to restore this object
   models_.clear();
-  std::vector<std::string> lines = Common::Split(model_str.c_str(), '\n');
+  std::vector<std::string> lines = Common::SplitLines(model_str.c_str());
 
   // get number of classes
   auto line = Common::FindFromLines(lines, "num_class=");
@@ -917,7 +917,7 @@ bool GBDT::LoadModelFromString(const std::string& model_str) {
   // get feature names
   line = Common::FindFromLines(lines, "feature_names=");
   if (line.size() > 0) {
-    feature_names_ = Common::Split(line.substr(std::strlen("feature_names=")).c_str(), " ");
+    feature_names_ = Common::Split(line.substr(std::strlen("feature_names=")).c_str(), ' ');
     if (feature_names_.size() != static_cast<size_t>(max_feature_idx_ + 1)) {
       Log::Fatal("Wrong size of feature_names");
       return false;
@@ -929,7 +929,7 @@ bool GBDT::LoadModelFromString(const std::string& model_str) {
 
   line = Common::FindFromLines(lines, "feature_infos=");
   if (line.size() > 0) {
-    feature_infos_ = Common::Split(line.substr(std::strlen("feature_infos=")).c_str(), " ");
+    feature_infos_ = Common::Split(line.substr(std::strlen("feature_infos=")).c_str(), ' ');
     if (feature_infos_.size() != static_cast<size_t>(max_feature_idx_ + 1)) {
       Log::Fatal("Wrong size of feature_infos");
       return false;

src/io/tree.cpp

@@ -441,7 +441,7 @@ std::string Tree::NodeToIfElse(int index, bool is_predict_leaf_index) {
 }
 
 Tree::Tree(const std::string& str) {
-  std::vector<std::string> lines = Common::Split(str.c_str(), '\n');
+  std::vector<std::string> lines = Common::SplitLines(str.c_str());
   std::unordered_map<std::string, std::string> key_vals;
   for (const std::string& line : lines) {
     std::vector<std::string> tmp_strs = Common::Split(line.c_str(), '=');

src/lightgbm_R.cpp

@@ -135,7 +135,7 @@ LGBM_SE LGBM_DatasetSetFeatureNames_R(LGBM_SE handle,
   LGBM_SE feature_names,
   LGBM_SE call_state) {
   R_API_BEGIN();
-  auto vec_names = Common::Split(R_CHAR_PTR(feature_names), "\t");
+  auto vec_names = Common::Split(R_CHAR_PTR(feature_names), '\t');
   std::vector<const char*> vec_sptr;
   int len = static_cast<int>(vec_names.size());
   for (int i = 0; i < len; ++i) {

src/objective/binary_objective.hpp

@@ -28,7 +28,7 @@ public:
   explicit BinaryLogloss(const std::vector<std::string>& strs) {
     sigmoid_ = -1;
     for (auto str : strs) {
-      auto tokens = Common::Split(str.c_str(), ":");
+      auto tokens = Common::Split(str.c_str(), ':');
       if (tokens.size() == 2) {
         if (tokens[0] == std::string("sigmoid")) {
           Common::Atof(tokens[1].c_str(), &sigmoid_);

src/objective/multiclass_objective.hpp

@@ -22,7 +22,7 @@ public:
   explicit MulticlassSoftmax(const std::vector<std::string>& strs) {
     num_class_ = -1;
     for (auto str : strs) {
-      auto tokens = Common::Split(str.c_str(), ":");
+      auto tokens = Common::Split(str.c_str(), ':');
       if (tokens.size() == 2) {
         if (tokens[0] == std::string("num_class")) {
           Common::Atoi(tokens[1].c_str(), &num_class_);
@@ -151,7 +151,7 @@ public:
     num_class_ = -1;
     sigmoid_ = -1;
     for (auto str : strs) {
-      auto tokens = Common::Split(str.c_str(), ":");
+      auto tokens = Common::Split(str.c_str(), ':');
       if (tokens.size() == 2) {
         if (tokens[0] == std::string("num_class")) {
           Common::Atoi(tokens[1].c_str(), &num_class_);

src/objective/objective_function.cpp

@@ -31,7 +31,7 @@ ObjectiveFunction* ObjectiveFunction::CreateObjectiveFunction(const std::string&
 }
 
 ObjectiveFunction* ObjectiveFunction::CreateObjectiveFunction(const std::string& str) {
-  auto strs = Common::Split(str.c_str(), " ");
+  auto strs = Common::Split(str.c_str(), ' ');
   auto type = strs[0];
   if (type == std::string("regression")) {
     return new RegressionL2loss(strs);