From 0d59859c670b9de37bffa8a6e536497c88d9f25d Mon Sep 17 00:00:00 2001
From: Guolin Ke <guolin.ke@outlook.com>
Date: Fri, 19 Jul 2019 01:16:50 +0800
Subject: [PATCH] throw error when meet non ascii (#2229)

* throw error when meet non ascii

* check ascii for config strings.
---
 include/LightGBM/dataset.h      | 5 +++++
 include/LightGBM/utils/common.h | 9 +++++++++
 src/io/config.cpp               | 3 +++
 3 files changed, 17 insertions(+)

diff --git a/include/LightGBM/dataset.h b/include/LightGBM/dataset.h
index 92cc201cc62..e688522fbb1 100644
--- a/include/LightGBM/dataset.h
+++ b/include/LightGBM/dataset.h
@@ -8,6 +8,7 @@
 #include <LightGBM/config.h>
 #include <LightGBM/feature_group.h>
 #include <LightGBM/meta.h>
+#include <LightGBM/utils/common.h>
 #include <LightGBM/utils/openmp_wrapper.h>
 #include <LightGBM/utils/random.h>
 #include <LightGBM/utils/text_reader.h>
@@ -555,6 +556,10 @@ class Dataset {
     // replace ' ' in feature_names with '_'
     bool spaceInFeatureName = false;
     for (auto& feature_name : feature_names_) {
+      // check ascii
+      if (!Common::CheckASCII(feature_name)) {
+        Log::Fatal("Do not support non-ascii characters in feature name.");
+      }
       if (feature_name.find(' ') != std::string::npos) {
         spaceInFeatureName = true;
         std::replace(feature_name.begin(), feature_name.end(), ' ', '_');
diff --git a/include/LightGBM/utils/common.h b/include/LightGBM/utils/common.h
index f42aa8295e3..8ad82245411 100644
--- a/include/LightGBM/utils/common.h
+++ b/include/LightGBM/utils/common.h
@@ -895,6 +895,15 @@ static T SafeLog(T x) {
   }
 }
 
+inline bool CheckASCII(const std::string& s) {
+  for (auto c : s) {
+    if (static_cast<unsigned char>(c) > 127) {
+      return false;
+    }
+  }
+  return true;
+}
+
 }  // namespace Common
 
 }  // namespace LightGBM
diff --git a/src/io/config.cpp b/src/io/config.cpp
index d0924ac0576..446b4971d92 100644
--- a/src/io/config.cpp
+++ b/src/io/config.cpp
@@ -17,6 +17,9 @@ void Config::KV2Map(std::unordered_map<std::string, std::string>& params, const
   if (tmp_strs.size() == 2) {
     std::string key = Common::RemoveQuotationSymbol(Common::Trim(tmp_strs[0]));
     std::string value = Common::RemoveQuotationSymbol(Common::Trim(tmp_strs[1]));
+    if (!Common::CheckASCII(key) || !Common::CheckASCII(value)) {
+      Log::Fatal("Do not support non-ascii characters in config.");
+    }
     if (key.size() > 0) {
       auto value_search = params.find(key);
       if (value_search == params.end()) {  // not set