Support Qwen/QwQ-32B (needed str.{split,lstrip}) (#56)

* Add str.split(sep), .strip([chars]), .rstrip([chars]), .lstrip([chars])

* test Qwen/QwQ-32B template

Author: ochafik

include/minja/minja.hpp

@@ -1379,13 +1379,27 @@ struct ArgumentsExpression {
     }
 };
 
-static std::string strip(const std::string & s) {
-  auto start = s.find_first_not_of(" \t\n\r");
+static std::string strip(const std::string & s, const std::string & chars = "", bool left = true, bool right = true) {
+  auto charset = chars.empty() ? " \t\n\r" : chars;
+  auto start = left ? s.find_first_not_of(charset) : 0;
   if (start == std::string::npos) return "";
-  auto end = s.find_last_not_of(" \t\n\r");
+  auto end = right ? s.find_last_not_of(charset) : s.size() - 1;
   return s.substr(start, end - start + 1);
 }
 
+static std::vector<std::string> split(const std::string & s, const std::string & sep) {
+  std::vector<std::string> result;
+  size_t start = 0;
+  size_t end = s.find(sep);
+  while (end != std::string::npos) {
+    result.push_back(s.substr(start, end - start));
+    start = end + sep.length();
+    end = s.find(sep, start);
+  }
+  result.push_back(s.substr(start));
+  return result;
+}
+
 static std::string capitalize(const std::string & s) {
   if (s.empty()) return s;
   auto result = s;
@@ -1468,8 +1482,26 @@ class MethodCallExpr : public Expression {
         } else if (obj.is_string()) {
           auto str = obj.get<std::string>();
           if (method->get_name() == "strip") {
-            vargs.expectArgs("strip method", {0, 0}, {0, 0});
-            return Value(strip(str));
+            vargs.expectArgs("strip method", {0, 1}, {0, 0});
+            auto chars = vargs.args.empty() ? "" : vargs.args[0].get<std::string>();
+            return Value(strip(str, chars));
+          } else if (method->get_name() == "lstrip") {
+            vargs.expectArgs("lstrip method", {0, 1}, {0, 0});
+            auto chars = vargs.args.empty() ? "" : vargs.args[0].get<std::string>();
+            return Value(strip(str, chars, /* left= */ true, /* right= */ false));
+          } else if (method->get_name() == "rstrip") {
+            vargs.expectArgs("rstrip method", {0, 1}, {0, 0});
+            auto chars = vargs.args.empty() ? "" : vargs.args[0].get<std::string>();
+            return Value(strip(str, chars, /* left= */ false, /* right= */ true));
+          } else if (method->get_name() == "split") {
+            vargs.expectArgs("split method", {1, 1}, {0, 0});
+            auto sep = vargs.args[0].get<std::string>();
+            auto parts = split(str, sep);
+            Value result = Value::array();
+            for (const auto& part : parts) {
+              result.push_back(Value(part));
+            }
+            return result;
           } else if (method->get_name() == "capitalize") {
             vargs.expectArgs("capitalize method", {0, 0}, {0, 0});
             return Value(capitalize(str));

tests/CMakeLists.txt

@@ -263,6 +263,7 @@ set(MODEL_IDS
     Qwen/Qwen2.5-VL-3B-Instruct
     Qwen/Qwen2.5-VL-72B-Instruct
     Qwen/Qwen2.5-VL-7B-Instruct
+    Qwen/QwQ-32B
     Qwen/QwQ-32B-Preview
     rubenroy/Zurich-14B-GCv2-5m
     rubenroy/Zurich-7B-GCv2-5m

tests/test-syntax.cpp

@@ -74,6 +74,13 @@ TEST(SyntaxTest, SimpleCases) {
         return testing::Throws<std::runtime_error>(Property(&std::runtime_error::what, testing::HasSubstr(expected_substr)));
     };
 
+    EXPECT_EQ("a", render("{{ ' a '.strip() }}", {}, {}));
+    EXPECT_EQ("a ", render("{{ ' a '.lstrip() }}", {}, {}));
+    EXPECT_EQ(" a", render("{{ ' a '.rstrip() }}", {}, {}));
+    EXPECT_EQ("bcXYZab", render("{{ 'abcXYZabc'.strip('ac') }}", {}, {}));
+
+    EXPECT_EQ(R"(["a", "b"])", render("{{ 'a b'.split(' ') | tojson }}", {}, {}));
+
     EXPECT_EQ(
         "Ok",
         render("{{ 'ok'.capitalize() }}", {}, {}));