Skip to content

support rsplit #24

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
f291400 wants to merge 3 commits into
base: main
Choose a base branch
from
Open

support rsplit #24

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
9ec978a
support rsplit
f291400 Dec 29, 2025
2ba6b8c
del test files
f291400 Dec 30, 2025
4503608
update
f291400 Dec 31, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
39 changes: 34 additions & 5 deletions include/minja/minja.hpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1446,24 +1446,42 @@ struct ArgumentsExpression {
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 "";
if (start == std::string::npos) return "";
Copy link
Copy Markdown
Collaborator

@CISC CISC Jan 10, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
if (start == std::string::npos) return "";
if (start == std::string::npos) return "";

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) {
static std::vector<std::string> split(const std::string & s, const std::string & sep, int maxsplit = -1) {
std::vector<std::string> result;
size_t start = 0;
size_t end = s.find(sep);
while (end != std::string::npos) {
int splits = 0;
while (end != std::string::npos && (maxsplit < 0 || splits < maxsplit)) {
result.push_back(s.substr(start, end - start));
start = end + sep.length();
end = s.find(sep, start);
splits++;
Comment on lines +1458 to +1463
Copy link
Copy Markdown
Collaborator

@CISC CISC Jan 10, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
int splits = 0;
while (end != std::string::npos && (maxsplit < 0 || splits < maxsplit)) {
result.push_back(s.substr(start, end - start));
start = end + sep.length();
end = s.find(sep, start);
splits++;
while (end != std::string::npos && maxsplit != 0) {
result.push_back(s.substr(start, end - start));
start = end + sep.length();
end = s.find(sep, start);
--maxsplit;

}
result.push_back(s.substr(start));
return result;
}

static std::vector<std::string> rsplit(const std::string & s, const std::string & sep, int maxsplit = -1) {
std::vector<std::string> result;
size_t end = s.length();
size_t pos = s.rfind(sep);
int splits = 0;
while (pos != std::string::npos && (maxsplit < 0 || splits < maxsplit)) {
result.insert(result.begin(), s.substr(pos + sep.length(), end - pos - sep.length()));
end = pos;
splits++;
if (pos == 0) break;
pos = s.rfind(sep, pos - 1);
}
result.insert(result.begin(), s.substr(0, end));
Comment on lines +1473 to +1481
Copy link
Copy Markdown
Collaborator

@CISC CISC Jan 10, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
int splits = 0;
while (pos != std::string::npos && (maxsplit < 0 || splits < maxsplit)) {
result.insert(result.begin(), s.substr(pos + sep.length(), end - pos - sep.length()));
end = pos;
splits++;
if (pos == 0) break;
pos = s.rfind(sep, pos - 1);
}
result.insert(result.begin(), s.substr(0, end));
while (pos != std::string::npos && maxsplit != 0) {
result.push_back(s.substr(pos + sep.length(), end - pos - sep.length()));
end = pos;
--maxsplit;
if (pos == 0) break;
pos = s.rfind(sep, pos - 1);
}
result.push_back(s.substr(0, end));
std::reverse(result.begin(), result.end());

return result;
}

static std::string capitalize(const std::string & s) {
if (s.empty()) return s;
auto result = s;
Expand Down Expand Up @@ -1566,9 +1584,20 @@ class MethodCallExpr : public Expression {
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});
vargs.expectArgs("split method", {1, 2}, {0, 0});
auto sep = vargs.args[0].get<std::string>();
int maxsplit = vargs.args.size() > 1 ? vargs.args[1].to_int() : -1;
auto parts = split(str, sep, maxsplit);
Value result = Value::array();
for (const auto& part : parts) {
result.push_back(Value(part));
}
return result;
} else if (method->get_name() == "rsplit") {
vargs.expectArgs("rsplit method", {1, 2}, {0, 0});
auto sep = vargs.args[0].get<std::string>();
auto parts = split(str, sep);
int maxsplit = vargs.args.size() > 1 ? vargs.args[1].to_int() : -1;
auto parts = rsplit(str, sep, maxsplit);
Value result = Value::array();
for (const auto& part : parts) {
result.push_back(Value(part));
Expand Down
12 changes: 12 additions & 0 deletions tests/test-syntax.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -79,6 +79,18 @@ TEST(SyntaxTest, SimpleCases) {
EXPECT_EQ("bcXYZab", render("{{ 'abcXYZabc'.strip('ac') }}", {}, {}));

EXPECT_EQ(R"(["a", "b"])", render("{{ 'a b'.split(' ') | tojson }}", {}, {}));

// Test rsplit (reverse split) with maxsplit parameter
// rsplit splits from right to left, which is crucial for extracting content after the last delimiter
// Used in chat templates like DeepSeek-R1: content.rsplit('</think>', 1)[-1]
EXPECT_EQ(R"(["a-b", "c"])", render("{{ 'a-b-c'.rsplit('-', 1) | tojson }}", {}, {}));
EXPECT_EQ(R"(["a", "b-c"])", render("{{ 'a-b-c'.split('-', 1) | tojson }}", {}, {}));
EXPECT_EQ(R"(["prefix</think>middle", "suffix"])", render("{{ 'prefix</think>middle</think>suffix'.rsplit('</think>', 1) | tojson }}", {}, {}));

// Test rsplit with indexing - extract content after the last delimiter
EXPECT_EQ(" suffix", render("{{ 'prefix</think>middle</think> suffix'.rsplit('</think>', 1)[-1] }}", {}, {}));
EXPECT_EQ(R"(["a", "b", "c"])", render("{{ 'a-b-c'.rsplit('-') | tojson }}", {}, {}));


EXPECT_EQ(
"Ok",
Expand Down