Teknium
1cefabc8af
A regex \n (or a raw newline) in a search_files content pattern cannot
match in rg's default line-oriented mode. It previously either
hard-errored ('the literal "\n" is not allowed in a regex' — 17
occurrences in the production window) or, after the newline-warning
patch, returned 0 matches with an explanation — either way the model's
cross-line search intent required a manual workaround.
The rg engine now detects the pattern shape (_pattern_has_regex_newline,
already used by the warning path: odd-backslash \n escape or raw
newline; escaped \\n literals excluded) and enables -U/--multiline up
front, noting the mode switch in the result warning. Plain patterns are
untouched; the old line-oriented explanation is retained for the grep
fallback engine, which has no multiline mode.
52 lines
1.9 KiB
Python
52 lines
1.9 KiB
Python
"""Tests for search_files auto-multiline routing on \\n patterns."""
|
|
|
|
import json
|
|
|
|
import pytest
|
|
|
|
from tools.file_tools import search_tool
|
|
|
|
|
|
@pytest.fixture
|
|
def proj(tmp_path, monkeypatch):
|
|
monkeypatch.setenv("HERMES_HOME", str(tmp_path / ".hermes"))
|
|
d = tmp_path / "proj"
|
|
d.mkdir()
|
|
(d / "mod.py").write_text(
|
|
"def setup():\n init_db()\n return True\n\n"
|
|
"def teardown():\n close_db()\n"
|
|
)
|
|
return d
|
|
|
|
|
|
class TestAutoMultiline:
|
|
def test_newline_regex_matches_across_lines(self, proj):
|
|
r = json.loads(search_tool(r"def setup\(\):\n init_db\(\)", path=str(proj), task_id="t-ml"))
|
|
assert "error" not in r
|
|
assert r["total_count"] >= 1
|
|
assert "multiline" in r.get("warning", "")
|
|
|
|
def test_literal_newline_in_pattern_matches(self, proj):
|
|
# A raw newline in the pattern (not the \n escape) also routes to
|
|
# multiline mode. Keep the pattern free of regex metachars.
|
|
r = json.loads(search_tool("return True\n\ndef teardown", path=str(proj), task_id="t-ml"))
|
|
assert "error" not in r
|
|
assert r["total_count"] >= 1
|
|
|
|
def test_plain_pattern_unaffected(self, proj):
|
|
r = json.loads(search_tool("init_db", path=str(proj), task_id="t-ml"))
|
|
assert r["total_count"] == 1
|
|
assert "multiline" not in r.get("warning", "")
|
|
|
|
def test_escaped_backslash_n_stays_literal(self, proj):
|
|
# \\n = literal backslash+n search, not a newline: no multiline mode.
|
|
(proj / "strings.py").write_text('SEP = "a\\\\nb"\n')
|
|
r = json.loads(search_tool(r"a\\nb", path=str(proj), task_id="t-ml"))
|
|
assert "error" not in r
|
|
assert "multiline" not in (r.get("warning") or "")
|
|
|
|
def test_multiline_zero_match_is_clean(self, proj):
|
|
r = json.loads(search_tool(r"def missing\(\):\n nope\(\)", path=str(proj), task_id="t-ml"))
|
|
assert "error" not in r
|
|
assert r["total_count"] == 0
|