From 46f6b6cdf15c67aedf0c871d201b8db320bccbdf Mon Sep 17 00:00:00 2001
From: Deepak Mallubhotla <dmallubhotla+github@gmail.com>
Date: Wed, 26 Feb 2025 21:01:19 -0600
Subject: [PATCH] feat: Adds ability to parse bayesruns without timestamps

---
 deepdog/results/__init__.py          | 27 ++++++++++++++++++++-------
 tests/results/test_parse_filename.py | 19 +++++++++++++++++++
 2 files changed, 39 insertions(+), 7 deletions(-)
 create mode 100644 tests/results/test_parse_filename.py

diff --git a/deepdog/results/__init__.py b/deepdog/results/__init__.py
index a931aca..e697085 100644
--- a/deepdog/results/__init__.py
+++ b/deepdog/results/__init__.py
@@ -19,6 +19,11 @@ FILENAME_REGEX = re.compile(
 	r"(?P<timestamp>\d{8}-\d{6})-(?P<filename_slug>.*)\.realdata\.fast_filter\.bayesrun\.csv"
 )
 
+# probably a better way but who cares
+NO_TIMESTAMP_FILENAME_REGEX = re.compile(
+	r"(?P<filename_slug>.*)\.realdata\.fast_filter\.bayesrun\.csv"
+)
+
 
 SUBSET_SIM_FILENAME_REGEX = re.compile(
 	r"(?P<filename_slug>.*)-(?:no_adaptive_steps_)?(?P<num_ss_runs>\d+)-nc_(?P<n_c>\d+)-ns_(?P<n_s>\d+)-mmax_(?P<mmax>\d+)\.multi\.subsetsim\.csv"
@@ -46,15 +51,23 @@ class GeneralOutput:
 	results: typing.Sequence[GeneralModelResult]
 
 
+def _parse_string_output_filename(
+	filename: str,
+) -> typing.Tuple[typing.Optional[str], str]:
+	if match := FILENAME_REGEX.match(filename):
+		groups = match.groupdict()
+		return (groups["timestamp"], groups["filename_slug"])
+	elif match := NO_TIMESTAMP_FILENAME_REGEX.match(filename):
+		groups = match.groupdict()
+		return (None, groups["filename_slug"])
+	else:
+		raise ValueError(f"Could not parse {filename} as a bayesrun output filename")
+
+
 def _parse_output_filename(file: pathlib.Path) -> BayesrunOutputFilename:
 	filename = file.name
-	match = FILENAME_REGEX.match(filename)
-	if not match:
-		raise ValueError(f"{filename} was not a valid bayesrun output")
-	groups = match.groupdict()
-	return BayesrunOutputFilename(
-		timestamp=groups["timestamp"], filename_slug=groups["filename_slug"], path=file
-	)
+	timestamp, slug = _parse_string_output_filename(filename)
+	return BayesrunOutputFilename(timestamp=timestamp, filename_slug=slug, path=file)
 
 
 def _parse_ss_output_filename(file: pathlib.Path) -> BayesrunOutputFilename:
diff --git a/tests/results/test_parse_filename.py b/tests/results/test_parse_filename.py
new file mode 100644
index 0000000..04c0c52
--- /dev/null
+++ b/tests/results/test_parse_filename.py
@@ -0,0 +1,19 @@
+import deepdog.results
+import pytest
+
+
+def test_parse_bayesrun_filename():
+	valid1 = "20250226-204120-dot1-dot1-2-0.realdata.fast_filter.bayesrun.csv"
+
+	timestamp, slug = deepdog.results._parse_string_output_filename(valid1)
+	assert timestamp == "20250226-204120"
+	assert slug == "dot1-dot1-2-0"
+
+	valid2 = "dot1-dot1-2-0.realdata.fast_filter.bayesrun.csv"
+
+	timestamp, slug = deepdog.results._parse_string_output_filename(valid2)
+	assert timestamp is None
+	assert slug == "dot1-dot1-2-0"
+
+	with pytest.raises(ValueError):
+		deepdog.results._parse_string_output_filename("not_a_valid_filename")