Merge pull request #183 from pepkit/dev

v0.9.1 release

docs/changelog.md

@@ -2,6 +2,12 @@
 
 This project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html) and [Keep a Changelog](https://keepachangelog.com/en/1.0.0/) format.
 
+## [0.9.1] - 2024-04-24
+### Fixed
+- Pipestat summarize html report columns now show stats only  [#148](https://github.com/pepkit/pipestat/issues/148).
+- When creating HTML reports from both sample and project level results (multi results), only sample-level results show in the main index table [#150](https://github.com/pepkit/pipestat/issues/150). 
+- Add more complex schema during dependency check to mitigate false test failures regarding different output schemas [#181](https://github.com/pepkit/pipestat/issues/181). 
+
 ## [0.9.0] - 2024-04-19
 ### Fixed
 - Bug with rm_record for filebackend

pipestat/_version.py

@@ -1 +1 @@
-__version__ = "0.9.0"
+__version__ = "0.9.1"

pipestat/exceptions.py

@@ -19,6 +19,7 @@
     "InvalidTimeFormatError",
     "PipestatDependencyError",
     "ColumnNotFoundError",
+    "SchemaValidationErrorDuringReport",
 ]
 
 

pipestat/jinja_templates/index.html

@@ -199,7 +199,7 @@
 	<!--		};-->
 
 	<!--		})(jQuery);-->
-	</script>
+<!--	</script>-->
 	<script>
 		$.noConflict();
 		jQuery(function ($) {

pipestat/reports.py

@@ -704,7 +704,7 @@ def create_index_html(self, navbar, footer):
             all_result_identifiers = input_sample_attributes + all_result_identifiers
 
         if self.prj.cfg["multi_result_files"] is True:
-            pipeline_types = ["sample", "project"]
+            pipeline_types = ["sample"]
         else:
             pipeline_types = [self.prj.backend.pipeline_type]
 
@@ -731,6 +731,15 @@ def create_index_html(self, navbar, footer):
                     if key not in sample_stat_results.keys():
                         sample_stat_results[key] = ""
 
+                for key in self.schema.keys():
+                    if "type" in self.schema[key]:
+                        if (
+                            self.schema[key]["type"] == "file"
+                            or self.schema[key]["type"] == "image"
+                            or self.schema[key]["type"] == "object"
+                        ):
+                            del sample_stat_results[key]
+
                 # Sort to ensure alignment in the table
                 sorted_sample_stat_results = dict(sorted(sample_stat_results.items()))
 
@@ -780,13 +789,14 @@ def create_index_html(self, navbar, footer):
         )
 
         project_objects = self.create_project_objects()
-        columns = ["Record Identifiers"] + list(sorted_sample_stat_results.keys())
+        columns_table = ["Record Identifiers"] + list(sorted_sample_stat_results.keys())
+        columns_stats = list(sorted_sample_stat_results.keys())
         template_vars = dict(
             navbar=navbar,
             stats_file_path=stats_file_path,
             objs_file_path=objs_file_path,
-            columns=columns,
-            columns_json=dumps(columns),
+            columns=columns_table,
+            columns_json=dumps(columns_stats),
             table_row_data=table_row_data,
             project_name=self.prj.cfg[PROJECT_NAME],
             pipeline_name=self.pipeline_name,
@@ -938,7 +948,7 @@ def get_nonhighlighted_results(self, types):
     def _stats_to_json_str(self):
         results = {}
         if self.prj.cfg["multi_result_files"] is True:
-            pipeline_types = ["sample", "project"]
+            pipeline_types = ["sample"]
         else:
             pipeline_types = [self.prj.backend.pipeline_type]
 

tests/conftest.py

@@ -44,7 +44,6 @@
     )
     DB_DEPENDENCIES = False
 
-
 # SERVICE_UNAVAILABLE = False
 # DB_DEPENDENCIES = True
 

tests/data/config.yaml

@@ -1,6 +1,6 @@
 project_name: test
 record_identifier: sample1
-schema_path: sample_output_schema.yaml
+schema_path: sample_output_schema_recursive.yaml
 database:
   dialect: postgresql
   driver: psycopg

tests/test_pipestat.py

@@ -355,6 +355,38 @@ def test_complex_object_report(
                 ]
             )
 
+    @pytest.mark.parametrize(
+        "val",
+        [
+            {"output_file": {"path": "path_string", "title": "title_string"}},
+            {
+                "output_image": {
+                    "path": "path_string",
+                    "thumbnail_path": "thumbnail_path_string",
+                    "title": "title_string",
+                }
+            },
+        ],
+    )
+    @pytest.mark.parametrize("backend", ["db"])
+    def test_complex_object_report_missing_fields(
+        self, val, config_file_path, recursive_schema_file_path, results_file_path, backend
+    ):
+        with NamedTemporaryFile() as f, ContextManagerDBTesting(DB_URL):
+            results_file_path = f.name
+            args = dict(schema_path=recursive_schema_file_path, database_only=False)
+            backend_data = (
+                {"config_file": config_file_path}
+                if backend == "db"
+                else {"results_file_path": results_file_path}
+            )
+            args.update(backend_data)
+
+            psm = SamplePipestatManager(**args)
+            del val[list(val.keys())[0]]["path"]
+            with pytest.raises(SchemaValidationErrorDuringReport):
+                psm.report(record_identifier=REC_ID, values=val, force_overwrite=True)
+
     @pytest.mark.parametrize(
         ["rec_id", "val"],
         [