Merge pull request #75 from Pennycook/feature/coverage-format

Finalize coverage schema

Author: Pennycook

MANIFEST.in

@@ -1,5 +1,3 @@
-include p3analysis/data/coverage-0.1.0.schema
-include p3analysis/data/coverage-0.2.0.schema
-include p3analysis/data/coverage-0.3.0.schema
+include p3analysis/data/coverage.schema
 include p3analysis/plot/backend/templates/cascade.tex
 include p3analysis/plot/backend/templates/navchart.tex

case-studies/babelstream/coverage.csv

@@ -75,4 +75,4 @@ The JSON string format follows the schema `here`_, and should be considered
 experimental.
 
 .. _here:
-   https://raw.githubusercontent.com/intel/p3-analysis-library/master/p3/data/coverage-0.1.0.schema
+   https://raw.githubusercontent.com/intel/p3-analysis-library/master/p3/data/coverage.schema

docs/source/data.rst

@@ -34,7 +34,7 @@ def _validate_coverage_json(json_string: str) -> object:
 
     instance = json.loads(json_string)
 
-    schema_string = pkgutil.get_data(__name__, "coverage-0.3.0.schema")
+    schema_string = pkgutil.get_data(__name__, "coverage.schema")
     if not schema_string:
         msg = "Could not locate coverage schema file"
         raise RuntimeError(msg)
@@ -47,7 +47,7 @@ def _validate_coverage_json(json_string: str) -> object:
         msg = "Coverage string failed schema validation"
         raise ValueError(msg)
     except jsonschema.exceptions.SchemaError:
-        msg = "coverage-0.3.0.schema is not a valid schema"
+        msg = "coverage.schema is not a valid schema"
         raise RuntimeError(msg)
 
     return instance

p3analysis/data/_validation.py

@@ -1,6 +1,6 @@
 {
   "$schema": "https://json-schema.org/draft/2020-12/schema",
-  "$id": "https://raw.githubusercontent.com/intel/p3-analysis-library/main/p3/data/coverage-0.2.0.schema",
+  "$id": "https://raw.githubusercontent.com/intel/p3-analysis-library/main/p3/data/coverage.schema",
   "title": "Coverage",
   "description": "Lines of code used in each file of a code base.",
   "type": "array",
@@ -10,31 +10,27 @@
       "file": {
         "type": "string"
       },
-      "path": {
+      "id": {
         "type": "string"
       },
-      "regions": {
+      "used_lines": {
         "type": "array",
         "items": {
-          "type": "array",
-          "prefixItems": [
-            {
-              "type": "integer"
-            },
-            {
-              "type": "integer"
-            },
-            {
-              "type": "integer"
-            }
-          ],
-          "items": false
+            "type": "integer"
+        }
+      },
+      "unused_lines": {
+        "type": "array",
+        "items": {
+            "type": "integer"
         }
       }
     },
     "required": [
       "file",
-      "regions"
+      "id",
+      "used_lines",
+      "unused_lines"
     ]
   }
 }

p3analysis/data/coverage-0.1.0.schema

@@ -56,16 +56,8 @@ def _coverage_to_divergence(maps):
     for p, coverage in enumerate(maps):
         for entry in coverage:
             unique_fn = (entry["file"], entry["id"])
-            for region in entry["lines"]:
-                # If a region is a single integer, it represents one line.
-                if isinstance(region, int):
-                    line = region
-                    linemap[(unique_fn, line)].add(p)
-
-                # If a region is a list, it represents a [start, end] pair.
-                if isinstance(region, list):
-                    for line in range(region[0], region[1]):
-                        linemap[(unique_fn, line)].add(p)
+            for line in entry["used_lines"]:
+                linemap[(unique_fn, line)].add(p)
 
     setmap = collections.defaultdict(int)
     for key, platforms in linemap.items():

p3analysis/data/coverage-0.3.0.schema

@@ -13,19 +13,19 @@ class TestValidation(unittest.TestCase):
 
     def test_coverage_json_valid(self):
         """p3analysis.data.validation.coverage_json_valid"""
-        json_string = '[{"file": "path", "id": "sha", "lines": [1, 2, [3, 5]]}]'
+        json_string = '[{"file": "path", "id": "sha", "used_lines": [1, 2, 3, 5], "unused_lines": []}]'
         result_object = _validate_coverage_json(json_string)
-        expected_object = [{"file": "path", "id": "sha", "lines": [1, 2, [3, 5]]}]
+        expected_object = [{"file": "path", "id": "sha", "used_lines": [1, 2, 3, 5], "unused_lines": []}]
         self.assertTrue(result_object == expected_object)
 
     def test_coverage_json_invalid(self):
         """p3analysis.data.validation.coverage_json_invalid"""
-        json_string = '[{"file": "path", "id": "sha", "lines": [["1"]]}]'
+        json_string = '[{"file": "path", "id": "sha", "used_lines": [["1"]], "unused_lines": []}]'
         with self.assertRaises(ValueError):
             _validate_coverage_json(json_string)
 
         with self.assertRaises(TypeError):
-            json_object = [{"file": "path", "id": "sha", "lines": [["1"]]}]
+            json_object = [{"file": "path", "id": "sha", "used_lines": [["1"]], "unused_lines": []}]
             _validate_coverage_json(json_object)
 
 

p3analysis/data/coverage-0.2.0.schema renamed to p3analysis/data/coverage.schema

@@ -37,7 +37,8 @@ def test_side_effects(self):
                 {
                     "file": "file.cpp",
                     "id": "0",
-                    "lines": [0],
+                    "used_lines": [0],
+                    "unused_lines": [],
                 },
             ],
         )
@@ -69,7 +70,8 @@ def test_divergence(self):
                 {
                     "file": "foo.cpp",
                     "id": "0",
-                    "lines": [[0, 9]],
+                    "used_lines": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
+                    "unused_lines": [],
                 },
             ],
         )
@@ -79,12 +81,14 @@ def test_divergence(self):
                 {
                     "file": "foo.cpp",
                     "id": "0",
-                    "lines": [[0, 9]],
+                    "used_lines": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
+                    "unused_lines": [],
                 },
                 {
                     "file": "bar.cpp",
                     "id": "1",
-                    "lines": [[0, 9]],
+                    "used_lines": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
+                    "unused_lines": [],
                 },
             ],
         )
@@ -123,7 +127,8 @@ def test_divergence_single(self):
                 {
                     "file": "file.cpp",
                     "id": "0",
-                    "lines": [0],
+                    "used_lines": [0],
+                    "unused_lines": [],
                 },
             ],
         )
@@ -156,7 +161,8 @@ def test_divergence_duplicate(self):
                 {
                     "file": "foo.cpp",
                     "id": "0",
-                    "lines": [[0, 9]],
+                    "used_lines": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
+                    "unused_lines": [],
                 },
             ],
         )
@@ -168,7 +174,8 @@ def test_divergence_duplicate(self):
                 {
                     "file": "foo.cpp",
                     "id": "1",
-                    "lines": [[0, 9]],
+                    "used_lines": [0, 1, 2, 3, 4, 5, 6, 7, 8, 9],
+                    "unused_lines": [],
                 },
             ],
         )