Universum 0.19.19

.readthedocs.yml

@@ -1,17 +1,23 @@
-# .readthedocs.yml
-# Read the Docs configuration file
+# Read the Docs configuration file for Sphinx projects
 # See https://docs.readthedocs.io/en/stable/config-file/v2.html for details
 
 # Required
 version: 2
 
-# Build documentation in the docs/ directory with Sphinx
+# Set the OS, Python version and other tools you might need
+build:
+  os: ubuntu-22.04
+  tools:
+    python: "3.8"
+
+# Build documentation in the "docs/" directory with Sphinx
 sphinx:
   configuration: doc/conf.py
-
-# Optionally set the version of Python and requirements required to build your docs
+
+# Optional but recommended, declare the Python requirements required
+# to build your documentation
+# See https://docs.readthedocs.io/en/stable/guides/reproducible-builds.html
 python:
-  version: 3.7
   install:
     - method: pip
       path: .

CHANGELOG.rst

@@ -1,6 +1,18 @@
 Change log
 ==========
 
+0.19.19 (2023-11-22)
+--------------------
+
+Bug fixes
+~~~~~~~~~
+
+* **report:** support originalUriBaseIds fields for SARIF
+  (causing malfunction of underline comments to the Swarm)
+* **doc:** update RTD (https://universum.readthedocs.io/en/latest/) config
+  (old config format no longer supported)
+
+
 0.19.18 (2023-11-10)
 --------------------
 

tests/test_code_report.py

@@ -123,6 +123,52 @@ def finalize(self) -> str:
 }
 """
 
+sarif_report_split_uri = """
+{
+  "$schema": "https://raw.githubusercontent.com/oasis-tcs/sarif-spec/master/Schemata/sarif-schema-2.1.0.json",
+  "version": "2.1.0",
+  "runs": [
+    {
+      "tool": {
+        "driver": {
+          "name": "Checkstyle",
+          "semanticVersion": "8.43",
+          "version": "8.43"
+        }
+      },
+      "results": [
+        {
+          "level": "warning",
+          "locations": [
+            {
+              "physicalLocation": {
+                "artifactLocation": {
+                  "uri": "my_file",
+                  "uriBaseId": "ROOTPATH"
+                },
+                "region": {
+                  "startColumn": 1,
+                  "startLine": 1
+                }
+              }
+            }
+          ],
+          "message": {
+            "text": "Error!"
+          },
+          "ruleId": "testRule"
+        }
+      ],
+      "originalUriBaseIds": {
+        "ROOTPATH": {
+          "uri": "my_path"
+        }
+      }
+    }
+  ]
+}
+"""
+
 config_uncrustify = """
 code_width = 120
 input_tab_size = 2
@@ -142,6 +188,7 @@ def finalize(self) -> str:
     [[json_report], False],
     [[sarif_report_minimal], True],
     [[sarif_report], False],
+    [[sarif_report_split_uri], False],
     [[json_report_minimal, sarif_report_minimal], True],
     [[json_report, sarif_report], False],
     [[json_report_minimal, sarif_report], False],
@@ -151,6 +198,7 @@ def finalize(self) -> str:
     'json_issues_found',
     'sarif_no_issues',
     'sarif_issues_found',
+    'sarif_split_uri_issues_found',
     'both_tested_no_issues',
     'both_tested_issues_in_both',
     'both_tested_issues_in_sarif',

universum/__init__.py

@@ -1,2 +1,2 @@
 __title__ = "Universum"
-__version__ = "0.19.18"
+__version__ = "0.19.19"

universum/modules/code_report_collector.py

@@ -3,6 +3,7 @@
 import os
 import urllib.parse
 from copy import deepcopy
+from pathlib import Path
 from typing import Dict, List, Optional, TextIO, Tuple
 
 from . import artifact_collector, reporter
@@ -53,6 +54,35 @@ def _report_as_pylint_json(self, report) -> int:
             self.reporter.code_report(path, message)
         return len(report)
 
+    def _process_one_sarif_issue(self, issue, root_uri_base_paths, who) -> None:
+        what: str = issue.get('message')
+        for location in issue.get('locations', []):
+            location_data: Dict[str, Dict[str, str]] = location.get('physicalLocation')
+            if not location_data:
+                continue
+            artifact_data = location_data.get('artifactLocation')
+            if not artifact_data:
+                if location_data.get('address'):
+                    continue  # binary artifact can't be processed
+                raise ValueError("Unexpected lack of artifactLocation tag")
+            if artifact_data.get('uriBaseId'):
+                uri = artifact_data.get('uri')
+                if not uri:
+                    raise ValueError("Unexpected lack of uri tag")
+                uri_base_id = artifact_data.get('uriBaseId', '')
+                root_base_path = root_uri_base_paths.get(uri_base_id, '')
+                if uri_base_id and not root_base_path:
+                    raise ValueError(f"Unexpected lack of 'originalUriBaseIds' value for {uri_base_id}")
+                path = str(Path(root_base_path, urllib.parse.unquote(uri)))
+            else:
+                path = urllib.parse.unquote(artifact_data.get('uri', ''))
+            region_data = location_data.get('region')
+            if not region_data:
+                continue  # TODO: cover this case as comment to the file as a whole
+            message: reporter.ReportMessage = {"message": f"{who} : {what}",
+                                               "line": int(region_data.get('startLine', '0'))}
+            self.reporter.code_report(path, message)
+
     def _report_as_sarif_json(self, report) -> int:
         version: str = report.get('version', '')
         if version != '2.1.0':
@@ -61,25 +91,11 @@ def _report_as_sarif_json(self, report) -> int:
         for run in report.get('runs', []):
             analyzer_data: Dict[str, str] = run.get('tool').get('driver')  # non-optional per definition
             who: str = f"{analyzer_data.get('name')} [{analyzer_data.get('version', '?')}]"
+            root_uri_base_paths: Dict[str, str] = {uri_base_id: urllib.parse.urlparse(root_path['uri']).path for
+                                                   uri_base_id, root_path in run.get('originalUriBaseIds', {}).items()}
             for issue in run.get('results', []):
                 issue_count += 1
-                what: str = issue.get('message')
-                for location in issue.get('locations', []):
-                    location_data: Dict[str, Dict[str, str]] = location.get('physicalLocation')
-                    if not location_data:
-                        continue
-                    artifact_data = location_data.get('artifactLocation')
-                    if not artifact_data:
-                        if location_data.get('address'):
-                            continue  # binary artifact can't be processed
-                        raise ValueError("Unexpected lack of artifactLocation tag")
-                    path: str = urllib.parse.unquote(artifact_data.get('uri', ''))
-                    region_data = location_data.get('region')
-                    if not region_data:
-                        continue  # TODO: cover this case as comment to the file as a whole
-                    message: reporter.ReportMessage = {"message": f"{who} : {what}",
-                                                       "line": int(region_data.get('startLine', '0'))}
-                    self.reporter.code_report(path, message)
+                self._process_one_sarif_issue(issue, root_uri_base_paths, who)
         return issue_count
 
     @make_block("Processing code report results")