Remove profiling code, and fix linter errors and tests

web/server/codechecker_server/api/mass_store_run.py

@@ -42,7 +42,7 @@
 from ..metadata import checker_is_unavailable, MetadataInfoParser
 
 from .report_server import ThriftRequestHandler
-from .thrift_enum_helper import report_extended_data_type_str, review_status_enum
+from .thrift_enum_helper import report_extended_data_type_str
 
 
 LOG = get_logger('server')
@@ -725,7 +725,7 @@ def __add_report(
         """ Add report to the database. """
         try:
             checker_name = report.checker_name
-            
+
             # Cache the severity of the checkers
             try:
                 severity = self.__severity_map[checker_name]
@@ -815,7 +815,8 @@ def __process_report_file(
         if not reports:
             return True
 
-        def get_review_status_from_source(report: Report) -> Dict[str, Any]:
+        def get_review_status_from_source(
+                report: Report) -> Tuple[Dict[str, Any], bool]:
             """
             Return the review status belonging to the given report and a
             boolean value which indicates whether the review status comes from
@@ -853,7 +854,7 @@ def get_review_status_from_source(report: Report) -> Dict[str, Any]:
                     review_status["status"] = rs[0]
                     review_status["message"] = rs[1]
 
-                    return review_status
+                    return review_status, True
                 elif len(src_comment_data) > 1:
                     LOG.warning(
                         "Multiple source code comment can be found "
@@ -865,8 +866,7 @@ def get_review_status_from_source(report: Report) -> Dict[str, Any]:
                         f"{source_file_name}|{report.line}|"
                         f"{report.checker_name}")
 
-            return review_status
-
+            return review_status, False
 
         def get_missing_file_ids(report: Report) -> List[str]:
             """ Returns file paths which database file id is missing. """
@@ -919,9 +919,7 @@ def get_missing_file_ids(report: Report) -> List[str]:
             analyzer_name = mip.checker_to_analyzer.get(
                 report.checker_name, report.analyzer_name)
 
-            # TODO do this in bulk
-            rs_from_source = get_review_status_from_source(report)
-            scc = True if rs_from_source else False
+            rs_from_source, scc = get_review_status_from_source(report)
 
             # False positive and intentional reports are considered as closed
             # reports which is indicated with non-null "fixed_at" date.
@@ -938,7 +936,8 @@ def get_missing_file_ids(report: Report) -> List[str]:
                 rs_from_source, scc, detection_status, detected_at,
                 run_history_time, analysis_info, analyzer_name, fixed_at)
 
-            self.__new_report_hashes[report.report_hash] = rs_from_source["status"]
+            self.__new_report_hashes[report.report_hash] = \
+                rs_from_source["status"]
             self.__already_added_report_hashes.add(report_path_hash)
 
             LOG.debug("Storing report done. ID=%d", report_id)
@@ -1001,7 +1000,6 @@ def get_skip_handler(
                 if not report_file.is_supported(f):
                     continue
 
-
         for root_dir_path, _, report_file_paths in os.walk(report_dir):
             LOG.debug("Get reports from '%s' directory", root_dir_path)
 
@@ -1025,13 +1023,13 @@ def get_skip_handler(
                 processed_result_file_count += 1
 
         # Get all relevant review_statuses for the newly stored reports
-        #all_review_statues = session.query(ReviewStatus.bug_hash, ReviewStatus.status, DBReport.id) \
-        reports_to_rs_rules = session.query(ReviewStatus, DBReport.id) \
+        # TODO Call self.getReviewStatusRules instead of the beloew query
+        # but before first check the performance
+        reports_to_rs_rules = session.query(ReviewStatus, DBReport) \
             .join(DBReport, DBReport.bug_id == ReviewStatus.bug_hash) \
-            .filter(sqlalchemy.and_(DBReport.run_id == run_id, # Might be faster to query without condition
-                                    ReviewStatus.bug_hash.in_(self.__new_report_hashes)))
-        # TODO Call self.getReviewStatusRules instead of the above query
-
+            .filter(sqlalchemy.and_(DBReport.run_id == run_id,
+                                    ReviewStatus.bug_hash.
+                                    in_(self.__new_report_hashes)))
 
         # Create the sqlalchemy mappings for the bulk update
         review_status_change = []
@@ -1043,24 +1041,18 @@ def get_skip_handler(
                   rs_info[0].date)
             review_status_change.append(
                 {
-                    "id" : rs_info[1],
+                    "id": rs_info[1].id,
                     "review_status": rs_info[0].status,
                     "review_status_author": rs_info[0].author,
                     "review_status_date": rs_info[0].date,
-                    "review_status_is_in_source" : False,
-                    "review_status_message" : rs_info[0].message
+                    "review_status_is_in_source": False,
+                    "review_status_message": rs_info[0].message,
+                    "fixed_at": rs_info[1].review_status_date
                 }
-            ) 
-        print(review_status_change)
+            )
+        # Update all newly stored reports if there are any rs-rules for them
         session.bulk_update_mappings(DBReport, review_status_change)
 
-
-        # Update all newly stored reports if there are any rev-stat rules for them
-        # Find if any newly stored report need a "custom" review status.
-
-        # TODO Ask Tibi about reports already in DB.
-
-
         LOG.info("[%s] Processed %d analyzer result file(s).", self.__name,
                  processed_result_file_count)
 

web/server/codechecker_server/api/report_server.py

@@ -20,11 +20,8 @@
 import zlib
 
 from copy import deepcopy
-import cProfile
-import pstats
-
 from collections import defaultdict
-from datetime import date, datetime, timedelta
+from datetime import datetime, timedelta
 from typing import Dict, List, Optional, Set, Tuple
 
 import sqlalchemy
@@ -3322,14 +3319,7 @@ def massStoreRun(self, name, tag, version, b64zip, force,
         from codechecker_server.api.mass_store_run import MassStoreRun
         m = MassStoreRun(self, name, tag, version, b64zip, force,
                          trim_path_prefixes, description)
-        with cProfile.Profile() as pr:
-            res = m.store()
-
-        stats = pstats.Stats(pr)
-        stats.sort_stats(pstats.SortKey.TIME)
-        stats.dump_stats(f"/home/ekutgab/ws/tools/snakeviz/dump_{datetime.timestamp(datetime.now())}.prof")
-
-        return res
+        return m.store()
 
     @exc_to_thrift_reqfail
     @timeit