chore: simplify the looking up component information by getting the ID and repository from the lookup Component object instead of having their own SELECT query

Author: Trong Nhan Mai

src/macaron/build_spec_generator/macaron_db_extractor.py

@@ -15,7 +15,7 @@
 from sqlalchemy.exc import MultipleResultsFound, SQLAlchemyError
 from sqlalchemy.orm import Session, aliased
 
-from macaron.database.table_definitions import Analysis, CheckFacts, Component, MappedCheckResult, Repository
+from macaron.database.table_definitions import Analysis, CheckFacts, Component, MappedCheckResult
 from macaron.errors import QueryMacaronDatabaseError
 from macaron.slsa_analyzer.checks.build_as_code_check import BuildAsCodeFacts
 from macaron.slsa_analyzer.checks.build_script_check import BuildScriptFacts
@@ -353,32 +353,8 @@ def get_sql_stmt_build_script_check(component_id: int) -> Select[tuple[BuildScri
     )
 
 
-def get_sql_stmt_repository(component_id: int) -> Select[tuple[Repository]]:
-    """Return an SQLAlchemy SELECT statement to query the Repository for a given PackageURL.
-
-    Parameters
-    ----------
-    purl_string : str
-        The PackageURL string to find the Repository.
-
-    Returns
-    -------
-    Select[tuple[Repository]]
-        The SQLAlchemy SELECT statement.
-    """
-    return (
-        select(Repository)
-        .select_from(Component)
-        .join(
-            Repository,
-            onclause=Component.id == Repository.component_id,
-        )
-        .where(Component.id == component_id)
-    )
-
-
-def lookup_latest_component_id(purl: PackageURL, session: Session) -> int | None:
-    """Return the component id of the latest analysis that matches a given PackageURL string.
+def lookup_latest_component(purl: PackageURL, session: Session) -> Component | None:
+    """Return the component of the latest analysis that matches a given PackageURL string.
 
     Parameters
     ----------
@@ -389,29 +365,29 @@ def lookup_latest_component_id(purl: PackageURL, session: Session) -> int | None
 
     Returns
     -------
-    int | None
-        The latest component id or None if there isn't one available in the database.
+    Component | None
+        The latest component or None if there isn't one available in the database.
 
     Raises
     ------
     QueryMacaronDatabaseError
         If there is an unexpected error when executing the SQLAlchemy query.
     """
-    latest_component_id_stmt = get_sql_stmt_latest_component_for_purl(purl)
-    logger.debug("Latest Analysis and Component query \n %s", compile_sqlite_select_statement(latest_component_id_stmt))
+    latest_component_stmt = get_sql_stmt_latest_component_for_purl(purl)
+    logger.debug("Latest Analysis and Component query \n %s", compile_sqlite_select_statement(latest_component_stmt))
 
     try:
-        component_results = session.execute(latest_component_id_stmt)
+        component_results = session.execute(latest_component_stmt)
     except SQLAlchemyError as generic_exec_error:
         raise QueryMacaronDatabaseError(
-            f"Critical: unexpected error when execute query {compile_sqlite_select_statement(latest_component_id_stmt)}."
+            f"Critical: unexpected error when execute query {compile_sqlite_select_statement(latest_component_stmt)}."
         ) from generic_exec_error
 
     latest_component = component_results.scalars().first()
     if not latest_component:
         return None
 
-    return latest_component.id
+    return latest_component
 
 
 def lookup_build_tools_check(component_id: int, session: Session) -> Sequence[BuildToolFacts]:
@@ -687,37 +663,3 @@ def lookup_any_build_command(component_id: int, session: Session) -> list[Generi
             error,
         )
         return []
-
-
-def lookup_repository(component_id: int, session: Session) -> Repository | None:
-    """Return the Repository instance for given PackageURL string.
-
-    Parameters
-    ----------
-    component_id : int
-        The component id to look for the Repository.
-    session : Session
-        The SQLAlcemy Session that connects to the Macaron database.
-
-    Returns
-    -------
-    Repository
-        The Repository instances obtained from querying the database.
-
-    Raises
-    ------
-    QueryMacaronDatabaseError
-        If the query result from the database contains more than one Repository instance,
-        or there is an unexpected error when executing the SQLAlchemy query.
-    """
-    repository_select_statement = get_sql_stmt_repository(component_id)
-    logger.debug(
-        "Repository for component %d \n %s.", component_id, compile_sqlite_select_statement(repository_select_statement)
-    )
-
-    repository_result = lookup_one_or_none(
-        select_statement=repository_select_statement,
-        session=session,
-    )
-
-    return repository_result

src/macaron/build_spec_generator/reproducible_central/rc_build_info.py

@@ -15,8 +15,7 @@
     GenericBuildCommandInfo,
     lookup_any_build_command,
     lookup_build_tools_check,
-    lookup_latest_component_id,
-    lookup_repository,
+    lookup_latest_component,
 )
 from macaron.database.table_definitions import Repository
 from macaron.errors import QueryMacaronDatabaseError
@@ -64,36 +63,30 @@ def get_rc_internal_build_info(
         An instance of ``RcInternalBuildInfo`` or None if there was an error.
     """
     try:
-        latest_component_id = lookup_latest_component_id(
+        latest_component = lookup_latest_component(
             purl=purl,
             session=session,
         )
     except QueryMacaronDatabaseError as lookup_component_error:
         logger.error(
-            "Unexpected result from querying latest component id for %s. Error: %s",
+            "Unexpected result from querying latest component for %s. Error: %s",
             purl.to_string(),
             lookup_component_error,
         )
         return None
-    if not latest_component_id:
+    if not latest_component:
         logger.error(
             "Cannot find an analysis result for PackageURL %s in the database. "
             + "Please check if an analysis for it exists in the database.",
             purl.to_string(),
         )
         return None
+
+    latest_component_id = latest_component.id
     logger.debug("Latest component ID: %d", latest_component_id)
 
-    try:
-        lookup_component_repository = lookup_repository(latest_component_id, session)
-    except QueryMacaronDatabaseError as lookup_repository_error:
-        logger.error(
-            "Unexpected result from querying repository information for %s. Error: %s",
-            purl.to_string(),
-            lookup_repository_error,
-        )
-        return None
-    if not lookup_component_repository:
+    latest_component_repository = latest_component.repository
+    if not latest_component_repository:
         logger.error(
             "Cannot find any repository information for %s in the database.",
             purl.to_string(),
@@ -102,8 +95,8 @@ def get_rc_internal_build_info(
     logger.info(
         "Repository information for purl %s: url %s, commit %s",
         purl,
-        lookup_component_repository.remote_path,
-        lookup_component_repository.commit_sha,
+        latest_component_repository.remote_path,
+        latest_component_repository.commit_sha,
     )
 
     try:
@@ -146,7 +139,7 @@ def get_rc_internal_build_info(
 
     return RcInternalBuildInfo(
         purl=purl,
-        repository=lookup_component_repository,
+        repository=latest_component_repository,
         latest_component_id=latest_component_id,
         build_tool_facts=build_tool_facts,
         generic_build_command_facts=lookup_build_command_infos,