Skip to content

fix: add BCL method blocklist to cross-file inference #440

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
V0v1kkk wants to merge 1 commit into
base: v4
Choose a base branch
from
Open

fix: add BCL method blocklist to cross-file inference #440

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
35 changes: 35 additions & 0 deletions graphify/extract.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3345,6 +3345,39 @@ def extract(paths: list[Path], cache_root: Path | None = None) -> dict:
# Cross-file call resolution for all languages
# Each extractor saved unresolved calls in raw_calls. Now that we have all
# nodes from all files, resolve any callee that exists in another file.
_BCL_METHOD_BLOCKLIST = frozenset({
"contains", "equals", "gethashcode", "tostring", "gettype",
"compareto", "startswith", "endswith", "replace", "split",
"trim", "trimstart", "trimend", "substring", "indexof",
"lastindexof", "insert", "remove", "toarray", "tolist",
"todictionary", "count", "any", "all", "first", "firstordefault",
"last", "lastordefault", "single", "singleordefault",
"where", "select", "selectmany", "orderby", "orderbydescending",
"groupby", "skip", "take", "aggregate", "sum", "min", "max",
"average", "concat", "zip", "distinct", "union", "intersect",
"except", "reverse", "append", "prepend", "add", "clear",
"dispose", "close", "read", "write", "flush", "seek",
"getawaiter", "getresult", "configureawait",
"trygetvalue", "containskey", "containsvalue",
"format", "join", "isnullorempty", "isnullorwhitespace",
"parse", "tryparse",
"listasync", "getasync", "saveasync", "deleteasync",
"updateasync", "createasync", "findasync", "existsasync",
"executeasync", "sendasync", "receiveasync",
"openasync", "closeasync", "readasync", "writeasync",
"createdbcontext", "abortwithstatus",
"abortwithstatuscode", "map", "mapget", "mappost", "mapput",
"mapdelete", "useswagger", "useswaggerui",
"addsingleton", "addscoped", "addtransient",
"useendpoints", "userouting", "useauthorization",
"useauthentication", "usecors", "usehttpsredirection",
"getlogger", "loginformation", "logwarning", "logerror",
"logdebug", "logcritical",
"ok", "notfound", "badrequest", "unauthorized",
"nocontent", "created", "accepted",
"run", "build", "createbuilder",
})

global_label_to_nid: dict[str, str] = {}
for n in all_nodes:
raw = n.get("label", "")
Expand All @@ -3358,6 +3391,8 @@ def extract(paths: list[Path], cache_root: Path | None = None) -> dict:
callee = rc.get("callee", "")
if not callee:
continue
if callee.lower() in _BCL_METHOD_BLOCKLIST:
continue
tgt = global_label_to_nid.get(callee.lower())
caller = rc["caller_nid"]
if tgt and tgt != caller and (caller, tgt) not in existing_pairs:
Expand Down