Skip to content

fix(c-parser): reject call sites inside function bodies; support nginx-style split-line defs (#331) #352

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
justrach wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fix(c-parser): reject call sites inside function bodies; support nginx-style split-line defs (#331) #352

Show file tree
Hide file tree
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
85 changes: 79 additions & 6 deletions src/explore.zig
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -830,6 +830,7 @@ pub const Explorer = struct {
var in_py_docstring = false;
var in_block_comment = false;
var in_go_import_block = false;
var c_brace_depth: u32 = 0;
var lines = std.mem.splitScalar(u8, content, '\n');
while (lines.next()) |line| {
line_num += 1;
Expand Down Expand Up @@ -905,7 +906,7 @@ pub const Explorer = struct {
} else if (outline.language == .typescript or outline.language == .javascript) {
try parser.parseTsLine(trimmed, line_num, &outline);
} else if (outline.language == .c or outline.language == .cpp) {
try parser.parseCLine(trimmed, line_num, &outline);
try parser.parseCLine(line, trimmed, line_num, &outline, prev_line_trimmed, &c_brace_depth);
} else if (outline.language == .rust) {
try parser.parseRustLine(trimmed, line_num, &outline, prev_line_trimmed);
} else if (outline.language == .php) {
Expand Down Expand Up @@ -2197,9 +2198,9 @@ pub const Explorer = struct {
}
}

fn parseCLine(self: *Explorer, raw_line: []const u8, line_num: u32, outline: *FileOutline) !void {
fn parseCLine(self: *Explorer, raw_line: []const u8, trimmed: []const u8, line_num: u32, outline: *FileOutline, prev_trimmed: []const u8, brace_depth: *u32) !void {
const a = self.allocator;
const line = stripLineComment(raw_line);
const line = stripLineComment(trimmed);
if (line.len == 0) return;

if (startsWith(line, "#include") or startsWith(line, "#import")) {
Expand All @@ -2222,22 +2223,28 @@ pub const Explorer = struct {

if (parseObjCType(line)) |type_sym| {
try appendOutlineSymbol(a, outline, type_sym.name, type_sym.kind, line_num, line);
applyBraceDelta(brace_depth, countBracesDelta(line));
return;
}

if (extractObjCMethodName(line)) |name| {
try appendOutlineSymbol(a, outline, name, .method, line_num, line);
applyBraceDelta(brace_depth, countBracesDelta(line));
return;
}

if (parseCNamedType(line)) |type_sym| {
try appendOutlineSymbol(a, outline, type_sym.name, type_sym.kind, line_num, line);
applyBraceDelta(brace_depth, countBracesDelta(line));
return;
}

if (extractCFunctionName(line)) |name| {
const at_col0 = raw_line.len > 0 and raw_line[0] != ' ' and raw_line[0] != '\t';
if (extractCFunctionName(line, at_col0, prev_trimmed, brace_depth.*, outline.language == .cpp)) |name| {
try appendOutlineSymbol(a, outline, name, .function, line_num, line);
}

applyBraceDelta(brace_depth, countBracesDelta(line));
}

fn parseRustLine(self: *Explorer, line: []const u8, line_num: u32, outline: *FileOutline, prev_line: []const u8) !void {
Expand Down Expand Up @@ -4281,7 +4288,14 @@ fn extractObjCMethodName(line: []const u8) ?[]const u8 {
return extractIdent(rest);
}

fn extractCFunctionName(line: []const u8) ?[]const u8 {
fn extractCFunctionName(line: []const u8, at_col0: bool, prev_trimmed: []const u8, brace_depth: u32, is_cpp: bool) ?[]const u8 {
// Anything inside a function body is a call site, not a definition.
// C: depth 0 = file scope. Any depth >= 1 means inside a function body.
// C++: depth 0 = file scope, depth 1 = class/struct body (methods allowed).
// Depth >= 2 means inside a function body.
const max_depth: u32 = if (is_cpp) 1 else 0;
if (brace_depth > max_depth) return null;

const stripped = stripCAttributesPrefix(line);
if (stripped.len == 0 or stripped[0] == '#') return null;
if (startsWith(stripped, "typedef ")) return null;
Expand All @@ -4300,14 +4314,73 @@ fn extractCFunctionName(line: []const u8) ?[]const u8 {
if (isCKeyword(name)) return null;

const before_name = std.mem.trim(u8, before_paren[0..span.start], " \t*(&");
if (before_name.len == 0) return null;
if (before_name.len == 0) {
// nginx-style: return type on previous line, function name starts this line.
// Accept only if at column 0 and prev line looks like a type (identifier,
// optionally preceded by storage qualifiers), not a statement or brace.
if (!at_col0) return null;
if (prev_trimmed.len == 0) return null;
if (prev_trimmed[0] == '{' or prev_trimmed[0] == '}' or
prev_trimmed[0] == '(' or prev_trimmed[0] == ')')
return null;
if (std.mem.indexOfScalar(u8, prev_trimmed, ';') != null) return null;
if (std.mem.indexOfScalar(u8, prev_trimmed, '(') != null) return null;
if (isCForbiddenFunctionPrefix(prev_trimmed)) return null;
// prev line must start with an identifier (a type name or qualifier)
if (extractIdent(std.mem.trimStart(u8, prev_trimmed, " \t*")) == null) return null;
return name;
}
if (!at_col0 and !looksLikeCMethodDef(before_name)) return null;
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector Bot Apr 30, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Allow indented keyword-prefixed C/C++ definitions

Remove or relax this gate: it rejects any non-column-0 definition unless looksLikeCMethodDef passes, and that helper returns false when the first token is a C keyword like static, inline, extern, or const. As a result, indented definitions such as static/inline methods inside C++ class bodies (and indented static C functions) are no longer indexed, which is a regression in symbol recall introduced by this commit.

Useful? React with 👍 / 👎.

if (hasCAssignmentBeforeName(before_name)) return null;
if (isCForbiddenFunctionPrefix(before_name)) return null;
if (std.mem.endsWith(u8, before_name, ".") or std.mem.endsWith(u8, before_name, "->")) return null;

return name;
}

fn countChar(s: []const u8, ch: u8) u32 {
var n: u32 = 0;
for (s) |c| if (c == ch) { n += 1; };
return n;
}

fn applyBraceDelta(depth: *u32, delta: i32) void {
if (delta >= 0) {
depth.* +|= @intCast(delta);
} else {
const sub: u32 = @intCast(-delta);
depth.* -|= sub;
}
}

fn countBracesDelta(line: []const u8) i32 {
var delta: i32 = 0;
var i: usize = 0;
while (i < line.len) : (i += 1) {
const ch = line[i];
if (ch == '"' or ch == '\'') {
const q = ch;
i += 1;
while (i < line.len) : (i += 1) {
if (line[i] == '\\') { i += 1; continue; }
if (line[i] == q) break;
}
} else if (ch == '{') {
delta += 1;
} else if (ch == '}') {
delta -= 1;
Comment on lines +4368 to +4371
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector Bot Apr 30, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Ignore inline block comments in brace-depth accounting

Brace depth is updated by counting { and } directly on the parsed line, but only string/char literals are skipped; /* ... */ spans are not. This causes braces inside inline block comments (for example /* } */ within a function body) to corrupt c_brace_depth, which can incorrectly return to file scope and reintroduce false-positive function indexing for subsequent call sites.

Useful? React with 👍 / 👎.

}
}
return delta;
}

fn looksLikeCMethodDef(before_name: []const u8) bool {
const trimmed = std.mem.trimStart(u8, before_name, " \t*(&");
const first = extractIdent(trimmed) orelse return false;
return !isCKeyword(first) and !std.mem.eql(u8, first, "return") and
!std.mem.eql(u8, first, "case");
}

fn stripCAttributesPrefix(line: []const u8) []const u8 {
var rest = std.mem.trimStart(u8, line, " \t");
while (startsWith(rest, "__attribute__((")) {
Expand Down
71 changes: 71 additions & 0 deletions src/tests.zig
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7587,6 +7587,77 @@ test "issue-207: ScanState.name covers all states" {
try testing.expectEqualStrings("ready", mcp_mod.ScanState.ready.name());
}

test "issue-331: C parser does not index indented call sites as functions" {
var arena = std.heap.ArenaAllocator.init(testing.allocator);
defer arena.deinit();
const a = arena.allocator();
var explorer = Explorer.init(a);

try explorer.indexFile("test.c",
\\void real_func(int x) {
\\ fprintf(stderr, "curl_easy_perform() failed: %s\n",
\\ curl_easy_strerror(res));
\\ curl_easy_perform(curl);
\\ if (SSL_get_options(ctx))
\\ return;
\\}
);

const syms = explorer.outlines.get("test.c").?.symbols.items;
var found_false = false;
for (syms) |sym| {
if (sym.kind == .function) {
if (std.mem.eql(u8, sym.name, "fprintf") or
std.mem.eql(u8, sym.name, "curl_easy_perform") or
std.mem.eql(u8, sym.name, "curl_easy_strerror") or
std.mem.eql(u8, sym.name, "SSL_get_options"))
{
found_false = true;
}
}
}
try testing.expect(!found_false);
var found_real = false;
for (syms) |sym| {
if (sym.kind == .function and std.mem.eql(u8, sym.name, "real_func"))
found_real = true;
}
try testing.expect(found_real);
}

test "issue-331: C parser finds nginx-style split-line definitions" {
var arena = std.heap.ArenaAllocator.init(testing.allocator);
defer arena.deinit();
const a = arena.allocator();
var explorer = Explorer.init(a);

try explorer.indexFile("ngx_http_request.c",
\\ngx_int_t
\\ngx_http_init_connection(ngx_connection_t *c)
\\{
\\ ngx_http_connection_t *hc;
\\}
\\
\\static ngx_int_t
\\ngx_http_create_request(ngx_http_request_t *r)
\\{
\\ return NGX_OK;
\\}
);

const syms = explorer.outlines.get("ngx_http_request.c").?.symbols.items;
var found_init = false;
var found_create = false;
for (syms) |sym| {
if (sym.kind == .function) {
if (std.mem.eql(u8, sym.name, "ngx_http_init_connection")) found_init = true;
if (std.mem.eql(u8, sym.name, "ngx_http_create_request")) found_create = true;
}
}
try testing.expect(found_init);
try testing.expect(found_create);
}

test "issue-346: root_policy rejects dangerous ambient cwd roots" {
const root_policy = @import("root_policy.zig");
try testing.expect(!root_policy.isIndexableRoot("/"));
Expand Down
Loading