Skip to content

Fix panics from symbolParserV2 #338

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

Merged
merged 3 commits into from
Sep 23, 2025
Merged

Fix panics from symbolParserV2 #338

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
90baa68
Use shared IsSimpleIdentifierCharacter when testing identifier charac…
efritz Sep 11, 2025
b49e849
WIP.
efritz Sep 11, 2025
52041ac
Add additional test cases.
efritz Sep 11, 2025
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
9 changes: 2 additions & 7 deletions bindings/go/scip/symbol_parser.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,6 @@ package scip
import (
"fmt"
"strings"
"unicode"

"github.com/cockroachdb/errors"
"github.com/sourcegraph/beaut"
Expand Down Expand Up @@ -469,10 +468,6 @@ func (e unrecognizedDescriptorError) Error() string {
return fmt.Sprintf("unrecognized descriptor %q", e.value)
}

func isIdentifierCharacter(r rune) bool {
return unicode.IsLetter(r) || unicode.IsDigit(r) || r == '-' || r == '+' || r == '$' || r == '_'
}

func (z *symbolParserV2) advanceOneByte(b byte) {
assert(z.currentRune == rune(b), "passed in byte does not match current rune")
nextRune, nextRuneByteLength := z.peekNext()
Expand All @@ -484,7 +479,7 @@ func (z *symbolParserV2) advanceOneByte(b byte) {

func (z *symbolParserV2) advanceRune() {
nextRune, nextRuneByteLength := z.peekNext()
z.advance(nextRune, min(nextRuneByteLength, 1))
z.advance(nextRune, nextRuneByteLength)
}

func (z *symbolParserV2) acceptOneByte(b byte, what parseCtx) error {
Expand All @@ -503,7 +498,7 @@ func (z *symbolParserV2) acceptIdentifier(what parseCtx, sw *stringWriter) error
start := z.byteIndex
slen := len(z.SymbolString)
for z.byteIndex < slen {
if !isIdentifierCharacter(z.currentRune) {
if !shared.IsSimpleIdentifierCharacter(z.currentRune) {
break
}
z.advanceRune()
Expand Down
15 changes: 15 additions & 0 deletions bindings/go/scip/symbol_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -108,6 +108,19 @@ func TestParseSymbol(t *testing.T) {
},
},
},
{
Symbol: "a b c d `F⃗`.", Expected: &Symbol{
Scheme: "a",
Package: &Package{
Manager: "b",
Name: "c",
Version: "d",
},
Descriptors: []*Descriptor{{
Name: "F⃗", Suffix: Descriptor_Term,
}},
},
},
}
for _, test := range tests {
t.Run(test.Symbol, func(t *testing.T) {
Expand All @@ -127,6 +140,8 @@ func TestParseSymbolError(t *testing.T) {
"lsif-java maven package 1.0.0 java/io/File#Entry.trailingstring",
"lsif-java maven package 1.0.0 java/io/File#Entry.unrecognizedSuffix@",
"lsif-java maven package 1.0.0 java/io/File#Entry.nonSimpλeIdentifier.",
"lsif-java maven package 1.0.0 java/io/File#Entry.`unterminatedEscapedIdentifier",
"lsif-java maven package 1.0.0 java/io/File#Entry.[UnterminatedDescriptorSuffix",
"local 🧠",
"local ",
"local &&&",
Expand Down