Send languageId 'typescriptreact' / 'javascriptreact' for .tsx / .jsx files (#1436)

* Fix: send languageId 'typescriptreact' / 'javascriptreact' for .tsx / .jsx

Without this, .tsx files are opened with languageId 'typescript', so
tsserver parses JSX as syntax errors and recovers by truncating the
enclosing symbol's range at the first multi-line JSX expression. The
resulting symptoms:

- find_symbol(name, include_body=True) on a React component returns a
  body that ends mid-component, hiding everything below.
- The same component shows up as multiple Method-kind symbols (one per
  call site) plus a separately-tracked Constant for the definition,
  because tsserver mistakes JSX-tag tokens for member access.

Reproducer (before fix, real-world TSX file):
  SidebarPDF range = [11:1-25:207]   (truncated at first JSX, line 25)
After fix:
  SidebarPDF range = [11:1-281:2]    (full body)

The base SolidLanguageServer._get_language_id_for_file is explicitly
designed for this — its docstring says "Override in subclasses to
return file-specific language IDs." This change just exercises that
hook for the React file extensions.

Adds a regression test + jsx_component.tsx fixture covering the same
arrow-function-with-multi-line-JSX-ternary pattern that triggers the
truncation in real codebases (see oraios/serena#1029 for an earlier
report whose root cause was not identified).
This commit is contained in:
Robin Jehn authored and GitHub committed 2026-04-29 18:03:41 +02:00
1 parent 28c2866bf4
commit 37c837ffd3
4 files changed
+87 -2

No files matched your search

@@ -217,6 +217,15 @@ class TypeScriptLanguageServer(SolidLanguageServer):
def _create_launch_command(self, core_path: str) -> list[str]:
return [core_path, "--stdio"]
def _get_language_id_for_file(self, relative_file_path: str) -> str:
# JSX is parsed as TS without this, which silently truncates symbol
# ranges at the first multi-line JSX expression.
if relative_file_path.endswith(".tsx"):
return "typescriptreact"
if relative_file_path.endswith(".jsx"):
return "javascriptreact"
return self.language_id
def _get_initialize_params(self, repository_absolute_path: str) -> InitializeParams:
"""
Returns the initialize params for the TypeScript Language Server.
@@ -0,0 +1,44 @@
// Regression fixture: mirrors the real-world pattern that caused
// languageId=typescript (instead of typescriptreact) to truncate symbol
// ranges at the first multi-line JSX expression.
import * as React from "react"
type SectionProps = { title: string; emphasised?: boolean }
function Section({ title, emphasised }: SectionProps) {
return emphasised ? (
<h1 style={{ color: "red" }}>{title}</h1>
) : (
<h2 style={{ color: "gray" }}>{title}</h2>
)
}
export function JsxComponent({ heading, items }: { heading: string; items: string[] }) {
const renderHeader = (title: string) =>
title.length > 10 ? (
<Section title={title} emphasised />
) : (
<Section title={title} />
)
// The truncation bug used to cut JsxComponent's range right around here,
// hiding everything below from find_symbol. Keep this comment so the
// regression test can assert the function body extends past it.
const renderItem = (item: string, idx: number) => (
<li key={idx} style={{ marginBottom: 4 }}>
{item}
</li>
)
return (
<div>
{renderHeader(heading)}
<ul>{items.map(renderItem)}</ul>
</div>
)
}
export function trailingHelper(): string {
return "this symbol is invisible to find_symbol when JsxComponent's range is truncated"
}
@@ -5,7 +5,8 @@
"strict": true,
"esModuleInterop": true,
"forceConsistentCasingInFileNames": true,
"skipLibCheck": true
"skipLibCheck": true,
"jsx": "react"
},
"include": ["**/*.ts"]
"include": ["**/*.ts", "**/*.tsx"]
}
@@ -33,6 +33,37 @@ class TestTypescriptLanguageServer:
"index.ts should reference helperFunction (tried all positions in selectionRange)"
)
@pytest.mark.parametrize("language_server", [Language.TYPESCRIPT], indirect=True)
def test_tsx_symbol_range_not_truncated_by_jsx(self, language_server: SolidLanguageServer) -> None:
# Regression: when the language id is sent as "typescript" instead of
# "typescriptreact" for .tsx files, tsserver parses JSX as syntax
# errors and recovers by truncating the enclosing symbol's range at
# the first multi-line JSX expression. find_symbol then returns a
# body that ends mid-component and hides everything below.
file_path = "jsx_component.tsx"
roots = language_server.request_document_symbols(file_path).root_symbols
jsx_component = next((s for s in roots if s.get("name") == "JsxComponent"), None)
assert jsx_component is not None, "JsxComponent not found at root level of jsx_component.tsx"
end_line = jsx_component["location"]["range"]["end"]["line"]
# JsxComponent's body extends to line 38 (0-based 37) in the fixture;
# the truncation bug cut it at the first multi-line JSX (~line 21).
# Use a generous lower bound so the test survives small fixture edits
# that don't affect the regression behaviour we care about.
assert end_line >= 30, (
f"JsxComponent symbol range truncated at line {end_line + 1} (1-based); "
f"expected end at or past line 31 (1-based). "
f"This indicates the .tsx file was opened with the wrong languageId."
)
# The trailing helper must be visible as a top-level symbol — it lives
# past the truncation point and disappears entirely when the bug is
# active because tsserver stops emitting symbols after the parse error.
assert any(s.get("name") == "trailingHelper" for s in roots), (
"trailingHelper missing from jsx_component.tsx root symbols; tsserver likely stopped parsing at the first JSX expression."
)
@pytest.mark.parametrize("language_server", [Language.TYPESCRIPT], indirect=True)
def test_bare_symbol_names(self, language_server) -> None:
all_symbols = request_all_symbols(language_server)