Merge pull request #1243 from oraios/ls-name-normalisation

Improve LS symbol name normalisation handling

src/solidlsp/language_servers/al_language_server.py

@@ -18,7 +18,7 @@ from overrides import override
 
 from solidlsp import ls_types
 from solidlsp.language_servers.common import quote_windows_path
-from solidlsp.ls import DocumentSymbols, LSPFileBuffer, SolidLanguageServer
+from solidlsp.ls import DocumentSymbols, LSPFileBuffer, RawDocumentSymbol, SolidLanguageServer
 from solidlsp.ls_config import Language, LanguageServerConfig
 from solidlsp.ls_types import SymbolKind, UnifiedSymbolInformation
 from solidlsp.ls_utils import FileUtils
@@ -1007,35 +1007,25 @@ class ALLanguageServer(SolidLanguageServer):
         # Get symbols from parent implementation
         document_symbols = super().request_document_symbols(relative_file_path, file_buffer=file_buffer)
 
-        # Normalize names by stripping AL object metadata, storing originals for hover
-        def normalize_name(symbol: UnifiedSymbolInformation) -> None:
-            original_name = symbol["name"]
-            normalized_name = self._extract_al_display_name(original_name)
-
-            # Store original name if it was normalized (for hover injection)
-            # Only store if we have valid position data to avoid false matches at (0, 0)
-            if original_name != normalized_name:
-                sel_range = symbol.get("selectionRange")
-                if sel_range:
-                    start = sel_range.get("start")
-                    if start and "line" in start and "character" in start:
-                        line = start["line"]
-                        char = start["character"]
-                        self._al_original_names[(relative_file_path, line, char)] = original_name
-
-            symbol["name"] = normalized_name
-
-            # Process children recursively
-            if symbol.get("children"):
-                for child in symbol["children"]:
-                    normalize_name(child)
-
-        # Apply to all root symbols
-        for sym in document_symbols.root_symbols:
-            normalize_name(sym)
-
         return document_symbols
 
+    def _normalize_symbol_name(self, symbol: RawDocumentSymbol, relative_file_path: str) -> str:
+        original_name = symbol["name"]
+        normalized_name = self._extract_al_display_name(original_name)
+
+        # Store original name if it was normalized (for hover injection)
+        # Only store if we have valid position data to avoid false matches at (0, 0)
+        if original_name != normalized_name:
+            sel_range = symbol.get("selectionRange")
+            if sel_range:
+                start = sel_range.get("start")  # type: ignore
+                if start and "line" in start and "character" in start:
+                    line = start["line"]
+                    char = start["character"]
+                    self._al_original_names[(relative_file_path, line, char)] = original_name
+
+        return normalized_name
+
     @override
     def request_hover(
         self, relative_file_path: str, line: int, column: int, file_buffer: LSPFileBuffer | None = None

src/solidlsp/language_servers/csharp_language_server.py

@@ -7,7 +7,7 @@ import os
 import platform
 import shutil
 import threading
-from collections.abc import Iterable
+from collections.abc import Hashable, Iterable
 from dataclasses import replace
 from pathlib import Path
 from typing import Any, cast
@@ -15,10 +15,15 @@ from typing import Any, cast
 from overrides import override
 
 from serena.util.dotnet import DotNETUtil
-from solidlsp.ls import DocumentSymbols, LanguageServerDependencyProvider, LSPFileBuffer, SolidLanguageServer
+from solidlsp.ls import (
+    LanguageServerDependencyProvider,
+    LSPFileBuffer,
+    RawDocumentSymbol,
+    SolidLanguageServer,
+)
 from solidlsp.ls_config import LanguageServerConfig
 from solidlsp.ls_exceptions import SolidLSPException
-from solidlsp.ls_types import Hover, UnifiedSymbolInformation
+from solidlsp.ls_types import Hover
 from solidlsp.ls_utils import FileUtils, PathUtils
 from solidlsp.lsp_protocol_handler.lsp_types import InitializeParams, InitializeResult
 from solidlsp.settings import SolidLSPSettings
@@ -218,28 +223,6 @@ class CSharpLanguageServer(SolidLanguageServer):
     def is_ignored_dirname(self, dirname: str) -> bool:
         return super().is_ignored_dirname(dirname) or dirname in ["bin", "obj", "packages", ".vs"]
 
-    @override
-    def request_document_symbols(self, relative_file_path: str, file_buffer: Any = None) -> DocumentSymbols:
-        """
-        Override to normalize Roslyn symbol names and cache originals.
-
-        Roslyn 5.5.0+ returns symbol names with type annotations:
-        - Properties: "Name : string"
-        - Methods: "Add(int, int) : int"
-
-        This method:
-        1. Normalizes names to base form ("Name", "Add")
-        2. Caches original names for rich information display
-        3. Populates LSP spec's 'detail' field with type/signature info
-        """
-        symbols = super().request_document_symbols(relative_file_path, file_buffer)
-
-        # Normalize all symbols recursively
-        for symbol in symbols.iter_symbols():
-            self._normalize_symbol_name(symbol, relative_file_path)
-
-        return symbols
-
     @override
     def request_hover(self, relative_file_path: str, line: int, column: int, file_buffer: LSPFileBuffer | None = None) -> Hover | None:
         """
@@ -265,12 +248,20 @@ class CSharpLanguageServer(SolidLanguageServer):
 
         return hover
 
-    def _normalize_symbol_name(self, symbol: UnifiedSymbolInformation, relative_file_path: str) -> None:
-        """
-        Normalize a single symbol's name and cache the original.
-        Processes children recursively.
-        """
-        original_name = symbol.get("name", "")
+    def _document_symbols_cache_fingerprint(self) -> Hashable | None:
+        normalize_symbol_name_version = 1
+        return normalize_symbol_name_version
+
+    def _normalize_symbol_name(self, symbol: RawDocumentSymbol, relative_file_path: str) -> str:
+        # Roslyn 5.5.0+ returns symbol names with type annotations:
+        #  - Properties: "Name : string"
+        #  - Methods: "Add(int, int) : int"
+        #
+        # This method:
+        #  1. Normalizes names to base form ("Name", "Add")
+        #  2. Caches original names for rich information display
+        #  3. Populates LSP spec's 'detail' field with type/signature info
+        original_name = symbol["name"]
 
         # Extract base name and type/signature info
         normalized_name, type_info = self._extract_base_name_and_type(original_name)
@@ -279,24 +270,18 @@ class CSharpLanguageServer(SolidLanguageServer):
         if original_name != normalized_name:
             sel_range = symbol.get("selectionRange")
             if sel_range:
-                start = sel_range.get("start")
+                start = sel_range.get("start")  # type: ignore
                 if start and "line" in start and "character" in start:
                     line = start["line"]
                     char = start["character"]
                     cache_key = (relative_file_path, line, char)
                     self._original_symbol_names[cache_key] = original_name
 
-            # Populate LSP spec's 'detail' field with type/signature information
+            # Populate 'detail' field with type/signature information (for UnifiedSymbolInformation)
             if type_info and "detail" not in symbol:
-                symbol["detail"] = type_info
+                symbol["detail"] = type_info  # type: ignore
 
-        # Update the symbol name
-        symbol["name"] = normalized_name
-
-        # Process children recursively
-        children = symbol.get("children", [])
-        for child in children:
-            self._normalize_symbol_name(child, relative_file_path)
+        return normalized_name
 
     @staticmethod
     def _extract_base_name_and_type(roslyn_name: str) -> tuple[str, str]:

src/solidlsp/ls.py

@@ -48,7 +48,13 @@ from solidlsp.lsp_protocol_handler.server import (
 from solidlsp.settings import SolidLSPSettings
 from solidlsp.util.cache import load_cache, save_cache
 
-GenericDocumentSymbol = Union[LSPTypes.DocumentSymbol, LSPTypes.SymbolInformation, ls_types.UnifiedSymbolInformation]
+RawDocumentSymbol = Union[DocumentSymbol, SymbolInformation]
+"""
+Type alias for the raw symbol information returned by a language server in response to a
+`textDocument/documentSymbol` request.
+The `DocumentSymbol` is the preferred type, but the legacy type `SymbolInformation` is also still used.
+"""
+
 log = logging.getLogger(__name__)
 
 _debug_enabled = log.isEnabledFor(logging.DEBUG)
@@ -211,7 +217,7 @@ class SymbolBodyFactory:
     def __init__(self, file_buffer: LSPFileBuffer):
         self._lines = file_buffer.split_lines()
 
-    def create_symbol_body(self, symbol: GenericDocumentSymbol) -> SymbolBody:
+    def create_symbol_body(self, symbol: UnifiedSymbolInformation) -> SymbolBody:
         existing_body = symbol.get("body", None)
         if existing_body and isinstance(existing_body, SymbolBody):
             return existing_body
@@ -1262,7 +1268,7 @@ class SolidLanguageServer(ABC):
         The returned symbols are considered "raw document symbols" (in contrast to processed symbols returned by `request_document_symbols`).
 
         NOTE: This method can be overridden in subclasses to post-process the raw results.
-              When doing so, be sure to update the init parameter `cache_version_raw_document_symbols`
+              When doing so after the initial implementation, be sure to update the init parameter `cache_version_raw_document_symbols`
               to a different version (add 1) to ensure that all caches are invalidated appropriately.
               IMPORTANT: Since rebuilding the raw document symbol cache from the language server results
               is potentially expensive, prefer overriding the `request_document_symbols` method
@@ -1312,13 +1318,30 @@ class SolidLanguageServer(ABC):
         with self._open_file_context(relative_file_path, file_buffer=file_data) as fd:
             return get_raw_document_symbols(fd)
 
+    def _normalize_symbol_name(self, symbol: RawDocumentSymbol, relative_file_path: str) -> str:
+        """
+        Normalizes the name of the given symbol, e.g. by removing parameter lists from method symbols.
+
+        Override this method in subclasses to implement language-specific normalization logic.
+        NOTE: When changing the override of this method after the initial LS implementation,
+              be sure to also override `_document_symbols_cache_fingerprint` in order to ensure that
+              the caches are invalidated appropriately.
+
+        :param symbol: the symbol
+        :param relative_file_path: the relative path of the file the symbol is located in
+        :return: the normalized name of the symbol
+        """
+        # the default implementation does not change the name
+        return symbol["name"]
+
     def request_document_symbols(self, relative_file_path: str, file_buffer: LSPFileBuffer | None = None) -> DocumentSymbols:
         """
         Retrieves the collection of symbols in the given file.
 
         NOTE: This method can be overridden in subclasses to post-process the results.
-              When doing so, be sure to also override `_document_symbols_cache_fingerprint`
+              When doing so after the initial LS implementation, be sure to also override `_document_symbols_cache_fingerprint`
               to ensure that the caches are invalidated appropriately.
+              DO NOT override this method to modify symbol names; override `_normalize_symbol_name` instead.
 
         :param relative_file_path: The relative path of the file that has the symbols
         :param file_buffer: an optional file buffer if the file is already opened.
@@ -1362,7 +1385,7 @@ class SolidLanguageServer(ABC):
 
             body_factory = SymbolBodyFactory(file_data)
 
-            def convert_to_unified_symbol(original_symbol_dict: GenericDocumentSymbol) -> ls_types.UnifiedSymbolInformation:
+            def convert_to_unified_symbol(original_symbol_dict: RawDocumentSymbol) -> ls_types.UnifiedSymbolInformation:
                 """
                 Converts the given symbol dictionary to the unified representation, ensuring
                 that all required fields are present (except 'children' which is handled separately).
@@ -1403,16 +1426,23 @@ class SolidLanguageServer(ABC):
                 return item
 
             def convert_symbols_with_common_parent(
-                symbols: list[DocumentSymbol] | list[SymbolInformation] | list[UnifiedSymbolInformation],
+                symbols: list[DocumentSymbol] | list[SymbolInformation],
                 parent: ls_types.UnifiedSymbolInformation | None,
             ) -> list[ls_types.UnifiedSymbolInformation]:
                 """
                 Converts the given symbols into UnifiedSymbolInformation with proper parent-child relationships,
                 adding overload indices for symbols with the same name under the same parent.
                 """
+                # apply name normalization and count occurrences of each symbol name
                 total_name_counts: dict[str, int] = defaultdict(lambda: 0)
                 for symbol in symbols:
-                    total_name_counts[symbol["name"]] += 1
+                    name = self._normalize_symbol_name(symbol, relative_file_path=relative_file_path)
+                    symbol["name"] = name
+                    total_name_counts[name] += 1
+
+                # convert symbols to the unified representation and
+                #  * add overload indices where necessary
+                #  * ensure that the "parent" field is set correctly
                 name_counts: dict[str, int] = defaultdict(lambda: 0)
                 unified_symbols = []
                 for symbol in symbols:
@@ -1727,7 +1757,7 @@ class SolidLanguageServer(ABC):
 
     def create_symbol_body(
         self,
-        symbol: ls_types.UnifiedSymbolInformation | LSPTypes.SymbolInformation,
+        symbol: ls_types.UnifiedSymbolInformation,
         factory: SymbolBodyFactory | None = None,
     ) -> SymbolBody:
         if factory is None: