From ae17daca850766d06e9812c3367c93d8dd789f15 Mon Sep 17 00:00:00 2001
From: Niels Thykier <niels@thykier.net>
Date: Sat, 6 Apr 2024 11:35:20 +0000
Subject: [PATCH] fix: respect client's preferred encoding when possible

Previously, `pygls` would always use `UTF-16` except when the client
tried to hide the fact that it supports `UTF-16` (which the LSP spec
requires it to do in all cases). Now, `pygls` will choose the editor's
preferred encoding.

When it is `UTF-32`, `pygls` saves a bit of computation in most
position codec related operations (`X_to_client_units` +
`client_num_units` are faster, `X_from_client_units` is about the
same), which is great. When it is `UTF-16` or `UTF-8`, the
computational load is about the same.

Closes: #445
---
 pygls/capabilities.py         | 23 +++++++++++++----------
 tests/test_feature_manager.py | 13 +++++++++++++
 2 files changed, 26 insertions(+), 10 deletions(-)

diff --git a/pygls/capabilities.py b/pygls/capabilities.py
index 975e5e24..44a6d2ed 100644
--- a/pygls/capabilities.py
+++ b/pygls/capabilities.py
@@ -24,6 +24,14 @@
 logger = logging.getLogger(__name__)
 T = TypeVar("T")
 
+_SUPPORTED_ENCODINGS = frozenset(
+    [
+        types.PositionEncodingKind.Utf8,
+        types.PositionEncodingKind.Utf16,
+        types.PositionEncodingKind.Utf32,
+    ]
+)
+
 
 def get_capability(
     client_capabilities: types.ClientCapabilities, field: str, default: Any = None
@@ -401,16 +409,11 @@ def _with_position_encodings(self):
         if encodings is None:
             return self
 
-        if types.PositionEncodingKind.Utf16 in encodings:
-            return self
-
-        if types.PositionEncodingKind.Utf32 in encodings:
-            self.server_cap.position_encoding = types.PositionEncodingKind.Utf32
-            return self
-
-        if types.PositionEncodingKind.Utf8 in encodings:
-            self.server_cap.position_encoding = types.PositionEncodingKind.Utf8
-            return self
+        # We match client preference where this an overlap between its and our supported encodings.
+        for encoding in encodings:
+            if encoding in _SUPPORTED_ENCODINGS:
+                self.server_cap.position_encoding = encoding
+                return self
 
         logger.warning(f"Unknown `PositionEncoding`s: {encodings}")
 
diff --git a/tests/test_feature_manager.py b/tests/test_feature_manager.py
index f69f12a3..744fcdb1 100644
--- a/tests/test_feature_manager.py
+++ b/tests/test_feature_manager.py
@@ -240,6 +240,19 @@ def server_capabilities(**kwargs):
                     ]
                 )
             ),
+            server_capabilities(position_encoding=lsp.PositionEncodingKind.Utf8),
+        ),
+        (
+            lsp.INITIALIZE,
+            None,
+            lsp.ClientCapabilities(
+                general=lsp.GeneralClientCapabilities(
+                    position_encodings=[
+                        lsp.PositionEncodingKind.Utf32,
+                        lsp.PositionEncodingKind.Utf8,
+                    ]
+                )
+            ),
             server_capabilities(position_encoding=lsp.PositionEncodingKind.Utf32),
         ),
         (