Skip to content

perf(napi/parser): optimize string deserialization for non-ASCII sources #20834

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
overlookmotel merged 1 commit into from
Mar 30, 2026
Merged

perf(napi/parser): optimize string deserialization for non-ASCII sources #20834

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
18 changes: 14 additions & 4 deletions apps/oxlint/src-js/generated/deserialize.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,6 +10,7 @@ let uint8,
sourceText,
sourceIsAscii,
sourceStartPos,
firstNonAsciiPos,
parent = null,
getLoc;

Expand Down Expand Up @@ -42,6 +43,14 @@ function deserializeWith(buffer, sourceTextInput, sourceByteLen, getLocInput, de
float64 = buffer.float64;
sourceText = sourceTextInput;
sourceIsAscii = sourceText.length === sourceByteLen;
if (!sourceIsAscii) {
firstNonAsciiPos = sourceByteLen;
for (let i = sourceStartPos, e = sourceStartPos + sourceByteLen; i < e; i++)
if (uint8[i] >= 128) {
firstNonAsciiPos = i - sourceStartPos;
break;
}
}
getLoc = getLocInput;
return deserialize(uint32[536870900]);
}
Expand Down Expand Up @@ -5857,11 +5866,12 @@ function deserializeStr(pos) {
len = uint32[pos32 + 2];
if (len === 0) return "";
pos = uint32[pos32];
if (sourceIsAscii && pos >= sourceStartPos) return sourceText.substr(pos - sourceStartPos, len);
// Longer strings use `TextDecoder`
// TODO: Find best switch-over point
if (pos >= sourceStartPos && (sourceIsAscii || pos - sourceStartPos + len <= firstNonAsciiPos))
return sourceText.substr(pos - sourceStartPos, len);
// Use `TextDecoder` for strings longer than 9 bytes.
// For shorter strings, the byte-by-byte loop below avoids native call overhead.
let end = pos + len;
if (len > 50) return decodeStr(uint8.subarray(pos, end));
if (len > 9) return decodeStr(uint8.subarray(pos, end));
// Shorter strings decode by hand to avoid native call
let out = "",
c;
Expand Down
19 changes: 14 additions & 5 deletions napi/parser/src-js/generated/deserialize/js.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
// Auto-generated code, DO NOT EDIT DIRECTLY!
// To edit this generated file you have to edit `tasks/ast_tools/src/generators/raw_transfer.rs`.

let uint8, uint32, float64, sourceText, sourceIsAscii, sourceEndPos;
let uint8, uint32, float64, sourceText, sourceIsAscii, sourceEndPos, firstNonAsciiPos;

const textDecoder = new TextDecoder("utf-8", { ignoreBOM: true }),
decodeStr = textDecoder.decode.bind(textDecoder),
Expand All @@ -20,6 +20,14 @@ function deserializeWith(buffer, sourceTextInput, sourceByteLen, getLocInput, de
float64 = buffer.float64;
sourceText = sourceTextInput;
sourceIsAscii = sourceText.length === sourceByteLen;
if (!sourceIsAscii) {
firstNonAsciiPos = sourceByteLen;
for (let i = 0; i < sourceByteLen; i++)
if (uint8[i] >= 128) {
firstNonAsciiPos = i;
break;
}
}
return deserialize(uint32[536870900]);
}

Expand Down Expand Up @@ -4513,11 +4521,12 @@ function deserializeStr(pos) {
len = uint32[pos32 + 2];
if (len === 0) return "";
pos = uint32[pos32];
if (sourceIsAscii && pos < sourceEndPos) return sourceText.substr(pos, len);
// Longer strings use `TextDecoder`
// TODO: Find best switch-over point
if (pos < sourceEndPos && (sourceIsAscii || pos + len <= firstNonAsciiPos))
return sourceText.substr(pos, len);
// Use `TextDecoder` for strings longer than 9 bytes.
// For shorter strings, the byte-by-byte loop below avoids native call overhead.
let end = pos + len;
if (len > 50) return decodeStr(uint8.subarray(pos, end));
if (len > 9) return decodeStr(uint8.subarray(pos, end));
// Shorter strings decode by hand to avoid native call
let out = "",
c;
Expand Down
18 changes: 14 additions & 4 deletions napi/parser/src-js/generated/deserialize/js_parent.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ let uint8,
sourceText,
sourceIsAscii,
sourceEndPos,
firstNonAsciiPos,
parent = null;

const textDecoder = new TextDecoder("utf-8", { ignoreBOM: true }),
Expand All @@ -26,6 +27,14 @@ function deserializeWith(buffer, sourceTextInput, sourceByteLen, getLocInput, de
float64 = buffer.float64;
sourceText = sourceTextInput;
sourceIsAscii = sourceText.length === sourceByteLen;
if (!sourceIsAscii) {
firstNonAsciiPos = sourceByteLen;
for (let i = 0; i < sourceByteLen; i++)
if (uint8[i] >= 128) {
firstNonAsciiPos = i;
break;
}
}
return deserialize(uint32[536870900]);
}

Expand Down Expand Up @@ -5049,11 +5058,12 @@ function deserializeStr(pos) {
len = uint32[pos32 + 2];
if (len === 0) return "";
pos = uint32[pos32];
if (sourceIsAscii && pos < sourceEndPos) return sourceText.substr(pos, len);
// Longer strings use `TextDecoder`
// TODO: Find best switch-over point
if (pos < sourceEndPos && (sourceIsAscii || pos + len <= firstNonAsciiPos))
return sourceText.substr(pos, len);
// Use `TextDecoder` for strings longer than 9 bytes.
// For shorter strings, the byte-by-byte loop below avoids native call overhead.
let end = pos + len;
if (len > 50) return decodeStr(uint8.subarray(pos, end));
if (len > 9) return decodeStr(uint8.subarray(pos, end));
// Shorter strings decode by hand to avoid native call
let out = "",
c;
Expand Down
19 changes: 14 additions & 5 deletions napi/parser/src-js/generated/deserialize/js_range.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
// Auto-generated code, DO NOT EDIT DIRECTLY!
// To edit this generated file you have to edit `tasks/ast_tools/src/generators/raw_transfer.rs`.

let uint8, uint32, float64, sourceText, sourceIsAscii, sourceEndPos;
let uint8, uint32, float64, sourceText, sourceIsAscii, sourceEndPos, firstNonAsciiPos;

const textDecoder = new TextDecoder("utf-8", { ignoreBOM: true }),
decodeStr = textDecoder.decode.bind(textDecoder),
Expand All @@ -20,6 +20,14 @@ function deserializeWith(buffer, sourceTextInput, sourceByteLen, getLocInput, de
float64 = buffer.float64;
sourceText = sourceTextInput;
sourceIsAscii = sourceText.length === sourceByteLen;
if (!sourceIsAscii) {
firstNonAsciiPos = sourceByteLen;
for (let i = 0; i < sourceByteLen; i++)
if (uint8[i] >= 128) {
firstNonAsciiPos = i;
break;
}
}
return deserialize(uint32[536870900]);
}

Expand Down Expand Up @@ -5063,11 +5071,12 @@ function deserializeStr(pos) {
len = uint32[pos32 + 2];
if (len === 0) return "";
pos = uint32[pos32];
if (sourceIsAscii && pos < sourceEndPos) return sourceText.substr(pos, len);
// Longer strings use `TextDecoder`
// TODO: Find best switch-over point
if (pos < sourceEndPos && (sourceIsAscii || pos + len <= firstNonAsciiPos))
return sourceText.substr(pos, len);
// Use `TextDecoder` for strings longer than 9 bytes.
// For shorter strings, the byte-by-byte loop below avoids native call overhead.
let end = pos + len;
if (len > 50) return decodeStr(uint8.subarray(pos, end));
if (len > 9) return decodeStr(uint8.subarray(pos, end));
// Shorter strings decode by hand to avoid native call
let out = "",
c;
Expand Down
18 changes: 14 additions & 4 deletions napi/parser/src-js/generated/deserialize/js_range_parent.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ let uint8,
sourceText,
sourceIsAscii,
sourceEndPos,
firstNonAsciiPos,
parent = null;

const textDecoder = new TextDecoder("utf-8", { ignoreBOM: true }),
Expand All @@ -26,6 +27,14 @@ function deserializeWith(buffer, sourceTextInput, sourceByteLen, getLocInput, de
float64 = buffer.float64;
sourceText = sourceTextInput;
sourceIsAscii = sourceText.length === sourceByteLen;
if (!sourceIsAscii) {
firstNonAsciiPos = sourceByteLen;
for (let i = 0; i < sourceByteLen; i++)
if (uint8[i] >= 128) {
firstNonAsciiPos = i;
break;
}
}
return deserialize(uint32[536870900]);
}

Expand Down Expand Up @@ -5602,11 +5611,12 @@ function deserializeStr(pos) {
len = uint32[pos32 + 2];
if (len === 0) return "";
pos = uint32[pos32];
if (sourceIsAscii && pos < sourceEndPos) return sourceText.substr(pos, len);
// Longer strings use `TextDecoder`
// TODO: Find best switch-over point
if (pos < sourceEndPos && (sourceIsAscii || pos + len <= firstNonAsciiPos))
return sourceText.substr(pos, len);
// Use `TextDecoder` for strings longer than 9 bytes.
// For shorter strings, the byte-by-byte loop below avoids native call overhead.
let end = pos + len;
if (len > 50) return decodeStr(uint8.subarray(pos, end));
if (len > 9) return decodeStr(uint8.subarray(pos, end));
// Shorter strings decode by hand to avoid native call
let out = "",
c;
Expand Down
19 changes: 14 additions & 5 deletions napi/parser/src-js/generated/deserialize/ts.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
// Auto-generated code, DO NOT EDIT DIRECTLY!
// To edit this generated file you have to edit `tasks/ast_tools/src/generators/raw_transfer.rs`.

let uint8, uint32, float64, sourceText, sourceIsAscii, sourceEndPos;
let uint8, uint32, float64, sourceText, sourceIsAscii, sourceEndPos, firstNonAsciiPos;

const textDecoder = new TextDecoder("utf-8", { ignoreBOM: true }),
decodeStr = textDecoder.decode.bind(textDecoder),
Expand All @@ -20,6 +20,14 @@ function deserializeWith(buffer, sourceTextInput, sourceByteLen, getLocInput, de
float64 = buffer.float64;
sourceText = sourceTextInput;
sourceIsAscii = sourceText.length === sourceByteLen;
if (!sourceIsAscii) {
firstNonAsciiPos = sourceByteLen;
for (let i = 0; i < sourceByteLen; i++)
if (uint8[i] >= 128) {
firstNonAsciiPos = i;
break;
}
}
return deserialize(uint32[536870900]);
}

Expand Down Expand Up @@ -4822,11 +4830,12 @@ function deserializeStr(pos) {
len = uint32[pos32 + 2];
if (len === 0) return "";
pos = uint32[pos32];
if (sourceIsAscii && pos < sourceEndPos) return sourceText.substr(pos, len);
// Longer strings use `TextDecoder`
// TODO: Find best switch-over point
if (pos < sourceEndPos && (sourceIsAscii || pos + len <= firstNonAsciiPos))
return sourceText.substr(pos, len);
// Use `TextDecoder` for strings longer than 9 bytes.
// For shorter strings, the byte-by-byte loop below avoids native call overhead.
let end = pos + len;
if (len > 50) return decodeStr(uint8.subarray(pos, end));
if (len > 9) return decodeStr(uint8.subarray(pos, end));
// Shorter strings decode by hand to avoid native call
let out = "",
c;
Expand Down
18 changes: 14 additions & 4 deletions napi/parser/src-js/generated/deserialize/ts_parent.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ let uint8,
sourceText,
sourceIsAscii,
sourceEndPos,
firstNonAsciiPos,
parent = null;

const textDecoder = new TextDecoder("utf-8", { ignoreBOM: true }),
Expand All @@ -26,6 +27,14 @@ function deserializeWith(buffer, sourceTextInput, sourceByteLen, getLocInput, de
float64 = buffer.float64;
sourceText = sourceTextInput;
sourceIsAscii = sourceText.length === sourceByteLen;
if (!sourceIsAscii) {
firstNonAsciiPos = sourceByteLen;
for (let i = 0; i < sourceByteLen; i++)
if (uint8[i] >= 128) {
firstNonAsciiPos = i;
break;
}
}
return deserialize(uint32[536870900]);
}

Expand Down Expand Up @@ -5385,11 +5394,12 @@ function deserializeStr(pos) {
len = uint32[pos32 + 2];
if (len === 0) return "";
pos = uint32[pos32];
if (sourceIsAscii && pos < sourceEndPos) return sourceText.substr(pos, len);
// Longer strings use `TextDecoder`
// TODO: Find best switch-over point
if (pos < sourceEndPos && (sourceIsAscii || pos + len <= firstNonAsciiPos))
return sourceText.substr(pos, len);
// Use `TextDecoder` for strings longer than 9 bytes.
// For shorter strings, the byte-by-byte loop below avoids native call overhead.
let end = pos + len;
if (len > 50) return decodeStr(uint8.subarray(pos, end));
if (len > 9) return decodeStr(uint8.subarray(pos, end));
// Shorter strings decode by hand to avoid native call
let out = "",
c;
Expand Down
19 changes: 14 additions & 5 deletions napi/parser/src-js/generated/deserialize/ts_range.js
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
// Auto-generated code, DO NOT EDIT DIRECTLY!
// To edit this generated file you have to edit `tasks/ast_tools/src/generators/raw_transfer.rs`.

let uint8, uint32, float64, sourceText, sourceIsAscii, sourceEndPos;
let uint8, uint32, float64, sourceText, sourceIsAscii, sourceEndPos, firstNonAsciiPos;

const textDecoder = new TextDecoder("utf-8", { ignoreBOM: true }),
decodeStr = textDecoder.decode.bind(textDecoder),
Expand All @@ -20,6 +20,14 @@ function deserializeWith(buffer, sourceTextInput, sourceByteLen, getLocInput, de
float64 = buffer.float64;
sourceText = sourceTextInput;
sourceIsAscii = sourceText.length === sourceByteLen;
if (!sourceIsAscii) {
firstNonAsciiPos = sourceByteLen;
for (let i = 0; i < sourceByteLen; i++)
if (uint8[i] >= 128) {
firstNonAsciiPos = i;
break;
}
}
return deserialize(uint32[536870900]);
}

Expand Down Expand Up @@ -5403,11 +5411,12 @@ function deserializeStr(pos) {
len = uint32[pos32 + 2];
if (len === 0) return "";
pos = uint32[pos32];
if (sourceIsAscii && pos < sourceEndPos) return sourceText.substr(pos, len);
// Longer strings use `TextDecoder`
// TODO: Find best switch-over point
if (pos < sourceEndPos && (sourceIsAscii || pos + len <= firstNonAsciiPos))
return sourceText.substr(pos, len);
// Use `TextDecoder` for strings longer than 9 bytes.
// For shorter strings, the byte-by-byte loop below avoids native call overhead.
let end = pos + len;
if (len > 50) return decodeStr(uint8.subarray(pos, end));
if (len > 9) return decodeStr(uint8.subarray(pos, end));
// Shorter strings decode by hand to avoid native call
let out = "",
c;
Expand Down
18 changes: 14 additions & 4 deletions napi/parser/src-js/generated/deserialize/ts_range_parent.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,7 @@ let uint8,
sourceText,
sourceIsAscii,
sourceEndPos,
firstNonAsciiPos,
parent = null;

const textDecoder = new TextDecoder("utf-8", { ignoreBOM: true }),
Expand All @@ -26,6 +27,14 @@ function deserializeWith(buffer, sourceTextInput, sourceByteLen, getLocInput, de
float64 = buffer.float64;
sourceText = sourceTextInput;
sourceIsAscii = sourceText.length === sourceByteLen;
if (!sourceIsAscii) {
firstNonAsciiPos = sourceByteLen;
for (let i = 0; i < sourceByteLen; i++)
if (uint8[i] >= 128) {
firstNonAsciiPos = i;
break;
}
}
return deserialize(uint32[536870900]);
}

Expand Down Expand Up @@ -5966,11 +5975,12 @@ function deserializeStr(pos) {
len = uint32[pos32 + 2];
if (len === 0) return "";
pos = uint32[pos32];
if (sourceIsAscii && pos < sourceEndPos) return sourceText.substr(pos, len);
// Longer strings use `TextDecoder`
// TODO: Find best switch-over point
if (pos < sourceEndPos && (sourceIsAscii || pos + len <= firstNonAsciiPos))
return sourceText.substr(pos, len);
// Use `TextDecoder` for strings longer than 9 bytes.
// For shorter strings, the byte-by-byte loop below avoids native call overhead.
let end = pos + len;
if (len > 50) return decodeStr(uint8.subarray(pos, end));
if (len > 9) return decodeStr(uint8.subarray(pos, end));
// Shorter strings decode by hand to avoid native call
let out = "",
c;
Expand Down
Loading
Loading