Skip to content

Tokenize hexadecimal string sequences + minor enhancements #970

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 4 commits into from
Nov 23, 2019
Merged

Tokenize hexadecimal string sequences + minor enhancements #970

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
5cb5779
Tokenize hexadecimal string sequences
MaxGraey Nov 22, 2019
3980190
refactor
MaxGraey Nov 22, 2019
a7cfe07
minor optimizations for tokenizer
MaxGraey Nov 23, 2019
4769e5d
refactoring
MaxGraey Nov 23, 2019
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
44 changes: 22 additions & 22 deletions src/tokenizer.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1146,6 +1146,9 @@ export class Tokenizer extends DiagnosticEmitter {
}
return this.readUnicodeEscape(); // \uDDDD
}
case CharCode.x: {
return this.readHexadecimalEscape(); // \xDD
}
case CharCode.CARRIAGERETURN: {
if (
this.pos < end &&
Expand Down Expand Up @@ -1237,21 +1240,18 @@ export class Tokenizer extends DiagnosticEmitter {
testInteger(): bool {
var end = this.end;
var text = this.source.text;
if (this.pos + 1 < end && text.charCodeAt(this.pos) == CharCode._0) {
switch (text.charCodeAt(this.pos + 2)) {
var pos = this.pos;
if (pos + 1 < end && text.charCodeAt(pos) == CharCode._0) {
switch (text.charCodeAt(pos + 2) | 32) {
case CharCode.x:
case CharCode.X:
case CharCode.b:
case CharCode.B:
case CharCode.o:
case CharCode.O: return true;
case CharCode.o: return true;
}
}
var pos = this.pos;
while (pos < end) {
let c = text.charCodeAt(pos);
if (c == CharCode.DOT || c == CharCode.e || c == CharCode.E) return false;
if ((c < CharCode._0 || c > CharCode._9) && c != CharCode._) break;
if (c == CharCode.DOT || (c | 32) == CharCode.e) return false;
if (c != CharCode._ && (c < CharCode._0 || c > CharCode._9)) break;
// does not validate separator placement (this is done in readXYInteger)
pos++;
}
Expand All @@ -1261,19 +1261,16 @@ export class Tokenizer extends DiagnosticEmitter {
readInteger(): I64 {
var text = this.source.text;
if (this.pos + 2 < this.end && text.charCodeAt(this.pos) == CharCode._0) {
switch (text.charCodeAt(this.pos + 1)) {
case CharCode.x:
case CharCode.X: {
switch (text.charCodeAt(this.pos + 1) | 32) {
case CharCode.x: {
this.pos += 2;
return this.readHexInteger();
}
case CharCode.b:
case CharCode.B: {
case CharCode.b: {
this.pos += 2;
return this.readBinaryInteger();
}
case CharCode.o:
case CharCode.O: {
case CharCode.o: {
this.pos += 2;
return this.readOctalInteger();
}
Expand Down Expand Up @@ -1517,7 +1514,7 @@ export class Tokenizer extends DiagnosticEmitter {
}
if (this.pos < end) {
let c = text.charCodeAt(this.pos);
if (c == CharCode.e || c == CharCode.E) {
if ((c | 32) == CharCode.e) {
if (
++this.pos < end &&
(c = text.charCodeAt(this.pos)) == CharCode.MINUS || c == CharCode.PLUS &&
Expand All @@ -1537,8 +1534,7 @@ export class Tokenizer extends DiagnosticEmitter {
throw new Error("not implemented"); // TBD
}

readUnicodeEscape(): string {
var remain = 4;
readHexadecimalEscape(remain: i32 = 2): string {
var value = 0;
var end = this.end;
var text = this.source.text;
Expand Down Expand Up @@ -1569,6 +1565,10 @@ export class Tokenizer extends DiagnosticEmitter {
return String.fromCharCode(value);
}

readUnicodeEscape(): string {
return this.readHexadecimalEscape(4);
}

private readExtendedUnicodeEscape(): string {
var start = this.pos;
var value = this.readHexInteger();
Expand Down Expand Up @@ -1603,11 +1603,11 @@ export class Tokenizer extends DiagnosticEmitter {
}

if (invalid) return "";
return value32 < 65536
return value32 < 0x10000
? String.fromCharCode(value32)
: String.fromCharCode(
((value32 - 65536) >>> 10) + 0xD800,
((value32 - 65536) & 1023) + 0xDC00
((value32 - 0x10000) >>> 10) | 0xD800,
((value32 - 0x10000) & 1023) | 0xDC00
);
}

Expand Down
Loading