-
-
Notifications
You must be signed in to change notification settings - Fork 84
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Add a mapper for JavaScirpt strings.
- Loading branch information
Showing
3 changed files
with
184 additions
and
0 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,7 @@ | ||
export interface MappedText { | ||
text: string; | ||
/** | ||
* | ||
*/ | ||
map: number[]; | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,44 @@ | ||
import { mapRawString } from './typescript'; | ||
|
||
describe('mappers typescript', () => { | ||
test.each` | ||
text | expected | ||
${''} | ${''} | ||
${'hello'} | ${'hello'} | ||
${'hello\\x20there'} | ${'hello\x20there'} | ||
${'hello\\u0020there'} | ${'hello\u0020there'} | ||
${'hello\\u{020}there'} | ${'hello\u{020}there'} | ||
${'a\\tb'} | ${'a\tb'} | ||
${'a\\rb'} | ${'a\rb'} | ||
${'a\\nb'} | ${'a\nb'} | ||
${'a\\dd'} | ${'add'} | ||
${'a\\x'} | ${'ax'} | ||
${'a\\xy'} | ${'axy'} | ||
${'a\\x9h'} | ${'ax9h'} | ||
${'a\\u9h'} | ${'au9h'} | ||
${'a\\u{9h}'} | ${'au{9h}'} | ||
`('mapRawString $# [$text]', ({ text, expected }) => { | ||
const r = mapRawString(text); | ||
expect(toCharCodes(r.text)).toBe(toCharCodes(expected)); | ||
expect(r.text).toBe(expected); | ||
}); | ||
|
||
test.each` | ||
text | expected | ||
${''} | ${[]} | ||
${'hello'} | ${[]} | ||
${'hello\\x20there'} | ${[5, 5, 9, 6, 14, 11]} | ||
${'hello\\u0020there'} | ${[5, 5, 11, 6, 16, 11]} | ||
${'hello\\u{020}there'} | ${[5, 5, 12, 6, 17, 11]} | ||
`('mapRawString map $# [$text]', ({ text, expected }) => { | ||
const r = mapRawString(text); | ||
expect(r.map).toEqual(expected); | ||
}); | ||
}); | ||
|
||
function toCharCodes(s: string): string { | ||
return s | ||
.split('') | ||
.map((a) => ('000' + a.charCodeAt(0).toString(16)).slice(-4)) | ||
.join(', '); | ||
} |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Original file line number | Diff line number | Diff line change |
---|---|---|
@@ -0,0 +1,133 @@ | ||
/** | ||
* Mappers for TypeScript and JavaScript | ||
*/ | ||
|
||
import { MappedText } from './types'; | ||
|
||
const hexChars: Record<string, number | undefined> = { | ||
'0': 0, | ||
'1': 1, | ||
'2': 2, | ||
'3': 3, | ||
'4': 4, | ||
'5': 5, | ||
'6': 6, | ||
'7': 7, | ||
'8': 8, | ||
'9': 9, | ||
A: 10, | ||
B: 11, | ||
C: 12, | ||
D: 13, | ||
E: 14, | ||
F: 15, | ||
a: 10, | ||
b: 11, | ||
c: 12, | ||
d: 13, | ||
e: 14, | ||
f: 15, | ||
}; | ||
|
||
const escapeChars: Record<string, string | undefined> = { | ||
t: '\t', | ||
n: '\n', | ||
r: '\r', | ||
b: '\b', | ||
'\\': '\\', | ||
'"': '"', | ||
"'": "'", | ||
}; | ||
|
||
export function mapRawString(text: string): MappedText { | ||
const end = text.length; | ||
let t = ''; | ||
const map: number[] = []; | ||
const isHex = /^[0-9a-fA-F]+$/; | ||
let i: number, j: number; | ||
for (i = 0, j = 0; i < end; ++i) { | ||
let parsed: number; | ||
const ti = text[i]; | ||
if (ti === '\\') { | ||
map.push(i, j); | ||
const tc = text[++i]; | ||
const ec = escapeChars[tc]; | ||
if (ec) { | ||
t += ec; | ||
j += ec.length; | ||
map.push(i, j); | ||
continue; | ||
} | ||
switch (tc) { | ||
case 'u': | ||
{ | ||
let char: string; | ||
let end: number; | ||
if (text[i + 1] !== '{') { | ||
const digits = text.slice(i + 1, i + 5); | ||
parsed = isHex.test(digits) ? parseInt(digits, 16) : NaN; | ||
char = isNaN(parsed) ? '' : String.fromCharCode(parsed); | ||
end = i + 4; | ||
} else { | ||
for (end = i + 2; text[end] in hexChars; ++end) { | ||
// do nothing | ||
} | ||
if (text[end] !== '}') { | ||
char = ''; | ||
} else { | ||
const digits = text.slice(i + 2, end); | ||
parsed = isHex.test(digits) ? parseInt(digits, 16) : NaN; | ||
char = isNaN(parsed) ? '' : String.fromCodePoint(parsed); | ||
} | ||
} | ||
if (!char) { | ||
t += tc; | ||
j += 1; | ||
} else { | ||
t += char; | ||
j += char.length; | ||
i = end; | ||
} | ||
} | ||
break; | ||
case 'x': | ||
{ | ||
const digits = text.slice(i + 1, i + 3); | ||
parsed = isHex.test(digits) ? parseInt(digits, 16) : NaN; | ||
if (isNaN(parsed)) { | ||
// give up, it is not valid | ||
t += tc; | ||
j += 1; | ||
} else { | ||
t += String.fromCharCode(parsed); | ||
i += 2; | ||
++j; | ||
} | ||
} | ||
break; | ||
case '0': | ||
// Deprecated in ES5 | ||
t += '0'; | ||
j += 1; | ||
break; | ||
default: | ||
t += tc; | ||
++j; | ||
break; | ||
} | ||
map.push(i + 1, j); | ||
continue; | ||
} | ||
t += ti; | ||
++j; | ||
} | ||
|
||
if (i !== j || map.length) { | ||
map.push(i, j); | ||
} | ||
|
||
return { | ||
text: t, | ||
map, | ||
}; | ||
} |