mirror of
https://github.com/vercel-labs/scriptc.git
synced 2026-10-28 06:53:42 +08:00
Chris Tate
2840a92124
A while loop that advances a counter through a string, such as
while (pos < text.length) {
const ch = text.charCodeAt(pos);
pos++;
if (ch === 13 && pos < text.length && text.charCodeAt(pos) === 10) pos++;
...
}
kept the counter as a double, so every read converted it and every
charCodeAt took the general index path. The guarded while-counter facts
accepted only a literal or a binding the loop never writes as the
bound. They now also accept the length of a string binding the loop
never writes, which is at most 2^31 - 1 units.
The counter's maximum is also tracked along each path of the body
instead of summing every increment: an increment inside an `if` whose
condition compares the counter below such a bound starts from that
bound, and exits end their path. The second increment above therefore
keeps the counter within int32, and the counter gets int32 storage and
integer charCodeAt reads.
106 lines
2.6 KiB
TypeScript
106 lines
2.6 KiB
TypeScript
// While loops whose counter is bounded by a string's length: line starts
|
||
// over LF, CRLF, CR and Unicode separators, guarded second increments,
|
||
// early exits, non-ASCII and astral text, and the counter after the loop.
|
||
|
||
function lineStarts(text: string): number[] {
|
||
const result: number[] = [];
|
||
let lineStart = 0;
|
||
let pos = 0;
|
||
while (pos < text.length) {
|
||
const ch = text.charCodeAt(pos);
|
||
pos++;
|
||
if (ch === 13) {
|
||
if (pos < text.length && text.charCodeAt(pos) === 10) pos++;
|
||
} else if (ch !== 10 && ch !== 0x2028 && ch !== 0x2029) {
|
||
continue;
|
||
}
|
||
result.push(lineStart);
|
||
lineStart = pos;
|
||
}
|
||
result.push(lineStart);
|
||
return result;
|
||
}
|
||
|
||
function skipSpaces(text: string, start: number): number {
|
||
let pos = start;
|
||
while (pos < text.length && (text.charCodeAt(pos) === 32 || text.charCodeAt(pos) === 9)) pos++;
|
||
return pos;
|
||
}
|
||
|
||
function countWords(text: string): number {
|
||
let words = 0;
|
||
let pos = 0;
|
||
while (pos < text.length) {
|
||
pos = skipSpaces(text, pos);
|
||
if (pos >= text.length) break;
|
||
words++;
|
||
while (pos < text.length && text.charCodeAt(pos) !== 32 && text.charCodeAt(pos) !== 9) pos++;
|
||
}
|
||
return words;
|
||
}
|
||
|
||
function firstDigit(text: string): number {
|
||
let pos = 0;
|
||
while (pos < text.length) {
|
||
const ch = text.charCodeAt(pos);
|
||
if (ch >= 48 && ch <= 57) return pos;
|
||
pos += 1;
|
||
if (ch === 92) pos += 1; // skip an escaped character
|
||
}
|
||
return -pos;
|
||
}
|
||
|
||
function pairs(text: string): string {
|
||
let out = "";
|
||
let pos = 0;
|
||
while (pos < text.length) {
|
||
const ch = text.charCodeAt(pos++);
|
||
if (ch >= 0xd800 && ch <= 0xdbff && pos < text.length) {
|
||
const low = text.charCodeAt(pos);
|
||
if (low >= 0xdc00 && low <= 0xdfff) {
|
||
pos++;
|
||
out += "P";
|
||
continue;
|
||
}
|
||
}
|
||
out += ch < 128 ? "a" : "u";
|
||
}
|
||
return out + ":" + pos;
|
||
}
|
||
|
||
const texts = [
|
||
"",
|
||
"a",
|
||
"\n",
|
||
"\r",
|
||
"\r\n",
|
||
"one\ntwo\nthree",
|
||
"one\r\ntwo\r\nthree\r\n",
|
||
"a\rb\r\rc\r\n\r\nd",
|
||
"x
y
z",
|
||
"é\r\nü\nß\r",
|
||
"😀\r\n😀😀\n",
|
||
"tab\tseparated\t words here",
|
||
"\\1 then 2",
|
||
"no digits",
|
||
"\ud800 lone \udc00 halves 😀",
|
||
];
|
||
for (const text of texts) {
|
||
console.log(
|
||
JSON.stringify(text),
|
||
lineStarts(text).join(","),
|
||
countWords(text),
|
||
firstDigit(text),
|
||
pairs(text),
|
||
skipSpaces(text, 0),
|
||
);
|
||
}
|
||
|
||
// A longer CRLF text, as a checkout with Windows line endings has.
|
||
let big = "";
|
||
for (let i = 0; i < 2000; i++) big += "line " + i + (i % 3 === 0 ? "\r\n" : i % 3 === 1 ? "\n" : "\r");
|
||
const starts = lineStarts(big);
|
||
let sum = 0;
|
||
for (const s of starts) sum += s;
|
||
console.log(starts.length, sum, starts[starts.length - 1], countWords(big), firstDigit(big));
|