mirror of
https://github.com/vercel/next.js.git
synced 2026-09-20 02:25:18 +08:00
dan
7ffacec8ef
This adds more fixtures modeled after Flight payloads from real sites: - Vercel Dashboard-like (very app-y) - React Docs-like after App Router conversion (mostly MDX site) - Vercel Blog-like (passing down data from CMS) (Actual data is randomly generated with a seed) These are simplifications but I tried to incorporate the originals' corresponding quirks. Such as Vercel Dashboard having many client components; syntax highlight with many small spans in React Docs; Vercel Blog currently shipping a load of data unnecessarily on the index page. (The last one is not ideal but I think we should actually benchmark "bad" cases like this too so I kept that.) ### Screenshots <img width="1325" height="1021" alt="Screenshot 2026-07-15 at 04 29 43" src="https://github.com/user-attachments/assets/62c80722-6fd5-4884-89db-106345f6412d" /> <img width="1360" height="994" alt="Screenshot 2026-07-15 at 04 30 21" src="https://github.com/user-attachments/assets/0db93cd8-43ca-41df-b3e2-c422e0c94656" /> <img width="1368" height="991" alt="Screenshot 2026-07-15 at 04 30 43" src="https://github.com/user-attachments/assets/9369e9be-12a4-4a1e-af32-01b6fdd4a457" /> ### Comparison with real payloads ``` === dashboard.html (fixture) vs p-overview.html (real) total KB 208 637 rows (model/I/T/other) 186/48/7/1 240/125/5/27 byte share model/I/T % 92/4/4 36/62/2 median row size B 590 106 max depth 28 53 mean depth 8.4 10.5 elements per KB(model) 14.9 5.2 pure-data byte share % 24 21 client-ref elements % 41 32 objects:elements ratio 1.17 1.23 avg props per element 1.7 3.1 median children fanout 4 4 string bytes % 24 54 median string len B 10 15 row refs per KB 0.9 0.4 encoded scalars per KB 3.5 1.2 undefined markers 347 740 === docs.html (fixture) vs nextjs-docs.html (real) total KB 261 487 rows (model/I/T/other) 58/15/7/1 55/43/2/20 byte share model/I/T % 93/1/6 94/6/0 median row size B 193 340 max depth 27 32 mean depth 21.9 12.3 elements per KB(model) 0.8 0.8 pure-data byte share % 8 9 client-ref elements % 16 33 objects:elements ratio 6.26 4.92 avg props per element 1.7 2.8 median children fanout 4 4 string bytes % 47 64 median string len B 17 35 row refs per KB 0.2 0.1 encoded scalars per KB 7.5 2.9 undefined markers 1949 1377 === blog.html (fixture) vs vercel-blog.html (real) total KB 475 797 rows (model/I/T/other) 41/15/0/1 102/53/7/14 byte share model/I/T % 100/0/0 87/8/5 median row size B 426 505 max depth 34 44 mean depth 9.7 12.2 elements per KB(model) 0.8 1.1 pure-data byte share % 92 85 client-ref elements % 23 33 objects:elements ratio 28.92 16.39 avg props per element 1.9 2.7 median children fanout 3 4 string bytes % 46 48 median string len B 6 9 row refs per KB 0.1 0.1 encoded scalars per KB 0.4 0.6 undefined markers 161 426 ``` --------- Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
55 lines
1.5 KiB
JavaScript
55 lines
1.5 KiB
JavaScript
// Minimal deterministic tokenizer for the docs fixture's code blocks.
|
|
// Produces the span-per-token structure a real syntax highlighter emits,
|
|
// which is where the deep element nesting in real docs payloads comes from.
|
|
const KEYWORDS = new Set([
|
|
'import',
|
|
'export',
|
|
'default',
|
|
'function',
|
|
'return',
|
|
'const',
|
|
'let',
|
|
'if',
|
|
'else',
|
|
'from',
|
|
'new',
|
|
'typeof',
|
|
'null',
|
|
'true',
|
|
'false',
|
|
'async',
|
|
'await',
|
|
])
|
|
|
|
export function tokenize(code) {
|
|
return code.split('\n').map((line) => {
|
|
const tokens = []
|
|
let rest = line
|
|
while (rest.length > 0) {
|
|
let m
|
|
if ((m = rest.match(/^\/\/.*$/))) {
|
|
tokens.push({ t: 'cm', s: m[0] })
|
|
} else if ((m = rest.match(/^'[^']*'|^"[^"]*"|^`[^`]*`/))) {
|
|
tokens.push({ t: 'str', s: m[0] })
|
|
} else if ((m = rest.match(/^[A-Za-z_$][\w$]*/))) {
|
|
tokens.push({
|
|
t: KEYWORDS.has(m[0]) ? 'kw' : /^[A-Z]/.test(m[0]) ? 'cls' : 'id',
|
|
s: m[0],
|
|
})
|
|
} else if ((m = rest.match(/^\d[\d._]*/))) {
|
|
tokens.push({ t: 'num', s: m[0] })
|
|
} else if ((m = rest.match(/^[{}()[\].,;:<>=+\-*/!?&|]+/))) {
|
|
tokens.push({ t: 'pn', s: m[0] })
|
|
} else if ((m = rest.match(/^\s+/))) {
|
|
tokens.push({ t: 'ws', s: m[0] })
|
|
} else {
|
|
tokens.push({ t: 'pl', s: rest[0] })
|
|
rest = rest.slice(1)
|
|
continue
|
|
}
|
|
rest = rest.slice(m[0].length)
|
|
}
|
|
return tokens.length ? tokens : [{ t: 'ws', s: '' }]
|
|
})
|
|
}
|