fix(pdf): candidates sorted by data offset, JSON depth pre-scan before parse, budget wording; chore(memory): BLK-009 mitigated with gate, EVAL-014, journal, TODO, CLAUDE.md import notes

This commit is contained in:
bchanot committed 2026-10-11 17:31:07 +02:00
1 parent 3a6e92625a
commit 62b2b9d86a
9 files changed
+188 -30

No files matched your search

+71 -17
View File
@@ -261,9 +261,10 @@ type EndstreamFinder = (offset: number) => number
/**
* Searches `endstream` once over the file instead of once per candidate:
* candidates come in offset order, so the last hit serves every offset
* before it and a miss clears the bytes it covered for the next search. An
* offset out of order (never produced today) just restarts the search.
* candidates come in offset order (`embeddedStreamHeads` sorts them), so the
* last hit serves every offset before it and a miss clears the bytes it
* covered for the next search. An offset out of order (never produced since
* the sort) restarts the search: a defensive fallback, never the normal path.
*/
function endstreamFinder(bytes: Uint8Array, end: number): EndstreamFinder {
let lastHit = -1
@@ -302,14 +303,37 @@ function filterOf(dict: string): EmbeddedFileCandidate['filter'] {
return /\/Filter\s*(\[\s*)?\/FlateDecode\b/.test(dict) ? 'FlateDecode' : null
}
/** An `EmbeddedFile` dictionary followed by `stream`, before its data is measured. */
interface StreamHead {
dict: DictSpan
offset: number
}
/**
* Every `/Type /EmbeddedFile` dictionary followed by `stream`, sorted by data
* offset (stable). Nested dictionaries list outermost first, so their offsets
* come out descending and each one would reset the `endstream` finder: 32 of
* them rescanned 16 MiB each (audit of 3a6e926, finding 1). Sorted, the
* finder never restarts.
*/
function embeddedStreamHeads(bytes: Uint8Array, end: number): StreamHead[] {
const heads: StreamHead[] = []
for (const pos of findTypedDicts(bytes, EMBEDDED_FILE, end)) {
const dict = dictAround(bytes, pos, end)
if (!dict) continue
const offset = streamDataOffset(bytes, dict.end, end)
if (offset < 0) continue
heads.push({ dict, offset })
}
return heads.sort((a, b) => a.offset - b.offset)
}
function candidateOf(
bytes: Uint8Array,
dict: DictSpan,
{ dict, offset }: StreamHead,
end: number,
findEndstream: EndstreamFinder,
): Omit<EmbeddedFileCandidate, 'name'> | null {
const offset = streamDataOffset(bytes, dict.end, end)
if (offset < 0) return null
const length =
declaredLength(bytes, dict.text, offset, end) ??
measuredLength(bytes, offset, findEndstream)
@@ -392,20 +416,19 @@ export function hasPdfHeader(bytes: Uint8Array): boolean {
/**
* Every `/Type /EmbeddedFile` stream of the file, named when its Filespec
* is in clear (export without object streams); `osteo-report*` names first,
* then file order. At most MAX_CANDIDATES, within MAX_PDF_BYTES.
* then data offset order. At most MAX_CANDIDATES, within MAX_PDF_BYTES.
*/
export function findEmbeddedFiles(bytes: Uint8Array): EmbeddedFileCandidate[] {
const end = Math.min(bytes.byteLength, MAX_PDF_BYTES)
const names = filespecNames(bytes, end)
const findEndstream = endstreamFinder(bytes, end)
const found: EmbeddedFileCandidate[] = []
for (const pos of findTypedDicts(bytes, EMBEDDED_FILE, end)) {
const dict = dictAround(bytes, pos, end)
if (!dict) continue
const candidate = candidateOf(bytes, dict, end, findEndstream)
for (const head of embeddedStreamHeads(bytes, end)) {
const candidate = candidateOf(bytes, head, end, findEndstream)
if (!candidate) continue
const { objectNumber } = head.dict
const name =
dict.objectNumber === null ? null : (names.get(dict.objectNumber) ?? null)
objectNumber === null ? null : (names.get(objectNumber) ?? null)
found.push({ ...candidate, name })
}
const named = (c: EmbeddedFileCandidate) =>
@@ -440,6 +463,34 @@ function startsJsonObject(data: Uint8Array): boolean {
return data[i] === 0x7b
}
/** The report and its envelope nest under 16 levels; deeper is not ours. */
const MAX_JSON_DEPTH = 64
/**
* Linear bracket-depth count over the raw bytes before `JSON.parse`: a 16 MiB
* document nested thousands deep costs the parser a second and a gigabyte
* (audit of 3a6e926, finding 3). String literals are skipped, their escapes
* honoured; UTF-8 continuation bytes never collide with the ASCII tokens.
*/
function withinJsonDepth(data: Uint8Array): boolean {
let depth = 0
let inString = false
for (let i = 0; i < data.byteLength; i += 1) {
const byte = data[i]!
if (inString) {
if (byte === 0x5c) i += 1 // backslash: the escaped byte is skipped
else if (byte === 0x22) inString = false
continue
}
if (byte === 0x22) inString = true
else if (byte === 0x7b || byte === 0x5b) {
depth += 1
if (depth > MAX_JSON_DEPTH) return false
} else if (byte === 0x7d || byte === 0x5d) depth -= 1
}
return true
}
/** JSON with a numeric `envelopeVersion` or `version`; undefined otherwise. */
function parseVersioned(data: Uint8Array): unknown {
let parsed: unknown
@@ -464,10 +515,13 @@ export interface LocatedAttachment {
/**
* The first candidate whose data is a versioned JSON document, decoded once.
* None: `attachment_stripped` when the stamp is visible, else `no_attachment`.
* One MAX_ATTACHMENT_BYTES budget of examined content (raw or inflated) is
* shared by every candidate: a candidate that does not fit what is left ends
* the search, so 32 crafted streams cost at most one attachment's worth of
* inflation and parsing. A stream cancelled mid-inflation is not charged.
* One MAX_ATTACHMENT_BYTES budget of content (raw or inflated) is shared by
* every candidate: a candidate that does not fit what is left ends the
* search, so at most 16 MiB of candidate content is retained and parsed. A
* cancelled inflation is not charged (audit of 3a6e926, finding 2), so up to
* MAX_CANDIDATES oversized streams may each cost one capped inflation of CPU
* (bounded, no memory retained); charging them would let bombs starve a real
* unnamed attachment placed after them.
*/
export async function locateAttachment(
bytes: Uint8Array,
@@ -478,7 +532,7 @@ export async function locateAttachment(
const data = await candidateBytes(bytes, candidate, budget)
if (!data) continue
budget -= data.byteLength
if (!startsJsonObject(data)) continue
if (!startsJsonObject(data) || !withinJsonDepth(data)) continue
const parsed = parseVersioned(data)
if (parsed !== undefined) return { bytes: data, data: parsed }
}
+83 -2
View File
@@ -3,7 +3,8 @@
* on the frozen fixtures (object-stream layout), crafted layouts (two files,
* indirect `/Length`, `\r\n`, no space after `/Type`), garbage, the keyword
* stamp, the object-stream bomb the reader never inflates, and the candidate
* cost bounds (monotonic `endstream` search, shared 16 MiB budget, `{` check).
* cost bounds (monotonic `endstream` search over offset-sorted candidates,
* shared 16 MiB budget, `{` check, bracket-depth pre-scan before JSON.parse).
*/
import { deflateSync } from 'node:zlib'
import { beforeAll, describe, expect, it, vi } from 'vitest'
@@ -19,7 +20,11 @@ import {
type EmbeddedFileCandidate,
} from '../src'
import { inflateFlate } from '../src/attachment/inflate'
import { decodePdfString, hasArchiveStamp } from '../src/attachment/scan'
import {
decodePdfString,
hasArchiveStamp,
locateAttachment,
} from '../src/attachment/scan'
import { readFixtureBytes } from './helpers/draft'
import {
FIXED_EXPORTED_AT,
@@ -449,6 +454,25 @@ describe('candidate cost bounds (audit M2)', () => {
expect(elapsed).toBeLessThan(1000)
})
it('32 nested EmbeddedFile dicts (descending offsets) without endstream on a 20 MiB file: no candidate, no finder reset', async () => {
// Outermost `/Type` first in the file, its `stream` last: offsets come out
// reversed; the sort by offset keeps the endstream search to one pass.
let nested: Uint8Array = ascii('<< /Type /EmbeddedFile >>\nstream\n')
for (let level = 1; level < 32; level += 1) {
nested = concat([
ascii('<< /Type /EmbeddedFile /A '),
nested,
ascii(' >>\nstream\n'),
])
}
const pdf = craftPdf([ascii('2 0 obj\n'), nested, filled('x', 20 * MiB)])
const { result, elapsed } = await timed('32 nested, no endstream', () =>
findEmbeddedFiles(pdf),
)
expect(result).toEqual([])
expect(elapsed).toBeLessThan(500)
})
it('several indirect /Length streams in a row: each measured to its own endstream', () => {
const payloads = ['{"version":3}', '{"version":4,"x":1}', '{"v":5}']
const pdf = craftPdf(
@@ -501,6 +525,63 @@ describe('candidate cost bounds (audit M2)', () => {
}
})
describe('bracket-depth pre-scan before JSON.parse (audit finding 3)', () => {
const flateObject = (num: number, raw: Uint8Array) => {
const data = new Uint8Array(deflateSync(raw))
return streamObject({
num,
dict: `/Type /EmbeddedFile /Filter /FlateDecode /Length ${data.byteLength}`,
data,
})
}
const withSpy = async (run: () => Promise<void>) => {
const parse = vi.spyOn(JSON, 'parse')
try {
await run()
return parse.mock.calls.length
} finally {
parse.mockRestore()
}
}
it('a 16 KB Flate candidate opening 8 million "[" deep: skipped unparsed, no_attachment fast', async () => {
const raw = concat([ascii('{"version":3,"x":'), filled('[', 8_000_000)])
const object = flateObject(2, raw)
expect(object.byteLength).toBeLessThan(16 * 1024)
const calls = await withSpy(async () => {
const { elapsed } = await timed('8M-deep candidate', () =>
rejects(craftPdf([object]), 'no_attachment'),
)
expect(elapsed).toBeLessThan(100)
})
expect(calls).toBe(0)
})
it('2000 "[" inside a string with escaped quotes and backslashes: not rejected, parsed once', async () => {
const text = `{"version":3,"note":"\\"${'['.repeat(2000)}\\\\ \\" [[[["}`
const pdf = craftPdf([
streamObject({
num: 2,
dict: `/Type /EmbeddedFile /Length ${text.length}`,
data: ascii(text),
}),
])
const calls = await withSpy(async () => {
const located = await locateAttachment(pdf)
expect(located.data).toMatchObject({ version: 3 })
})
expect(calls).toBe(1)
})
it('the real envelope passes the pre-scan and is parsed once', async () => {
const calls = await withSpy(async () => {
const located = await locateAttachment(exported)
expect(located.data).toMatchObject({ envelopeVersion: 1 })
})
expect(calls).toBe(1)
})
})
describe('one 16 MiB budget shared by every candidate', () => {
const garbageObject = (num: number) =>
streamObject({