Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Worph
|
862f73d26d | ||
|
Worph
|
b855adb822 | ||
|
Worph
|
9bf2e623f9 | ||
|
Worph
|
7bdb54f9a7 |
@@ -1,9 +1,23 @@
|
||||
/**
|
||||
* The `fileType` vocabulary — see METADATA_KEYS.md §1.
|
||||
*
|
||||
* ⚠ INVARIANT: a value belongs here only if an `(extension, mimeType)` lookup
|
||||
* can decide it on its own. Nothing that requires knowing what the content
|
||||
* *is* goes in this field — that is `contentKind`'s job — and nothing that
|
||||
* decides *which app gets the record* depends on it — that is `domain`'s job
|
||||
* (METADATA_KEYS.md §14.16).
|
||||
*
|
||||
* `card` is the one deliberate exception: it describes no bytes at all and is
|
||||
* therefore never produced by the tables here, only stamped by a card feeder.
|
||||
*/
|
||||
export type SimpleFileType =
|
||||
'audio'
|
||||
| 'video'
|
||||
| 'image'
|
||||
| 'document'
|
||||
| 'archive'
|
||||
| 'subtitle'
|
||||
| 'torrent'
|
||||
| 'card'
|
||||
| 'other'
|
||||
| 'undefined';
|
||||
@@ -0,0 +1,125 @@
|
||||
/**
|
||||
* `contentKind` → `domain` / `workForm` — the routing tables from
|
||||
* METADATA_KEYS.md §1.
|
||||
*
|
||||
* `domain` answers "which application is this record destined for?" and is the
|
||||
* key every client filters its catalogue on — **one value per app**, no
|
||||
* alternation. `workForm` answers the other question the old `film`/`tv` split
|
||||
* was secretly encoding: is this work complete in itself, or one instalment of
|
||||
* a run? It is cross-domain, so a comic issue is `serial` in `literature`
|
||||
* exactly as an episode is `serial` in `screen`.
|
||||
*
|
||||
* Both are **stored, not derived on read**: that is what lets the `contentKind`
|
||||
* vocabulary stay open, because a peer that has never heard of a kind still
|
||||
* routes the record correctly without having to interpret the token.
|
||||
*
|
||||
* ⚠ This binding is **permanent and one-way**. Add kinds freely; never re-map
|
||||
* an existing kind to a different domain. Because the value is stored, two
|
||||
* peers on different versions that disagree about where a kind belongs produce
|
||||
* a split-brain that redeploying cannot heal — the wrong domain is already
|
||||
* written into records across the mesh. If a kind has to move, mint a new kind.
|
||||
* The `film`+`tv` → `screen` merge (METADATA_KEYS.md §14.17) is the one
|
||||
* deliberate exception, taken once and paid for with a corpus sweep.
|
||||
*
|
||||
* ⚠ Mirror of the Rust table in `meta-feeder-sdk::domain`. Edit both together.
|
||||
*/
|
||||
export type Domain =
|
||||
'screen'
|
||||
| 'music'
|
||||
| 'literature'
|
||||
| 'science';
|
||||
|
||||
/** Is the work complete in itself, or one instalment of a run? */
|
||||
export type WorkForm = 'standalone' | 'serial';
|
||||
|
||||
/**
|
||||
* The one-way binding. A kind that is absent here has no domain, which means
|
||||
* the record is **not independently routable** — correct for sidecars
|
||||
* (subtitles, artwork) and for un-anchored hits, a producer bug for anything
|
||||
* else.
|
||||
*
|
||||
* ⚠ `pack` is deliberately absent: a season pack and an album release are the
|
||||
* same structural thing, so the kind alone cannot tell `screen` from `music`.
|
||||
* The writer stamps `pack`'s domain from its own context — see
|
||||
* {@link domainForContentKind}'s contract.
|
||||
*
|
||||
* ⚠ `podcast` / `podcastEpisode` are absent too: the `spoken` domain was
|
||||
* retired unused, and the change that first *writes* those kinds picks their
|
||||
* domain.
|
||||
*/
|
||||
export const domainByContentKind: { [contentKind: string]: Domain } = {
|
||||
// screen — films and serials alike; the split lives in workFormByContentKind
|
||||
movie: 'screen',
|
||||
series: 'screen',
|
||||
episode: 'screen',
|
||||
// music
|
||||
track: 'music',
|
||||
album: 'music',
|
||||
artist: 'music',
|
||||
musicVideo: 'music',
|
||||
djMix: 'music',
|
||||
liveSet: 'music',
|
||||
// literature
|
||||
book: 'literature',
|
||||
// An audiobook's identity is the book — same author, same ISBN family,
|
||||
// same series as the ebook — so meta-read can group the two editions on
|
||||
// one page. The player does not decide the domain.
|
||||
audiobook: 'literature',
|
||||
comic: 'literature',
|
||||
manga: 'literature',
|
||||
magazine: 'literature',
|
||||
// science
|
||||
paper: 'science',
|
||||
};
|
||||
|
||||
/**
|
||||
* The `workForm` twin of {@link domainByContentKind}.
|
||||
*
|
||||
* ⚠ `pack` is absent for the same reason: a season pack is `serial`, an album
|
||||
* release is `standalone`, and only the writer knows which.
|
||||
*/
|
||||
export const workFormByContentKind: { [contentKind: string]: WorkForm } = {
|
||||
// screen
|
||||
movie: 'standalone',
|
||||
series: 'serial',
|
||||
episode: 'serial',
|
||||
// music — an album is a closed work, not an ongoing run, so every rung of
|
||||
// the music ladder is standalone.
|
||||
track: 'standalone',
|
||||
album: 'standalone',
|
||||
artist: 'standalone',
|
||||
musicVideo: 'standalone',
|
||||
djMix: 'standalone',
|
||||
liveSet: 'standalone',
|
||||
// literature — the split that proves workForm is not a screen-only axis.
|
||||
book: 'standalone',
|
||||
audiobook: 'standalone',
|
||||
comic: 'serial',
|
||||
manga: 'serial',
|
||||
magazine: 'serial',
|
||||
// science
|
||||
paper: 'standalone',
|
||||
};
|
||||
|
||||
/**
|
||||
* Resolve the domain a `contentKind` belongs to.
|
||||
*
|
||||
* Returns `undefined` for `pack` (not derivable from the kind — the writer
|
||||
* supplies it), for sidecar/format kinds that route nowhere, and for any kind
|
||||
* this build has never heard of. A caller that already knows the domain from
|
||||
* its own context must prefer that over this table.
|
||||
*/
|
||||
export function domainForContentKind(contentKind: string | undefined | null): Domain | undefined {
|
||||
if (!contentKind) return undefined;
|
||||
return domainByContentKind[contentKind.trim()];
|
||||
}
|
||||
|
||||
/**
|
||||
* Resolve the work form a `contentKind` sits on. Same contract as
|
||||
* {@link domainForContentKind}: `undefined` means "not derivable", never a
|
||||
* guess. Whoever writes `contentKind` writes both of these in the same breath.
|
||||
*/
|
||||
export function workFormForContentKind(contentKind: string | undefined | null): WorkForm | undefined {
|
||||
if (!contentKind) return undefined;
|
||||
return workFormByContentKind[contentKind.trim()];
|
||||
}
|
||||
@@ -1,5 +1,14 @@
|
||||
import {SimpleFileType} from "../SimpleFileType.js";
|
||||
|
||||
/**
|
||||
* Extension → `fileType`. Half of the canonical classification table
|
||||
* documented in METADATA_KEYS.md §1 (the other half is
|
||||
* {@link mimeTypeMappings}); this file is the source of truth and the doc
|
||||
* mirrors it.
|
||||
*
|
||||
* An extension absent from this map resolves to `other`, which makes the file
|
||||
* invisible to every typed query — so a missing entry is not a cosmetic gap.
|
||||
*/
|
||||
export const extensionMappings: { [key: string]: SimpleFileType } = {
|
||||
// Audio
|
||||
'mp3': 'audio',
|
||||
@@ -7,7 +16,19 @@ export const extensionMappings: { [key: string]: SimpleFileType } = {
|
||||
'flac': 'audio',
|
||||
'aac': 'audio',
|
||||
'ogg': 'audio',
|
||||
'oga': 'audio',
|
||||
'opus': 'audio',
|
||||
'm4a': 'audio',
|
||||
// `m4b` is the audiobook container — without it `contentKind=audiobook`
|
||||
// had no extension that resolved to `audio` (METADATA_KEYS.md §14.15).
|
||||
'm4b': 'audio',
|
||||
'wma': 'audio',
|
||||
'aiff': 'audio',
|
||||
'aif': 'audio',
|
||||
'ape': 'audio',
|
||||
'wv': 'audio',
|
||||
'dsf': 'audio',
|
||||
'mka': 'audio',
|
||||
// Video
|
||||
'mp4': 'video',
|
||||
'mkv': 'video',
|
||||
@@ -27,6 +48,8 @@ export const extensionMappings: { [key: string]: SimpleFileType } = {
|
||||
'ts': 'video',
|
||||
'vob': 'video',
|
||||
'ogm': 'video',
|
||||
'ogv': 'video',
|
||||
'asf': 'video',
|
||||
'divx': 'video',
|
||||
'xvid': 'video',
|
||||
// Document
|
||||
@@ -37,31 +60,64 @@ export const extensionMappings: { [key: string]: SimpleFileType } = {
|
||||
'pptx': 'document',
|
||||
'xls': 'document',
|
||||
'xlsx': 'document',
|
||||
'odt': 'document',
|
||||
'ods': 'document',
|
||||
'odp': 'document',
|
||||
'txt': 'document',
|
||||
'md': 'document',
|
||||
'rtf': 'document',
|
||||
// Images (are document)
|
||||
'jpg': 'document',
|
||||
'jpeg': 'document',
|
||||
'png': 'document',
|
||||
'gif': 'document',
|
||||
'bmp': 'document',
|
||||
'tif': 'document',
|
||||
'tiff': 'document',
|
||||
'svg': 'document',
|
||||
'webp': 'document',
|
||||
// Document — literature formats. Their absence blocked meta-read outright
|
||||
// (METADATA_KEYS.md §14.15).
|
||||
'epub': 'document',
|
||||
'mobi': 'document',
|
||||
'azw': 'document',
|
||||
'azw3': 'document',
|
||||
'djvu': 'document',
|
||||
// Images
|
||||
// ⚠ These used to map to `document` ("Images (are document)"), which meant
|
||||
// the `image` bucket was unreachable from this table while Rust feeders
|
||||
// wrote it anyway. A consumer asking for documents must not receive
|
||||
// posters — see METADATA_KEYS.md §14.15.
|
||||
'jpg': 'image',
|
||||
'jpeg': 'image',
|
||||
'png': 'image',
|
||||
'gif': 'image',
|
||||
'bmp': 'image',
|
||||
'tif': 'image',
|
||||
'tiff': 'image',
|
||||
'svg': 'image',
|
||||
'webp': 'image',
|
||||
'avif': 'image',
|
||||
'heic': 'image',
|
||||
'heif': 'image',
|
||||
'ico': 'image',
|
||||
// Archive
|
||||
'zip': 'archive',
|
||||
'rar': 'archive',
|
||||
'7z': 'archive',
|
||||
'tar': 'archive',
|
||||
'tgz': 'archive',
|
||||
'gz': 'archive',
|
||||
'bz2': 'archive',
|
||||
'xz': 'archive',
|
||||
'zst': 'archive',
|
||||
// Archive — comic containers. A `.cbz` is literally a zip, so `archive` is
|
||||
// the honest byte-level answer; `contentKind=comic` + `domain=literature`
|
||||
// are what route it to meta-read (METADATA_KEYS.md §14.16).
|
||||
'cbz': 'archive',
|
||||
'cbr': 'archive',
|
||||
//subtitles
|
||||
'srt': 'subtitle',
|
||||
'sub': 'subtitle',
|
||||
'sbv': 'subtitle',
|
||||
'vtt': 'subtitle',
|
||||
// ⚠ ASS/SSA is what meta-watch renders through libass — the client's
|
||||
// primary subtitle format was the one this classifier did not know.
|
||||
'ass': 'subtitle',
|
||||
'ssa': 'subtitle',
|
||||
'ttml': 'subtitle',
|
||||
'dfxp': 'subtitle',
|
||||
'smi': 'subtitle',
|
||||
//torrent
|
||||
'torrent': 'torrent',
|
||||
};
|
||||
@@ -1,11 +1,32 @@
|
||||
import {SimpleFileType} from "../SimpleFileType.js";
|
||||
|
||||
/**
|
||||
* MIME type → `fileType`. The other half of the canonical classification
|
||||
* table (see {@link extensionMappings} and METADATA_KEYS.md §1).
|
||||
*
|
||||
* ⚠ Resolution is conservative on purpose: when a sniffed MIME maps to a
|
||||
* definite value that *disagrees* with the extension's value,
|
||||
* `FileTypeConfigurable.getFileType` returns `undefined` rather than guessing
|
||||
* — a wrong `fileType` routes a file to a handler that cannot open it. Adding
|
||||
* a mapping here therefore also creates a new way to disagree; only add ones
|
||||
* whose extension counterpart agrees.
|
||||
*/
|
||||
export const mimeTypeMappings: { [key: string]: SimpleFileType } = {
|
||||
'text/plain': 'undefined',//text could be anything document or subtitle or other
|
||||
// Audio MIME types
|
||||
'audio/mpeg': 'audio',
|
||||
'audio/wav': 'audio',
|
||||
'audio/x-wav': 'audio',
|
||||
'audio/flac': 'audio',
|
||||
'audio/ogg': 'audio',
|
||||
'audio/opus': 'audio',
|
||||
'audio/aac': 'audio',
|
||||
// ftyp brands `M4A `/`M4B ` sniff as audio/mp4 while a real video mp4
|
||||
// sniffs as video/mp4, so this does not collide with the `mp4` extension.
|
||||
'audio/mp4': 'audio',
|
||||
'audio/x-ms-wma': 'audio',
|
||||
'audio/x-aiff': 'audio',
|
||||
'audio/x-ape': 'audio',
|
||||
// Video MIME types
|
||||
'video/mp4': 'video',
|
||||
'video/mpeg': 'video',
|
||||
@@ -13,8 +34,12 @@ export const mimeTypeMappings: { [key: string]: SimpleFileType } = {
|
||||
'video/x-msvideo': 'video',
|
||||
'video/x-flv': 'video',
|
||||
'video/x-ms-wmv': 'video',
|
||||
'video/x-ms-asf': 'video',
|
||||
'video/x-matroska': 'video',
|
||||
'video/webm': 'video',
|
||||
'video/ogg': 'video',
|
||||
'video/3gpp': 'video',
|
||||
'video/mp2t': 'video',
|
||||
// Document MIME types
|
||||
'application/pdf': 'document',
|
||||
'application/msword': 'document',
|
||||
@@ -23,20 +48,47 @@ export const mimeTypeMappings: { [key: string]: SimpleFileType } = {
|
||||
'application/vnd.openxmlformats-officedocument.presentationml.presentation': 'document',
|
||||
'application/vnd.ms-excel': 'document',
|
||||
'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet': 'document',
|
||||
'image/jpeg': 'document',
|
||||
'image/png': 'document',
|
||||
'image/gif': 'document',
|
||||
'application/vnd.oasis.opendocument.text': 'document',
|
||||
'application/vnd.oasis.opendocument.spreadsheet': 'document',
|
||||
'application/vnd.oasis.opendocument.presentation': 'document',
|
||||
'application/rtf': 'document',
|
||||
// Literature containers (METADATA_KEYS.md §14.15)
|
||||
'application/epub+zip': 'document',
|
||||
'application/x-mobipocket-ebook': 'document',
|
||||
'image/vnd.djvu': 'document',
|
||||
'text/markdown': 'document',
|
||||
// Image MIME types — no longer folded into `document` (§14.15)
|
||||
'image/jpeg': 'image',
|
||||
'image/png': 'image',
|
||||
'image/gif': 'image',
|
||||
'image/webp': 'image',
|
||||
'image/bmp': 'image',
|
||||
'image/tiff': 'image',
|
||||
'image/svg+xml': 'image',
|
||||
'image/avif': 'image',
|
||||
'image/heic': 'image',
|
||||
'image/x-icon': 'image',
|
||||
// Archive MIME types
|
||||
'application/zip': 'archive',
|
||||
'application/x-rar-compressed': 'archive',
|
||||
'application/vnd.rar': 'archive',
|
||||
'application/x-7z-compressed': 'archive',
|
||||
'application/gzip': 'archive',
|
||||
'application/x-bzip2': 'archive',
|
||||
'application/x-xz': 'archive',
|
||||
'application/zstd': 'archive',
|
||||
'application/x-tar': 'archive',
|
||||
// Comic containers sniff as their underlying zip/rar, which agrees with
|
||||
// the `cbz`/`cbr` extensions — both say `archive`.
|
||||
'application/vnd.comicbook+zip': 'archive',
|
||||
'application/vnd.comicbook-rar': 'archive',
|
||||
//torrent
|
||||
'application/x-bittorrent': 'torrent',
|
||||
//subtitles
|
||||
'text/vtt': 'subtitle',
|
||||
'text/srt': 'subtitle',
|
||||
'text/ssa': 'subtitle',
|
||||
'text/x-ssa': 'subtitle',
|
||||
'text/sub': 'subtitle',
|
||||
'application/x-subrip': 'subtitle',
|
||||
};
|
||||
@@ -13,6 +13,7 @@ export * from './tools/StringArrayOperation.js';
|
||||
export * from './tools/TwoStringsOperation.js';
|
||||
|
||||
export * from './config/AnimeKeywords.js';
|
||||
export * from './config/DomainMapping.js';
|
||||
export * from './config/ExtentionsMapping.js';
|
||||
export * from './config/KeywordsArray.js';
|
||||
export * from './config/MimeTypeMapping.js';
|
||||
|
||||
@@ -1,10 +1,17 @@
|
||||
/**
|
||||
* Multicodec / multihash codes for every digest meta-hash can compute.
|
||||
*
|
||||
* Source of truth for these numbers, mirrored in:
|
||||
* Source of truth for these numbers. The same codes appear in the CID utility
|
||||
* RANK, which is a separate thing this file does not implement:
|
||||
* - `packages/meta-core/internal/cid/rank.go`
|
||||
* - the `cid_rank.rs` in each of meta-search and meta-share
|
||||
* - `/cid-rank-vectors.json` (the golden fixture that pins them all together)
|
||||
* - `/cid-rank-vectors.json` (the golden fixture pinning those three together)
|
||||
*
|
||||
* ⚠ This package used to vendor that fixture at `src/tests/cid-rank-vectors.json`
|
||||
* and no test ever loaded it, so every vector added cost a commit here for
|
||||
* nothing. Removed 2026-09-09. If a TypeScript rank implementation is ever
|
||||
* written, re-add the path to `scripts/check-cid-vectors.sh` *and* a test that
|
||||
* asserts it — a vendored fixture nobody reads is not a guard.
|
||||
*
|
||||
* ⚠ meta-hash encodes `codec == multihash code` (see `ComputeHash.cidFinalize`:
|
||||
* `CID.createV1(code, create(code, digest))`), whereas the fullhash plugin and
|
||||
|
||||
@@ -1,166 +0,0 @@
|
||||
{
|
||||
"$schema": "cid-rank-vectors/v1",
|
||||
"$comment": [
|
||||
"CANONICAL golden vectors for the CID utility rank. THE single source of truth.",
|
||||
"The rank decides which of a record's several CIDs is elected canonical - the cid a",
|
||||
"record is advertised and addressed by. It is reimplemented in Go, 2x Rust and 3x TS;",
|
||||
"they cannot share code (independent submodules, no cargo path-dep). These vectors are",
|
||||
"the only thing holding them in sync: every implementation's test suite loads this file.",
|
||||
"",
|
||||
"This file is VENDORED into each consuming submodule (submodule CI cannot read above its",
|
||||
"own tree). scripts/check-cid-vectors.sh diffs every copy against this one.",
|
||||
"",
|
||||
"Ranking is by UTILITY for external retrieval, not cryptographic strength.",
|
||||
"Ties break on the lexicographically smaller cid, so the election is deterministic",
|
||||
"across peers and does not churn.",
|
||||
"",
|
||||
"See METADATA_KEYS.md section 2/14.13 and docs/cid-formats.md."
|
||||
],
|
||||
"ladder": {
|
||||
"40": "dag-pb (IPFS block)",
|
||||
"30": "sha2-256 / sha3-256 / sha3-384 - real content digests",
|
||||
"25": "nzb-posting - content-derived (Message-ID set digest), but not itself fetchable",
|
||||
"20": "BitTorrent infohashes - swarm interop",
|
||||
"10": "midhash256 - the record address",
|
||||
"5": "opaque locators (nzb-release, url, card) - never outrank a real digest",
|
||||
"0": "weak/unknown digests, unparseable input"
|
||||
},
|
||||
"tieBreak": "lexicographically smaller cid wins",
|
||||
"vectors": [
|
||||
{
|
||||
"name": "ipfs-dagpb",
|
||||
"cid": "bafybeiaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 40,
|
||||
"note": "dag-pb codec 0x70 - chunked IPFS file, broadest network reach"
|
||||
},
|
||||
{
|
||||
"name": "sha2-256-raw-codec",
|
||||
"cid": "bafkreiaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 30,
|
||||
"note": "fullhash/gateway convention: raw codec 0x55, mh names the algo"
|
||||
},
|
||||
{
|
||||
"name": "sha2-256-codec-eq-mh",
|
||||
"cid": "baejbeibku6ua2l6r5olnggx4pto2sii2s5jeeawgh4cbkhlbmp52gudbua",
|
||||
"rank": 30,
|
||||
"note": "REAL meta-hash fixture; meta-hash sets codec == mh"
|
||||
},
|
||||
{
|
||||
"name": "sha3-256",
|
||||
"cid": "baelbmidner7x3dd7t2kldh6wiq4w6lsye7qrwo6uoqot2t52zkhqk56fnq",
|
||||
"rank": 30,
|
||||
"note": "REAL meta-hash fixture"
|
||||
},
|
||||
{
|
||||
"name": "sha3-384",
|
||||
"cid": "baekrkmeglipkjf33exqexdvijl4twipruay4wsbvt44akce43lq5rgccxgr7v6dwksmj3sxedakevc53g6ga",
|
||||
"rank": 30,
|
||||
"note": "REAL meta-hash fixture"
|
||||
},
|
||||
{
|
||||
"name": "nzb-posting",
|
||||
"cid": "bagbsaeraaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 25,
|
||||
"note": "codec 0x1003 + REAL sha2-256 multihash (0x12) over the normalised, sorted Message-ID set - NOT a locator, so it sits ABOVE tier 5, but it addresses no fetchable block (bitswap can never satisfy a want for it - the digest is over an id set, not over any block's bytes), so it stays BELOW a real content digest (30): once meta-share materialises the media and re-seeds it, that genuine sha2-256 cid must win the canonical election, not this one. Rank MUST match on codec BEFORE falling through to the mh switch, or this scores 30 (same trap as nzb-release/url, in reverse: those need a codec check because their mh is identity 0x00; this needs one because its mh is REAL sha2-256 and would otherwise tie with tier 30)."
|
||||
},
|
||||
{
|
||||
"name": "btih-v2-codec-eq-mh",
|
||||
"cid": "bag3sdnzbeaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 20,
|
||||
"note": "meta-hash encoder convention"
|
||||
},
|
||||
{
|
||||
"name": "btih-v2-raw-codec",
|
||||
"cid": "bafk3oijaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 20,
|
||||
"note": "fullhash encoder convention - SAME tier, both conventions must match"
|
||||
},
|
||||
{
|
||||
"name": "btih-v1-file",
|
||||
"cid": "bagasbajacqaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 20,
|
||||
"note": "gateway per-file BitTorrent v1"
|
||||
},
|
||||
{
|
||||
"name": "btih-v2-file",
|
||||
"cid": "bagbcbaraeaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 20,
|
||||
"note": "gateway per-file BitTorrent v2"
|
||||
},
|
||||
{
|
||||
"name": "midhash256-codec-eq-mh",
|
||||
"cid": "bagacbabaeaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 10,
|
||||
"note": "the record address; internally meaningful, externally invisible"
|
||||
},
|
||||
{
|
||||
"name": "midhash256-raw-codec",
|
||||
"cid": "bafkyaibaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 10
|
||||
},
|
||||
{
|
||||
"name": "nzb-release-locator",
|
||||
"cid": "bagcsaaazcbqxa2jonz5gez3fmvvs42lomzx55ln657fp4aab",
|
||||
"rank": 5,
|
||||
"note": "codec 0x1005 + IDENTITY multihash 0x00. The locator code is in the CODEC slot, not the mh slot - rank MUST match on codec. Tier 5 = below midhash: a locator never outranks a real digest, it wins only as a record's sole cid."
|
||||
},
|
||||
{
|
||||
"name": "url-locator",
|
||||
"cid": "bagdcaaaznb2hi4dthixs6zlymfwxa3dffzxxezzpmexhazdg",
|
||||
"rank": 5,
|
||||
"note": "codec 0x1006 + IDENTITY multihash 0x00. Same tier/reasoning as nzb-release."
|
||||
},
|
||||
{
|
||||
"name": "card-locator",
|
||||
"cid": "bagdsaaanar2g2zdcor3duojvgq3ts",
|
||||
"rank": 5,
|
||||
"note": "codec 0x1007 + IDENTITY multihash 0x00, digest = varint(len(source)) || source || id — here (\"tmdb\",\"tv:95479\"). Same codec-slot rule as nzb-release/url: match on the CODEC, never the mh. The limit case of the family — the only CID in MetaMesh with NO bytes behind it anywhere, ever: it addresses a *work* (a series, a film), not a file, so the byte path 404s by design and bitswap never offers it (seeding is gated on sha2-256). Tier 5 is load-bearing for the planned cross-source merge: one card record may carry BOTH a TMDB and a MyAnimeList locator, and if a real card body is ever added (see card-tier-search.md §4.3) its sha2-256 must win the canonical election over both locators without any addressing change. Ranking it 0 instead would still lose to a digest, but would put the implementations back out of agreement — which is the exact failure this fixture exists to prevent."
|
||||
},
|
||||
{
|
||||
"name": "sha1",
|
||||
"cid": "baeircff3eqvxxaqqot2lt242stkdtk3gq4c2vra",
|
||||
"rank": 0,
|
||||
"note": "REAL meta-hash fixture; weak digest"
|
||||
},
|
||||
{
|
||||
"name": "md5",
|
||||
"cid": "bahkqdvibcatpcfl7ine2n625eb5ml5mzkfaa",
|
||||
"rank": 0,
|
||||
"note": "REAL meta-hash fixture; weak digest"
|
||||
},
|
||||
{
|
||||
"name": "crc32",
|
||||
"cid": "bagzafmqcathsbnrk",
|
||||
"rank": 0,
|
||||
"note": "REAL meta-hash fixture; weak digest"
|
||||
},
|
||||
{
|
||||
"name": "bt-pieces-root",
|
||||
"cid": "bafkyf3qceaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 0,
|
||||
"note": "torrent-internal merkle root, NOT a file-identity cid"
|
||||
},
|
||||
{
|
||||
"name": "cidv0-rejected",
|
||||
"cid": "QmYwAPJzv5CZsnA625s3Xf2nemtYgPpHdWEz79ojWnPbdG",
|
||||
"rank": 0,
|
||||
"note": "TRAP: Go rejected this (rank 0) while Rust's MsCid::from_str ACCEPTED it and ranked it 40 (dag-pb). Strict parse = CIDv1 base32-lower only. This vector pins the fix."
|
||||
},
|
||||
{
|
||||
"name": "token-form-rejected",
|
||||
"cid": "midhash256:bagacbabaeaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
|
||||
"rank": 0,
|
||||
"note": "TRAP: the deprecated <algo>:<cid> token form. Rust used to strip the prefix and rank it 10. It must now be rejected."
|
||||
},
|
||||
{
|
||||
"name": "garbage",
|
||||
"cid": "not-a-cid",
|
||||
"rank": 0
|
||||
},
|
||||
{
|
||||
"name": "empty",
|
||||
"cid": "",
|
||||
"rank": 0
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,2 +1,16 @@
|
||||
export type SimpleFileType = 'audio' | 'video' | 'document' | 'archive' | 'other' | 'undefined';
|
||||
|
||||
/**
|
||||
* The `fileType` vocabulary — METADATA_KEYS.md §1. Kept in lockstep with
|
||||
* `filename-tool`'s `SimpleFileType`, which is the classifier that produces
|
||||
* these values; this copy is the wire/type-level mirror.
|
||||
*/
|
||||
export type SimpleFileType =
|
||||
'audio'
|
||||
| 'video'
|
||||
| 'image'
|
||||
| 'document'
|
||||
| 'archive'
|
||||
| 'subtitle'
|
||||
| 'torrent'
|
||||
| 'card'
|
||||
| 'other'
|
||||
| 'undefined';
|
||||
|
||||
Reference in New Issue
Block a user