nx_dr_corpus.nx source
↩ module page · 26 lines · 1457 B
1// nx_dr_corpus.nx -- FILE-BACKED corpus mode for the sovereign deep-research engine (DR-9).
2// The chain judged documents passed as argv strings, which caps a source at the argv limit --
3// a real fetched web page (tens of KB) cannot ride there. This organ reads a source document
4// from DISK, so the engine runs over the corpus the live nx_fetch spine already writes
5// (knowledge/library/*.txt). That is the concrete unlock for a full-corpus benchmark run.
6// FAIL-LOUD BY CONSTRUCTION: an unreadable or empty source returns -1 so the caller REPORTS it
7// rather than silently scoring a missing file as zero coverage (a silent-truncation trap).
8// Composes nx_dr_chain (judge -> conduct -> score) and nx_dr_run (tokenizer).
9// Every func <=6 params (NAS nx_cc >6-arg skew, debt seq239). No hardware writes (Rule 26).
10//
11// module: nishi-core.research.dr_corpus
12// depends: nx_dr_chain.nx, nx_dr_run.nx, nx_syscalls.nx
13// genealogy_id: drbench_2026_corpus_scale
14import "nx_dr_chain.nx"
15import "nx_dr_run.nx"
16import "nx_syscalls.nx"
17
18// Read a sovereign corpus document from disk and tokenize it into out_ids.
19// Returns the token count, or -1 when the file is unreadable/empty (fail-loud).
20func corp_tokenize_file(path: *u8, out_ids: *i64, maxn: i64) -> i64 {
21 let lenp: *i64 = sys_mmap(8) as *i64
22 lenp[0] = 0
23 let buf: *u8 = sys_read_file(path, lenp)
24 if lenp[0] <= 0 { return 0 - 1 }
25 return drr_tokenize(buf, lenp[0], out_ids, maxn)
26}