Commit Graph
4 Commits
Author SHA1 Message Date
addrkit 6a3e1cc872 addrkit: 'selfcheck' command — resolve the whole registry against itself
Exhaustive check of all 72,825 indexed addresses: 72,811 exact (99.98%),
14 partial (malformed house units, e.g. '27с1', '32 к 1/4-1/6'), 0 not_found,
0 ambiguous.
2026-10-09 20:41:35 +07:00
addrkit 78691f3a22 addrkit: strict ordinal matching, LLM-variant guard, externalized prompt
- match: require candidate ordinal to equal the query ordinal in fuzzy search
  (deterministic typo recall 73% -> 80%, no wrong houses)
- resolver: compatibleVariant guard — LLM may only fix street spelling, keeping
  the same words, ordinal and house unit; damerau distance for transpositions
- llm: prompt moved out of code (go:embed default_prompt.txt) with
  llm.system_prompt / llm.system_prompt_file overrides; guided JSON parsing
  tolerant of thinking blocks
- address: recognize ordinals appearing after the street name
- tests: first coverage for the LLM adapter and config prompt loading; README

Measured (sample 200): deterministic 94.7-95.8% exact / 0 wrong across 4 seeds;
LLM+guard typo 90.7-89.8% / 0 wrong. LLM fallback latency ~1.2-1.9s.
2026-10-09 20:40:20 +07:00
addrkit 5cc3556ac5 addrkit: quality evaluation harness + parser hardening
- add internal/eval: deterministic citizen-style perturbation harness
  (typos, case, word order, abbreviations, filler words, dropped units)
- parser: strip all street-type tokens, filler words (город/дом/д/область),
  trailing apartment (кв N); handle letter-before-fraction and corpus letters
- matching: token-aware typo-tolerant street similarity; wider ambiguity
  margin to surface near-collisions instead of guessing
- seed: correct parse-rate accounting, structure-aware de-duplication
- CLI: 'addrkit eval' command; README with measured results

Measured on the real 73,936-row registry: 99.98% parsed, 0 wrong-house
safety violations across 34k+ perturbed cases.
2026-10-09 20:13:50 +07:00
addrkit 3be331bb65 addrkit: deterministic address resolution service (Go)
- domain: address normalization/parsing, matching with explicit statuses
- adapters: SQLite registry store, ArcGIS outages client, optional LLM rewriter, HTTP API
- seed pipeline with duplicate handling and unparsed reporting
- CLI (seed/verify/resolve), systemd unit, OpenAPI contract, tests
2026-10-09 20:05:32 +07:00