{"adoption": {"forks": 298, "observed_at": "2026-08-28T04:03:14.367598+00:00", "stars": 1016}, "canonical_url": "https://ross.abutalabs.com/products/ahocorasickdoublearraytrie", "card": {"archived": false, "artifact_type": "library", "description": "An extremely fast implementation of Aho Corasick algorithm based on Double Array Trie.", "domain": ["developer-tools"], "enriched": true, "function": ["parser", "search-engine", "nlp"], "health_score": 20, "homepage": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html", "language": "Java", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["hankcs/AhoCorasickDoubleArrayTrie"], "name": "hankcs/AhoCorasickDoubleArrayTrie", "platform": ["jvm"], "pushed_at": "2021-11-24T17:09:04+00:00", "repo": "hankcs/AhoCorasickDoubleArrayTrie", "stars": 1016, "tags": ["aho-corasick", "double-array-trie", "multi-pattern-matching", "string-matching", "text-processing", "algorithms", "natural-language-processing"], "topics": ["aho-corasick", "doublearraytrie", "algorithm", "java", "fast"], "urls": [], "use_cases": ["find all occurrences of many keywords in a text fast", "multi-pattern string matching in Java", "linkify or highlight dictionary words in text", "dictionary-based text annotation", "fast keyword matching for NLP tokenization", "spell-check text against a large dictionary"], "what_it_is": "A Java library implementing the Aho-Corasick multi-pattern string matching algorithm on top of a Double Array Trie, achieving O(n) matching speed. It is used as a core data structure in the HanLP NLP package and is available via Maven Central.", "when_to_avoid": ["you need a non-JVM language implementation", "you only need single-pattern search (use a simpler algorithm)", "you need an actively maintained library with recent releases"], "when_to_choose": ["you need extremely fast multi-pattern matching over a large dictionary in Java", "memory-efficient string matching matters", "you're building NLP pipelines like segmentation or term extraction"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/ahocorasickdoublearraytrie", "repo": "hankcs/AhoCorasickDoubleArrayTrie", "role": "main", "score": 23}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T07:11:18.765394+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be6757473f929f94386d6d0cf3ec9898da785fb7dbaca499d2199bc3e43ec73a", "fetched_at": "2026-08-28T04:03:14.367598+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hankcs/AhoCorasickDoubleArrayTrie"}, {"content_hash": "20de0d214b935a803da8bd720ea96318926fb235be7103f2a80eaeb672019056", "fetched_at": "2026-08-29T13:10:32.778041+00:00", "kind": "homepage", "missing": false, "url": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html"}, {"content_hash": "001a7ec350a1d140c546837b9b1dc9992af6a53f55145a9844c13f8722b40fc2", "fetched_at": "2026-08-29T13:10:32.787982+00:00", "kind": "site_page", "missing": false, "url": "https://www.hankcs.com/about"}, {"content_hash": "c01d28ddc3264f11f44fdc8fab545fd11c3594376c44b1c0a3101cf49276f4a4", "fetched_at": "2026-08-29T13:10:32.792093+00:00", "kind": "site_page", "missing": false, "url": "http://www.hankcs.com/about"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T07:11:18.765394+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be6757473f929f94386d6d0cf3ec9898da785fb7dbaca499d2199bc3e43ec73a", "fetched_at": "2026-08-28T04:03:14.367598+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hankcs/AhoCorasickDoubleArrayTrie"}, {"content_hash": "20de0d214b935a803da8bd720ea96318926fb235be7103f2a80eaeb672019056", "fetched_at": "2026-08-29T13:10:32.778041+00:00", "kind": "homepage", "missing": false, "url": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html"}, {"content_hash": "001a7ec350a1d140c546837b9b1dc9992af6a53f55145a9844c13f8722b40fc2", "fetched_at": "2026-08-29T13:10:32.787982+00:00", "kind": "site_page", "missing": false, "url": "https://www.hankcs.com/about"}, {"content_hash": "c01d28ddc3264f11f44fdc8fab545fd11c3594376c44b1c0a3101cf49276f4a4", "fetched_at": "2026-08-29T13:10:32.792093+00:00", "kind": "site_page", "missing": false, "url": "http://www.hankcs.com/about"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T07:11:18.765394+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be6757473f929f94386d6d0cf3ec9898da785fb7dbaca499d2199bc3e43ec73a", "fetched_at": "2026-08-28T04:03:14.367598+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hankcs/AhoCorasickDoubleArrayTrie"}, {"content_hash": "20de0d214b935a803da8bd720ea96318926fb235be7103f2a80eaeb672019056", "fetched_at": "2026-08-29T13:10:32.778041+00:00", "kind": "homepage", "missing": false, "url": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html"}, {"content_hash": "001a7ec350a1d140c546837b9b1dc9992af6a53f55145a9844c13f8722b40fc2", "fetched_at": "2026-08-29T13:10:32.787982+00:00", "kind": "site_page", "missing": false, "url": "https://www.hankcs.com/about"}, {"content_hash": "c01d28ddc3264f11f44fdc8fab545fd11c3594376c44b1c0a3101cf49276f4a4", "fetched_at": "2026-08-29T13:10:32.792093+00:00", "kind": "site_page", "missing": false, "url": "http://www.hankcs.com/about"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T07:11:18.765394+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be6757473f929f94386d6d0cf3ec9898da785fb7dbaca499d2199bc3e43ec73a", "fetched_at": "2026-08-28T04:03:14.367598+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hankcs/AhoCorasickDoubleArrayTrie"}, {"content_hash": "20de0d214b935a803da8bd720ea96318926fb235be7103f2a80eaeb672019056", "fetched_at": "2026-08-29T13:10:32.778041+00:00", "kind": "homepage", "missing": false, "url": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html"}, {"content_hash": "001a7ec350a1d140c546837b9b1dc9992af6a53f55145a9844c13f8722b40fc2", "fetched_at": "2026-08-29T13:10:32.787982+00:00", "kind": "site_page", "missing": false, "url": "https://www.hankcs.com/about"}, {"content_hash": "c01d28ddc3264f11f44fdc8fab545fd11c3594376c44b1c0a3101cf49276f4a4", "fetched_at": "2026-08-29T13:10:32.792093+00:00", "kind": "site_page", "missing": false, "url": "http://www.hankcs.com/about"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T07:11:18.765394+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be6757473f929f94386d6d0cf3ec9898da785fb7dbaca499d2199bc3e43ec73a", "fetched_at": "2026-08-28T04:03:14.367598+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hankcs/AhoCorasickDoubleArrayTrie"}, {"content_hash": "20de0d214b935a803da8bd720ea96318926fb235be7103f2a80eaeb672019056", "fetched_at": "2026-08-29T13:10:32.778041+00:00", "kind": "homepage", "missing": false, "url": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html"}, {"content_hash": "001a7ec350a1d140c546837b9b1dc9992af6a53f55145a9844c13f8722b40fc2", "fetched_at": "2026-08-29T13:10:32.787982+00:00", "kind": "site_page", "missing": false, "url": "https://www.hankcs.com/about"}, {"content_hash": "c01d28ddc3264f11f44fdc8fab545fd11c3594376c44b1c0a3101cf49276f4a4", "fetched_at": "2026-08-29T13:10:32.792093+00:00", "kind": "site_page", "missing": false, "url": "http://www.hankcs.com/about"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T07:11:18.765394+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be6757473f929f94386d6d0cf3ec9898da785fb7dbaca499d2199bc3e43ec73a", "fetched_at": "2026-08-28T04:03:14.367598+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hankcs/AhoCorasickDoubleArrayTrie"}, {"content_hash": "20de0d214b935a803da8bd720ea96318926fb235be7103f2a80eaeb672019056", "fetched_at": "2026-08-29T13:10:32.778041+00:00", "kind": "homepage", "missing": false, "url": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html"}, {"content_hash": "001a7ec350a1d140c546837b9b1dc9992af6a53f55145a9844c13f8722b40fc2", "fetched_at": "2026-08-29T13:10:32.787982+00:00", "kind": "site_page", "missing": false, "url": "https://www.hankcs.com/about"}, {"content_hash": "c01d28ddc3264f11f44fdc8fab545fd11c3594376c44b1c0a3101cf49276f4a4", "fetched_at": "2026-08-29T13:10:32.792093+00:00", "kind": "site_page", "missing": false, "url": "http://www.hankcs.com/about"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:14.367598+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T07:11:18.765394+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be6757473f929f94386d6d0cf3ec9898da785fb7dbaca499d2199bc3e43ec73a", "fetched_at": "2026-08-28T04:03:14.367598+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hankcs/AhoCorasickDoubleArrayTrie"}, {"content_hash": "20de0d214b935a803da8bd720ea96318926fb235be7103f2a80eaeb672019056", "fetched_at": "2026-08-29T13:10:32.778041+00:00", "kind": "homepage", "missing": false, "url": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html"}, {"content_hash": "001a7ec350a1d140c546837b9b1dc9992af6a53f55145a9844c13f8722b40fc2", "fetched_at": "2026-08-29T13:10:32.787982+00:00", "kind": "site_page", "missing": false, "url": "https://www.hankcs.com/about"}, {"content_hash": "c01d28ddc3264f11f44fdc8fab545fd11c3594376c44b1c0a3101cf49276f4a4", "fetched_at": "2026-08-29T13:10:32.792093+00:00", "kind": "site_page", "missing": false, "url": "http://www.hankcs.com/about"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T07:11:18.765394+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be6757473f929f94386d6d0cf3ec9898da785fb7dbaca499d2199bc3e43ec73a", "fetched_at": "2026-08-28T04:03:14.367598+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hankcs/AhoCorasickDoubleArrayTrie"}, {"content_hash": "20de0d214b935a803da8bd720ea96318926fb235be7103f2a80eaeb672019056", "fetched_at": "2026-08-29T13:10:32.778041+00:00", "kind": "homepage", "missing": false, "url": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html"}, {"content_hash": "001a7ec350a1d140c546837b9b1dc9992af6a53f55145a9844c13f8722b40fc2", "fetched_at": "2026-08-29T13:10:32.787982+00:00", "kind": "site_page", "missing": false, "url": "https://www.hankcs.com/about"}, {"content_hash": "c01d28ddc3264f11f44fdc8fab545fd11c3594376c44b1c0a3101cf49276f4a4", "fetched_at": "2026-08-29T13:10:32.792093+00:00", "kind": "site_page", "missing": false, "url": "http://www.hankcs.com/about"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T07:11:18.765394+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be6757473f929f94386d6d0cf3ec9898da785fb7dbaca499d2199bc3e43ec73a", "fetched_at": "2026-08-28T04:03:14.367598+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hankcs/AhoCorasickDoubleArrayTrie"}, {"content_hash": "20de0d214b935a803da8bd720ea96318926fb235be7103f2a80eaeb672019056", "fetched_at": "2026-08-29T13:10:32.778041+00:00", "kind": "homepage", "missing": false, "url": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html"}, {"content_hash": "001a7ec350a1d140c546837b9b1dc9992af6a53f55145a9844c13f8722b40fc2", "fetched_at": "2026-08-29T13:10:32.787982+00:00", "kind": "site_page", "missing": false, "url": "https://www.hankcs.com/about"}, {"content_hash": "c01d28ddc3264f11f44fdc8fab545fd11c3594376c44b1c0a3101cf49276f4a4", "fetched_at": "2026-08-29T13:10:32.792093+00:00", "kind": "site_page", "missing": false, "url": "http://www.hankcs.com/about"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T07:11:18.765394+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "be6757473f929f94386d6d0cf3ec9898da785fb7dbaca499d2199bc3e43ec73a", "fetched_at": "2026-08-28T04:03:14.367598+00:00", "kind": "readme", "missing": false, "url": "https://github.com/hankcs/AhoCorasickDoubleArrayTrie"}, {"content_hash": "20de0d214b935a803da8bd720ea96318926fb235be7103f2a80eaeb672019056", "fetched_at": "2026-08-29T13:10:32.778041+00:00", "kind": "homepage", "missing": false, "url": "http://www.hankcs.com/program/algorithm/aho-corasick-double-array-trie.html"}, {"content_hash": "001a7ec350a1d140c546837b9b1dc9992af6a53f55145a9844c13f8722b40fc2", "fetched_at": "2026-08-29T13:10:32.787982+00:00", "kind": "site_page", "missing": false, "url": "https://www.hankcs.com/about"}, {"content_hash": "c01d28ddc3264f11f44fdc8fab545fd11c3594376c44b1c0a3101cf49276f4a4", "fetched_at": "2026-08-29T13:10:32.792093+00:00", "kind": "site_page", "missing": false, "url": "http://www.hankcs.com/about"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4165, "days_push": 1743, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 23, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}