search: prefix/wildcard queries + 14 tests

prefixTerms matches indexed terms by prefix (allTerms + isPrefixOf); prefixDocs
unions their docs; prefixRankTfIdf ranks via the matched terms. 136/136.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

lib/search/api.sx

@@ -4,7 +4,7 @@
 ;; interpreter. Public Haskell entry points: indexDoc, lookupTerm, deleteDoc,
 ;; docFreq, allTerms, tokens, positioned, evalQuery, parseQuery, searchQuery,
 ;; rankTfIdf, rankBm25, topNTfIdf, topNBm25, fedIndex, aclFilter, searchTfIdfAcl,
-;; topNTfIdfAcl, searchBm25Acl.
+;; topNTfIdfAcl, searchBm25Acl, prefixTerms, prefixDocs, prefixRankTfIdf.
 
 (define
   search/src
@@ -19,4 +19,6 @@
     "\n"
     search/rank-src
     "\n"
-    search/fed-src))
+    search/fed-src
+    "\n"
+    search/prefix-src))

lib/search/conformance.conf

@@ -24,6 +24,7 @@ PRELOADS=(
   lib/search/parse.sx
   lib/search/rank.sx
   lib/search/fed.sx
+  lib/search/prefix.sx
   lib/search/api.sx
   lib/search/testlib.sx
 )
@@ -34,4 +35,5 @@ SUITES=(
   "parse:lib/search/tests/parse.sx"
   "rank:lib/search/tests/rank.sx"
   "integration:lib/search/tests/integration.sx"
+  "prefix:lib/search/tests/prefix.sx"
 )

lib/search/prefix.sx

@@ -0,0 +1,10 @@
+;; search prefix / wildcard queries — Haskell source fragment. Depends on index +
+;; rank (reuses candStep / rankTfIdf). A prefix matches every indexed term that
+;; starts with it; the matching terms are unioned (OR) into a docid set.
+;;   prefixTerms     :: String -> Index -> [Term]      (sorted, from allTerms)
+;;   prefixDocs      :: String -> Index -> [DocId]     (sorted union)
+;;   prefixRankTfIdf :: String -> Index -> [DocId]     (ranked by the matched terms)
+
+(define
+  search/prefix-src
+  "prefixTerms pre idx = filter (isPrefixOf pre) (allTerms idx)\nprefixDocs pre idx = foldl (candStep idx) [] (prefixTerms pre idx)\nprefixRankTfIdf pre idx = rankTfIdf (prefixTerms pre idx) idx\n")

lib/search/scoreboard.json

@@ -1,14 +1,15 @@
 {
   "lang": "search",
-  "total_passed": 122,
+  "total_passed": 136,
   "total_failed": 0,
-  "total": 122,
+  "total": 136,
   "suites": [
     {"name":"index","passed":18,"failed":0,"total":18},
     {"name":"boolean","passed":28,"failed":0,"total":28},
     {"name":"parse","passed":32,"failed":0,"total":32},
     {"name":"rank","passed":23,"failed":0,"total":23},
-    {"name":"integration","passed":21,"failed":0,"total":21}
+    {"name":"integration","passed":21,"failed":0,"total":21},
+    {"name":"prefix","passed":14,"failed":0,"total":14}
   ],
-  "generated": "2026-06-06T20:07:30+00:00"
+  "generated": "2026-06-06T20:21:41+00:00"
 }

lib/search/scoreboard.md

@@ -1,6 +1,6 @@
 # search scoreboard
 
-**122 / 122 passing** (0 failure(s)).
+**136 / 136 passing** (0 failure(s)).
 
 | Suite | Passed | Total | Status |
 |-------|--------|-------|--------|
@@ -9,3 +9,4 @@
 | parse | 32 | 32 | ok |
 | rank | 23 | 23 | ok |
 | integration | 21 | 21 | ok |
+| prefix | 14 | 14 | ok |

lib/search/tests/prefix.sx

@@ -0,0 +1,63 @@
+;; Extension — prefix / wildcard queries.
+;; Corpus: 1 "alpha alpine"  2 "beta apple"  3 "banana alpha"
+;; allTerms sorted: alpha alpine apple banana beta
+
+(define
+  prefix-setup
+  "idx = indexDoc 3 \"banana alpha\" (indexDoc 2 \"beta apple\" (indexDoc 1 \"alpha alpine\" emptyIndex))\n")
+
+(define
+  prefix-cases
+  (list
+    (list
+      "prefix terms two matches"
+      "prefixTerms \"al\" idx"
+      (list "alpha" "alpine"))
+    (list
+      "prefix terms narrower"
+      "prefixTerms \"alp\" idx"
+      (list "alpha" "alpine"))
+    (list
+      "prefix terms wide"
+      "prefixTerms \"a\" idx"
+      (list "alpha" "alpine" "apple"))
+    (list "prefix terms single" "prefixTerms \"ban\" idx" (list "banana"))
+    (list "prefix terms exact term" "prefixTerms \"beta\" idx" (list "beta"))
+    (list "prefix terms none" "prefixTerms \"z\" idx" (list))
+    (list
+      "prefix docs union"
+      "prefixDocs \"al\" idx"
+      (list 1 3))
+    (list "prefix docs single term" "prefixDocs \"ban\" idx" (list 3))
+    (list
+      "prefix docs wide"
+      "prefixDocs \"a\" idx"
+      (list 1 2 3))
+    (list "prefix docs none" "prefixDocs \"z\" idx" (list))
+    (list
+      "prefix docs exact"
+      "prefixDocs \"alpha\" idx"
+      (list 1 3))
+    (list
+      "prefix rank ranks by matched terms"
+      "prefixRankTfIdf \"al\" idx"
+      (list 1 3))
+    (list
+      "prefix rank single doc"
+      "prefixRankTfIdf \"ban\" idx"
+      (list 3))
+    (list "prefix rank empty" "prefixRankTfIdf \"z\" idx" (list))))
+
+(define
+  prefix-results
+  (search-batch
+    prefix-setup
+    (map (fn (c) (nth c 1)) prefix-cases)))
+
+(map-indexed
+  (fn
+    (i c)
+    (hk-test (nth c 0) (nth prefix-results i) (nth c 2)))
+  prefix-cases)
+
+{:fail hk-test-fail :pass hk-test-pass :fails hk-test-fails}

plans/search-on-sx.md

@@ -108,8 +108,19 @@ lib/search/index.sx                     lib/search/eval.sx
 - [x] `lib/search/tests/integration.sx` — 21 cases: index merge, cross-peer df/lookup,
   position preservation, boolean/phrase over the merge, ACL filter + top-N + bm25
 
+## Extensions (post-roadmap, search-shaped vocabulary)
+
+- [x] prefix / wildcard queries (`prefixTerms`, `prefixDocs`, `prefixRankTfIdf`) — 14 tests
+- [ ] fuzzy matching — edit distance term expansion
+- [ ] result pagination (offset / limit)
+- [ ] snippet / highlight generation
+- [ ] stemming (suffix stripping) — recall-improving normalizer
+
 ## Progress log
 
+- **Extension: prefix/wildcard queries (136/136 total).** `prefixTerms` matches every
+  indexed term starting with a prefix (via allTerms + isPrefixOf); `prefixDocs` unions
+  their docs; `prefixRankTfIdf` ranks treating the matched terms as the query. 14 tests.
 - **Phase 4 complete — federation + ACL (122/122 total). Roadmap done.** `fedIndex`
   merges per-peer inverted indices (union posting lists per term) after relabelling
   local DocIds to global `gid = peer*1000 + local` — the bijection makes (peer,doc-id)