prolog: operator-table parser + < > =< >= built-ins, 19 tests

lib/prolog/parser.sx

@@ -1,28 +1,20 @@
 ;; lib/prolog/parser.sx — tokens → Prolog AST
 ;;
-;; Phase 1 grammar (NO operator table yet):
+;; Phase 4 grammar (with operator table):
 ;;   Program      := Clause* EOF
-;;   Clause       := Term "." | Term ":-" Term "."
-;;   Term         := Atom | Var | Number | String | Compound | List
-;;   Compound     := atom "(" ArgList ")"
-;;   ArgList      := Term ("," Term)*
-;;   List         := "[" "]" | "[" Term ("," Term)* ("|" Term)? "]"
+;;   Clause       := Term[999] "." | Term[999] ":-" Term[1200] "."
+;;   Term[Pmax] uses precedence climbing on the operator table:
+;;     primary = Atom | Var | Number | String | Compound | List | "(" Term[1200] ")"
+;;     while next token is infix op `op` with prec(op) ≤ Pmax:
+;;       consume op; parse rhs at right-prec(op); fold into compound(op-name,[lhs,rhs])
 ;;
-;; Term AST shapes (all tagged lists for uniform dispatch):
-;;   ("atom"  name)            — atom
-;;   ("var"   name)            — variable template (parser-time only)
-;;   ("num"   value)           — integer or float
-;;   ("str"   value)           — string literal
-;;   ("compound" functor args) — compound term, args is list of term-ASTs
-;;   ("cut")                   — the cut atom !
+;; Op type → right-prec for op at precedence P:
+;;   xfx → P-1   strict-both
+;;   xfy → P     right-associative
+;;   yfx → P-1   left-associative
 ;;
-;; A clause is (list "clause" head body). A fact is head with body = ("atom" "true").
-;;
-;; The empty list is (atom "[]"). Cons is compound "." with two args:
-;; [1, 2, 3]   → .(1, .(2, .(3, [])))
-;; [H|T]       → .(H, T)
+;; AST shapes are unchanged — operators just become compound terms.
 
-;; ── Parser state helpers ────────────────────────────────────────────
 (define
   pp-peek
   (fn
@@ -66,7 +58,6 @@
             (if (= (get t :value) nil) "" (get t :value))
             "'"))))))
 
-;; ── AST constructors ────────────────────────────────────────────────
 (define pl-mk-atom (fn (name) (list "atom" name)))
 (define pl-mk-var (fn (name) (list "var" name)))
 (define pl-mk-num (fn (n) (list "num" n)))
@@ -74,18 +65,14 @@
 (define pl-mk-compound (fn (f args) (list "compound" f args)))
 (define pl-mk-cut (fn () (list "cut")))
 
-;; Term tag extractors
 (define pl-term-tag (fn (t) (if (list? t) (first t) nil)))
 (define pl-term-val (fn (t) (nth t 1)))
 (define pl-compound-functor (fn (t) (nth t 1)))
 (define pl-compound-args (fn (t) (nth t 2)))
 
-;; Empty-list atom and cons helpers
 (define pl-nil-term (fn () (pl-mk-atom "[]")))
-
 (define pl-mk-cons (fn (h t) (pl-mk-compound "." (list h t))))
 
-;; Build cons list from a list of terms + optional tail
 (define
   pl-mk-list-term
   (fn
@@ -95,9 +82,60 @@
       tail
       (pl-mk-cons (first items) (pl-mk-list-term (rest items) tail)))))
 
-;; ── Term parser ─────────────────────────────────────────────────────
+;; ── Operator table (Phase 4) ──────────────────────────────────────
+;; Each entry: (name precedence type). Type ∈ "xfx" "xfy" "yfx".
 (define
-  pp-parse-term
+  pl-op-table
+  (list
+    (list "," 1000 "xfy")
+    (list ";" 1100 "xfy")
+    (list "->" 1050 "xfy")
+    (list "=" 700 "xfx")
+    (list "\\=" 700 "xfx")
+    (list "is" 700 "xfx")
+    (list "<" 700 "xfx")
+    (list ">" 700 "xfx")
+    (list "=<" 700 "xfx")
+    (list ">=" 700 "xfx")
+    (list "+" 500 "yfx")
+    (list "-" 500 "yfx")
+    (list "*" 400 "yfx")
+    (list "/" 400 "yfx")
+    (list "mod" 400 "yfx")))
+
+(define
+  pl-op-find
+  (fn
+    (name table)
+    (cond
+      ((empty? table) nil)
+      ((= (first (first table)) name) (rest (first table)))
+      (true (pl-op-find name (rest table))))))
+
+(define pl-op-lookup (fn (name) (pl-op-find name pl-op-table)))
+
+;; Token → (name prec type) for known infix ops, else nil.
+(define
+  pl-token-op
+  (fn
+    (t)
+    (let
+      ((ty (get t :type)) (vv (get t :value)))
+      (cond
+        ((and (= ty "punct") (= vv ","))
+          (let
+            ((info (pl-op-lookup ",")))
+            (if (nil? info) nil (cons "," info))))
+        ((= ty "atom")
+          (let
+            ((info (pl-op-lookup vv)))
+            (if (nil? info) nil (cons vv info))))
+        (true nil)))))
+
+;; ── Term parser ─────────────────────────────────────────────────────
+;; Primary term: atom, var, num, str, compound (atom + paren), list, cut, parens.
+(define
+  pp-parse-primary
   (fn
     (st)
     (let
@@ -111,6 +149,12 @@
           ((and (= ty "op") (= vv "!"))
             (do (pp-advance! st) (pl-mk-cut)))
           ((and (= ty "punct") (= vv "[")) (pp-parse-list st))
+          ((and (= ty "punct") (= vv "("))
+            (do
+              (pp-advance! st)
+              (let
+                ((inner (pp-parse-term-prec st 1200)))
+                (do (pp-expect! st "punct" ")") inner))))
           ((= ty "atom")
             (do
               (pp-advance! st)
@@ -133,13 +177,51 @@
                 (if (= vv nil) "" vv)
                 "'"))))))))
 
-;; Parse one or more comma-separated terms (arguments).
+;; Operator-aware term parser: precedence climbing.
+(define
+  pp-parse-term-prec
+  (fn
+    (st max-prec)
+    (let ((left (pp-parse-primary st))) (pp-parse-op-rhs st left max-prec))))
+
+(define
+  pp-parse-op-rhs
+  (fn
+    (st left max-prec)
+    (let
+      ((op-info (pl-token-op (pp-peek st))))
+      (cond
+        ((nil? op-info) left)
+        (true
+          (let
+            ((name (first op-info))
+              (prec (nth op-info 1))
+              (ty (nth op-info 2)))
+            (cond
+              ((> prec max-prec) left)
+              (true
+                (let
+                  ((right-prec (if (= ty "xfy") prec (- prec 1))))
+                  (do
+                    (pp-advance! st)
+                    (let
+                      ((right (pp-parse-term-prec st right-prec)))
+                      (pp-parse-op-rhs
+                        st
+                        (pl-mk-compound name (list left right))
+                        max-prec))))))))))))
+
+;; Backwards-compat alias.
+(define pp-parse-term (fn (st) (pp-parse-term-prec st 999)))
+
+;; Args inside parens: parse at prec 999 so comma-as-operator (1000)
+;; is not consumed; the explicit comma loop handles separation.
 (define
   pp-parse-arg-list
   (fn
     (st)
     (let
-      ((first-arg (pp-parse-term st)) (args (list)))
+      ((first-arg (pp-parse-term-prec st 999)) (args (list)))
       (do
         (append! args first-arg)
         (define
@@ -150,12 +232,12 @@
               (pp-at? st "punct" ",")
               (do
                 (pp-advance! st)
-                (append! args (pp-parse-term st))
+                (append! args (pp-parse-term-prec st 999))
                 (loop)))))
         (loop)
         args))))
 
-;; Parse a [ ... ] list literal. Consumes the "[".
+;; List literal.
 (define
   pp-parse-list
   (fn
@@ -168,7 +250,7 @@
         (let
           ((items (list)))
           (do
-            (append! items (pp-parse-term st))
+            (append! items (pp-parse-term-prec st 999))
             (define
               comma-loop
               (fn
@@ -177,52 +259,17 @@
                   (pp-at? st "punct" ",")
                   (do
                     (pp-advance! st)
-                    (append! items (pp-parse-term st))
+                    (append! items (pp-parse-term-prec st 999))
                     (comma-loop)))))
             (comma-loop)
             (let
-              ((tail (if (pp-at? st "punct" "|") (do (pp-advance! st) (pp-parse-term st)) (pl-nil-term))))
+              ((tail (if (pp-at? st "punct" "|") (do (pp-advance! st) (pp-parse-term-prec st 999)) (pl-nil-term))))
               (do (pp-expect! st "punct" "]") (pl-mk-list-term items tail)))))))))
 
 ;; ── Body parsing ────────────────────────────────────────────────────
-;; A clause body is a comma-separated list of goals. We flatten into a
-;; right-associative `,` compound: (A, B, C) → ','(A, ','(B, C))
-;; If only one goal, it's that goal directly.
-(define
-  pp-parse-body
-  (fn
-    (st)
-    (let
-      ((first-goal (pp-parse-term st)) (rest-goals (list)))
-      (do
-        (define
-          gloop
-          (fn
-            ()
-            (when
-              (pp-at? st "punct" ",")
-              (do
-                (pp-advance! st)
-                (append! rest-goals (pp-parse-term st))
-                (gloop)))))
-        (gloop)
-        (if
-          (= (len rest-goals) 0)
-          first-goal
-          (pp-build-conj first-goal rest-goals))))))
-
-(define
-  pp-build-conj
-  (fn
-    (first-goal rest-goals)
-    (if
-      (= (len rest-goals) 0)
-      first-goal
-      (pl-mk-compound
-        ","
-        (list
-          first-goal
-          (pp-build-conj (first rest-goals) (rest rest-goals)))))))
+;; A body is a single term parsed at prec 1200 — operator parser folds
+;; `,`, `;`, `->` automatically into right-associative compounds.
+(define pp-parse-body (fn (st) (pp-parse-term-prec st 1200)))
 
 ;; ── Clause parsing ──────────────────────────────────────────────────
 (define
@@ -230,12 +277,11 @@
   (fn
     (st)
     (let
-      ((head (pp-parse-term st)))
+      ((head (pp-parse-term-prec st 999)))
       (let
         ((body (if (pp-at? st "op" ":-") (do (pp-advance! st) (pp-parse-body st)) (pl-mk-atom "true"))))
         (do (pp-expect! st "punct" ".") (list "clause" head body))))))
 
-;; Parse an entire program — returns list of clauses.
 (define
   pl-parse-program
   (fn
@@ -253,13 +299,9 @@
         (ploop)
         clauses))))
 
-;; Parse a single query term (no trailing "."). Returns the term.
 (define
   pl-parse-query
   (fn (tokens) (let ((st {:idx 0 :tokens tokens})) (pp-parse-body st))))
 
-;; Convenience: source → clauses
 (define pl-parse (fn (src) (pl-parse-program (pl-tokenize src))))
-
-;; Convenience: source → query term
 (define pl-parse-goal (fn (src) (pl-parse-query (pl-tokenize src))))