Add search self-tests (hash consistency, QSearch sanity) and a native EPD parser (`epd` command + ParseEpdRecord), fixing a silent-corruption bug in convert_epd.pl that broke every Black-to-move EPD conversion.

testsearch.c: TestSearchHashConsistency exercises the hash table through real search (repeat-with-warm-table and shallow-then-deep agreement) rather than synthetic store/probe calls. TestQSearchSanity checks termination and a node-count ceiling; its own header documents that the TEST=1 self-test build doesn't define PERF_COUNTERS, so it checks whole-search node count rather than the qsearch-only counter. A planned null-move zugzwang test was dropped in favor of tests/zugzwang.epd (best-move outcome, not an internal counter) after the three classic literature positions turned out not to structurally reach this engine's verification-search code path on this build.

fen.c/script.c/command.c: new `epd <file>` command reads raw EPD directly via ParseEpdRecord, reusing ScriptCommand's existing suite-reporting machinery (factored into _ProcessSuiteLine/_PrintSuiteReport). Replaces the need for tests/convert_epd.pl, which had a real bug: its bm/am regex's [^b]+ filler breaks on any Black-to-move record (side-to-move field is literally "b"), and unscoped $fen/$id/$solution globals meant a failed match silently duplicated the previous record instead of erroring.

tests/ep_to_epd.pl converts the existing setboard/solution/avoid/id/go suites back to real EPD; cross-checked ecm_ringers.ep_ via `script` against ecm_ringers.epd via `epd` -- byte-identical node counts and solve stats. Added .epd siblings for every genuine tactical suite in tests/.

Added src/TESTING_PLAN.md: full audit of test*.c coverage gaps (dead SEE oracle, unwired eval/recognizer tests, zero hash-table correctness coverage, thin search self-tests) with a prioritized plan for closing them.

Co-Authored-By: Claude Sonnet 5 <[email protected]>

1 files changed, 262 insertions, 116 deletions

diff --git a/src/script.c b/src/script.c
index 0bc09e4..e8d6f9a 100644
--- a/src/script.c
+++ b/src/script.c
@@ -349,6 +349,160 @@ Return value:
 
 
 
+//
+// Shared by ScriptCommand and EpdCommand: process one already-read
+// line exactly the way a script file's line is processed -- "go"
+// triggers a search plus counter accumulation, anything else is
+// dispatched through the normal command parser. Factored out so
+// EpdCommand can feed it lines synthesized from a raw EPD record
+// (setboard/id/solution/avoid/go) instead of lines read verbatim from
+// a file, without duplicating this logic or its counter bookkeeping.
+//
+static void
+_ProcessSuiteLine(char *szLine, POSITION *pos)
+{
+    Trace("SCRIPT> %s\n", szLine);
+    if (!STRNCMPI(szLine, "go", 2))
+    {
+        (void)Think(pos);
+        g_SuiteCounters.u64TotalNodeCount +=
+            g_Options.u64NodesSearched;
+        g_SuiteCounters.u64TotalBetaCutoffs +=
+            g_Options.u64BetaCutoffs;
+        g_SuiteCounters.u64TotalBetaCutoffsOnFirstMove +=
+            g_Options.u64BetaCutoffsOnFirstMove;
+        g_SuiteCounters.u64TotalCounterMoveTries +=
+            g_Options.u64CounterMoveTries;
+        g_SuiteCounters.u64TotalCounterMoveHits +=
+            g_Options.u64CounterMoveHits;
+        g_SuiteCounters.u64TotalLeftoverTries +=
+            g_Options.u64LeftoverTries;
+        g_SuiteCounters.u64TotalLeftoverAlpha +=
+            g_Options.u64LeftoverAlpha;
+        g_SuiteCounters.u64TotalLeftoverFH +=
+            g_Options.u64LeftoverFH;
+        {
+            ULONG v;
+            for (v = 0; v < CM_EVIDENCE_BUCKETS; v++)
+            {
+                g_SuiteCounters.u64TotalCMEvidenceTries[v] +=
+                    g_Options.u64CMEvidenceTries[v];
+                g_SuiteCounters.u64TotalCMEvidenceFH[v] +=
+                    g_Options.u64CMEvidenceFH[v];
+            }
+        }
+    }
+    else
+    {
+        PushNewInput(szLine);
+        if (FALSE == g_fExitProgram)
+        {
+            ParseUserInput(FALSE);
+        }
+    }
+}
+
+
+//
+// Shared by ScriptCommand and EpdCommand: the end-of-suite banner and
+// statistics report. Verbatim extraction of what used to be
+// ScriptCommand's own tail -- see that function's history for the
+// meaning of each field.
+//
+static void
+_PrintSuiteReport(double dSuiteStart)
+{
+    ULONG u, v, uMax;
+    double dMult = (double)g_Options.uMyIncrement / (double)SUITE_NUM_HISTOGRAM;
+
+    Banner();
+    Trace("\n"
+          "TEST SCRIPT execution complete.  Final statistics:\n"
+          "--------------------------------------------------\n"
+          "    correct solutions   : %u\n"
+          "    incorrect solutions : %u\n"
+          "    total problems      : %u\n"
+          "    total nodecount     : %"
+               COMPILER_LONGLONG_UNSIGNED_FORMAT "\n"
+          "    avg. search speed   : %6.1f nps\n"
+          "    avg. solution time  : %3.1f sec\n"
+          "    avg. search depth   : %4.1f ply\n"
+          "    1st move beta cut   : %5.2f percent\n"
+          "    avg. eff. branching : %5.3f\n"
+          "    counter move hit %% : %5.2f percent (%"
+               COMPILER_LONGLONG_UNSIGNED_FORMAT " tries)\n"
+          "    leftover            : %5.2f%% alpha, %5.2f%% FH (%"
+               COMPILER_LONGLONG_UNSIGNED_FORMAT " tries)\n"
+          "    script time         : %6.1f sec\n\n",
+          g_SuiteCounters.uCorrect,
+          g_SuiteCounters.uIncorrect,
+          g_SuiteCounters.uTotal,
+          g_SuiteCounters.u64TotalNodeCount,
+          ((double)g_SuiteCounters.u64TotalNodeCount /
+           (SystemTimeStamp() - dSuiteStart)),
+          ((g_SuiteCounters.uCorrect > 0) ?
+           (g_SuiteCounters.dSigmaSolutionTime /
+            (double)g_SuiteCounters.uCorrect) : 0.0),
+          ((double)g_SuiteCounters.uSigmaDepth /
+           (double)g_SuiteCounters.uTotal),
+          (100.0 * (double)g_SuiteCounters.u64TotalBetaCutoffsOnFirstMove /
+           ((double)g_SuiteCounters.u64TotalBetaCutoffs + 1.0)),
+          (g_SuiteCounters.dSigmaEBF /
+           ((double)g_SuiteCounters.uEBFCount + 1.0)),
+          (100.0 * (double)g_SuiteCounters.u64TotalCounterMoveHits /
+           ((double)g_SuiteCounters.u64TotalCounterMoveTries + 1.0)),
+          g_SuiteCounters.u64TotalCounterMoveTries,
+          (100.0 * (double)g_SuiteCounters.u64TotalLeftoverAlpha /
+           ((double)g_SuiteCounters.u64TotalLeftoverTries + 1.0)),
+          (100.0 * (double)g_SuiteCounters.u64TotalLeftoverFH /
+           ((double)g_SuiteCounters.u64TotalLeftoverTries + 1.0)),
+          g_SuiteCounters.u64TotalLeftoverTries,
+          (SystemTimeStamp() - dSuiteStart));
+
+    // Countermove evidence calibration -- FH% per evidence bucket,
+    // an ongoing check that COUNTERMOVE_EVIDENCE_THRESHOLD (chess.h)
+    // is still well-calibrated as the engine/data evolve.
+    {
+        static const ULONG uCMEvidenceFloors[CM_EVIDENCE_BUCKETS] =
+            { 0, 1, 100, 1000, 10000, 100000, 1000000 };
+        Trace("\ncountermove evidence calibration:\n");
+        for (v = 0; v < CM_EVIDENCE_BUCKETS; v++)
+        {
+            Trace("    evidence >= %8lu : %5.2f%% FH (%"
+                  COMPILER_LONGLONG_UNSIGNED_FORMAT " tries)\n",
+                  uCMEvidenceFloors[v],
+                  (100.0 * (double)g_SuiteCounters.u64TotalCMEvidenceFH[v] /
+                   ((double)g_SuiteCounters.u64TotalCMEvidenceTries[v] + 1.0)),
+                  g_SuiteCounters.u64TotalCMEvidenceTries[v]);
+        }
+    }
+
+    // Histogram stuff
+    if (g_SuiteCounters.uTotal > 0) {
+        uMax = g_SuiteCounters.uHistogram[0];
+        for (u = 1; u < SUITE_NUM_HISTOGRAM; u++)
+        {
+            if (g_SuiteCounters.uHistogram[u] > uMax)
+            {
+                uMax = g_SuiteCounters.uHistogram[u];
+            }
+        }
+        for (u = 0; u < SUITE_NUM_HISTOGRAM; u++)
+        {
+            Trace("%4.1f .. %4.1f: ",
+                  (double)u * dMult, (double)(u + 1) * dMult);
+            for (v = 0;
+                 (uMax > 0) && (v < 50 * g_SuiteCounters.uHistogram[u] / uMax);
+                 v++)
+            {
+                Trace("*");
+            }
+            Trace("\n");
+        }
+    }
+}
+
+
 COMMAND(ScriptCommand)
 /**
 
@@ -389,8 +543,6 @@ Return value:
     FILE *p;
     static CHAR szLine[SMALL_STRING_LEN_CHAR];
     double dSuiteStart;
-    ULONG u, v, uMax;
-    double dMult;
 
     if (argc < 2)
     {
@@ -402,143 +554,137 @@ Return value:
         Trace("Error (file doesn't exist): %s\n", argv[1]);
         return;
     }
-    
+
     p = fopen(argv[1], "rb");
     if (NULL != p)
     {
-        // Doing the script...
         dSuiteStart = SystemTimeStamp();
         memset(&(g_SuiteCounters), 0, sizeof(g_SuiteCounters));
         while(fgets(szLine, ARRAY_LENGTH(szLine), p))
         {
-            Trace("SCRIPT> %s\n", szLine);
-            if (!STRNCMPI(szLine, "go", 2))
-            {
-                (void)Think(pos);
-                g_SuiteCounters.u64TotalNodeCount +=
-                    g_Options.u64NodesSearched;
-                g_SuiteCounters.u64TotalBetaCutoffs +=
-                    g_Options.u64BetaCutoffs;
-                g_SuiteCounters.u64TotalBetaCutoffsOnFirstMove +=
-                    g_Options.u64BetaCutoffsOnFirstMove;
-                g_SuiteCounters.u64TotalCounterMoveTries +=
-                    g_Options.u64CounterMoveTries;
-                g_SuiteCounters.u64TotalCounterMoveHits +=
-                    g_Options.u64CounterMoveHits;
-                g_SuiteCounters.u64TotalLeftoverTries +=
-                    g_Options.u64LeftoverTries;
-                g_SuiteCounters.u64TotalLeftoverAlpha +=
-                    g_Options.u64LeftoverAlpha;
-                g_SuiteCounters.u64TotalLeftoverFH +=
-                    g_Options.u64LeftoverFH;
-                for (v = 0; v < CM_EVIDENCE_BUCKETS; v++)
-                {
-                    g_SuiteCounters.u64TotalCMEvidenceTries[v] +=
-                        g_Options.u64CMEvidenceTries[v];
-                    g_SuiteCounters.u64TotalCMEvidenceFH[v] +=
-                        g_Options.u64CMEvidenceFH[v];
-                }
-            }
-            else
-            {
-                PushNewInput(szLine);
-                if (TRUE == g_fExitProgram) break;
-                ParseUserInput(FALSE);
-            }
+            _ProcessSuiteLine(szLine, pos);
+            if (TRUE == g_fExitProgram) break;
         }
         fclose(p);
+        _PrintSuiteReport(dSuiteStart);
+    }
+}
 
-        // Banner and end results
-        dMult = (double)g_Options.uMyIncrement / (double)SUITE_NUM_HISTOGRAM;
-        Banner();
-        Trace("\n"
-              "TEST SCRIPT execution complete.  Final statistics:\n"
-              "--------------------------------------------------\n"
-              "    correct solutions   : %u\n"
-              "    incorrect solutions : %u\n"
-              "    total problems      : %u\n"
-              "    total nodecount     : %" 
-                   COMPILER_LONGLONG_UNSIGNED_FORMAT "\n"
-              "    avg. search speed   : %6.1f nps\n"
-              "    avg. solution time  : %3.1f sec\n"
-              "    avg. search depth   : %4.1f ply\n"
-              "    1st move beta cut   : %5.2f percent\n"
-              "    avg. eff. branching : %5.3f\n"
-              "    counter move hit %% : %5.2f percent (%"
-                   COMPILER_LONGLONG_UNSIGNED_FORMAT " tries)\n"
-              "    leftover            : %5.2f%% alpha, %5.2f%% FH (%"
-                   COMPILER_LONGLONG_UNSIGNED_FORMAT " tries)\n"
-              "    script time         : %6.1f sec\n\n",
-              g_SuiteCounters.uCorrect,
-              g_SuiteCounters.uIncorrect,
-              g_SuiteCounters.uTotal,
-              g_SuiteCounters.u64TotalNodeCount,
-              ((double)g_SuiteCounters.u64TotalNodeCount /
-               (SystemTimeStamp() - dSuiteStart)),
-              ((g_SuiteCounters.uCorrect > 0) ?
-               (g_SuiteCounters.dSigmaSolutionTime /
-                (double)g_SuiteCounters.uCorrect) : 0.0),
-              ((double)g_SuiteCounters.uSigmaDepth /
-               (double)g_SuiteCounters.uTotal),
-              (100.0 * (double)g_SuiteCounters.u64TotalBetaCutoffsOnFirstMove /
-               ((double)g_SuiteCounters.u64TotalBetaCutoffs + 1.0)),
-              (g_SuiteCounters.dSigmaEBF /
-               ((double)g_SuiteCounters.uEBFCount + 1.0)),
-              (100.0 * (double)g_SuiteCounters.u64TotalCounterMoveHits /
-               ((double)g_SuiteCounters.u64TotalCounterMoveTries + 1.0)),
-              g_SuiteCounters.u64TotalCounterMoveTries,
-              (100.0 * (double)g_SuiteCounters.u64TotalLeftoverAlpha /
-               ((double)g_SuiteCounters.u64TotalLeftoverTries + 1.0)),
-              (100.0 * (double)g_SuiteCounters.u64TotalLeftoverFH /
-               ((double)g_SuiteCounters.u64TotalLeftoverTries + 1.0)),
-              g_SuiteCounters.u64TotalLeftoverTries,
-              (SystemTimeStamp() - dSuiteStart));
 
-        // Countermove evidence calibration -- FH% per evidence bucket,
-        // an ongoing check that COUNTERMOVE_EVIDENCE_THRESHOLD (chess.h)
-        // is still well-calibrated as the engine/data evolve.
+COMMAND(EpdCommand)
+/**
+
+Routine description:
+
+    Runs a raw EPD test suite file directly -- no perl preprocessing
+    into a setboard/solution/go script first. Historically the only
+    way to run a suite from real-world EPD (the "board stm castle ep
+    [halfmove fullmove] bm <move>; id \"...\"; ..." format most public
+    tactical suites ship in) was tests/convert_epd.pl, which had a
+    real, silent-corruption bug: its single "everything between the
+    board and bm is [^b]+" regex breaks on any Black-to-move record
+    (the side-to-move field is literally the character "b"), and
+    because $fen/$id/$solution were unscoped globals rather than
+    per-line locals, a failed match silently carried the *previous*
+    record's board and solution forward instead of erroring --
+    confirmed live by feeding it a real 5-position batch, where the
+    one Black-to-move line came out as a byte-for-byte duplicate of
+    the line before it. This command replaces that whole external
+    preprocessing step with real per-record EPD parsing (see
+    ParseEpdRecord, fen.c) feeding the exact same
+    _ProcessSuiteLine/_PrintSuiteReport machinery ScriptCommand uses,
+    so a raw EPD file can just be handed to the engine directly.
+
+    Usage:
+
+        epd <required filename>
+
+Parameters:
+
+    The COMMAND macro hides four arguments from the input parser:
+
+        CHAR *szInput : the full line of input
+        ULONG argc    : number of argument chunks
+        CHAR *argv[]  : array of ptrs to each argument chunk
+        POSITION *pos : a POSITION pointer to operate on
+
+Return value:
+
+    void
+
+**/
+{
+    FILE *p;
+    static CHAR szLine[SMALL_STRING_LEN_CHAR];
+    static CHAR szSynth[SMALL_STRING_LEN_CHAR];
+    CHAR szFen[SMALL_STRING_LEN_CHAR];
+    CHAR szId[SMALL_STRING_LEN_CHAR];
+    CHAR szMoves[SUITE_MAX_SOLUTIONS + SUITE_MAX_AVOIDS][SMALL_STRING_LEN_CHAR];
+    ULONG uNumMoves;
+    FLAG fIsAvoid;
+    double dSuiteStart;
+    ULONG u;
+    ULONG uLineNum = 0;
+
+    if (argc < 2)
+    {
+        Trace("Error (Usage: epd <filename>): %s\n", argv[0]);
+        return;
+    }
+    if (FALSE == SystemDoesFileExist(argv[1]))
+    {
+        Trace("Error (file doesn't exist): %s\n", argv[1]);
+        return;
+    }
+
+    p = fopen(argv[1], "rb");
+    if (NULL != p)
+    {
+        dSuiteStart = SystemTimeStamp();
+        memset(&(g_SuiteCounters), 0, sizeof(g_SuiteCounters));
+        while(fgets(szLine, ARRAY_LENGTH(szLine), p))
         {
-            static const ULONG uCMEvidenceFloors[CM_EVIDENCE_BUCKETS] =
-                { 0, 1, 100, 1000, 10000, 100000, 1000000 };
-            Trace("\ncountermove evidence calibration:\n");
-            for (v = 0; v < CM_EVIDENCE_BUCKETS; v++)
+            uLineNum++;
+            if (FALSE == ParseEpdRecord(szLine, szFen, ARRAY_LENGTH(szFen),
+                                        szId, ARRAY_LENGTH(szId),
+                                        szMoves, ARRAY_LENGTH(szMoves),
+                                        &uNumMoves, &fIsAvoid))
             {
-                Trace("    evidence >= %8lu : %5.2f%% FH (%"
-                      COMPILER_LONGLONG_UNSIGNED_FORMAT " tries)\n",
-                      uCMEvidenceFloors[v],
-                      (100.0 * (double)g_SuiteCounters.u64TotalCMEvidenceFH[v] /
-                       ((double)g_SuiteCounters.u64TotalCMEvidenceTries[v] + 1.0)),
-                      g_SuiteCounters.u64TotalCMEvidenceTries[v]);
+                if (szLine[0] && (szLine[0] != '\n') && (szLine[0] != '#'))
+                {
+                    Trace("epd: skipping unparseable line %lu: %s",
+                          uLineNum, szLine);
+                }
+                continue;
             }
-        }
 
-        // Histogram stuff
-        if (g_SuiteCounters.uTotal > 0) {
-            uMax = g_SuiteCounters.uHistogram[0];
-            for (u = 1; u < SUITE_NUM_HISTOGRAM; u++) 
+            snprintf(szSynth, ARRAY_LENGTH(szSynth), "setboard %s\n", szFen);
+            _ProcessSuiteLine(szSynth, pos);
+            if (TRUE == g_fExitProgram) break;
+
+            if (szId[0])
             {
-                if (g_SuiteCounters.uHistogram[u] > uMax) 
-                {
-                    uMax = g_SuiteCounters.uHistogram[u];
-                }
+                snprintf(szSynth, ARRAY_LENGTH(szSynth), "id %s\n", szId);
+                _ProcessSuiteLine(szSynth, pos);
             }
-            for (u = 0; u < SUITE_NUM_HISTOGRAM; u++)
+
+            for (u = 0; u < uNumMoves; u++)
             {
-                Trace("%4.1f .. %4.1f: ",
-                      (double)u * dMult, (double)(u + 1) * dMult);
-                for (v = 0;
-                     (uMax > 0) && (v < 50 * g_SuiteCounters.uHistogram[u] / uMax);
-                     v++)
-                {
-                    Trace("*");
-                }
-                Trace("\n");
+                snprintf(szSynth, ARRAY_LENGTH(szSynth), "%s %s\n",
+                          fIsAvoid ? "avoid" : "solution", szMoves[u]);
+                _ProcessSuiteLine(szSynth, pos);
             }
+
+            _ProcessSuiteLine("go\n", pos);
+            if (TRUE == g_fExitProgram) break;
         }
+        fclose(p);
+        _PrintSuiteReport(dSuiteStart);
     }
 }
 
-FLAG 
+
+FLAG
 WeAreRunningASuite(void)
 /**