Merge pull request #2 from ok2/feature/swiftforth-number-conversion

feat(core): SwiftForth input number conversion, DPL and NH

CHANGELOG.md

@@ -5,6 +5,32 @@ All notable changes to WAFER are documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [0.2.2] - 2026-08-06
+
+### Added
+
+- **SwiftForth-style input number conversion.** Punctuation (`,` `.` `+`
+  `/` `:` and an embedded `-`) anywhere after the leftmost digit now forces
+  double-cell conversion, so `12.34`, `1,234`, `12:30:45` and `2026-08-06`
+  all convert as doubles without a custom parser. Previously only a
+  trailing `.` worked and `1.5` was an "unknown word" error. The
+  punctuation is a double-cell marker, not a fractional point: every
+  spelling of `1234` (`1234.`, `123.4`, `.1234`) yields the same value.
+- **`DPL`** ( -- addr ): digits to the right of the rightmost punctuation
+  character in the last converted number, negative when the token carried
+  none. Seeded at -1024 and bumped once per digit, matching `sf64`.
+  Together with `<# #>` this is how fixed-point input is scaled.
+- **`NH`** ( -- addr ): the high-order cell dropped by a single-cell
+  conversion, so a token that overflows a cell can be recovered as a
+  double (`4000000000 NH @ D.`).
+
+Verified token-for-token against SwiftForth `sf64`: DPL values, double
+promotion and sign handling agree on every probed form. One deliberate
+divergence — WAFER also accepts a sign before a base prefix (`-$FF`), which
+`sf64` rejects; the Forth 2012 spelling `$-FF` works in both. A leading `+`
+is punctuation rather than a sign in both engines, so `+7` is the double 7
+with `DPL` = 1.
+
 ## [0.2.1] - 2026-08-06
 
 ### Fixed

CLAUDE.md

@@ -79,7 +79,7 @@ Handle in `interpret_token_immediate()` or `compile_token()` as a special case.
 
 ## Testing
 
-- Run `cargo test --workspace` before committing (currently 542 unit + 1 benchmark + 11 compliance + 9 comparison + 5 crypto)
+- Run `cargo test --workspace` before committing (currently 562 unit + 1 benchmark + 11 compliance + 9 comparison + 5 crypto)
 - Forth 2012 compliance: `cargo test -p wafer-core --test compliance`
 - Cross-engine comparison (vs gforth): `cargo test -p wafer-core --test comparison`
 - Performance benchmarks (release mode): `cargo test -p wafer-core --test comparison -- --nocapture --ignored`

Cargo.lock

@@ -132,15 +132,6 @@ dependencies = [
  "generic-array",
 ]
 
-[[package]]
-name = "block-buffer"
-version = "0.12.1"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "d2f6c7dbe95a6ed67ad9f18e57daf93a2f034c524b99fd2b76d18fdfeb6660aa"
-dependencies = [
- "hybrid-array",
-]
-
 [[package]]
 name = "bumpalo"
 version = "3.20.3"
@@ -182,9 +173,9 @@ checksum = "f079e83a288787bcd14a6aea84cee5c87a67c5a3e660c30f557a3d24761b3527"
 
 [[package]]
 name = "clap"
-version = "4.6.5"
+version = "4.6.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "301b56658598e48f3648647ac6fc887be7e7108eddfa4e9b63fcf3ec58c0cadf"
+checksum = "473c7e07f409a8d772161724aa8db6a765a2532a70f9667eeb7b49d3d02fbdca"
 dependencies = [
  "clap_builder",
  "clap_derive",
@@ -192,9 +183,9 @@ dependencies = [
 
 [[package]]
 name = "clap_builder"
-version = "4.6.5"
+version = "4.6.6"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "94a65403d1a1bd28f7dc68eb8506e8874808ee5eecb59298de588e2e1407a078"
+checksum = "7b48fea5a88e9ae728a2dcbedbfc0e730f7d60da42e1cb049a83c9fb8b789889"
 dependencies = [
  "anstream",
  "anstyle",
@@ -255,12 +246,6 @@ dependencies = [
  "windows-sys",
 ]
 
-[[package]]
-name = "const-oid"
-version = "0.10.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "a6ef517f0926dd24a1582492c791b6a4818a4d94e789a334894aa15b0d12f55c"
-
 [[package]]
 name = "cpp_demangle"
 version = "0.5.1"
@@ -279,15 +264,6 @@ dependencies = [
  "libc",
 ]
 
-[[package]]
-name = "cpufeatures"
-version = "0.3.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "8b2a41393f66f16b0823bb79094d54ac5fbd34ab292ddafb9a0456ac9f87d201"
-dependencies = [
- "libc",
-]
-
 [[package]]
 name = "cranelift-assembler-x64"
 version = "0.134.3"
@@ -352,7 +328,7 @@ dependencies = [
  "rustc-hash",
  "serde",
  "serde_derive",
- "sha2 0.10.9",
+ "sha2",
  "smallvec",
  "target-lexicon",
  "wasmtime-internal-core",
@@ -478,15 +454,6 @@ dependencies = [
  "typenum",
 ]
 
-[[package]]
-name = "crypto-common"
-version = "0.2.2"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "ce6e4c961d6cd6c9a86db418387425e8bdeaf05b3c8bc1411e6dca4c252f1453"
-dependencies = [
- "hybrid-array",
-]
-
 [[package]]
 name = "debugid"
 version = "0.8.0"
@@ -502,19 +469,8 @@ version = "0.10.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "9ed9a281f7bc9b7576e61468ba615a66a5c8cfdff42420a70aa82701a3b1e292"
 dependencies = [
- "block-buffer 0.10.4",
+ "block-buffer",
- "crypto-common 0.1.7",
+ "crypto-common",
-]
-
-[[package]]
-name = "digest"
-version = "0.11.3"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "f1dd6dbb5841937940781866fa1281a1ff7bd3bf827091440879f9994983d5c2"
-dependencies = [
- "block-buffer 0.12.1",
- "const-oid",
- "crypto-common 0.2.2",
 ]
 
 [[package]]
@@ -795,15 +751,6 @@ dependencies = [
  "windows-sys",
 ]
 
-[[package]]
-name = "hybrid-array"
-version = "0.4.14"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "707114b52a152fa7bdb290cd7cd5912d9467273b6d74e21b8d81aca1f8533f6b"
-dependencies = [
- "typenum",
-]
-
 [[package]]
 name = "id-arena"
 version = "2.3.0"
@@ -1400,13 +1347,13 @@ dependencies = [
 
 [[package]]
 name = "sha1"
-version = "0.11.0"
+version = "0.10.7"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "aacc4cc499359472b4abe1bf11d0b12e688af9a805fa5e3016f9a386dc2d0214"
+checksum = "a978451301f4db1d02937a4ab3ccce137717b81826e79b7d49ffe3244a13c3b8"
 dependencies = [
  "cfg-if",
- "cpufeatures 0.3.0",
+ "cpufeatures",
- "digest 0.11.3",
+ "digest",
 ]
 
 [[package]]
@@ -1416,19 +1363,8 @@ source = "registry+https://github.com/rust-lang/crates.io-index"
 checksum = "a7507d819769d01a365ab707794a4084392c824f54a7a6a7862f8c3d0892b283"
 dependencies = [
  "cfg-if",
- "cpufeatures 0.2.17",
+ "cpufeatures",
- "digest 0.10.7",
+ "digest",
-]
-
-[[package]]
-name = "sha2"
-version = "0.11.0"
-source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "446ba717509524cb3f22f17ecc096f10f4822d76ab5c0b9822c5f9c284e825f4"
-dependencies = [
- "cfg-if",
- "cpufeatures 0.3.0",
- "digest 0.11.3",
 ]
 
 [[package]]
@@ -1653,7 +1589,7 @@ checksum = "0b928f33d975fc6ad9f86c8f283853ad26bdd5b10b7f1542aa2fa15e2289105a"
 
 [[package]]
 name = "wafer"
-version = "0.2.1"
+version = "0.2.2"
 dependencies = [
  "anyhow",
  "clap",
@@ -1664,13 +1600,13 @@ dependencies = [
 
 [[package]]
 name = "wafer-core"
-version = "0.2.1"
+version = "0.2.2"
 dependencies = [
  "anyhow",
  "insta",
  "proptest",
  "sha1",
- "sha2 0.11.0",
+ "sha2",
  "thiserror 2.0.19",
  "wasm-encoder 0.255.0",
  "wasmparser 0.255.0",
@@ -1679,7 +1615,7 @@ dependencies = [
 
 [[package]]
 name = "wafer-web"
-version = "0.2.1"
+version = "0.2.2"
 dependencies = [
  "anyhow",
  "js-sys",
@@ -1966,7 +1902,7 @@ dependencies = [
  "semver",
  "serde",
  "serde_derive",
- "sha2 0.10.9",
+ "sha2",
  "smallvec",
  "target-lexicon",
  "wasm-encoder 0.252.0",
@@ -1989,7 +1925,7 @@ dependencies = [
  "rustix",
  "serde",
  "serde_derive",
- "sha2 0.10.9",
+ "sha2",
  "toml",
  "wasmtime-environ",
  "windows-sys",
@@ -2239,18 +2175,18 @@ dependencies = [
 
 [[package]]
 name = "zerocopy"
-version = "0.8.55"
+version = "0.8.56"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "b5a105cd7b140f6eeec8acff2ea38135d3cab283ada58540f629fe51e46696eb"
+checksum = "556764e583adb45a9f8d413c2a147fa7e8d821e48e12b14fd560b607998b75eb"
 dependencies = [
  "zerocopy-derive",
 ]
 
 [[package]]
 name = "zerocopy-derive"
-version = "0.8.55"
+version = "0.8.56"
 source = "registry+https://github.com/rust-lang/crates.io-index"
-checksum = "0fe976fb70c78cd64cccfe3a6fc142244e8a77b70959b30faf9d0ac37ee228eb"
+checksum = "f2ab42fc20575779bd240faa45f94a74256f755c0fa9e89f0ede20d91d0cdfc1"
 dependencies = [
  "proc-macro2",
  "quote",

Cargo.toml

@@ -3,7 +3,7 @@ members = ["crates/*"]
 resolver = "2"
 
 [workspace.package]
-version = "0.2.1"
+version = "0.2.2"
 edition = "2024"
 license = "MIT OR Apache-2.0"
 repository = "https://github.com/ok2/wafer"
@@ -48,6 +48,6 @@ anyhow = "1"
 thiserror = "2"
 proptest = "1"
 insta = "1"
-sha1 = "0.11"
+sha1 = "0.10"
-sha2 = "0.11"
+sha2 = "0.10"
 send_wrapper = "0.6"

crates/core/src/memory.rs

@@ -108,6 +108,23 @@ pub const SYSVAR_HLD: u32 = SYSVAR_BASE + 28;
 pub const SYSVAR_LEAVE_FLAG: u32 = SYSVAR_BASE + 32;
 /// Throw code left by a compiled stack-guard fault for `_STACK_FAULT_`.
 pub const SYSVAR_FAULT_CODE: u32 = SYSVAR_BASE + 36;
+/// DPL: digits right of the rightmost punctuation in the last converted
+/// number; negative when the token carried no punctuation.
+pub const SYSVAR_DPL: u32 = SYSVAR_BASE + 40;
+/// NH: high-order cell of the last single-cell conversion, so an
+/// out-of-range token can be recovered as a double.
+pub const SYSVAR_NH: u32 = SYSVAR_BASE + 44;
+
+/// Seed for [`SYSVAR_DPL`] before conversion starts.
+///
+/// `SwiftForth` seeds DPL with a negative value and bumps it once per digit,
+/// so an unpunctuated token still ends up negative. Punctuation resets the
+/// counter to zero, which makes the final value the digit count right of the
+/// rightmost punctuation character.
+///
+/// The exact seed is observable: `sf64` reports DPL as -1020 after `1234`
+/// and -1023 after `-1`, both of which pin it to -1024.
+pub const DPL_INIT: i32 = -1024;
 
 #[cfg(test)]
 mod tests {
@@ -149,6 +166,9 @@ mod tests {
             SYSVAR_NUM_TIB,
             SYSVAR_HLD,
             SYSVAR_LEAVE_FLAG,
+            SYSVAR_FAULT_CODE,
+            SYSVAR_DPL,
+            SYSVAR_NH,
         ];
         for offset in all_offsets {
             assert!(offset + CELL_SIZE <= SYSVAR_BASE + SYSVAR_SIZE);

crates/core/src/outer.rs

@@ -23,12 +23,64 @@ use crate::ir::IrOp;
 #[cfg(feature = "crypto")]
 use crate::memory::HASH_SCRATCH_BASE;
 use crate::memory::{
-    CELL_SIZE, DATA_STACK_TOP, FLOAT_SIZE, FLOAT_STACK_BASE, FLOAT_STACK_TOP, INPUT_BUFFER_BASE,
+    CELL_SIZE, DATA_STACK_TOP, DPL_INIT, FLOAT_SIZE, FLOAT_STACK_BASE, FLOAT_STACK_TOP,
-    INPUT_BUFFER_SIZE, RETURN_STACK_TOP, SYSVAR_BASE_VAR, SYSVAR_FAULT_CODE, SYSVAR_HERE,
+    INPUT_BUFFER_BASE, INPUT_BUFFER_SIZE, RETURN_STACK_TOP, SYSVAR_BASE_VAR, SYSVAR_DPL,
-    SYSVAR_LEAVE_FLAG, SYSVAR_NUM_TIB, SYSVAR_STATE, SYSVAR_TO_IN,
+    SYSVAR_FAULT_CODE, SYSVAR_HERE, SYSVAR_LEAVE_FLAG, SYSVAR_NH, SYSVAR_NUM_TIB, SYSVAR_STATE,
+    SYSVAR_TO_IN,
 };
 use crate::optimizer::optimize;
 
+// ---------------------------------------------------------------------------
+// Number conversion
+// ---------------------------------------------------------------------------
+
+/// Characters that force double-cell conversion, following `SwiftForth`'s
+/// input number conversion rules.
+///
+/// A leading `-` is the one exception: it binds as a sign, which keeps `-1`
+/// a single-cell number while `1-2` converts as a double.
+const DOUBLE_PUNCTUATION: [u8; 6] = *b",.+-/:";
+
+/// Split a leading minus off a token, returning whether it was negative.
+///
+/// Only `-` is a sign. A leading `+` stays punctuation, matching `sf64`,
+/// where `+7` converts as the double 7 with `DPL` = 1.
+///
+/// The sign may sit between a base-override prefix and the digits (`$-FF`,
+/// the Forth 2012 spelling) or, as a WAFER extension, before the prefix
+/// (`-$FF`), so this runs at both positions.
+fn strip_sign(s: &str) -> (bool, &str) {
+    match s.as_bytes().first() {
+        Some(b'-') => (true, &s[1..]),
+        _ => (false, s),
+    }
+}
+
+/// A numeric token that converted successfully.
+#[derive(Debug, Clone, Copy, PartialEq, Eq)]
+struct NumberLiteral {
+    /// The accumulated 64-bit value, sign applied.
+    value: i64,
+    /// Digits right of the rightmost punctuation character. Negative when the
+    /// token carried no punctuation, which is how `DPL` reports "single-cell".
+    dpl: i32,
+    /// Whether punctuation forced double-cell conversion.
+    is_double: bool,
+}
+
+impl NumberLiteral {
+    /// Low-order cell — the value a single-cell conversion leaves on the stack.
+    fn lo(self) -> i32 {
+        self.value as i32
+    }
+
+    /// High-order cell. For a single-cell conversion this is what `NH` holds,
+    /// letting an out-of-range token be recovered as a double.
+    fn hi(self) -> i32 {
+        (self.value >> 32) as i32
+    }
+}
+
 // ---------------------------------------------------------------------------
 // Control-flow compilation state
 // ---------------------------------------------------------------------------
@@ -1194,22 +1246,18 @@ impl<R: Runtime> ForthVM<R> {
             return Ok(());
         }
 
-        // Try to parse as double-number (trailing dot)
+        // Try to convert as a number; punctuation makes it double-cell
-        if let Some((lo, hi)) = self.parse_double_number(token) {
+        if let Some(lit) = self.parse_numeric_literal(token) {
-            self.push_data_stack(lo)?;
+            self.record_number_conversion(lit);
-            self.push_data_stack(hi)?;
+            self.push_data_stack(lit.lo())?;
             if self.recording_toplevel && self.state == 0 {
-                self.toplevel_ir.push(IrOp::PushI32(lo));
+                self.toplevel_ir.push(IrOp::PushI32(lit.lo()));
-                self.toplevel_ir.push(IrOp::PushI32(hi));
             }
-            return Ok(());
+            if lit.is_double {
-        }
+                self.push_data_stack(lit.hi())?;
-
-        // Try to parse as number
-        if let Some(n) = self.parse_number(token) {
-            self.push_data_stack(n)?;
                 if self.recording_toplevel && self.state == 0 {
-                self.toplevel_ir.push(IrOp::PushI32(n));
+                    self.toplevel_ir.push(IrOp::PushI32(lit.hi()));
+                }
             }
             return Ok(());
         }
@@ -1571,16 +1619,13 @@ impl<R: Runtime> ForthVM<R> {
             return Ok(());
         }
 
-        // Try to parse as double-number (trailing dot)
+        // Try to convert as a number; punctuation makes it double-cell
-        if let Some((lo, hi)) = self.parse_double_number(token) {
+        if let Some(lit) = self.parse_numeric_literal(token) {
-            self.push_ir(IrOp::PushI32(lo));
+            self.record_number_conversion(lit);
-            self.push_ir(IrOp::PushI32(hi));
+            self.push_ir(IrOp::PushI32(lit.lo()));
-            return Ok(());
+            if lit.is_double {
+                self.push_ir(IrOp::PushI32(lit.hi()));
             }
-
-        // Try to parse as number
-        if let Some(n) = self.parse_number(token) {
-            self.push_ir(IrOp::PushI32(n));
             return Ok(());
         }
 
@@ -2731,85 +2776,111 @@ impl<R: Runtime> ForthVM<R> {
     // Number parsing
     // -----------------------------------------------------------------------
 
-    /// Try to parse a token as a number.
+    /// Try to convert a token to a number, following `SwiftForth`'s input
-    fn parse_number(&self, token: &str) -> Option<i32> {
+    /// number conversion rules.
+    ///
+    /// Punctuation (`,` `.` `+` `-` `/` `:`) forces double-cell conversion, so
+    /// `12.34`, `1,234`, `12:30:45` and `2026-08-06` all convert as doubles.
+    /// Only a leading `-` escapes this and binds as a sign, which keeps `-1`
+    /// single-cell; a leading `+` stays punctuation, so `+7` is the double 7.
+    ///
+    /// `DPL` counts up once per digit from [`DPL_INIT`] and resets to zero at
+    /// every punctuation character, so it ends up holding the digit count right
+    /// of the rightmost punctuation, and stays negative for unpunctuated tokens.
+    fn parse_numeric_literal(&self, token: &str) -> Option<NumberLiteral> {
         let token = token.trim();
         if token.is_empty() {
             return None;
         }
 
-        // Check for negative prefix
+        // A leading sign binds to the number; it is not double punctuation.
-        let (negative, rest) = if let Some(stripped) = token.strip_prefix('-') {
+        let (neg_outer, rest) = strip_sign(token);
-            (true, stripped)
-        } else {
-            (false, token)
-        };
 
         if rest.is_empty() {
             return None;
         }
 
-        // Parse based on prefix
+        // Character literal: 'x' → ASCII value of x. No digits, so DPL stays
-        let result = if let Some(hex) = rest.strip_prefix('$') {
+        // at its seed and the result is always single-cell.
-            i64::from_str_radix(hex, 16).ok()
+        if rest.len() == 3 && rest.as_bytes()[0] == b'\'' && rest.as_bytes()[2] == b'\'' {
-        } else if let Some(dec) = rest.strip_prefix('#') {
+            let value = i64::from(rest.as_bytes()[1]);
-            dec.parse::<i64>().ok()
+            return Some(NumberLiteral {
-        } else if let Some(bin) = rest.strip_prefix('%') {
+                value: if neg_outer { -value } else { value },
-            i64::from_str_radix(bin, 2).ok()
+                dpl: DPL_INIT,
-        } else if rest.len() == 3 && rest.as_bytes()[0] == b'\'' && rest.as_bytes()[2] == b'\'' {
+                is_double: false,
-            // Character literal: 'x' → ASCII value of x
+            });
-            Some(rest.as_bytes()[1] as i64)
-        } else {
-            i64::from_str_radix(rest, self.base).ok()
-        };
-
-        result.map(|n| if negative { -(n as i32) } else { n as i32 })
         }
 
-    /// Try to parse a token as a double-number (token ends with `.`).
+        // A base-override prefix sits before the leftmost digit.
-    /// Returns (lo, hi) where the double-cell value is (hi << 32) | lo.
+        let (radix, after_prefix) = match rest.as_bytes()[0] {
-    fn parse_double_number(&self, token: &str) -> Option<(i32, i32)> {
+            b'$' => (16, &rest[1..]),
-        let token = token.trim();
+            b'#' => (10, &rest[1..]),
-        if token.is_empty() {
+            b'%' => (2, &rest[1..]),
+            _ => (self.base, rest),
+        };
+
+        // Forth 2012 spells a signed based number `#-1289`, so the sign can
+        // also follow the prefix. Either way it precedes the leftmost digit
+        // and so is a sign rather than double punctuation.
+        let (neg_inner, digits) = strip_sign(after_prefix);
+        let negative = neg_outer ^ neg_inner;
+
+        if digits.is_empty() {
             return None;
         }
 
-        // Check for trailing dot (double-number indicator)
+        // Walk the digit string, stripping punctuation and tracking DPL.
-        let without_dot = token.strip_suffix('.')?;
+        let mut buf = String::with_capacity(digits.len());
-        if without_dot.is_empty() {
+        let mut dpl = DPL_INIT;
+        let mut is_double = false;
+        for &b in digits.as_bytes() {
+            if DOUBLE_PUNCTUATION.contains(&b) {
+                is_double = true;
+                dpl = 0;
+            } else {
+                buf.push(char::from(b));
+                dpl += 1;
+            }
+        }
+
+        if buf.is_empty() {
             return None;
         }
 
-        // Check for negative prefix
+        // i128 accumulation so the full u64 range survives conversion.
-        let (negative, rest) = if let Some(stripped) = without_dot.strip_prefix('-') {
+        let magnitude = i128::from_str_radix(&buf, radix).ok()?;
-            (true, stripped)
+        let value = if negative {
+            -(magnitude as i64)
         } else {
-            (false, without_dot)
+            magnitude as i64
         };
 
-        if rest.is_empty() {
+        Some(NumberLiteral {
-            return None;
+            value,
-        }
+            dpl,
-
+            is_double,
-        // Parse based on prefix -- use i128 to handle the full u64 range
-        let result: Option<i128> = if let Some(hex) = rest.strip_prefix('$') {
-            i128::from_str_radix(hex, 16).ok()
-        } else if let Some(dec) = rest.strip_prefix('#') {
-            dec.parse::<i128>().ok()
-        } else if let Some(bin) = rest.strip_prefix('%') {
-            i128::from_str_radix(bin, 2).ok()
-        } else {
-            i128::from_str_radix(rest, self.base).ok()
-        };
-
-        result.map(|n| {
-            let val: i64 = if negative { -(n as i64) } else { n as i64 };
-            let lo = val as i32;
-            let hi = (val >> 32) as i32;
-            (lo, hi)
         })
     }
 
+    /// Publish the outcome of a conversion in `DPL` and `NH`.
+    ///
+    /// `NH` only carries meaning after a single-cell conversion, where it holds
+    /// the high-order cell that the stack result dropped.
+    fn record_number_conversion(&mut self, lit: NumberLiteral) {
+        self.rt.mem_write_i32(SYSVAR_DPL, lit.dpl);
+        if !lit.is_double {
+            self.rt.mem_write_i32(SYSVAR_NH, lit.hi());
+        }
+    }
+
+    /// Try to parse a token as a single-cell number, ignoring `DPL`/`NH`.
+    /// Used where only a plain cell value is meaningful.
+    fn parse_number(&self, token: &str) -> Option<i32> {
+        self.parse_numeric_literal(token)
+            .filter(|lit| !lit.is_double)
+            .map(NumberLiteral::lo)
+    }
+
     // -----------------------------------------------------------------------
     // Float literal parsing
     // -----------------------------------------------------------------------
@@ -3092,6 +3163,7 @@ impl<R: Runtime> ForthVM<R> {
         self.register_to_in()?;
         self.register_state_var()?;
         self.register_base_var()?;
+        self.register_number_conversion_vars()?;
 
         // Double-cell arithmetic
         self.register_m_star()?;
@@ -5151,6 +5223,22 @@ impl<R: Runtime> ForthVM<R> {
         Ok(())
     }
 
+    /// DPL ( -- addr ) and NH ( -- addr ): input number conversion results.
+    ///
+    /// `DPL` holds the digit count right of the rightmost punctuation
+    /// character in the last converted number, or a negative value when the
+    /// token carried none. `NH` holds the high-order cell dropped by a
+    /// single-cell conversion, so an out-of-range token can be recovered as a
+    /// double.
+    fn register_number_conversion_vars(&mut self) -> anyhow::Result<()> {
+        self.rt.mem_write_i32(SYSVAR_DPL, DPL_INIT);
+        self.rt.mem_write_i32(SYSVAR_NH, 0);
+
+        self.register_primitive("DPL", false, vec![IrOp::PushI32(SYSVAR_DPL as i32)])?;
+        self.register_primitive("NH", false, vec![IrOp::PushI32(SYSVAR_NH as i32)])?;
+        Ok(())
+    }
+
     /// M* ( n1 n2 -- d ) signed multiply producing double-cell result.
     fn register_m_star(&mut self) -> anyhow::Result<()> {
         let func: HostFn = Box::new(move |ctx: &mut dyn HostAccess| {
@@ -10828,6 +10916,111 @@ mod tests {
         assert_eq!(eval_stack("1E 2.5E 1E F~"), vec![0]); // |1-2.5| = 1.5 >= 1
     }
 
+    #[test]
+    fn punctuation_anywhere_converts_as_double() {
+        // The punctuation is a double-cell marker, not a fractional point:
+        // every form below carries the same digits, so the value is the same.
+        // eval_stack reports top-first, so a double reads as [hi, lo].
+        for token in ["1234.", "123.4", "12.34", "1.234", ".1234"] {
+            assert_eq!(eval_stack(token), vec![0, 1234], "token {token}");
+        }
+        // SwiftForth accepts comma, colon, slash, plus and dash too, which is
+        // what makes dates and times convert without a custom parser.
+        assert_eq!(eval_stack("1,234"), vec![0, 1234]);
+        assert_eq!(eval_stack("12:30:45"), vec![0, 123045]);
+        assert_eq!(eval_stack("2026-08-06"), vec![0, 20260806]);
+        assert_eq!(eval_stack("12/34"), vec![0, 1234]);
+        assert_eq!(eval_stack("1+234"), vec![0, 1234]);
+    }
+
+    #[test]
+    fn dpl_counts_digits_right_of_last_punctuation() {
+        for (token, dpl) in [("1234.", 0), ("123.4", 1), ("12.34", 2), (".1234", 4)] {
+            assert_eq!(eval_stack(&format!("{token} 2DROP DPL @")), vec![dpl]);
+        }
+        // Only the rightmost punctuation counts.
+        assert_eq!(eval_stack("12:30:45 2DROP DPL @"), vec![2]);
+    }
+
+    #[test]
+    fn dpl_stays_negative_for_unpunctuated_numbers() {
+        // A leading minus is a sign, not punctuation, so these stay single-cell.
+        for token in ["1234", "-1", "$FF"] {
+            let dpl = eval_stack(&format!("{token} DROP DPL @"))[0];
+            assert!(dpl < 0, "token {token} left DPL = {dpl}");
+        }
+        assert_eq!(eval_stack("-1"), vec![-1]);
+        // DPL counts up from its seed once per digit.
+        assert_eq!(eval_stack("1234 DROP DPL @"), vec![DPL_INIT + 4]);
+        assert_eq!(eval_stack("-1 DROP DPL @"), vec![DPL_INIT + 1]);
+    }
+
+    #[test]
+    fn leading_plus_is_punctuation_not_a_sign() {
+        // sf64 converts `+7` as the double 7 with DPL = 1: unlike `-`, a
+        // leading `+` does not bind to the number.
+        assert_eq!(eval_stack("+7"), vec![0, 7]);
+        assert_eq!(eval_stack("+7 2DROP DPL @"), vec![1]);
+        // Same after a base prefix.
+        assert_eq!(eval_stack("#+7"), vec![0, 7]);
+        assert_eq!(eval_stack("$+F"), vec![0, 15]);
+    }
+
+    #[test]
+    fn repeated_punctuation_only_counts_from_the_last_one() {
+        // sf64: `12..34` is 1234 with DPL 2, `1-2-3` is 123 with DPL 1.
+        assert_eq!(eval_stack("12..34"), vec![0, 1234]);
+        assert_eq!(eval_stack("12..34 2DROP DPL @"), vec![2]);
+        assert_eq!(eval_stack("1-2-3"), vec![0, 123]);
+        assert_eq!(eval_stack("1-2-3 2DROP DPL @"), vec![1]);
+    }
+
+    #[test]
+    fn nh_recovers_an_out_of_range_single_number() {
+        // 4000000000 overflows a signed cell, so the stack value is truncated.
+        assert_eq!(eval_stack("4000000000"), vec![-294967296]);
+        // NH carries the high cell, making the true value recoverable.
+        assert_eq!(eval_stack("4000000000 NH @"), vec![0, -294967296]);
+        assert_eq!(eval_output("4000000000 NH @ D."), "4000000000 ");
+    }
+
+    #[test]
+    fn float_literals_still_win_over_double_punctuation() {
+        // `1.5E0` has an embedded dot, but "15E0" is not a decimal number,
+        // so conversion falls through to the float parser.
+        assert_eq!(eval_output("1.5E0 F."), "1.500000 ");
+        assert_eq!(eval_output("-3.25E0 F."), "-3.250000 ");
+        assert_eq!(eval_output("1E-3 F."), "0.001000 ");
+    }
+
+    #[test]
+    fn double_punctuation_respects_base_prefixes() {
+        assert_eq!(eval_stack("$FF."), vec![0, 255]);
+        assert_eq!(eval_stack("$F.F"), vec![0, 255]);
+        assert_eq!(eval_stack("%1010."), vec![0, 10]);
+        assert_eq!(eval_stack("#12.34"), vec![0, 1234]);
+        assert_eq!(eval_stack("-$FF."), vec![-1, -255]);
+    }
+
+    #[test]
+    fn sign_after_a_base_prefix_is_a_sign_not_punctuation() {
+        // Forth 2012 spells signed based numbers with the sign after the
+        // prefix. The dash precedes the leftmost digit, so it must not
+        // trigger double-cell conversion.
+        assert_eq!(eval_stack("#-1289"), vec![-1289]);
+        assert_eq!(eval_stack("$-12eF"), vec![-4847]);
+        assert_eq!(eval_stack("%-10010110"), vec![-150]);
+        // The sign may also precede the prefix, and both spellings cancel.
+        assert_eq!(eval_stack("-$FF"), vec![-255]);
+        assert_eq!(eval_stack("-$-FF"), vec![255]);
+    }
+
+    #[test]
+    fn punctuated_numbers_compile_into_definitions() {
+        assert_eq!(eval_stack(": D1 12.34 ; D1"), vec![0, 1234]);
+        assert_eq!(eval_output(": STAMP 2026-08-06 D. ; STAMP"), "20260806 ");
+    }
+
     #[test]
     fn optimizer_doesnt_break_basic_arithmetic() {
         assert_eq!(eval_stack("5 3 +"), vec![8]);

crates/core/src/wordhelp.rs

@@ -350,6 +350,16 @@ pub const WORD_DOCS: &[(&str, &str, &str)] = &[
         "Convert digits, accumulating into ud.",
     ),
     ("BASE", "( -- addr )", "Variable holding the number base."),
+    (
+        "DPL",
+        "( -- addr )",
+        "Variable: digits right of the last punctuation; negative if none.",
+    ),
+    (
+        "NH",
+        "( -- addr )",
+        "Variable: high cell dropped by the last single-cell conversion.",
+    ),
     ("HEX", "( -- )", "Set BASE to sixteen."),
     ("DECIMAL", "( -- )", "Set BASE to ten."),
     // -- Core: strings --

deny.toml

@@ -18,11 +18,11 @@ confidence-threshold = 0.8
 [bans]
 multiple-versions = "deny"
 wildcards = "deny"
-# Transitive duplicates from wasmtime v31 -- will resolve when upgrading
+# Transitive duplicates from wasmtime v47 dependencies
 skip = [
     "getrandom",
+    "syn",
     "hashbrown",
-    "r-efi",
     "thiserror",
     "thiserror-impl",
     "wasm-encoder",