Start pplus-library: 16 verified routines in six modules

Routines written once in pseudo and checked at every level, so programs
can use them by name instead of rewriting and re-verifying them:

- stats: Mean, Variance (two-pass)
- numerics: KahanSum, LinearInterp, Trapezoid
- align: LinearGapPenalty, AffineGapPenalty, MatchScore,
  NeedlemanWunschScore
- md: LennardJones, LennardJonesForce, MinimumImage, PairDistance
- seq: GCContent, HammingDistance
- special: ErfApprox (Abramowitz and Stegun 7.1.26)

Each has contracts, cases, reference implementations in Python, Mojo
and (for the numerical ones) C at more than one level, and nine have a
Dafny proof over exact numbers. status.json and STATUS.md are written by
pplus-core's library-check: every check passes or is open/unverified as
listed there. The Mojo references still need the pinned compiler's
answers (library-verify-mojo, network).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01FgvbRdoEheAHqsRmr2WuKZ
This commit is contained in:
alexmandClaude committed 2026-10-05 11:58:22 +00:00
commit df12b2a008
103 files changed
+3025

No files matched your search

+12
View File
@@ -0,0 +1,12 @@
{
"tool": "dafny",
"version": "4.11.0",
"flags": [
"verify",
"--resource-limit",
"20000000"
],
"source_sha256": "f2c5d94943f4b176c99c71e1073bb1c6a8ec6d2eb560d03526aaa3476b9162b1",
"verdict": "verified",
"summary": "5 verified, 0 errors"
}
@@ -0,0 +1,30 @@
function GC(s: string, n: nat): nat
requires n <= |s|
{
if n == 0 then 0 else GC(s, n - 1) + (if s[n - 1] == 'G' || s[n - 1] == 'C' then 1 else 0)
}
lemma GCAtMost(s: string, n: nat)
requires n <= |s|
ensures GC(s, n) <= n
{
if n > 0 { GCAtMost(s, n - 1); }
}
method GCContent(s: string) returns (f: real)
requires |s| > 0
ensures f == (GC(s, |s|) as real) / (|s| as real)
ensures 0.0 <= f <= 1.0
{
var count := 0;
var i := 0;
while i < |s|
invariant 0 <= i <= |s|
invariant count == GC(s, i)
{
if s[i] == 'G' || s[i] == 'C' { count := count + 1; }
i := i + 1;
}
GCAtMost(s, |s|);
f := (count as real) / (|s| as real);
}
@@ -0,0 +1,7 @@
def gc_content(s: String) -> Float64:
var count = 0
for i in range(s.count_codepoints()):
var c = String(s[codepoint=i])
if c == "G" or c == "C":
count = count + 1
return Float64(count) / Float64(s.count_codepoints())
@@ -0,0 +1,6 @@
def gc_content(s):
count = 0
for c in s:
if c == "G" or c == "C":
count += 1
return count / len(s)
+43
View File
@@ -0,0 +1,43 @@
{
"name": "GCContent",
"summary": "The fraction of the letters of a sequence that are G or C.",
"tags": [
"sequences",
"counting"
],
"sources": [
{
"title": "Any molecular biology text: GC content"
}
],
"cases": [
{
"call": "GCContent(\"GATTACA\")"
},
{
"call": "GCContent(\"GGCC\")"
},
{
"call": "GCContent(\"ATAT\")"
}
],
"references": [
{
"lang": "python",
"level": "plain",
"file": "ref/python/plain.py",
"note": "The same count."
},
{
"lang": "mojo",
"level": "plain",
"file": "ref/mojo/plain.mojo",
"note": "The same count in Mojo."
}
],
"proof": {
"lang": "dafny",
"file": "proof/gc_content.dfy",
"note": "The count never exceeds the length, so the fraction lies in [0, 1]."
}
}
+12
View File
@@ -0,0 +1,12 @@
// GCContent: the fraction of the letters of S that are G or C. Other letters
// (N for an unknown base, lowercase) count in the length and not in the count.
FUNCTION GCContent(S : STRING) RETURNS FLOAT
REQUIRE LENGTH(S) > 0
DECLARE Count : INTEGER <- 0
FOR I <- 0 TO LENGTH(S)
IF S[I] == 'G' OR S[I] == 'C' THEN
Count <- Count + 1
ENDIF
NEXT I
RETURN Count / LENGTH(S)
ENDFUNCTION