fix: use log1p for small p in stats/base/dists/planck/quantile

[Abhist17]

Description

What is the purpose of this pull request?

This pull request:

• uses -log1p( -p ) instead of -ln( 1.0 - p ) in stats/base/dists/planck/quantile (JS, factory and C).
• clamps the result at 0, like geometric/quantile, so p = 0 and inputs where -log1p( -p ) / lambda underflows (e.g. quantile( 5.0e-324, 2.0 )) return 0 instead of -1.

Forming 1 - p in double precision rounds away the low-order bits of p. That gives two kinds of wrong answer:

var quantile = require( '@stdlib/stats/base/dists/planck/quantile' );

// `1 - p` rounds to `1`, so the result is `ceil(0) - 1`, outside the support:
quantile( 1.0e-20, 1.0 );
// develop: -1
// this PR: 0

// `1 - 1e-15` is off by about 11%, which a small `lambda` turns into whole steps:
quantile( 1.0e-15, 1.0e-17 );
// develop: 111
// this PR: 100 (2048-bit evaluation of `ceil(-ln(1-p)/lambda) - 1` agrees)

SciPy's planck.ppf already uses log1p(-q), so the existing Python fixtures pass unchanged with exact equality.

Tests: a new "small p" test in test.quantile.js, test.factory.js and test.native.js covers p = 1e-20 and 1e-300 (expected 0) and two small-lambda cases (expected 100, checked against 2048-bit BigFloat). Four of those assertions fail on develop.

Related Issues

Does this pull request have any related issues?

None. Same bug as #15762 (weibull/quantile) and #15763 (exponential/quantile).

Questions

Any questions for reviewers of this pull request?

No.

Other

Any other information relevant to this pull request? This may include screenshots, references, and/or implementation notes.

No.

Checklist

Please ensure the following tasks are completed before submitting this pull request.

• Read, understood, and followed the contributing guidelines.

AI Assistance

When authoring the changes proposed in this PR, did you use any kind of AI assistance?

• Yes
• No

If you answered "yes" above, how did you use AI assistance?

• Code generation (e.g., when writing an implementation or fixing a bug)
• Test/benchmark generation
• Documentation (including examples)
• Research and understanding

Disclosure

If you answered "yes" to using AI assistance, please provide a short disclosure indicating how you used AI assistance. This helps reviewers determine how much scrutiny to apply when reviewing your contribution. Example disclosures: "This PR was written primarily by Claude Code." or "I consulted ChatGPT to understand the codebase, but the proposed changes were fully authored manually by myself.".

This PR was written primarily by Claude Code. I found the bug by reading the stats/base/dists quantile functions for 1 - p cancellation.

---

@stdlib-js/reviewers

[stdlib-bot]

Coverage Report

Package	Statements	Branches	Functions	Lines
stats/base/dists/planck/quantile	$\\color{green}288/288$ $\\color{green}+0.00\\%$	$\\color{green}25/25$ $\\color{green}+0.00\\%$	$\\color{green}4/4$ $\\color{green}+0.00\\%$	$\\color{green}288/288$ $\\color{green}+0.00\\%$

The above coverage report was generated for the changes in this PR.

[0PrashantYadav0]

Suggested change

	return ceil( -log1p( -p ) / lambda ) - 1.0;
	return max( 0.0, ceil( -log1p( -p ) / lambda ) - 1.0 );

Should this clamp at 0 like geometric/quantile? -log1p( -p ) / lambda can still underflow to 0, so quantile( 5.0e-324, 2.0 ) and quantile( 1.0e-300, 1.0e300 ) return -1. The clamp would also settle the p = 0 question in the description. Same in lib/factory.js:73 and src/main.c:43 (plus @stdlib/math/base/special/max in manifest.json).

[Abhist17]

Yes, clamped with max( 0.0, ... ) in main.js, factory.js and src/main.c, with @stdlib/math/base/special/max added to all three manifest confs (571b8e9). New tests in all three files cover p = 0, quantile( 5.0e-324, 2.0 ) and quantile( 1.0e-300, 1.0e300 ), which returned -1 before and now return 0. That also answers the p = 0 question, so I dropped it from the description.

[0PrashantYadav0]

Suggested change

	tape( 'the created function evaluates the quantile for small `p`', function test( t ) {
	tape( 'the returned function evaluates the quantile for small `p`', function test( t ) {

Match the other test names in this file.

[Abhist17]

Renamed in 571b8e9.