* using log directory ‘/data/localhost/ripley/R/packages/tests-noLD/Rita.Rcheck’
* using R Under development (unstable) (2026-11-13 r90888)
* using platform: x86_64-pc-linux-gnu
* R was compiled by
    gcc (GCC) 16.2.1 20261029 (Red Hat 16.2.1-3)
    GNU Fortran (GCC) 16.2.1 20261029 (Red Hat 16.2.1-3)
* running under: Fedora Linux 44 (Server Edition)
* using session charset: UTF-8
* current time: 2026-11-14 04:02:27 UTC
* using option ‘--no-stop-on-test-error’
* checking for file ‘Rita/DESCRIPTION’ ... OK
* checking extension type ... Package
* this is package ‘Rita’ version ‘2.0.0’
* package encoding: UTF-8
* checking package namespace information ... OK
* checking package dependencies ... OK
* checking if this is a source package ... OK
* checking if there is a namespace ... OK
* checking for executable files ... OK
* checking for hidden files and directories ... OK
* checking for portable file names ... OK
* checking for sufficient/correct file permissions ... OK
* checking whether package ‘Rita’ can be installed ... OK
* checking package directory ... OK
* checking DESCRIPTION meta-information ... OK
* checking top-level files ... OK
* checking for left-over files ... OK
* checking index information ... OK
* checking package subdirectories ... OK
* checking code files for non-ASCII characters ... OK
* checking R files for syntax errors ... OK
* checking whether the package can be loaded ... OK
* checking whether the package can be loaded with stated dependencies ... OK
* checking whether the package can be unloaded cleanly ... OK
* checking whether the namespace can be loaded with stated dependencies ... OK
* checking whether the namespace can be unloaded cleanly ... OK
* checking loading without being on the library search path ... OK
* checking use of S3 registration ... OK
* checking dependencies in R code ... OK
* checking S3 generic/method consistency ... OK
* checking replacement functions ... OK
* checking foreign function calls ... OK
* checking R code for possible problems ... OK
* checking Rd files ... OK
* checking Rd metadata ... OK
* checking Rd line widths ... OK
* checking Rd cross-references ... OK
* checking for missing documentation entries ... OK
* checking for code/documentation mismatches ... OK
* checking Rd \usage sections ... OK
* checking Rd contents ... OK
* checking for unstated dependencies in examples ... OK
* checking examples ... OK
* checking for unstated dependencies in ‘tests’ ... OK
* checking tests ...
  Running ‘ad-published.R’
  Running ‘chisq-repair.R’
  Running ‘correction-a1.R’
  Running ‘correction-a2.R’
  Running ‘correction-b6.R’
  Running ‘correction-b8.R’
  Running ‘dp-published.R’
  Running ‘foundation.R’
  Running ‘jb-repair.R’
  Running ‘rita-pass1.R’
  Running ‘rita-pass2.R’
  Running ‘rita-pass3a.R’
  Running ‘sw-ksl.R’
  Running ‘transform-repair.R’
 [25s/27s] ERROR
Running the tests in ‘tests/ad-published.R’ failed.
Complete output:
  > source("helpers/legacy-reporting.R", local=TRUE)
  > library(Rita)
  > checks <- 0L
  > check <- function(ok,label) {
  +   if (!isTRUE(ok)) stop(label,call.=FALSE)
  +   checks <<- checks+1L
  + }
  > close <- function(x,y,tol=1e-12) isTRUE(legacy_all_equal(unname(x),unname(y),tolerance=tol))
  > probability <- get('.rita_ad_pvalue',asNamespace('Rita'))
  > 
  > # Fixed Table 4.9 results independently evaluated with Python Decimal at
  > # 50-digit precision. They exercise all four regions, not package snapshots.
  > z <- c(.15,.25,.45,.8)
  > p <- c(.9630771618746098041,.7446512446013424107,
  +        .2760150184697347072,.03832717900008682781)
  > for(i in seq_along(z)) check(close(probability(z[i]),p[i]),'Table 4.9 fixed value')
  > 
  > # Table 4.7, Case 3: the published critical values and the approximation agree
  > # to table/approximation precision, not exactly.
  > check(abs(probability(.752)-.05)<.0004,'Table 4.7 five-percent critical value')
  > check(abs(probability(1.035)-.01)<.0002,'Table 4.7 one-percent critical value')
  > 
  > # Direct transcription of Table 4.9 as a coefficient table, with the explicit
  > # equality convention documented for Rita. No registry/production helper oracle.
  > table_probability <- function(z) {
  +   coefficients <- rbind(c(-13.436,101.14,-223.73),c(-8.318,42.796,-59.938),
  +                         c(.9177,-4.279,-1.38),c(1.2937,-5.709,.0186))
  +   region <- if(z<=.2) 1L else if(z<=.34) 2L else if(z<.6) 3L else 4L
  +   exponent <- sum(coefficients[region,]*c(1,z,z^2))
  +   if(region<=2) 1-exp(exponent) else exp(exponent)
  + }
  > for(knot in c(.2,.34,.6)) for(offset in c(-1e-10,0,1e-10))
  +   check(close(probability(knot+offset),table_probability(knot+offset)),
  +         'breakpoint side/equality matches documented table region')
  > 
  > # Independently reindexed weighted sum (published reversed upper-tail form).
  > reference_statistic <- function(x) {
  +   n <- length(x); standardized <- (sort(x)-mean(x))/sd(x)
  +   A <- -n-mean((2*seq_len(n)-1)*
  +        (pnorm(standardized,log.p=TRUE)+rev(pnorm(-standardized,log.p=TRUE))))
  +   A*(1+.75/n+2.25/n^2)
  + }
  > regions <- integer()
  > for(seed in c(1,2,4,9)) {
  +   set.seed(seed); x<-rnorm(40); A<-reference_statistic(x)
  +   regions<-c(regions,findInterval(A,c(.2,.34,.6))+1L)
  +   expected_p<-table_probability(A)
  +   actual<-ADTest(x)
  +   check(legacy_identical(actual,list(c(AD=round(A,3)),c(`P-value`=round(expected_p,3)),
  +                              c(Sig.=expected_p<.05))), 'end-to-end published formula')
  +   check(legacy_identical(MasterTest(3,x),actual) &&
  +         legacy_identical(MasterTest('anderson-darling',x),actual),'independent AD dispatch contract')
  + }
  > check(legacy_identical(sort(regions),1:4),'end-to-end fixtures cover every p-value region')
  > 
  > # Stephens (1974) weights illustration: use the base statistic from that source
  > # with Rita's intentionally retained 1986 modification/calibration.
  > weights <- c(148,154,158,160,161,162,166,170,182,195,236)
  > A <- reference_statistic(weights)
  > check(abs(A-1.0289297700)<1e-10,'weights example with 1986 modification')
  > check(abs(table_probability(A)-.0104540238)<1e-9,'weights later-form reference p')
  > check(legacy_identical(ADTest(weights),list(c(AD=1.029),c(`P-value`=.010),c(Sig.=TRUE))),
  +       'weights public result names and rounding')
  > # p rounds to .010 but the unrounded value is above .0102.
  > check(legacy_identical(unname(ADTest(weights,alpha=.0102)[[3]]),FALSE),
  +       'decision uses unrounded p')
  > check(legacy_identical(unname(ADTest(weights,alpha=.02,j=2)[[3]]),FALSE),
  +       'Bonferroni decision preserved')
  > check(legacy_identical(ADTest(c(weights,NA,NaN)),ADTest(weights)), 'existing missing-value omission')
  > 
  > # A standardized positive outlier makes pnorm round to one; direct log tails
  > # must retain a finite statistic and reflection invariance.
  > x <- c(rep(0,99),100)
  > check(any(pnorm((x-mean(x))/sd(x))==1),'fixture reaches CDF rounding failure')
  > A <- reference_statistic(x)
  > check(is.finite(A) && abs(A-38.533)<.0005,'known outlier statistic')
  > for(y in list(x,-x,10+3*x)) {
  +   ans<-ADTest(y)
  +   check(all(is.finite(unlist(ans))) && close(ans[[1]],round(A,3)),
  +         'finite log-tail statistic and affine/reflection invariance')
  + }
  > check(legacy_identical(ADTest(x),ADTest(-x)),'outlier reflected result agrees')
  > 
  > for(x in list(rep(1,12),rep(0,20),c(rep(3,12),NA,NaN),numeric(),1,
  +               c(1:12,Inf))) {
  +   warnings <- character()
  +   result <- withCallingHandlers(tryCatch(ADTest(x),error=identity),warning=function(w) {
  +     warnings <<- c(warnings,conditionMessage(w)); invokeRestart('muffleWarning')
  +   })
  +   check(inherits(result,'error') && grepl('finite, positive sample standard deviation',
  +         conditionMessage(result),fixed=TRUE) && length(warnings)==0,
  +         'invalid variation terminates with informative error before arithmetic')
  + }
  > 
  > # LEGACY EXTREME TAIL, pending maintainer policy: deliberately preserve the
  > # last polynomial, even where it is not a valid probability. These assertions
  > # guard the explicitly deferred scope; they are NOT calibration endorsements.
  > for(A in c(10,40,200,400,1000))
  +   check(close(probability(A),exp(1.2937-5.709*A+.0186*A^2)),
  +         'LEGACY TAIL no unapproved replacement or clamp')
  > extreme <- rep(c(-1,1),1000); A<-reference_statistic(extreme)
  > check(is.finite(A) && probability(A)>1 &&
  +       close(ADTest(extreme)[[2]],round(probability(A),3)),
  +       'LEGACY TAIL public behavior retained pending policy')
  Error: LEGACY TAIL public behavior retained pending policy
  Execution halted
* checking PDF version of manual ... OK
* checking HTML version of manual ... OK
* checking for non-standard things in the check directory ... OK
* checking for detritus in the temp directory ... OK
* DONE

Status: 1 ERROR
See
  ‘/data/localhost/ripley/R/packages/tests-noLD/Rita.Rcheck/00check.log’
for details.

Command exited with non-zero status 1
Time 0:54.61, 43.89 + 4.40