inst/doc/validation-and-sharing-indexes.R

In bigANNOY: Approximate k-Nearest Neighbour Search for 'bigmemory' Matrices with Annoy

knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>"
)

options(bigANNOY.progress = FALSE)
set.seed(20260326)

library(bigANNOY)
library(bigmemory)

share_dir <- tempfile("bigannoy-share-")
dir.create(share_dir, recursive = TRUE, showWarnings = FALSE)

ref_dense <- matrix(
  c(
    0.0, 0.0,
    1.0, 0.0,
    0.0, 1.0,
    1.0, 1.0
  ),
  ncol = 2,
  byrow = TRUE
)

ref_big <- as.big.matrix(ref_dense)
index_path <- file.path(share_dir, "ref.ann")

index <- annoy_build_bigmatrix(
  ref_big,
  path = index_path,
  n_trees = 20L,
  metric = "euclidean",
  seed = 77L,
  load_mode = "lazy"
)

index

metadata <- read.dcf(index$metadata_path)
metadata[, c(
  "metadata_version",
  "package_version",
  "annoy_version",
  "index_id",
  "metric",
  "n_dim",
  "n_ref",
  "n_trees",
  "build_seed",
  "build_threads",
  "build_backend",
  "file_size",
  "file_mtime",
  "file_md5",
  "load_mode",
  "index_file"
)]

validation <- annoy_validate_index(
  index,
  strict = TRUE,
  load = TRUE
)

validation$valid
validation$checks[, c("check", "passed", "severity")]

reopened <- annoy_open_index(
  path = index$path,
  load_mode = "lazy"
)

annoy_is_loaded(reopened)
annoy_validate_index(reopened, strict = TRUE, load = TRUE)$valid
annoy_is_loaded(reopened)

shared_dir <- tempfile("bigannoy-shared-copy-")
dir.create(shared_dir, recursive = TRUE, showWarnings = FALSE)

shared_index_path <- file.path(shared_dir, basename(index$path))
shared_metadata_path <- file.path(shared_dir, basename(index$metadata_path))

file.copy(index$path, shared_index_path, overwrite = TRUE)
file.copy(index$metadata_path, shared_metadata_path, overwrite = TRUE)

shared <- annoy_open_index(
  path = shared_index_path,
  load_mode = "lazy"
)

shared_report <- annoy_validate_index(
  shared,
  strict = TRUE,
  load = TRUE
)

shared_report$valid

bad_metadata <- read.dcf(shared_metadata_path)
bad_metadata[1L, "file_md5"] <- "corrupted"
write.dcf(as.data.frame(bad_metadata, stringsAsFactors = FALSE), file = shared_metadata_path)

shared_bad <- annoy_open_index(shared_index_path, load_mode = "lazy")
bad_report <- annoy_validate_index(
  shared_bad,
  strict = FALSE,
  load = FALSE
)

bad_report$valid
bad_report$checks[, c("check", "passed", "severity")]

strict_error <- tryCatch(
  {
    annoy_validate_index(shared_bad, strict = TRUE, load = FALSE)
    NULL
  },
  error = function(e) conditionMessage(e)
)

strict_error

renamed_path <- file.path(shared_dir, "renamed.ann")
file.copy(shared_index_path, renamed_path, overwrite = TRUE)

rename_error <- tryCatch(
  {
    annoy_open_index(renamed_path, metadata_path = shared_metadata_path)
    NULL
  },
  error = function(e) conditionMessage(e)
)

rename_error