Merge remote-tracking branch 'origin/main' into add-usage-vignette

.github/workflows/R-CMD-check.yaml

@@ -46,7 +46,7 @@ jobs:
 
       - name: Install lamindb
         run: |
-          pip install lamindb[bionty]
+          pip install lamindb[bionty,wetlab]
 
       - name: Log in to Lamin
         run: |

.github/workflows/pkgdown.yaml

@@ -44,7 +44,7 @@ jobs:
 
       - name: Install lamindb
         run: |
-          pip install lamindb[bionty]
+          pip install lamindb[bionty,wetlab]
 
       - name: Log in to Lamin
         run: |
@@ -60,7 +60,7 @@ jobs:
 
       - name: Deploy to GitHub pages 🚀
         if: github.event_name != 'pull_request'
-        uses: JamesIves/github-pages-deploy-action@v4.5.0
+        uses: JamesIves/github-pages-deploy-action@v4
         with:
           clean: false
           branch: gh-pages

.gitignore

@@ -1,3 +1,9 @@
 .Rproj.user
+.Rhistory
+.Rdata
+.httr-oauth
+.quarto
+*.Rproj
+
 experiments
 docs

CHANGELOG.md

@@ -6,7 +6,7 @@
 
 * Read user settings from env file created by lamin Python package (PR #2, PR #8).
 
-* Render a pkgdown website (PR #13).
+* Add `to_string()` and `print()` methods to the `Record` class and (incomplete) `describe()` method to the `Artifact()` class (PR #22).
 
 ## MAJOR CHANGES
 
@@ -21,17 +21,21 @@
 
 ## MINOR CHANGES
 
-* Update `README` with new set up instructions and simplify (PR #14).
-
 * Do not complain when foreign keys are not found in a record, but also do not complain when they are (PR #13).
 
-* Further simplify the `README`, and move the detailed usage description to a separate vignette (PR #13).
+* Define a current user and current instance with lamin-cli prior to testing and generating documentation in the CI (PR #23).
+
+* Add a simple unit test which queries laminlabs/lamindata (PR #27).
+
+## DOCUMENTATION
+
+* Update `README` with new set up instructions and simplify (PR #14).
 
 * Add a `pkgdown` website to the project (PR #13).
 
-* Generate vignettes using Quarto (PR #13).
+* Further simplify the `README`, and move the detailed usage description to a separate vignette (PR #13).
 
-* Define a current user and current instance with lamin-cli prior to testing and generating documentation in the CI (PR #23).
+* Generate vignettes using Quarto (PR #13).
 
 * Add vignette to showcase laminr usage (PR #18).
 

DESCRIPTION

@@ -1,6 +1,6 @@
 Package: laminr
 Title: LaminDB interface in R
-Version: 0.1.0.9000
+Version: 0.1.0.9001
 Authors@R:
     c(person("Robrecht", "Cannoodt",
         role = c("aut", "cre"),
@@ -26,5 +26,8 @@ Imports:
 Suggests:
     anndata,
     quarto,
-    s3 (>= 1.1.0)
+    s3 (>= 1.1.0),
+    testthat (>= 3.0.0),
+    withr
 VignetteBuilder: quarto
+Config/testthat/edition: 3

R/Artifact.R

@@ -49,6 +49,55 @@ ArtifactRecord <- R6::R6Class( # nolint object_name_linter
       } else {
         cli_abort(paste0("Unsupported storage type: ", artifact_storage$type))
       }
+    },
+    describe = function(style = TRUE) {
+      provenance_fields <- c(
+        storage = "root",
+        transform = "name",
+        run = "started_at",
+        created_by = "handle",
+        test = "fail"
+      )
+
+      output_strings <- character()
+
+      provenance_strings <- purrr::map_chr(
+        names(provenance_fields),
+        function(.field) {
+          field_name <- try(self[[.field]][[provenance_fields[.field]]])
+          if (inherits(field_name, "try-error") || is.null(field_name)) {
+            return(NA_character_)
+          }
+
+          if (is.character(field_name)) {
+            field_name <- paste0("'", field_name, "'")
+          }
+
+          paste0(
+            cli::col_blue("    $", .field),
+            cli::col_br_blue(" = "),
+            cli::col_yellow(field_name)
+          )
+        }
+      ) |>
+        purrr::discard(is.na)
+
+      if (length(provenance_strings) > 0) {
+        output_strings <- c(
+          output_strings,
+          cli::style_italic(cli::col_br_magenta("  Provenance")),
+          provenance_strings
+        )
+      }
+
+      self$print(style)
+      for (.line in output_strings) {
+        if (isFALSE(style)) {
+          .line <- cli::ansi_strip(.line)
+        }
+
+        cli::cat_line(.line)
+      }
     }
   )
 )

R/Record.R

@@ -94,6 +94,62 @@ Record <- R6::R6Class( # nolint object_name_linter
           )
         )
       }
+    },
+    print = function(style = TRUE) {
+      cli::cat_line(self$to_string(style))
+    },
+    to_string = function(style = FALSE) {
+      important_fields <- c(
+        "uid",
+        "handle",
+        "name",
+        "root",
+        "description",
+        "key"
+      )
+
+      record_fields <- private$.api$get_record(
+        module_name = private$.registry$module$name,
+        registry_name = private$.registry$name,
+        id_or_uid = private$.data[["uid"]],
+        include_foreign_keys = TRUE
+      )
+
+      # Get the important fields that are in the record
+      important_fields <- intersect(important_fields, names(record_fields))
+      # Put important fields before all other fields
+      field_names <- c(
+        important_fields, setdiff(names(record_fields), important_fields)
+      )
+
+      field_strings <- purrr::map_chr(field_names, function(.name) {
+        value <- record_fields[[.name]]
+
+        if (is.null(value)) {
+          return(NA_character_)
+        }
+
+        if (is.character(value)) {
+          value <- paste0("'", value, "'")
+        }
+
+        paste0(
+          cli::col_blue(.name), cli::col_br_blue("="), cli::col_yellow(value)
+        )
+      }) |>
+        purrr::discard(is.na)
+
+      string <- paste0(
+        cli::style_bold(cli::col_green(private$.registry$class_name)), "(",
+        paste(field_strings, collapse = ", "),
+        ")"
+      )
+
+      if (isFALSE(style)) {
+        string <- cli::ansi_strip(string)
+      }
+
+      return(string)
     }
   ),
   private = list(

README.md

@@ -48,8 +48,11 @@ Get an artifact:
 
 ``` r
 artifact <- db$Artifact$get("KBW89Mf7IGcekja2hADu")
+artifact
 ```
 
+    Artifact(uid='KBW89Mf7IGcekja2hADu', description='Myeloid compartment', key='cell-census/2024-07-01/h5ads/fe52003e-1460-4a65-a213-2bb1a508332f.h5ad', version='2024-07-01', _accessor='AnnData', id=3659, transform_id=22, size=691757462, is_latest=TRUE, created_by_id=1, _hash_type='md5-n', type='dataset', created_at='2024-07-12T12:34:10.345829+00:00', n_observations=51552, updated_at='2024-07-12T12:40:48.837026+00:00', run_id=27, suffix='.h5ad', visibility=1, _key_is_virtual=FALSE, hash='SZ5tB0T4YKfiUuUkAL09ZA', storage_id=2)
+
 Access some of its fields:
 
 ``` r

README.qmd

@@ -49,6 +49,7 @@ Get an artifact:
 
 ```{r get_artifact}
 artifact <- db$Artifact$get("KBW89Mf7IGcekja2hADu")
+artifact
 ```
 
 Access some of its fields:

tests/testthat.R

@@ -0,0 +1,12 @@
+# This file is part of the standard setup for testthat.
+# It is recommended that you do not modify it.
+#
+# Where should you do additional test configuration?
+# Learn more about the roles of various files in:
+# * https://r-pkgs.org/testing-design.html#sec-tests-files-overview
+# * https://testthat.r-lib.org/articles/special-files.html
+
+library(testthat)
+library(laminr)
+
+test_check("laminr")

tests/testthat/helper-setup_lamindata_instance.R

@@ -0,0 +1,42 @@
+local_setup_lamindata_instance <- function(env = parent.frame()) {
+  root_dir <- withr::local_file(tempfile(), .local_envir = env)
+  withr::local_envvar(c(LAMIN_SETTINGS_DIR = root_dir), .local_envir = env)
+
+  # create a temporary directory for the settings
+  lamin_dir <- file.path(root_dir, ".lamin")
+  dir.create(lamin_dir, recursive = TRUE, showWarnings = FALSE)
+
+  # generate user settings
+  user_settings <- list(
+    email = "null",
+    password = "null",
+    access_token = "null",
+    api_key = "null",
+    uid = "00000000",
+    uuid = "null",
+    handle = "anonymous",
+    name = "null"
+  )
+  user_lines <- paste0("lamin_user_", names(user_settings), "=", unlist(user_settings))
+  writeLines(user_lines, file.path(lamin_dir, "current_user.env"))
+
+  # generate instance settings
+  instance_settings <- list(
+    owner = "laminlabs",
+    name = "lamindata",
+    api_url = "https://us-east-1.api.lamin.ai",
+    storage_root = "s3://lamindata",
+    storage_region = "us-east-1",
+    db = "null",
+    schema_str = "bionty,wetlab",
+    schema_id = "097186c3e91c01ced47aa3e01a3c1515",
+    id = "037ba1e08d804f91a90275a47735076a",
+    git_repo = "null",
+    keep_artifacts_local = "False"
+  )
+  instance_lines <- paste0("lamindb_instance_", names(instance_settings), "=", unlist(instance_settings))
+  writeLines(instance_lines, file.path(lamin_dir, "current_instance.env"))
+  writeLines(instance_lines, file.path(lamin_dir, "instance--laminlabs--lamindata.env"))
+
+  root_dir
+}

tests/testthat/test-connect_lamindata.R

@@ -0,0 +1,21 @@
+skip_if_offline()
+
+test_that("Connecting to lamindata works", {
+  local_setup_lamindata_instance()
+
+  # try to connect to lamindata
+  db <- connect("laminlabs/lamindata")
+
+  # check whether schema was parsed and classes were created
+  expect_equal(db$Artifact$name, "artifact")
+
+  # try to fetch a record
+  artifact <- db$Artifact$get("mePviem4DGM4SFzvLXf3")
+
+  expect_equal(artifact$uid, "mePviem4DGM4SFzvLXf3")
+  expect_equal(artifact$suffix, ".csv")
+
+  # try to fetch linked records
+  created_by <- artifact$created_by
+  expect_equal(created_by$handle, "sunnyosun")
+})