Merge pull request #283 from ropensci/v5.0.0

V5.0.0

DESCRIPTION

@@ -6,7 +6,7 @@ Description: A programmatic interface to 'FishBase', re-written
     supports experimental access to 'SeaLifeBase' data, which contains
     nearly 200,000 species records for all types of aquatic life not covered by
     'FishBase.'
-Version: 4.1.1
+Version: 5.0.0
 Encoding: UTF-8
 License: CC0
 Authors@R: c(person("Carl", "Boettiger",
@@ -26,31 +26,20 @@ LazyData: true
 Depends:
     R (>= 4.0)
 Imports:
-    methods,
-    utils,
-    tools,
-    purrr,
-    progress,
-    memoise,
-    rlang,
-    magrittr,
-    readr (>= 2.0.0),
+    glue,
     stringr,
+    purrr,
     jsonlite,
-    DBI,
     dplyr,
-    dbplyr,
-    duckdb,
-    contentid (>= 0.0.15),
-    rstudioapi,
-    fs,
-    glue,
-    tibble
+    duckdbfs,
+    rlang,
+    magrittr,
+    memoise
 Suggests:
     testthat,
     rmarkdown,
     knitr,
     covr,
     spelling
-RoxygenNote: 7.2.3
+RoxygenNote: 7.3.1
 Language: en-US

NAMESPACE

@@ -9,22 +9,15 @@ export(common_to_sci)
 export(country)
 export(countrysub)
 export(countrysubref)
-export(db_dir)
-export(db_disconnect)
 export(diet)
 export(diet_items)
-export(distribution)
-export(docs)
 export(ecology)
 export(ecosystem)
 export(estimate)
 export(faoareas)
-export(fb_conn)
-export(fb_import)
 export(fb_tables)
 export(fb_tbl)
 export(fecundity)
-export(fishbase_pane)
 export(fooditems)
 export(genetics)
 export(introductions)
@@ -36,7 +29,6 @@ export(load_taxa)
 export(maturity)
 export(morphology)
 export(morphometrics)
-export(occurrence)
 export(oxygen)
 export(popchar)
 export(popgrowth)
@@ -52,17 +44,13 @@ export(sci_to_common)
 export(spawning)
 export(species)
 export(species_by_ecosystem)
-export(species_list)
-export(species_names)
 export(speed)
 export(stocks)
 export(swimming)
 export(synonyms)
 export(validate_names)
-importFrom(dbplyr,translate_sql)
 importFrom(dplyr,collect)
 importFrom(dplyr,distinct)
-importFrom(dplyr,enquo)
 importFrom(dplyr,filter)
 importFrom(dplyr,left_join)
 importFrom(dplyr,mutate)
@@ -71,24 +59,9 @@ importFrom(dplyr,rename)
 importFrom(dplyr,right_join)
 importFrom(dplyr,select)
 importFrom(dplyr,sym)
-importFrom(fs,dir_create)
-importFrom(fs,dir_ls)
-importFrom(fs,path)
 importFrom(magrittr,`%>%`)
-importFrom(methods,as)
-importFrom(methods,is)
-importFrom(progress,progress_bar)
-importFrom(purrr,map_chr)
 importFrom(purrr,map_dfr)
-importFrom(readr,read_csv)
 importFrom(rlang,"!!")
 importFrom(rlang,.data)
-importFrom(stats,na.omit)
-importFrom(stringr,str_extract)
 importFrom(stringr,str_to_lower)
-importFrom(tools,R_user_dir)
-importFrom(utils,data)
 importFrom(utils,globalVariables)
-importFrom(utils,lsf.str)
-importFrom(utils,packageVersion)
-importFrom(utils,read.csv)

NEWS.md

@@ -23,10 +23,35 @@ And constructed with the following guidelines:
 
 For more information on SemVer, please visit http://semver.org/.
 
+v 5.0.0
+-------
+
+Another streamlined re-design following new abilities for data hosting and access.
+This release relies on a HuggingFace datasets hosting for data and metadata hosting
+in parquet and schema.org.  
+
+Data access is simplified to use the simple HuggingFace datasets API instead
+of the previous contentid-based resolution. This allows metadata to be defined
+with directly alongside the data platform independent of the R package.  
+
+A simplified access protocol relies on `duckdbfs` for direct reads of tables.
+Several functions previously used only to manage connections are now deprecated
+or removed, along with a significant number of dependencies.
+
+Core use still centers around the same package API using the `fb_tbl()` function,
+with legacy helper functions for common tables like `species()` are still accessible and
+can still optionally filter by species name where appropriate.  As before, loading the
+full tables and sub-setting manually is still recommended.
+
+Historic helper  functions like `load_taxa()` (combining the taxonomic classification from Species,
+Genus, Family and Order tables), `validate_names()`, and `common_to_sci()` and 
+`sci_to_common()` should be in working order, all using table-based outputs.
+
+
 v 4.1.1
 -------
 
-* hotfix for bug in 4.1.0 on Windows -- duckdb httpfs on windows creates sigfault
+* hotfix for bug in 4.1.0 on Windows -- `duckdb` `httpfs` on windows created `segfault`
 
 v 4.1.0
 --------

R/00-endpoint.R

@@ -1,90 +1,48 @@
 
-utils::globalVariables("sci_name", package="rfishbase")
-
-
 ## Allows us to define functions for each endpoint using closures
 #' @importFrom dplyr left_join rename sym
 #' @importFrom rlang !! .data
 endpoint <- function(endpt, join = NULL, by = NULL){
 
   function(species_list = NULL, 
            fields = NULL, 
-           server = getOption("FISHBASE_API", "fishbase"), 
-           version = get_latest_release(),
-           db = default_db(server, version),
+           server = c("fishbase", "sealifebase"), 
+           version = "latest",
+           db = NULL,
            ...){
 
-    out <- fb_tbl(endpt, server, version, db) %>% fix_ids()
+    out <- fb_tbl(endpt, server, version) %>% fix_ids()
 
     if(!is.null(species_list)){
       species <-
-        dplyr::select(fb_tbl("species", server, version, db),
-                      "SpecCode", "Genus", "Species") %>%
+        fb_tbl("species", server, version) %>%
+        dplyr::select("SpecCode", "Genus", "Species") %>%
         dplyr::mutate(sci_name = paste(Genus, Species)) %>%
         dplyr::filter(sci_name %in% species_list) %>%
         dplyr::select(Species=sci_name, "SpecCode")
+
       out <- dplyr::inner_join(species, out) %>% dplyr::distinct()
     }
-
 
     if(!is.null(fields)){
-      out <- select(out, !!fields) %>% dplyr::distinct()
+      out <- dplyr::select(out, !!fields) %>% dplyr::distinct()
     }
 
-    if(!is.null(join))
-      out <- left_join(out, join, by = by)
-
-    dplyr::collect(out)
-  }
-
-}
-
-
-species_subset <- function(species_list, 
-                           full_data, 
-                           server = getOption("FISHBASE_API", "fishbase"),
-                           version = get_latest_release(),
-                           db = default_db()){
-
-
-  species <-
-    dplyr::select(dplyr::tbl(db, "species"),
-                  "SpecCode", "Genus", "Species") %>%
-    dplyr::mutate(sci_name = paste(Genus, Species)) %>%
-    dplyr::select("SpecCode", Species=sci_name) %>%
-    collect()
-
-
-
-  ## "Species" in many tables is just the epithet, we want full species name so drop that.
-  if("Species" %in% colnames(full_data)){
-    sp <- dplyr::sym("Species")
-    full_data <- dplyr::select(full_data, - !!sp)
-  }
-
-  if(is.null(species_list)){
-    return(dplyr::left_join(species, full_data, by = "SpecCode"))
+    if(!is.null(join)) {
+      out <- dplyr::left_join(out, join, by = by)
+    }
+    out
   }
-
-  speccodes(species_list, table = species, db = db) %>% 
-      dplyr::left_join(full_data, by = "SpecCode")
 }
 
-
 ## handle ids or species names, returning remote table for joining
 speccodes <- function(species_list, table, db){ 
   if(is.integer(species_list)){
     df <- dplyr::tibble(SpecCode = species_list)
   } else {
     df <- dplyr::tibble(Species = species_list)
   }
-
-  ## Manually copy. we want a left_join since right_join isn't in RSQLite
-  ## but left_join(copy=TRUE) would copy the larger table instead
-  #tmp <- tmp_tablename()
-  #dplyr::copy_to(db, df = df, name = tmp, overwrite=TRUE, temporary=TRUE) 
-  #df <- dplyr::tbl(db, tmp)
-
+
   suppressMessages({
   dplyr::left_join(df, table) %>%
     select("SpecCode", "Species")
@@ -93,8 +51,6 @@ speccodes <- function(species_list, table, db){
 
 
 
-
-
 #' @importFrom dplyr sym
 fix_ids <- function(full_data){
   if("Speccode" %in% colnames(full_data)){ 
@@ -111,13 +67,22 @@ fix_ids <- function(full_data){
 ## Define function that maps sci names to SpecCode, subsets table by requested sci name or spec code
 #' @importFrom dplyr mutate select
 fb_species <- function(server = getOption("FISHBASE_API", "fishbase"),
-                       version = get_latest_release(),
-                       db = default_db(server, version), 
+                       version = "latest",
+                       db = NULL, 
                        ...){
-  load_taxa(server, version, db, collect = FALSE, ...) %>% dplyr::select("SpecCode", "Species")
+  load_taxa(server, version, db=NULL, collect = FALSE, ...) %>%
+    dplyr::select("SpecCode", "Species")
 }
 
 
 
 tmp_tablename <- function(n=10)
   paste0("tmp_", paste0(sample(letters, n, replace = TRUE), collapse = ""))
+
+
+utils::globalVariables("sci_name", package="rfishbase")
+
+
+#' @importFrom magrittr `%>%`
+#' @export
+magrittr::`%>%`