refactored ask and grab

andrewallenbruce · Mar 30, 2024 · b7d687e · b7d687e
1 parent 149cbbc
commit b7d687e
Show file tree

Hide file tree

Showing 18 changed files with 126 additions and 240 deletions.
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -34,7 +34,7 @@ Imports:
     tidyr,
     vctrs,
     zip,
-    here,
+    data.table,
     tictoc
 Suggests: 
     roxyglobals,

diff --git a/NAMESPACE b/NAMESPACE
@@ -2,14 +2,7 @@
 
 export("%>%")
 export(ask)
-export(clean_deactivation)
-export(clean_endpoints)
-export(clean_locations)
 export(clean_number)
-export(clean_weekly)
-export(create_address)
-export(create_identifiers)
-export(create_taxonomy)
 export(dispense)
 export(grab)
 export(is_directory)

diff --git a/R/browse.R b/R/browse.R
@@ -1,25 +1,28 @@
-#' List the most recent NPPES Data Dissemination releases
+#' NPPES Data Dissemination releases
 #'
-#' @param save `<chr>` write to disk using `readr::write_csv()` ; default is `FALSE`
+#' @param save `<lgl>` write data to disk with `data.table::fwrite()`; default is `FALSE`
 #'
-#' @param path `<chr>` path to save to; default is `here::here()`
+#' @param path `<chr>` path to save csv to; default is `fs::path_wd()`
 #'
-#' @return tibble with
+#' @return A [tibble][tibble::tibble-package] of the search results.
 #'
 #' @examplesIf interactive()
-#' nppez::ask()
+#' tmp <- fs::dir_create(fs::path_temp("nppez"))
 #'
+#' nppez::ask(save = TRUE)
+#'
+#' fs::dir_delete(tmp)
 #' @autoglobal
 #' @export
 ask <- function(save = FALSE,
-                path = here::here("./")) {
+                path = fs::path_wd()) {
 
-  tictoc::tic("Download Time")
+  tictoc::tic("Download Time") ########################
 
   url <- "https://download.cms.gov/nppes/NPI_Files.html"
   html <- rvest::read_html(url)
 
-  tictoc::toc()
+  tictoc::toc() ########################################
 
   names <- html |>
     rvest::html_elements("li") |>
@@ -56,42 +59,54 @@ ask <- function(save = FALSE,
     ) |>
     dplyr::select(-date_wk1, -name)
 
+  class(results) <- c("ask", class(results))
+
   if (save) {
-    readr::write_csv(
+    data.table::fwrite(
       results,
-      file = paste0(
-        path,
-        stringr::str_replace(
-          results[[1]][[1]],
-          ".zip",
-          ".csv"
-          )
-        )
+      fs::path(path,
+               fs::path_ext_set(
+                 results[[1]][[1]],
+                 ".csv"
+                 )
+               )
       )
   }
   return(results)
 }
 
 #' Download NPPES ZIP files to a local directory
-#'
-#' @param dir path to local directory to download ZIPs to
+#' @param obj `<tbl_df>` object of class `ask`, returned from `nppez::ask()`
+#' @param files `<chr>` vector of files to download from ZIPs; default behavior is to download all files
+#' @param path `<chr>` path to download ZIPs to; default is `fs::path_wd()`
 #'
 #' @return tibble
 #'
 #' @examplesIf interactive()
-#' nppez::grab(dir = tempdir())
+#' nppez::ask() |>
+#' nppez::grab(files = "NPPES_Deactivated_NPI_Report_031124.zip")
 #'
 #' @autoglobal
 #' @export
-grab <- function(dir) {
+grab <- function(obj,
+                 files = NULL,
+                 path = fs::path_wd()) {
+
+  stopifnot("`obj` must be of class 'ask'" = inherits(obj, "ask"))
+
+  if (!is.null(files)) {
+
+    stopifnot("No `files` in results" = files %in% obj$file)
+
+    obj <- vctrs::vec_slice(obj, vctrs::vec_in(obj$file, files))
 
-  zips <- nppez::ask()$url
+    }
 
   curl::multi_download(
-    urls = zips,
-    destfiles = stringr::str_c(
-      dir,
-      basename(zips)
+    urls = obj$url,
+    destfiles = fs::path(
+      path,
+      basename(obj$url)
       )
     )
 }

diff --git a/R/clean.R b/R/clean.R
@@ -8,7 +8,7 @@
 #' clean_deactivation("D:/<directory name>")
 #'
 #' @autoglobal
-#' @export
+#' @noRd
 clean_deactivation <- function(dir) {
 
   path <- fs::dir_ls(dir, glob = "*.xlsx")
@@ -54,7 +54,7 @@ clean_deactivation <- function(dir) {
 #' clean_endpoints("D:/<directory>/<filename>.csv")
 #'
 #' @autoglobal
-#' @export
+#' @noRd
 clean_endpoints <- function(dir) {
 
   path <- "D:/nppez_data/unzips/endpoint_pfile_20050523-20230409.csv"
@@ -89,7 +89,7 @@ clean_endpoints <- function(dir) {
 #' clean_locations("D:/<directory>/<filename>.csv")
 #' }
 #' @autoglobal
-#' @export
+#' @noRd
 clean_locations <- function(csv = NULL) {
 
   ## Non-Primary Practice Locations
@@ -127,7 +127,7 @@ clean_locations <- function(csv = NULL) {
 #' clean_weekly("D:/<directory>/<filename>.csv")
 #' }
 #' @autoglobal
-#' @export
+#' @noRd
 clean_weekly <- function(csv = NULL) {
 
   week <- readr::read_csv(
@@ -515,7 +515,7 @@ clean_weekly <- function(csv = NULL) {
 #' create_identifiers()
 #' }
 #' @autoglobal
-#' @export
+#' @noRd
 create_identifiers <- function(df) {
 
   identifier <- df |>
@@ -569,7 +569,7 @@ create_identifiers <- function(df) {
 #' create_taxonomy()
 #' }
 #' @autoglobal
-#' @export
+#' @noRd
 create_taxonomy <- function(df) {
 
   code <- df |>
@@ -641,7 +641,7 @@ create_taxonomy <- function(df) {
 #' create_address()
 #' }
 #' @autoglobal
-#' @export
+#' @noRd
 create_address <- function(df) {
 
   practice <- df |>

diff --git a/R/utils.R b/R/utils.R
@@ -1,21 +1,21 @@
 #' Generate a sequence of numbers with a new prefix
 #'
-#' @param n `<int>` Number of sequences to generate
+#' @param n `<int>` Numeric sequence to generate
 #' @param new `<chr>` New prefix
-#' @param old `<chr>` Old prefix
 #' @param between `<chr>` Separator between `new` and `old`, default `" = "`
-#' @param enclose `<chr>` *(optional)* Vector `length(x) == 2` with which to enclose output
+#' @param old `<chr>` Old prefix
 #' @param collapse `<chr>` Separator between sequences, default `", "`
+#' @param enclose `<chr>` *(optional)* Vector of `length(x) == 2` with which to enclose output
 #' @param style `<lgl>` Apply `styler::style_text()` to output, default `TRUE`
 #'
 #' @return `<chr>` collapsed vector of `n` sequences
 #'
 #' @examples
-#' x <- rename_seq(
-#' n        = 3, # can also be 25:300 etc.
+#' rename_seq(
+#' n        = 10,
 #' new      = "id_issuer_",
-#' old      = "Other.ID.Issuer.",
 #' between  = " = ",
+#' old      = "Other.ID.Issuer.",
 #' enclose  = c("x = c(", ")"),
 #' collapse = ",\n ",
 #' style    = TRUE)
@@ -24,10 +24,10 @@
 #' @export
 rename_seq <- function(n,
                        new,
-                       old,
                        between = " = ",
-                       enclose = NULL,
+                       old,
                        collapse = ", ",
+                       enclose = NULL,
                        style = TRUE) {
 
   x <- stringr::str_c(
@@ -38,8 +38,17 @@ rename_seq <- function(n,
     seq(n),
     collapse = collapse)
 
-  if (!is.null(enclose)) {x <- stringr::str_c(enclose[1], x, enclose[2])}
-  if (style) {x <- styler::style_text(x)}
+  if (!is.null(enclose)) {
+    x <- stringr::str_c(
+      enclose[1],
+      x,
+      enclose[2]
+    )
+  }
+
+  if (style) {
+    x <- styler::style_text(x)
+  }
   return(x)
 }
 
@@ -50,7 +59,7 @@ rename_seq <- function(n,
 #' @returns `<chr>` single line character vector
 #'
 #' @examplesIf interactive()
-#' is_directory("D:/")
+#' single_line_string("D:/")
 #'
 #' @autoglobal
 #' @export

diff --git a/README.Rmd b/README.Rmd
@@ -45,25 +45,33 @@ library(nppez)
 List the most recent NPPES Data Dissemination releases
 
 ```{r ask}
-nppez::ask()
+x <- nppez::ask()
+x
 ```
 
-## Grab
+### Grab
 
 Download NPPES ZIP files to a local directory
 
-```{r grab, eval=FALSE}
-nppez::grab(dir = "C:/<folder-to-save-zip-files-to>")
+```{r grab}
+nppez::grab(x, files = "NPPES_Deactivated_NPI_Report_031124.zip")
 ```
 
+
+```{r, echo=FALSE}
+fs::file_delete("NPPES_Deactivated_NPI_Report_031124.zip")
+```
+
+
+
 |download_date |    size|file                                                                 |
 |:-------------|-------:|:--------------------------------------------------------------------|
 |2023-04-12    |   3.62M|D:/nppez_data/zips/NPPES_Data_Dissemination_040323_040923_Weekly.zip |
 |2023-04-12    | 851.05M|D:/nppez_data/zips/NPPES_Data_Dissemination_April_2023.zip           |
 |2023-04-12    |   1.78M|D:/nppez_data/zips/NPPES_Deactivated_NPI_Report_041023.zip           |
 
 
-# Peek
+### Peek
 
 ```{r peek, eval=FALSE}
 nppez::peek(dir = "<path-to-downloaded-zip-files>")
@@ -114,13 +122,13 @@ dplyr::filter(parent_zip == "NPPES_Data_Dissemination_April_2023.zip") |>
 |NPPES_Data_Dissemination_April_2023.zip |npidata_pfile_20050523-20230409.csv   |         801.64M|             8.66G|
 
 
-# Prune
+### Prune
 
 ```{r prune, eval=FALSE}
 nppez::prune(dir = "<path-to-downloaded-zip-files>")
 ```
 
-# Dispense
+### Dispense
 
 ```{r dispense, eval=FALSE}
 nppez::dispense(from = "<path-to-downloaded-zip-files>",

diff --git a/README.md b/README.md
@@ -28,8 +28,9 @@ library(nppez)
 List the most recent NPPES Data Dissemination releases
 
 ``` r
-nppez::ask()
-#> Download Time: 0.42 sec elapsed
+x <- nppez::ask()
+#> Download Time: 0.34 sec elapsed
+x
 #> # A tibble: 5 × 4
 #>   file                                              url       date          size
 #>   <chr>                                             <chr>     <date>     <fs::b>
@@ -40,12 +41,17 @@ nppez::ask()
 #> 5 NPPES_Data_Dissemination_031824_032424_Weekly.zip https://… 2024-03-18   4.31M
 ```
 
-## Grab
+### Grab
 
 Download NPPES ZIP files to a local directory
 
 ``` r
-nppez::grab(dir = "C:/<folder-to-save-zip-files-to>")
+nppez::grab(x, files = "NPPES_Deactivated_NPI_Report_031124.zip")
+#> # A tibble: 1 × 10
+#>   success status_code resumefrom url    destfile error type  modified           
+#>   <lgl>         <int>      <dbl> <chr>  <chr>    <chr> <chr> <dttm>             
+#> 1 TRUE            200          0 https… "C:\\Us… <NA>  appl… 2024-03-11 00:01:43
+#> # ℹ 2 more variables: time <dbl>, headers <list>
 ```
 
 | download_date |    size | file                                                                 |
@@ -54,7 +60,7 @@ nppez::grab(dir = "C:/<folder-to-save-zip-files-to>")
 | 2023-04-12    | 851.05M | D:/nppez_data/zips/NPPES_Data_Dissemination_April_2023.zip           |
 | 2023-04-12    |   1.78M | D:/nppez_data/zips/NPPES_Deactivated_NPI_Report_041023.zip           |
 
-# Peek
+### Peek
 
 ``` r
 nppez::peek(dir = "<path-to-downloaded-zip-files>")
@@ -74,13 +80,13 @@ nppez::peek(dir = "<path-to-downloaded-zip-files>")
 | NPPES_Data_Dissemination_April_2023.zip | pl_pfile_20050523-20230409.csv        |             22M |            65.51M |
 | NPPES_Data_Dissemination_April_2023.zip | npidata_pfile_20050523-20230409.csv   |         801.64M |             8.66G |
 
-# Prune
+### Prune
 
 ``` r
 nppez::prune(dir = "<path-to-downloaded-zip-files>")
 ```
 
-# Dispense
+### Dispense
 
 ``` r
 nppez::dispense(from = "<path-to-downloaded-zip-files>",