Update again

Author: twedl

NAMESPACE

@@ -1,4 +1,4 @@
 # Generated by roxygen2: do not edit by hand
 
 export(download_geography)
-export(geoinfo)
+export(geo_info)

R/utils.R

@@ -1,8 +1,3 @@
-## Utility functions for Canadian geographic shapefiles and filenames
-
-
-
-
 #' Download and unzip Canadian shapefiles
 #'
 #' Download and unzip Canadian shapefiles from Statistics Canada
@@ -33,13 +28,17 @@ download_geography <- function(geo_path, geo_dir = NULL) {
     geo_dir <- here::here("geography", geo_folder_name)
   }
 
-  temp <- tempfile()
+  if (str_sub(geo_path, 1, 4) == "http") {
+    # the path is a url pointing to statcan.gc.ca
+    temp <- tempfile()
+    utils::download.file(geo_path, temp)
+    unzipped_files <- utils::unzip(temp, exdir = geo_dir)
+    unlink(temp)
 
-  utils::download.file(geo_path, temp)
-
-  unzipped_files <- utils::unzip(temp, exdir = geo_dir)
-
-  unlink(temp)
+  } else {
+    # this assumes the path goes directly to a local/server folder
+    unzipped_files <- utils::unzip(geo_path, exdir = geo_dir)
+  }
 
   shp_path <- stringr::str_subset(unzipped_files, pattern = ".shp")
 
@@ -61,9 +60,9 @@ download_geography <- function(geo_path, geo_dir = NULL) {
 #'
 #' @examples
 #' \donttest{
-#' geoinfo("lpr_000a16a_e")
+#' geo_info("lpr_000a16a_e")
 #' }
-geoinfo <- function(filename) {
+geo_info <- function(filename) {
 
   extract_codes <- canmap::code_pos
 

README.Rmd

@@ -55,10 +55,10 @@ A list of useful links to clean up later:
 
 ### Parsing the filename for metadata
 
-Suppose you've downloaded the geography file ```lpr_000a16a_e.zip```. The filename defines the important geographic characteristics of the file (you can process using the ```code_pos``` dataset for code positions, or ```get_geoinfo```).
+Suppose you've downloaded the geography file ```lpr_000a16a_e.zip```. The filename defines the important geographic characteristics of the file (you can process using the ```code_pos``` dataset for code positions, or ```geo_info```).
 
 ```{r codes, warning = FALSE, message = FALSE}
-str(geoinfo("lpr_000a16a_e"))
+str(geo_info("lpr_000a16a_e"))
 ```
 
 And each of these codes has a meaning that can be found (sometimes) in the geography guide that accompanies a downloaded file (but you can't find out the details until *after* you've downloaded it, and is missing some information).

data-raw/process_shapefile_info.r

@@ -4,14 +4,14 @@ library(usethis)
 library(httr) # for later.
 
 
-# shapefile_info <- readr::read_csv("data-raw/shapefile_info.csv")
 shapefile_paths <- readr::read_csv("data-raw/shapefile_paths.csv")
 
 base_url_1 <- "http://www12.statcan.gc.ca/census-recensement/"
 base_url_2 <- "/geo/bound-limit/files-fichiers/"
 
 
 shapefile_paths %>% count(geo_code)
+
 # only get shapefiles
 shapefile_paths <- shapefile_paths %>%
   filter(format == "ArcGIS (.shp)" & language == "english" & geo_code != "rnf") %>%
@@ -30,8 +30,6 @@ shapefile_paths <- shapefile_paths %>%
 
 si <- shapefile_paths %>%
   distinct() %>%
-  # select(path) %>%
-  # slice(1:100) %>%
   rowwise() %>%
   mutate(http_type = path %>%
            httr::HEAD() %>%
@@ -45,35 +43,14 @@ shapefile_paths <- shapefile_paths %>% semi_join(si, by = "path")
 
 usethis::use_data(shapefile_paths, overwrite = TRUE)
 
-# x <- fs::dir_info("//fld6filer/fichiersGEOfiles/Geographie_2016_Geography/Spatial_Info_Products-Produits_d'info_spatiale", recursive = TRUE) %>%
-#   mutate(ext = fs::path_ext(path),
-#          filepath = fs::path_file(path) %>% fs::path_ext_remove()) %>%
-#   select(filepath, ext, type, size, path)
-#
-# y <- x %>%
-#   filter(type == "file" & ext == "zip") %>%
-#   pull(filepath) %>%
-#   map_df(get_geoinfo)
-#
-# # that's a lot, holy moly.s
-#
-# shapefile_paths <- x %>%
-#   filter(type == "file" & ext == "zip") %>%
-#   mutate(filepath = as.character(filepath)) %>%
-#   left_join(y, by = c("filepath" = "filename"))
-
-# usethis::use_data(shapefile_paths)
-
-
-
 
 ############# and code info
 
 code_book_ <- readr::read_csv("data-raw/code_book.csv")
 code_book <- dplyr::select(code_book_, -start_chr, -stop_chr, -long_desc)
 usethis::use_data(code_book, internal = FALSE, overwrite = TRUE)
 
- # save this as well.
+# save this as well.
 code_pos <- code_book_ %>%
   dplyr::distinct(code_type, start_chr, stop_chr)
 usethis::use_data(code_pos, internal = FALSE, overwrite = TRUE)