using custm arrow_open_dataset to detect when parquet file is corrupted

ipeaGIT · Feb 1, 2025 · 4f37227 · 4f37227
1 parent 6d5cb27
commit 4f37227
Show file tree

Hide file tree

Showing 3 changed files with 4 additions and 4 deletions.
diff --git a/R/match_cases.R b/R/match_cases.R
@@ -26,7 +26,7 @@ match_cases <- function(con,
   # Load CNEFE data and write to DuckDB
   # filter cnefe to include only states and municipalities
   # present in the input table, reducing the search scope
-  filtered_cnefe <- arrow::open_dataset( path_to_parquet ) |>
+  filtered_cnefe <- arrow_open_dataset( path_to_parquet ) |>
     dplyr::filter(estado %in% input_states) |>
     dplyr::filter(municipio %in% input_municipio) |>
     dplyr::compute()

diff --git a/R/match_weighted_cases.R b/R/match_weighted_cases.R
@@ -27,7 +27,7 @@ match_weighted_cases <- function(con,
   # Load CNEFE data and write to DuckDB
   # filter cnefe to include only states and municipalities
   # present in the input table, reducing the search scope
-  filtered_cnefe <- arrow::open_dataset( path_to_parquet ) |>
+  filtered_cnefe <- arrow_open_dataset( path_to_parquet ) |>
     dplyr::filter(estado %in% input_states) |>
     dplyr::filter(municipio %in% input_municipio) |>
     dplyr::compute()

diff --git a/R/utils.R b/R/utils.R
@@ -13,8 +13,8 @@ arrow_open_dataset <- function(filename){
     arrow::open_dataset(filename),
     error = function(e){
       msg <- paste(
-        "File cached locally seems to be corrupted. Please download it again using 'cache = FALSE'.",
-        sprintf("Alternatively, you can remove the corrupted file with 'geocodebr::geocodebr_cache(delete_file = \"%s\")'", basename(filename)),
+        "Arquivo local possivelmente corrompido. ",
+        "Apague os arquivos do cache com 'geocodebr::deletar_pasta_cache()' e tente novamente.",
         sep = "\n"
       )
       stop(msg)