file regex

Author: nmdefries

backfill_corrections/delphiBackfillCorrection/R/io.R

@@ -101,13 +101,13 @@ subset_valid_files <- function(files_list, file_type = c("daily", "rollup"), par
   switch(file_type,
          daily = {
            start_dates <- as.Date(
-             sub("^.*/.*_as_of_([0-9]{8}).parquet$", "\\1", files_list),
+             sub("^.*/.*_as_of_([0-9]{8})[.]parquet$", "\\1", files_list),
              format = date_format
            )
            end_dates <- start_dates
          },
          rollup = {
-           rollup_pattern <- "^.*/.*_from_([0-9]{8})_to_([0-9]{8}).parquet$"
+           rollup_pattern <- "^.*/.*_from_([0-9]{8})_to_([0-9]{8})[.]parquet$"
            start_dates <- as.Date(
              sub(rollup_pattern, "\\1", files_list),
              format = date_format
@@ -148,7 +148,7 @@ create_name_pattern <- function(indicator, signal,
                                 file_type = c("daily", "rollup")) {
   file_type <- match.arg(file_type)
   switch(file_type,
-         daily = str_interp("${indicator}_${signal}_as_of_[0-9]{8}.parquet$"),
-         rollup = str_interp("${indicator}_${signal}_from_[0-9]{8}_to_[0-9]{8}.parquet$")
+         daily = str_interp("${indicator}_${signal}_as_of_[0-9]{8}[.]parquet$"),
+         rollup = str_interp("${indicator}_${signal}_from_[0-9]{8}_to_[0-9]{8}[.]parquet$")
   )
 }

backfill_corrections/delphiBackfillCorrection/R/main.R

@@ -240,7 +240,7 @@ main <- function(params) {
 
   if (params$train_models) {
     msg_ts("Removing stored models")
-    files_list <- list.files(params$cache_dir, pattern="*.model", full.names = TRUE)
+    files_list <- list.files(params$cache_dir, pattern="[.]model$", full.names = TRUE)
     file.remove(files_list)
   }
 

backfill_corrections/delphiBackfillCorrection/R/model.R

@@ -299,7 +299,7 @@ get_training_date_range <- function(params) {
     # `20220628_20220529_changehc_covid_state_lambda0.1_count_ca_lag5_tau0.9.model`
     # where the leading date is the training end date for that model, and the
     # second date is the training start date.
-    model_files <- list.files(params$cache_dir, "202[0-9]{5}_202[0-9]{5}*.model")
+    model_files <- list.files(params$cache_dir, "^202[0-9]{5}_202[0-9]{5}.*[.]model$")
     if (length(model_files) == 0) {
       # We know we'll be retraining models today.
       training_end_date <- TODAY