bczernecki · bczernecki · Sep 15, 2026
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -21,3 +21,4 @@ vignettes/articles/usecase.Rmd
 ^\.positai$
 ^\.claude$
 CLAUDE.md$
+^\.posit/assistant$
diff --git a/.github/copilot-instructions.md b/.github/copilot-instructions.md
@@ -28,7 +28,7 @@ Run commands from the package root.
   - **OGIMET**: HTML is scraped with `XML::readHTMLTable`; station identity is based on WMO IDs. Hourly precipitation post-processing is handled by `precip_split()`.
   - **NOAA / Wyoming**: direct file or page downloads for ISH hourly data, Mauna Loa CO2, and Wyoming soundings.
 
-- IMGW column renaming is a distinct normalization layer. Most IMGW functions accept `col_names = "short" | "full" | "polish"` and pass results through `meteo_shortening_imgw()` or `hydro_shortening_imgw()`. The mapping tables live in built-in datasets backed by `data-raw/`.
+- IMGW column renaming is a distinct normalization layer. IMGW functions return short English names and attach the original full parameter label as a per-column `label` attribute through `meteo_shortening_imgw()` or `hydro_shortening_imgw()`. The mapping tables live in built-in datasets backed by `data-raw/`.
 
 - Package data and docs follow standard R package patterns:
   - exported code in `R/`

diff --git a/.gitignore b/.gitignore
@@ -16,3 +16,4 @@ pkgdown
 test-out.txt
 .positai
 .aider*
+.posit/assistant
diff --git a/CLAUDE.md b/CLAUDE.md
@@ -29,7 +29,7 @@ Run from the package root in R:
 - **OGIMET**: HTML scraping via `XML::readHTMLTable` from `ogimet.com`. Stations are identified by WMO ID. `precip_split` / `R/precip_split.R` handles 6/12/24h precipitation disaggregation for hourly data.
 - **NOAA / Wyoming**: direct file downloads (ISH gzipped fixed-width, CO2 text, sounding HTML).
 
-**Column-name shortening layer.** Most IMGW download functions accept `col_names = "short" | "full" | "polish"` and pass the raw frame through `meteo_shortening_imgw()` / `hydro_shortening_imgw()` (in `R/*_shortening_imgw.R`). Full and short names are looked up against `imgw_meteo_abbrev` / `imgw_hydro_abbrev` (built-in data). When you add a new IMGW column, update both the abbrev table (`data-raw/`) and the shortener.
+**Column-name shortening layer.** IMGW download functions return short English names and attach the original full IMGW parameter label as a per-column `label` attribute. Names are looked up against `imgw_meteo_abbrev` / `imgw_hydro_abbrev` (built-in data). When you add a new IMGW column, update both the abbrev table (`data-raw/`) and the shortener.
 
 **Graceful network failure** is required for CRAN. Use `test_url()` (`R/test_url.R`) to gate downloads, and follow the existing `allow_failure = TRUE` pattern: wrap the real worker (`*_bp` "best practice" inner function) in `tryCatch` so user-facing functions return `NULL`/`invisible()` with a `message()` instead of erroring. Tests follow the same convention — every network test starts with `if (!curl::has_internet()) return(invisible(NULL))`. Don't add tests that fail when offline.
 

diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,6 +1,6 @@
 Package: climate
 Title: Interface to Download Meteorological (and Hydrological) Datasets
-Version: 1.4.0
+Version: 1.4.1
 Authors@R: c(person(given = "Bartosz",
            family = "Czernecki",
            role = c("aut", "cre"),

diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,11 @@
+# climate 1.4.1
+
+* fixed IMGW meteorological and hydrological parameter mappings for current metadata labels
+* removed the `col_names` choice between short, full, and Polish column names to simplify usage
+* original full IMGW parameter names are available through each column's `label` attribute
+* updated documentation, README, and vignettes to describe the simplified naming scheme
+
+
 # climate 1.4.0
 
 * adding the `synop_parser()` function for reading raw SYNOP messages

diff --git a/R/hydro_imgw.R b/R/hydro_imgw.R
@@ -16,6 +16,7 @@
 #' @return A data.frame with columns describing the hydrological parameters
 #' (e.g. flow, water level) where each row represent a measurement,
 #' depending on the interval, at a given hour, month or year.
+#' IMGW parameter columns carry a `label` attribute with the original metadata label.
 #' If `coords = TRUE` additional two columns with geographic coordinates are added.
 #' @examples
 #' \donttest{
@@ -30,12 +31,18 @@ hydro_imgw = function(interval,
 
   if (interval == "daily") {
     # dobowe
-    calosc = hydro_imgw_daily(year = year, station = station, ...)
+    calosc = hydro_imgw_daily(
+      year = year,
+      station = station,
+      ...
+    )
   } else if (interval == "monthly") {
     # miesieczne
-    calosc = hydro_imgw_monthly(year = year,
-                                station = station,
-                                ...)
+    calosc = hydro_imgw_monthly(
+      year = year,
+      station = station,
+      ...
+    )
   } else{
     stop("Wrong `interval` value. It should be either 'daily' or 'monthly'", call. = FALSE)
   }

diff --git a/R/hydro_imgw_daily.R b/R/hydro_imgw_daily.R
@@ -174,6 +174,8 @@ hydro_imgw_daily_bp = function(year,
       attr(all_data[[cols]], "label") = meta$label[ind]
     }
   }
+  all_data = imgw_rename_params_to_labels(all_data, meta)
+  all_data = hydro_shortening_imgw(all_data, ...)
 
   return(all_data)
 }
diff --git a/R/hydro_imgw_monthly.R b/R/hydro_imgw_monthly.R
@@ -127,6 +127,8 @@ hydro_imgw_monthly_bp = function(year,
       attr(all_data[[cols]], "label") = meta$label[ind]
       }
   }
+  all_data = imgw_rename_params_to_labels(all_data, meta)
+  all_data = hydro_shortening_imgw(all_data, ...)
 
   return(all_data)
 }
diff --git a/R/hydro_shortening_imgw.R b/R/hydro_shortening_imgw.R
@@ -3,58 +3,58 @@
 #' Shortening column names of hydrological parameters to improve the readability of downloaded dataset from
 #' the danepubliczne.imgw.pl collection and removing duplicated column names
 #' @param data downloaded dataset with original column names
-#' @param col_names three types of column names possible: "short" - default,
-#' values with shorten names,
-#' "full" - full English description,
-#' "polish" - original names in the dataset
 #' @param remove_duplicates whether to remove duplicated column names
 #' (default TRUE - i.e., columns with duplicated names are deleted)
 #' @export
-#' @returns data.frame with shorten names of hydrological parameters
+#' @returns data.frame with short English names of hydrological parameters.
+#' Existing column attributes, including the original IMGW `label` metadata,
+#' are preserved.
 #' @examples
 #' \donttest{
-#'   monthly = data = hydro_imgw("monthly", year = 1969, col_names = "polish")
+#'   monthly = data = hydro_imgw("monthly", year = 1969)
 #'   
 #'   if (is.data.frame(monthly)) {
-#'   abbr = hydro_shortening_imgw(data = monthly,
-#'       col_names = "full",
-#'       remove_duplicates = TRUE)
+#'   abbr = hydro_shortening_imgw(data = monthly, remove_duplicates = TRUE)
 #'   head(abbr)
 #'   }
 #' }
 #'
 
 hydro_shortening_imgw = function(data,
-                                 col_names = "short",
                                  remove_duplicates = TRUE) {
 
-  if (col_names != "polish") {
-    abbrev = climate::imgw_hydro_abbrev
-    # additional workarounds for mac os but not only...
-    abbrev$fullname = gsub(x = abbrev$fullname, pattern = "'", replacement = "")
-    abbrev$fullname = gsub(x = abbrev$fullname, pattern = "\\^", replacement = "")
-    # end of workaround
-    orig_columns = trimws(gsub("\\s+", " ", colnames(data))) # remove double spaces
+  data = as.data.frame(data)
+  column_attributes = lapply(data, attributes)
 
-    matches = match(orig_columns, abbrev$fullname)
-    matches = matches[!is.na(matches)]
+  abbrev = climate::imgw_hydro_abbrev
+  # additional workarounds for mac os but not only...
+  abbrev$fullname = gsub(x = abbrev$fullname, pattern = "'", replacement = "")
+  abbrev$fullname = gsub(x = abbrev$fullname, pattern = "\\^", replacement = "")
+  abbrev$fullname = stringi::stri_trans_general(abbrev$fullname, "LATIN-ASCII")
+  # end of workaround
+  orig_columns = trimws(gsub("\\s+", " ", colnames(data))) # remove double spaces
+  orig_columns = gsub(x = orig_columns, pattern = "'", replacement = "")
+  orig_columns = gsub(x = orig_columns, pattern = "\\^", replacement = "")
+  orig_columns = stringi::stri_trans_general(orig_columns, "LATIN-ASCII")
+  # `Data` is created by the package and is not an IMGW parameter.
+  orig_columns[orig_columns == "Data"] = NA_character_
 
-    if (col_names == "short") {
-      # abbrev english
-      colnames(data)[orig_columns %in% abbrev$fullname] = abbrev$abbr_eng[matches]
-    }
-
-    if (col_names == "full") {
-      # full english names:
-      colnames(data)[orig_columns %in% abbrev$fullname] = abbrev$fullname_eng[matches]
-    }
-  }
+  matches = match(orig_columns, abbrev$fullname)
+  matches = matches[!is.na(matches)]
+  colnames(data)[orig_columns %in% abbrev$fullname] = abbrev$abbr_eng[matches]
 
   # removing duplicated column names:  (e.g. station's name)
   if (remove_duplicates == TRUE) {
-    data = data[, !duplicated(colnames(data))]
+    keep = !duplicated(colnames(data))
+    data = data[, keep, drop = FALSE]
+    column_attributes = column_attributes[keep]
   }
   data = unique(data)
+  for (ind in seq_along(column_attributes)) {
+    if (!is.null(column_attributes[[ind]])) {
+      attributes(data[[ind]]) = column_attributes[[ind]]
+    }
+  }
   rownames(data) = NULL
   return(data)
 }
diff --git a/R/meteo_imgw.R b/R/meteo_imgw.R
@@ -15,8 +15,6 @@
 #'   (default `FALSE` — status columns are deleted). Not used when `rank = "telemetry"`.
 #' @param coords add coordinates of the station (logical value `TRUE` or `FALSE`).
 #'   Default `FALSE`.
-#' @param col_names column name style: `"short"` (default), `"full"` (English descriptions),
-#'   or `"polish"` (original dataset names). Not used when `rank = "telemetry"`.
 #' @param station name of meteorological station(s).
 #'   For ranks `"synop"`, `"climate"`, `"precip"`: station name(s) in CAPITAL LETTERS.
 #'   Please note that station names may change over time — sometimes two names are required,
@@ -33,6 +31,7 @@
 #' @return A data.frame with meteorological parameters where each row is a measurement.
 #'   For ranks `"synop"`, `"climate"`, `"precip"`: measurements at a given hour, day, or month,
 #'   depending on `interval`. If `coords = TRUE` two additional coordinate columns are appended.
+#'   IMGW parameter columns also carry a `label` attribute with the original Polish metadata label.
 #'   For `rank = "telemetry"`: a data.table with 10-minute interval observations (not
 #'   expert-validated). If `coords = TRUE` columns `name`, `lon`, `lat`, and `alt` are appended.
 #' @examples
@@ -52,7 +51,6 @@ meteo_imgw = function(interval = NULL,
                       status = FALSE,
                       coords = FALSE,
                       station = NULL,
-                      col_names = "short",
                       parameters = NULL,
                       ...) {
   if (rank == "telemetry") {
@@ -70,22 +68,19 @@ meteo_imgw = function(interval = NULL,
                               year      = year,
                               status    = status,
                               coords    = coords,
-                              station   = station,
-                              col_names = col_names, ...)
+                              station   = station, ...)
   } else if (interval == "monthly") {
     result = meteo_imgw_monthly(rank      = rank,
                                 year      = year,
                                 status    = status,
                                 coords    = coords,
-                                station   = station,
-                                col_names = col_names, ...)
+                                station   = station, ...)
   } else if (interval == "hourly") {
     result = meteo_imgw_hourly(rank      = rank,
                                year      = year,
                                status    = status,
                                coords    = coords,
-                               station   = station,
-                               col_names = col_names, ...)
+                               station   = station, ...)
   } else {
     stop("Wrong `interval` value. It should be either 'hourly', 'daily', or 'monthly'.")
   }

diff --git a/R/meteo_imgw_daily.R b/R/meteo_imgw_daily.R
@@ -14,10 +14,6 @@
 #' database and thus providing both names is needed
 #' (e.g. `station = c("POZNAŃ", "POZNAŃ-ŁAWICA", "WARSZAWA", "WARSZAWA-OKĘCIE")`).
 #' Stations' IDs (numeric) are no longer valid
-#' @param col_names three types of column names possible:
-#' "short" - default, values with shorten names,
-#' "full" - full English description,
-#' "polish" - original names in the dataset
 #' @param allow_failure logical - whether to proceed or stop on failure. By default set to TRUE (i.e. don't stop on error). For debugging purposes change to FALSE
 #' @param ... other parameters that may be passed to the 'shortening' function that
 #' shortens column names
@@ -35,7 +31,6 @@ meteo_imgw_daily = function(rank = "synop",
                              status = FALSE,
                              coords = FALSE,
                              station = NULL,
-                             col_names = "short",
                              allow_failure = TRUE,
                              ...) {
   if (allow_failure) {
@@ -45,8 +40,7 @@ meteo_imgw_daily = function(rank = "synop",
         year,
         status,
         coords,
-        station,
-        col_names
+        station
       ),
       error = function(e) {
         message(paste(
@@ -63,7 +57,6 @@ meteo_imgw_daily = function(rank = "synop",
       status,
       coords,
       station,
-      col_names,
       ...
     )
   }
@@ -74,7 +67,6 @@ meteo_imgw_daily_bp = function(rank,
                                 status,
                                 coords,
                                 station,
-                                col_names,
                                 ...) {
   translit = check_locale()
   base_url = "https://danepubliczne.imgw.pl/data/dane_pomiarowo_obserwacyjne/"
@@ -399,7 +391,7 @@ meteo_imgw_daily_bp = function(rank,
   }
 
   all_data = imgw_rename_params_to_labels(all_data, meta)
-  all_data = meteo_shortening_imgw(all_data, col_names = col_names, remove_duplicates = TRUE)
+  all_data = meteo_shortening_imgw(all_data, remove_duplicates = TRUE)
 
   # check if there any messages gathered in env$logs and if it is not empty then print them:
   if (length(env$logs) > 0) {

diff --git a/R/meteo_imgw_hourly.R b/R/meteo_imgw_hourly.R
@@ -9,9 +9,6 @@
 #' (default status = FALSE - i.e. the status columns are deleted)
 #' @param coords add coordinates of the station (logical value TRUE or FALSE)
 #' @param station name of meteorological station(s) (character vector)
-#' @param col_names three types of column names possible: "short" - default,
-#' values with shorten names, "full" - full English description,
-#' "polish" - original names in the dataset
 #' @param allow_failure logical - whether to proceed or stop on failure. By default set to TRUE (i.e. don't stop on error). For debugging purposes change to FALSE
 #' @param ... other parameters that may be passed to the 'shortening'
 #' function that shortens column names
@@ -31,7 +28,6 @@ meteo_imgw_hourly = function(rank = "synop",
                               status = FALSE,
                               coords = FALSE,
                               station = NULL,
-                              col_names = "short",
                               allow_failure = TRUE,
                               ...) {
   if (allow_failure) {
@@ -41,8 +37,7 @@ meteo_imgw_hourly = function(rank = "synop",
         year,
         status,
         coords,
-        station,
-        col_names, ...
+        station, ...
       ),
       error = function(e) {
         message(paste(
@@ -58,8 +53,7 @@ meteo_imgw_hourly = function(rank = "synop",
       year,
       status,
       coords,
-      station,
-      col_names, ...
+      station, ...
     )
   }
 }
@@ -70,8 +64,7 @@ meteo_imgw_hourly_bp = function(rank,
                                  year,
                                  status,
                                  coords,
-                                 station,
-                                 col_names, ...) {
+                                 station, ...) {
   translit = check_locale()
   stopifnot(rank == "synop" | rank == "climate") # for hourly data only synop and climate has data
   base_url = "https://danepubliczne.imgw.pl/data/dane_pomiarowo_obserwacyjne/"
@@ -279,7 +272,7 @@ meteo_imgw_hourly_bp = function(rank,
   }
 
   all_data = imgw_rename_params_to_labels(all_data, meta)
-  all_data = meteo_shortening_imgw(all_data, col_names = col_names, ...)
+  all_data = meteo_shortening_imgw(all_data, ...)
 
   # check if there any messages gathered in env$logs and if it is not empty then print them:
   if (length(env$logs) > 0) {