wtassinari · albhasan · Jul 10, 2026
diff --git a/.Rbuildignore b/.Rbuildignore
@@ -13,3 +13,7 @@
 ^\.vscode$
 ^\.idea$
 ^\.Rhistory$
+^.*\.gitkeep$
+README.html
+sticker_queimadasR.png
+
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Package: queimadasR
 Type: Package
 Title: Download and Analysis of Wildfire Data from INPE
-Version: 0.2.0
+Version: 0.2.1
 Authors@R: c(
     person("Wagner", "Tassinari",
            email = "wagner.tassinari@ufrrj.br",
@@ -38,7 +38,6 @@ License: MIT + file LICENSE
 Encoding: UTF-8
 LazyData: false
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.1
 Depends:
     R (>= 3.5.0)
 Imports:
@@ -48,7 +47,6 @@ Suggests:
     testthat (>= 3.0.0),
     knitr,
     rmarkdown
-VignetteBuilder: knitr
 URL: https://github.com/wtassinari/queimadasR
 BugReports: https://github.com/wtassinari/queimadasR/issues
-
+Config/roxygen2/version: 8.0.0
diff --git a/LICENSE b/LICENSE
@@ -0,0 +1,2 @@
+YEAR: 2026
+COPYRIGHT HOLDER: queimadasR authors
diff --git a/LICENSE.md b/LICENSE.md
@@ -0,0 +1,21 @@
+# MIT License
+
+Copyright (c) 2026 queimadasR authors
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.
diff --git a/R/download_fire_spots.R b/R/download_fire_spots.R
@@ -48,8 +48,8 @@
 #' north_states <- c("ACRE", "AMAPA", "AMAZONAS", "PARA", "RONDONIA", "RORAIMA", "TOCANTINS")
 #' north_data <- download_fire_spots(
 #'   start_date_str = "01/08/2023",
-#'   end_date_str   = "30/09/2023",
-#'   target_states  = north_states,
+#'   end_date_str = "30/09/2023",
+#'   target_states = north_states,
 #'   deduplicate_final = TRUE
 #' )
 #'
@@ -66,14 +66,14 @@
 #' @export
 download_fire_spots <- function(
   start_date_str, end_date_str,
-  region            = "Brasil",
-  target_states     = NULL,
+  region = "Brasil",
+  target_states = NULL,
   target_satellites = NULL,
-  timeout           = 300,
-  sleep_sec         = 1,
+  timeout = 300,
+  sleep_sec = 1,
   show_satellites_when_empty = TRUE,
   deduplicate_final = TRUE,
-  dedup_keys        = c("latitude", "longitude", "data_pas", "municipio")
+  dedup_keys = c("latitude", "longitude", "data_pas", "municipio")
 ) {
   options(timeout = timeout)
 
@@ -101,7 +101,8 @@ download_fire_spots <- function(
   # Parse datetime strings to POSIXct in GMT, trying multiple formats
   parse_datetime_gmt <- function(x) {
     as.POSIXct(
-      x, tz = "GMT",
+      x,
+      tz = "GMT",
       tryFormats = c(
         "%Y-%m-%d %H:%M:%S",
         "%Y-%m-%d %H:%M",
@@ -124,16 +125,18 @@ download_fire_spots <- function(
     # Also try any column whose name starts with "data"
     candidates <- unique(c(candidates, grep("^data", names(df), ignore.case = TRUE, value = TRUE)))
     candidates <- intersect(candidates, names(df))
-    if (length(candidates) == 0) return(NULL)
+    if (length(candidates) == 0) {
+      return(NULL)
+    }
 
-    best     <- NULL
-    best_ok  <- -1L
+    best <- NULL
+    best_ok <- -1L
     for (nm in candidates) {
-      x  <- parse_datetime_gmt(df[[nm]])
+      x <- parse_datetime_gmt(df[[nm]])
       ok <- sum(!is.na(x))
       if (ok > best_ok) {
         best_ok <- ok
-        best    <- nm
+        best <- nm
       }
     }
     best
@@ -147,12 +150,14 @@ download_fire_spots <- function(
     "GOES_13" = c("GOES-13", "GOES_13", "GOES-13D", "GOES_13D"),
     "NPP_375" = c("NPP-375", "NPP_375", "NPP-375D", "NPP_375D", "SUOMI_NPP_375", "SUOMI_NPP_375D")
   )
-  sat_alias        <- lapply(sat_alias, norm_sat)
+  sat_alias <- lapply(sat_alias, norm_sat)
   names(sat_alias) <- norm_sat(names(sat_alias))
 
   # Expand satellite names to include all known aliases
   expand_sats <- function(sats) {
-    if (is.null(sats)) return(NULL)
+    if (is.null(sats)) {
+      return(NULL)
+    }
     s_norm <- norm_sat(sats)
     unique(unlist(lapply(s_norm, function(s) {
       if (s %in% names(sat_alias)) sat_alias[[s]] else s
@@ -181,16 +186,16 @@ download_fire_spots <- function(
   # Parse input dates
   # ---------------------------
   start_date <- as.Date(start_date_str, format = "%d/%m/%Y")
-  end_date   <- as.Date(end_date_str,   format = "%d/%m/%Y")
+  end_date <- as.Date(end_date_str, format = "%d/%m/%Y")
   if (is.na(start_date) || is.na(end_date)) stop("Invalid date format. Use 'DD/MM/YYYY'.")
-  if (end_date < start_date)                stop("end_date must be >= start_date.")
+  if (end_date < start_date) stop("end_date must be >= start_date.")
 
   start_year <- as.integer(format(start_date, "%Y"))
-  end_year   <- as.integer(format(end_date,   "%Y"))
-  years      <- seq(start_year, end_year)
+  end_year <- as.integer(format(end_date, "%Y"))
+  years <- seq(start_year, end_year)
 
   dt_start <- as.POSIXct(paste0(format(start_date, "%Y-%m-%d"), " 00:00:00"), tz = "GMT")
-  dt_end   <- as.POSIXct(paste0(format(end_date,   "%Y-%m-%d"), " 23:59:59"), tz = "GMT")
+  dt_end <- as.POSIXct(paste0(format(end_date, "%Y-%m-%d"), " 23:59:59"), tz = "GMT")
 
   use_all_satellites <- is.null(target_satellites) ||
     (length(target_satellites) == 1 && toupper(target_satellites) %in% c("TODOS", "ALL"))
@@ -199,7 +204,7 @@ download_fire_spots <- function(
   cat("Filter Period:", start_date_str, "to", end_date_str, "\n")
   cat("Years to Download:", paste(years, collapse = ", "), "\n")
   cat("Region:", region, "\n")
-  if (!is.null(target_states))   cat("Filtering by States:", paste(target_states, collapse = ", "), "\n")
+  if (!is.null(target_states)) cat("Filtering by States:", paste(target_states, collapse = ", "), "\n")
   if (use_all_satellites) {
     cat("Filtering by Satellites: ALL\n")
   } else {
@@ -210,112 +215,120 @@ download_fire_spots <- function(
   # ---------------------------
   # Loop over years
   # ---------------------------
-  data_list       <- vector("list", length(years))
-  success_count   <- 0L
-  error_count     <- 0L
+  data_list <- vector("list", length(years))
+  success_count <- 0L
+  error_count <- 0L
 
   for (i in seq_along(years)) {
     current_year <- years[i]
-    file_name    <- paste0("focos_br_todos-sats_", current_year, ".zip")
+    file_name <- paste0("focos_br_todos-sats_", current_year, ".zip")
     url <- paste0(
       "https://dataserver-coids.inpe.br/queimadas/queimadas/focos/csv/anual/Brasil_todos_sats/",
       file_name
     )
 
     cat(sprintf("[%d/%d] %s ... ", i, length(years), current_year))
 
-    temp_dir   <- tempdir()
+    temp_dir <- tempdir()
     local_file <- file.path(temp_dir, file_name)
 
-    res <- tryCatch({
-      # Download file
-      status <- download.file(url, local_file, mode = "wb", quiet = TRUE, method = "auto")
-      if (status != 0) stop("Download failed (download.file returned != 0).")
-
-      # Find CSV inside the ZIP
-      zip_list <- unzip(local_file, list = TRUE)
-      csvs     <- zip_list$Name[grepl("\\.csv$", zip_list$Name, ignore.case = TRUE)]
-      if (length(csvs) == 0) stop("ZIP does not contain a CSV file.")
-      csv_in_zip <- csvs[1]
-
-      # Read CSV directly from the ZIP
-      year_data <- read.csv(unz(local_file, csv_in_zip), stringsAsFactors = FALSE)
-
-      # Detect datetime column and standardize as data_pas
-      dt_col <- find_datetime_column(year_data)
-      if (is.null(dt_col)) {
-        stop(paste0("Could not find a datetime column. Columns found: ", paste(names(year_data), collapse = ", ")))
-      }
+    res <- tryCatch(
+      {
+        # Download file
+        status <- utils::download.file(url, local_file,
+          mode = "wb",
+          quiet = TRUE, method = "auto"
+        )
+        if (status != 0) stop("Download failed (download.file returned != 0).")
+
+        # Find CSV inside the ZIP
+        zip_list <- utils::unzip(local_file, list = TRUE)
+        csvs <-
+          zip_list$Name[grepl("\\.csv$", zip_list$Name, ignore.case = TRUE)]
+        if (length(csvs) == 0) stop("ZIP does not contain a CSV file.")
+        csv_in_zip <- csvs[1]
+
+        # Read CSV directly from the ZIP
+        year_data <- utils::read.csv(unz(local_file, csv_in_zip),
+          stringsAsFactors = FALSE
+        )
+
+        # Detect datetime column and standardize as data_pas
+        dt_col <- find_datetime_column(year_data)
+        if (is.null(dt_col)) {
+          stop(paste0("Could not find a datetime column. Columns found: ", paste(names(year_data), collapse = ", ")))
+        }
 
-      dt_parsed <- parse_datetime_gmt(year_data[[dt_col]])
-      if (all(is.na(dt_parsed))) stop(paste0("Failed to convert datetime column: ", dt_col))
-
-      # Ensure data_pas column is always present as POSIXct
-      year_data$data_pas <- dt_parsed
-
-      # Filter by period
-      filtered_data <- year_data[year_data$data_pas >= dt_start & year_data$data_pas <= dt_end, , drop = FALSE]
-
-      # Filter by state
-      if (!is.null(target_states) && region == "Brasil") {
-        uf_candidates <- c("estado", "uf", "sigla_uf", "estado_sigla")
-        uf_col        <- intersect(uf_candidates, names(filtered_data))
-        if (length(uf_col) > 0) {
-          uf_col        <- uf_col[1]
-          target_norm   <- norm_txt(target_states)
-          filtered_data <- filtered_data[norm_txt(filtered_data[[uf_col]]) %in% target_norm, , drop = FALSE]
-        } else {
-          warning("State filter was requested, but no 'estado/uf' column was found.")
+        dt_parsed <- parse_datetime_gmt(year_data[[dt_col]])
+        if (all(is.na(dt_parsed))) stop(paste0("Failed to convert datetime column: ", dt_col))
+
+        # Ensure data_pas column is always present as POSIXct
+        year_data$data_pas <- dt_parsed
+
+        # Filter by period
+        filtered_data <- year_data[year_data$data_pas >= dt_start & year_data$data_pas <= dt_end, , drop = FALSE]
+
+        # Filter by state
+        if (!is.null(target_states) && region == "Brasil") {
+          uf_candidates <- c("estado", "uf", "sigla_uf", "estado_sigla")
+          uf_col <- intersect(uf_candidates, names(filtered_data))
+          if (length(uf_col) > 0) {
+            uf_col <- uf_col[1]
+            target_norm <- norm_txt(target_states)
+            filtered_data <- filtered_data[norm_txt(filtered_data[[uf_col]]) %in% target_norm, , drop = FALSE]
+          } else {
+            warning("State filter was requested, but no 'estado/uf' column was found.")
+          }
         }
-      }
 
-      # Filter by satellite (with aliases), only if NOT using all satellites
-      if (!use_all_satellites && region == "Brasil") {
-        sat_candidates <- c("satelite", "satellite", "sensor")
-        sat_col        <- intersect(sat_candidates, names(filtered_data))
-        if (length(sat_col) > 0) {
-          sat_col <- sat_col[1]
+        # Filter by satellite (with aliases), only if NOT using all satellites
+        if (!use_all_satellites && region == "Brasil") {
+          sat_candidates <- c("satelite", "satellite", "sensor")
+          sat_col <- intersect(sat_candidates, names(filtered_data))
+          if (length(sat_col) > 0) {
+            sat_col <- sat_col[1]
 
-          expanded_targets <- expand_sats(target_satellites)  # normalized
-          sat_vals_norm    <- norm_sat(filtered_data[[sat_col]])
+            expanded_targets <- expand_sats(target_satellites) # normalized
+            sat_vals_norm <- norm_sat(filtered_data[[sat_col]])
 
-          filtered_data2 <- filtered_data[sat_vals_norm %in% expanded_targets, , drop = FALSE]
+            filtered_data2 <- filtered_data[sat_vals_norm %in% expanded_targets, , drop = FALSE]
 
-          if (nrow(filtered_data2) == 0L && show_satellites_when_empty) {
-            top_sats <- sort(table(norm_sat(filtered_data[[sat_col]])), decreasing = TRUE)
-            top_sats <- head(top_sats, 10)
-            cat("\n    Warning: satellite filter returned zero records for this year. Available satellites (top 10):\n")
-            print(top_sats)
-          }
+            if (nrow(filtered_data2) == 0L && show_satellites_when_empty) {
+              top_sats <- sort(table(norm_sat(filtered_data[[sat_col]])), decreasing = TRUE)
+              top_sats <- utils::head(top_sats, 10)
+              cat("\n    Warning: satellite filter returned zero records for this year. Available satellites (top 10):\n")
+              print(top_sats)
+            }
 
-          filtered_data <- filtered_data2
-        } else {
-          warning("Satellite filter was requested, but no 'satelite/satellite/sensor' column was found.")
+            filtered_data <- filtered_data2
+          } else {
+            warning("Satellite filter was requested, but no 'satelite/satellite/sensor' column was found.")
+          }
         }
-      }
 
-      # Tag reference year
-      filtered_data$ref_year <- rep.int(current_year, nrow(filtered_data))
+        # Tag reference year
+        filtered_data$ref_year <- rep.int(current_year, nrow(filtered_data))
 
-      # Clean up ZIP file
-      if (file.exists(local_file)) file.remove(local_file)
+        # Clean up ZIP file
+        if (file.exists(local_file)) file.remove(local_file)
 
-      list(ok = TRUE, data = filtered_data)
-
-    }, error = function(e) {
-      if (file.exists(local_file)) file.remove(local_file)
-      list(ok = FALSE, err = conditionMessage(e))
-    })
+        list(ok = TRUE, data = filtered_data)
+      },
+      error = function(e) {
+        if (file.exists(local_file)) file.remove(local_file)
+        list(ok = FALSE, err = conditionMessage(e))
+      }
+    )
 
     if (isTRUE(res$ok)) {
-      data_list[[i]]  <- res$data
-      success_count   <- success_count + 1L
-      cat("✓ (", format(nrow(res$data), big.mark = ","), "fire spots)\n")
+      data_list[[i]] <- res$data
+      success_count <- success_count + 1L
+      cat("\\u2713 (", format(nrow(res$data), big.mark = ","), "fire spots)\n")
       Sys.sleep(sleep_sec)
     } else {
-      error_count     <- error_count + 1L
-      data_list[[i]]  <- NULL
-      cat("✗ Error\n")
+      error_count <- error_count + 1L
+      data_list[[i]] <- NULL
+      cat("\\u2717 Error\n")
       cat("    Details:", res$err, "\n")
     }
   }
@@ -332,13 +345,17 @@ download_fire_spots <- function(
   cat("\nCombining data...\n")
   complete_data <- do.call(rbind.data.frame, data_list[!vapply(data_list, is.null, logical(1))])
   cat("Total (before deduplication):", format(nrow(complete_data), big.mark = ","), "\n")
-  cat("Memory size:", format(object.size(complete_data), units = "MB"), "\n")
+  cat(
+    "Memory size:",
+    format(utils::object.size(complete_data), units = "MB"),
+    "\n"
+  )
 
   if (isTRUE(deduplicate_final)) {
     cat("\nDeduplicating by:", paste(dedup_keys, collapse = ", "), "...\n")
-    before        <- nrow(complete_data)
+    before <- nrow(complete_data)
     complete_data <- dedup_fire_spots(complete_data, dedup_keys)
-    after         <- nrow(complete_data)
+    after <- nrow(complete_data)
     cat("Removed:", format(before - after, big.mark = ","), "duplicates.\n")
     cat("Total (after deduplication):", format(after, big.mark = ","), "\n")
   }
Original file line number	Diff line number	Diff line change
		@@ -0,0 +1,2 @@
		YEAR: 2026
		COPYRIGHT HOLDER: queimadasR authors