primeira versao de padronizar_ceps()

DESCRIPTION

@@ -15,6 +15,9 @@ Description: Padroniza endereços brasileiros a partir de diferentes
 License: MIT + file LICENSE
 URL: https://github.com/ipeaGIT/enderecopadrao
 BugReports: https://github.com/ipeaGIT/enderecopadrao/issues
+Imports: 
+    checkmate,
+    stringr
 Suggests: 
     testthat (>= 3.0.0)
 Config/testthat/edition: 3

NAMESPACE

@@ -1,2 +1,3 @@
 # Generated by roxygen2: do not edit by hand
 
+export(padronizar_ceps)

R/padronizar_ceps.R

@@ -0,0 +1,44 @@
+#' Padronizar CEPs
+#'
+#' Padroniza CEPs.
+#'
+#' @param ceps Um vetor de caracteres ou números. Os CEPs a serem padronizados.
+#'
+#' @return Um vetor de caracteres com os CEPs padronizados.
+#'
+#' @examples
+#' ceps <- c("22290-140", "22.290-140", "22290 140", "22290140")
+#' padronizar_ceps(ceps)
+#'
+#' ceps <- c(22290140, 1000000, NA)
+#' padronizar_ceps(ceps)
+#'
+#' @export
+padronizar_ceps <- function(ceps) {
+  checkmate::assert(
+    checkmate::check_character(ceps),
+    checkmate::check_numeric(ceps),
+    combine = "or"
+  )
+
+  # alguns ceps podem vir vazios e devem permanecer vazios ao final. nesse caso,
+  # a chamada da str_pad() abaixo faz com que esses ceps virem "00000000". para
+  # evitar que o resultado contenha esses valores, identificamos o indice dos
+  # ceps vazios para ao final "reesvazia-los"
+
+  indice_cep_vazio <- which(ceps == "" | is.na(ceps))
+
+  ceps_padrao <- if (is.numeric(ceps)) {
+    format(ceps, scientific = FALSE)
+  } else {
+    ceps
+  }
+
+  ceps_padrao <- stringr::str_squish(ceps_padrao)
+  ceps_padrao <- stringr::str_replace_all(ceps_padrao, "\\.|-|,| ", "")
+  ceps_padrao <- stringr::str_pad(ceps_padrao, width = 8, pad = "0")
+
+  ceps_padrao[indice_cep_vazio] <- ""
+
+  return(ceps_padrao)
+}

_pkgdown.yml

@@ -1,2 +1,7 @@
+reference:
+  - title: "Campos individuais"
+  - contents:
+    - padronizar_ceps
+
 development:
   mode: auto

codemeta.json

@@ -48,7 +48,34 @@
     }
   ],
   "softwareRequirements": {
+    "1": {
+      "@type": "SoftwareApplication",
+      "identifier": "checkmate",
+      "name": "checkmate",
+      "provider": {
+        "@id": "https://cran.r-project.org",
+        "@type": "Organization",
+        "name": "Comprehensive R Archive Network (CRAN)",
+        "url": "https://cran.r-project.org"
+      },
+      "sameAs": "https://CRAN.R-project.org/package=checkmate"
+    },
+    "2": {
+      "@type": "SoftwareApplication",
+      "identifier": "stringr",
+      "name": "stringr",
+      "provider": {
+        "@id": "https://cran.r-project.org",
+        "@type": "Organization",
+        "name": "Comprehensive R Archive Network (CRAN)",
+        "url": "https://cran.r-project.org"
+      },
+      "sameAs": "https://CRAN.R-project.org/package=stringr"
+    },
     "SystemRequirements": null
   },
-  "fileSize": "4.336KB"
+  "fileSize": "6.204KB",
+  "readme": "https://github.com/ipeaGIT/enderecopadrao/blob/main/README.md",
+  "contIntegration": ["https://github.com/ipeaGIT/enderecopadrao/actions?query=workflow%3Acheck", "https://app.codecov.io/gh/ipeaGIT/enderecopadrao?branch=main"],
+  "developmentStatus": "https://lifecycle.r-lib.org/articles/stages.html"
 }