ipea · rafapereirabr · May 23, 2026 · May 23, 2026 · May 23, 2026 · May 23, 2026
diff --git a/DESCRIPTION b/DESCRIPTION
@@ -1,7 +1,7 @@
 Type: Package
 Package: geocodebr
 Title: Geolocalização De Endereços Brasileiros (Geocoding Brazilian Addresses)
-Version: 0.6.2
+Version: 0.6.2.9000
 Authors@R: c(
     person("Rafael H. M.", "Pereira", , "rafa.pereira.br@gmail.com", role = c("aut", "cre"),
            comment = c(ORCID = "0000-0003-2125-7465")),
@@ -42,7 +42,6 @@ Imports:
     duckspatial (>= 1.0.0),
     enderecobr (>= 0.5.0),
     fs,
-    geoarrow (>= 0.4.2),
     glue,
     h3r,
     httr2 (>= 1.0.0),
@@ -68,4 +67,4 @@ Config/testthat/edition: 3
 Encoding: UTF-8
 Language: pt
 Roxygen: list(markdown = TRUE)
-RoxygenNote: 7.3.3
+Config/roxygen2/version: 8.0.0
diff --git a/NEWS.md b/NEWS.md
@@ -1,3 +1,20 @@
+# geocodebr v0.6.3 dev
+
+## Correção de bugs (Bug fixes)
+
+- Bug corrigido que agora permite usuários passarem como input tabelas de 
+endereços com apenas alguns campos. Os campos de municio e unidade da federação
+continuam sendo obrigatórios. Encerra [#89](https://github.com/ipeaGIT/geocodebr/issues/89)
+e [#94](https://github.com/ipeaGIT/geocodebr/issues/94)
+
+## Mudanças pequenas (Minor changes)
+
+- A função `geocode_reverso()` teve pequeno ganho de velocidade, com drástica 
+redução no consumo de memória. Na amostra de 1000 pontos, o uso de memória caiu
+de 161MB para 95MB.
+
+
+
 # geocodebr v0.6.2
 
 ## Correção de bugs (Bug fixes)
@@ -7,7 +24,7 @@ data release corrente, e ignora eventuais dados de releases antigos que estejam
 na pasta. [Encerra #90](https://github.com/ipeaGIT/geocodebr/issues/90)
 - A função `geocode()` agora retorna erro informativo quando alguma coluna na tabela 
 de input tem nome com algum caractere não alfanumérico, como . , ? ^ - ! ~. Não 
-há problema com o sublinhado _, como em “name_muni”. Fecha [issue #92](https://github.com/ipeaGIT/geocodebr/issues/92)
+há problema com o barra baixa _, como em “name_muni”. Fecha [issue #92](https://github.com/ipeaGIT/geocodebr/issues/92)
 - Corrigido erro na função de `geocode_reverso()` que impedia usar valores muito
 altos de `dist_max`. [Encerra #88](https://github.com/ipeaGIT/geocodebr/issues/88)
 - Incluido 'Language: pt' na DESCRIPTION

diff --git a/R/geocode.R b/R/geocode.R
@@ -210,6 +210,30 @@ geocode_core <- function(
   # systime start 66666 ----------------
   # timer$mark("Start")
 
+  # fix eventual missing fields in input data -------------------------------------------------------
+  # geocodebr requires all address fields to be declared
+  # if one or more fields are empty, we add mock columns with empty strings
+
+  campos_endereco <- assert_and_assign_address_fields(
+    campos_endereco,
+    enderecos
+  )
+
+  # determine which columns are missing, if any
+  missing_cols <- campos_endereco[unlist(lapply(campos_endereco, is.null))]
+
+  if (length(missing_cols)>=1) {
+
+    # add empty string to missing cols
+    data.table::setDT(enderecos)
+    new_colnames <- paste0(names(missing_cols), "tempgeocodebr")
+    enderecos[, (new_colnames) := NA_character_ ]
+
+    # update address fields with fake columns
+    campos_endereco[sapply(campos_endereco, is.null)] <- as.list(new_colnames)
+  }
+
+
   # normalize input data -------------------------------------------------------
   # standardizing the addresses table to increase the chances of finding a match
   # in the CNEFE data
@@ -219,11 +243,6 @@ geocode_core <- function(
       message_standardizing_addresses()
     }
 
-    campos_endereco <- assert_and_assign_address_fields(
-      campos_endereco,
-      enderecos
-    )
-
     input_padrao <- enderecobr::padronizar_enderecos(
       enderecos = enderecos,
       campos_do_endereco = enderecobr::correspondencia_campos(
@@ -487,6 +506,21 @@ geocode_core <- function(
   # drop geocodebr temp id column
   output_df[, tempidgeocodebr := NULL]
 
+  # # col precisao como ordered factor
+  # ordem_precisao <- c(
+  #   "numero",
+  #   "numero_aproximado",
+  #   "logradouro",
+  #   "cep",
+  #   "localidade",
+  #   "municipio"
+  # )
+  # output_df[, precisao := factor(
+  #   precisao,
+  #   levels = ordem_precisao,
+  #   ordered = TRUE
+  # )]
+
   # Disconnect from DuckDB when done
   duckdb::dbDisconnect(con)
 
@@ -508,6 +542,11 @@ geocode_core <- function(
     # timer$mark("Add H3")
   }
 
+  # drop eventual mock columns with empty strings
+  if (length(missing_cols)>=1) {
+    output_df[, (new_colnames) := NULL]
+  }
+
   # remove data.table class
   data.table::setindex(output_df, NULL)
   data.table::setDF(output_df)

diff --git a/R/geocode_reverso.R b/R/geocode_reverso.R
@@ -67,9 +67,6 @@ geocode_reverso <- function(
     )
   }
 
-  # pontos <- sf::st_transform(pontos, 4674)
-
-
   # prep input -------------------------------------------------------
 
   # converte pontos de input para data.frame
@@ -114,24 +111,8 @@ geocode_reverso <- function(
   # limita escopo de busca aos municipios  -------------------------------------------------------
   # determine potential municipalities
   munis <- system.file("extdata/munis_bbox_2022.parquet", package = "geocodebr") |>
-    arrow::open_dataset() |>
-    sf::st_as_sf()
-
-  # place holder to use geoarrow becaue:
-  #   Namespace in Imports field not imported from: 'geoarrow'
-  #        All declared Imports should be used.
-  geoarrow::as_geoarrow_vctr("POINT (0 1)")
-
-  # munis_path <- system.file("extdata/munis_2022.parquet", package = "geocodebr")
-  #
-  # query_register_muni <- glue::glue(
-  #   "CREATE OR REPLACE TEMP VIEW munis AS
-  #       SELECT *,
-  #       geometry::GEOMETRY AS geometry
-  #   FROM read_parquet('{munis_path}');"
-  # )
-  #
-  # DBI::dbExecute(conn, query_register_muni)
+    duckspatial::ddbs_open_dataset()
+
 
   potential_munis <- duckspatial::ddbs_join(
     x = pontos,
@@ -185,22 +166,28 @@ geocode_reverso <- function(
   # ST_Point(lon, lat)::GEOMETRY('EPSG:4674') AS geom
 
 
-  cnefe_utm_duck <-  duckspatial::ddbs_transform(
+  # converte cnefe para UTM
+  cnefe_utm_duck <- duckspatial::ddbs_transform(
     x = 'cnefe_tb',
-    y = 'EPSG:31983',conn = conn,
+    y = 'EPSG:31983',
+    conn = conn,
     quiet = TRUE
   )
 
-  # input to UTM
-  input_utm_duck <-  duckspatial::ddbs_transform(
+  # converte pontos para UTM
+  input_utm_duck <- duckspatial::ddbs_transform(
     x = pontos,
     y = 'EPSG:31983',
+    conn = conn,
+    name = "pontos_utm",
+    overwrite = T,
     quiet = TRUE
   )
 
-  # buffers around input points
+  # buffer around input points
   buff <- duckspatial::ddbs_buffer(
-    x = input_utm_duck,
+    x = "pontos_utm",
+    conn = conn,
     distance = dist_max,
     quiet = TRUE
   )
@@ -210,30 +197,14 @@ geocode_reverso <- function(
     result <- duckspatial::ddbs_join(
       x = cnefe_utm_duck,
       y = buff,
-      join = "within",
+      join = "intersects", # intersects within
+      conn = conn,
+      name = "join_result",
+      overwrite = T,
       quiet = TRUE
     )
   )
 
-  # write to connection
-  duckspatial::ddbs_write_table(
-    conn = conn,
-    data = input_utm_duck,
-    name = "pontos_utm",
-    overwrite = T,
-    temp_view = T,
-    quiet = TRUE
-  )
-
-  duckspatial::ddbs_write_table(
-    conn = conn,
-    data = result,
-    name = "join_result",
-    overwrite = T,
-    temp_view = T,
-    quiet = TRUE
-  )
-
   # Get column names from both tables
   cols_a <- DBI::dbGetQuery(conn, "SELECT column_name FROM (DESCRIBE pontos_utm)")$column_name
   cols_b <- DBI::dbGetQuery(conn, "SELECT column_name FROM (DESCRIBE join_result)")$column_name
@@ -256,7 +227,7 @@ geocode_reverso <- function(
         ST_Distance(a.geometry, b.geometry) AS distancia_metros,
         ROW_NUMBER() OVER (
           PARTITION BY a.id
-          ORDER BY ST_Distance(a.geometry, b.geometry)
+          ORDER BY distancia_metros
         ) AS rn
       FROM pontos_utm AS a
       JOIN join_result AS b

diff --git a/R/onLoad.R b/R/onLoad.R
diff --git a/cran-comments.md b/cran-comments.md
@@ -1,21 +1,22 @@
 ## R CMD check results
 
-── R CMD check results ────────────────────────────────────────────── geocodebr 0.6.2 ────
-Duration: 2m 33.3s
+── R CMD check results ───────────────────────────────────────────── geocodebr 0.6.3 ────
+Duration: 2m 39s
 
 0 errors ✔ | 0 warnings ✔ | 0 notes ✔
 
-# geocodebr v0.6.2
 
-## Correção de bugs (Bug fixes)
+# geocodebr v0.6.3
 
-- Fixed a bug to ensure that the package uses only cached data from the 
-current release and ignores any data from older releases that may be 
-in the folder. [Closes #90](https://github.com/ipeaGIT/geocodebr/issues/90)
-- The `geocode()` function now returns an informational error when a column in the 
-input table has a name containing a non-alphanumeric character, such as . , ? ^ - ! ~. There 
-is no issue with the underscore _, as in “name_muni”. Closed [issue #92](https://github.com/ipeaGIT/geocodebr/issues/92)
-- Fixed a bug in the `geocode_reverso()` function that prevented the use of very
-high values for `dist_max`. [Closes #88](https://github.com/ipeaGIT/geocodebr/issues/88)
-- Added ‘Language: pt’ to DESCRIPTION
+## Bug fixes
 
+- Fixed a bug that now allows users to pass address tables containing only a 
+subset of address fields as input. Municipality and state fields remain 
+mandatory. Closes [#89](https://github.com/ipeaGIT/geocodebr/issues/89)
+and [#94](https://github.com/ipeaGIT/geocodebr/issues/94)
+
+## Minor changes
+
+- The `geocode_reverso()` function achieved a small speed improvement, along 
+with a substantial reduction in memory usage. In a sample of 1,000 points, 
+memory consumption dropped from 161MB to 95MB.
diff --git a/inst/extdata/large_sample.parquet b/inst/extdata/large_sample.parquet
diff --git a/inst/extdata/munis_bbox_2022.parquet b/inst/extdata/munis_bbox_2022.parquet
diff --git a/man/definir_pasta_cache.Rd b/man/definir_pasta_cache.Rd
diff --git a/man/geocodebr.Rd b/man/geocodebr.Rd
diff --git a/tests/tests_rafa/benchmark_20k.R b/tests/tests_rafa/benchmark_20k.R
@@ -9,14 +9,16 @@ ncores <- 7
 
 
 campos <- geocodebr::definir_campos(
-  logradouro = 'logradouro',
-  numero = 'numero',
+  # logradouro = 'logradouro',
+  # numero = 'numero',
   cep = 'cep',
   localidade = 'bairro',
   municipio = 'municipio',
   estado = 'uf'
 )
 
+input_df$logradouro <- NULL
+input_df$numero <- NULL
 
 bench::mark(iterations = 3,
   a <- geocodebr::geocode(
@@ -34,5 +36,8 @@ bench::mark(iterations = 3,
 #          expression    min median `itr/sec` mem_alloc `gc/sec` n_itr  n_gc total_time result memory
 # streetmap 0.6.0 dev  7.10s  7.26s     0.136    5.47MB        0     5     0      36.7s <df>   <Rprofmem>
 # laptop    0.6.0 CRAN  5.2s  5.53s     0.174    7.46MB        0     5     0      28.8s <df>
-# load 1 a <- geoc…  8.1s  8.79s     0.116    3.03MB        0     3     0        26s
-# sem 1 a <- geoc… 10.3s  10.5s    0.0944    3.03MB        0     3     0      31.8s
+#1              ""    8.67s  8.86s     0.113    2.04MB   0.0565     2     1      17.7s <df>
+#1              ""    8.35s  8.82s     0.115    5.43MB        0     3     0      26.1s <df>
+#1        "NA_int"    6.52s  6.58s     0.152    4.18MB   0.0760     2     1      13.2s <df>
+#1        "NA_int"    6.54s  6.81s     0.147    1.73MB   0.0734     2     1      13.6s <df>
+1 a <- geocodebr::ge… 7.58s  7.72s     0.124    4.18MB        0     3     0      24.1s <df>
diff --git a/tests/tests_rafa/generate_sample_data.R b/tests/tests_rafa/generate_sample_data.R
@@ -130,6 +130,9 @@ setDT(df)
 df[, id := 1:nrow(df)]
 head(df)
 
+data.table::setindex(df, NULL)
+data.table::setDF(df)
+
 arrow::write_parquet(df, './inst/extdata/large_sample.parquet')