diff --git a/DESCRIPTION b/DESCRIPTION
index 78274e5279e73081d90c7b8ef55d20352b56b6ef..9a71a5fe8c24437b7b86091779ab42d0b3c5621a 100644
--- a/DESCRIPTION
+++ b/DESCRIPTION
@@ -1,6 +1,6 @@
Package: floodam.data
Title: Collect and Process Data on Flood Damage (French Context)
-Version: 0.9.40.0
+Version: 0.9.41.0
Authors@R: c(
person(given = "Frédéric",
family = "Grelot",
@@ -52,7 +52,6 @@ Depends:
R (>= 3.4.0)
Imports:
data.table,
- fst,
grDevices,
httr,
kableExtra,
diff --git a/NAMESPACE b/NAMESPACE
index 0d0969c2da5d18b128e4386ac5b8c676c2c8f9d0..28fd9c733967d5325d1bfebdba903f59ead39fa9 100644
--- a/NAMESPACE
+++ b/NAMESPACE
@@ -1,10 +1,10 @@
# Generated by roxygen2: do not edit by hand
export(adapt.eaip)
-export(adapt.geo_sirene)
export(adapt_admin_express)
export(adapt_ban)
export(adapt_gaspar)
+export(adapt_geo_sirene)
export(adapt_rpg)
export(add_journal)
export(add_log_info)
@@ -32,6 +32,7 @@ export(download_archive)
export(download_ban)
export(download_bd_topo)
export(download_gaspar)
+export(download_geo_sirene)
export(extract.stat.log)
export(extract_building)
export(extract_building_agricultural)
@@ -42,6 +43,9 @@ export(format_archive)
export(format_scope)
export(generate_report)
export(get_archive)
+export(get_base_url)
+export(get_date_from_html)
+export(get_link_from_html)
export(gpkg_from_7z)
export(in_layer)
export(plot_construction_date)
@@ -60,7 +64,9 @@ export(save_archive)
export(select_scope)
export(send_message)
export(shp_from_7z)
+export(subset_with_message)
export(summarise_dwelling)
+export(to_logical)
export(update_ban)
export(update_state)
import(kableExtra)
diff --git a/NEWS.md b/NEWS.md
index c6e42e822c5c8ece01863fdf58ca338b24efc14c..5a50ef908dbafa5b1b363caa2e1b4a25a8a5865a 100644
--- a/NEWS.md
+++ b/NEWS.md
@@ -1,3 +1,98 @@
+# floodam.data 0.9.41.0
+
+## Enhancements
+
+* `adapt_geo_sirene()` (rename)
+ * new name for `adapat.geo_sirene`
+ * process changed to fit with `add_log_info()` and use of what classical
+ steps should be for all data (read with a scheme, select observations, split
+ by departments if necessary, add eaip information, save data and plot a map)
+ * documentation updated
+* `add_eaip()` (internal)
+ * messages added to better fllow analysis
+* `add_log_info()`
+ * better generation of sub-messages for analysis
+* `analyse_archive()`
+ * new `origin` for "geo-sirene"
+ * documentation & tests updated
+* `apply_scheme()`
+ * `Date` is used to detect when to apply `as.Date()` (consistency)
+ * `logical` type is detected and transformed with `to_logical()`
+* `download_archive()`
+ * adaptation to `get_archive()` (removal of parameter `html`, inclusion of
+ field `local_origin` in `to_do` parameter)
+ * field `short` in `to_do` may be missing
+ * documentation updated
+* `download_ban()`
+ * adaptation to `get_link_from_html()`
+ * introduction of parameter `repository`, different from `origin` (only url)
+ * simplification of process
+ * documentation updated (markdown format)
+* `download_geo_sirene()` (rename)
+ * new name for `download.geo_sirene`
+ * introduction of parameter `repository`, different from `origin` (only url)
+ * introduction of parameter `scope`, used when `repository` is "data.gouv"
+ * simplification of process
+ * documentation updated (markdown format)
+* `format_journal()` (internal)
+ * enhanced format dates coming from `base::Sys.Date()`
+* `get_archive()`
+ * adaptation to `get_link_from_html()`
+ * simplification and introduction of `local_origin` to deal with relative
+ links
+ * documentation updated
+* `get_base_url()` (new)
+ * return the parent url from a url
+ * documentation & tests added
+* `get_date_from_html()` (new)
+ * find admissible dates in a html page
+ * documentation & tests added
+* `get_link_from_html()` (new)
+ * find links in a html page
+ * documentation & tests added
+* `read_csv_with_scheme()`
+ * `Date` is used to detect when to apply `as.Date()` (consistency)
+ * `logical` type is detected and transformed with `to_logical()`
+ * preprocessing to remove observations with `NA` in lon\lat before
+ transformation with `sf::st_as_sf()`
+ * messages generation added
+* `scheme_bd_topo_3` (data)
+ * complete missing `type_source`
+* `scheme_gaspar_azi` (data)
+ * correct value for `type` and `type_source`
+* `scheme_gaspar_catnat` (data)
+ * correct value for `type` and `type_source`
+* `scheme_gaspar_dicrim` (data)
+ * correct value for `type` and `type_source`
+* `scheme_gaspar_pcs` (data)
+ * correct value for `type` and `type_source`
+* `scheme_gaspar_pprn` (data)
+ * correct value for `type` and `type_source`
+* `scheme_gaspar_risq` (data)
+ * correct value for `type_source`
+* `scheme_rpg_1` (data)
+ * correct value for `type_source`
+* `scheme_rpg_1` (data)
+ * correct value for `type_source`
+* `scheme_sirene_2019` (data)
+ * style of field names "." → "_"
+ * "longitude" and "latitude" renamed to "lon" and "lat" in `name` field for
+ consistency and usage in `read_csv_with_scheme()`
+ * documentation updated
+* `scheme_sirene_na` (data)
+ * style of field names "." → "_"
+ * documentation updated
+* `subset_with_message()` (new)
+ * subset without side-effects and with messages useful for `add_log_info()`
+ * documentation added
+* `split_dep()` (new, internal)
+ * split a `sf` `data.frame `either geomatically if a department `sf` object
+ is given, or through the information given in `commune` if not
+ * documentation added
+* `to_logical()`
+ * default treatment for easy English and French usage
+ * documentation updated & tests added
+
# floodam.data 0.9.40.0
## Enhancements
@@ -103,14 +198,15 @@
## Enhancements
* `adapt_admin_express()`
- * replace adapt.admin_express
- * use add_log_info for journal from new journal system
- * use read_with_scheme to read and format data
- * use save_archive to save result
- * option 'export' renamed in 'extension' for cohérence with save_archive
+ * replace `adapt.admin_express`
+ * use `add_log_info()` for journal from new journal system
+ * use `read_with_scheme()` to read and format data
+ * use `save_archive()` to save result
+ * option 'export' renamed in 'extension' for consistency with
+ `save_archive()`
* documentation updated
* `analyse_archive()`
- * function within its own file and exporteds
+ * function within its own file and exported
* treat 2 formats ('ign' & 'floodam.data')
* addition of warnings
* function tested in test_analyse_archive
@@ -141,12 +237,12 @@
* utilisation de add_journal_new au lieu de add_journal
* `add_journal()`
* reprise de add_journal_new
- * ancienne add_journal renommée temporairement en add_journal_old le
+ * ancien add_journal renommée temporairement en add_journal_old le
temps de la migration
* meilleure présentation des sous-tâches en introduisant le paramètre
degree
* `write_journal()` (new)
- * permet d'écrire un journal produit par add_journal_new soit au format
+ * permet d'écrire un journal produit par `add_journal_new()` soit au format
"csv", soit au format "log" en fonction de l'extension du fichier
* si aucun fichier n'est donné, le message au format "log" est affiché
sur la sortie standard
@@ -173,12 +269,12 @@
* pour zip, attention fait appel à une commande 'system' en modifiant
le nom du fichier pour faire une commande qui sera détectée par
`data.table::fread()`, et présume que le format sera csv et pourra être lu
- avec read_csv_with_scheme
+ avec `read_csv_with_scheme()`
* pour zip, modifie temporairemen l'option
'datatable.fread.input.cmd.message' pour éviter le message renvoyé par
`data.table::fread()`
* `read_csv_with_scheme()` (new)
- * correspond à ancienne version de read_with_scheme qui était csv
+ * correspond à ancienne version de `read_with_scheme()` qui était "csv"
spécifique
* `read_gpkg_with_scheme()` (new)
* gestion de gpkg avec scheme et projection
@@ -191,7 +287,7 @@
* Séparation claire de la décompression et de la lecture
* Sécurité si plusieurs gpkg
* `download_admin_express()`
- * transformation de download.admin_express
+ * transformation de `download.admin_express`
* meilleure gestion des options (et match.arg)
* `scheme_admin_express_3_1 `(data)
* nouveau format à partir des infos IGN (version 3-1)
@@ -208,7 +304,7 @@
* documentation
* corrections de coquilles (à la volée) pour les datasets
* regroupement des documentions pour fonction de la famille
- read_with_scheme
+ `read_with_scheme()`
* data.cquest.org
* toutes les mentions à l'adresse passent en https au lieu de http
* Roxygen
diff --git a/R/adapt.geo_sirene.R b/R/adapt.geo_sirene.R
deleted file mode 100644
index acd0073b1be295a72ae055b6e410dee97fcab31f..0000000000000000000000000000000000000000
--- a/R/adapt.geo_sirene.R
+++ /dev/null
@@ -1,324 +0,0 @@
-#' @title Adapt sirene data
-#'
-#' @description
-#' The following treatment are performed:
-#' - Only some fileds are selected, field names (colnames) are consistently set.
-#' - NA values are consistently set.
-#' - Type of fields are consistently set, some checks are performed on transformations.
-#' - Data set is cut and saved by departments
-#' - Only observations with spatial coordinates are kept.
-#' - Exposition of observations (belonging or not to eaip) is added.
-#'
-#' @param origin character, path to the directory where archive are stored
-#' @param destination character, path to the directory where results should be saved
-#' @param archive character, vector of archive to be adpated
-#' @param export character, option for export format of the results
-#' @param scheme data.frame, how archive variables should be treated
-#' @param na_value data.frame, list of NA values for each variables
-#' @param eaip_path character, path where eaip archives should be find
-#' @param projection optional numeric, 4 digits projection to use
-#' @param order_by optional character, name of the variable to sort the output data.
-#' Default sorting is by state and eaip (if added).
-#' @param retrieve logical, should the result be returned
-#' @param verbose logical, should the function give some sumup informations.
-#'
-#' @return if retrieve = TRUE, data.frame of adapated data stored in archive.
-#'
-#' @export
-#'
-#' @encoding UTF-8
-#' @author Victor Champonnois et Frédéric Grelot
-#'
-#' @examples
-#'
-#' \dontrun{
-#' origin = ""
-#' destination = tempdir()
-#' archive = "geo_siret_34.csv.gz"
-#' result = adapt.geo_sirene(origin, destination, verbose = TRUE, retrieve = TRUE)
-#' }
-
-adapt.geo_sirene = function(origin,
- destination,
- archive,
- export = "fst",
- scheme = floodam.data::scheme_sirene_2019,
- na_value = floodam.data::scheme_sirene_na,
- eaip_path = NULL,
- projection = 4326,
- order_by = c("state", "eaip"),
- retrieve = FALSE,
- verbose = FALSE) {
-
- ### Recursive call if archive is missing
- if (missing(archive)) {archive = list.files(origin, pattern = ".csv.gz$")}
- if (length(archive) > 1)
- return(lapply(archive,
- adapt.geo_sirene,
- origin = origin,
- destination = destination,
- export = export,
- scheme = scheme,
- na_value = na_value,
- eaip_path = eaip_path,
- projection = projection,
- order_by = order_by,
- retrieve = retrieve,
- verbose = verbose))
- if (length(archive) == 0)
- return(NULL)
-
- ### Analyse archive
- path = file.path(origin, archive)
- analyse = regmatches(archive, regexec("(.*?)[.](csv[.]gz|gz)$", archive, perl = TRUE))[[1]]
- if (length(analyse) == 0) return(NULL)
- name = analyse[2]
- extension = analyse[3]
- location = utils::tail(strsplit(origin, "/")[[1]], 1)
-
- ### Start journal information
- dir.create(destination, showWarnings = FALSE, recursive = TRUE) # Check if error may be generated.
- start_time = Sys.time()
- journal = add_journal_old(
- "WARNING: This file is automatically produced by floodam.data. Do not edit by hand.", "",
- "Contents", "\t1. General log informations", "\t2. Stats on removed data", "\t3. Stats on exposition", "",
- first = TRUE)
- journal = add_journal_old(
- sprintf("%s from '%s' adpated by floodam.data (%s)", archive, location, utils::packageVersion("floodam.data")),
- journal = journal, verbose = verbose, first = TRUE)
- journal = add_journal_old(sprintf("Starting time: %s", Sys.time()), journal = journal, verbose = verbose)
- on.exit(journal <- add_journal_old("",
- sprintf("Total time elapsed for %s from '%s': %s", name, location, fmt(Sys.time() - start_time)),
- journal = journal, verbose = verbose, first = TRUE))
- on.exit(write(journal, file.path(destination, sprintf("%s.%s", name, "log"))), add = TRUE)
-
- ### Read file and do selection, change colnames, start easy formatting
- scheme = scheme[order(scheme[["order"]]), ]
- colClasses = ifelse(scheme[["keep"]], "character", "NULL")
- colClasses[scheme[["type"]] == "integer" & scheme[["keep"]]] = "integer"
- colClasses[scheme[["type"]] == "numeric" & scheme[["keep"]]] = "numeric"
- scheme = scheme[scheme[["keep"]], ]
- rownames(scheme) = scheme[["name"]]
-
- size = c(inital = file.info(path)[["size"]])
- result = data.table::fread(path, colClasses = colClasses, na.strings = "",
- data.table = FALSE, col.names = scheme[["name"]])
-
- ### Mores adaptations
- # NA treament
- for (i in 1:nrow(na_value)) {
- var = na_value[i, "name"]
- result[[var]] = treat_na(result[[var]], na_value[i, "na.value"])
- }
-
- # format factors (after NA treatment)
- selection = rownames(scheme)[scheme[["type"]] == "factor"]
- result[selection] = lapply(result[selection], as.factor)
-
- # format Date (after NA treatment)
- selection = rownames(scheme)[scheme[["type"]] == "Date"]
- result[selection] = lapply(result[selection], as.Date)
- for (var in selection) {
- if (all(is.na(result[[var]]))) {
- journal = add_journal_old(sprintf("Possible format error for '%s'. All values are NA.", var),
- journal = journal, verbose = verbose)
- }
- }
-
- # format logical
- result[["employer"]] = to_logical(result[["employer"]], "O", "N")
- result[["hq"]] = to_logical(result[["hq"]], "true", "false")
-
- selection = rownames(scheme)[scheme[["type"]] == "logical"]
- for (var in selection) {
- if (all(is.na(result[[var]]))) {
- journal = add_journal_old(sprintf("Possible format error for '%s'. All values are NA.", var),
- journal = journal, verbose = verbose)
- }
- }
-
- # Check type
- test = sapply(result, class) == scheme[["type"]]
- if (all(test)) {
- journal = add_journal_old("All variables have the good type.", journal = journal, verbose = verbose)
- } else {
- journal = add_journal_old(
- sprintf("Some variables do not have the good type. Check %s.",
- paste("'", names(test)[!test], "'", sep = "", collapse = ", ")),
- journal = journal, verbose = verbose)
- }
-
- int_time = Sys.time()
- journal = add_journal_old(
- sprintf("Time elapsed: %s", fmt(int_time - start_time)),
- journal = journal, verbose = verbose)
-
- ### GIS adaptations by departments
-
- result = split(result, substring(result[["commune"]], 1, 2))
-
- # Remove some departements ?
- departement_remove = grep("98", names(result))
- if (length(departement_remove) > 0) result = result[-departement_remove]
-
- stat_remove = list()
- stat_eaip = list()
-
- for (d in names(result)) {
- journal = add_journal_old("",
- sprintf("Treating department %s in %s from '%s'.", d, name, location),
- journal = journal, verbose = verbose, first = TRUE)
-
- # Treat observations with missing spatial coordinates
- result[[d]][["coord"]] = stats::complete.cases(result[[d]][, c("longitude", "latitude")])
-
- stat = table(result[[d]][c("state", "coord")])
- colnames(stat) = c("missing", "present")
-
- journal = add_journal_old(
- sprintf("Observations removed due to missing spatial coordinates: %s over %s, %s remaining (%1.1f%%)",
- sum(stat[, "missing"]), sum(stat), sum(stat[, "present"]),
- sum(stat[, "present"]) / sum(stat) * 100),
- journal = journal, verbose = verbose)
- stat_remove[[d]] = as.data.frame(stat)
-
- # Removing observations with missing spatial coordinates
- result[[d]] = result[[d]][result[[d]][["coord"]],]
- result[[d]][["coord"]] = NULL
-
- # Transform in sf format
- result[[d]] = sf::st_as_sf(result[[d]], coords =c("longitude", "latitude"), crs = projection)
-
- # Adding information from eaip
- if (!is.null(eaip_path)) {
- if (is.character(eaip_path)) {
- eaip = try(
- suppressWarnings(readRDS(file.path(eaip_path, sprintf("eaip_%s.rds", format_scope(d))))),
- silent = TRUE
- )
- }
- if ("try-error" %in% class(eaip)) {
- journal = add_journal_old(sprintf("'eaip' analysis not included: '%s' is not a path to an rds archive.", path),
- journal = journal,
- verbose = verbose)
- } else if (!"sf" %in% class(eaip)) {
- journal = add_journal_old(
- sprintf("'eaip' analysis not included: '%s' is not a sf object.", path),
- journal = journal,
- verbose = verbose)
- } else {
- eaip = sf::st_transform(eaip, crs = projection)
- result[[d]][["eaip"]] = in_layer(result[[d]], eaip)
-
- stat = table(unclass(result[[d]])[c("state", "eaip")])
- colnames(stat) = c("out", "in")
-
- journal = add_journal_old(
- sprintf("'eaip' analysis included: %s in eaip over %s (%1.1f%%)",
- sum(stat[, "in"]), sum(stat), sum(stat[, "in"]) / sum(stat) * 100),
- journal = journal, verbose = verbose)
- stat_eaip[[d]] = as.data.frame(stat)
- }
- }
-
- ### Ordering
- selection = order_by[order_by %in% names(result[[d]])]
- if (length(selection) == 0) {
- journal = add_journal_old(
- "Result unsorted. 'order_by' does not contain any admissible name for geo_sirene data.",
- journal = journal, verbose = verbose)
- } else {
- result[[d]] = result[[d]][do.call(order, unclass(result[[d]])[selection]), ]
- journal = add_journal_old(
- sprintf("Result sorted by %s", paste("'", selection, "'", sep = "", collapse = " + ")),
- journal = journal, verbose = verbose)
- }
-
- ### Save result
- if ("rds" %in% export) {
- if (length(result) == 1) {
- path = file.path(destination, sprintf("%s.%s", name, "rds"))
- } else {
- path = file.path(destination, sprintf("%s-%s.%s", name, d, "rds"))
- }
- saveRDS(result[[d]], path)
- journal = add_journal_old(
- sprintf("Result saved as %s. Size: %s (%0.3f of inital)",
- path, file.info(path)[["size"]], file.info(path)[["size"]] / size),
- journal = journal, verbose = verbose)
- }
- if ("fst" %in% export) {
- sf::st_geometry(result[[d]]) = NULL
- if (length(result) == 1) {
- path = file.path(destination, sprintf("%s.%s", name, "fst"))
- } else {
- path = file.path(destination, sprintf("%s-%s.%s", name, d, "fst"))
- }
- fst::write.fst(result[[d]], path, compress = 100)
- journal = add_journal_old(
- sprintf("Result saved as %s. Size: %s (%0.3f of inital)",
- path, file.info(path)[["size"]], file.info(path)[["size"]] / size),
- journal = journal, verbose = verbose)
- }
- if (all(! export %in% c("rds", "fst"))) {
- journal = add_journal_old(
- sprintf("Result not saved: '%s' not admissible as export", export),
- journal = journal, verbose = verbose)
- }
-
-
- journal = add_journal_old(
- sprintf("Time elapsed: %s", fmt(Sys.time() - int_time)),
- journal = journal, verbose = verbose)
- int_time = Sys.time()
- }
-
- ### Add useful journal information
- journal_end = length(journal)
- journal[4] = paste(sep = "",
- journal[4], sprintf(": 8-%s", journal_end + 2)
- )
-
- stat_remove = do.call(rbind, stat_remove)
- if (!is.null(stat_remove)) {
- stat_remove[["departement"]] = substring(rownames(stat_remove), 1, 2)
- stat_remove = stat_remove[c("departement", "state", "coord", "Freq")]
- stat_remove[["Freq"]] = as.integer(stat_remove[["Freq"]])
- row.names(stat_remove) = NULL
- journal[5] = paste(sep = "",
- journal[5],
- sprintf(": %s-%s", journal_end + 4, journal_end + 4 + nrow(stat_remove))
- )
- journal_end = journal_end + nrow(stat_remove)
- on.exit(suppressWarnings(
- write(c("", utils::capture.output(stat_remove)), file.path(destination, sprintf("%s.%s", name, "log")),
- append = TRUE)),
- add = TRUE)
- } else {
- journal[5] = paste(sep = "", journal[5], ": none")
- }
-
- stat_eaip = do.call(rbind, stat_eaip)
- if (!is.null(stat_eaip)) {
- stat_eaip[["departement"]] = substring(rownames(stat_eaip), 1, 2)
- stat_eaip = stat_eaip[c("departement", "state", "eaip", "Freq")]
- stat_eaip[["Freq"]] = as.integer(stat_eaip[["Freq"]])
- row.names(stat_eaip) = NULL
- journal[6] = paste(sep = "",
- journal[6],
- sprintf(": %s-%s", journal_end + 6, journal_end + 6 + nrow(stat_eaip))
- )
- on.exit(suppressWarnings(
- write(c("", utils::capture.output(stat_eaip)), file.path(destination, sprintf("%s.%s", name, "log")),
- append = TRUE)),
- add = TRUE)
- } else {
- journal[6] = paste(sep = "", journal[6], ": none")
- }
-
- ### Retrieve result
- if (retrieve) {
- if (length(result) == 1) return(invisible(result[[1]]))
- return(invisible(result))
- }
-}
diff --git a/R/adapt_admin_express.R b/R/adapt_admin_express.R
index d41b8afa7a75799cd1e6164d9e8622fa5b774bcb..53e07f86f69332678173a0464e6508be34cb9c59 100644
--- a/R/adapt_admin_express.R
+++ b/R/adapt_admin_express.R
@@ -3,10 +3,10 @@
#' @description
#' `adapt_admin_express()` treats Admin Express archives to be in a standard
#' format. It is suited for IGN archives. It used by default
-#' \code{scheme_admin_express_3_1} as scheme. For older versions
-#' \code{scheme_admin_express_2_0} is also available.
+#' `scheme_admin_express_3_1`` as scheme. For older versions
+#' `scheme_admin_express_2_0` is also available.
#'
-#' Beware that code{adapt_admin_express} will perform all possibles combinations
+#' Beware that `adapt_admin_express()` will perform all possibles combinations
#' of archives present in origin and layers available in scheme if those
#' parameters are not specified.
#'
@@ -15,7 +15,7 @@
#'
#' - depending on how many archives and layers are to be treated, a recursive
#' call may be perform to do all desired combinations.
-#' - archive is read with [read_with_scheme()], which may imply that it is
+#' - archive is read with `read_with_scheme()`, which may imply that it is
#' uncompressed, then read (usually as a shp or a gpkg file), reprojected if
#' asked, and finally adapted.
#' - the output is saved as rds in given destination withe[save_archive()]. The
diff --git a/R/adapt_geo_sirene.R b/R/adapt_geo_sirene.R
new file mode 100644
index 0000000000000000000000000000000000000000..4cbb8f849d967ae37bdbfa3c27e12940d88d9f01
--- /dev/null
+++ b/R/adapt_geo_sirene.R
@@ -0,0 +1,318 @@
+#' @title Adapt geolocalized Sirene data
+#'
+#' @description
+#' `adapt_geo_sirene()` adapt geolocalized Sirene database to a common format.
+#'
+#' @details
+#' The following treatments are performed:
+#' - Only some fileds are selected, field names (colnames) are consistently set.
+#' - NA values are consistently set.
+#' - Type of fields are consistently set, some checks are performed on transformations.
+#' - Data set is cut and saved by departments
+#' - Only observations with spatial coordinates are kept.
+#' - Exposition of observations (belonging or not to eaip) is added.
+#'
+#' @param origin character, path to the directory where archive are stored.
+#' @param destination character, path to the directory where results should be
+#' saved.
+#' @param archive character, vector of archive to be adpated.
+#' @param scheme data.frame, how archive variables should be treated.
+#' @param projection numeric, 4 digits projection to use.
+#' @param active logical, should only active activities be kept.
+#' @param path_eaip character, path where eaip archives should be find.
+#' @param path_admin character, path where administrative archives should be
+#' find.
+#' @param journal logical, should a journal file be saved.
+#' @param map logical, should a map be plotted (for check purpose).
+#' @param verbose logical, should the function give some sumup informations.
+#' @param retrieve logical, should the result be returned.
+#'
+#' @return if retrieve = TRUE, data.frame of adapated data stored in archive.
+#'
+#' @export
+#'
+#' @encoding UTF-8
+#'
+#' @examples
+#'
+#' \dontrun{
+#' dest = tempdir()
+#' download_geo_sirene(dest, "data.gouv", scope = "department", version = "34")
+#' archive = "geo_siret_34.csv.gz"
+#' origin = file.path(dest, "version_2019", "2024-03")
+#' dest = file.path(dest, "adapted")
+#' result = adapt_geo_sirene(origin, dest, verbose = TRUE, retrieve = TRUE)
+#' }
+
+adapt_geo_sirene = function(
+ origin,
+ destination,
+ archive,
+ scheme = floodam.data::scheme_sirene_2019,
+ projection = 4326,
+ active = TRUE,
+ path_eaip = NULL,
+ path_admin = NULL,
+ journal = TRUE,
+ map = !is.null(path_eaip),
+ verbose = TRUE,
+ retrieve = FALSE
+) {
+ ### Recursive call if archive is missing
+ if (missing(archive)) {archive = list.files(origin, pattern = ".csv.gz$")}
+ if (length(archive) > 1) {
+ return(
+ lapply(
+ archive,
+ adapt_geo_sirene,
+ origin = origin,
+ destination = destination,
+ scheme = scheme,
+ projection = projection,
+ active = active,
+ path_eaip = path_eaip,
+ path_admin = path_admin,
+ journal = journal,
+ map = map,
+ verbose = verbose,
+ retrieve = retrieve
+ )
+ )
+ }
+ if (length(archive) == 0) {
+ return(NULL)
+ }
+
+ archive = file.path(origin, archive)
+ message(sprintf("'geo_sirene' adaptation from '%s'...", basename(archive)))
+ old_s2 = suppressMessages(sf::sf_use_s2(FALSE))
+ on.exit(suppressMessages(sf::sf_use_s2(old_s2)))
+
+ # Load admin_dep if found
+ if (!is.null(path_admin)) {
+ admin_dep = file_version(
+ path_admin,
+ "admin-express-cog_department.*rds"
+ )
+ if (length(admin_dep) == 1) {
+ admin_dep = readRDS(admin_dep)
+ } else {
+ admin_dep = NULL
+ }
+ } else {
+ admin_dep = NULL
+ }
+
+ # Analyse archive and make elementary tests
+ info = suppressWarnings(analyse_archive(archive, "geo-sirene"))
+ if (!info["data"] %in% "geo-siret") {
+ cat("\t- Not 'geo-siret' data. Nothing is done.")
+ return(NULL)
+ }
+ if (info["version"] != "2019") {
+ cat(
+ sprintf(
+ "\t- version '%s' is not implemented. Nothing is done.",
+ info["version"]
+ )
+ )
+ return(NULL)
+ }
+
+ # Prepare outputs and open journal
+ geo_siret = format_archive(info, extension = "rds")
+ dir.create(destination, showWarnings = FALSE, recursive = TRUE)
+ if (isTRUE(journal)) {
+ journal = file.path(destination, gsub(".rds", ".log", geo_siret))
+ init_log_info(
+ journal,
+ main = sprintf("%s in %s", basename(archive), origin),
+ treatment = "adapt_geo_sirene",
+ )
+ } else {
+ journal = FALSE
+ }
+
+ # Reading archive with scheme information
+ result = add_log_info(
+ archive,
+ read_with_scheme,
+ info = list(
+ "short" = "read 'geo-siret'",
+ "long" = "Reading original 'geo-siret' archive and applying scheme"
+ ),
+ journal = journal,
+ verbose = verbose,
+ verification = expression(info_dim(result)),
+ scheme = scheme,
+ projection = projection
+ )
+
+ # NA treament → TO BE KEPT ??? if yes need adaptation.
+ # for (i in 1:nrow(na_value)) {
+ # var = na_value[i, "name"]
+ # result[[var]] = treat_na(result[[var]], na_value[i, "na.value"])
+ # }
+
+ # Select only active activities if asked.
+ if (isTRUE(active)) {
+ result = add_log_info(
+ result,
+ fun = subset_with_message,
+ info = list(
+ "short" = "select active activities",
+ "long" = "Selecting active activities"
+ ),
+ journal = journal,
+ verbose = verbose,
+ verification = expression(info_dim(result)),
+ rows = result[["state"]] == "A"
+ )
+ }
+
+ # Split result by department.
+ result = add_log_info(
+ result,
+ fun = split_dep,
+ info = list(
+ "short" = "split 'geo-siret' by department",
+ "long" = "Splitting result by department"
+ ),
+ journal = journal,
+ verbose = verbose,
+ verification = expression(length(result)),
+ admin_dep = admin_dep
+ )
+
+ # Select only scope if any, otherwise select only valid department
+ if (info["scope"] %in% format_scope(floodam.data::department[["code"]])) {
+ result = result[info["scope"]]
+ } else {
+ selection = names(result) %in%
+ format_scope(floodam.data::department[["code"]])
+ result = result[selection]
+ }
+
+ # At this stage result must be split by valid department
+ for (dep in names(result)) {
+ info["scope"] = dep
+ geo_siret = format_archive(info, extension = "rds")
+
+ # Adding 'eaip' information
+ if (!is.null(path_eaip)) {
+ result[[dep]] = add_log_info(
+ result[[dep]],
+ add_eaip,
+ info = list(
+ "short" = sprintf("add eaip [%s]", info["scope"]),
+ "long" = sprintf(
+ "Addition of 'eaip' information [%s]",
+ info["scope"]
+ )
+ ),
+ journal = journal,
+ verbose = verbose,
+ verification = expression(sum(result[['eaip']])),
+ path_eaip = path_eaip,
+ department = info["scope"]
+ )
+ }
+
+ # Saving data
+ add_log_info(
+ result[[dep]],
+ saveRDS,
+ info = list(
+ "short" = sprintf(
+ "save [%s] to %s",
+ info["scope"],
+ file.path(destination, geo_siret)
+ ),
+ "long" = sprintf("Saving geo-siret [%s]", info["scope"])
+ ),
+ journal = journal,
+ verbose = verbose,
+ verification = expression(object.size(x)),
+ file = file.path(destination, geo_siret)
+ )
+
+ # Plot map
+ if (map == TRUE) {
+ map_log = gsub(".rds", ".png", geo_siret)
+ add_log_info(
+ result[[dep]],
+ map_log_geo_siret,
+ info = list(
+ "short" = sprintf(
+ "plot check map [%s] to %s",
+ info["scope"],
+ file.path(destination, map_log)
+ ),
+ "long" = sprintf(
+ "Plotting map (check purpose) [%s]",
+ info["scope"]
+ )
+ ),
+ journal = journal,
+ verbose = verbose,
+ dep = info["scope"],
+ admin_dep = admin_dep,
+ path_map = file.path(destination, map_log)
+ )
+ }
+ }
+
+ ### Retrieve result
+ if (retrieve == TRUE) {
+ if (length(result) == 1) return(invisible(result[[1]]))
+ return(invisible(result))
+ }
+}
+
+map_log_geo_siret = function(x, path_map, admin_dep = NULL, dep) {
+ grDevices::png(path_map, width = 1000, height = 1000)
+ on.exit(grDevices::dev.off())
+
+ if (is.null(x[["eaip"]])) {
+ col = "gray"
+ } else {
+ col = ifelse(x[["eaip"]], "red", "black")
+ col[is.na(col)] = "gray"
+ }
+
+ plot(
+ x[0],
+ type = "p",
+ pch = 15,
+ cex = .05,
+ col = col,
+ border = col,
+ cex.axis = 2,
+ axes = TRUE,
+ xaxt = "n",
+ yaxt = "n",
+ reset = FALSE
+ )
+
+ if (!is.null(admin_dep)) {
+ col = ifelse(
+ admin_dep[["department"]] == format_scope(dep, "insee"),
+ scales::alpha("yellow", .05), scales::alpha("blue", .05)
+ )
+ plot(admin_dep[0], col = col, border = "black", add = TRUE)
+ }
+ graphics::axis(2, at = pretty(sf::st_bbox(x)[c(2, 4)], 5), cex.axis = 2)
+ graphics::axis(4, at = pretty(sf::st_bbox(x)[c(2, 4)], 5), cex.axis = 2)
+ graphics::axis(1, at = pretty(sf::st_bbox(x)[c(1, 3)], 5), cex.axis = 2)
+ graphics::axis(3, at = pretty(sf::st_bbox(x)[c(1, 3)], 5), cex.axis = 2)
+ graphics::grid()
+
+ graphics::legend(
+ x = "bottomright",
+ inset = 1/100,
+ legend = c("within eaip", "outside eaip"),
+ fill = c("red", "black"),
+ cex = 1
+ )
+ return(invisible(NULL))
+}
\ No newline at end of file
diff --git a/R/add_journal.R b/R/add_journal.R
index 9c08c9606824de7897c28f2e50dc6a4271f36294..8f52149c9096ab9e5a50d92c308ca5c97872242d 100644
--- a/R/add_journal.R
+++ b/R/add_journal.R
@@ -17,10 +17,10 @@
#'
#' If the parameter 'status' is not missing, `add_journal()` try to find
#' to which 'task' this is relevant. This can be done by giving explictly the
-#' 'id', or by ginving the 'task'. If nothing is given, it is supposed that it
+#' 'id', or by giving the 'task'. If nothing is given, it is supposed that it
#' corresponds with the the last task with missing 'status'. For found 'task',
#' it sets 'status' to given 'status', 'end' to current time. 'elapsed' to the
-#' formatted difftime between 'end' and 'start' with \code{floodam.data::fmt}.
+#' formatted difftime between 'end' and 'start' with `floodam.data::fmt()`.
#'
#' If verbose == TRUE, a message is sent. If 'task' is given, a new line is
#' sent, but not ended by 'EOL'. When 'status' is given, message depend on what
@@ -28,7 +28,7 @@
#' current task, it is completed with status and elapsed time. If not, a new
#' line is sent with the whole information (start, task, status, elapsed).
#' 'degree' is used to have some tabular formatting. The message sent is
-#' formatted by \code{floodam.date:::format_journal}.
+#' formatted by `floodam.date:::format_journal()`.
#'
#' @param journal data.frame, journal to be amended. May be missing (see
#' details).
@@ -46,7 +46,6 @@
#' @export
#'
#' @encoding UTF-8
-#' @author Frédéric Grelot
#'
#' @examples
#'
@@ -192,7 +191,7 @@ format_journal = function(journal) {
if (is.na(journal[i, "status"])) {
msg = sprintf(
"%s: [%s] %s%s...",
- journal[i, "start"],
+ format(journal[i, "start"]),
id,
tab,
journal[i, "task"]
@@ -200,7 +199,7 @@ format_journal = function(journal) {
} else {
msg = sprintf(
"%s: [%s] %s%s... %s [%s]",
- journal[i, "start"],
+ format(journal[i, "start"]),
id,
tab,
journal[i, "task"],
diff --git a/R/add_log_info.R b/R/add_log_info.R
index 16e15af8c384d8b935ad5e10e7d7fb5fc03da0f6..3b5a0f5da6063d5985ae098d99e9df944f369722 100644
--- a/R/add_log_info.R
+++ b/R/add_log_info.R
@@ -1,18 +1,35 @@
#' @title Apply a step to data analysis
#'
#' @description
-#' This function allows to embed a analysis made by a function, so that log
-#' information can be saved in a consistent way, messages can be sent depending
-#' on the parameter verbose.
-#'
+#' `add_log_info()` encapsulates an analysis performed by another function, to
+#' feed a consistently saved log. Messages can also be returned directly.
+#'
+#' @details
+#' `add_log_info()` is designed to feed a log step by step during a
+#' multi-stage analysis:
+#' - Information on stage names is entered in the `info` parameter, in both
+#' short (for the log) and long (for on-the-fly messages) versions.
+#' -The level of analysis is controlled by the `level` parameter, which
+#' influences the number of tabs in messages sent or saved.
+#'
+#' Messages generated include step names and elapsed time for analysis. These
+#' messages can be completed in two ways:
+#' - An expression can be sent via the `verification` parameter, which must be
+#' kept simple and act either on input data (x) or on results (result).
+#' - messages returned by the `fun` function are captured and minimally
+#' formatted by adding tabs according to the level value.
+#'
+#' Captured messages are added to the log file, while those generated by
+#' `verification` are added to a dedicated csv file.
+#'
+#' WARNING: because of partial match used in R for arguments, some errors may
+#' occur when add_log_info is used without naming explicitly arguments.
+#'
#' @param x data to be adapted.
#' @param fun function, the analysis that may performed on x.
#' @param info list, gives the name of the step both in 'short' and 'long'
#' terms.
-#' @param journal either FALSE, if not must be a character of length one, and
-#' will be interpreted at the log file where to save any log information. Its
-#' format should be in '*.log' in order to create also a '*-log.csv' log file
-#' that will store information on time and any given verification in csv format.
+#' @param journal character or FALSE. See details.
#' @param verbose logical, should the some messages be sent in real time.
#' @param verification expression, a simple treatment that will be added to
#' *log.csv, may be missing.
@@ -25,14 +42,49 @@
#' @export
#'
#' @encoding UTF-8
-#' @author Frédéric Grelot
+#'
+#' @examples
+#' journal = file.path(tempdir(), "journal.log")
+#' info = list("short" = "Mean by Species", "long" = "Mean by Species")
+#' result = add_log_info(
+#' iris[4],
+#' aggregate,
+#' info,
+#' journal,
+#' by = iris["Species"],
+#' FUN = mean,
+#' verification = expression(ncol(result))
+#' )
+#' aggregate_special = function(x, ...) {
+#' selection = sapply(x, is.numeric) | sapply(x, is.logical)
+#' if (sum(!selection) != 0) {
+#' message(
+#' sprintf(
+#' "- %s colum(s) are(is) neither numeric nor logical (%s). ",
+#' sum(!selection),
+#' paste0(names(x)[!selection], "|")
+#' ),
+#' "They are(It is) dropped."
+#' )
+#' }
+#' aggregate(x[selection], ...)
+#' }
+#' result = add_log_info(
+#' iris,
+#' aggregate_special,
+#' info,
+#' journal,
+#' by = iris["Species"],
+#' FUN = mean,
+#' verification = expression(ncol(result))
+#' )
add_log_info = function(
x,
fun,
info,
journal,
- verbose,
+ verbose = TRUE,
verification,
level = 1,
...
@@ -41,14 +93,16 @@ add_log_info = function(
if (is.na(level)) level = 1
level = paste(rep("\t", level), collapse = "")
- if (verbose == TRUE) cat(sprintf("%s- %s... ", level, info[["long"]]))
+ if (isTRUE(verbose)) {
+ message(sprintf("%s- %s... ", level, info[["long"]]), appendLF = FALSE)
+ }
start = Sys.time()
-
- result = fun(x, ...)
-
+ msg_add = utils::capture.output(result <- fun(x, ...), type = "message")
+ msg_add = grep("^- ", msg_add, value = TRUE)
+
if (
- journal != FALSE &&
+ !isFALSE(journal) &&
! missing(verification) &&
methods::is(verification, "expression")
) {
@@ -64,9 +118,12 @@ add_log_info = function(
duration = sprintf("(%s %s)", round(elapsed, 2), attr(elapsed, "units"))
time = round(as.numeric(elapsed, units = "secs"), 3)
- if (journal != FALSE) {
+ if (!isFALSE(journal)) {
msg = sprintf("%s- %s: done %s.", level, info[["short"]], duration)
write(msg, journal, append = TRUE)
+ if (length(msg_add) > 0) {
+ write(paste0(level, msg_add), journal, append = TRUE)
+ }
utils::write.table(
data.frame(
@@ -84,7 +141,12 @@ add_log_info = function(
)
}
- if (verbose == TRUE) cat(sprintf("done %s\n", duration))
+ if (isTRUE(verbose)) {
+ message(sprintf("done %s", duration))
+ if (length(msg_add) > 0) {
+ message(paste0("\t", level, msg_add, collapse = "\n"))
+ }
+ }
return(result)
}
@@ -126,12 +188,8 @@ init_log_info = function(
}
info_sf = function() {
- info = sf::sf_extSoftVersion()
- info = paste(
- c(names(info), "s2"),
- c(info, sf::sf_use_s2()),
- sep = ":", collapse = ", "
- )
+ info = c(sf::sf_extSoftVersion(), "s2" = sf::sf_use_s2())
+ info = paste(names(info), info, sep = ":", collapse = ", ")
sprintf("sf (%s): %s", utils::packageVersion("sf"), info)
}
diff --git a/R/analyse_archive.R b/R/analyse_archive.R
index 3505135d5868820d9cf35c50d3cfb03f485f000f..82234dc716c1b278eac1c8f682a6eb2a1615fd75 100644
--- a/R/analyse_archive.R
+++ b/R/analyse_archive.R
@@ -1,13 +1,20 @@
-#' @title Analyse names of archive to get useful infomations.
+#' @title Get useful infomations from archive path
#'
#' @description
-#' The function is set for IGN's names of archive, that should normally be
-#' "well" structured with this scheme :
-#' data-type_version_precision_format_projection_scope_date.ext. Sometimes a
-#' less frequent format is
-#' data-name_version_precision_format_projection_scope_proj_date.ext. In the
-#' latter case, "proj" is given in another format than "projection", but also in
-#' a documented way.
+#' `analyse_archive()` analyses paths of archives to get useful infomations. It
+#' can deal with IGN's names, `floodam.data`'s names.
+#'
+#' @details
+#'
+#' `analyse_archive()` is set for IGN's names of archive, that should normally
+#' be "well" structured with this scheme :
+#' - data-type_version_precision_format_projection_scope_date.ext.
+#'
+#' Sometimes a less frequent format is:
+#' - data-name_version_precision_format_projection_scope_proj_date.ext.
+#'
+#' In the latter case, "proj" is given in another format than "projection", but
+#' also in a documented way.
#'
#' From this structure, an analysis is done to retrieve, the type of data, the
#' version, the precision (very often it is empty), the format used (something
@@ -19,17 +26,17 @@
#'
#' This is also done when the format is the less frequent case, because in this
#' case, the projection is not given.
+#'
+#' `analyse_archive()` is also set for `floodam-data`'s names.
#'
#' @param x character vector
-#' @param origin character, to choose the format. Only "ign" is available at the
-#' moment.
-#'
+#' @param origin character, to choose the format. See details.
+#'
#' @return either a vector or a matrix depending on the length of x.
#'
#' @export
#'
#' @encoding UTF-8
-#' @author Frédéric Grelot
#'
#' @examples
#' ign = c(
@@ -55,13 +62,29 @@
#' "ADMIN-EXPRESS-COG_3-1__SHP_RGAF09UTM20_GLP_2022-04-15.7z"
#' )
#' analyse_archive(floodam, "floodam.data")
+#'
+#' geo_sirene = c(
+#' "2024-01/geo_siret_34.csv.gz",
+#' "2024-01/StockEtablissement_utf8_geo.csv.gz",
+#' "2024-01/StockEtablissementActif_utf8_geo.csv.gz",
+#' "2024-01/StockEtablissementFerme_utf8_geo.csv.gz",
+#' "2024-01/geo_sirene.csv.gz",
+#' "2024-01/etablissements_actifs.csv.gz",
+#' "2024-01/etablissements_fermes.csv.gz",
+#' "bad-date/geo_siret_34.csv.gz"
+#' )
+#' analyse_archive(geo_sirene, "geo-sirene")
-analyse_archive = function(x, origin = c("ign", "floodam.data")) {
+analyse_archive = function(
+ x,
+ origin = c("ign", "floodam.data", "geo-sirene")
+) {
origin = match.arg(origin)
if (length(x) > 1) return(t(sapply(x, analyse_archive, origin = origin)))
date_pattern = "[0-9]{4}-[0-9]{2}-[0-9]{2}"
+ month_pattern = "^[0-9]{4}-[0-9]{2}$"
if (origin == "ign") {
scope_admissible = c(
@@ -223,6 +246,67 @@ analyse_archive = function(x, origin = c("ign", "floodam.data")) {
}
}
+ if (origin == "geo-sirene") {
+ result = stats::setNames(
+ rep(NA_character_, 7),
+ c(
+ "data",
+ "precision",
+ "version",
+ "scope",
+ "vintage",
+ "extension",
+ "name"
+ )
+ )
+
+ result["extension"] = basename_ext(x)
+ result["name"] = basename_core(x)
+ result["vintage"] = basename(dirname(x))
+ if (!grepl(month_pattern, result["vintage"])) result["vintage"] = NA
+
+ if (result["name"] == "geo_sirene") {
+ result["data"] = "geo-siret"
+ result["version"] = "2017"
+ result["scope"] = "france"
+ }
+ if (result["name"] == "etablissements_actifs") {
+ result["data"] = "geo-siret"
+ result["precision"] = "active"
+ result["version"] = "2017"
+ result["scope"] = "france"
+ }
+ if (result["name"] == "etablissements_fermes") {
+ result["data"] = "geo-siret"
+ result["precision"] = "closed"
+ result["version"] = "2017"
+ result["scope"] = "france"
+ }
+ if (result["name"] == "StockEtablissementActif_utf8_geo") {
+ result["data"] = "geo-siret"
+ result["precision"] = "active"
+ result["version"] = "2019"
+ result["scope"] = "france"
+ }
+ if (result["name"] == "StockEtablissementFerme_utf8_geo") {
+ result["data"] = "geo-siret"
+ result["precision"] = "closed"
+ result["version"] = "2019"
+ result["scope"] = "france"
+ }
+ if (result["name"] == "StockEtablissement_utf8_geo") {
+ result["data"] = "geo-siret"
+ result["version"] = "2019"
+ result["scope"] = "france"
+ }
+ if (grepl("geo_siret", result["name"])) {
+ result["data"] = "geo-siret"
+ result["version"] = "2019"
+ temp = unlist(strsplit(result["name"], "_"))
+ result["scope"] = format_scope(temp[length(temp)])
+ }
+ }
+
# Replacing empty string by NA
result[result == ""] = NA
diff --git a/R/apply_scheme.R b/R/apply_scheme.R
index 5e224511faf6534e8ad3b5830c99cacf5de30f05..1c73553c1a0f399e5a02bf309e201fc00ed0745a 100644
--- a/R/apply_scheme.R
+++ b/R/apply_scheme.R
@@ -2,8 +2,8 @@
#'
#' @description
#' The function applies a scheme to a data.frame or a sf object, which consists
-#' in keeping only variable that should be kept, renaming variables, and setting
-#' the type of variable.
+#' in keeping only variables that should be kept, renaming variables, and
+#' setting the type of variables.
#'
#' @param x data.frame or sf, data to be adapted.
#' @param scheme data.frame, scheme to be applied.
@@ -25,7 +25,6 @@
#' @export
#'
#' @encoding UTF-8
-#' @author Frédéric Grelot
apply_scheme = function(x, scheme, selection = NULL, name_origin = NULL) {
if (!is.null(name_origin)) {
@@ -62,7 +61,7 @@ apply_scheme = function(x, scheme, selection = NULL, name_origin = NULL) {
selection = scheme[["name"]][scheme[["type"]] == "factor"]
x[selection] = lapply(x[selection], as.factor)
- selection = scheme[["name"]][scheme[["type"]] == "date"]
+ selection = scheme[["name"]][scheme[["type"]] == "Date"]
x[selection] = lapply(x[selection], as.Date)
selection = scheme[["name"]][scheme[["type"]] == "numeric"]
@@ -71,6 +70,9 @@ apply_scheme = function(x, scheme, selection = NULL, name_origin = NULL) {
selection = scheme[["name"]][scheme[["type"]] == "integer"]
x[selection] = lapply(x[selection], as.integer)
+ selection = scheme[["name"]][scheme[["type"]] == "logical"]
+ x[selection] = lapply(x[selection], to_logical)
+
if (!is.null(geometry)) {
x = sf::st_set_geometry(x, geometry)
}
diff --git a/R/basename_extended.R b/R/basename_extended.R
index 153ca230901cf6e157c39651ebbd2a17779691a3..6020011c3a099c245f79eb799c6235d07a45868f 100644
--- a/R/basename_extended.R
+++ b/R/basename_extended.R
@@ -3,22 +3,20 @@
#'
#' @description
#' Utilities for getting name of files and extension in another whay than of
-#' [tools::file_ext()] and others corresponding functions.
+#' `tools::file_ext()`` and others corresponding functions.
+#'
+#' @details
+#' `basename_core()`` differs from `tools::file_path_sans_ext()` in this:
+#' - `basename()` is first applied
+#' - "compounded" extensions are removed. See examples.
#'
#' @param x character vector, file paths
#'
#' @return character vector of processed files.
#'
-#' @details
-#'
-#' \code{basename_core()} differs from [tools::file_path_sans_ext()] in this:
-#' - [basename()] is first applied
-#' - "compounded" extensions are removed. See examples.
-#'
#' @export
#'
#' @encoding UTF-8
-#' @author Frédéric Grelot
#'
#' @examples
#'
@@ -29,7 +27,6 @@
#' basename_core("toto.7z.001")
#' basename_core("path/toto.csv")
#' basename_core("path/toto.csv.gz")
-#'
basename_core = function(x) {
x = basename(x)
@@ -40,9 +37,8 @@ basename_core = function(x) {
#' @rdname basename_extended
#'
#' @details
-#'
-#' \code{basename_ext()} differs from [tools::file_path_sans_ext()] in this:
-#' - [basename()] is first applied
+#' `basename_ext()` differs from `tools::file_path_sans_ext()` in this:
+#' - `basename()` is first applied
#' - "compounded" extensions are extracted. See examples.
#'
#' @export
diff --git a/R/data.R b/R/data.R
index a0d1ba2f8ab9e1f3b7417c99f4d1b324db2229ce..55f9e0ad119ca3c62b2c306f11491b72af7b023f 100644
--- a/R/data.R
+++ b/R/data.R
@@ -361,15 +361,15 @@
#' @format A data frame with 57 rows and 10 variables:
#' \describe{
#' \item{name}{character, name of variables used in floodam.data.}
-#' \item{name.origin}{character, name of variables as defined in original
+#' \item{name_origin}{character, name of variables as defined in original
#' data.}
#' \item{order}{integer, order of the variables in original data.}
#' \item{keep}{logical, defined if floodam.data will keep this variable.}
#' \item{type}{character, type that will be used within floodam.data.}
-#' \item{label.french}{character, variables description in French.}
+#' \item{label_french}{character, variables description in French.}
#' \item{source}{character, source of the variables.}
-#' \item{length.source}{integer, length of variables in source.}
-#' \item{type.source}{character, type of variables in source.}
+#' \item{length_source}{integer, length of variables in source.}
+#' \item{type_source}{character, type of variables in source.}
#' \item{comment}{character, some comments on choice made.}
#' }
"scheme_sirene_2019"
@@ -382,7 +382,7 @@
#' @format A data frame with 3 rows and 2 variables:
#' \describe{
#' \item{name}{character, name of variable as used in floodam.data.}
-#' \item{na.value}{character, value that is to be considered as na.value.}
+#' \item{na_value}{character, value that is to be considered as na.value.}
#' }
"scheme_sirene_na"
diff --git a/R/download.geo_sirene.R b/R/download.geo_sirene.R
deleted file mode 100644
index 8d85ab58769f3be58b8183d91ff64a3bbc38cbd8..0000000000000000000000000000000000000000
--- a/R/download.geo_sirene.R
+++ /dev/null
@@ -1,85 +0,0 @@
-#' Download Géo SIRENE
-#'
-#' Function used to downlaod Geolocalized SIRENE data-base.
-#'
-#' @param destination character, the address where dara are stocked.
-#' @param origin character, either a keyword or the address from where data are downloaded. Best to keep it
-#' at default value. See details.
-#' @param name character, vector of acceptable names fo archive to be downloaded.
-#' @param extension character, vector of acceptable types of archive to be downloaded.
-#' @param version string, version of ADMIN EXPRESS to be downloaded.
-#' @param date character, date of the archive to be downloaded.
-#' @param month character, vector of month to be downloaded
-#' @param version_insee string, INSEE version to be downloaded. Only used with \code{origin = "cquest"}.
-#' @param verbose logical, should the function send some messages while running.
-#'
-#' @return nothing
-#'
-#' @section Details:
-#'
-#' If \code{origin == "cquest"}, then all necessary variables are filled with those values:
-#' \itemize{
-#' \item \bold{origin} is changed to \url{https://data.cquest.org/geo_sirene}. This url is adapted depending
-#' on version_insee.
-#' \item \bold{version_insee} If value is "v2019", then the version 2019 is dowloaded from
-#' \url{https://data.cquest.org/geo_sirene}.
-#' \item \bold{name} If version is not set to null, then default value is changed to "StockEtablissement_utf8",
-#' which should be the most complete version at France level.
-#' \item \bold{extension} default value is changed to "csv.gz".
-#' \item \bold{month} is used to set something equivalent to date, but directly in origin.
-#' \item \bold{date} is set to null, because conflict may occur with month.
-#' }
-#'
-#' If not, everything shall be filled so that `download_archive()` can make a successful download.
-#'
-#' @export
-#'
-#' @examples
-#' \dontrun{
-#' origin = "https://data.cquest.org/geo_sirene"
-#' destination = tempdir()
-#' month = c("2018-11", "2019-05", "2020-03")
-#' download.geo_sirene(origin, destination, month = month)
-#' unlink(destination)
-#' }
-
-download.geo_sirene = function(
- destination,
- origin = "cquest",
- name = NULL,
- extension = NULL,
- version = NULL,
- date = NULL,
- month = NULL,
- version_insee = "v2019",
- verbose = TRUE) {
- if (origin == "cquest") {
- origin = "https://data.cquest.org/geo_sirene"
- if (version_insee == "v2019") {
- origin = file.path(origin, version_insee)
- version_insee = "version_2019"
- } else {
- version_insee = "version_2017"
- }
- if (is.null(month)) {
- x = read_url(origin)
- month = max(unlist(regmatches(x, gregexpr("(?<=href=([\\\"']))\\d{4}-\\d{2}(?=\\/\\1)", x, perl = TRUE))))
- }
- month_origin = month
- if (version_insee == "version_2019") month_origin = gsub("(2018|2019)", "\\1/\\1", month, perl = TRUE)
- origin = file.path(origin, month_origin)
- destination = file.path(destination, version_insee, month)
- if (is.null(extension)) extension = "csv.gz"
- if (is.null(version) && is.null(name)) name = "StockEtablissement_utf8"
- date = NULL
- }
-
- to_do = data.frame(
- origin = origin,
- destination = destination,
- short = "download.geo_sirene",
- stringsAsFactors = FALSE
- )
-
- download_archive(to_do, extension = extension, name = name, date = date, version = version, verbose = verbose)
-}
\ No newline at end of file
diff --git a/R/download_archive.R b/R/download_archive.R
index a65a482567bac3610651370351fe7e473c141db0..5cb6df8f89b824f18f9dc28da5c7a69c1e71d1d2 100644
--- a/R/download_archive.R
+++ b/R/download_archive.R
@@ -1,14 +1,26 @@
-#' Download distant archives
+#' @title Download distant archives
#'
-#' Core function used to downlaod archives
+#' @description
+#' `download_archive()` is the core function used to downlaod archives from
+#' other specific functions.
+#'
+#' @details
+#' `download_archive()` is used by other more specific functions. It takes as
+#' input a `to_do` `data.frame` giving correspondance between origin urls to
+#' local destinations. `to_do` is expected to contain those fields:
+#'
+#' * `origin`: the origin urls where to find archives.
+#' * `destination`: the local places where to save archives.
+#' * `short`: the name in short of what type of archives is being
+#' downloaded, used for log information. If missing, it is set to "unknown".
+#' * `local_origin`: the local origin for sites giving relative links, and for
+#' which it is different from `origin`. If missing, `origin` is used.
#'
-#' This function is used by other more specific functions. It takes as input a
-#' to_do data.frame giving correspondance between origin urls to local
-#' destinations. It also to select some types of archives to be downloaded. On
-#' the good construction of the to_do data.frame depends the success of the
-#' downloads!
+#' For each line of `to_do`, all archives that matches condition given by other
+#' parameters (`extension`, `name`, `date`, `version`) are downloaded.
#'
-#' @param to_do data.frame. Two columns of character are expected.
+#' @param to_do data.frame. Four columns of character are expected, thow of
+#' which being mandatory. See details.
#' @param extension character, vector of acceptable types of archive to be
#' downloaded.
#' @param name character, vector of acceptable names fo archive to be
@@ -17,13 +29,11 @@
#' filter.
#' @param version character, something like a version that should be used as a
#' filter.
-#' @param html character, indicates if the page is "simple" or is coming from
-#' "data.gouv". This has implications on how to look for links.
-#' @param verbose logical, should the function send somme messages while
+#' @param verbose logical, should the function send some messages while
#' running.
#'
-#' @return nothing
-#'
+#' @return An invisible `data.frame` of log.
+#'
#' @export
#'
#' @examples
@@ -32,16 +42,14 @@
#' to_do_cquest = data.frame(
#' origin = "https://data.cquest.org/registre_parcellaire_graphique/2018",
#' destination = destination,
-#' short = "rpg_cquest",
-#' stringsAsFactors = FALSE
+#' short = "rpg_cquest"
#' )
#' download_archive(to_do_cquest, version = "D976", verbose = TRUE)
#'
#' to_do_ign = data.frame(
#' origin = "https://geoservices.ign.fr/rpg",
#' destination = destination,
-#' short = "rpg_ign",
-#' stringsAsFactors = FALSE
+#' short = "rpg_ign"
#' )
#' download_archive(to_do_ign, version = "D976", date = "2020", verbose = TRUE)
#' download_archive(to_do_ign, version = "D976", verbose = TRUE)
@@ -56,7 +64,6 @@ download_archive = function(
name = NULL,
date = NULL,
version = NULL,
- html = "simple",
verbose = FALSE
) {
result = list()
@@ -79,7 +86,7 @@ download_archive = function(
name = name,
date = date,
version = version,
- html = html
+ local_origin = to_do[i, "local_origin"]
)
),
silent = TRUE
@@ -157,11 +164,16 @@ download_archive = function(
verbose = verbose
)
result[[origin]] = journal
+ short = if (is.null(to_do[i, "short"])) {
+ "unknown"
+ } else {
+ gsub("/", "_", to_do[i, "short"])
+ }
write_journal(
journal,
file.path(
to_do[i, "destination"],
- sprintf("%s.%s", gsub("/", "_", to_do[i, "short"]), "log")
+ sprintf("%s.%s", short , "log")
)
)
}
diff --git a/R/download_ban.R b/R/download_ban.R
index 4a25a7b128270ebaf4247a042f7bf6a10545d5d9..1c909e1977091b19e074eca5ecfb470312335efe 100644
--- a/R/download_ban.R
+++ b/R/download_ban.R
@@ -1,89 +1,87 @@
-#' Download BAN
+#' @title Download BAN
#'
-#' Function used to downlaod BAN
+#' @description
+#' `downlaod_ban()` is used has a wrapper of `download_archive()` to download
+#' easily BAN database.
+#'
+#' @details
+#'
+#' If `repository` is set to "data.gouv", then all necessary variables are
+#' filled with those values:
+#'
+#' * **origin** is set to "https://adresse.data.gouv.fr/data/ban/adresses"
+#' * **name** default value is changed to "adresses"
+#' * **extension** default value is changed to "csv.gz"
+#' * **date** default value is used to choose a given directory. If
+#' date is `NULL`, then the most recent version is taken (equivalent to
+#' "latest").
+#' * **version** must be something within "ban" or "bal". When "ban"
+#' is used the file with one position per address is used. When "bal" is
+#' used, the file with several position per address is used.
+#' * **department** is used. Should be admissible French
+#' departments (a formatting will be attempted with `format_scope()`).
+#' If `NULL`, region may be used. If both are `NULL`, all departments from
+#' `floodam.data::department`` will be used.
+#' * **region** may be used if department is `NULL`. Should be
+#' admissible French regions (a formatting will be attempted with
+#' `format_scope()`). If region is given and department is `NULL`, all
+#' departments from given region will be used.
+#'
+#' If `repository` is set to "other", everything shall be filled so that
+#' `download_archive()` can make a successful download.
#'
#' @param destination character, the address where data are stocked.
-#' @param origin character, either a keyword or the address from where data are downloaded. See details.
-#' @param name character, vector of acceptable names for archive to be downloaded.
-#' @param extension character, vector of acceptable types of archive to be downloaded.
+#' @param repository character, keyword or the repository from where data are
+#' downloaded. Best to use given options. See details.
+#' @param origin character, url address from where data are downloaded. It is
+#' set when repository is something else than "other".
+#' @param extension character, vector of acceptable types of archive to be
+#' downloaded.
#' @param date character, date of the archive to be downloaded.
#' @param version string, version of BAN to be downloaded. See details.
-#' @param department integer, or converted to integer. Departments that should be considered. See details.
-#' @param region integer, or converted to integer. Regions that should be considered. See details.
+#' @param department integer, or converted to integer. Departments that should
+#' be considered. See details.
+#' @param region integer, or converted to integer. Regions that should be
+#' considered. See details.
#' @param verbose logical, should the function send some messages while running.
#'
-#' @return nothing
-#'
-#' @section Details:
-#'
-#' If \code{origin == "data.gouv"}, then all necessary variables are filled with
-#' those values:
-#' \itemize{
-#' \item \bold{origin} is changed to
-#' "https://adresse.data.gouv.fr/data/ban/adresses"
-#' \item \bold{name} default value is changed to "adresses"
-#' \item \bold{extension} default value is changed to "csv.gz"
-#' \item \bold{date} default value is used to choose a given directory. If
-#' date is null, then the most recent version is taken (equivalent to
-#' "latest").
-#' \item \bold{version} must be something within "ban" or "bal". When "ban"
-#' is used the file with one position per address is used. When "bal" is
-#' used, the file with several position per address is used.
-#' \item \bold{department} is used. Should be admissible French
-#' departments (a formatting will be attempted with `format_scope()`).
-#' If NULL, region may be used. If both are NULL, all departments from
-#' floodam.data::department will be used.
-#' \item \bold{region} may be used if department is null. Should be
-#' admissible French regions (a formatting will be attempted with
-#' `format_scope()`). If region is given and department is NULL, all
-#' departments from given region will be used.
-#' }
-#'
-#' If not, everything shall be filled so that `download_archive()` can make
-#' a successful download.
+#' @return An invisible `data.frame` of log.
#'
#' @export
#'
#' @examples
#' \dontrun{
-#' destination = tempdir()
-#' download_ban(destination)
-#' download_ban(destination, department = 34)
-#' download_ban(destination, department = 34, date = "2022-01-01")
-#' download_ban(destination, region = 11, date = "2022-01-01")
-#' download_ban(destination, department = 34, date = "2022-09-20", version = "bal")
+#' dest = tempdir()
+#' download_ban(dest)
+#' download_ban(dest, department = 34)
+#' download_ban(dest, department = 34, date = "2022-01-01")
+#' download_ban(dest, region = 76, date = "2022-01-01")
+#' download_ban(dest, department = 976, date = "2022-09-20", version = "bal")
#'
-#' unlink(destination)
+#' unlink(dest)
#' }
download_ban = function(
destination,
- origin = "data.gouv",
- name = NULL,
+ repository = c("data.gouv", "other"),
+ origin = NULL,
extension = NULL,
date = NULL,
- version = NULL,
+ version = c("ban", "bal"),
department = NULL,
region = NULL,
- verbose = TRUE) {
+ verbose = TRUE
+) {
+ repository = match.arg(repository)
- if (origin == "data.gouv") {
- version = match.arg(version, c("ban", "bal"))
+ if (repository == "data.gouv") {
+ version = match.arg(version)
origin = "https://adresse.data.gouv.fr/data/ban/adresses"
name = if (is.null(name)) "adresses"
extension = if (is.null(extension)) "csv.gz"
date = if (is.null(date)) "latest" else date
- date_admissible = as.Date(
- names(
- get_archive(
- origin,
- name = "[0-9]{4}-[0-9]{2}-[0-9]{2}",
- html = "data.gouv",
- extension = NULL
- )
- )
- )
+ date_admissible = as.Date(get_date_from_html(origin, expected = "day"))
date = if (format(date) == "latest") {
format(max(date_admissible))
} else {
@@ -91,18 +89,19 @@ download_ban = function(
format(date_admissible[selection])
}
- if ("ban" %in% version) {
- origin = file.path(origin, date, "csv")
- destination = file.path(destination, "ban", date)
- }
- if ("bal" %in% version) {
- origin = file.path(origin, date, "csv-bal")
- destination = file.path(destination, "bal", date)
-
- }
+ origin = switch(
+ version,
+ ban = file.path(origin, date, "csv"),
+ bal = file.path(origin, date, "csv-bal")
+ )
+ destination = file.path(destination, version, date)
if (!is.null(department)) {
- version = format_scope(department, type = "insee", scope = "department")
+ version = format_scope(
+ department,
+ type = "insee",
+ scope = "department"
+ )
} else {
if (!is.null(region)) {
region = format_scope(region, type = "insee", scope = "region")
@@ -118,6 +117,7 @@ download_ban = function(
to_do = data.frame(
origin = origin,
destination = destination,
+ local_origin = get_base_url(origin),
short = "download_ban",
stringsAsFactors = FALSE
)
@@ -128,7 +128,6 @@ download_ban = function(
name = name,
date = NULL,
version = version,
- html = "data.gouv",
verbose = verbose
)
}
diff --git a/R/download_geo_sirene.R b/R/download_geo_sirene.R
new file mode 100644
index 0000000000000000000000000000000000000000..93657e9cf79ebd2a81bea6bd9f1bb152398eb748
--- /dev/null
+++ b/R/download_geo_sirene.R
@@ -0,0 +1,162 @@
+#' @title Download geo SIRENE
+#'
+#' @description
+#' `downlaod_geo_sirene()` is used has a wrapper of `download_archive()` to
+#' download easily geolocalized SIRENE database.
+#'
+#' @details
+#'
+#' If `repository` is set to "cquest", then all necessary variables are filled
+#' with those values:
+#'
+#' * **origin** is changed to https://data.cquest.org/geo_sirene. This
+#' url is adapted depending on version_insee. Some extra efforts are necessary
+#' to deal with version_insee and vintage of data.
+#' * **version_insee** can be set either to "2019" (default) or "2017".
+#' #' * **month** is used to set something equivalent to date, and to adapt
+#' `origin`. Some extra efforts is necessary depending on years because of the
+#' structure of the repository (some months are grouped by year, some not, and
+#' this evolves).
+#' * **name** default value is changed to "StockEtablissement_utf8" when
+#' `version_insee` is "2019", "etablissements_actifs" when `version_insee` is
+#' "2017" expect for old vintage for which it is changed to "geo_sirene".
+#' * **extension** default value is changed to "csv.gz".
+#'
+#' If `repository` is set to "data.gouv", then all necessary variables are
+#' filled with those values:
+#'
+#' * **origin** is changed to https://files.data.gouv.fr/geo-sirene.
+#' * **version_insee** is set to "2019".
+#' * **month** is used to set something equivalent to date, and to adapt
+#' `origin`.
+#' * **scope** is used to access to available scopes for download (France,
+#' departments or communes). It is used to adapt `origin`.
+#' * **name** is set depending on `scope`: "StockEtablissementActif_utf8_geo"
+#' for "france", "geo_siret" for "department", `NULL` for "commune".
+#' * **extension** is set depending on `scope`: "csv.gz" for "france" and
+#' "department", "csv" for "commune".
+#'
+#' If `origin` is set to "other", everything shall be filled so that
+#' `download_archive()` can make a successful download.
+#'
+#' @param destination character, the address where dara are stocked.
+#' @param repository character, keyword or the repository from where data are
+#' downloaded. Best to use given options. See details.
+#' @param origin character, url address from where data are downloaded. It is
+#' set when repository is something else than "other".
+#' @param name character, vector of acceptable names fo archive to be
+#' downloaded. See details.
+#' @param extension character, vector of acceptable types of archive to be
+#' downloaded.
+#' @param version string, version of geo_sirene to be downloaded. Useful to set
+#' departments or communes when `repository` is "data.gouv".
+#' @param month character, vector of month to be downloaded.
+#' @param version_insee string, INSEE version to be downloaded. Only used with
+#' `origin` = "cquest". See details.
+#' @param scope string, scope for download when repository is "data.gouv".
+#' See details.
+#' @param verbose logical, should the function send some messages while running.
+#'
+#' @return An invisible `data.frame` of log.
+#'
+#' @export
+#'
+#' @examples
+#' \dontrun{
+#' dest = tempdir()
+#' month = c("2019-01", "2020-01", "2021-01")
+#' download_geo_sirene(dest)
+#' download_geo_sirene(dest, month = month)
+#' download_geo_sirene(dest, version_insee = "2017")
+#' download_geo_sirene(dest, version_insee = "2017", month = "2018-01")
+#'
+#' download_geo_sirene(dest, repository = "data.gouv")
+#' month = c("2020-01", "2021-01", "2022-01", "2023-01", "2024-01")
+#' log_sirene = download_geo_sirene(dest, "data.gouv", month = month)
+#' log_sirene
+#' download_geo_sirene(dest, "data.gouv", scope = "department", version = "34")
+#' download_geo_sirene(dest, "data.gouv", scope = "commune", version = "34170")
+#' unlink(destination)
+#' }
+
+download_geo_sirene = function(
+ destination,
+ repository = c("cquest", "data.gouv", "other"),
+ origin = NULL,
+ name = NULL,
+ extension = NULL,
+ version = NULL,
+ month = NULL,
+ version_insee = c("2019", "2017"),
+ scope = c("france", "department", "commune"),
+ verbose = TRUE
+) {
+ repository = match.arg(repository)
+ scope = match.arg(scope)
+
+ if (repository == "cquest") {
+ version_insee = match.arg(version_insee)
+ origin = "https://data.cquest.org/geo_sirene"
+ origin = file.path(origin, sprintf("v%s", version_insee))
+ version_insee = sprintf("version_%s", version_insee)
+
+ if (is.null(month)) month = max(get_date_from_html(origin))
+ month_origin = month
+
+ # Need to deal with arborescence organized by year (but not for all)
+ if (version_insee == "version_2019") {
+ year = get_date_from_html(origin, expected = "year", last = FALSE)
+ pattern = sprintf("(%s)", paste(year, collapse = "|"))
+ month_origin = gsub(pattern, "\\1/\\1", month, perl = TRUE)
+ }
+
+ origin = file.path(origin, month_origin)
+ destination = file.path(destination, version_insee, month)
+ if (is.null(extension)) extension = "csv.gz"
+ if (is.null(version) && is.null(name)) {
+ if (version_insee == "version_2019") {
+ name = "StockEtablissement_utf8"
+ }
+ if (version_insee == "version_2017" && month >= "2019-04") {
+ name = "etablissements_actifs"
+ }
+ if (version_insee == "version_2017" && month <= "2019-03") {
+ name = "geo_sirene"
+ }
+ }
+ }
+
+ if (repository == "data.gouv") {
+ version_insee = "version_2019"
+ origin = "https://files.data.gouv.fr/geo-sirene"
+ if (is.null(month)) month = max(get_date_from_html(origin))
+ origin = file.path(origin, month)
+ destination = file.path(destination, version_insee, month)
+ extension = "csv.gz"
+ name = "StockEtablissementActif_utf8_geo"
+ if (scope == "department") {
+ origin = file.path(origin, "dep")
+ name = "geo_siret"
+ }
+ if (scope == "commune") {
+ origin = file.path(origin, "communes")
+ name = NULL
+ extension = "csv"
+ }
+ }
+
+ to_do = data.frame(
+ origin = origin,
+ destination = destination,
+ short = "download_geo_sirene",
+ stringsAsFactors = FALSE
+ )
+
+ download_archive(
+ to_do,
+ extension = extension,
+ name = name,
+ version = version,
+ verbose = verbose
+ )
+}
\ No newline at end of file
diff --git a/R/extract_building.R b/R/extract_building.R
index e201b48d3f0bd91d26740349e1c91f6561fbd959..a78fbcbc586b2d62adba76ef499430091f88e8d3 100644
--- a/R/extract_building.R
+++ b/R/extract_building.R
@@ -1,46 +1,52 @@
#' @title Extract building information from BD TOPO
#'
#' @description
-#' The function `extract_building`` extracts the layer 'batiment' from BD TOPO.
-#' First it uncompresses the archive '*.7z', typically comming from the use of
-#' download.bd_topo(). Then it extracts from 'gpkg file' the 'batiment',
-#' 'commune' and 'departement' layers as sf objects, applies scheme to all
-#' created sf objects. A selection of 'polygon' is made in 'batiment', to ensure
-#' that only those of current 'department' are kept, and the 'commune' to which
-#' they belong is added. The projection is set to 'projection'. If asked, the
-#' eaip information is added. If asked a map for checking purpose is saved. If
-#' asked the resulting sf object is returned (this is not default behaviour).
-#' Result is saved according to 'destination' path.
+#' `extract_building()` extracts the layer 'batiment' from BD TOPO.
+#'
+#' @details
+#' - First `extract_building()` uncompresses the archive '*.7z', typically
+#' comming from the use of `download_bd_topo()`.
+#' - Then it extracts from 'gpkg file' the 'batiment', 'commune' and
+#' 'departement' layers as sf objects, applies scheme to all
+#' created sf objects.
+#' - A selection of 'polygon' is made in 'batiment', to ensure that only those
+#' of current 'department' are kept, and the 'commune' to which they belong is
+#' added. The projection is set to 'projection'.
+#' - If asked, the eaip information is added. If asked a map for checking
+#' purpose is saved.
+#' - If asked the resulting sf object is returned (this is not default
+#' behaviour).
+#' - Result is saved according to 'destination' path.
#'
#' @param origin character, path to the directory where archive are stored.
-#' @param destination character, path to the directory where results should be saved.
+#' @param destination character, path to the directory where results should be
+#' saved.
#' @param archive character, vector of archive to be adpated.
#' @param scheme data.frame, how archive variables should be treated.
+#' @param projection numeric, 4 digits projection to use.
+#' @param path_eaip character, path where eaip archives should be find.
#' @param journal logical, should a journal file be saved.
#' @param map logical, should a map be plotted (for check purpose).
-#' @param path_eaip character, path where eaip archives should be find.
-#' @param projection numeric, 4 digits projection to use.
-#' @param retrieve logical, should the result be returned.
#' @param verbose logical, should the function give some sumup informations.
+#' @param retrieve logical, should the result be returned.
#'
#' @return if retrieve = TRUE, data.frame of adapated data stored in archive.
#'
#' @export
#'
#' @encoding UTF-8
-#' @author Frédéric Grelot
extract_building = function(
origin,
destination,
archive,
scheme = floodam.data::scheme_bd_topo_3,
+ projection = 4326,
+ path_eaip = NULL,
journal = TRUE,
map = FALSE,
- path_eaip = NULL,
- projection = 4326,
- retrieve = FALSE,
- verbose = TRUE
+ verbose = TRUE,
+ retrieve = FALSE
) {
### Recursive call if archive is missing
if (missing(archive)) {archive = list.files(origin, pattern = ".7z$")}
diff --git a/R/get_archive.R b/R/get_archive.R
index 03021034db94a9346513203ad354afdae9a48d18..2434c8997d06386042a8deec7a54553d29fe7477 100644
--- a/R/get_archive.R
+++ b/R/get_archive.R
@@ -14,37 +14,40 @@
#' filter.
#' @param directory logical, should directories be found instead of archives.
#' See details.
-#' @param html character, indicates if the page is "simple" or is coming from
-#' "data.gouv". This has implications on how to look for links.
-#'
+#' @param local_origin character, the local url address to add to relative
+#' links. When set to `NULL`` (default), origin is used.
+
#' @return A character vector of all archives or directory found in origin
#' matching with given constraints.
#'
#' @details
+#' First, all links are retrieved with `get_link_from_html()`.
+#'
+#' If `directory` is TRUE, only finishing pattern "\" are kept, and this pattern
+#' is erased. `extension` is not used in this case.
#'
-#' First, a regex search is made to find in x names enclosed in href="name" or
-#' href='name'.
+#' When `extension` is givens, it may contain different possibilities. All are
+#' matched at the end of archives' names.
#'
-#' `extension` may contain different possibilities. It will be matches at
-#' the end of archives' names. This may lead to an empty character as result.
+#' At this point, a check is made to see if remaining links are relative (not
+#' starting by "http" or "https") or absolute. All relative links are completed
+#' with `local_origin`. All links are named with `base::basename()`, those names
+#' are used for further selections.
#'
-#' `name` may contain different possibilities. It will be matched at the
-#' beginning of archives' names. This may lead to an empty character as result.
+#' `name` may contain different possibilities. It is matched at the
+#' beginning of archives' names.
#'
+#' `version` may contain different possibilities. Il will be matched
+#' anywhere in archives' names. This may lead an empty character as result.
+#'
#' `date` may contain either "last", and so anything that can be considered
#' as a date in archives' names ("\%Y", "\%Y-\%m", "\%Y-\%m-\%d") is matched
#' against and the max is taken. If nothing matches, all archives' names are
-#' kept. code{date} may also contain anything admissible for code{create_date}.
+#' kept. `date` may also contain anything admissible for `create_date()`.
#' If so, anything that can be considered as a date in archives' names ("\%Y",
#' "\%Y-\%m", "\%Y-\%m-\%d") is matched against, and only archives' names whose
-#' date pertain to \code{create_date(date)} are kept, possibly nothing.
+#' date pertain to `create_date(date)` are kept, possibly nothing.
#'
-#' `version` may contain different possibilities. Il will be matched
-#' anywhere in archives' names. This may lead an empty character as result.
-#'
-#' If `directory` is set to TRUE, `extension` is not used. Instead,
-#' links finishing by "\" are looked after.
-#'
#' @export
#'
#' @examples
@@ -74,6 +77,14 @@
#' get_archive(origin, "7z", "ADMIN-EXPRESS-COG", date = "last")
#' get_archive(origin, "7z", "ADMIN-EXPRESS-COG", version = "FRA", date = "last")
#' get_archive(origin, "7z", "ADMIN-EXPRESS", date = 2021:2022)
+#'
+#' # "BAN" archives in data.gouv.fr
+#' origin = "https://adresse.data.gouv.fr/data/ban/adresses"
+#' get_archive(
+#' origin,
+#' name = "[0-9]{4}-[0-9]{2}-[0-9]{2}",
+#' extension = NULL,
+#' local_origin = get_base_url(origin)
#' }
get_archive = function(
@@ -83,10 +94,8 @@ get_archive = function(
date = NULL,
version = NULL,
directory = FALSE,
- html = c("simple", "data.gouv")
+ local_origin = NULL
) {
- html = match.arg(html)
-
if (length(origin) > 1) {
result = lapply(
origin,
@@ -95,59 +104,31 @@ get_archive = function(
name = name,
date = date,
version = version,
- directory = directory
+ directory = directory,
+ local_origin = local_origin
)
names(result) = NULL
result = result[-duplicated(result)]
return(unlist(result))
}
- x = read_url(origin)
- if ("try-error" %in% class(x)) {
- return(invisible())
+ if (is.null(local_origin)) local_origin = origin
+ result = get_link_from_html(origin)
+
+ if (directory == TRUE) {
+ pattern = complete_pattern("/", extension = FALSE, ending = TRUE)
+ result = grep(pattern, result, value = TRUE)
+ result = gsub(pattern, "", result)
+ extension = NULL
}
-
- if (directory == TRUE) {extension = "/"}
- if (html == "data.gouv") {
- result = unlist(strsplit(x, '"'))
- if (!is.null(extension)) {
- result = unique(
- grep(
- complete_pattern(
- extension,
- extension = !directory,
- ending = TRUE
- ),
- result,
- value = TRUE)
- )
- }
- if (!is.null(name)) {
- result = unique(
- grep(
- complete_pattern(sprintf("%s[_-]*", name), begin = TRUE),
- result,
- value = TRUE
- )
- )
- }
- } else {
- pattern = "(?<=href=([\"'])).*?(?=\\1)"
- result = grep(
- complete_pattern(extension, extension = !directory, ending = TRUE),
- unlist(regmatches(x, gregexpr(pattern, x, perl = TRUE))),
- value = TRUE
- )
- result = grep(
- "^(?![.]{1,2}$)",
- gsub("/$", "", result),
- perl = TRUE,
- value = TRUE
- )
+ if (!is.null(extension)) {
+ pattern = complete_pattern(extension, extension = TRUE, ending = TRUE)
+ result = grep(pattern, result, value = TRUE)
+ result = grep("^(?![.]{1,2}$)", result, perl = TRUE, value = TRUE)
}
selection = grepl("^http", result)
- result[!selection] = file.path(origin, result[!selection])
+ result[!selection] = file.path(local_origin, result[!selection])
result = stats::setNames(result, basename(result))
if (!is.null(name)) {
diff --git a/R/get_link_from_html.R b/R/get_link_from_html.R
new file mode 100644
index 0000000000000000000000000000000000000000..e2bbd9eda0bfbec9885b31222c7d8168f2a62b09
--- /dev/null
+++ b/R/get_link_from_html.R
@@ -0,0 +1,116 @@
+#' @title Get links in a html page
+#'
+#' @description
+#' `get_link_from_html()` returns all links present in a html page.
+#'
+#' `get_date_from_html()` returns links present in a html page that correspond
+#' to dates.
+#'
+#' @param url character, address of the url.
+#' @param x character vector, of url is missing, gives directly a character
+#' vector that could have been the result from `read_url(url)`.
+#' @param expected character, what type of dates are expected between month,
+#' day, or year.
+#' @param last logical, should a "last" date be looked for.
+#'
+#' @return
+#' character of links founded. NULL if nothing has been found.
+#'
+#' @export
+#' @encoding UTF-8
+#'
+#' @examples
+#' x = c(
+#' "<html>",
+#' "<head><title>Index of /example/</title></head>",
+#' "<body>",
+#' "<h1>Index of /example/</h1><hr><pre>",
+#' "<a href='../'>../</a>",
+#' "<a href='parent/2023-11/archive.csv.gz'>archive.csv.gz</a>",
+#' "<a href='2023-12/archive.csv.gz'>archive.csv.gz</a>",
+#' "<a href=\"2024-01/\">2024-01/</a> 07-Jan-2024 09:54",
+#' "<a href=\"parent/child/2024-02/\">2024-02/</a> 07-Feb-2024 09:54",
+#' "<a href=\"2024-03\">2024-03</a> 07-Mar-2024 10:02",
+#' "<a href=\"2024-01-01/\">2024-01-01/</a> 02-Jan-2024 09:56",
+#' "<a href=\"2024-01-02\">2024-01-02</a> 03-jan-2024 11:02",
+#' "<a href=\"2023/\">2023/</a> 01-Feb-2023 15:54",
+#' "<a href=\"2024\">2024</a> 01-Feb-2024 15:54",
+#' "<a href=\"last/\">last/</a> 07-Mar-2024 10:02",
+#' "</pre><hr></body>",
+#' "</html>"
+#' )
+#' get_link_from_html(x = x)
+#'
+#' get_date_from_html(x = x)
+#' get_date_from_html(x = x, expected = "day")
+#' get_date_from_html(x = x, expected = "year")
+#' get_date_from_html(x = x, expected = "any")
+#' get_date_from_html(x = x[-(8:10)])
+#' get_date_from_html(x = x[-(8:10)], last = TRUE)
+
+get_link_from_html = function(url = NULL, x = NULL) {
+
+ if (!is.null(url)) x = read_url(url)
+ if (is.null(x)) return(x)
+
+ # Make sure that x is a vector with only one tag or one value per element
+ x = paste(x, collapse = "")
+ pattern = "!-!"
+ while (length(grep(pattern, x) > 0)) {
+ pattern = sprintf("%s%s", pattern, pattern)
+ }
+ x = gsub(">", sprintf(">%s", pattern), x)
+ x = gsub("<", sprintf("%s<", pattern), x)
+ x = gsub(sprintf("%s%s", pattern, pattern), pattern, x)
+ x = unlist(strsplit(x, pattern))
+
+ pattern = "(?<=href=([\"'])).*?(?=\\1)"
+ result = unlist(regmatches(x, gregexpr(pattern, x, perl = TRUE)))
+ if (identical(result, character())) result = NULL
+
+ return(result)
+}
+
+#' @rdname get_link_from_html
+#' @export
+
+get_date_from_html = function(
+ url = NULL,
+ x = NULL,
+ expected = c("month", "day", "year", "any"),
+ last = FALSE
+) {
+ expected = match.arg(expected)
+
+ pattern = "/$"
+ result = gsub(pattern, "", get_link_from_html(url, x))
+ if (is.null(result)) return(result)
+
+ result = basename(result)
+ pattern = switch(
+ expected,
+ month = "\\d{4}-\\d{2}",
+ day = "\\d{4}-\\d{2}-\\d{2}",
+ year = "\\d{4}",
+ "\\d{4}-\\d{2}-\\d{2}|\\d{4}-\\d{2}|\\d{4}"
+ )
+ if (isTRUE(last)) {
+ pattern = sprintf("(%s|last|latest)", pattern)
+ }
+ pattern = sprintf("^%s$", pattern)
+
+ result = grep(pattern, result, value = TRUE)
+
+ if (identical(result, "last")) {
+ msg = c(
+ "Only `last` has been found. ",
+ sprintf(
+ "Possible mismatch with expected format (%s)",
+ expected
+ )
+ )
+ warning(msg)
+ }
+
+ return(result)
+}
\ No newline at end of file
diff --git a/R/read_with_scheme.R b/R/read_with_scheme.R
index 53d1b396148fd7d0fb1e17f7a4131fd8616f0c2b..71fe7d58f900dab4ef4d6c2c1a7bd3b84e80c10c 100644
--- a/R/read_with_scheme.R
+++ b/R/read_with_scheme.R
@@ -30,7 +30,6 @@
#' @export
#'
#' @encoding UTF-8
-#' @author Frédéric Grelot
read_with_scheme = function(
x,
@@ -126,9 +125,10 @@ read_csv_with_scheme = function(
treatment = list(
"factor" = as.factor,
- "date" = as.Date,
+ "Date" = as.Date,
"numeric" = as.numeric,
- "integer" = as.integer
+ "integer" = as.integer,
+ "logical" = to_logical
)
for (type in names(treatment)) {
selection = scheme[["name"]][scheme[["type"]] == type]
@@ -141,10 +141,20 @@ read_csv_with_scheme = function(
colClasses = "character"
)
}
+ message(sprintf("- %s observations loaded.", nrow(result)))
if (all(c("lon", "lat") %in% names(result))) {
+ selection = !is.na(result[["lon"]]) & !is.na(result[["lon"]])
+ if (any(!selection)) {
+ message(
+ sprintf(
+ "- %s observations without lon/lat (removed).",
+ sum(!selection)
+ )
+ )
+ }
result = sf::st_as_sf(
- result,
+ result[selection, ],
coords = c("lon", "lat"),
crs = projection
)
diff --git a/R/utilities.R b/R/utilities.R
index 29ef122c445e9d17d26199919daaff4dcf1cd66f..5c9b289c00fe8bcf70d8e8f87cd6e471a0e2a284 100644
--- a/R/utilities.R
+++ b/R/utilities.R
@@ -1,27 +1,4 @@
## In this file are grouped function that are used but should not be exported
-#'
-#' @title Transform a character vector in logical one
-#'
-#' @description
-#' Use a modality for TRUE and onther for FALSE
-#'
-#' @param x character vector
-#' @param true character, modality for TRUE
-#' @param false character, modality for FALSE
-#'
-#' @return logical vector
-#'
-#' @encoding UTF-8
-#' @author Victor Champonnois et Frédéric Grelot
-#'
-#' @examples
-#' x = sample(c("red", "blue"), 10, replace = TRUE)
-#' floodam.data:::to_logical(x, "red", "blue")
-#' floodam.data:::to_logical(x, "red", "green")
-
-to_logical = function(x, true = TRUE, false = FALSE) {
- data.table::fifelse(x == true, TRUE, data.table::fifelse(x == false, FALSE, NA))
-}
#' @title Add NA for a given value
#'
@@ -40,12 +17,14 @@ to_logical = function(x, true = TRUE, false = FALSE) {
#' floodam.data:::treat_na(x, "green")
treat_na = function(x, value) {
- na.value = switch(EXPR = typeof(x),
+ na_value = switch(
+ EXPR = typeof(x),
"character" = NA_character_,
"integer" = NA_integer_,
"double" = NA_real_,
- NA)
- data.table::fifelse(x == value, na.value, x)
+ NA
+ )
+ data.table::fifelse(x == value, na_value, x)
}
#' @title Add information to a journal
@@ -92,4 +71,166 @@ file_version = function(path, pattern, version = "last") {
1
)
return(result)
-}
\ No newline at end of file
+}
+
+#' @title Get parent url from an url
+#'
+#' @description
+#' `getbase_url()` gets the base parent from an url.
+#'
+#' @details
+#' `get_base_url()` keeps unchanged links that do not start exactlty by
+#' "http://" or "https://".
+#'
+#' @param url character, address of the url.
+#'
+#' @export
+#'
+#' @examples
+#'
+#' get_base_url("http://parent/child/archive.csv.gz")
+#' get_base_url("https://parent/child/archive.csv.gz")
+#' get_base_url("parent/child/archive.csv.gz")
+
+get_base_url = function(url) {
+ pattern = "(https?://[^/]+)/.*"
+ gsub(pattern, "\\1", url)
+}
+
+#' @title Subset with message
+#'
+#' @description
+#' `subset_with_message()` makes subset of data.frame that is suitable for
+#' a processing of data.
+#'
+#' @details
+#' `subset_with_message()` sends message when:
+#' - `rows` is not logical because it is an obligation for this function.
+#' - `columns` is not a character vector of valid column names, because it is an
+#' obligation for this function.
+#' - `rows` conducts to delete some observations.
+#'
+#' @param x data.frame.
+#' @param rows logical, observations to be kept.
+#' @param columns character, variables to be kept.
+#'
+#' @return `data.frame` of selected observations and variables.
+#'
+#' @export
+
+subset_with_message = function(x, rows, columns) {
+ if (missing(rows)) rows = rep(TRUE, nrow(x))
+ if (missing(columns)) columns = colnames(x)
+ if (!is.logical(rows)) {
+ message("- rows must be logical. No subset performed on observations.")
+ rows = rep(TRUE, nrow(x))
+ }
+ if (!is.character(columns) || !all(columns %in% names(x))) {
+ message(
+ "- columns must be valid column names. ",
+ "No subset performed on variables"
+ )
+ columns = names(x)
+ }
+ if (sum(rows) < nrow(x)) {
+ message(
+ sprintf(
+ "- %s observations not in selection (removed).",
+ sum(!rows)
+ )
+ )
+ }
+ return(x[rows, columns, dop = FALSE])
+}
+
+#' @title Transform a vector in a logical ones
+#'
+#' @description
+#' `as_logical()` enhances `as.logical()`, especially when input is a
+#' character, by treating some comon cases, at least in English and French
+#' context.
+#'
+#' @details
+#' When applied to a character vector, `as_logical()` tests if all values are
+#' in a set of admissibles values for `TRUE` cases, `FALSE` cases, and `NA`
+#' cases. If it is the case, it makes all substitutions so that a `logical`
+#' vector is returned by `as.logical()`.
+#'
+#' Some defaults cases are implemented (all insensitive to case)
+#'
+#' - English TRUE/FALSE with:
+#' - `TRUE` for "T" and "TRUE"
+#' - `FALSE` for "F" and "FALSE"
+#' - English YES/NO with:
+#' - `TRUE` for "Y" and "YES"
+#' - `FALSE` for "N" and "NO"
+#' - French TRUE/FALSE with:
+#' - `TRUE` for "V" and "VRAI"
+#' - `FALSE` for "F" and "FAUX"
+#' - French YES/NO with:
+#' - `TRUE` for "O" and "OUI"
+#' - `FALSE` for "N" and "NON"
+#'
+#' `true` and `false` can be used to add more cases. To be used they must be
+#' both given, if not none is considered. Even if `true` and `false` are given,
+#' default substitutions for French and English cases are performed.
+#'
+#' @param x vector, values to be transformed.
+#' @param true character, optional values for `TRUE` cases.
+#' @param false character, optional values for `FALSE` cases.
+#' @param as_is logical, should result be sent as character (for recursive
+#' call).
+#'
+#' @return logical
+#'
+#' @encoding UTF-8
+#'
+#' @export
+#'
+#' @examples
+#'
+#' # Default behaviour
+#' to_logical(c(0:2, NA))
+#'
+#' # For English (default, case insensitive)
+#' to_logical(c("true", "false", "t", "f", "True", "False", "", "NA", NA))
+#' to_logical(c("y", "n", "Yes", "No"))
+#'
+#' # For French (default)
+#' to_logical(c("n", "o", "Non", "Oui"))
+#' to_logical(c("v", "f", "vrai", "faux"))
+#'
+#' # For other convention (language)
+#' x = c("si", "no", NA)
+#' to_logical(x)
+#' to_logical(x, true = "SI", false = "NO")
+#'
+#' # Cannot mix language (by default)
+#' x = c("NON", "OUI", "YES", "NO")
+#' to_logical(x)
+#'
+#' # Can use parameters in this case
+#' to_logical(x, true = c("OUI", "YES"), false = c("NO", "NON"))
+
+to_logical = function(x, true, false, as_is = FALSE) {
+ if (is.character(x)) {
+ x = toupper(x)
+ na = c("", "NA", NA)
+ if (!missing(true) & !(missing(false))) {
+ true = toupper(true)
+ false = toupper(false)
+ if (all(x %in% c(true, false, na))) {
+ x[x %in% true] = TRUE
+ x[x %in% false] = FALSE
+ }
+ if (isTRUE(as_is)) {
+ return(x)
+ }
+ } else {
+ x = to_logical(x, c("y", "yes"), c("n", "no"), TRUE)
+ x = to_logical(x, c("o", "oui"), c("n", "non"), TRUE)
+ x = to_logical(x, c("v", "vrai"), c("f", "faux"), TRUE)
+ }
+ }
+ as.logical(x)
+}
diff --git a/R/utilities_geomatic.R b/R/utilities_geomatic.R
index 1481fbebcb299dc2f5c70e7629b324d70589d966..10cea73615abc7158793eca35d4ddba0a9d623ff 100644
--- a/R/utilities_geomatic.R
+++ b/R/utilities_geomatic.R
@@ -16,7 +16,6 @@
#' @return sf object with both commune and department information added.
#'
#' @encoding UTF-8
-#' @author Frédéric Grelot
add_commune = function(x, commune, department = NULL) {
if (!is.null(department)) {
@@ -47,11 +46,14 @@ add_eaip = function(x, path_eaip, department) {
path_eaip,
sprintf("eaip_%s.rds", format_scope(department))
)
+ message(sprintf("- %s observations treated.", nrow(x)))
if (length(eaip) == 0) {
x[["eaip"]] = NA
+ message("- no eaip layer found. NA added.")
} else {
eaip = readRDS(eaip)
x[["eaip"]] = in_layer(x, eaip)
+ message(sprintf("- %s observations in eaip.", sum(x[["eaip"]])))
}
return(x)
}
@@ -60,4 +62,68 @@ analyse_projection = function(x, default = 2154) {
result = rep(default, length(x))
result[x == "LAMB93"] = 2154
return(result)
-}
\ No newline at end of file
+}
+
+#' @title Split a `sf` data.frame by `department`
+#'
+#' @description
+#' Split a `sf` data.frame with information `commune` by `department`.
+#' `commune` information is mandatory in input.
+#'
+#' @details
+#' The information in `commune` is interpreted to construct a first version of
+#' department for each observation.
+#'
+#' If `admin_dep` is given, a `sf::st_intersects()` is performed to get
+#' departement from geographic perspective. A consistency analysis between both
+#' versions is done. In case of inconsistencies, messages ar thrown. The
+#' geographic perspective is kept.
+#'
+#' @param x sf object.
+#' @param admin_dep sf object.
+#'
+#' @return A list of sf objects.
+#'
+#' @encoding UTF-8
+
+split_dep = function(x, admin_dep = NULL) {
+ dep_commune = substring(x[["commune"]], 1, 2)
+ selection = dep_commune %in% "97"
+ dep_commune[selection] = substring(x[["commune"]][selection], 1, 3)
+ if (is.null(admin_dep)) {
+ message(
+ "- No layer department provided, ",
+ "split is done on 'commune' field."
+ )
+ dep = dep_commune
+ } else {
+ dep = sapply(
+ sf::st_intersects(x, admin_dep),
+ function(x) {if (length(x) != 1) NA else x}
+ )
+ dep = suppressMessages(
+ sf::st_drop_geometry(admin_dep)[dep, "department"]
+ )
+ test = dep == dep_commune
+ if (any(is.na(test))) {
+ message(
+ sprintf(
+ "- %s observations out of scope (removed).",
+ sum(is.na(test))
+ )
+ )
+ }
+ if (any(test %in% FALSE)) {
+ message(
+ sprintf(
+ "- %s observations not in 'commune' department (removed).",
+ sum(test %in% FALSE)
+ )
+ )
+ }
+ }
+ x["department"] = dep
+ result = split(x, dep)
+ names(result) = format_scope(names(result))
+ return(result)
+}
diff --git a/data-raw/scheme.R b/data-raw/scheme.R
index d32dc6f7a8169b44c9e76307ef134bd076ca4ecd..ce5030509462b6b8904597015304bb29af637fb5 100644
--- a/data-raw/scheme.R
+++ b/data-raw/scheme.R
@@ -248,7 +248,7 @@ scheme_sirene_2019 = data.table::fread(
"inst/extdata/scheme_sirene_2019.csv",
data.table = FALSE
)
-Encoding(scheme_sirene_2019[["label.french"]]) = "UTF-8"
+Encoding(scheme_sirene_2019[["label_french"]]) = "UTF-8"
Encoding(scheme_sirene_2019[["comment"]]) = "UTF-8"
usethis::use_data(scheme_sirene_2019, overwrite = TRUE)
diff --git a/data/scheme_admin_express_2_0.rda b/data/scheme_admin_express_2_0.rda
index 46637cd80a19137cd64538a13de33112b0a665a6..8c778cebbb5edc68a5c46a16faf37f4a6c9f3dab 100644
Binary files a/data/scheme_admin_express_2_0.rda and b/data/scheme_admin_express_2_0.rda differ
diff --git a/data/scheme_admin_express_3_1.rda b/data/scheme_admin_express_3_1.rda
index 5b8c336292ca2c75f2a9f5a286753dff3ab0b90d..02a887dfc39de068a4365c06a02bd834e9de055a 100644
Binary files a/data/scheme_admin_express_3_1.rda and b/data/scheme_admin_express_3_1.rda differ
diff --git a/data/scheme_bd_topo_3.rda b/data/scheme_bd_topo_3.rda
index 885743924346776aa963c2de35f8f44fe84065ef..19d2ed8aa04dce7b3caf5e262b3f43d7142fa2be 100644
Binary files a/data/scheme_bd_topo_3.rda and b/data/scheme_bd_topo_3.rda differ
diff --git a/data/scheme_gaspar_azi.rda b/data/scheme_gaspar_azi.rda
index 2957942f11bb0584311a8961266c0a045b35b89c..110b93ac93e1fbdf32d34a838fa4a048d8e8afda 100644
Binary files a/data/scheme_gaspar_azi.rda and b/data/scheme_gaspar_azi.rda differ
diff --git a/data/scheme_gaspar_catnat.rda b/data/scheme_gaspar_catnat.rda
index b4c162838a3c79f0e699fe27ce3b6b789f5a7492..1d23cf7a658a632997491e8147fbaddfa95baeb1 100644
Binary files a/data/scheme_gaspar_catnat.rda and b/data/scheme_gaspar_catnat.rda differ
diff --git a/data/scheme_gaspar_pprn.rda b/data/scheme_gaspar_pprn.rda
index e64d45ed4114968a6364f4e4ad3d9bb23b71b88f..9aae8f718a84a488d7aacd0d494ec4facb3eae09 100644
Binary files a/data/scheme_gaspar_pprn.rda and b/data/scheme_gaspar_pprn.rda differ
diff --git a/data/scheme_gaspar_risq.rda b/data/scheme_gaspar_risq.rda
index 265e5bb38c2fb7188b14d58d8fbe1aba58c8b5d3..27a0b16b88b32f5e344bb2a26fa3311ba9326f82 100644
Binary files a/data/scheme_gaspar_risq.rda and b/data/scheme_gaspar_risq.rda differ
diff --git a/data/scheme_insee_logement_2019.rda b/data/scheme_insee_logement_2019.rda
index 6bfb19bc31b301748c64f3e226852bb168bf6583..c1d363a58629c962a6985c175d97ccb550bbc4ff 100644
Binary files a/data/scheme_insee_logement_2019.rda and b/data/scheme_insee_logement_2019.rda differ
diff --git a/data/scheme_rpg_1.rda b/data/scheme_rpg_1.rda
index 225982e92dd538b35076f324a99d6ad75dafa243..15b48afc865ebd2946df224b227e074a27d24fa1 100644
Binary files a/data/scheme_rpg_1.rda and b/data/scheme_rpg_1.rda differ
diff --git a/data/scheme_rpg_2.rda b/data/scheme_rpg_2.rda
index 46ed4cebf1a21a25761d56a4211aafd33b65510b..edbc13f1282828ea1439c1f60476f5da15896691 100644
Binary files a/data/scheme_rpg_2.rda and b/data/scheme_rpg_2.rda differ
diff --git a/data/scheme_sirene_2019.rda b/data/scheme_sirene_2019.rda
index fe6fb54b1e29b4e5f26dffe4c45d5d56b325ed68..af70c3ce386dbbe36399a85be83a28ee05c4090d 100644
Binary files a/data/scheme_sirene_2019.rda and b/data/scheme_sirene_2019.rda differ
diff --git a/data/scheme_sirene_na.rda b/data/scheme_sirene_na.rda
index 1f32dacc83c5c94cadb82fa52aa7e7a2c8616fb9..b6d276daa5152ced87e5883022c9c5d88469fe60 100644
Binary files a/data/scheme_sirene_na.rda and b/data/scheme_sirene_na.rda differ
diff --git a/dev/tag-message b/dev/tag-message
index 7012fc7c3524308b111df2993a1a10c3ba30e2dd..93cb15eea283b6ca57745957b4267630bf273cc8 100644
--- a/dev/tag-message
+++ b/dev/tag-message
@@ -1,8 +1,8 @@
-floodam.data Version: 0.9.40.0
+floodam.data Version: 0.9.41.0
0 errors ✔ | 0 warnings ✔ | 0 notes ✔
**Details** see NEWS.md
-# git tag -a v0.9.40.0 -F dev/tag-message
+# git tag -a v0.9.41.0 -F dev/tag-message
# git push --tags
diff --git a/inst/extdata/scheme_admin_express_2_0.csv b/inst/extdata/scheme_admin_express_2_0.csv
index 22d3c1bed6da58f9d91521b7cf83bd03031583ea..48766ac017a2ccc1cb4f4575689ccde526d5ae3f 100644
--- a/inst/extdata/scheme_admin_express_2_0.csv
+++ b/inst/extdata/scheme_admin_express_2_0.csv
@@ -1,27 +1,27 @@
-"name","name_origin","layer","order","keep","type","label_fr","source","length_source","type_source","comment"
-"id","ID","COMMUNE",1,"FALSE","character","Identifiant de la commune","IGN",24,"character",
-"commune_label_fr","NOM_COM","COMMUNE",2,"TRUE","character","Nom de la commune","IGN",50,"character",
-"commune_label_fr_cap","NOM_COM_M","COMMUNE",3,"FALSE","character","Nom de la commune en majuscules","IGN",50,"character",
-"commune","INSEE_COM","COMMUNE",4,"TRUE","character","Numéro INSEE de la commune","IGN",5,"character",
-"status","STATUT","COMMUNE",5,"FALSE","character","Statut administratif","IGN",22,"character",
-"district","INSEE_ARR","COMMUNE",6,"FALSE","character","Numéro INSEE de l'arrondissement","IGN",2,"character",
-"department","INSEE_DEP","COMMUNE",7,"TRUE","character","Numéro INSEE du département","IGN",3,"character",
-"region","INSEE_REG","COMMUNE",8,"FALSE","character","Numéro INSEE de la région","IGN",2,"character",
-"epci","CODE_EPCI","COMMUNE",9,"TRUE","character","Code de l'EPCI","IGN",21,"character",
-"population","POPULATION","COMMUNE",10,"TRUE","integer","Population de la commune","IGN",8,"integer",
-"type","TYPE","COMMUNE",11,"FALSE","character","Type de la commune selon le COG","IGN",3,"character",
-"id","ID","DEPARTEMENT",1,"FALSE","character","Identifiant du département","IGN",24,"character",
-"department_label_fr","NOM_DEP","DEPARTEMENT",2,"TRUE","character","Nom du département","IGN",30,"character",
-"department_label_fr_cap","NOM_DEP_M","DEPARTEMENT",3,"FALSE","character","Nom du département en capitales","IGN",30,"character",
-"department","INSEE_DEP","DEPARTEMENT",4,"TRUE","character","Numéro INSEE du département","IGN",3,"character",
-"region","INSEE_REG","DEPARTEMENT",5,"TRUE","character","Numéro INSEE de la région","IGN",2,"character",
-"capital","CHF_DEP","DEPARTEMENT",6,"FALSE","character","Code INSEE de la commune chef-lieu du département","IGN",5,"character","Apparemment non présent dans les versions récentes"
-"id","ID","EPCI",1,"FALSE","character","Identifiant de l'EPCI","IGN",24,"character",
-"epci","CODE_EPCI","EPCI",2,"TRUE","character","Code de l'EPCI","IGN",9,"character",
-"epci_label_fr","NOM_EPCI","EPCI",3,"TRUE","character","Nom de l'EPCI","IGN",230,"character",
-"type","TYPE_EPCI","EPCI",4,"TRUE","character","Type de l'EPCI","IGN",9,"character",
-"id","ID","REGION",1,"FALSE","character","Identifiant de la région","IGN",24,"character",
-"region_label_fr","NOM_REG","REGION",2,"TRUE","character","Nom de la région","IGN",35,"character",
-"region_label_fr_cap","NOM_REG_M","REGION",3,"FALSE","character","Nom de la région","IGN",35,"character",
-"region","INSEE_REG","REGION",4,"TRUE","character","Numéro INSEE de la région","IGN",2,"character",
-"capital","CHF_REG","REGION",5,"FALSE","character","Code INSEE du chef-lieu de la région","IGN",5,"character","Apparemment non présent dans les versions récentes"
+name;name_origin;layer;order;keep;type;label_fr;source;length_source;type_source;comment
+id;ID;COMMUNE;1;FALSE;character;Identifiant de la commune;IGN;24;character;
+commune_label_fr;NOM_COM;COMMUNE;2;TRUE;character;Nom de la commune;IGN;50;character;
+commune_label_fr_cap;NOM_COM_M;COMMUNE;3;FALSE;character;Nom de la commune en majuscules;IGN;50;character;
+commune;INSEE_COM;COMMUNE;4;TRUE;character;Numéro INSEE de la commune;IGN;5;character;
+status;STATUT;COMMUNE;5;FALSE;character;Statut administratif;IGN;22;character;
+district;INSEE_ARR;COMMUNE;6;FALSE;character;Numéro INSEE de l'arrondissement;IGN;2;character;
+department;INSEE_DEP;COMMUNE;7;TRUE;character;Numéro INSEE du département;IGN;3;character;
+region;INSEE_REG;COMMUNE;8;FALSE;character;Numéro INSEE de la région;IGN;2;character;
+epci;CODE_EPCI;COMMUNE;9;TRUE;character;Code de l'EPCI;IGN;21;character;
+population;POPULATION;COMMUNE;10;TRUE;integer;Population de la commune;IGN;8;integer;
+type;TYPE;COMMUNE;11;FALSE;character;Type de la commune selon le COG;IGN;3;character;
+id;ID;DEPARTEMENT;1;FALSE;character;Identifiant du département;IGN;24;character;
+department_label_fr;NOM_DEP;DEPARTEMENT;2;TRUE;character;Nom du département;IGN;30;character;
+department_label_fr_cap;NOM_DEP_M;DEPARTEMENT;3;FALSE;character;Nom du département en capitales;IGN;30;character;
+department;INSEE_DEP;DEPARTEMENT;4;TRUE;character;Numéro INSEE du département;IGN;3;character;
+region;INSEE_REG;DEPARTEMENT;5;TRUE;character;Numéro INSEE de la région;IGN;2;character;
+capital;CHF_DEP;DEPARTEMENT;6;FALSE;character;Code INSEE de la commune chef-lieu du département;IGN;5;character;Apparemment non présent dans les versions récentes
+id;ID;EPCI;1;FALSE;character;Identifiant de l'EPCI;IGN;24;character;
+epci;CODE_EPCI;EPCI;2;TRUE;character;Code de l'EPCI;IGN;9;character;
+epci_label_fr;NOM_EPCI;EPCI;3;TRUE;character;Nom de l'EPCI;IGN;230;character;
+type;TYPE_EPCI;EPCI;4;TRUE;character;Type de l'EPCI;IGN;9;character;
+id;ID;REGION;1;FALSE;character;Identifiant de la région;IGN;24;character;
+region_label_fr;NOM_REG;REGION;2;TRUE;character;Nom de la région;IGN;35;character;
+region_label_fr_cap;NOM_REG_M;REGION;3;FALSE;character;Nom de la région;IGN;35;character;
+region;INSEE_REG;REGION;4;TRUE;character;Numéro INSEE de la région;IGN;2;character;
+capital;CHF_REG;REGION;5;FALSE;character;Code INSEE du chef-lieu de la région;IGN;5;character;Apparemment non présent dans les versions récentes
diff --git a/inst/extdata/scheme_admin_express_3_1.csv b/inst/extdata/scheme_admin_express_3_1.csv
index c2068629ceea48207bf409c2e04b88449b083152..b6c225169f76868df0e4204e9f40b917a8d5dca3 100644
--- a/inst/extdata/scheme_admin_express_3_1.csv
+++ b/inst/extdata/scheme_admin_express_3_1.csv
@@ -1,25 +1,25 @@
-"name","name_origin","layer","order","keep","type","label_fr","source","length_source","type_source","comment"
-"id","ID","COMMUNE",1,"FALSE","character","Identifiant de la commune","IGN",24,"character",
-"commune_label_fr","NOM","COMMUNE",2,"TRUE","character","Nom de la commune","IGN",50,"character",
-"commune_label_fr_cap","NOM_M","COMMUNE",3,"FALSE","character","Nom de la commune en majuscules","IGN",50,"character",
-"commune","INSEE_COM","COMMUNE",4,"TRUE","character","Code INSEE de la commune","IGN",5,"character",
-"status","STATUT","COMMUNE",5,"FALSE","character","Statut administratif","IGN",22,"character",
-"population","POPULATION","COMMUNE",6,"TRUE","integer","Population de la commune","IGN",8,"integer",
-"canton","INSEE_CAN","COMMUNE",7,"FALSE","character","Code INSEE du canton","IGN",2,"character",
-"district","INSEE_ARR","COMMUNE",8,"FALSE","character","Code INSEE de l'arrondissement","IGN",2,"character",
-"department","INSEE_DEP","COMMUNE",9,"TRUE","character","Code INSEE du département","IGN",3,"character",
-"region","INSEE_REG","COMMUNE",10,"TRUE","character","Code INSEE de la région","IGN",2,"character",
-"epci","SIREN_EPCI","COMMUNE",11,"TRUE","character","Code SIREN des EPCI","IGN",21,"character",
-"id","ID","DEPARTEMENT",1,"FALSE","character","Identifiant du département","IGN",24,"character",
-"department_label_fr_cap","NOM_M","DEPARTEMENT",2,"FALSE","character","Nom du département en majuscules","IGN",30,"character",
-"department_label_fr","NOM","DEPARTEMENT",3,"TRUE","character","Nom du département","IGN",30,"character",
-"department","INSEE_DEP","DEPARTEMENT",4,"TRUE","character","Code INSEE du département","IGN",3,"character",
-"region","INSEE_REG","DEPARTEMENT",5,"TRUE","character","Code INSEE de la région","IGN",2,"character",
-"id","ID","EPCI",1,"FALSE","character","Identifiant de l'EPCI","IGN",24,"character",
-"epci","CODE_SIREN","EPCI",2,"TRUE","character","Code SIREN de l'entité administrative","IGN",9,"character",
-"epci_label_fr","NOM","EPCI",3,"TRUE","character","Nom de l'EPCI","IGN",230,"character",
-"type","NATURE","EPCI",4,"TRUE","character","Nature de l'EPCI","IGN",9,"character",
-"id","ID","REGION",1,"FALSE","character","Identifiant de la région","IGN",24,"character",
-"region_label_fr_cap","NOM_REG_M","REGION",2,"FALSE","character","Nom de la région en majuscules","IGN",35,"character",
-"region_label_fr","NOM_REG","REGION",3,"TRUE","character","Nom de la région","IGN",35,"character",
-"region","INSEE_REG","REGION",4,"TRUE","character","Code INSEE de la région","IGN",2,"character",
+name;name_origin;layer;order;keep;type;label_fr;source;length_source;type_source;comment
+id;ID;COMMUNE;1;FALSE;character;Identifiant de la commune;IGN;24;character;
+commune_label_fr;NOM;COMMUNE;2;TRUE;character;Nom de la commune;IGN;50;character;
+commune_label_fr_cap;NOM_M;COMMUNE;3;FALSE;character;Nom de la commune en majuscules;IGN;50;character;
+commune;INSEE_COM;COMMUNE;4;TRUE;character;Code INSEE de la commune;IGN;5;character;
+status;STATUT;COMMUNE;5;FALSE;character;Statut administratif;IGN;22;character;
+population;POPULATION;COMMUNE;6;TRUE;integer;Population de la commune;IGN;8;integer;
+canton;INSEE_CAN;COMMUNE;7;FALSE;character;Code INSEE du canton;IGN;2;character;
+district;INSEE_ARR;COMMUNE;8;FALSE;character;Code INSEE de l'arrondissement;IGN;2;character;
+department;INSEE_DEP;COMMUNE;9;TRUE;character;Code INSEE du département;IGN;3;character;
+region;INSEE_REG;COMMUNE;10;TRUE;character;Code INSEE de la région;IGN;2;character;
+epci;SIREN_EPCI;COMMUNE;11;TRUE;character;Code SIREN des EPCI;IGN;21;character;
+id;ID;DEPARTEMENT;1;FALSE;character;Identifiant du département;IGN;24;character;
+department_label_fr_cap;NOM_M;DEPARTEMENT;2;FALSE;character;Nom du département en majuscules;IGN;30;character;
+department_label_fr;NOM;DEPARTEMENT;3;TRUE;character;Nom du département;IGN;30;character;
+department;INSEE_DEP;DEPARTEMENT;4;TRUE;character;Code INSEE du département;IGN;3;character;
+region;INSEE_REG;DEPARTEMENT;5;TRUE;character;Code INSEE de la région;IGN;2;character;
+id;ID;EPCI;1;FALSE;character;Identifiant de l'EPCI;IGN;24;character;
+epci;CODE_SIREN;EPCI;2;TRUE;character;Code SIREN de l'entité administrative;IGN;9;character;
+epci_label_fr;NOM;EPCI;3;TRUE;character;Nom de l'EPCI;IGN;230;character;
+type;NATURE;EPCI;4;TRUE;character;Nature de l'EPCI;IGN;9;character;
+id;ID;REGION;1;FALSE;character;Identifiant de la région;IGN;24;character;
+region_label_fr_cap;NOM_REG_M;REGION;2;FALSE;character;Nom de la région en majuscules;IGN;35;character;
+region_label_fr;NOM_REG;REGION;3;TRUE;character;Nom de la région;IGN;35;character;
+region;INSEE_REG;REGION;4;TRUE;character;Code INSEE de la région;IGN;2;character;
diff --git a/inst/extdata/scheme_ban.csv b/inst/extdata/scheme_ban.csv
index 7e0fca86f9959e44e58466960e4fc9d06b1ae7dc..ec0661e88855c9d72e27d4cf0528c7806de44209 100644
--- a/inst/extdata/scheme_ban.csv
+++ b/inst/extdata/scheme_ban.csv
@@ -1,24 +1,24 @@
-name name_origin order keep type label_fr source length_source type_source comment
-id id 1 TRUE character Identifiant data.gouv.fr NA character Clé d’interopérabilité telle que définie dans la spécification du format d'échange BAL 1.3. Lorsqu'aucun code FANTOIR n'est connu, un code transitoire composé de 6 caractères alpha-numériques est généré.
-id_fantoir id_fantoir 2 FALSE character identifiant FANTOIR data.gouv.fr NA character Identifiant FANTOIR de la voie, le cas échant. L'identifiant est préfixé par la commune de rattachement FANTOIR (commune actuelle ou commune ancienne)
-address_number numero 3 TRUE integer Numéro dans la voie data.gouv.fr NA integer Numéro de l’adresse dans la voie
-address_rep rep 4 TRUE factor Indice de répétition data.gouv.fr NA character Indice de répétition associé au numéro (par exemple bis, a…)
-address_street nom_voie 5 TRUE character Nom de la voie data.gouv.fr NA character Nom de la voie en minuscules accentuées
-address_code code_postal 6 TRUE character Code postal data.gouv.fr NA character Code postal du bureau de distribution de la voie
-commune code_insee 7 TRUE character Code INSEE data.gouv.fr NA character Code INSEE de la commune actuelle sur la base du Code Officiel géographique en vigueur
-commune_name nom_commune 8 FALSE character Nom officiel de la commune data.gouv.fr NA character Nom officiel de la commune actuelle
-commune_old code_insee_ancienne_commune 9 FALSE character Code INSEE de l'ancienne commune data.gouv.fr NA character Code INSEE de l'ancienne commune sur laquelle est située l'adresse
-commune_old_name nom_ancienne_commune 10 FALSE character Nom de l'ancienne commune data.gouv.fr NA character Nom de l'ancienne commune sur laquelle est située l'adresse
-x x 11 FALSE numeric Abscisse en projection légale data.gouv.fr NA numeric Coordonnées cartographique en projection légale
-y y 12 FALSE numeric Ordonnée en projection légale data.gouv.fr NA numeric Coordonnées cartographique en projection légale
-lon lon 13 TRUE numeric Longitude en WGS-84 data.gouv.fr NA numeric Longitude en WGS-84
-lat lat 14 TRUE numeric Latitude en WGS-84 data.gouv.fr NA numeric Latitude en WGS-84
-position_type type_position 15 TRUE factor Type de position data.gouv.fr NA factor Type de position telle que définie dans la spécification du format d'échange BAL 1.3. Peut-être vide si inconnu ou non renseigné.
-alias alias 16 FALSE logical Vide data.gouv.fr NA logical Vide
-locality_name nom_ld 17 TRUE character Nom du lieu-dit de rattachement data.gouv.fr NA character Nom du lieu-dit de rattachement (ou autre type de toponyme)
-commune_name_postal libelle_acheminement 18 FALSE character Nom de la commune d’acheminement data.gouv.fr NA character Nom de la commune d’acheminement
-address_street_postal nom_afnor 19 FALSE character Nom postale de la voie data.gouv.fr NA character Nom de la voie normalisé selon la norme postale
-position_source source_position 20 TRUE factor Source de la position géographique data.gouv.fr NA factor Source de la position géographique. Valeurs possibles : (commune, cadastre, arcep, laposte, insee, sdis, inconnue)
-address_source source_nom_voie 21 FALSE factor Source du nom de la voie data.gouv.fr NA factor Source du nom de la voie. Valeurs possibles : (commune, cadastre, arcep, laposte, insee, sdis, inconnue)
-commune_certification certification_commune 22 TRUE logical Certification par la commune data.gouv.fr NA integer Indique si l’adresse a été certifiée par la commune. Valeurs possibles : (1 pour oui, 0 pour non)
-registry_parcel cad_parcelles 23 FALSE character Parcelles cadastrales data.gouv.fr NA character Liste les identifiants des parcelles cadastrales auxquelles l’adresse est rattachée, si l'information est connue. Codage de l’identifiant sur 14 caractères. Séparateur |. Donnée en cours de fiabilisation
+name;name_origin;order;keep;type;label_fr;source;length_source;type_source;comment
+id;id;1;TRUE;character;Identifiant;data.gouv.fr;NA;character;Clé d’interopérabilité telle que définie dans la spécification du format d'échange BAL 1.3. Lorsqu'aucun code FANTOIR n'est connu, un code transitoire composé de 6 caractères alpha-numériques est généré.
+id_fantoir;id_fantoir;2;FALSE;character;identifiant FANTOIR;data.gouv.fr;NA;character;Identifiant FANTOIR de la voie, le cas échant. L'identifiant est préfixé par la commune de rattachement FANTOIR (commune actuelle ou commune ancienne)
+address_number;numero;3;TRUE;integer;Numéro dans la voie;data.gouv.fr;NA;integer;Numéro de l’adresse dans la voie
+address_rep;rep;4;TRUE;factor;Indice de répétition;data.gouv.fr;NA;character;Indice de répétition associé au numéro (par exemple bis, a…)
+address_street;nom_voie;5;TRUE;character;Nom de la voie;data.gouv.fr;NA;character;Nom de la voie en minuscules accentuées
+address_code;code_postal;6;TRUE;character;Code postal;data.gouv.fr;NA;character;Code postal du bureau de distribution de la voie
+commune;code_insee;7;TRUE;character;Code INSEE;data.gouv.fr;NA;character;Code INSEE de la commune actuelle sur la base du Code Officiel géographique en vigueur
+commune_name;nom_commune;8;FALSE;character;Nom officiel de la commune;data.gouv.fr;NA;character;Nom officiel de la commune actuelle
+commune_old;code_insee_ancienne_commune;9;FALSE;character;Code INSEE de l'ancienne commune;data.gouv.fr;NA;character;Code INSEE de l'ancienne commune sur laquelle est située l'adresse
+commune_old_name;nom_ancienne_commune;10;FALSE;character;Nom de l'ancienne commune;data.gouv.fr;NA;character;Nom de l'ancienne commune sur laquelle est située l'adresse
+x;x;11;FALSE;numeric;Abscisse en projection légale;data.gouv.fr;NA;numeric;Coordonnées cartographique en projection légale
+y;y;12;FALSE;numeric;Ordonnée en projection légale;data.gouv.fr;NA;numeric;Coordonnées cartographique en projection légale
+lon;lon;13;TRUE;numeric;Longitude en WGS-84;data.gouv.fr;NA;numeric;Longitude en WGS-84
+lat;lat;14;TRUE;numeric;Latitude en WGS-84;data.gouv.fr;NA;numeric;Latitude en WGS-84
+position_type;type_position;15;TRUE;factor;Type de position;data.gouv.fr;NA;factor;Type de position telle que définie dans la spécification du format d'échange BAL 1.3. Peut-être vide si inconnu ou non renseigné.
+alias;alias;16;FALSE;logical;Vide;data.gouv.fr;NA;logical;Vide
+locality_name;nom_ld;17;TRUE;character;Nom du lieu-dit de rattachement;data.gouv.fr;NA;character;Nom du lieu-dit de rattachement (ou autre type de toponyme)
+commune_name_postal;libelle_acheminement;18;FALSE;character;Nom de la commune d’acheminement;data.gouv.fr;NA;character;Nom de la commune d’acheminement
+address_street_postal;nom_afnor;19;FALSE;character;Nom postale de la voie;data.gouv.fr;NA;character;Nom de la voie normalisé selon la norme postale
+position_source;source_position;20;TRUE;factor;Source de la position géographique;data.gouv.fr;NA;factor;Source de la position géographique. Valeurs possibles : (commune, cadastre, arcep, laposte, insee, sdis, inconnue)
+address_source;source_nom_voie;21;FALSE;factor;Source du nom de la voie;data.gouv.fr;NA;factor;Source du nom de la voie. Valeurs possibles : (commune, cadastre, arcep, laposte, insee, sdis, inconnue)
+commune_certification;certification_commune;22;TRUE;logical;Certification par la commune;data.gouv.fr;NA;integer;Indique si l’adresse a été certifiée par la commune. Valeurs possibles : (1 pour oui, 0 pour non)
+registry_parcel;cad_parcelles;23;FALSE;character;Parcelles cadastrales;data.gouv.fr;NA;character;Liste les identifiants des parcelles cadastrales auxquelles l’adresse est rattachée, si l'information est connue. Codage de l’identifiant sur 14 caractères. Séparateur |. Donnée en cours de fiabilisation
diff --git a/inst/extdata/scheme_bd_topo_3.csv b/inst/extdata/scheme_bd_topo_3.csv
index 783d27b55ee58f3bba5d0ee4e3c68ab74b97d92f..3b1fd2f5108600e6d421606e7b0bcb4988546e29 100644
--- a/inst/extdata/scheme_bd_topo_3.csv
+++ b/inst/extdata/scheme_bd_topo_3.csv
@@ -1,60 +1,60 @@
-"name";"name_origin_gpkg";"name_origin_shp";"layer";"order";"keep";"type";"unit";"label_fr";"source";"length_source";"type_source";"comment"
-"id";"cleabs";"ID";"batiment";1;"TRUE";"character";"NA";"Identifiant du bâtiment";"IGN";"NA";"character";"Identifiant unique de l'objet"
-"nature";"nature";"NATURE";"batiment";2;"TRUE";"factor";"NA";"Nature du bâtiment";"IGN";"NA";"factor";"Attribut permettant de distinguer différents types de bâtiments selon leur architecture"
-"destination_principal";"usage_1";"USAGE1";"batiment";3;"TRUE";"factor";"NA";"Usage principal";"IGN";"NA";"factor";"Usage du bâtiment ou d'une partie du bâtiment"
-"destination_secondary";"usage_2";"USAGE2";"batiment";4;"TRUE";"factor";"NA";"Usage secondaire";"IGN";"NA";"factor";"Autre usage d'un bâtiment de fonction mixte"
-"building_light";"construction_legere";"LEGER";"batiment";5;"TRUE";"logical";"NA";"Construction légère";"IGN";"NA";"logical";"Indique qu'il s'agit d'une structure légère, non attachée au sol par l'intermédiaire de fondations, ou d'un bâtiment ou partie de bâtiment ouvert sur au moins un côté"
-"state";"etat_de_l_objet";"ETAT";"batiment";6;"TRUE";"factor";"NA";"État de l'objet bati";"IGN";"NA";"factor";"État ou stade de vie d'un objet qui, pour le thème bâti, peut être en projet, en construction, en service ou en ruine"
-"date_creation";"date_creation";"DATE_CREAT";"batiment";7;"TRUE";"Date";"NA";"Date de création";"IGN";"NA";"Date";"Date et heure à laquelle l'objet a été saisi pour la première fois dans la base de données de production de l'IGN"
-"date_update";"date_modification";"DATE_MAJ";"batiment";8;"TRUE";"Date";"NA";"Date de modification";"IGN";"NA";"Date";"Date et heure à laquelle l'objet a été modifié pour la dernière fois dans la base de données de production"
-"date_apparition";"date_d_apparition";"DATE_APP";"batiment";9;"TRUE";"Date";"NA";"Date d'apparition";"IGN";"NA";"Date";"Date de création, de construction ou d'apparition de l'objet, ou date la plus ancienne à laquelle on peut attester de sa présence sur le terrain. La date d'apparition est issue de la date de construction présente dans les fichiers MAJIC (données de la DGFIP)"
-"date_confirmation";"date_de_confirmation";"DATE_CONF";"batiment";10;"TRUE";"Date";"NA";"Date de confirmation";"IGN";"NA";"Date";"Date la plus récente à laquelle on peut attester de la présence de l'objet sur le terrain"
-"source";"sources";"SOURCE";"batiment";11;"TRUE";"character";"NA";"Sources";"IGN";"NA";"character";"Sources attestant l'existence de l'objet, éventuellement dans le cadre d'un partenariat : organisme, administration, fichier de référence"
-"source_id";"identifiants_sources";"ID_SOURCE";"batiment";12;"TRUE";"character";"NA";"Identifiants sources";"IGN";"NA";"character";"Identifiants de l'objet dans les répertoires des organismes consultés pour leur inventaire"
-"accuracy_planimetric";"precision_planimetrique";"PREC_PLANI";"batiment";13;"TRUE";"numeric";"m";"Précision planimétrique";"IGN";"NA";"numeric";"Précision altimétrique (en mètres) de la géométrie décrivant l'objet"
-"accuracy_altimetric";"precision_altimetrique";"PREC_ALTI";"batiment";14;"TRUE";"numeric";"m";"Précision altimétrique";"IGN";"NA";"numeric";"Précision planimétrique (en mètres) de la géométrie décrivant l'objet"
-"dwelling";"nombre_de_logements";"NB_LOGTS";"batiment";15;"TRUE";"integer";"NA";"Nombre de logements";"IGN";"NA";"integer";"Nombre de logement dans le bâtiment"
-"level";"nombre_d_etages";"NB_ETAGES";"batiment";16;"TRUE";"integer";"NA";"Nombre d'étages";"IGN";"NA";"integer";"Nombre total d'étages du bâtiment, rez-de-chaussée compris. Les sous-sol ne sont pas comptés"
-"material_wall";"materiaux_des_murs";"MAT_MURS";"batiment";17;"TRUE";"factor";"NA";"Matériaux des murs";"IGN";"NA";"character";"Code indiquant les matériaux des murs du bâtiment, issu des informations contenues dans les fichiers fonciers"
-"material_roof";"materiaux_de_la_toiture";"MAT_TOITS";"batiment";18;"TRUE";"factor";"NA";"Matériaux de la toiture";"IGN";"NA";"character";"Code indiquant les matériaux de la toiture du bâtiment, issu des informations contenues dans les fichiers fonciers"
-"height";"hauteur";"HAUTEUR";"batiment";19;"TRUE";"numeric";"m";"Hauteur";"IGN";"NA";"numeric";"Hauteur du bâtiment mesurée entre le sol et le point haut de la gouttière (altitude maximum de la polyligne décrivant le bâtiment), exprimée en mètres."
-"z_min_floor";"altitude_minimale_sol";"Z_MIN_SOL";"batiment";20;"TRUE";"numeric";"m";"Altitude minimale sol";"IGN";"NA";"numeric";"Altitude représentative au pied du bâtiment, du côté bas de la pente, exprimée en mètres"
-"z_min_roof";"altitude_minimale_toit";"Z_MIN_TOIT";"batiment";21;"TRUE";"numeric";"m";"Altitude minimale toit";"IGN";"NA";"numeric";"Altitude du toit du bâtiment au niveau de l'arête décrivant son contour, exprimée en mètres."
-"z_max_roof";"altitude_maximale_toit";"Z_MAX_TOIT";"batiment";22;"TRUE";"numeric";"m";"Altitude maximale toit";"IGN";"NA";"numeric";"Altitude qui correspond à la hauteur maximale du toit, c’est-à -dire au faîte du toit, exprimée en mètres."
-"z_max_floor";"altitude_maximale_sol";"Z_MAX_SOL";"batiment";23;"TRUE";"numeric";"m";"Altitude maximale sol";"IGN";"NA";"numeric";"Altitude qui correspond à l’altitude maximale située au pied d’un bâtiment, exprimée en mètres"
-"origin";"origine_du_batiment";"ORIGIN_BAT";"batiment";24;"TRUE";"factor";"NA";"Origine du bâtiment";"IGN";"NA";"factor";"Précise l'origine de la géométrie du bâtiment"
-"majic_quality";"appariement_fichiers_fonciers";"APP_FF";"batiment";25;"TRUE";"character";"NA";"Appariement fichiers fonciers";"IGN";"NA";"character";"Indicateur relatif à la fiabilité de l'appariement avec les fichiers fonciers"
-"id";"cleabs";"ID";"commune";1;"TRUE";"character";"NA";;"IGN";"NA";"character";"Identifiant unique de l'objet"
-"commune";"code_insee";"INSEE_COM";"commune";2;"TRUE";"factor";"NA";;"IGN";"NA";"character";"Il s’agit du numéro officiel attribué par l’INSEE à la Commune : il est composé de 5 chiffres, les deux premiers correspondant au numéro de Département"
-"district";"code_insee_de_l_arrondissement";"INSEE_ARR";"commune";3;"FALSE";"factor";"NA";;"IGN";"NA";"character";"Code INSEE de l'Arrondissement auquel appartient cette Commune"
-"territorial_authority";"code_insee_de_la_collectivite_t";"INSEE_COL";"commune";4;"FALSE";"factor";"NA";;"IGN";"NA";"character";"Code INSEE de la Collectivité territoriale de niveau départemental incluant cette Commune"
-"department";"code_insee_du_departement";"INSEE_DEP";"commune";5;"TRUE";"factor";"NA";;"IGN";"NA";"character";"Code INSEE du Département"
-"region";"code_insee_de_la_region";"INSEE_REG";"commune";6;"TRUE";"factor";"NA";;"IGN";"NA";"character";"Code INSEE de la Région à laquelle appartient la Commune concernée"
-"population";"population";"POPULATION";"commune";7;"TRUE";"integer";"NA";;"IGN";"NA";"integer";"Chiffre de population sans double compte"
-"area";"surface_en_ha";"SURFACE_HA";"commune";8;"TRUE";"integer";"ha";;"IGN";"NA";"integer";"Superficie cadastrale en hectares de la commune telle que donnée par l'INSEE"
-"date_creation";"date_creation";"DATE_CREAT";"commune";9;"FALSE";"Date";"NA";;"IGN";"NA";"Date";"Date et heure à laquelle l'objet a été saisi pour la première fois dans la base de données de production de l'IGN"
-"date_update";"date_modification";"DATE_MAJ";"commune";10;"FALSE";"Date";"NA";;"IGN";"NA";"Date";"Date et heure à laquelle l'objet a été modifié pour la dernière fois dans la base de données de production"
-"date_apparition";"date_d_apparition";"DATE_APP";"commune";11;"TRUE";"Date";"NA";;"IGN";"NA";"Date";"Date de création, de construction ou d'apparition de l'objet, ou date la plus ancienne à laquelle on peut attester de sa présence sur le terrain"
-"date_confirmation";"date_de_confirmation";"DATE_CONF";"commune";12;"TRUE";"Date";"NA";;"IGN";"NA";"Date";"Date la plus récente à laquelle on peut attester de la présence de l'objet sur le terrain"
-"postal_code";"code_postal";"CODE_POST";"commune";13;"TRUE";"factor";"NA";;"IGN";"NA";"character";"Code postal lié à la Commune"
-"name";"nom_officiel";"NOM";"commune";14;"TRUE";"character";"NA";;"IGN";"NA";"character";"Ce champ comporte le toponyme intégral (avec article s’il y a) de la Commune. Il est saisi en lettres majuscules et minuscules, toutes deux accentuées"
-"district_head";"chef_lieu_d_arrondissement";"CL_ARROND";"commune";15;"TRUE";"logical";"NA";;"IGN";"NA";"logical";"Indique si la commune est chef-lieu d'Arrondissement ou non"
-"territorial_authority_head";"chef_lieu_de_collectivite_terr";"CL_COLLTER";"commune";16;"TRUE";"logical";"NA";;"IGN";"NA";"logical";"Indique si la commune est chef-lieu d'une Collectivité territoriale ou non"
-"department_head";"chef_lieu_de_departement";"CL_DEPART";"commune";17;"TRUE";"logical";"NA";;"IGN";"NA";"logical";"Indique si la commune est chef-lieu d'un Département ou non"
-"region_head";"chef_lieu_de_region";"CL_REGION";"commune";18;"TRUE";"logical";"NA";;"IGN";"NA";"logical";"Indique si la commune est chef-lieu d'une Région ou non"
-"state_capital";"capitale_d_etat";"CAPITALE";"commune";19;"FALSE";"logical";"NA";;"IGN";"NA";"logical";"Indique si la commune est la capitale d'Etat ou non"
-"date_census";"date_du_recensement";"DATE_RCT";"commune";20;"TRUE";"Date";"NA";;"IGN";"NA";"Date";"Date du recensement correspondant au chiffre de population saisi dans le champ 'Population' (en 2007, ce champ prend la valeur '01/01/1999')"
-"institution_census";"organisme_recenseur";"RECENSEUR";"commune";21;"FALSE";"character";"NA";;"IGN";"NA";"character";"Organisme officiel fournissant les données de la population des unités administratives françaises"
-"siren_epci";"codes_siren_des_epci";"SIREN_EPCI";"commune";22;"FALSE";"character";"NA";;"IGN";"NA";"character";"code SIREN des EPCI à fiscalité propre auxquels appartient la Commune"
-"link_head";"lien_vers_chef_lieu";"ID_CH_LIEU";"commune";23;"FALSE";"character";"NA";;"IGN";"NA";;"Lien vers l’identifiant de la Zone d'habitation du chef-lieu duquel dépend la Commune"
-"link_administrative_authority";"liens_vers_autorite_administrat";"ID_AUT_ADM";"commune";24;"FALSE";"character";"NA";;"IGN";"NA";;"Lien vers la clé absolue de l'objet Zone d'activité ou d'intérêt, de Nature=""Mairie"", de la Commune concernée, lieu de l'autorité administrative communale"
-"siren";"code_siren";"CODE_SIREN";"commune";25;"FALSE";"character";"NA";;"IGN";"NA";"character";"Code SIREN de l'entité administrative"
-"id";"cleabs";"ID";"departement";1;"TRUE";"character";"NA";;"IGN";"NA";"character";"Identifiant unique de l'objet"
-"department";"code_insee";"INSEE_DEP";"departement";2;"FALSE";"factor";"NA";;"IGN";"NA";"character";"Code INSEE du Département"
-"region";"code_insee_de_la_region";"INSEE_REG";"departement";3;"TRUE";"factor";"NA";;"IGN";"NA";"character";"Code INSEE de la Région"
-"name";"nom_officiel";"NOM";"departement";4;"TRUE";"character";"NA";;"IGN";"NA";"character";"Nom du Département selon l'INSEE"
-"date_creation";"date_creation";"DATE_CREAT";"departement";5;"FALSE";"Date";"NA";;"IGN";"NA";"Date";"Date et heure à laquelle l'objet a été saisi pour la première fois dans la base de données de production de l'IGN"
-"date_update";"date_modification";"DATE_MAJ";"departement";6;"FALSE";"Date";"NA";;"IGN";"NA";"Date";"Date et heure à laquelle l'objet a été modifié pour la dernière fois dans la base de données de production"
-"date_apparition";"date_d_apparition";"DATE_APP";"departement";7;"TRUE";"Date";"NA";;"IGN";"NA";"Date";"Date de création, de construction ou d'apparition de l'objet, ou date la plus ancienne à laquelle on peut attester de sa présence sur le terrain"
-"date_confirmation";"date_de_confirmation";"DATE_CONF";"departement";8;"TRUE";"Date";"NA";;"IGN";"NA";"Date";"Date la plus récente à laquelle on peut attester de la présence de l'objet sur le terrain"
-"link_administrative_authority";"liens_vers_autorite_administrat";"ID_AUT_ADM";"departement";9;"FALSE";"character";"NA";;"IGN";"NA";;"Lien vers (clé absolue) de l'objet Zone d'activité ou d'intérêt de Nature='Préfecture' du département concerné"
+name;name_origin_gpkg;name_origin_shp;layer;order;keep;type;unit;label_fr;source;length_source;type_source;comment
+id;cleabs;ID;batiment;1;TRUE;character;NA;Identifiant du bâtiment;IGN;NA;character;Identifiant unique de l'objet
+nature;nature;NATURE;batiment;2;TRUE;factor;NA;Nature du bâtiment;IGN;NA;factor;Attribut permettant de distinguer différents types de bâtiments selon leur architecture
+destination_principal;usage_1;USAGE1;batiment;3;TRUE;factor;NA;Usage principal;IGN;NA;factor;Usage du bâtiment ou d'une partie du bâtiment
+destination_secondary;usage_2;USAGE2;batiment;4;TRUE;factor;NA;Usage secondaire;IGN;NA;factor;Autre usage d'un bâtiment de fonction mixte
+building_light;construction_legere;LEGER;batiment;5;TRUE;logical;NA;Construction légère;IGN;NA;logical;Indique qu'il s'agit d'une structure légère, non attachée au sol par l'intermédiaire de fondations, ou d'un bâtiment ou partie de bâtiment ouvert sur au moins un côté
+state;etat_de_l_objet;ETAT;batiment;6;TRUE;factor;NA;État de l'objet bati;IGN;NA;factor;État ou stade de vie d'un objet qui, pour le thème bâti, peut être en projet, en construction, en service ou en ruine
+date_creation;date_creation;DATE_CREAT;batiment;7;TRUE;Date;NA;Date de création;IGN;NA;Date;Date et heure à laquelle l'objet a été saisi pour la première fois dans la base de données de production de l'IGN
+date_update;date_modification;DATE_MAJ;batiment;8;TRUE;Date;NA;Date de modification;IGN;NA;Date;Date et heure à laquelle l'objet a été modifié pour la dernière fois dans la base de données de production
+date_apparition;date_d_apparition;DATE_APP;batiment;9;TRUE;Date;NA;Date d'apparition;IGN;NA;Date;Date de création, de construction ou d'apparition de l'objet, ou date la plus ancienne à laquelle on peut attester de sa présence sur le terrain. La date d'apparition est issue de la date de construction présente dans les fichiers MAJIC (données de la DGFIP)
+date_confirmation;date_de_confirmation;DATE_CONF;batiment;10;TRUE;Date;NA;Date de confirmation;IGN;NA;Date;Date la plus récente à laquelle on peut attester de la présence de l'objet sur le terrain
+source;sources;SOURCE;batiment;11;TRUE;character;NA;Sources;IGN;NA;character;Sources attestant l'existence de l'objet, éventuellement dans le cadre d'un partenariat : organisme, administration, fichier de référence
+source_id;identifiants_sources;ID_SOURCE;batiment;12;TRUE;character;NA;Identifiants sources;IGN;NA;character;Identifiants de l'objet dans les répertoires des organismes consultés pour leur inventaire
+accuracy_planimetric;precision_planimetrique;PREC_PLANI;batiment;13;TRUE;numeric;m;Précision planimétrique;IGN;NA;numeric;Précision altimétrique (en mètres) de la géométrie décrivant l'objet
+accuracy_altimetric;precision_altimetrique;PREC_ALTI;batiment;14;TRUE;numeric;m;Précision altimétrique;IGN;NA;numeric;Précision planimétrique (en mètres) de la géométrie décrivant l'objet
+dwelling;nombre_de_logements;NB_LOGTS;batiment;15;TRUE;integer;NA;Nombre de logements;IGN;NA;integer;Nombre de logement dans le bâtiment
+level;nombre_d_etages;NB_ETAGES;batiment;16;TRUE;integer;NA;Nombre d'étages;IGN;NA;integer;Nombre total d'étages du bâtiment, rez-de-chaussée compris. Les sous-sol ne sont pas comptés
+material_wall;materiaux_des_murs;MAT_MURS;batiment;17;TRUE;factor;NA;Matériaux des murs;IGN;NA;character;Code indiquant les matériaux des murs du bâtiment, issu des informations contenues dans les fichiers fonciers
+material_roof;materiaux_de_la_toiture;MAT_TOITS;batiment;18;TRUE;factor;NA;Matériaux de la toiture;IGN;NA;character;Code indiquant les matériaux de la toiture du bâtiment, issu des informations contenues dans les fichiers fonciers
+height;hauteur;HAUTEUR;batiment;19;TRUE;numeric;m;Hauteur;IGN;NA;numeric;Hauteur du bâtiment mesurée entre le sol et le point haut de la gouttière (altitude maximum de la polyligne décrivant le bâtiment), exprimée en mètres.
+z_min_floor;altitude_minimale_sol;Z_MIN_SOL;batiment;20;TRUE;numeric;m;Altitude minimale sol;IGN;NA;numeric;Altitude représentative au pied du bâtiment, du côté bas de la pente, exprimée en mètres
+z_min_roof;altitude_minimale_toit;Z_MIN_TOIT;batiment;21;TRUE;numeric;m;Altitude minimale toit;IGN;NA;numeric;Altitude du toit du bâtiment au niveau de l'arête décrivant son contour, exprimée en mètres.
+z_max_roof;altitude_maximale_toit;Z_MAX_TOIT;batiment;22;TRUE;numeric;m;Altitude maximale toit;IGN;NA;numeric;Altitude qui correspond à la hauteur maximale du toit, c’est-à -dire au faîte du toit, exprimée en mètres.
+z_max_floor;altitude_maximale_sol;Z_MAX_SOL;batiment;23;TRUE;numeric;m;Altitude maximale sol;IGN;NA;numeric;Altitude qui correspond à l’altitude maximale située au pied d’un bâtiment, exprimée en mètres
+origin;origine_du_batiment;ORIGIN_BAT;batiment;24;TRUE;factor;NA;Origine du bâtiment;IGN;NA;factor;Précise l'origine de la géométrie du bâtiment
+majic_quality;appariement_fichiers_fonciers;APP_FF;batiment;25;TRUE;character;NA;Appariement fichiers fonciers;IGN;NA;character;Indicateur relatif à la fiabilité de l'appariement avec les fichiers fonciers
+id;cleabs;ID;commune;1;TRUE;character;NA;;IGN;NA;character;Identifiant unique de l'objet
+commune;code_insee;INSEE_COM;commune;2;TRUE;factor;NA;;IGN;NA;character;Il s’agit du numéro officiel attribué par l’INSEE à la Commune : il est composé de 5 chiffres, les deux premiers correspondant au numéro de Département
+district;code_insee_de_l_arrondissement;INSEE_ARR;commune;3;FALSE;factor;NA;;IGN;NA;character;Code INSEE de l'Arrondissement auquel appartient cette Commune
+territorial_authority;code_insee_de_la_collectivite_t;INSEE_COL;commune;4;FALSE;factor;NA;;IGN;NA;character;Code INSEE de la Collectivité territoriale de niveau départemental incluant cette Commune
+department;code_insee_du_departement;INSEE_DEP;commune;5;TRUE;factor;NA;;IGN;NA;character;Code INSEE du Département
+region;code_insee_de_la_region;INSEE_REG;commune;6;TRUE;factor;NA;;IGN;NA;character;Code INSEE de la Région à laquelle appartient la Commune concernée
+population;population;POPULATION;commune;7;TRUE;integer;NA;;IGN;NA;integer;Chiffre de population sans double compte
+area;surface_en_ha;SURFACE_HA;commune;8;TRUE;integer;ha;;IGN;NA;integer;Superficie cadastrale en hectares de la commune telle que donnée par l'INSEE
+date_creation;date_creation;DATE_CREAT;commune;9;FALSE;Date;NA;;IGN;NA;Date;Date et heure à laquelle l'objet a été saisi pour la première fois dans la base de données de production de l'IGN
+date_update;date_modification;DATE_MAJ;commune;10;FALSE;Date;NA;;IGN;NA;Date;Date et heure à laquelle l'objet a été modifié pour la dernière fois dans la base de données de production
+date_apparition;date_d_apparition;DATE_APP;commune;11;TRUE;Date;NA;;IGN;NA;Date;Date de création, de construction ou d'apparition de l'objet, ou date la plus ancienne à laquelle on peut attester de sa présence sur le terrain
+date_confirmation;date_de_confirmation;DATE_CONF;commune;12;TRUE;Date;NA;;IGN;NA;Date;Date la plus récente à laquelle on peut attester de la présence de l'objet sur le terrain
+postal_code;code_postal;CODE_POST;commune;13;TRUE;factor;NA;;IGN;NA;character;Code postal lié à la Commune
+name;nom_officiel;NOM;commune;14;TRUE;character;NA;;IGN;NA;character;Ce champ comporte le toponyme intégral (avec article s’il y a) de la Commune. Il est saisi en lettres majuscules et minuscules, toutes deux accentuées
+district_head;chef_lieu_d_arrondissement;CL_ARROND;commune;15;TRUE;logical;NA;;IGN;NA;logical;Indique si la commune est chef-lieu d'Arrondissement ou non
+territorial_authority_head;chef_lieu_de_collectivite_terr;CL_COLLTER;commune;16;TRUE;logical;NA;;IGN;NA;logical;Indique si la commune est chef-lieu d'une Collectivité territoriale ou non
+department_head;chef_lieu_de_departement;CL_DEPART;commune;17;TRUE;logical;NA;;IGN;NA;logical;Indique si la commune est chef-lieu d'un Département ou non
+region_head;chef_lieu_de_region;CL_REGION;commune;18;TRUE;logical;NA;;IGN;NA;logical;Indique si la commune est chef-lieu d'une Région ou non
+state_capital;capitale_d_etat;CAPITALE;commune;19;FALSE;logical;NA;;IGN;NA;logical;Indique si la commune est la capitale d'Etat ou non
+date_census;date_du_recensement;DATE_RCT;commune;20;TRUE;Date;NA;;IGN;NA;Date;Date du recensement correspondant au chiffre de population saisi dans le champ 'Population' (en 2007, ce champ prend la valeur '01/01/1999')
+institution_census;organisme_recenseur;RECENSEUR;commune;21;FALSE;character;NA;;IGN;NA;character;Organisme officiel fournissant les données de la population des unités administratives françaises
+siren_epci;codes_siren_des_epci;SIREN_EPCI;commune;22;FALSE;character;NA;;IGN;NA;character;code SIREN des EPCI à fiscalité propre auxquels appartient la Commune
+link_head;lien_vers_chef_lieu;ID_CH_LIEU;commune;23;FALSE;character;NA;;IGN;NA;character;Lien vers l’identifiant de la Zone d'habitation du chef-lieu duquel dépend la Commune
+link_administrative_authority;liens_vers_autorite_administrat;ID_AUT_ADM;commune;24;FALSE;character;NA;;IGN;NA;character;Lien vers la clé absolue de l'objet Zone d'activité ou d'intérêt, de Nature=Mairie, de la Commune concernée, lieu de l'autorité administrative communale
+siren;code_siren;CODE_SIREN;commune;25;FALSE;character;NA;;IGN;NA;character;Code SIREN de l'entité administrative
+id;cleabs;ID;departement;1;TRUE;character;NA;;IGN;NA;character;Identifiant unique de l'objet
+department;code_insee;INSEE_DEP;departement;2;FALSE;factor;NA;;IGN;NA;character;Code INSEE du Département
+region;code_insee_de_la_region;INSEE_REG;departement;3;TRUE;factor;NA;;IGN;NA;character;Code INSEE de la Région
+name;nom_officiel;NOM;departement;4;TRUE;character;NA;;IGN;NA;character;Nom du Département selon l'INSEE
+date_creation;date_creation;DATE_CREAT;departement;5;FALSE;Date;NA;;IGN;NA;Date;Date et heure à laquelle l'objet a été saisi pour la première fois dans la base de données de production de l'IGN
+date_update;date_modification;DATE_MAJ;departement;6;FALSE;Date;NA;;IGN;NA;Date;Date et heure à laquelle l'objet a été modifié pour la dernière fois dans la base de données de production
+date_apparition;date_d_apparition;DATE_APP;departement;7;TRUE;Date;NA;;IGN;NA;Date;Date de création, de construction ou d'apparition de l'objet, ou date la plus ancienne à laquelle on peut attester de sa présence sur le terrain
+date_confirmation;date_de_confirmation;DATE_CONF;departement;8;TRUE;Date;NA;;IGN;NA;Date;Date la plus récente à laquelle on peut attester de la présence de l'objet sur le terrain
+link_administrative_authority;liens_vers_autorite_administrat;ID_AUT_ADM;departement;9;FALSE;character;NA;;IGN;NA;character;Lien vers (clé absolue) de l'objet Zone d'activité ou d'intérêt de Nature='Préfecture' du département concerné
diff --git a/inst/extdata/scheme_gaspar_azi.csv b/inst/extdata/scheme_gaspar_azi.csv
index b3be6bb3457f2c5281f9f9d0fb35087b589bb808..702b01ede7df1251edba111faa75f3d562fa55a8 100644
--- a/inst/extdata/scheme_gaspar_azi.csv
+++ b/inst/extdata/scheme_gaspar_azi.csv
@@ -1,17 +1,17 @@
name;name_origin;order;keep;type;label_fr;source;length_source;type_source;comment
-id;cod_nat_azi;1;TRUE;character;ID de l’atlas;georisques;;text;
-azi_label_fr;lib_azi;2;TRUE;character;nom de l’atlas;georisques;;text;
-catchment_label_fr;lib_bassin_risque;3;TRUE;character;nom du bassin de risque;georisques;;text;
-hazard_label_fr;liste_risques;4;TRUE;factor;libellé du risque;georisques;;text;
-commune;cod_commune;5;TRUE;factor;code INSEE de la commune;georisques;;text;
-commune_label_fr;lib_commune;6;FALSE;factor;nom de la commune concernée;georisques;;text;
-date_program_start;dat_program_deb;7;TRUE;date;date de début de programmation;georisques;;text;
-date_program_end;dat_program_fin;8;TRUE;date;date de fin de programmation;georisques;;text;
-date_study_start;dat_etu_deb;9;TRUE;date;date de début des études;georisques;;text;
-date_study_end;dat_etu_fin;10;TRUE;date;date de fin des études;georisques;;text;
-date_info_start;dat_info_deb;11;TRUE;date;date de début d’information des communes;georisques;;text;
-date_info_end;dat_info_fin;12;TRUE;date;date de fin d’information des communes;georisques;;text;
-date_atlas;dat_realisation;13;TRUE;date;date de réalisation de l’atlas;georisques;;text;
-date_access;dat_diffusion;14;TRUE;date;date de diffusion de l’atlas;georisques;;text;
-date_internet;dat_pub_net;15;TRUE;date;date de publication sur Internet;georisques;;text;
-date_update;dat_maj;16;TRUE;date;date de mise à jour de la fiche gaspar;georisques;;text;
+id;cod_nat_azi;1;TRUE;character;ID de l’atlas;georisques;;character;
+azi_label_fr;lib_azi;2;TRUE;character;nom de l’atlas;georisques;;character;
+catchment_label_fr;lib_bassin_risque;3;TRUE;character;nom du bassin de risque;georisques;;character;
+hazard_label_fr;liste_risques;4;TRUE;factor;libellé du risque;georisques;;character;
+commune;cod_commune;5;TRUE;factor;code INSEE de la commune;georisques;;character;
+commune_label_fr;lib_commune;6;FALSE;factor;nom de la commune concernée;georisques;;character;
+date_program_start;dat_program_deb;7;TRUE;Date;date de début de programmation;georisques;;character;
+date_program_end;dat_program_fin;8;TRUE;Date;date de fin de programmation;georisques;;character;
+date_study_start;dat_etu_deb;9;TRUE;Date;date de début des études;georisques;;character;
+date_study_end;dat_etu_fin;10;TRUE;Date;date de fin des études;georisques;;character;
+date_info_start;dat_info_deb;11;TRUE;Date;date de début d’information des communes;georisques;;character;
+date_info_end;dat_info_fin;12;TRUE;Date;date de fin d’information des communes;georisques;;character;
+date_atlas;dat_realisation;13;TRUE;Date;date de réalisation de l’atlas;georisques;;character;
+date_access;dat_diffusion;14;TRUE;Date;date de diffusion de l’atlas;georisques;;character;
+date_internet;dat_pub_net;15;TRUE;Date;date de publication sur Internet;georisques;;character;
+date_update;dat_maj;16;TRUE;Date;date de mise à jour de la fiche gaspar;georisques;;character;
diff --git a/inst/extdata/scheme_gaspar_catnat.csv b/inst/extdata/scheme_gaspar_catnat.csv
index a2b6b44245df13f46fcff6aee99692f92da13bc9..ecb61fb41f9bb8d333229b5584510658013b9fb5 100644
--- a/inst/extdata/scheme_gaspar_catnat.csv
+++ b/inst/extdata/scheme_gaspar_catnat.csv
@@ -1,11 +1,11 @@
name;name_origin;order;keep;type;label_fr;source;length_source;type_source;comment
-id;cod_nat_catnat;1;TRUE;character;ID de l’arrêté;georisques;;text;
-commune;cod_commune;2;TRUE;factor;code INSEE de la commune;georisques;;text;
-commune_label_fr;lib_commune;3;FALSE;factor;nom de la commune;georisques;;text;
+id;cod_nat_catnat;1;TRUE;character;ID de l’arrêté;georisques;;character;
+commune;cod_commune;2;TRUE;factor;code INSEE de la commune;georisques;;character;
+commune_label_fr;lib_commune;3;FALSE;factor;nom de la commune;georisques;;character;
catnat;num_risque_jo;4;TRUE;factor;code du type d’événement;georisques;;integer;
-catnat_label_fr;lib_risque_jo;5;TRUE;factor;intitulé du type d’événement;georisques;;text;
-date_start;dat_deb;6;TRUE;date;date de début de l’événement;georisques;;text;
-date_end;dat_fin;7;TRUE;date;date de fin de l’événement;georisques;;text;
-date_decree;dat_pub_arrete;8;TRUE;date;date de l’arrếté;georisques;;text;
-date_jo;dat_pub_jo;9;TRUE;date;date de publication au journal officiel;georisques;;text;
-date_update;dat_maj;10;TRUE;date;date de mise à jour de la fiche gaspar;georisques;;text;
+catnat_label_fr;lib_risque_jo;5;TRUE;factor;intitulé du type d’événement;georisques;;character;
+date_start;dat_deb;6;TRUE;Date;date de début de l’événement;georisques;;character;
+date_end;dat_fin;7;TRUE;Date;date de fin de l’événement;georisques;;character;
+date_decree;dat_pub_arrete;8;TRUE;Date;date de l’arrếté;georisques;;character;
+date_jo;dat_pub_jo;9;TRUE;Date;date de publication au journal officiel;georisques;;character;
+date_update;dat_maj;10;TRUE;Date;date de mise à jour de la fiche gaspar;georisques;;character;
diff --git a/inst/extdata/scheme_gaspar_dicrim.csv b/inst/extdata/scheme_gaspar_dicrim.csv
index c94d71bd1ff05183feab28648a74903a188f75be..5499b17e465c7fcf98ce87751a14d7298fbd7e0d 100644
--- a/inst/extdata/scheme_gaspar_dicrim.csv
+++ b/inst/extdata/scheme_gaspar_dicrim.csv
@@ -1,4 +1,4 @@
-name,name_origin,order,keep,type,label_fr,source,length_source,type_source,comment
-commune,cod_commune,1,TRUE,factor,code INSEE de la commune,georisques,,text,
-commune_label_fr,lib_commune,2,FALSE,factor,nom de la commune concernée,georisques,,text,
-dat_publi_dicrim,dat_publi_dicrim,3,TRUE,date,date de publication du DICRIM,georisques,,text,
+name;name_origin;order;keep;type;label_fr;source;length_source;type_source;comment
+commune;cod_commune;1;TRUE;factor;code INSEE de la commune;georisques;;character;
+commune_label_fr;lib_commune;2;FALSE;factor;nom de la commune concernée;georisques;;character;
+dat_publi_dicrim;dat_publi_dicrim;3;TRUE;Date;date de publication du DICRIM;georisques;;character;
diff --git a/inst/extdata/scheme_gaspar_pcs.csv b/inst/extdata/scheme_gaspar_pcs.csv
index 9445e9fac45a87811d025d4ee72bf36edbf44dae..f48e7cc0604cc04ab928ca9bae26c49948aed616 100644
--- a/inst/extdata/scheme_gaspar_pcs.csv
+++ b/inst/extdata/scheme_gaspar_pcs.csv
@@ -1,10 +1,10 @@
-name,name_origin,order,keep,type,label_fr,source,length_source,type_source,comment
-id,cod_nat_pcs,1,TRUE,character,id du pcs,georisques,,text,
-pcs_label_fr,lib_pcs,2,TRUE,character,nom du pcs,georisques,,text,
-commune,cod_commune,3,TRUE,factor,code INSEE de la commune,georisques,,text,
-commune_label_fr,lib_commune,4,FALSE,factor,nom de la commune concernée,georisques,,text,
-catchment_label_fr,lib_bassin_risque,5,TRUE,character,nom du bassin de risque,georisques,,text,
-date_etu_start,dat_etu_pcs_deb,6,TRUE,date,date de début de l’etude du pcs,georisques,,text,
-date_etu_end,dat_etu_pcs_fin,7,TRUE,date,date de fin de l’etude du pcs,georisques,,text,
-dat_notif_fin,dat_notification_pcs_fin,8,TRUE,date,date de notification du pcs,georisques,,text,
-date_update,dat_maj,9,TRUE,date,date de mise à jour de la fiche gaspar,georisques,,text,
+name;name_origin;order;keep;type;label_fr;source;length_source;type_source;comment
+id;cod_nat_pcs;1;TRUE;character;id du pcs;georisques;;character;
+pcs_label_fr;lib_pcs;2;TRUE;character;nom du pcs;georisques;;character;
+commune;cod_commune;3;TRUE;factor;code INSEE de la commune;georisques;;character;
+commune_label_fr;lib_commune;4;FALSE;factor;nom de la commune concernée;georisques;;character;
+catchment_label_fr;lib_bassin_risque;5;TRUE;character;nom du bassin de risque;georisques;;character;
+date_etu_start;dat_etu_pcs_deb;6;TRUE;Date;date de début de l’etude du pcs;georisques;;character;
+date_etu_end;dat_etu_pcs_fin;7;TRUE;Date;date de fin de l’etude du pcs;georisques;;character;
+dat_notif_fin;dat_notification_pcs_fin;8;TRUE;Date;date de notification du pcs;georisques;;character;
+date_update;dat_maj;9;TRUE;Date;date de mise à jour de la fiche gaspar;georisques;;character;
diff --git a/inst/extdata/scheme_gaspar_pprn.csv b/inst/extdata/scheme_gaspar_pprn.csv
index 5649314a71f10b1ed0691cca7151d9b966e10269..b5451d6a0d40c7c2fc9c038679e376ada54d00b6 100644
--- a/inst/extdata/scheme_gaspar_pprn.csv
+++ b/inst/extdata/scheme_gaspar_pprn.csv
@@ -1,44 +1,44 @@
name;name_origin;order;keep;type;label_fr;source;length_source;type_source;comment
-id;cod_nat_pprn;1;TRUE;character;ID du PPRN;georisques;;text;
-pprn_label_fr;lib_pprn;2;TRUE;factor;libellé du PPRN;georisques;;text;
-catchment_label_fr;lib_bassin_risques;3;TRUE;factor;libellé du bassin de risque;georisques;;text;
+id;cod_nat_pprn;1;TRUE;character;ID du PPRN;georisques;;character;
+pprn_label_fr;lib_pprn;2;TRUE;factor;libellé du PPRN;georisques;;character;
+catchment_label_fr;lib_bassin_risques;3;TRUE;factor;libellé du bassin de risque;georisques;;character;
hazard;num_risque;4;TRUE;factor;code du risque;georisques;;integer;
-hazard_label_fr;lib_risque;5;TRUE;factor;libellé du risque;georisques;;text;
-pprn_revised;list_codenat_ppr_revise;6;TRUE;list;code du PPRN révisé;georisques;;text;
-commune;cod_commune;7;TRUE;factor;code INSEE de la commune;georisques;;text;
-commune_label_fr;lib_commune;8;FALSE;factor;nom de la commune;georisques;;text;
-comment;lib_commentaire;9;TRUE;character;commentaire;georisques;;text;
-type_label_fr;cod_ppr;10;TRUE;factor;code du PPRN;georisques;;text;
-;dat_program_deb;11;FALSE;date;date de début prévisionnel de l'élaboration;georisques;;text;
-;dat_program_fin;12;FALSE;date;date de fin prévisionnelle de l'élaboration;georisques;;text;
-;dat_montage_deb;13;FALSE;date;date de début de réflexion de l'élaboration;georisques;;text;
-;dat_montage_fin;14;FALSE;date;date de fin de réflexion de l'élaboration;georisques;;text;
-date_prescription;dat_prescription;15;TRUE;date;date de l'arrêté préfectoral portant prescription;georisques;;text;
-date_anticipated;dat_appli_ant;16;TRUE;date;date de l'arrêté préfectoral portant application anticipée;georisques;;text;
-date_deprescription;dat_deprescription;17;TRUE;date;date de l'arrêté préfectoral portant déprescription;georisques;;text;
-;dat_etu_hydro_deb;18;FALSE;date;date de début de réalisation des études hydrologiques et hydrauliques;georisques;;text;
-;dat_etu_hydro_fin;19;FALSE;date;date de fin de réalisation des études hydrologiques et hydrauliques;georisques;;text;
-;dat_etu_alea_deb;20;FALSE;date;date de début de l'élaboration des cartes d’aléas;georisques;;text;
-;dat_etu_alea_fin;21;FALSE;date;date de fin de l'élaboration des cartes d’aléas;georisques;;text;
-;dat_etu_enjeu_deb;22;FALSE;date;date de début de l'élaboration des cartes d’enjeux;georisques;;text;
-;dat_etu_enjeu_fin;23;FALSE;date;date de fin de l'élaboration des cartes d’enjeux;georisques;;text;
-;dat_etu_zona_regl_deb;24;FALSE;date;date de début de l'élaboration du zonage réglementaire;georisques;;text;
-;dat_etu_zona_regl_fin;25;FALSE;date;date de fin de l'élaboration du zonage réglementaire;georisques;;text;
-;dat_etu_rglmt_deb;26;FALSE;date;date de début de la rédaction de la notice de présentation et du règlement;georisques;;text;
-;dat_etu_rglmt_fin;27;FALSE;date;date de fin de la rédaction de la notice de présentation et du règlement;georisques;;text;
-;dat_concertation_deb;28;FALSE;date;date de début de la concertation;georisques;;text;
-;dat_concertation_fin;29;FALSE;date;date de fin de la concertation;georisques;;text;
-;dat_consultation_deb;30;FALSE;date;date de début de la consultation;georisques;;text;
-;dat_consultation_fin;31;FALSE;date;date de fin de la consultation;georisques;;text;
-;dat_consult_serv_deb;32;FALSE;date;date de début de la consultation des services;georisques;;text;
-;dat_consult_serv_fin;33;FALSE;date;date de fin de la consultation des services;georisques;;text;
-date_mise_a_enquete_deb;dat_mise_a_enquete_deb;34;TRUE;date;date d’ouverture de l’enquête publique;georisques;;text;
-date_mise_a_enquete_fin;dat_mise_a_enquete_fin;35;TRUE;date;date de fermeture de l’enquête publique;georisques;;text;
-date_approval;dat_approbation;36;TRUE;date;date de l'arrêté préfectoral portant approbation;georisques;;text;
-date_amendment;dat_modification;37;TRUE;date;date de l'arrêté préfectoral prescrivant une modification;georisques;;text;
-date_cancellation;dat_annulation;38;TRUE;date;date de la décision d'annulation du Tribunal Administratif;georisques;;text;
-date_plu;dat_annexion_plu;39;TRUE;date;date de l'arrêté municipal annexant le PPR au PLU;georisques;;text;
-date_extension;dat_proroga;40;TRUE;date;date de l'arrêté préfectoral prorogeant de 18 mois la date de prescription;georisques;;text;
-date_repeal;dat_abrog;41;TRUE;date;date de l'arrêté préfectoral portant abrogation;georisques;;text;
-revision;etat_revision;42;TRUE;logical;Indique si le PPR a été révisé ou non;georisques;;text;
-date_update;dat_maj;43;TRUE;date;date de mise à jour de la fiche gaspar;georisques;;text;
+hazard_label_fr;lib_risque;5;TRUE;factor;libellé du risque;georisques;;character;
+pprn_revised;list_codenat_ppr_revise;6;TRUE;list;code du PPRN révisé;georisques;;character;
+commune;cod_commune;7;TRUE;factor;code INSEE de la commune;georisques;;character;
+commune_label_fr;lib_commune;8;FALSE;factor;nom de la commune;georisques;;character;
+comment;lib_commentaire;9;TRUE;character;commentaire;georisques;;character;
+type_label_fr;cod_ppr;10;TRUE;factor;code du PPRN;georisques;;character;
+;dat_program_deb;11;FALSE;Date;date de début prévisionnel de l'élaboration;georisques;;character;
+;dat_program_fin;12;FALSE;Date;date de fin prévisionnelle de l'élaboration;georisques;;character;
+;dat_montage_deb;13;FALSE;Date;date de début de réflexion de l'élaboration;georisques;;character;
+;dat_montage_fin;14;FALSE;Date;date de fin de réflexion de l'élaboration;georisques;;character;
+date_prescription;dat_prescription;15;TRUE;Date;date de l'arrêté préfectoral portant prescription;georisques;;character;
+date_anticipated;dat_appli_ant;16;TRUE;Date;date de l'arrêté préfectoral portant application anticipée;georisques;;character;
+date_deprescription;dat_deprescription;17;TRUE;Date;date de l'arrêté préfectoral portant déprescription;georisques;;character;
+;dat_etu_hydro_deb;18;FALSE;Date;date de début de réalisation des études hydrologiques et hydrauliques;georisques;;character;
+;dat_etu_hydro_fin;19;FALSE;Date;date de fin de réalisation des études hydrologiques et hydrauliques;georisques;;character;
+;dat_etu_alea_deb;20;FALSE;Date;date de début de l'élaboration des cartes d’aléas;georisques;;character;
+;dat_etu_alea_fin;21;FALSE;Date;date de fin de l'élaboration des cartes d’aléas;georisques;;character;
+;dat_etu_enjeu_deb;22;FALSE;Date;date de début de l'élaboration des cartes d’enjeux;georisques;;character;
+;dat_etu_enjeu_fin;23;FALSE;Date;date de fin de l'élaboration des cartes d’enjeux;georisques;;character;
+;dat_etu_zona_regl_deb;24;FALSE;Date;date de début de l'élaboration du zonage réglementaire;georisques;;character;
+;dat_etu_zona_regl_fin;25;FALSE;Date;date de fin de l'élaboration du zonage réglementaire;georisques;;character;
+;dat_etu_rglmt_deb;26;FALSE;Date;date de début de la rédaction de la notice de présentation et du règlement;georisques;;character;
+;dat_etu_rglmt_fin;27;FALSE;Date;date de fin de la rédaction de la notice de présentation et du règlement;georisques;;character;
+;dat_concertation_deb;28;FALSE;Date;date de début de la concertation;georisques;;character;
+;dat_concertation_fin;29;FALSE;Date;date de fin de la concertation;georisques;;character;
+;dat_consultation_deb;30;FALSE;Date;date de début de la consultation;georisques;;character;
+;dat_consultation_fin;31;FALSE;Date;date de fin de la consultation;georisques;;character;
+;dat_consult_serv_deb;32;FALSE;Date;date de début de la consultation des services;georisques;;character;
+;dat_consult_serv_fin;33;FALSE;Date;date de fin de la consultation des services;georisques;;character;
+date_mise_a_enquete_deb;dat_mise_a_enquete_deb;34;TRUE;Date;date d’ouverture de l’enquête publique;georisques;;character;
+date_mise_a_enquete_fin;dat_mise_a_enquete_fin;35;TRUE;Date;date de fermeture de l’enquête publique;georisques;;character;
+date_approval;dat_approbation;36;TRUE;Date;date de l'arrêté préfectoral portant approbation;georisques;;character;
+date_amendment;dat_modification;37;TRUE;Date;date de l'arrêté préfectoral prescrivant une modification;georisques;;character;
+date_cancellation;dat_annulation;38;TRUE;Date;date de la décision d'annulation du Tribunal Administratif;georisques;;character;
+date_plu;dat_annexion_plu;39;TRUE;Date;date de l'arrêté municipal annexant le PPR au PLU;georisques;;character;
+date_extension;dat_proroga;40;TRUE;Date;date de l'arrêté préfectoral prorogeant de 18 mois la date de prescription;georisques;;character;
+date_repeal;dat_abrog;41;TRUE;Date;date de l'arrêté préfectoral portant abrogation;georisques;;character;
+revision;etat_revision;42;TRUE;logical;Indique si le PPR a été révisé ou non;georisques;;character;
+date_update;dat_maj;43;TRUE;Date;date de mise à jour de la fiche gaspar;georisques;;character;
diff --git a/inst/extdata/scheme_gaspar_risq.csv b/inst/extdata/scheme_gaspar_risq.csv
index b32ae506784fe2a94e2246b00f2ce610cf1fcab9..c9026816b3a3af7d94ffc4299721bbb269c9d8d5 100644
--- a/inst/extdata/scheme_gaspar_risq.csv
+++ b/inst/extdata/scheme_gaspar_risq.csv
@@ -1,4 +1,4 @@
name;name_origin;order;keep;type;label_fr;source;length_source;type_source;comment
-commune;cod_commune;2;TRUE;factor;code INSEE de la commune;georisques;;text;
-commune_label_fr;lib_commune;3;FALSE;factor;nom de la commune concernée;georisques;;text;
-hazard_label_fr;lib_risque_long;4;TRUE;factor;libellé complet du risque;georisques;;text;
+commune;cod_commune;2;TRUE;factor;code INSEE de la commune;georisques;;character;
+commune_label_fr;lib_commune;3;FALSE;factor;nom de la commune concernée;georisques;;character;
+hazard_label_fr;lib_risque_long;4;TRUE;factor;libellé complet du risque;georisques;;character;
diff --git a/inst/extdata/scheme_insee_logement_2019.csv b/inst/extdata/scheme_insee_logement_2019.csv
index 735023161f362221f3fdcb59cc489d53d307d34c..6307ffb6d3916d217060b2c5505d9a07256323a6 100644
--- a/inst/extdata/scheme_insee_logement_2019.csv
+++ b/inst/extdata/scheme_insee_logement_2019.csv
@@ -1,8 +1,8 @@
-"name";"name_origin";"order";"keep";"type";"label_fr";"source";"length_source";"type_source";"comment"
-"niv_geo";"NIVGEO";1;"FALSE";"character";"niveau administratif";"insee.fr";"NA";"character";"niveau administratif groupant les données."
-"commune";"CODGEO";2;"TRUE";"character";"Code INSEE";"insee.fr";"NA";"character";"Code INSEE de la commune actuelle sur la base du Code Officiel géographique en vigueur"
-"commune_name";"LIBGEO";3;"FALSE";"character";"Nom officiel de la commune";"insee.fr";"NA";"character";"Nom officiel de la commune actuelle"
-"usage";"CATL";4;"FALSE";"factor";"Catégorie de logement";"insee.fr";"NA";"integer";"Catégorie de logement : 1) résidences principales; 2)logements occasionnels; 3)résidences secondaires; 4)logements vacants"
-"period";"ACHL20";5;"TRUE";"factor";"Epoque d'achèvement de la construction";"insee.fr";"NA";"character";"Epoque d'achèvement de la construction : A11) Avant 1919; A12) De 1919 à 1945; B11) De 1946 à 1970; B12) De 1971 à 1990; C100) De 1991 à 2005; C106P) De 2006 à 2015"
-"type";"TYPLR";6;"TRUE";"factor";"Type de logement";"insee.fr";"NA";"integer";"Type de logement : 1) maisons; 2) appartements; 3) autres"
-"dwelling";"NB";7;"TRUE";"numeric";"Nombre de logements";"insee.fr";"NA";"character";"Nombre de logements. Pour une raison inconnue le nombre contient des chiffres decimaux"
+name;name_origin;order;keep;type;label_fr;source;length_source;type_source;comment
+niv_geo;NIVGEO;1;FALSE;character;niveau administratif;insee.fr;NA;character;
+commune;CODGEO;2;TRUE;character;Code INSEE;insee.fr;NA;character;
+commune_name;LIBGEO;3;FALSE;character;Nom officiel de la commune;insee.fr;NA;character;
+usage;CATL;4;FALSE;factor;Catégorie de logement;insee.fr;NA;integer;(1 : résidences principales, 2 : logements occasionnels, 3 : résidences secondaires, 4 : logements vacants)
+period;ACHL20;5;TRUE;factor;Époque d'achèvement de la construction;insee.fr;NA;character;(A11 : avant 1919, A12 : 1919 à 1945, B11 : 1946 à 1970, B12 : 1971 à 1990, C100 : 1991 à 2005, C106P : 2006 à 2015)
+type;TYPLR;6;TRUE;factor;Type de logement;insee.fr;NA;integer;(1 : maisons, 2 : appartements, 3 : autres)
+dwelling;NB;7;TRUE;numeric;Nombre de logements;insee.fr;NA;character;Pour une raison non documentée le nombre contient des chiffres décimaux
diff --git a/inst/extdata/scheme_rpg_1.csv b/inst/extdata/scheme_rpg_1.csv
index b9c4e45268178bff26ed4057f419648f5c7f946a..13af69b767892e93522ab39d40e1f98235aedead 100644
--- a/inst/extdata/scheme_rpg_1.csv
+++ b/inst/extdata/scheme_rpg_1.csv
@@ -1,10 +1,10 @@
-"name";"name_origin";"layer";"order";"keep";"type";"label_fr";"source";"length_source";"type_source";"comment"
-"ilot";"NUM_ILOT";"ILOTS_ANONYMES";1;"FALSE";"character";"ID de l’ilôt";"IGN";;"text";
-"commune";"COMMUNE";"ILOTS_ANONYMES";2;"FALSE";"factor";"Commune de rattachement de la parcelle";"IGN";;"text";
-"juridical";"FORME_JURI";"ILOTS_ANONYMES";3;"FALSE";"factor";"Forme juridique de l’exploitation";"IGN";;"text";
-"surface_declared";"SURF_DECLA";"ILOTS_ANONYMES";4;"FALSE";"numeric";"Surface déclarée";"IGN";;"numeric";
-"department";"DEP_RATTACH";"ILOTS_ANONYMES";5;"FALSE";"factor";"Département de rattachement de la parcelle";"IGN";;"text";
-"surface_graph";"SURF_GRAPH";"ILOTS_ANONYMES";6;"FALSE";"numeric";"Surface d’origine de la parcelle graphique";"IGN";;"numeric";
-"surface";"SURF_CULTU";"ILOTS_ANONYMES";7;"TRUE";"numeric";"Surface d’origine de la parcelle graphique";"IGN";;"numeric";
-"group";"CODE_CULTU";"ILOTS_ANONYMES";8;"TRUE";"factor";"Code du groupe de la culture présente";"IGN";;"text";
-"group.label.fr";"NOM_CULTU";"ILOTS_ANONYMES";9;"FALSE";"factor";"Étiquette du groupe de la culture présente";"IGN";;"text";
+name;name_origin;layer;order;keep;type;label_fr;source;length_source;type_source;comment
+ilot;NUM_ILOT;ILOTS_ANONYMES;1;FALSE;character;ID de l’ilôt;IGN;;character;
+commune;COMMUNE;ILOTS_ANONYMES;2;FALSE;factor;Commune de rattachement de la parcelle;IGN;;character;
+juridical;FORME_JURI;ILOTS_ANONYMES;3;FALSE;factor;Forme juridique de l’exploitation;IGN;;character;
+surface_declared;SURF_DECLA;ILOTS_ANONYMES;4;FALSE;numeric;Surface déclarée;IGN;;numeric;
+department;DEP_RATTACH;ILOTS_ANONYMES;5;FALSE;factor;Département de rattachement de la parcelle;IGN;;character;
+surface_graph;SURF_GRAPH;ILOTS_ANONYMES;6;FALSE;numeric;Surface d’origine de la parcelle graphique;IGN;;numeric;
+surface;SURF_CULTU;ILOTS_ANONYMES;7;TRUE;numeric;Surface d’origine de la parcelle graphique;IGN;;numeric;
+group;CODE_CULTU;ILOTS_ANONYMES;8;TRUE;factor;Code du groupe de la culture présente;IGN;;character;
+group.label.fr;NOM_CULTU;ILOTS_ANONYMES;9;FALSE;factor;Étiquette du groupe de la culture présente;IGN;;character;
diff --git a/inst/extdata/scheme_rpg_2.csv b/inst/extdata/scheme_rpg_2.csv
index 7978e1064e26d3f2c62563ce707fb2c9c6d5f3d8..06dadf95b05174e6ca8858a9d46bc6bf5ef6c883 100644
--- a/inst/extdata/scheme_rpg_2.csv
+++ b/inst/extdata/scheme_rpg_2.csv
@@ -1,8 +1,8 @@
-"name";"name_origin";"layer";"order";"keep";"type";"label_fr";"source";"length_source";"type_source";"comment"
-"id";"ID_PARCEL";"PARCELLES_GRAPHIQUES";1;"TRUE";"character";"ID de la parcelle graphique";"IGN";;"text";
-"surface";"SURF_PARC";"PARCELLES_GRAPHIQUES";2;"TRUE";"numeric";"Surface d’origine de la parcelle graphique";"IGN";;"numeric";
-"culture";"CODE_CULTU";"PARCELLES_GRAPHIQUES";3;"TRUE";"factor";"Code de la culture présente";"IGN";;"text";
-"group";"CODE_GROUP";"PARCELLES_GRAPHIQUES";4;"TRUE";"factor";"Code du groupe de la culture présente";"IGN";;"text";
-"catch_1";"CULTURE_D1";"PARCELLES_GRAPHIQUES";5;"TRUE";"factor";"Première culture dérobée";"IGN";;"text";
-"catch_2";"CULTURE_D2";"PARCELLES_GRAPHIQUES";6;"TRUE";"factor";"Seconde culture dérobée";"IGN";;"text";
-"ilot";"NUM_ILOT";"ILOTS_ANONYMES";1;"FALSE";"character";"ID de l’ilôt";"IGN";;"text";
+name;name_origin;layer;order;keep;type;label_fr;source;length_source;type_source;comment
+id;ID_PARCEL;PARCELLES_GRAPHIQUES;1;TRUE;character;ID de la parcelle graphique;IGN;;character;
+surface;SURF_PARC;PARCELLES_GRAPHIQUES;2;TRUE;numeric;Surface d’origine de la parcelle graphique;IGN;;numeric;
+culture;CODE_CULTU;PARCELLES_GRAPHIQUES;3;TRUE;factor;Code de la culture présente;IGN;;character;
+group;CODE_GROUP;PARCELLES_GRAPHIQUES;4;TRUE;factor;Code du groupe de la culture présente;IGN;;character;
+catch_1;CULTURE_D1;PARCELLES_GRAPHIQUES;5;TRUE;factor;Première culture dérobée;IGN;;character;
+catch_2;CULTURE_D2;PARCELLES_GRAPHIQUES;6;TRUE;factor;Seconde culture dérobée;IGN;;character;
+ilot;NUM_ILOT;ILOTS_ANONYMES;1;FALSE;character;ID de l’ilôt;IGN;;character;
diff --git a/inst/extdata/scheme_sirene_2019.csv b/inst/extdata/scheme_sirene_2019.csv
index 23da98db309231f28f30cdf7123872ac5e9b36da..177290fe8ca937358e77173b27f2f3e2bb856db3 100644
--- a/inst/extdata/scheme_sirene_2019.csv
+++ b/inst/extdata/scheme_sirene_2019.csv
@@ -1,58 +1,58 @@
-name;name.origin;order;keep;type;label.french;source;length.source;type.source;comment
-siren;siren;1;FALSE;character;Numéro Siren;INSEE;9;text;Redondant avec siret
-nic;nic;2;FALSE;character;Numéro NIC;INSEE;5;text;Redondant avec siret
-siret;siret;3;TRUE;character;Numéro Siret;INSEE;14;text;
-diffusion;statutDiffusionEtablissement;4;FALSE;factor;Statut de diffusion de l’établissement;INSEE;1;code;Diffusion (grand) public ou non
-creation_date;dateCreationEtablissement;5;TRUE;Date;Date de création de l’établissement;INSEE;10;date;
-staff;trancheEffectifsEtablissement;6;TRUE;factor;Tranche d’effectif salarié de l’établissement;INSEE;2;code;
-staff_year;anneeEffectifsEtablissement;7;TRUE;integer;Année de validité de la tranche d’effectif salarié de l’établissement;INSEE;4;date;
-ape_rm;activitePrincipaleRegistreMetiersEtablissement;8;FALSE;factor;Activité exercée par l’artisan inscrit au registre des métiers;INSEE;6;code;Redonant avec ape et beaucoup de valeurs manquantes
-last_date;dateDernierTraitementEtablissement;9;TRUE;Date;Date du dernier traitement de l’établissement dans le répertoire Sirene;INSEE;10;date;
-hq;etablissementSiege;10;TRUE;logical;Qualité de siège ou non de l’établissement;INSEE;5;text;
+name;name_origin;order;keep;type;label_french;source;length_source;type_source;comment
+siren;siren;1;FALSE;character;Numéro Siren;INSEE;9;character;Redondant avec siret
+nic;nic;2;FALSE;character;Numéro NIC;INSEE;5;character;Redondant avec siret
+siret;siret;3;TRUE;character;Numéro Siret;INSEE;14;character;
+diffusion;statutDiffusionEtablissement;4;FALSE;factor;Statut de diffusion de l’établissement;INSEE;1;character;Diffusion (grand) public ou non
+creation_date;dateCreationEtablissement;5;TRUE;Date;Date de création de l’établissement;INSEE;10;character;
+staff;trancheEffectifsEtablissement;6;TRUE;factor;Tranche d’effectif salarié de l’établissement;INSEE;2;character;
+staff_year;anneeEffectifsEtablissement;7;TRUE;integer;Année de validité de la tranche d’effectif salarié de l’établissement;INSEE;4;character;
+ape_rm;activitePrincipaleRegistreMetiersEtablissement;8;FALSE;factor;Activité exercée par l’artisan inscrit au registre des métiers;INSEE;6;character;Redonant avec ape et beaucoup de valeurs manquantes
+last_date;dateDernierTraitementEtablissement;9;TRUE;Date;Date du dernier traitement de l’établissement dans le répertoire Sirene;INSEE;10;character;
+hq;etablissementSiege;10;TRUE;logical;Qualité de siège ou non de l’établissement;INSEE;5;character;
period_number;nombrePeriodesEtablissement;11;FALSE;numeric;Nombre de périodes de l’établissement;INSEE;2;numeric;
-address;complementAdresseEtablissement;12;FALSE;character;Complément d’adresse;INSEE;38;text;Redondant avec geo_adresse
+address;complementAdresseEtablissement;12;FALSE;character;Complément d’adresse;INSEE;38;character;Redondant avec geo_adresse
route_number;numeroVoieEtablissement;13;FALSE;numeric;Numéro de voie;INSEE;4;numeric;Redondant avec geo_adresse
-repetition;indiceRepetitionEtablissement;14;FALSE;character;Indice de répétition dans la voie;INSEE;1;text;Redondant avec geo_adresse
-toute_type;typeVoieEtablissement;15;FALSE;factor;Type de voie;INSEE;4;code;Redondant avec geo_adresse
-route_label;libelleVoieEtablissement;16;FALSE;character;Libellé de voie;INSEE;100;text;Redondant avec geo_adresse
-postal;codePostalEtablissement;17;FALSE;character;Code postal;INSEE;5;text;Redondant avec geo_adresse
-commune_label;libelleCommuneEtablissement;18;FALSE;character;Libellé de la commune;INSEE;100;text;Redondant avec geo_adresse
-foreign_commune_label;libelleCommuneEtrangerEtablissement;19;FALSE;character;Libellé de la commune pour un établissement situé à l’étranger;INSEE;100;text;Redondant avec geo_adresse
-distribution;distributionSpecialeEtablissement;20;FALSE;character;Distribution spéciale de l’établissement;INSEE;26;text;Redondant avec geo_adresse
-commune;codeCommuneEtablissement;21;TRUE;character;Code commune de l’établissement;INSEE;5;code;Code INSEE commune
-cedex;codeCedexEtablissement;22;FALSE;character;Code cedex;INSEE;9;text;Redondant avec geo_adresse
-cedex_label;libelleCedexEtablissement;23;FALSE;character;Libellé du code cedex;INSEE;100;text;Redondant avec geo_adresse
-country;codePaysEtrangerEtablissement;24;FALSE;factor;Code pays pour un établissement situé à l’étranger;INSEE;5;code;Redondant avec geo_adresse
-country_label;libellePaysEtrangerEtablissement;25;FALSE;character;Libellé du pays pour un établissement situé à l’étranger;INSEE;100;text;Redondant avec geo_adresse
-address_2;complementAdresse2Etablissement;26;FALSE;character;Complément d’adresse secondaire;INSEE;38;text;Pour entrée secondaire d’une entreprise
+repetition;indiceRepetitionEtablissement;14;FALSE;character;Indice de répétition dans la voie;INSEE;1;character;Redondant avec geo_adresse
+toute_type;typeVoieEtablissement;15;FALSE;factor;Type de voie;INSEE;4;character;Redondant avec geo_adresse
+route_label;libelleVoieEtablissement;16;FALSE;character;Libellé de voie;INSEE;100;character;Redondant avec geo_adresse
+postal;codePostalEtablissement;17;FALSE;character;Code postal;INSEE;5;character;Redondant avec geo_adresse
+commune_label;libelleCommuneEtablissement;18;FALSE;character;Libellé de la commune;INSEE;100;character;Redondant avec geo_adresse
+foreign_commune_label;libelleCommuneEtrangerEtablissement;19;FALSE;character;Libellé de la commune pour un établissement situé à l’étranger;INSEE;100;character;Redondant avec geo_adresse
+distribution;distributionSpecialeEtablissement;20;FALSE;character;Distribution spéciale de l’établissement;INSEE;26;character;Redondant avec geo_adresse
+commune;codeCommuneEtablissement;21;TRUE;character;Code commune de l’établissement;INSEE;5;character;Code INSEE commune
+cedex;codeCedexEtablissement;22;FALSE;character;Code cedex;INSEE;9;character;Redondant avec geo_adresse
+cedex_label;libelleCedexEtablissement;23;FALSE;character;Libellé du code cedex;INSEE;100;character;Redondant avec geo_adresse
+country;codePaysEtrangerEtablissement;24;FALSE;factor;Code pays pour un établissement situé à l’étranger;INSEE;5;character;Redondant avec geo_adresse
+country_label;libellePaysEtrangerEtablissement;25;FALSE;character;Libellé du pays pour un établissement situé à l’étranger;INSEE;100;character;Redondant avec geo_adresse
+address_2;complementAdresse2Etablissement;26;FALSE;character;Complément d’adresse secondaire;INSEE;38;character;Pour entrée secondaire d’une entreprise
route_2_number;numeroVoie2Etablissement;27;FALSE;numeric;Numéro de la voie de l’adresse secondaire;INSEE;4;numeric;Pour entrée secondaire d’une entreprise
-repetition_2;indiceRepetition2Etablissement;28;FALSE;character;Indice de répétition dans la voie pour l’adresse secondaire;INSEE;1;text;Pour entrée secondaire d’une entreprise
-route_2_type;typeVoie2Etablissement;29;FALSE;factor;Type de voie de l’adresse secondaire;INSEE;4;code;Pour entrée secondaire d’une entreprise
-route_2_label;libelleVoie2Etablissement;30;FALSE;character;Libellé de voie de l’adresse secondaire;INSEE;100;text;Pour entrée secondaire d’une entreprise
-postal_2;codePostal2Etablissement;31;FALSE;character;Code postal de l’adresse secondaire;INSEE;5;text;Pour entrée secondaire d’une entreprise
-commune_2_label;libelleCommune2Etablissement;32;FALSE;character;Libellé de la commune de l’adresse secondaire;INSEE;100;text;Pour entrée secondaire d’une entreprise
-foreign_commune_2_label;libelleCommuneEtranger2Etablissement;33;FALSE;character;Libellé de la commune de l’adresse secondaire pour un établissement situé à l’étranger;INSEE;100;text;Pour entrée secondaire d’une entreprise
-distribution_2;distributionSpeciale2Etablissement;34;FALSE;character;Distribution spéciale de l’adresse secondaire de l’établissement;INSEE;26;text;Pour entrée secondaire d’une entreprise
-commune_2;codeCommune2Etablissement;35;FALSE;factor;Code commune de l’adresse secondaire;INSEE;5;code;Pour entrée secondaire d’une entreprise
-cedex_2;codeCedex2Etablissement;36;FALSE;character;Code cedex de l’adresse secondaire;INSEE;9;text;Pour entrée secondaire d’une entreprise
-cedex_2_label;libelleCedex2Etablissement;37;FALSE;character;Libellé du code cedex de l’adresse secondaire;INSEE;100;text;Pour entrée secondaire d’une entreprise
-country_2;codePaysEtranger2Etablissement;38;FALSE;factor;Code pays de l’adresse secondaire pour un établissement situé à l’étranger;INSEE;5;code;Pour entrée secondaire d’une entreprise
-country_2_label;libellePaysEtranger2Etablissement;39;FALSE;character;Libellé du pays de l’adresse secondaire pour un établissement situé à l’étranger;INSEE;100;text;Pour entrée secondaire d’une entreprise
-start_date;dateDebut;40;FALSE;Date;Date de début d''une période d'historique d'un établissement;INSEE;10;date;
-state;etatAdministratifEtablissement;41;TRUE;factor;État administratif de l’établissement;INSEE;1;code;
-sign_1;enseigne1Etablissement;42;FALSE;character;Première ligne d’enseigne de l’établissement;INSEE;50;text;
-sign_2;enseigne2Etablissement;43;FALSE;character;Deuxième ligne d’enseigne de l’établissement;INSEE;50;text;
-sign_3;enseigne3Etablissement;44;FALSE;character;Troisième ligne d’enseigne de l’établissement;INSEE;50;text;
-name_usual;denominationUsuelleEtablissement;45;FALSE;character;Dénomination usuelle de l’établissement;INSEE;100;text;Beaucoup de valeurs manquantes
-ape;activitePrincipaleEtablissement;46;TRUE;factor;Activité principale de l''établissement pendant la période;INSEE;6;code;
-ape_label;nomenclatureActivitePrincipaleEtablissement;47;FALSE;factor;Nomenclature d’activité de la variable ape;INSEE;8;code;Redondant avec activitePrincipaleEtablissement
-employer;caractereEmployeurEtablissement;48;TRUE;logical;Caractère employeur de l’établissement;INSEE;1;code;
-longitude;longitude;49;TRUE;numeric;Longitude géographique (en degré);data.cquest.org;;numeric;
-latitude;latitude;50;TRUE;numeric;Latitude géographique (en degré);data.cquest.org;;numeric;
+repetition_2;indiceRepetition2Etablissement;28;FALSE;character;Indice de répétition dans la voie pour l’adresse secondaire;INSEE;1;character;Pour entrée secondaire d’une entreprise
+route_2_type;typeVoie2Etablissement;29;FALSE;factor;Type de voie de l’adresse secondaire;INSEE;4;character;Pour entrée secondaire d’une entreprise
+route_2_label;libelleVoie2Etablissement;30;FALSE;character;Libellé de voie de l’adresse secondaire;INSEE;100;character;Pour entrée secondaire d’une entreprise
+postal_2;codePostal2Etablissement;31;FALSE;character;Code postal de l’adresse secondaire;INSEE;5;character;Pour entrée secondaire d’une entreprise
+commune_2_label;libelleCommune2Etablissement;32;FALSE;character;Libellé de la commune de l’adresse secondaire;INSEE;100;character;Pour entrée secondaire d’une entreprise
+foreign_commune_2_label;libelleCommuneEtranger2Etablissement;33;FALSE;character;Libellé de la commune de l’adresse secondaire pour un établissement situé à l’étranger;INSEE;100;character;Pour entrée secondaire d’une entreprise
+distribution_2;distributionSpeciale2Etablissement;34;FALSE;character;Distribution spéciale de l’adresse secondaire de l’établissement;INSEE;26;character;Pour entrée secondaire d’une entreprise
+commune_2;codeCommune2Etablissement;35;FALSE;factor;Code commune de l’adresse secondaire;INSEE;5;character;Pour entrée secondaire d’une entreprise
+cedex_2;codeCedex2Etablissement;36;FALSE;character;Code cedex de l’adresse secondaire;INSEE;9;character;Pour entrée secondaire d’une entreprise
+cedex_2_label;libelleCedex2Etablissement;37;FALSE;character;Libellé du code cedex de l’adresse secondaire;INSEE;100;character;Pour entrée secondaire d’une entreprise
+country_2;codePaysEtranger2Etablissement;38;FALSE;factor;Code pays de l’adresse secondaire pour un établissement situé à l’étranger;INSEE;5;character;Pour entrée secondaire d’une entreprise
+country_2_label;libellePaysEtranger2Etablissement;39;FALSE;character;Libellé du pays de l’adresse secondaire pour un établissement situé à l’étranger;INSEE;100;character;Pour entrée secondaire d’une entreprise
+start_date;dateDebut;40;FALSE;Date;Date de début d''une période d'historique d'un établissement;INSEE;10;character;
+state;etatAdministratifEtablissement;41;TRUE;factor;État administratif de l’établissement;INSEE;1;character;
+sign_1;enseigne1Etablissement;42;FALSE;character;Première ligne d’enseigne de l’établissement;INSEE;50;character;
+sign_2;enseigne2Etablissement;43;FALSE;character;Deuxième ligne d’enseigne de l’établissement;INSEE;50;character;
+sign_3;enseigne3Etablissement;44;FALSE;character;Troisième ligne d’enseigne de l’établissement;INSEE;50;character;
+name_usual;denominationUsuelleEtablissement;45;FALSE;character;Dénomination usuelle de l’établissement;INSEE;100;character;Beaucoup de valeurs manquantes
+ape;activitePrincipaleEtablissement;46;TRUE;factor;Activité principale de l''établissement pendant la période;INSEE;6;character;
+ape_label;nomenclatureActivitePrincipaleEtablissement;47;FALSE;factor;Nomenclature d’activité de la variable ape;INSEE;8;character;Redondant avec activitePrincipaleEtablissement
+employer;caractereEmployeurEtablissement;48;TRUE;logical;Caractère employeur de l’établissement;INSEE;1;character;
+lon;longitude;49;TRUE;numeric;Longitude géographique (en degré);data.cquest.org;;numeric;
+lat;latitude;50;TRUE;numeric;Latitude géographique (en degré);data.cquest.org;;numeric;
geo_score;geo_score;51;TRUE;numeric;Score de la qualité de la géolocalisation;data.cquest.org;;numeric;
-geo_type;geo_type;52;TRUE;factor;Type de géolocalisation;data.cquest.org;;text;
-geo_adresse;geo_adresse;53;TRUE;character;Adresse obtenue par la géolocalisation;data.cquest.org;;text;
-geo_id;geo_id;54;FALSE;character;geo_id;data.cquest.org;;code;
-geo_ligne;geo_ligne;55;FALSE;character;geo_ligne;data.cquest.org;;code;
-geo_l4;geo_l4;56;FALSE;character;geo_l4;data.cquest.org;;text;
-geo_l5;geo_l5;57;FALSE;character;geo_l5;data.cquest.org;;code;
+geo_type;geo_type;52;TRUE;factor;Type de géolocalisation;data.cquest.org;;character;
+geo_adresse;geo_adresse;53;TRUE;character;Adresse obtenue par la géolocalisation;data.cquest.org;;character;
+geo_id;geo_id;54;FALSE;character;geo_id;data.cquest.org;;character;
+geo_ligne;geo_ligne;55;FALSE;character;geo_ligne;data.cquest.org;;character;
+geo_l4;geo_l4;56;FALSE;character;geo_l4;data.cquest.org;;character;
+geo_l5;geo_l5;57;FALSE;character;geo_l5;data.cquest.org;;character;
diff --git a/inst/extdata/scheme_sirene_na.csv b/inst/extdata/scheme_sirene_na.csv
index c1000df643d7cfc07c1acdad9f767ad05425d180..7d7f55d805d99248a33edd9aba5f90f620ca2032 100644
--- a/inst/extdata/scheme_sirene_na.csv
+++ b/inst/extdata/scheme_sirene_na.csv
@@ -1,4 +1,4 @@
-name;na.value
+name;na_value
creation_date;1900-01-01
ape;00.0Z
ape;00.00Z
diff --git a/script/maintain_geo_sirene.R b/script/maintain_geo_sirene.R
index 1ae7a8bc29f3017440411709fa0fde369cd2206f..2d04e664dd0317d3f099814a326793a9cf64fe20 100755
--- a/script/maintain_geo_sirene.R
+++ b/script/maintain_geo_sirene.R
@@ -5,18 +5,39 @@ arg = commandArgs(trailingOnly = TRUE)
##
## nohup ./script_dl.geo_sirene.R > script_dl.geo_sirene.out &
##
-origin = "https://data.cquest.org/geo_sirene/"
-destination = "~/floodam-data/sirene/geo_sirene"
+
if(length(arg) == 0) month = format(Sys.Date(), "%Y-%m")
if(length(arg) == 1) month = arg[1]
if(length(arg) >= 2) month = floodam.data::create.month(arg[1], arg[2])
-# month = floodam.data::create.month("2018-10", "2020-04")
-invisible(floodam.data::download.geo_sirene(origin, destination, month = month))
+destination = "data-floodam/original/geo_sirene"
+floodam.data::download_geo_sirene(destination, month = month)
+
+floodam.data::alert_mattermost(
+ sprintf(
+ "Hello ! Vintage **%s** of **geo_sirene** has been downloaded.\n",
+ paste("-", month, collapse = "\n")
+ )
+)
+
+origin = file.path(destination, "version_2019", month)
+destination = file.path(
+ "data-floodam/adapted/geo_sirene",
+ "version_2019",
+ month
+)
+
+adapt_geo_sirene(
+ origin,
+ destination,
+ archive = "StockEtablissementActif_utf8_geo.csv.gz",
+ path_eaip = "data-floodam/adapted/eaip",
+ path_admin = "data-floodam/adapted/admin-express"
+)
floodam.data::alert_mattermost(
sprintf(
- "Hello ! For your information, following versions of geo_sirene have been downloaded:\n%s",
+ "Hello ! Vintage **%s** of **geo_sirene** has been adapted.\n",
paste("-", month, collapse = "\n")
)
)
\ No newline at end of file
diff --git a/tests/testthat/test_analyse_archive.R b/tests/testthat/test_analyse_archive.R
index d4b50a7525e19abcd31b9fb1f1ab92c9a8600078..8c56bef0cec6b86a807b4c7761d1b4864751057c 100644
--- a/tests/testthat/test_analyse_archive.R
+++ b/tests/testthat/test_analyse_archive.R
@@ -8,23 +8,45 @@ test_that("Test analyse_archive",
)
expect_identical(
- names(analyse),
- c(
- "data", "version", "precision", "type", "projection",
- "scope", "vintage", "year", "extension", "name"
- )
+ analyse["data"],
+ setNames("RPG", "data")
+ )
+ expect_identical(
+ analyse["version"],
+ setNames("2-0", "version")
+ )
+ expect_identical(
+ analyse["precision"],
+ setNames(NA_character_, "precision")
+ )
+ expect_identical(
+ analyse["type"],
+ setNames("SHP", "type")
+ )
+ expect_identical(
+ analyse["projection"],
+ setNames("LAMB93", "projection")
+ )
+ expect_identical(
+ analyse["scope"],
+ setNames("R76", "scope")
+ )
+ expect_identical(
+ analyse["vintage"],
+ setNames("2020-01-01", "vintage")
+ )
+ expect_identical(
+ analyse["year"],
+ setNames("2020", "year")
+ )
+ expect_identical(
+ analyse["extension"],
+ setNames("7z", "extension")
+ )
+ expect_identical(
+ analyse["name"],
+ setNames("RPG_2-0__SHP_LAMB93_R76_2020-01-01", "name")
)
-
- expect_identical(analyse[["data"]], "RPG")
- expect_identical(analyse[["version"]], "2-0")
- expect_identical(analyse[["precision"]], NA_character_)
- expect_identical(analyse[["type"]], "SHP")
- expect_identical(analyse[["projection"]], "LAMB93")
- expect_identical(analyse[["scope"]], "R76")
- expect_identical(analyse[["vintage"]], "2020-01-01")
- expect_identical(analyse[["year"]], "2020")
- expect_identical(analyse[["extension"]], "7z")
- expect_identical(analyse[["name"]], "RPG_2-0__SHP_LAMB93_R76_2020-01-01")
archive_floodam = "rpg_parcelle_D001_2020-01-01.rds"
analyse = expect_warning(
@@ -40,19 +62,136 @@ test_that("Test analyse_archive",
)
# origin = "floodam.data"
- analyse = expect_silent(analyse_archive(archive_floodam, origin = "floodam.data"))
+ analyse = expect_silent(
+ analyse_archive(archive_floodam, origin = "floodam.data")
+ )
expect_identical(
- names(analyse),
- c("data", "precision", "scope", "vintage", "extension", "name")
+ analyse["data"],
+ setNames("rpg", "data")
+ )
+ expect_identical(
+ analyse["precision"],
+ setNames("parcelle", "precision")
+ )
+ expect_identical(
+ analyse["scope"],
+ setNames("D001", "scope")
+ )
+ expect_identical(
+ analyse["vintage"],
+ setNames("2020-01-01", "vintage")
+ )
+ expect_identical(
+ analyse["extension"],
+ setNames("rds", "extension")
+ )
+ expect_identical(
+ analyse["name"],
+ setNames("rpg_parcelle_D001_2020-01-01", "name")
+ )
+
+ # origin = "geo-sirene"
+ geo_sirene = c(
+ "2024-01/geo_siret_34.csv.gz",
+ "2024-01/StockEtablissement_utf8_geo.csv.gz",
+ "2024-01/StockEtablissementActif_utf8_geo.csv.gz",
+ "2024-01/StockEtablissementFerme_utf8_geo.csv.gz",
+ "2024-01/geo_sirene.csv.gz",
+ "2024-01/etablissements_actifs.csv.gz",
+ "2024-01/etablissements_fermes.csv.gz",
+ "bad-date/geo_siret_34.csv.gz"
+ )
+
+ analyse = expect_silent(
+ analyse_archive(geo_sirene, origin = "geo-sirene")
+ )
+ names = c(
+ "data", "precision", "version", "scope", "vintage",
+ "extension", "name"
)
- expect_identical(analyse[["data"]], "rpg")
- expect_identical(analyse[["precision"]], "parcelle")
- expect_identical(analyse[["scope"]], "D001")
- expect_identical(analyse[["vintage"]], "2020-01-01")
- expect_identical(analyse[["extension"]], "rds")
- expect_identical(analyse[["name"]], "rpg_parcelle_D001_2020-01-01")
+ expect_identical(colnames(analyse), names)
+ expect_identical(
+ analyse_archive(geo_sirene[1], origin = "geo-sirene"),
+ setNames(
+ c(
+ "geo-siret", NA, "2019", "D034", "2024-01", "csv.gz",
+ "geo_siret_34"
+ ),
+ names
+ )
+ )
+ expect_identical(
+ analyse_archive(geo_sirene[2], origin = "geo-sirene"),
+ setNames(
+ c(
+ "geo-siret", NA, "2019", "france", "2024-01", "csv.gz",
+ "StockEtablissement_utf8_geo"
+ ),
+ names
+ )
+ )
+ expect_identical(
+ analyse_archive(geo_sirene[3], origin = "geo-sirene"),
+ setNames(
+ c(
+ "geo-siret", "active", "2019", "france", "2024-01",
+ "csv.gz", "StockEtablissementActif_utf8_geo"
+ ),
+ names
+ )
+ )
+ expect_identical(
+ analyse_archive(geo_sirene[4], origin = "geo-sirene"),
+ setNames(
+ c(
+ "geo-siret", "closed", "2019", "france", "2024-01",
+ "csv.gz", "StockEtablissementFerme_utf8_geo"
+ ),
+ names
+ )
+ )
+ expect_identical(
+ analyse_archive(geo_sirene[5], origin = "geo-sirene"),
+ setNames(
+ c(
+ "geo-siret", NA, "2017", "france", "2024-01",
+ "csv.gz", "geo_sirene"
+ ),
+ names
+ )
+ )
+ expect_identical(
+ analyse_archive(geo_sirene[6], origin = "geo-sirene"),
+ setNames(
+ c(
+ "geo-siret", "active", "2017", "france", "2024-01",
+ "csv.gz", "etablissements_actifs"
+ ),
+ names
+ )
+ )
+ expect_identical(
+ analyse_archive(geo_sirene[7], origin = "geo-sirene"),
+ setNames(
+ c(
+ "geo-siret", "closed", "2017", "france", "2024-01",
+ "csv.gz", "etablissements_fermes"
+ ),
+ names
+ )
+ )
+ expect_identical(
+ analyse_archive(geo_sirene[8], origin = "geo-sirene"),
+ setNames(
+ c(
+ "geo-siret", NA, "2019", "D034", NA, "csv.gz",
+ "geo_siret_34"
+ ),
+ names
+ )
+ )
}
)
diff --git a/tests/testthat/test_get_base_url.R b/tests/testthat/test_get_base_url.R
new file mode 100644
index 0000000000000000000000000000000000000000..f47b2e1aa1dc264189f16b039a7e01bec9f9bb84
--- /dev/null
+++ b/tests/testthat/test_get_base_url.R
@@ -0,0 +1,18 @@
+test_that("Test get_base_url",
+ {
+ expect_identical(
+ get_base_url("http://parent/child/archive.csv.gz"),
+ "http://parent"
+ )
+
+ expect_identical(
+ get_base_url("https://parent/child/archive.csv.gz"),
+ "https://parent"
+ )
+
+ expect_identical(
+ get_base_url("parent/child/archive.csv.gz"),
+ "parent/child/archive.csv.gz"
+ )
+ }
+)
\ No newline at end of file
diff --git a/tests/testthat/test_get_date_from_html.R b/tests/testthat/test_get_date_from_html.R
new file mode 100644
index 0000000000000000000000000000000000000000..13f6f2893900ba5f130c810fd03093f67b9552de
--- /dev/null
+++ b/tests/testthat/test_get_date_from_html.R
@@ -0,0 +1,38 @@
+test_that("Test get_date_from_html",
+ {
+ x = c(
+ "<html>",
+ "<head><title>Index of /example/</title></head>",
+ "<body>",
+ "<h1>Index of /example/</h1><hr><pre>",
+ "<a href='../'>../</a>",
+ "<a href='parent/2023-11/archive.csv.gz'>archive.csv.gz</a>",
+ "<a href='2023-12/archive.csv.gz'>archive.csv.gz</a>",
+ "<a href=\"2024-01/\">2024-01/</a> 07-Jan-2024 09:54",
+ "<a href=\"parent/child/2024-02/\">2024-02/</a> 07-Feb-2024 09:54",
+ "<a href=\"2024-03\">2024-03</a> 07-Mar-2024 10:02",
+ "<a href=\"2024-01-01/\">2024-01-01/</a> 02-Jan-2024 09:56",
+ "<a href=\"2024-01-02\">2024-01-02</a> 03-jan-2024 11:02",
+ "<a href=\"2023/\">2023/</a> 01-Feb-2023 15:54",
+ "<a href=\"2024\">2024</a> 01-Feb-2024 15:54",
+ "<a href=\"last/\">last/</a> 07-Mar-2024 10:02",
+ "</pre><hr></body>",
+ "</html>"
+ )
+
+ month = c("2024-01", "2024-02", "2024-03")
+ last = c(month, "last")
+ day = c("2024-01-01", "2024-01-02")
+ year = c("2023", "2024")
+ combine = c(month, day, year)
+
+ expect_identical(get_date_from_html(x = x), month)
+ expect_identical(get_date_from_html(x = x, expected = "month"), month)
+ expect_identical(get_date_from_html(x = x, expected = "day"), day)
+ expect_identical(get_date_from_html(x = x, expected = "any"), combine)
+ expect_identical(get_date_from_html(x = x, last = TRUE), last)
+ expect_identical(get_date_from_html(x = x[-(8:10)]), character())
+ last = expect_warning(get_date_from_html(x = x[-(8:10)], last = TRUE))
+ expect_identical(last, "last")
+ }
+)
\ No newline at end of file
diff --git a/tests/testthat/test_get_link_from_html.R b/tests/testthat/test_get_link_from_html.R
new file mode 100644
index 0000000000000000000000000000000000000000..0b277ef0537185bccfd1ebbe6d6103ec35dc5b3f
--- /dev/null
+++ b/tests/testthat/test_get_link_from_html.R
@@ -0,0 +1,31 @@
+test_that("Test get_date_from_html",
+ {
+ x = c(
+ "<html>",
+ "<head><title>Index of /example/</title></head>",
+ "<body>",
+ "<h1>Index of /example/</h1><hr><pre>",
+ "<a href='../'>../</a>",
+ "<a href='parent/child/archive.csv.gz'>archive.csv.gz</a>",
+ "<a href=\"2024-01/\">2024-01/</a> 07-Jan-2024 00:12 -",
+ "<a href=\"2024-02/\">2024-02/</a> 07-Feb-2024 09:54 -",
+ "<a href=\"2024-03\">2024-03</a> 07-Mar-2024 10:02 -",
+ "<a href=\"2024-01-01/\">2024-01-01/</a> 02-Jan-2024 09:56 -",
+ "<a href=\"2024-01-02\">2024-01-02</a> 03-jan-2024 11:02 -",
+ "<a href=\"2023/\">2023/</a> 01-Feb-2023 15:54 -",
+ "<a href=\"2024\">2024</a> 01-Feb-2024 15:54 -",
+ "<a href=\"last/\">last/</a> 07-Mar-2024 10:02 -",
+ "</pre><hr></body>",
+ "</html>"
+ )
+
+ result = c(
+ "../", "parent/child/archive.csv.gz", "2024-01/", "2024-02/",
+ "2024-03", "2024-01-01/", "2024-01-02", "2023/", "2024", "last/")
+
+ expect_identical(get_link_from_html(x = x), result)
+
+ x = paste(x, collapse = "")
+ expect_identical(get_link_from_html(x = x), result)
+ }
+)
\ No newline at end of file
diff --git a/tests/testthat/test_to_logical.R b/tests/testthat/test_to_logical.R
new file mode 100644
index 0000000000000000000000000000000000000000..b9cae6d92a6edf352364633d48d5c6a2fc0065ba
--- /dev/null
+++ b/tests/testthat/test_to_logical.R
@@ -0,0 +1,42 @@
+test_that("Test to_logical",
+ {
+ x = c(0:2, NA)
+ expect_identical(to_logical(x), as.logical(x))
+
+ x = c(
+ "true", "false", "T", "F", "True", "False", "TRUE", "FALSE",
+ "", "NA", NA
+ )
+ expect_identical(to_logical(x), as.logical(x))
+
+ x = c("t", "f")
+ expect_identical(to_logical(x), as.logical(toupper(x)))
+
+ # English yes/no
+ x = c("y", "Yes", "n", "No")
+ response = c(TRUE, TRUE, FALSE, FALSE)
+ expect_identical(to_logical(x), response)
+ expect_identical(to_logical(tolower(x)), response)
+ expect_identical(to_logical(toupper(x)), response)
+
+ # French yes/no
+ x = c("o", "oui", "n", "non")
+ expect_identical(to_logical(x), response)
+
+ # French true/false
+ x = c("v", "Vrai", "f", "Faux")
+ expect_identical(to_logical(x), response)
+
+ # Mix do not work or explicit true and false
+ x = c("oui", "vrai")
+ expect_identical(to_logical(x), c(NA, NA))
+ expect_identical(to_logical(x, true = x), c(NA, NA))
+ expect_identical(to_logical(x, true = x, false = ""), c(TRUE, TRUE))
+
+ # For other convention (language)
+ x = c("s", "si", "n", "no")
+ true = c("S", "SI")
+ false = c("N", "NO")
+ expect_identical(to_logical(x, true, false), response)
+ }
+)