Merge pull request #54 from ropensci/encodingUTF8

Set encoding to UTF-8 for tags and user names in returned data.frames

DESCRIPTION

@@ -1,7 +1,7 @@
 Type: Package
 Package: osmapiR
 Title: 'OpenStreetMap' API
-Version: 0.1.0.9017
+Version: 0.1.0.9018
 Authors@R: c(
     person("Joan", "Maspons", , "[email protected]", role = c("aut", "cre", "cph"),
            comment = c(ORCID = "0000-0003-2286-8727")),

NEWS.md

@@ -15,10 +15,11 @@
 * Fix changesets' bbox in `st_as_sf.osmapi_chagesets()` ([84f16e7a](https://github.com/ropensci/osmapiR/commit/84f16e7adda087ab707cc2644c79ff1590cf307e)). 
 * Implement NA bboxes in `st_as_sf.osmapi_chagesets()` ([7ea4f5d7](https://github.com/ropensci/osmapiR/commit/7ea4f5d7f412ef8cf7691741b836cf45ddeb61f2)).
 * Remove dontrun in examples that don't require authentication (#47).
-* Improve performance when parsing gpx data to data.frame (#48)
-* Parse TrackPointExtension data from gpx if available (#49)
-* Tweaks in DESCRIPTION and CITATION files by @Maelle (#50, #51)
-* Sort OSM objects in `osm_get_objects(..., full_objects = TRUE)` and optimize (#52)
+* Improve performance when parsing gpx data to data.frame (#48).
+* Parse TrackPointExtension data from gpx if available (#49).
+* Tweaks in DESCRIPTION and CITATION files by @Maelle (#50, #51).
+* Sort OSM objects in `osm_get_objects(..., full_objects = TRUE)` and optimize (#52).
+* Set encoding to UTF-8 for tags and user names in returned data.frames (#54).
 
 
 # osmapiR 0.1.0

R/osmapi_user_data.R

@@ -542,6 +542,7 @@ osm_get_preferences_user <- function(key, format = c("R", "xml", "json")) {
 
   if (!missing(key)) {
     out <- httr2::resp_body_string(resp)
+    out <- enc2utf8(out)
   } else if (format %in% c("R", "xml")) {
     out <- httr2::resp_body_xml(resp)
     if (format == "R") {

R/xml_to_R.R

@@ -9,6 +9,7 @@ tags_xml2mat_wide <- function(xml_nodeset) {
     tagV <- vapply(tag, function(x) x, FUN.VALUE = character(2))
     m[i, tagV[1, ]] <- tagV[2, ]
   }
+  m <- enc2utf8(m)
 
   return(m)
 }
@@ -23,6 +24,8 @@ tags_xml2list_df <- function(xml_nodeset) {
       )),
       names = c("key", "value")
     )
+    tags_df$key <- enc2utf8(tags_df$key)
+    tags_df$value <- enc2utf8(tags_df$value)
 
     class(tags_df) <- c("tags_df", "data.frame")
 
@@ -35,7 +38,8 @@ tags_xml2list_df <- function(xml_nodeset) {
 
 ## Changesets ----
 
-# osm_download_changeset() in osmChange xml format. Not related
+# For osm_get_changesets() & osm_query_changesets().
+# osm_download_changeset() in osmChange xml format not related
 
 changeset_xml2DF <- function(xml, tags_in_columns = FALSE) {
   changesets <- xml2::xml_children(xml)
@@ -67,6 +71,7 @@ changeset_xml2DF <- function(xml, tags_in_columns = FALSE) {
   out$changes_count <- as.integer(out$changes_count)
   out$created_at <- as.POSIXct(out$created_at, format = "%Y-%m-%dT%H:%M:%OS", tz = "GMT")
   out$closed_at <- as.POSIXct(out$closed_at, format = "%Y-%m-%dT%H:%M:%OS", tz = "GMT")
+  out$user <- enc2utf8(out$user)
 
   discussion <- xml2::xml_child(changesets, "discussion")
 
@@ -79,6 +84,8 @@ changeset_xml2DF <- function(xml, tags_in_columns = FALSE) {
       comment_text <- xml2::xml_text(xml2::xml_child(x, "text"))
       dis <- data.frame(comment_attrs, comment_text)
       dis$date <- as.POSIXct(dis$date, format = "%Y-%m-%dT%H:%M:%OS", tz = "GMT")
+      dis$user <- enc2utf8(dis$user)
+      dis$comment_text <- enc2utf8(dis$comment_text)
 
       class(dis) <- c("changeset_comments", "data.frame")
 
@@ -202,6 +209,7 @@ object_xml2DF <- function(xml, tags_in_columns = FALSE) {
   out$visible <- ifelse(out$visible == "true", TRUE, FALSE)
   out$version <- as.integer(out$version)
   out$timestamp <- as.POSIXct(out$timestamp, format = "%Y-%m-%dT%H:%M:%OS", tz = "GMT")
+  out$user <- enc2utf8(out$user)
 
   members <- vector("list", length = length(objects))
   members[object_type == "way"] <- lapply(objects[object_type == "way"], function(x) {
@@ -270,11 +278,17 @@ gpx_meta_xml2DF <- function(xml) {
 
   gpx_attrs <- do.call(rbind, xml2::xml_attrs(gpx_files))
   description <- xml2::xml_text(xml2::xml_child(gpx_files, "description"))
-  tags <- lapply(xml2::xml_find_all(gpx_files, ".//tag", flatten = FALSE), xml2::xml_text)
+  tags <- lapply(xml2::xml_find_all(gpx_files, ".//tag", flatten = FALSE), function(x) {
+    x <- xml2::xml_text(x)
+    enc2utf8(x)
+  })
 
   out <- data.frame(gpx_attrs, description)
   out$timestamp <- as.POSIXct(out$timestamp, format = "%Y-%m-%dT%H:%M:%OS", tz = "GMT")
   out$pending <- ifelse(out$pending == "true", TRUE, FALSE)
+  out$name <- enc2utf8(out$name)
+  out$user <- enc2utf8(out$user)
+  out$description <- enc2utf8(out$description)
 
   out$tags <- tags
 
@@ -380,6 +394,7 @@ trk_xml2df <- function(trk) {
 
   details <- xml2::xml_find_all(trk, "./*[not(name() = 'trkseg')]") # no trkseg nodes
   trk_details <- stats::setNames(xml2::xml_text(details), nm = xml2::xml_name(details))
+  trk_details <- enc2utf8(trk_details)
   if (length(trk_details)) {
     names(trk_details) <- paste0("track_", names(trk_details))
   }
@@ -476,6 +491,9 @@ user_details_xml2DF <- function(xml) {
 
   out$account_created <- as.POSIXct(out$account_created, format = "%Y-%m-%dT%H:%M:%OS", tz = "GMT")
 
+  out$display_name <- enc2utf8(out$display_name)
+  out$description <- enc2utf8(out$description)
+
   return(out)
 }
 
@@ -515,6 +533,9 @@ logged_user_details_xml2list <- function(xml) {
     )
   )
 
+  out$user["display_name"] <- enc2utf8(out$user["display_name"])
+  out$description <- enc2utf8(out$description)
+
   return(out)
 }
 
@@ -529,6 +550,8 @@ user_preferences_xml2DF <- function(xml) {
     as.data.frame(do.call(rbind, xml2::xml_attrs(preference))),
     names = c("key", "value")
   )
+  out$key <- enc2utf8(out$key)
+  out$value <- enc2utf8(out$value)
 
   return(out)
 }
@@ -566,6 +589,9 @@ note_xml2DF <- function(xml) {
 
     comm <- data.frame(date, uid, user, user_url, action, text, html)
     comm$date <- as.POSIXct(comm$date, format = "%Y-%m-%d %H:%M:%OS", tz = "GMT")
+    comm$user <- enc2utf8(comm$user)
+    comm$text <- enc2utf8(comm$text)
+    comm$html <- enc2utf8(comm$html)
 
     class(comm) <- c("note_comments", "data.frame")
 

codemeta.json

@@ -8,7 +8,7 @@
   "codeRepository": "https://github.com/ropensci/osmapiR",
   "issueTracker": "https://github.com/ropensci/osmapiR/issues",
   "license": "https://spdx.org/licenses/GPL-3.0",
-  "version": "0.1.0.9017",
+  "version": "0.1.0.9018",
   "programmingLanguage": {
     "@type": "ComputerLanguage",
     "name": "R",
@@ -180,7 +180,7 @@
       "name": "osmapiR: OpenStreetMap API",
       "identifier": "10.32614/CRAN.package.osmapiR",
       "url": "https://docs.ropensci.org/osmapiR/",
-      "description": "R package version 0.1.0.9017 \nhttps://github.com/ropensci/osmapiR",
+      "description": "R package version 0.1.0.9018 \nhttps://github.com/ropensci/osmapiR",
       "@id": "https://doi.org/10.32614/CRAN.package.osmapiR",
       "sameAs": "https://doi.org/10.32614/CRAN.package.osmapiR"
     }

inst/WORDLIST

@@ -476,6 +476,7 @@ userName
 usethis
 usr
 usrs
+utf
 uvAy
 vals
 vapply