replace non ascii characters by unicode points

This commit is contained in:
2021-08-10 20:18:23 +02:00
parent b11289e093
commit 01ec0de76f
2 changed files with 3 additions and 3 deletions
+2 -2
View File
@@ -153,10 +153,10 @@ parse_speech <- function(speech_xml, date) {
}
} else if (xml_name(node) == "kommentar") {
# comments are of the form
# <kommentar>(blabla [Fraktion] blabla liasdf bla)</kommentar>
# <kommentar>(blabla [Fraktion] \u2013 blabla liasdf \u2013 bla)</kommentar>
xml_text(node) %>%
str_sub(2, -2) %>%
str_split("") %>%
str_split("\u2013") %>%
`[[`(1) %>%
lapply(parse_comment, speech_id = speech_id, on_speaker = cur_speaker) ->
cs