Merge branch 'master' of gitea:christian/hateimparlament

replace non ascii characters by unicode points
2021-08-10 20:18:33 +02:00 · 2021-08-10 20:18:23 +02:00
2 changed files with 3 additions and 3 deletions
@@ -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
@@ -64,7 +64,7 @@ repair_talks <- function(talks) {
 #' 
 #' returns a lookup table
 lookup_speaker <- function(tb, speaker, name_variable) {
-    tobereplaced <- "[-–—‑- ]"
+    tobereplaced <- "[\u002D\u2013\u2014\u2011\u00AD ]"
    speaker %>%
        unite(name, prename, lastname, sep=".*") %>%
        mutate(name = str_replace_all(name, tobereplaced, ".*")) ->
Author	SHA1	Message	Date
christian	05755f9737	Merge branch 'master' of gitea:christian/hateimparlament	2021-08-10 20:18:33 +02:00
christian	01ec0de76f	replace non ascii characters by unicode points	2021-08-10 20:18:23 +02:00