Add (not) self-published to useful virtual corpora
diff --git a/scripts/useful_deliko_subcorpora.R b/scripts/useful_deliko_subcorpora.R
index 4031038..9f69b2b 100644
--- a/scripts/useful_deliko_subcorpora.R
+++ b/scripts/useful_deliko_subcorpora.R
@@ -96,11 +96,16 @@
genre_definitions <- genre_definitions %>% select(-regex)
+self_published_regex<- ".*([Oo]n.[Dd]emand|[Bb][Oo][Dd]|[Nn]eobooks|[Bb]ook[Rr]ix|[Ee]publi|[Tt]redition|[Tt]olino [Mm]edia|TWENTYSIX|[Uu]ksak).*"
# Additional manually curated virtual corpora; edit this list as needed
extra_corpora <- tribble(
~id, ~de_title, ~en_title, ~corpus_query, ~de_description, ~en_description,
"award_winners", "Buchpreisträger", "Award winners", "award=buchpreis",
"Buchpreisträger.", "Award winners.",
+ "self_published", "Self-Publisher", "Self-published", glue("publisher=/{self_published_regex}/"),
+ "Self-Publisher.", "Self-published.",
+ "self_published_excluded", "Self-Publisher ausgeschlossen", "Self-published excluded", glue("publisher!=/{self_published_regex}/"),
+ "Self-Publisher ausgeschlossen.", "Self-published excluded.",
"translation", "Übersetzer*in angegeben", "Translator given", "translator=/.+/", "Übersetzer*in angegeben", "Translator given",
"no_translation", "Übersetzer*in nicht angegeben", "Translator not given", "translator!=/.+/", "Übersetzer*in nicht angegeben – wahrscheinlich keine Übersetzung", "Translator not given – probably no translation",
)