2 New Files, Renamed.

00_Setup.R

@@ -0,0 +1,8 @@
+#### Generiert die Ordnerstruktur der Daten #### 
+
+source("config/config.R")
+
+ifelse(!dir.exists(file.path("data/")), dir.create(file.path("data/")), FALSE)
+ifelse(!dir.exists(file.path(PFAD_EXCEL)), dir.create(file.path(PFAD_EXCEL)), FALSE)
+ifelse(!dir.exists(file.path(PFAD_OUT)), dir.create(file.path(PFAD_OUT)), FALSE)
+ifelse(!dir.exists(file.path(PFAD_EXCEL)), dir.create(file.path(PFAD_DB_OUT)), FALSE)

01_find_new_entries.R

@@ -83,4 +83,4 @@ distincts <- data.frame(distincts[nchar(distincts$bibliographicCitation) >= THRE
 colnames(distincts) <- (c('bibliographicCitation'))
 
 #Schreibt die Distincts in eine Exceldatei
-write_xlsx(distincts, "data/Output/distincts_automated_gc3d.xlsx")
+write_xlsx(distincts, paste(PFAD_OUT, "distincts_automated_gc3d.xlsx", sep=""))

02_not_in_db.R

@@ -0,0 +1,29 @@
+library("readxl")
+library("writexl")
+library("dplyr")
+library("xlsx")
+library("stringi")
+
+source("config/config.R")
+source("sparql.R")
+
+vorhanden_df = data.frame(get_current_geoera_lit_db()$citation)
+vorhanden_df_2 = unique(vorhanden_df)
+
+colnames(vorhanden_df) = (c(COLUMN_NAME))
+
+neu_df = data.frame(read_excel(paste(PFAD_EXCEL, "distincts_kontrolliert.xlsx", sep="")))
+neu_df = data.frame(lapply(neu_df, stri_enc_toutf8))
+neu_df_2 = unique(neu_df)
+
+all_df = rbind(vorhanden_df, neu_df)
+all_df_2 = unique(all_df)
+
+#inner_join finds common elements between two data frames
+#anti_join finds elements the are exclusively in one of the data frames
+common = inner_join(neu_df, vorhanden_df)
+not_in_db = anti_join(neu_df, common)
+
+not_in_db_2 = anti_join(all_df, vorhanden_df)
+
+write_xlsx(not_in_db, paste(PFAD_OUT, "not_in_db_",format(Sys.time(), "%Y_%m_%d") ,".xlsx", sep=""))