dupe_detect: Reset the _delete value to 1

out_parser: fix to sentence parsing, add additional (empty) string at end of merged field, to make merged field end on .
6 years ago · d0e9bf565b
parent ea8cfb071f
commit d0e9bf565b
2 changed files with 3 additions and 1 deletions
--- a/R/dupe_detect.R
+++ b/R/dupe_detect.R
@ -49,7 +49,7 @@ dupe_detect <- function(row, grid, cutoff_lower, cutoff_upper = 1, es_pwd, es_su
      #       file = paste0(getwd(),'/remove_ids.txt'),
      #       append=T)
      dupe_delete <- data.frame(id=unique(rownames(which(simil >= cutoff_lower & simil <= cutoff_upper, arr.ind = TRUE))),
-                                dupe_delete = rep(2,length(unique(rownames(which(simil >= cutoff_lower & simil <= cutoff_upper, arr.ind = TRUE))))))
+                                dupe_delete = rep(1,length(unique(rownames(which(simil >= cutoff_lower & simil <= cutoff_upper, arr.ind = TRUE))))))
      bulk <- c(apply(df, 1, bulk_writer, varname='duplicates', type = 'set', ver = ver),
                apply(dupe_delete, 1, bulk_writer, varname='_delete', type = 'set', ver = ver))
      if (length(bulk) > 0) {
--- a/R/out_parser.R
+++ b/R/out_parser.R
@ -39,6 +39,7 @@ out_parser <- function(out, field) {
                        out$highlight.preteaser,
                        out$highlight.teaser,
                        out$highlight.text,
+                        '',
                        sep = ". ")
  }

@ -54,6 +55,7 @@ out_parser <- function(out, field) {
                        out$`_source.preteaser`,
                        out$`_source.teaser`,
                        out$`_source.text`,
+                        '',
                        sep = ". ")
  }