actorizer: add pre_tags and post_tags to argument list

bulk_writer: updated to use _doc doctype
query_gen_actors: added NA for all searches that don't have pre- or postfixes

R/actorizer.R

@@ -13,7 +13,7 @@
 #' @export
 #' @examples
 #' actorizer(out, localhost = F, ids, prefix, postfix, identifier, es_super)
-actorizer <- function(out, localhost = F, ids, prefix, postfix, identifier, es_super, ver) {
+actorizer <- function(out, localhost = F, ids, prefix, postfix, pre_tags, post_tags, es_super, ver) {
   ### Function to filter out false positives using regex
   exceptionizer <- function(id, ud, doc, markers, pre_tags_regex, post_tags_regex,pre_tags,post_tags, prefix, postfix) {
     min <- min(ud$start[ud$sentence_id == id]) # Get start position of sentence

R/bulk_writer.R

@@ -27,19 +27,19 @@ bulk_writer <- function(x, index = 'maml', varname, type, ver) {
   }
   if (varname == "ud") {
     return(
-      paste0('{"update": {"_index": "',index,'", "_type": "doc", "_id": "',x[1],'"}}
+      paste0('{"update": {"_index": "',index,'", "_type": "_doc", "_id": "',x[1],'"}}
 { "script" : { "source": "ctx._source.version = \\"',ver,'\\"; ctx._source.ud = params.code; ctx._source.remove(\\"tokens\\")", "lang" : "painless", "params": { "code": ',json,'}}}')
     )
   }
   if (type == 'set') {
     return(
-      paste0('{"update": {"_index": "',index,'", "_type": "doc", "_id": "',x[1],'"}}
+      paste0('{"update": {"_index": "',index,'", "_type": "_doc", "_id": "',x[1],'"}}
 { "script" : { "source": "ctx._source.version = \\"',ver,'\\"; if (ctx._source.computerCodes != null) {ctx._source.computerCodes.',varname,' = params.code} else {ctx._source.computerCodes = params.object}", "lang" : "painless", "params": { "code": ',json,', "object": {"',varname,'": ',json,'} }}}')
     )
   }
   if (type == "add") {
     return(
-      paste0('{"update": {"_index": "',index,'", "_type": "doc", "_id": "',x[1],'"}}
+      paste0('{"update": {"_index": "',index,'", "_type": "_doc", "_id": "',x[1],'"}}
         {"script": {"source": "ctx._source.version = \\"',ver,'\\"; if (ctx._source.computerCodes != null && ctx._source.computerCodes.containsKey(\\"',varname,'\\")) {ctx._source.computerCodes.',varname,'.addAll(params.code)} else if (ctx._source.computerCodes != null) {ctx._source.computerCodes.',varname,' = params.code} else {ctx._source.computerCodes = params.object}", "lang" : "painless", "params": { "code": ',json,' , "object": {"',varname,'": ',json,'}}}}'
       )
     )

R/query_gen_actors.R

@@ -137,8 +137,9 @@ query_gen_actors <- function(actor, country, pre_tags, post_tags) {
     ids <- list(c(actor$`_source.actorId`,str_c(actor$`_source.partyId`,'_a')))
     actorid <- actor$`_source.actorId`
     query <- generator(country, actor$`_source.startDate`, actor$`_source.endDate`, query_string, pre_tags, post_tags, actorid)
-    return(data.frame(query = query, ids = I(ids), stringsAsFactors = F))
+    return(data.frame(query = query, ids = I(ids), prefix = NA, postfix = NA, stringsAsFactors = F))
   }
+
   ### Query generation for party searches
   if (actor$`_source.function` == "Party") {
     actor$`_source.startDate` <- "2000-01-01"
@@ -175,7 +176,7 @@ query_gen_actors <- function(actor, country, pre_tags, post_tags) {
       if (country == 'uk') {
         df2 <- data.frame(query = query, ids = I(ids), prefix = actor$`_source.notPrecededBy`, postfix = actor$`_source.notFollowedBy`, stringsAsFactors = F)
       } else {
-        df2 <- data.frame(query = query, ids = I(ids), stringsAsFactors = F)
+        df2 <- data.frame(query = query, ids = I(ids), prefix = NA, postfix = NA, stringsAsFactors = F)
       }
     }
     if (exists('df1') == T & exists('df2') == T) {