dp : texts_connected implemented

Author: petermeissner

R/diffrproject.R

@@ -45,12 +45,26 @@ diffrproject <-
       #### methods =============================================================
       # add text
       text_add = function( rtext, name = NULL ){
+
         # input check
         stopifnot("rtext"  %in% class(rtext))
+
+        # connecting text with other text
+        if( length(self$texts)>0 ){
+          next_item <- length(self$texts_connected)+1
+          last_item <- length(self$texts)
+          self$texts_connected[[next_item]] <-
+            list(
+              self$texts[[last_item]],
+              rtext
+            )
+        }
+
         # working variable creation
         names <- names(self$texts)
         ids   <- vapply(self$texts, `[[`, "", "id")
         id    <- rtext$id
+
         # doing-duty-to-do
         if( is.null(name) ){
           next_num <- max(c(as.numeric(text_extract(names, "\\d+")),0))+1
@@ -62,6 +76,7 @@ diffrproject <-
           rtext$id <- text_collapse(id, "_", i)
           i <- i+1
         }
+
         # return self for piping
         return(invisible(self))
       },

R/rtext.R

@@ -252,13 +252,18 @@ rtext <-
       self$encoding <- "UTF-8"
 
       #### Tokenizer
+      # assign tokenizer
       self$tokenizer <- tokenizer
       if( !is.null(tokenize_by) ){
         self$tokenizer <-
           function(x){
             text_tokenize(x, regex = tokenize_by, non_token = TRUE)
           }
       }
+      # check if tokenizer is valid
+      stopifnot( "data.frame" %in% class(self$tokenizer("")) )
+      stopifnot( dim2(self$tokenizer(""))==4 )
+
 
       #### Tokenize
       private$tokenize()

R/text_tools.R

@@ -334,6 +334,7 @@ text_extract_all <-
 #' function for collapsing text vectors
 #' @param x object to be collapsed
 #' @param sep separator between text parts
+#' @param ... additional passed on to specific methods (e.g. to paste within text_collapse.default())
 #' @export
 text_collapse <- function (x, ..., sep) {
   UseMethod("text_collapse")

dev.R

@@ -10,28 +10,21 @@ text_files <- list.files(text_path, pattern = "txt", full.names = TRUE)
 
 
 dp <- diffrproject$new()
-
-for( i in seq_along(text_files)){
-  tmp <-
-    rtext$new(
-      text_file   = text_files[i],
+dp$text_add(
+    rtext = rtext$new(
+      text_file   = text_files[1],
       encoding    = "latin1",
       tokenize_by = "\n"
-    )
-  dp$text_add(tmp, name=basename(text_files[i]))
-}
-
-
-dp$text_data()
-
-
-
-names(dp$texts)
-
-
-devtools::install_github("petermeissner/diffr")
-
-diffr::diffr(
-  text1 = dp$texts[[1]]$text_get(),
-  text2 = dp$texts[[2]]$text_get()
+    ),
+    name = basename(text_files[1])
+  )
+
+dp$text_add(
+  rtext = rtext$new(
+    text_file   = text_files[2],
+    encoding    = "latin1",
+    tokenize_by = "\n"
+  ),
+  name = basename(text_files[2])
 )
+