further exmamples moved to dontrun #273

R/S4classes.R

@@ -1015,6 +1015,7 @@ setClass("press_subcorpus", contains = "subcorpus")
 #' @rdname phrases-class
 #' @aliases phrases-class
 #' @examples
+#' \dontrun{
 #' # Workflow to create document-term-matrix with phrases
 #' 
 #' obs <- corpus("GERMAPARLMINI") %>%
@@ -1034,7 +1035,7 @@ setClass("press_subcorpus", contains = "subcorpus")
 #'   
 #' grep("erneuerbaren_Energien", colnames(dtm))
 #' grep("verpasste_Chancen", colnames(dtm))
-#' 
+#' }
 setClass(
   "phrases",
   contains = "regions"

R/cooccurrences.R

@@ -319,7 +319,7 @@ setMethod("cooccurrences", "context", function(.Object, method = "ll", verbose =
 #' 
 #' # compute cooccurrences for a set of partitions
 #' # (example not run by default to save time on test machines)
-#' \donttest{
+#' \dontrun{
 #' pb <- partition_bundle("GERMAPARLMINI", s_attribute = "speaker")
 #' ps <- count(pb, query = "Deutschland")[Deutschland >= 25][["partition"]]
 #' pb_min <- pb[ps]
@@ -830,7 +830,7 @@ setMethod("Cooccurrences", "subcorpus", function(
 #' @exportMethod as.simple_triplet_matrix
 #' @rdname all-cooccurrences-class
 #' @examples
-#' \donttest{
+#' \dontrun{
 #' # takes too much time on CRAN test machines
 #' use(pkg = "RcppCWB", corpus = "REUTERS")
 #' X <- Cooccurrences("REUTERS", p_attribute = "word", left = 2L, right = 2L)

R/decode.R

@@ -264,28 +264,29 @@ as.AnnotatedPlainTextDocument <- function(x, p_attributes = NULL, s_attributes =
 #' use(pkg = "RcppCWB", corpus = "REUTERS")
 #' 
 #' # Decode corpus as data.table
-#' dt <- decode("GERMAPARLMINI", to = "data.table")
+#' dt <- decode("REUTERS", to = "data.table")
 #' 
 #' # Decode corpus selectively
-#' dt <- decode("GERMAPARLMINI", to = "data.table", p_attributes = "word", s_attributes = "party")
+#' dt <- decode(
+#'   "REUTERS",
+#'   to = "data.table",
+#'   p_attributes = "word",
+#'   s_attributes = "id"
+#' )
 #' 
 #' # Decode a subcorpus
-#' dt <- corpus("GERMAPARLMINI") %>%
-#'   subset(speaker == "Angela Dorothea Merkel") %>%
-#'   decode(s_attributes = c("speaker", "party", "date"), to = "data.table")
-#' 
-#' # Decode subcorpus selectively
-#' corpus("GERMAPARLMINI") %>%
-#'   subset(speaker == "Angela Dorothea Merkel") %>%
-#'   decode(to = "data.table", p_attributes = "word", s_attributes = "party")
+#' dt <- corpus("REUTERS") %>%
+#'   subset(id %in% c("127", "144")) %>%
+#'   decode(s_attributes = "id", to = "data.table")
 #' 
 #' # Decode partition
-#' P <- partition("REUTERS", places = "kuwait", regex = TRUE)
-#' dt <- decode(P, to = "data.table")
+#' dt <- partition("REUTERS", places = "kuwait", regex = TRUE) %>%
+#'   decode(to = "data.table")
 #' 
 #' # Previous versions of polmineR offered an option to decode a single
 #' # s-attribute. This is how you could proceed to get a table with metadata.
-#' dt <- decode(P, s_attribute = "id", decode = FALSE, to = "data.table")
+#' dt <- partition("REUTERS", places = "kuwait", regex = TRUE) %>% 
+#'   decode(s_attribute = "id", decode = FALSE, to = "data.table")
 #' dt[, "word" := NULL]
 #' dt[,{list(cpos_left = min(.SD[["cpos"]]), cpos_right = max(.SD[["cpos"]]))}, by = "id"]
 #' 

R/features.R

@@ -96,6 +96,7 @@ NULL
 #' Manning, Christopher D.; Schuetze, Hinrich (1999): \emph{Foundations of Statistical Natural Language
 #' Processing}. MIT Press: Cambridge, Mass., pp. 151-189 (ch. 5).
 #' @examples
+#' \dontrun{
 #' use("polmineR")
 #' 
 #' kauder <- partition(
@@ -115,6 +116,7 @@ NULL
 #' terms_kauder <- features(kauder_count, all_count, included = TRUE)
 #' top100 <- subset(terms_kauder, rank_chisquare <= 100)
 #' head(top100)
+#' }
 #' 
 #' # get matrix with features (dontrun to keep time for examples short)
 #' \dontrun{

R/token_stream.R

@@ -58,28 +58,34 @@ NULL
 #' @examples
 #' use(pkg = "RcppCWB", corpus = "REUTERS")
 #' 
-#' # Decode first words of GERMAPARLMINI corpus (first sentence)
-#' get_token_stream(0:9, corpus = "GERMAPARLMINI", p_attribute = "word")
+#' # Decode first words of REUTERS corpus (first sentence)
+#' get_token_stream(0:20, corpus = "REUTERS", p_attribute = "word")
 #'
 #' # Decode first sentence and collapse tokens into single string
-#' get_token_stream(0:9, corpus = "GERMAPARLMINI", p_attribute = "word", collapse = " ")
+#' get_token_stream(0:20, corpus = "REUTERS", p_attribute = "word", collapse = " ")
 #'
 #' # Decode regions defined by two-column integer matrix
-#' region_matrix <- matrix(c(0L,9L,10L,25L), ncol = 2, byrow = TRUE)
-#' get_token_stream(region_matrix, corpus = "GERMAPARLMINI", p_attribute = "word", encoding = "latin1")
+#' region_matrix <- matrix(c(0L,20L,21L,38L), ncol = 2, byrow = TRUE)
+#' get_token_stream(
+#'   region_matrix,
+#'   corpus = "REUTERS",
+#'   p_attribute = "word",
+#'   encoding = "latin1"
+#' )
 #'
 #' # Use argument 'beautify' to remove surplus whitespace
+#' \dontrun{
 #' get_token_stream(
 #'   region_matrix,
 #'   corpus = "GERMAPARLMINI",
 #'   p_attribute = "word",
 #'   encoding = "latin1",
 #'   collapse = " ", beautify = TRUE
 #' )
+#' }
 #'
 #' # Decode entire corpus (corpus object / specified by corpus ID)
-#' fulltext <- get_token_stream("GERMAPARLMINI", p_attribute = "word")
-#' corpus("GERMAPARLMINI") %>%
+#' corpus("REUTERS") %>%
 #'   get_token_stream(p_attribute = "word") %>%
 #'   head()
 #'
@@ -90,9 +96,11 @@ NULL
 #'   head()
 #'
 #' # Decode partition_bundle
+#' \dontrun{
 #' pb_tokstr <- corpus("REUTERS") %>%
 #'   split(s_attribute = "id") %>%
 #'   get_token_stream(p_attribute = "word")
+#' }
 setGeneric("get_token_stream", function(.Object, ...) standardGeneric("get_token_stream"))
 
 
@@ -236,7 +244,7 @@ setMethod("get_token_stream", "regions", function(.Object, p_attribute = "word",
 #' @importFrom stringi stri_c
 #' @importFrom RcppCWB region_matrix_to_ids cl_lexicon_size
 #' @examples 
-#' \donttest{
+#' \dontrun{
 #' # Get token stream for partition_bundle
 #' pb <- partition_bundle("REUTERS", s_attribute = "id")
 #' ts_list <- get_token_stream(pb)
@@ -404,9 +412,9 @@ setOldClass("String")
 #' Decode as String.
 #'
 #' @examples
-#' use("polmineR")
-#' p <- partition("GERMAPARLMINI", date = "2009-11-10", speaker = "Angela Dorothea Merkel")
-#' s <- as(p, "String")
+#' corpus("REUTERS") %>% 
+#'   subset(id == "127") %>% 
+#'   as("String")
 #' @name partition_to_string
 setAs(from = "slice", to = "String", def = function(from){
   word <- get_token_stream(from, p_attribute = "word")