Merge pull request #2345 from quanteda/fix-docs

Minor documentation fixes

R/data-documentation.R

@@ -105,7 +105,7 @@
 #'   Dictionary*. Available at <https://www.snsoroka.com/data-lexicoder/>.
 #'   
 #'   Young, L. & Soroka, S. (2012). Affective News: The Automated Coding of
-#'   Sentiment in Political Texts]. \doi{10.1080/10584609.2012.671234}.
+#'   Sentiment in Political Texts. \doi{10.1080/10584609.2012.671234}.
 #'   *Political Communication*, 29(2), 205--231.
 #' @keywords data
 #' @examples 

R/quanteda-documentation.R

@@ -105,7 +105,7 @@
 #'   (literal) pattern matching.} }
 #' @note If "fixed" is used with `case_insensitive = TRUE`, features will
 #'   typically be lowercased internally prior to matching.  Also, glob matches
-#'   are converted to regular expressions (using [glob2rx][utils::glob2rx]) when
+#'   are converted to regular expressions (using [utils::glob2rx()]) when
 #'   they contain wild card characters, and to fixed pattern matches when they
 #'   do not.
 #' @name valuetype
@@ -124,7 +124,7 @@ NULL
 #'   or collocations object.  See [pattern] for details.
 #' @details The `pattern` argument is a vector of patterns, including
 #'   sequences, to match in a target object, whose match type is specified by
-#'   [valuetype()]. Note that an empty pattern (`""`) will match
+#'   [valuetype]. Note that an empty pattern (`""`) will match
 #'   "padding" in a [tokens] object.
 #'   \describe{
 #'   \item{`character`}{A character vector of token patterns to be selected
@@ -172,6 +172,7 @@ NULL
 #' (dict1 <- dictionary(list(us = c("president", "white house", "house of representatives"))))
 #' phrase(dict1)
 #' @keywords internal
+#' @seealso [valuetype], [case_insensitive]
 NULL
 
 #' Grouping variable(s) for various functions

R/tokens.R

@@ -2,19 +2,21 @@
 
 #' Construct a tokens object
 #'
-#' Construct a tokens object, either by importing a named list of characters
-#' from an external tokenizer, or by calling the internal \pkg{quanteda}
-#' tokenizer.
+#' @description Construct a tokens object, either by importing a named list of
+#'   characters from an external tokenizer, or by calling the internal
+#'   \pkg{quanteda} tokenizer.
 #'
-#' `tokens()` works on tokens class objects, which means that the removal rules
-#' can be applied post-tokenization, although it should be noted that it will
-#' not be possible to remove things that are not present.  For instance, if the
-#' `tokens` object has already had punctuation removed, then `tokens(x,
-#' remove_punct = TRUE)` will have no additional effect.
+#' @description `tokens()` can also be applied to tokens class objects, which
+#'   means that the removal rules can be applied post-tokenization, although it
+#'   should be noted that it will not be possible to remove things that are not
+#'   present.  For instance, if the `tokens` object has already had punctuation
+#'   removed, then `tokens(x, remove_punct = TRUE)` will have no additional
+#'   effect.
 #' @param x the input object to the tokens constructor; a [tokens], [corpus] or
 #'   [character] object to tokenize.
 #' @param what character; which tokenizer to use.  The default `what = "word"`
-#'   is the version 2 \pkg{quanteda} tokenizer.  Legacy tokenizers (version < 2)
+#'   is the current version of the \pkg{quanteda} tokenizer, set by
+#'   `quanteda_options(okens_tokenizer_word)`. Legacy tokenizers (version < 2)
 #'   are also supported, including the default `what = "word1"`. See the Details
 #'   and quanteda Tokenizers below.
 #' @param remove_punct logical; if `TRUE` remove all characters in the Unicode