Parametrize regex filter for collocates as collocateFilterRegex
Change-Id: I58009cf7b786eab322bf64492965f9f1f664dc04
diff --git a/R/collocationAnalysis.R b/R/collocationAnalysis.R
index 483c20c..5e3f7dd 100644
--- a/R/collocationAnalysis.R
+++ b/R/collocationAnalysis.R
@@ -34,6 +34,7 @@
#' @param exactFrequencies if FALSE, extrapolate observed co-occurrence frequencies from frequencies in search hits sample, otherwise retrieve exact co-occurrence frequencies
#' @param seed seed for random page collecting order
#' @param expand if TRUE, `node` and `vc` parameters are expanded to all of their combinations
+#' @param collocateFilterRegex allow only collocates matching the regular expression
#' @param ... more arguments will be passed to [collocationScoreQuery()]
#' @inheritParams collocationScoreQuery,KorAPConnection-method
#' @return Tibble with top collocates, association scores, corresponding URLs for web user interface queries, etc.
@@ -84,6 +85,7 @@
thresholdScore = "logDice",
threshold = 2.0,
localStopwords = c(),
+ collocateFilterRegex = '^[:alnum:]+-?[:alnum:]*$',
...) {
# https://stackoverflow.com/questions/8096313/no-visible-binding-for-global-variable-note-in-r-cmd-check
word <- frequency <- NULL
@@ -227,6 +229,7 @@
ignoreCollocateCase = FALSE,
stopwords = c(),
tokenizeRegex = "([! )(\uc2\uab,.:?\u201e\u201c\'\"]+|")",
+ collocateFilterRegex = '^[:alnum:]+-?[:alnum:]*$',
oldTable = data.frame(word = rep(NA, 1), frequency = rep(NA, 1)),
verbose = TRUE) {
word <- NULL # https://stackoverflow.com/questions/8096313/no-visible-binding-for-global-variable-note-in-r-cmd-check
@@ -241,6 +244,7 @@
s,
leftContextSize = leftContextSize,
rightContextSize = rightContextSize,
+ collocateFilterRegex = collocateFilterRegex,
oldTable = oldTable,
stopwords = stopwords
)
@@ -277,7 +281,7 @@
table(c(left, right)) %>%
dplyr::as_tibble(.name_repair = "minimal") %>%
dplyr::rename(word = 1, frequency = 2) %>%
- dplyr::filter(str_detect(word, '^[:alnum:]+-?[:alnum:]*$')) %>%
+ dplyr::filter(str_detect(word, collocateFilterRegex)) %>%
dplyr::anti_join(stopwordsTable, by="word") %>%
dplyr::bind_rows(oldTable)
}
@@ -408,6 +412,7 @@
rightContextSize = rightContextSize,
ignoreCollocateCase = ignoreCollocateCase,
stopwords = stopwords,
+ ...,
verbose = kco@verbose) %>%
mutate(frequency = frequency * q@totalResults / min(q@totalResults, searchHitsSampleLimit)) %>%
filter(frequency >= minOccur)
diff --git a/man/collocationAnalysis-KorAPConnection-method.Rd b/man/collocationAnalysis-KorAPConnection-method.Rd
index 1862f21..754dce4 100644
--- a/man/collocationAnalysis-KorAPConnection-method.Rd
+++ b/man/collocationAnalysis-KorAPConnection-method.Rd
@@ -26,6 +26,7 @@
thresholdScore = "logDice",
threshold = 2,
localStopwords = c(),
+ collocateFilterRegex = "^[:alnum:]+-?[:alnum:]*$",
...
)
}
@@ -60,6 +61,8 @@
\item{expand}{if TRUE, \code{node} and \code{vc} parameters are expanded to all of their combinations}
+\item{collocateFilterRegex}{allow only collocates matching the regular expression}
+
\item{...}{more arguments will be passed to \code{\link[=collocationScoreQuery]{collocationScoreQuery()}}}
}
\value{