问基于文本文件内容的语料库划分

EN

library(tm)
reut21578 <- system.file("texts", "crude", package = "tm")
corp <- VCorpus(DirSource(reut21578), list(reader = readReut21578XMLasPlain))

( corp_sub <- tm_filter(corp, function(x) any(grep("price reduction", content(x), fixed=TRUE))) )
# <<VCorpus>>
# Metadata:  corpus specific: 0, document level (indexed): 0
# Content:  documents: 1

cat(content(corp_sub[[1]]))
# Diamond Shamrock Corp said that
# effective today it had cut its contract prices for crude oil by
# 1.50 dlrs a barrel.
#     The reduction brings its posted price for West Texas
# Intermediate to 16.00 dlrs a barrel, the copany said.
#     "The price reduction today was made in the light of falling   # <=====
# oil product prices and a weak crude oil market," a company
# spokeswoman said.
#     Diamond is the latest in a line of U.S. oil companies that
# have cut its contract, or posted, prices over the last two days
# citing weak oil markets.
#  Reuter

require(tm)
data(crude)

require(quanteda)
# corpus constructor recognises tm Corpus objects 
(qcorpus <- corpus(crude))
## Corpus consisting of 20 documents.
# use subset method
(qcorpussub <- corpus_subset(qcorpus, grepl("price\\s+reduction", texts(qcorpus))))
## Corpus consisting of 1 document.

# see the context
## kwic(qcorpus, "price reduction")
##                       contextPre         keyword             contextPost
## [127, 45:46] copany said." The [ price reduction ] today was made in the

    library(tm)

        reut21578 <- system.file("texts", "crude", package = "tm")
        corp <- VCorpus(DirSource(reut21578), list(reader = readReut21578XMLasPlain))

        corpTF <- lapply(corp, function(x) any(grep("price reduction", content(x), fixed=TRUE)))

        for(i in 1:length(corp)) 
          corp[[i]]$meta["mySubset"] <- corpTF[i]

        idx <- meta(corp, tag ="mySubset") == 'TRUE'
        filtered <- corp[idx]

        cat(content(filtered[[1]]))