blob: 97000dea360aeec679ee3b0b73f6fbb21c5583f5 [file] [log] [blame]
Marc Kupietze95108e2019-09-18 13:23:58 +02001% Generated by roxygen2: do not edit by hand
2% Please edit documentation in R/KorAPQuery.R
3\docType{class}
4\name{KorAPQuery-class}
5\alias{KorAPQuery-class}
6\alias{KorAPQuery}
7\alias{initialize,KorAPQuery-method}
Marc Kupietzdbd431a2021-08-29 12:17:45 +02008\alias{corpusQuery,KorAPConnection-method}
9\alias{corpusQuery}
Marc Kupietze95108e2019-09-18 13:23:58 +020010\alias{fetchNext,KorAPQuery-method}
11\alias{fetchNext}
12\alias{fetchAll,KorAPQuery-method}
13\alias{fetchAll}
14\alias{fetchRest,KorAPQuery-method}
15\alias{fetchRest}
Marc Kupietz3f575282019-10-04 14:46:04 +020016\alias{frequencyQuery,KorAPConnection-method}
17\alias{frequencyQuery}
Marc Kupietzdbd431a2021-08-29 12:17:45 +020018\alias{buildWebUIRequestUrl}
Marc Kupietze95108e2019-09-18 13:23:58 +020019\alias{format.KorAPQuery}
20\alias{show,KorAPQuery-method}
21\title{Class KorAPQuery}
22\usage{
Marc Kupietz76685f52019-11-25 17:46:06 +010023\S4method{initialize}{KorAPQuery}(
24 .Object,
25 korapConnection = NULL,
26 request = NULL,
27 vc = "",
28 totalResults = 0,
29 nextStartIndex = 0,
30 fields = c("corpusSigle", "textSigle", "pubDate", "pubPlace", "availability",
31 "textClass", "snippet"),
32 requestUrl = "",
33 webUIRequestUrl = "",
34 apiResponse = NULL,
35 hasMoreMatches = FALSE,
36 collectedMatches = NULL
37)
Marc Kupietze95108e2019-09-18 13:23:58 +020038
Marc Kupietzdbd431a2021-08-29 12:17:45 +020039\S4method{corpusQuery}{KorAPConnection}(
40 kco,
41 query = if (missing(KorAPUrl))
42 stop("At least one of the parameters query and KorAPUrl must be specified.", call. =
43 FALSE) else httr::parse_url(KorAPUrl)$query$q,
44 vc = if (missing(KorAPUrl)) "" else httr::parse_url(KorAPUrl)$query$cq,
45 KorAPUrl,
46 metadataOnly = TRUE,
47 ql = if (missing(KorAPUrl)) "poliqarp" else httr::parse_url(KorAPUrl)$query$ql,
48 fields = c("corpusSigle", "textSigle", "pubDate", "pubPlace", "availability",
49 "textClass", "snippet"),
50 accessRewriteFatal = TRUE,
51 verbose = kco@verbose,
52 expand = length(vc) != length(query),
53 as.df = FALSE
54)
55
Marc Kupietz76685f52019-11-25 17:46:06 +010056\S4method{fetchNext}{KorAPQuery}(
57 kqo,
58 offset = kqo@nextStartIndex,
59 maxFetch = maxResultsPerPage,
Marc Kupietzdbd431a2021-08-29 12:17:45 +020060 verbose = kqo@korapConnection@verbose,
61 randomizePageOrder = FALSE
Marc Kupietz76685f52019-11-25 17:46:06 +010062)
Marc Kupietze95108e2019-09-18 13:23:58 +020063
Marc Kupietzdbd431a2021-08-29 12:17:45 +020064\S4method{fetchAll}{KorAPQuery}(kqo, verbose = kqo@korapConnection@verbose, ...)
Marc Kupietze95108e2019-09-18 13:23:58 +020065
Marc Kupietzdbd431a2021-08-29 12:17:45 +020066\S4method{fetchRest}{KorAPQuery}(kqo, verbose = kqo@korapConnection@verbose, ...)
Marc Kupietze95108e2019-09-18 13:23:58 +020067
Marc Kupietz76685f52019-11-25 17:46:06 +010068\S4method{frequencyQuery}{KorAPConnection}(
69 kco,
70 query,
71 vc = "",
72 conf.level = 0.95,
73 as.alternatives = FALSE,
74 ...
75)
Marc Kupietz3f575282019-10-04 14:46:04 +020076
Marc Kupietzdbd431a2021-08-29 12:17:45 +020077buildWebUIRequestUrl(
78 kco,
79 query = if (missing(KorAPUrl))
80 stop("At least one of the parameters query and KorAPUrl must be specified.", call. =
81 FALSE) else httr::parse_url(KorAPUrl)$query$q,
82 vc = if (missing(KorAPUrl)) "" else httr::parse_url(KorAPUrl)$query$cq,
83 KorAPUrl,
84 metadataOnly = TRUE,
85 ql = if (missing(KorAPUrl)) "poliqarp" else httr::parse_url(KorAPUrl)$query$ql,
86 fields = c("corpusSigle", "textSigle", "pubDate", "pubPlace", "availability",
87 "textClass", "snippet"),
88 accessRewriteFatal = TRUE
89)
90
Marc Kupietze95108e2019-09-18 13:23:58 +020091\method{format}{KorAPQuery}(x, ...)
92
93\S4method{show}{KorAPQuery}(object)
94}
95\arguments{
96\item{.Object}{}
97
Marc Kupietzb8972182019-09-20 21:33:46 +020098\item{korapConnection}{KorAPConnection object}
99
Marc Kupietze95108e2019-09-18 13:23:58 +0200100\item{request}{query part of the request URL}
101
Marc Kupietze2038322021-03-04 18:24:02 +0100102\item{vc}{string describing the virtual corpus in which the query should be performed. An empty string (default) means the whole corpus, as far as it is license-wise accessible.}
Marc Kupietze95108e2019-09-18 13:23:58 +0200103
104\item{totalResults}{number of hits the query has yielded}
105
106\item{nextStartIndex}{at what index to start the next fetch of query results}
107
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200108\item{fields}{(meta)data fields that will be fetched for every match.}
Marc Kupietze95108e2019-09-18 13:23:58 +0200109
110\item{requestUrl}{complete URL of the API request}
111
112\item{webUIRequestUrl}{URL of a web frontend request corresponding to the API request}
113
114\item{apiResponse}{data-frame representation of the JSON response of the API request}
115
Marc Kupietz7776dec2019-09-27 16:59:02 +0200116\item{hasMoreMatches}{logical that signals if more query results can be fetched}
Marc Kupietze95108e2019-09-18 13:23:58 +0200117
118\item{collectedMatches}{matches already fetched from the KorAP-API-server}
119
Marc Kupietz67edcb52021-09-20 21:54:24 +0200120\item{kco}{\code{\link[=KorAPConnection]{KorAPConnection()}} object (obtained e.g. from \code{new("KorAPConnection")}}
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200121
122\item{query}{string that contains the corpus query. The query language depends on the \code{ql} parameter. Either \code{query} must be provided or \code{KorAPUrl}.}
123
124\item{KorAPUrl}{instead of providing the query and vc string parameters, you can also simply copy a KorAP query URL from your browser and use it here (and in \code{KorAPConnection}) to provide all necessary information for the query.}
125
Marc Kupietz132f0052023-04-16 14:23:05 +0200126\item{metadataOnly}{logical that determines whether queries should return only metadata without any snippets. This can also be useful to prevent access rewrites. Note that the default value is TRUE.
127If you want your corpus queries to return not only metadata, but also KWICS, you need to authorize
128your RKorAPClient application as explained in the
129\href{https://github.com/KorAP/RKorAPClient#authorization}{authorization section}
130of the RKorAPClient Readme on GitHub and set the \code{metadataOnly} parameter to
131\code{FALSE}.}
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200132
133\item{ql}{string to choose the query language (see \href{https://github.com/KorAP/Kustvakt/wiki/Service:-Search-GET#user-content-parameters}{section on Query Parameters} in the Kustvakt-Wiki for possible values.}
134
135\item{accessRewriteFatal}{abort if query or given vc had to be rewritten due to insufficient rights (not yet implemented).}
136
137\item{verbose}{print progress information if true}
138
139\item{expand}{logical that decides if \code{query} and \code{vc} parameters are expanded to all of their combinations}
140
141\item{as.df}{return result as data frame instead of as S4 object?}
142
Marc Kupietz67edcb52021-09-20 21:54:24 +0200143\item{kqo}{object obtained from \code{\link[=corpusQuery]{corpusQuery()}}}
Marc Kupietze95108e2019-09-18 13:23:58 +0200144
145\item{offset}{start offset for query results to fetch}
146
147\item{maxFetch}{maximum number of query results to fetch}
148
Marc Kupietz67edcb52021-09-20 21:54:24 +0200149\item{randomizePageOrder}{fetch result pages in pseudo random order if true. Use \code{\link[=set.seed]{set.seed()}} to set seed for reproducible results.}
Marc Kupietze95108e2019-09-18 13:23:58 +0200150
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200151\item{...}{further arguments passed to or from other methods}
Marc Kupietze95108e2019-09-18 13:23:58 +0200152
Marc Kupietz67edcb52021-09-20 21:54:24 +0200153\item{conf.level}{confidence level of the returned confidence interval (passed through \code{\link[=ci]{ci()}} to \code{\link[=prop.test]{prop.test()}}).}
Marc Kupietz0c29cea2019-10-09 08:44:36 +0200154
Marc Kupietz71d6e052019-11-22 18:42:10 +0100155\item{as.alternatives}{LOGICAL that specifies if the query terms should be treated as alternatives. If \code{as.alternatives} is TRUE, the sum over all query hits, instead of the respective vc token sizes is used as total for the calculation of relative frequencies.}
156
Marc Kupietz3f575282019-10-04 14:46:04 +0200157\item{x}{KorAPQuery object}
158
Marc Kupietze95108e2019-09-18 13:23:58 +0200159\item{object}{KorAPQuery object}
160}
161\value{
Marc Kupietz67edcb52021-09-20 21:54:24 +0200162Depending on the \code{as.df} parameter, a table or a \code{\link[=KorAPQuery]{KorAPQuery()}} object that, among other information, contains the total number of results in \verb{@totalResults}. The resulting object can be used to fetch all query results (with \code{\link[=fetchAll]{fetchAll()}}) or the next page of results (with \code{\link[=fetchNext]{fetchNext()}}).
163A corresponding URL to be used within a web browser is contained in \verb{@webUIRequestUrl}
164Please make sure to check \verb{$collection$rewrites} to see if any unforeseen access rewrites of the query's virtual corpus had to be performed.
Marc Kupietze2038322021-03-04 18:24:02 +0100165
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200166The \code{kqo} input object with updated slots \code{collectedMatches}, \code{apiResponse}, \code{nextStartIndex}, \code{hasMoreMatches}
Marc Kupietze95108e2019-09-18 13:23:58 +0200167}
168\description{
Marc Kupietza6e4ee62021-03-05 09:00:15 +0100169This class provides methods to perform different kinds of queries on the KorAP API server.
Marc Kupietz67edcb52021-09-20 21:54:24 +0200170\code{KorAPQuery} objects, which are typically created by the \code{\link[=corpusQuery]{corpusQuery()}} method,
Marc Kupietza6e4ee62021-03-05 09:00:15 +0100171represent the current state of a query to a KorAP server.
Marc Kupietz3f575282019-10-04 14:46:04 +0200172
Marc Kupietz67edcb52021-09-20 21:54:24 +0200173\strong{\code{corpusQuery}} performs a corpus query via a connection to a KorAP-API-server
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200174
Marc Kupietz67edcb52021-09-20 21:54:24 +0200175\strong{\code{fetchNext}} fetches the next bunch of results of a KorAP query.
Marc Kupietz3f575282019-10-04 14:46:04 +0200176
Marc Kupietz67edcb52021-09-20 21:54:24 +0200177\strong{\code{fetchAll}} fetches all results of a KorAP query.
Marc Kupietza6e4ee62021-03-05 09:00:15 +0100178
Marc Kupietz67edcb52021-09-20 21:54:24 +0200179\strong{\code{frequencyQuery}} combines \code{\link[=corpusQuery]{corpusQuery()}}, \code{\link[=corpusStats]{corpusStats()}} and
180\code{\link[=ci]{ci()}} to compute a table with the relative frequencies and
Marc Kupietz3f575282019-10-04 14:46:04 +0200181confidence intervals of one ore multiple search terms across one or multiple
182virtual corpora.
Marc Kupietze95108e2019-09-18 13:23:58 +0200183}
184\examples{
Marc Kupietz6ae76052021-09-21 10:34:00 +0200185\dontrun{
186
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200187# Fetch metadata of every query hit for "Ameisenplage" and show a summary
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200188new("KorAPConnection") \%>\% corpusQuery("Ameisenplage") \%>\% fetchAll()
189}
190
Marc Kupietz6ae76052021-09-21 10:34:00 +0200191\dontrun{
192
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200193# Use the copy of a KorAP-web-frontend URL for an API query of "Ameise" in a virtual corpus
194# and show the number of query hits (but don't fetch them).
195
196new("KorAPConnection", verbose = TRUE) \%>\%
197 corpusQuery(KorAPUrl =
198 "https://korap.ids-mannheim.de/?q=Ameise&cq=pubDate+since+2017&ql=poliqarp")
Marc Kupietz6ae76052021-09-21 10:34:00 +0200199}
200
201\dontrun{
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200202
203# Plot the time/frequency curve of "Ameisenplage"
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200204new("KorAPConnection", verbose=TRUE) \%>\%
205 { . ->> kco } \%>\%
206 corpusQuery("Ameisenplage") \%>\%
207 fetchAll() \%>\%
208 slot("collectedMatches") \%>\%
209 mutate(year = lubridate::year(pubDate)) \%>\%
210 dplyr::select(year) \%>\%
211 group_by(year) \%>\%
212 summarise(Count = dplyr::n()) \%>\%
213 mutate(Freq = mapply(function(f, y)
214 f / corpusStats(kco, paste("pubDate in", y))@tokens, Count, year)) \%>\%
215 dplyr::select(-Count) \%>\%
216 complete(year = min(year):max(year), fill = list(Freq = 0)) \%>\%
217 plot(type = "l")
218}
Marc Kupietz6ae76052021-09-21 10:34:00 +0200219\dontrun{
220
221q <- new("KorAPConnection") \%>\% corpusQuery("Ameisenplage") \%>\% fetchNext()
Marc Kupietze95108e2019-09-18 13:23:58 +0200222q@collectedMatches
Marc Kupietz657d8e72020-02-25 18:31:50 +0100223}
Marc Kupietze95108e2019-09-18 13:23:58 +0200224
Marc Kupietz6ae76052021-09-21 10:34:00 +0200225\dontrun{
226
Marc Kupietz69cc54a2019-09-30 12:06:54 +0200227q <- new("KorAPConnection") \%>\% corpusQuery("Ameisenplage") \%>\% fetchAll()
Marc Kupietze95108e2019-09-18 13:23:58 +0200228q@collectedMatches
Marc Kupietz05b22772020-02-18 21:58:42 +0100229}
Marc Kupietze95108e2019-09-18 13:23:58 +0200230
Marc Kupietz6ae76052021-09-21 10:34:00 +0200231\dontrun{
232
Marc Kupietz05b22772020-02-18 21:58:42 +0100233q <- new("KorAPConnection") \%>\% corpusQuery("Ameisenplage") \%>\% fetchRest()
234q@collectedMatches
235}
236
Marc Kupietz6ae76052021-09-21 10:34:00 +0200237\dontrun{
238
Marc Kupietz3f575282019-10-04 14:46:04 +0200239new("KorAPConnection", verbose = TRUE) \%>\%
240 frequencyQuery(c("Mücke", "Schnake"), paste0("pubDate in ", 2000:2003))
Marc Kupietz05b22772020-02-18 21:58:42 +0100241}
Marc Kupietz3f575282019-10-04 14:46:04 +0200242
Marc Kupietze95108e2019-09-18 13:23:58 +0200243}
244\references{
245\url{https://ids-pub.bsz-bw.de/frontdoor/index/index/docId/9026}
Marc Kupietzdbd431a2021-08-29 12:17:45 +0200246
247\url{https://ids-pub.bsz-bw.de/frontdoor/index/index/docId/9026}
248}
249\seealso{
Marc Kupietz67edcb52021-09-20 21:54:24 +0200250\code{\link[=KorAPConnection]{KorAPConnection()}}, \code{\link[=fetchNext]{fetchNext()}}, \code{\link[=fetchRest]{fetchRest()}}, \code{\link[=fetchAll]{fetchAll()}}, \code{\link[=corpusStats]{corpusStats()}}
Marc Kupietze95108e2019-09-18 13:23:58 +0200251}