version 0.1.0

DESCRIPTION

@@ -0,0 +1,28 @@
+Package: bigQueryR
+Title: Interface with Google BigQuery with Shiny Compatibility
+Version: 0.1.0
+Authors@R: c(person("Mark", "Edmondson",email = "r@sunholo.com",
+                  role = c("aut", "cre")),
+             person("Hadley", "Wickham", , "hadley@rstudio.com", role = "ctb")
+                  )
+Description: Interface with Google BigQuery,
+    see <https://cloud.google.com/bigquery/> for more information.
+    This package uses 'googleAuthR' so is compatible with similar packages, 
+    including Google Cloud Storage (<https://cloud.google.com/storage/>) for result extracts. 
+URL: http://code.markedmondson.me/bigQueryR/
+BugReports: https://github.com/MarkEdmondson1234/bigQueryR/issues
+License: MIT + file LICENSE
+LazyData: TRUE
+Depends: R (>= 3.2.0)
+Imports: googleAuthR (>= 0.2.0)
+Suggests: shiny (>= 0.12.1), jsonlite (>= 0.9.21), httr (>= 1.1.0),
+        knitr, rmarkdown
+RoxygenNote: 5.0.1
+VignetteBuilder: knitr
+NeedsCompilation: no
+Packaged: 2016-06-13 15:27:06 UTC; mark
+Author: Mark Edmondson [aut, cre],
+  Hadley Wickham [ctb]
+Maintainer: Mark Edmondson <r@sunholo.com>
+Repository: CRAN
+Date/Publication: 2016-06-13 17:34:46

LICENSE

@@ -0,0 +1,2 @@
+YEAR: 2015
+COPYRIGHT HOLDER: Sunholo Ltd.

MD5

@@ -0,0 +1,44 @@
+6af3f02cc22d5969fa9e040899540ae8 *DESCRIPTION
+6346ec78b27187fcd99986124133fc2a *LICENSE
+3e07399cea02e89908a577cf166f9a3e *NAMESPACE
+0724adb8834a104d543457e8904259b8 *NEWS.md
+648363052aba9854b423375c99657918 *R/bigQueryR.R
+01672f25679abbfa0707f48efd714348 *R/cloudStorage.R
+9b3a51b950a50b6ecd6b406a1be1369a *R/dataParseFunctions.R
+6e7d4522868a48ce86b745c493504282 *R/downloadData.R
+548d7f98d9c1a887ff3c5cfd33d79851 *R/jobs.R
+2e82d5ec073e9d2b36ae027e193f7cbf *R/listBigQuery.R
+440c9973dcb208844c3edb429d0b9802 *R/options.R
+f772297399468e70b3e420a1516a1351 *R/query.R
+c8a80e9159390e4888025b8a8910b029 *R/tables.R
+a72bfa91dafebe6fe204accf2009264c *R/uploadData.R
+f20c09c89a63a3f153f162a16cd64c95 *R/utilities.R
+410890d9694f6f7855d320d4c0dd7a62 *README.md
+b6bf9fa119de5ecadc2965be4246d273 *build/vignette.rds
+9b4c6c4550611f20e113115fb16deda0 *inst/doc/bigQueryR.Rmd
+53ec04dfb822bc54a4119184b36dc788 *inst/doc/bigQueryR.html
+0ab1a7ba9227ed7bdd95302ad44b2645 *man/bigQueryR.Rd
+21dc463667cc1fcdf1031f8d75f666d2 *man/bqr_auth.Rd
+57e2b5ffc089a2058165301bb7a1514e *man/bqr_create_table.Rd
+e56931b4b933cbb94f91186d9bfba040 *man/bqr_delete_table.Rd
+5cead0ce5bf082e5f4ff3c443f396f5b *man/bqr_extract_data.Rd
+31a7d04a4f905fe896d51917ef753c4d *man/bqr_get_job.Rd
+ccbce4a844d3631cf75d6cc173e67ea3 *man/bqr_grant_extract_access.Rd
+eb00021cde39fd03185b5325e3db586e *man/bqr_list_datasets.Rd
+3242264356742e6692fd2381b94fe97f *man/bqr_list_jobs.Rd
+384fc76e5ea61dea13447d889433f663 *man/bqr_list_projects.Rd
+1a1da54c1496a3dd366a896fec099a5b *man/bqr_list_tables.Rd
+8af9a2131e608514747ddd274f42aa03 *man/bqr_query.Rd
+77e44347fe63363cc693ed538c7b0da1 *man/bqr_query_asynch.Rd
+10c0c1853541fe29b740003e4b007400 *man/bqr_table_data.Rd
+75e152274b3fb966adcb1b34517787c9 *man/bqr_table_meta.Rd
+48d94d31a9d1721c054e97c29c2c17ff *man/bqr_upload_data.Rd
+a2f3694cd0d6e26e4d2cb131c35ad424 *man/error.message.Rd
+0d884342e1dce6a8d9dde386ccefa52f *man/gcs_update_acl.Rd
+691565ef7e3c837f1f51d4d6b1b7680a *man/idempotency.Rd
+2240e92cd7767970a3f56d45070895a9 *man/is.NullOb.Rd
+57e5ee063d87b8133cb4785429c9685a *man/is.error.Rd
+172de60e13e30d803506104947d1f6b7 *man/myMessage.Rd
+5eeba1d521d9a6dda8a61512f6891b9a *man/parse_bqr_query.Rd
+fc01bed2025f8af7aff31ab1c21bfef7 *man/rmNullObs.Rd
+9b4c6c4550611f20e113115fb16deda0 *vignettes/bigQueryR.Rmd

NAMESPACE

@@ -0,0 +1,17 @@
+# Generated by roxygen2: do not edit by hand
+
+export(bqr_auth)
+export(bqr_create_table)
+export(bqr_delete_table)
+export(bqr_extract_data)
+export(bqr_get_job)
+export(bqr_grant_extract_access)
+export(bqr_list_datasets)
+export(bqr_list_jobs)
+export(bqr_list_projects)
+export(bqr_list_tables)
+export(bqr_query)
+export(bqr_query_asynch)
+export(bqr_table_data)
+export(bqr_table_meta)
+export(bqr_upload_data)

NEWS.md

@@ -0,0 +1,7 @@
+# bigQueryR 0.1.0
+
+* Added a `NEWS.md` file to track changes to the package.
+* Initial release
+
+
+

R/bigQueryR.R

@@ -0,0 +1,45 @@
+#' bigQueryR
+#' 
+#' Provides an interface with Google BigQuery
+#' 
+#' @seealso \url{https://cloud.google.com/bigquery/docs/reference/v2/?hl=en}
+#' 
+#' @docType package
+#' @name bigQueryR
+NULL
+
+#' Do OAuth2 authentication
+#' 
+#' @param token An existing OAuth2 token, if you have one.
+#' @param new_user Set to TRUE if you want to go through the authentication flow again.
+#' 
+#' @details 
+#' This function just wraps \code{\link[googleAuthR]{gar_auth}} from googleAuthR, 
+#'   but means you don't need to explictly load that library.
+#'   
+#' @seealso \code{\link[googleAuthR]{gar_auth}}
+#' 
+#' @examples 
+#' 
+#' \dontrun{
+#'   library(bigQueryR)
+#'   
+#'   ## this will open your browser
+#'   ## Authenticate with an email that has access to the BigQuery project you need
+#'   bqr_auth()
+#'   
+#'   ## verify under a new user
+#'   bqr_auth(new_user=TRUE)
+#'   
+#' }
+#' 
+#' @family bigQuery meta functions
+#' @export
+bqr_auth <- function(token=NULL, new_user=FALSE){
+  options("googleAuthR.scopes.selected" = getOption("bigQueryR.scope") )
+  options("googleAuthR.client_id" = getOption("bigQueryR.client_id"))
+  options("googleAuthR.client_secret" = getOption("bigQueryR.client_secret"))
+  options("googleAuthR.webapp.client_id" = getOption("bigQueryR.webapp.client_id"))
+  options("googleAuthR.webapp.client_secret" = getOption("bigQueryR.webapp.client_secret"))
+  googleAuthR::gar_auth(token=token, new_user=new_user)
+}

R/cloudStorage.R

@@ -0,0 +1,104 @@
+#' Update Google Cloud Storage ObjectAccessControls
+#' 
+#' Requires scopes set in bigQuery.scopes
+#'   \code{https://www.googleapis.com/auth/devstorage.full_control}
+#'   \code{https://www.googleapis.com/auth/cloud-platform}
+#' 
+#' @param bucket Google Cloud Storage bucket
+#' @param object Object to update
+#' @param entity entity to update or add
+#' @param entity_type what type of entity
+#' @param role Access permission for entity
+#' 
+#' @seealso \href{https://cloud.google.com/storage/docs/json_api/v1/objectAccessControls/insert}{objectAccessControls on Google API reference}
+#' 
+#' @examples 
+#' 
+#' \dontrun{
+#' library(bigQueryR)
+#' 
+#' ## Auth with a project that has at least BigQuery and Google Cloud Storage scope
+#' bqr_auth()
+#' 
+#' ## make a big query
+#' job <- bqr_query_asynch("your_project", 
+#'                         "your_dataset",
+#'                         "SELECT * FROM blah LIMIT 9999999", 
+#'                         destinationTableId = "bigResultTable")
+#'                         
+#' ## poll the job to check its status
+#' ## its done when job$status$state == "DONE"
+#' bqr_get_job("your_project", job$jobReference$jobId)
+#' 
+#' ##once done, the query results are in "bigResultTable"
+#' ## extract that table to GoogleCloudStorage:
+#' # Create a bucket at Google Cloud Storage at 
+#' # https://console.cloud.google.com/storage/browser
+#' 
+#' job_extract <- bqr_extract_data("your_project",
+#'                                 "your_dataset",
+#'                                 "bigResultTable",
+#'                                 "your_cloud_storage_bucket_name")
+#'                                 
+#' ## poll the extract job to check its status
+#' ## its done when job$status$state == "DONE"
+#' bqr_get_job("your_project", job_extract$jobReference$jobId)
+#' 
+#' ## to download via a URL and not logging in via Google Cloud Storage interface:
+#' ## Use an email that is Google account enabled
+#' ## Requires scopes:
+#' ##  https://www.googleapis.com/auth/devstorage.full_control
+#' ##  https://www.googleapis.com/auth/cloud-platform
+#' ## set via options("bigQueryR.scopes") and reauthenticate if needed
+#' 
+#' download_url <- bqr_grant_extract_access(job_extract, "your@email.com")
+#' 
+#' ## download_url may be multiple if the data is > 1GB
+#' 
+#' }
+#' 
+#' @family bigQuery upload functions
+#' @return TRUE if successful
+gcs_update_acl <- function(bucket,
+                           object,
+                           entity,
+                           entity_type = c("user",
+                                           "group",
+                                           "domian",
+                                           "project",
+                                           "allUsers",
+                                           "allAuthenticatedUsers"),
+                           role = c("READER","OWNER")){
+
+  entity_type <- match.arg(entity_type)
+  role <- match.arg(role)
+
+  stopifnot(inherits(bucket, "character"),
+            inherits(object, "character"),
+            inherits(entity, "character"))
+
+  accessControls <- list(
+    entity = paste0(entity_type,"-",entity),
+    role = role
+  )
+
+  insert <- 
+    googleAuthR::gar_api_generator("https://www.googleapis.com/storage/v1",
+                                   "POST",
+                                   path_args = list(b = bucket,
+                                                    o = object,
+                                                    acl = ""))
+
+  req <- insert(path_arguments = list(b = bucket, o = object),
+                the_body = accessControls)
+
+  if(req$status_code == 200){
+    myMessage("Access updated")
+    out <- TRUE
+  } else {
+    stop("Error setting access")
+  }
+
+  out
+
+}

R/dataParseFunctions.R

@@ -0,0 +1,36 @@
+#' Parse table data
+#' 
+#' @keywords internal
+parse_bqr_query <- function(x){
+
+  converter <- list(
+    integer = as.integer,
+    float = as.double,
+    boolean = as.logical,
+    string = identity,
+    timestamp = function(x) as.POSIXct(as.integer(x), origin = "1970-01-01", tz = "UTC")
+  )
+
+  schema <- x$schema$fields
+
+  ## when only one row, it makes it 3 obs. of 1 variable instead of 1 obs. of 3
+  data_f <- as.data.frame(Reduce(rbind, lapply(x$rows$f, function(x) x$v)), 
+                          stringsAsFactors = FALSE)
+
+  types <- tolower(schema$type)
+
+  out <- vector("list", length(types))
+  for(i in seq_along(types)){
+    ## this needs to behave when only length 1
+    out[[i]] <- converter[[types[i]]](data_f[,i])
+  }
+  names(out) <- schema$name
+
+  out <- as.data.frame(out, stringsAsFactors = FALSE)
+  attr(out, "jobReference") <- x$jobReference
+  attr(out, "pageToken") <- x$pageToken
+
+  out
+
+
+}