Updated

Author: ParamThakkar123

data/CommonDataModel/.Rbuildignore

@@ -0,0 +1,9 @@
+^.*\.Rproj$
+^\.Rproj\.user$
+^LICENSE\.md$
+.github/*
+extras/*
+docs/*
+rmd/*
+^CRAN-SUBMISSION$
+^cran-comments\.md$

data/CommonDataModel/.gitignore

@@ -0,0 +1,17 @@
+.Rproj.user
+.Rhistory
+.RData
+.Ruserdata
+extras/CodeToRun.R
+
+# OS generated files #
+######################
+.DS_Store
+.DS_Store?
+._*
+.Spotlight-V100
+.Trashes
+ehthumbs.db
+Thumbs.db
+extras/codeToRun.R
+output/

data/CommonDataModel/CRAN-SUBMISSION

@@ -0,0 +1,3 @@
+Version: 1.0.1
+Date: 2024-10-01 17:22:58 UTC
+SHA: 17b2d139c7e982c33cd8abb2ea7db0cd104e756a

data/CommonDataModel/CommonDataModel.Rproj

@@ -0,0 +1,21 @@
+Version: 1.0
+
+RestoreWorkspace: Default
+SaveWorkspace: Default
+AlwaysSaveHistory: Default
+
+EnableCodeIndexing: Yes
+UseSpacesForTab: Yes
+NumSpacesForTab: 2
+Encoding: UTF-8
+
+RnwWeave: Sweave
+LaTeX: XeLaTeX
+
+AutoAppendNewline: Yes
+StripTrailingWhitespace: Yes
+
+BuildType: Package
+PackageUseDevtools: Yes
+PackageInstallArgs: --no-multiarch --with-keep.source
+PackageRoxygenize: rd,collate,namespace

data/CommonDataModel/DESCRIPTION

@@ -0,0 +1,31 @@
+Package: CommonDataModel
+Type: Package
+Title: OMOP CDM DDL and Documentation Generator
+Version: 1.0.1
+Authors@R: person(given = "Clair",
+                    family = "Blacketer",
+                    role = c("aut", "cre"),
+                    email = "mblacke@its.jnj.com")
+Maintainer: Clair Blacketer <mblacke@its.jnj.com>
+Description: Generates the scripts required to create an Observational Medical Outcomes Partnership (OMOP) Common Data Model (CDM) database and associated documentation for supported database platforms. Leverages the 'SqlRender' package to convert the Data Definition Language (DDL) script written in parameterized Structured Query Language (SQL) to the other supported dialects.
+License: Apache License 2.0
+Encoding: UTF-8
+LazyData: true
+Depends:
+  DatabaseConnector,
+  SqlRender,
+  rJava
+Imports: 
+  rmarkdown,
+  stringr,
+  DBI,
+  dplyr,
+  readr
+Suggests:
+    knitr,
+    testthat (>= 3.0.0),
+    RSQLite,
+    withr
+NeedsCompilation: no
+RoxygenNote: 7.2.3
+Config/testthat/edition: 3

data/CommonDataModel/NAMESPACE

@@ -0,0 +1,22 @@
+# Generated by roxygen2: do not edit by hand
+
+export(buildRelease)
+export(buildReleaseZip)
+export(createDdl)
+export(createForeignKeys)
+export(createPrimaryKeys)
+export(downloadCurrentDdl)
+export(executeDdl)
+export(listSupportedDialects)
+export(listSupportedVersions)
+export(parseWiki)
+export(writeDdl)
+export(writeForeignKeys)
+export(writeIndex)
+export(writePrimaryKeys)
+import(DatabaseConnector)
+import(SqlRender)
+import(rJava)
+importFrom(utils,download.file)
+importFrom(utils,read.csv)
+importFrom(utils,write.csv)

data/CommonDataModel/NEWS.md

@@ -0,0 +1,10 @@
+CommonDataModel v5.4.2
+======================
+
+Bigfixes:
+
+1. Removed package test that was causing issues with downstream dependencies (test-BuildRelease.R)
+
+Documentation:
+
+1. Updated documentation for the OMOP Common Data Model based on the April Olympians 2024 initiative.

data/CommonDataModel/R/CommonDataModel-package.R

@@ -0,0 +1,4 @@
+#' @import rJava
+#' @import DatabaseConnector
+#' @import SqlRender
+NULL

data/CommonDataModel/R/WikiParser.R

@@ -0,0 +1,70 @@
+# Copyright 2017 Observational Health Data Sciences and Informatics
+#
+# This file is part of DDLGeneratr
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+#' Parse Wiki files
+#'
+#' @description
+#' Parses all .md files in the specified location (or any subfolders), extracting definitions
+#' of the Common Data Model.
+#'
+#' @param mdFilesLocation Path to the root folder of the Wiki repository.
+#' @param output_file     Path to where the output CSV file should be written.
+#' @return CSV files with the OMOP CDM specifications.
+#' @importFrom utils write.csv
+#' @export
+parseWiki <- function(mdFilesLocation, output_file) {
+  # mdFilesLocation <- "../CommonDataModel.wiki"
+  files <- list.files(mdFilesLocation, pattern = ".*\\.md", recursive = TRUE, full.names = TRUE)
+  file <- files[18]
+  parseTableRow <- function(row) {
+    cells <- stringr::str_trim(stringr::str_split(row, "\\|")[[1]])
+    if (substr(row, 1, 1) == "|") {
+      cells <- cells[2:5]
+    }
+    return(data.frame(field = tolower(cells[1]),
+                      required = cells[2],
+                      type = toupper(cells[3]),
+                      description = cells[4]))
+  }
+
+  parseMdFile <- function(file) {
+    text <- readChar(file, file.info(file)$size)
+    lines <- stringr::str_split(text, "\n")[[1]]
+    lines <- stringr::str_trim(lines)
+    tableStart <- grep("\\s*field\\s*\\|\\s*required\\s*\\|\\s*type\\s*\\|\\s*description\\s*", tolower(lines))
+    if (length(tableStart) > 1)
+      stop("More than one table definition found in ", file)
+
+    if (length(tableStart) == 1) {
+      tableName <- basename(file)
+      tableName <- tolower(stringr::str_sub(tableName, 1, -4))
+      writeLines(paste("Parsing table", tableName))
+      tableStart <- tableStart + 2
+      tableEnd <- c(which(lines == ""), length(lines) + 1)
+      tableEnd <- min(tableEnd[tableEnd > tableStart]) - 1
+      tableDefinition <- lapply(lines[tableStart:tableEnd], parseTableRow)
+      tableDefinition <- do.call(rbind, tableDefinition)
+      tableDefinition$table <- tableName
+      return(tableDefinition)
+    } else {
+      return(NULL)
+    }
+  }
+  tableDefinitions <- lapply(files, parseMdFile)
+  tableDefinitions <- do.call(rbind, tableDefinitions)
+  write.csv(tableDefinitions, output_file, row.names = FALSE)
+}

data/CommonDataModel/R/buildRelease.R

@@ -0,0 +1,102 @@
+# Copyright 2019 Observational Health Data Sciences and Informatics
+#
+# This file is part of CdmDdlBase
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+#' Create OMOP CDM SQL files
+#'
+#' Writes DDL, ForeignKey, PrimaryKey and index SQL files for given cdmVersion
+#' and targetDialect to the 'ddl' folder in specified output folder.
+#'
+#' @param cdmVersions The versions of the CDM you are creating, e.g. 5.3, 5.4.
+#'                   Defaults to all supported CDM versions.
+#' @param targetDialects A character vector of target dialects.
+#'                      Defaults to all supported dialects.
+#' @param outputfolder The base folder where the SQL files will be written.
+#'                     Subfolders will be created for each cdmVersion and targetDialect.
+#' @return Writes DDL, ForeignKey, PrimaryKey and index SQL files for given cdmVersion
+#'         and targetDialect to the 'ddl' folder in specified output folder.
+#' @export
+buildRelease <- function(cdmVersions = listSupportedVersions(),
+                         targetDialects = listSupportedDialects(),
+                         outputfolder = file.path(tempdir(), "inst", "ddl")){
+  basefolder <- outputfolder
+  for (cdmVersion in cdmVersions) {
+    for (targetDialect in targetDialects) {
+      outputfolder <- file.path(basefolder, cdmVersion, gsub(" ", "_", targetDialect))
+
+      writeDdl(targetDialect = targetDialect,
+               cdmVersion = cdmVersion,
+               outputfolder = outputfolder)
+
+      writePrimaryKeys(targetDialect = targetDialect,
+                       cdmVersion = cdmVersion,
+                       outputfolder = outputfolder)
+
+      writeForeignKeys(targetDialect = targetDialect,
+                       cdmVersion = cdmVersion,
+                       outputfolder = outputfolder)
+
+      writeIndex(targetDialect = targetDialect,
+                 cdmVersion = cdmVersion,
+                 outputfolder = outputfolder)
+    }
+  }
+}
+
+#' Create OMOP CDM release zip
+#'
+#' First calls \code{buildReleaseZips} for given cdmVersions and targetDialects.
+#' This writes the ddl sql files to the ddl folder.
+#' Then zips all written ddl files into a release zip to given output folder.
+#'
+#' If no (or multiple) targetDialect is given,
+#' then one zip is written with the files of all supported dialects.
+#'
+#' @param cdmVersion The version of the CDM you are creating, e.g. 5.3, 5.4.
+#'                   Defaults to all supported CDM versions.
+#' @param targetDialect The target dialect. Defaults to all supported dialects.
+#' @param outputfolder The output folder. Defaults to "output"
+#' @return A character string containing the OHDSQL DDL
+#' @export
+#' @examples
+#'\dontrun{
+#' buildReleaseZip(cdmVersion='5.3', targetDialect='sql server', outputfolder='.')
+#'}
+buildReleaseZip <- function(cdmVersion,
+                            targetDialect = listSupportedDialects(),
+                            outputfolder = file.path(tempdir(), "output")){
+  # argument checks
+  stopifnot(is.character(cdmVersion), length(cdmVersion) == 1, cdmVersion %in% listSupportedVersions())
+
+  if (!dir.exists(outputfolder)) {
+    dir.create(outputfolder)
+  }
+
+  files <- c()
+  for (dialect in targetDialect) {
+    buildRelease(cdmVersion, dialect, outputfolder = outputfolder)
+    files <- c(files, list.files(file.path(outputfolder, cdmVersion, gsub(" ", "_", dialect)),
+                                 pattern = ".*\\.sql$",
+                                 full.names = TRUE))
+  }
+
+  if (length(targetDialect) == 1) {
+    zipName <- file.path(outputfolder, paste0("OMOPCDM", "_", gsub(" ", "_", targetDialect), "_", cdmVersion, '.zip'))
+  } else {
+    zipName <- file.path(outputfolder, paste0("OMOPCDM", "_", cdmVersion, '.zip'))
+  }
+
+  DatabaseConnector::createZipFile(zipFile = zipName, files = files)
+}