updating main

.gitignore

@@ -172,3 +172,4 @@ cython_debug/
 
 # PyPI configuration file
 .pypirc
+.Rproj.user

README.md

@@ -1,73 +1,91 @@
 # gen3-metadata
 User friendly tools for downloading and manipulating gen3 metadata
 
-
-## 1. Set up python venv
-```bash
-python3 -m venv venv
-source venv/bin/activate
-pip install -r requirements.txt
-```
-
-## 2. Create config file 
+## Python Installation
 ```bash
-echo credentials_path=\"/path/to/credentials.json\" > .env
+git clone https://github.com/AustralianBioCommons/gen3-metadata.git
+bash build.sh
 ```
 
-## 3. Load library
-```bash
-pip install -e .
-```
-
-
-## 4. Usage Example
+## Usage Example
+- Notebook can be found in the `example_notebook.ipynb` file
+- Make sure to select .venv as the kernel in the notebook
 
 ```python
-import os
-from gen3_metadata.parser import Gen3MetadataParser
-
-# Set up credentials path
-key_file = os.getenv('credentials_path')
+from gen3_metadata.gen3_metadata_parser import Gen3MetadataParser
 
-# Initialize the Gen3MetadataParser
+# Initialise
+key_file = "path/to/credentials.json"
 gen3metadata = Gen3MetadataParser(key_file)
 
-# authenticate
+# Authenticate
 gen3metadata.authenticate()
 
-# Fetch data for different categories
-gen3metadata.fetch_data("program1", "AusDiab_Simulated", "subject")
-gen3metadata.fetch_data("program1", "AusDiab_Simulated", "demographic")
-gen3metadata.fetch_data("program1", "AusDiab_Simulated", "medical_history")
+# Fetching data and returning as dataframe
+program_name = "program1"
+project_code = "project1"
+node_label="medical_history"
+pd_data = gen3metadata.fetch_data_pd(program_name, project_code, node_label=node_label)
+pd_data
+
+# Fetching data and returning as json
+json_data = gen3metadata.fetch_data_json(program_name, project_code, node_label=node_label)
+json_data
+```
 
-# Convert fetched data to a pandas DataFrame
-gen3metadata.data_to_pd()
 
-# Print the keys of the data sets that have been fetched
-print(gen3metadata.data_store.keys())
+## Running Tests
 
-# Return a json of one of the datasets
-gen3metadata.data_store["program1/AusDiab_Simulated/subject"]
+The tests are written using the `pytest` framework. 
 
-# Return the pandas dataframe of one of the datasets
-gen3metadata.data_store_pd["program1/AusDiab_Simulated/subject"]
+```bash
+pytest -vv tests/
 ```
 
-The fetched data is stored in a dictionary within the `Gen3MetadataParser` instance.
-Each category of data fetched is stored as a key-value pair in this dictionary,
-where the key is the category name and the value is the corresponding data.
-This allows for easy access and manipulation of the data after it has been fetched.
+---
 
+# Installation of the R version of gen3-metadata
 
+You can install the gen3metadata R tool from
+[GitHub](https://github.com/) with:
 
+``` r
+if (!require("devtools")) install.packages("devtools")
+devtools::install_github("AustralianBioCommons/gen3-metadata", subdir = "gen3metadata-R")
+```
 
-## 5. Running Tests
+The package depends on several other packages, which should hopefully be installed automatically.
+If case this doesn't happen, run:
+``` r
+install.packages(c("httr", "jsonlite", "jose", "glue"))
+```
 
-The tests are written using the `pytest` framework. 
+Then all you need to do is load the package.
 
-```bash
-pytest tests/
+``` r
+library("gen3metadata")
 ```
 
+## Usage Example
 
+This is a basic example to authenticate and load some data.
 
+``` r
+# Load the library
+library("gen3metadata")
+
+# Set the path to the credentials file
+key_file_path <- "path/to/credentials.json"
+
+# Create the Gen3 Metadata Parser object
+gen3 <- Gen3MetadataParser(key_file_path)
+
+# Authenticate the object
+gen3 <- authenticate(gen3)
+
+# Load some data
+dat <- fetch_data(gen3,
+                  program_name = "program1",
+                  project_code = "AusDiab",
+                  node_label = "subject")
+```

build.sh

@@ -0,0 +1,7 @@
+
+#!/bin/bash
+python -m venv .venv
+source venv/bin/activate
+pip install --upgrade pip
+pip install -r requirements.txt
+pip install -e .

example_notebook.ipynb

@@ -0,0 +1,86 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# Example Workflow\n",
+    "- Make sure to run `bash build.sh` or follow the instructions in the README.md to build the package\n",
+    "- Make sure to select .venv as the kernel in the notebook"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from gen3_metadata.gen3_metadata_parser import Gen3MetadataParser"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Initialise\n",
+    "key_file = \"path/to/credentials.json\"\n",
+    "gen3metadata = Gen3MetadataParser(key_file)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Authenticate\n",
+    "gen3metadata.authenticate()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# fetching data and returning as dataframe\n",
+    "program_name= \"program1\"\n",
+    "project_code= \"AusDiab_Simulated\"\n",
+    "gen3metadata.fetch_data_pd(program_name, project_code, node_label= \"medical_history\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# fetching data and returning as json\n",
+    "gen3metadata.fetch_data_json(program_name, project_code, node_label= \"medical_history\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": ".venv",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.9.5"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

gen3metadata-R/DESCRIPTION

@@ -0,0 +1,24 @@
+Package: gen3metadata
+Type: Package
+Title: Gen3 metadata tools
+Version: 0.1.0
+Author: Corey Giles [aut, cre]
+Authors@R: c(person("Corey", "Giles", role = c("aut", "cre"),
+                    email = "Corey.Giles@Baker.edu.au",
+                    comment = c(ORCID = "0000-0002-6050-1259")))
+Maintainer: Corey Giles <Corey.Giles@Baker.edu.au>
+Description: User friendly tools for downloading and manipulating gen3 metadata
+License: GPL-3
+Encoding: UTF-8
+LazyData: true
+Language: en-AU
+RoxygenNote: 7.3.2
+Imports:
+    httr,
+    jsonlite,
+    jose,
+    glue
+Suggests: 
+    testthat (>= 3.0.0),
+    webmockr
+Config/testthat/edition: 3

gen3metadata-R/NAMESPACE

@@ -0,0 +1,16 @@
+# Generated by roxygen2: do not edit by hand
+
+S3method(authenticate,gen3_metadata)
+S3method(fetch_data,gen3_metadata)
+S3method(print,gen3_metadata)
+export(Gen3MetadataParser)
+export(authenticate)
+export(fetch_data)
+importFrom(glue,glue)
+importFrom(httr,GET)
+importFrom(httr,POST)
+importFrom(httr,add_headers)
+importFrom(httr,content)
+importFrom(httr,http_error)
+importFrom(jose,jwt_split)
+importFrom(jsonlite,fromJSON)

gen3metadata-R/R/gen3_metadata.R

@@ -0,0 +1,40 @@
+#' Create a Gen3 metadata parser object
+#'
+#' This function creates a new Gen3 metadata parser object by loading
+#' credentials from a key file. Use this object to interact with the Gen3 API.
+#'
+#' @param key_file Character string path to the JSON key file containing Gen3 credentials
+#' 
+#' @return A gen3_metadata object with credentials and base URL configured
+#' 
+#' @export
+Gen3MetadataParser <- function(key_file) {
+
+    # Create the object to store data
+    obj <- list(
+        key_file = key_file,
+        base_url = "",
+        credentials = list(
+            api_key = "",
+            key_id = ""
+        ),
+        header = NULL
+    )
+
+    # Load the key file
+    creds <- load_key_file(key_file)
+
+    # Set the credentials in the object
+    obj$credentials$api_key <- creds$api_key
+    obj$credentials$key_id <- creds$key_id
+
+    # Get the base URL from the API key
+    obj$base_url <- get_base_url(obj$credentials$api_key)
+
+    # Set the class of the object
+    class(obj) <- "gen3_metadata"
+
+    # Return the object
+    return(obj)
+
+}

gen3metadata-R/R/generics.R

@@ -0,0 +1,31 @@
+#' Authenticate with Gen3 API
+#'
+#' Generic function to authenticate a gen3_metadata object with the Gen3 API
+#' and obtain an access token for subsequent requests.
+#'
+#' @param gen3_metadata A gen3_metadata object
+#' 
+#' @return The authenticated gen3_metadata object (invisibly)
+#' 
+#' @export
+authenticate <- function(gen3_metadata) {
+    UseMethod("authenticate")
+}
+
+#' Fetch data from Gen3 API
+#'
+#' Generic function to fetch data from a specific node in the Gen3 submission API
+#' for a given program and project.
+#'
+#' @param gen3_metadata An authenticated gen3_metadata object
+#' @param program_name Character string name of the program
+#' @param project_code Character string code of the project
+#' @param node_label Character string label of the node to fetch data from
+#' @param api_version Character string API version (default: "v0")
+#' 
+#' @return Data frame containing the fetched data
+#' 
+#' @export
+fetch_data <- function(gen3_metadata, program_name, project_code, node_label, api_version) {
+    UseMethod("fetch_data")
+}

gen3metadata-R/R/get_base_url.R

@@ -0,0 +1,31 @@
+#' Extract base URL from Gen3 API key
+#'
+#' This function extracts the base URL from a Gen3 API key JWT token
+#' by parsing the 'iss' (issuer) field from the payload.
+#'
+#' @param api_key Character string containing the Gen3 API key (JWT token)
+#' 
+#' @return Character string containing the base URL
+#' 
+#' @importFrom jose jwt_split
+get_base_url <- function(api_key) {
+
+    # Check if the API key is provided
+    if (is.null(api_key) || api_key == "") {
+        stop("API key must be provided.")
+    }
+
+    # Extract the payload from the JWT
+    payload  <- jose::jwt_split(api_key)$payload
+
+    # Validate the payload
+    if (!"iss" %in% names(payload)) {
+        stop("The JWT payload must contain 'iss'.")
+    }
+
+    # Extract the base URL from the payload
+    base_url <- sub("/user$", "", payload$iss)
+
+    # Return the base url
+    return(base_url)
+}