Expand Text of Compact Data - data-manipulation

Question

I am stuck with some data manipulation.
This is a small portion of the input data (df):
site=c("C000-C002","C420-C421,C424")
histology=c("9835-9836","9811-9812,9837")
category=c("Leukemia","Leukemia")
df=data.frame(site,histology,category)
And this is what I want the processed data to look like:
You may assume Site and Histology are both 4-digit after text splitting.
In case anyone is interested, the full data table is here
Please help with the text processing, or if anyone knows an existing processed package or database in a similar format as the image, that would be great too.
Thank you very much.

Answer 1

I don't know R language. So I tried with Javascript as following.
function mapStartEnd(start, end) {
let list = [];
let info = {};
const siteStart = start.match(/([A-Z])(\d{3})/);
if (siteStart) {
const siteEnd = end.match(/([A-Z])(\d{3})/);
info = {
type: "site",
prefix: siteStart[1],
numLength: 3,
from: parseInt(siteStart[2], 10),
to: parseInt(siteEnd[2], 10),
};
}
const histologyStart = start.match(/\d{4}/);
if (histologyStart) {
const histologyEnd = end.match(/\d{4}/);
info = {
type: "histology",
prefix: "",
numLength: 4,
from: parseInt(histologyStart[0], 10),
to: parseInt(histologyEnd[0], 10),
};
}
const categoryStart = start.match(/[A-Z][a-z]+/);
if (categoryStart) {
const categoryEnd = end.match(/[A-Z][a-z]+/);
info = {
type: "category",
prefix: "",
numLength: 0,
from: categoryStart[0],
to: categoryEnd[0],
};
}
if (!info.numLength) {
list = [info.from, info.to];
} else {
for (let i = info.from; i <= info.to; i++) {
list.push(info.prefix + i.toString().padStart(info.numLength, "0"));
}
}
return list;
}
function c(list) {
return list.map((list2) => {
return list2.split(",").reduce((prev, cur) => {
const [start, end] = cur.split("-");
if (!end) prev.push(start);
else prev = [...prev, ...mapStartEnd(start, end)];
return prev;
}, []);
});
}
function map3(sites, histologys, categorys) {
let list = [];
for (let i = 0; i < sites.length; i++) {
const site = sites[i];
for (let j = 0; j < histologys.length; j++) {
const histology = histologys[j];
for (let k = 0; k < categorys.length; k++) {
const category = categorys[k];
// JSON format
// list.push({ site, histology, category });
// CSV format
list.push(`${site},${histology},${category}`);
}
}
}
return list;
}
function frame(sites, histologys, categorys) {
let list = [];
for (let i = 0; i < sites.length; i++) {
const site = sites[i];
const histology = histologys[i];
const category = categorys[i];
list = [...list, ...map3(site, histology, category)];
}
return list;
}
const site = c(["C000-C002", "C420-C421,C424"]);
const histology = c(["9835-9836", "9811-9812,9837"]);
const category = c(["Leukemia", "Leukemia"]);
const df = frame(site, histology, category);
console.log(df);
Result:
[
"C000,9835,Leukemia",
"C000,9836,Leukemia",
"C001,9835,Leukemia",
"C001,9836,Leukemia",
"C002,9835,Leukemia",
"C002,9836,Leukemia",
"C420,9811,Leukemia",
"C420,9812,Leukemia",
"C420,9837,Leukemia",
"C421,9811,Leukemia",
"C421,9812,Leukemia",
"C421,9837,Leukemia",
"C424,9811,Leukemia",
"C424,9812,Leukemia",
"C424,9837,Leukemia"
]
https://jsfiddle.net/dnu2g0vr/