feat: add data aggregation

.gitignore

@@ -1,4 +1,5 @@
 /node_modules/
 .env
 /prod/
-/data/**.csv
+/data/**.csv
+/data/**.md

README.md

@@ -18,6 +18,12 @@ To run this tool, complete the following steps:
 
 The tool will then begin collecting data, aggregating the results, and storing the results in `.csv` files. The files will be saved to the `data` directory, and can be opened with a text editor or most spreadsheet programs.
 
+## Aggregating Data
+
+After following the steps in the "Generating Data" section above, you can use the tool to aggregate data into a markdown file. Run `npm run aggregate` to start the automated process. The tool will read each `.csv` file within the `data` directory and parse it into a markdown list. The first column in each `.csv` file should be the contributor's _name_, and the second column should be the contributor's _url_ (GitHub, Twitter, YouTube, etc.). The tool will ignore any columns after the second column. The tool will generate the list in a `- [name](url)` format, to allow hotlinks. If the `url` is empty, the tool will add the contributor in the `- name` format.
+
+The list will be sorted and written to `data/contributors.md`, where you can copy and paste it to whichever platform you wish to announce top contributors on.
+
 ## Feedback and Bugs
 
 If you have feedback or a bug report, please feel free to open a GitHub issue!

package.json

@@ -4,6 +4,7 @@
   "description": "A tool to generate lists of contributors",
   "main": "./prod/index.js",
   "scripts": {
+    "aggregate": "node -r dotenv/config prod/modules/aggregateData.js",
     "build": "tsc",
     "lint": "eslint src --max-warnings 0",
     "start": "node -r dotenv/config prod/index.js",

src/modules/aggregateData.ts

@@ -0,0 +1,35 @@
+import { readFile, writeFile } from "fs/promises";
+import { join } from "path";
+
+import { getFileNames } from "../utils/getFileNames";
+import { logHandler } from "../utils/logHandler";
+
+(async () => {
+  logHandler.log("info", "Beginning data aggregation...");
+  const fileNames = await getFileNames();
+  const globalContributors: string[] = [];
+  for (const file of fileNames) {
+    logHandler.log("info", `Aggregating data from ${file}...`);
+    const filePath = join(process.cwd(), "data", file);
+    const content = await readFile(filePath, "utf8");
+    const contributors = content.split("\n").slice(1);
+    const mappedContributors = contributors.map((el) => {
+      if (!el) {
+        return "";
+      }
+      const [name, url] = el.split(",");
+      return url ? `- [${name}](${url})` : `- ${name}`;
+    });
+    globalContributors.push(...mappedContributors.filter((el) => el));
+  }
+  logHandler.log("info", "Writing data to output file...");
+  const outputFile = join(process.cwd(), "data", "contributors.md");
+  const sorted = globalContributors.sort((a, b) =>
+    a
+      .replace(/\W/gi, "")
+      .toLowerCase()
+      .localeCompare(b.replace(/\W/gi, "").toLowerCase())
+  );
+  await writeFile(outputFile, sorted.join("\n"));
+  logHandler.log("info", "Data aggregation complete!");
+})();

src/utils/getFileNames.ts

@@ -0,0 +1,19 @@
+import { readdir } from "fs/promises";
+import { join } from "path";
+
+import { logHandler } from "./logHandler";
+
+/**
+ * Module to get the file names within the data directory, excluding any
+ * that are not .csv files.
+ *
+ * @returns {string[]} An array of file names.
+ */
+export const getFileNames = async () => {
+  logHandler.log("info", "Reading files in the data directory...");
+  const dataDirectory = join(process.cwd(), "data");
+  const files = await readdir(dataDirectory);
+  const filtered = files.filter((file) => file.endsWith(".csv"));
+  logHandler.log("info", `Found ${filtered.length} CSV files.`);
+  return filtered;
+};