markdown_link_checker_sc 0.0.136 → 0.0.138

package/README.md

@@ -12,25 +12,36 @@ Current version only does internal link checking
 Usage: markdown_link_checker_sc [options]
 
 Options:
-  -r, --root <path>                   Root directory of your docs source, such as <repo>/docs (the folder which contains all your docs, assets, etc). Use -d as well to restrict search to a
-                                      particular subfolder. Defaults to current directory. (default: "D:\\github\\hamishwillee\\markdown_link_checker_sc")
-  -d, --directory [directory]         A subfolder or the root to search for markdown and html files. Such as: `en` for an English subfolder. Default empty (same as -r directory) (default:
-                                      "")
-  -i, --imagedir [directory]          The directory to search for all image files for global orphan checking, relative to root - such as: `assets` or `en`. Default empty if not explicitly
-                                      set, and global orphan checking will not be done (default: "")
+  -r, --repo <path>                   Repo root directory. Defaults to current directory. Everything resolved relative to this.) (default: "")
+  -d, --doc [directory]               Docs root directory, relative to -g (such as `docs`). Defaults to '' (all docs in root of repo). Use -d as well to restrict search to a particular subfolder. Defaults to current directory. (default:
+                                      "D:\\github\\hamishwillee\\markdown_link_checker_sc")
+  -e, --subdir [directory]            A subfolder of the docs root (-d) to search for markdown and html files. Such as: `en` for an English subfolder. Default empty (same as -d directory) (default: "")
+  -i, --imagedir [directory]          The directory to search for all image files for global orphan checking, relative docs root (-d) - such as: `assets` or `en`. Default empty if not explicitly set, and global orphan checking will not be done
+                                      (default: "")
   -c, --headingAnchorSlugify [value]  Slugify approach for turning markdown headings into heading anchors. Currently support vuepress only and always (default: "vuepress")
   -t, --tryMarkdownforHTML [value]    Try a markdown file extension check if a link to HTML fails. (default: true)
   -l, --log <types...>                Types of console logs to display logs for debugging. Types: functions, todo etc.
-  -f, --files <path>                  JSON file with array of files to report on (default is all files). Paths are relative relative to -d by default, but -r can be used to set a different
-                                      root. (default: "")
+  -f, --files <path>                  JSON file with array of files to report on (default is all files). JSON paths are usually relative to git repo root `-r`. (default: "")
   -s, --toc [value]                   full filename of TOC/Summary file in file system. If not specified, inferred from file with most links to other files
   -u, --site_url [value]              Site base url in form dev.example.com (used to catch absolute urls to local files)
   -o, --logtofile [value]             Output logs to file (default: true)
-  -p, --interactive [value]           Interactively add errors to the ignore list at _link_checker_sc/ignore_errors.json (default: false)
+  -p, --interactive [value]           Interactively add errors to the ignore list at <repo>/_link_checker_sc/ignore_errors.json (default: false)
   -c, --anchor_in_heading [value]     Detect anchors in heading such as: # Heading {#anchor} (default: true)
   -h, --help                          display help for command
 ```
 
+## Ignore file
+
+You can create a `_link_checker_sc\ignorefile.json` in the docs (path specified by `-d`) that lists any files you want to avoid parsing.
+This is a JSON array of file paths relative the the docsroot.
+
+For example, to not parse `en/_sidebar.md` your ignore file would have this pattern:
+
+```
+["en/_sidebar.md"]
+```
+
+Note that a missing ignorefile is not an error.
 
 ## What link formats can it match
 

package/index.js

@@ -3,9 +3,7 @@
 import fs from "fs";
 import path from "path";
 import { sharedData } from "./src/shared_data.js";
-//const path = require("path");
 import { program } from "commander";
-//const { program } = require("commander");
 import {
   logFunction,
   logToFile,
@@ -30,19 +28,23 @@ import { filterErrors, filterIgnoreErrors } from "./src/filters.js";
 
 program
   .option(
-    "-r, --root <path>",
-    "Root directory of your docs source, such as <repo>/docs (the folder which contains all your docs, assets, etc). Use -d as well to restrict search to a particular subfolder. Defaults to current directory.",
+    "-r, --repo <path>",
+    "Repo root directory. Defaults to current directory. Everything resolved relative to this.)",
+    ""
+  )
+  .option(
+    "-d, --doc [directory]",
+    "Docs root directory, relative to -g (such as `docs`). Defaults to '' (all docs in root of repo). Use -d as well to restrict search to a particular subfolder. Defaults to current directory.",
     process.cwd()
   )
   .option(
-    "-d, --directory [directory]",
-    "A subfolder or the docs root to search for markdown and html files. Such as: `en` for an English subfolder. Default empty (same as -r directory)",
+    "-e, --subdir [directory]",
+    "A subfolder of the docs root (-d) to search for markdown and html files. Such as: `en` for an English subfolder. Default empty (same as -d directory)",
     ""
   )
-
   .option(
     "-i, --imagedir [directory]",
-    "The directory to search for all image files for global orphan checking, relative to root - such as: `assets` or `en`. Default empty if not explicitly set, and global orphan checking will not be done",
+    "The directory to search for all image files for global orphan checking, relative docs root (-d) - such as: `assets` or `en`. Default empty if not explicitly set, and global orphan checking will not be done",
     ""
   )
   .option(
@@ -61,12 +63,7 @@ program
   )
   .option(
     "-f, --files <path>",
-    "JSON file with array of files to report on (default is all files). JSON paths are usually relative to git root. Resolved to absolute file paths using `-g`.",
-    ""
-  )
-  .option(
-    "-g, --repo [directory]",
-    "Repo root directory. Files in -f JSON are resolved to absolute paths relative to this dir. Defaults to current directory.)",
+    "JSON file with array of files to report on (default is all files). JSON paths are usually relative to git repo root `-r`.",
     ""
   )
   .option(
@@ -80,7 +77,7 @@ program
   .option("-o, --logtofile [value]", "Output logs to file", true)
   .option(
     "-p, --interactive [value]",
-    "Interactively add errors to the ignore list at _link_checker_sc/ignore_errors.json",
+    "Interactively add errors to the ignore list at <repo>/_link_checker_sc/ignore_errors.json",
     false
   )
   .option(
@@ -102,11 +99,40 @@ sharedData.allHTMLFiles = new Set([]);
 sharedData.allImageFiles = new Set([]);
 sharedData.allOtherFiles = new Set([]);
 
-const markdownDirectory = path.join(
-  sharedData.options.root,
-  sharedData.options.directory
+function resolveRepoPath(repoOption) {
+  // This gets the path from CWD by default, or resolves path up.
+  if (!repoOption || repoOption === ".") {
+    return process.cwd(); // Current working directory (Node.js)
+  }
+
+  if (repoOption === "..") {
+    return path.resolve(process.cwd(), ".."); // One directory up
+  }
+
+  return path.resolve(repoOption); // Resolve to absolute path
+}
+
+sharedData.options.repo = resolveRepoPath(sharedData.options.repo);
+
+sharedData.options.docsroot = path.join(
+  sharedData.options.repo,
+  sharedData.options.doc
 );
 
+// Markdown directory we are actually checking
+sharedData.options.markdownroot = path.join(
+  sharedData.options.docsroot,
+  sharedData.options.subdir
+);
+
+//console.log(`debug: sharedData.options.repo: ${sharedData.options.repo}`);
+//console.log(`debug: sharedData.options.doc: ${sharedData.options.doc}`);
+//console.log(`debug: sharedData.options.subdir: ${sharedData.options.subdir}`);
+//console.log(`debug: sharedData.options.docsroot: ${sharedData.options.docsroot}`);
+//console.log(`debug: sharedData.options.markdownroot: ${sharedData.options.markdownroot}`);
+
+//process.exit(1);
+
 // Function for loading JSON file that contains files to report on
 async function loadJSONFileToReportOn(filePath) {
   sharedData.options.log.includes("functions")
@@ -150,9 +176,9 @@ async function loadJSONFileToIgnore(filePath) {
     if (filesArray.length == 0) {
       return [];
     } else {
-      // Array relative to root, so update to have full path
+      // Array relative to repo root, so update to have full path
       filesArray = filesArray.map((str) =>
-        path.join(sharedData.options.root, str)
+        path.join(sharedData.options.docsroot, str)
       );
     }
 
@@ -162,8 +188,8 @@ async function loadJSONFileToIgnore(filePath) {
 
     return filesArray;
   } catch (error) {
-    //console.error(`Error reading file: ${error.message}`);
-    console.log(`Error reading ignore file: ${error.message}`);
+    //console.log(`Error reading ignore file: ${error.message}`);
+    //Note, ignore file is private really.
     return [];
     //process.exit(1);
   }
@@ -215,7 +241,7 @@ const processDirectory = async (dir) => {
       results.push(...subResults);
     } else if (sharedData.options.ignoreFiles.includes(file)) {
       // do nothing
-      // console.log(`XxxxXignorelist: file: ${file}`);
+      //console.log(`XxxxXignorelist: file: ${file}`);
     } else if (isMarkdown(file)) {
       sharedData.allMarkdownFiles.add(file);
       const result = await processFile(file);
@@ -246,7 +272,8 @@ const processDirectory = async (dir) => {
     : (sharedData.options.files = []);
 
   const pathToJsonIgnoreFile = path.join(
-    sharedData.options.root,
+    sharedData.options.repo,
+    sharedData.options.doc,
     "_link_checker_sc/ignorefile.json"
   );
   //console.log(`debug: pathToJsonIgnoreFile: ${pathToJsonIgnoreFile}`);
@@ -255,7 +282,7 @@ const processDirectory = async (dir) => {
   );
 
   // process  containing markdown, return results which includes links, headings, id anchors
-  const results = await processDirectory(markdownDirectory);
+  const results = await processDirectory(sharedData.options.markdownroot);
 
   if (!results.allErrors) {
     results.allErrors = [];

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "markdown_link_checker_sc",
-  "version": "0.0.136",
+  "version": "0.0.138",
   "description": "Markdown Link Checker",
   "main": "index.js",
   "scripts": {

package/src/errors.js

@@ -11,14 +11,18 @@ class LinkError {
       this.link = link;
       this.file = this.link.page;
       this.fileRelativeToRoot = this.link.fileRelativeToRoot;
+      //console.log(`debugX: fileRelativeToRoot: ${this.fileRelativeToRoot}`);
     } else {
       this.file = file; // i.e. infer file from link, but if link not specified then can take passed value
-      this.fileRelativeToRoot = this.file.split(sharedData.options.root)[1];
+      this.fileRelativeToRoot = this.file.split(sharedData.options.docsroot)[1];
+      //console.log(        `debug: sharedData.options.docsroot: ${sharedData.options.docsroot}`      );
+      //console.log(`debug: fileRelativeToRoot: ${this.fileRelativeToRoot}`);
       this.fileRelativeToRoot =
         this.fileRelativeToRoot.startsWith("/") ||
         this.fileRelativeToRoot.startsWith("\\")
           ? this.fileRelativeToRoot.substring(1)
           : this.fileRelativeToRoot;
+      //console.log(`debug: 2fileRelativeToRoot: ${this.fileRelativeToRoot}`);
     }
   }
 

package/src/filters.js

@@ -2,7 +2,7 @@ import fs from "fs";
 import path from "path";
 import { sharedData } from "./shared_data.js";
 import { logFunction } from "./helpers.js";
-import normalize from 'normalize-path';
+import normalize from "normalize-path";
 
 function filterIgnoreErrors(errors) {
   // This method removes any errors that are in the ignore errors list
@@ -11,7 +11,7 @@ function filterIgnoreErrors(errors) {
   // Currently it is the pages to output, as listed in the options.files to output.
   logFunction(`Function: filterIgnoreErrors(${errors})`);
   const errorFile = path.join(
-    sharedData.options.root,
+    sharedData.options.docsroot,
     "./_link_checker_sc/ignore_errors.json"
   );
 
@@ -33,7 +33,8 @@ function filterIgnoreErrors(errors) {
     sharedData.IgnoreErrors.forEach((ignorableError) => {
       if (
         error.type === ignorableError.type &&
-        normalize(error.fileRelativeToRoot) === normalize(ignorableError.fileRelativeToRoot)
+        normalize(error.fileRelativeToRoot) ===
+          normalize(ignorableError.fileRelativeToRoot)
       ) {
         // Same file and type, so probably filter out.
         if (!(error.link && ignorableError.link)) {

package/src/links.js

@@ -42,9 +42,9 @@ class Link {
     } else {
       throw new Error("Link: page argument is required.");
     }
-
+	//console.log(`debug: page: ${page}, sharedData.options.docsroot: ${sharedData.options.docsroot}`);
     // Create a relative file link for comparison
-    this.fileRelativeToRoot = this.page.split(sharedData.options.root)[1];
+    this.fileRelativeToRoot = this.page.split(sharedData.options.docsroot)[1];
     this.fileRelativeToRoot = (this.fileRelativeToRoot.startsWith('/') || this.fileRelativeToRoot.startsWith('\\')) ? this.fileRelativeToRoot.substring(1) : this.fileRelativeToRoot
 
     if (url) {

package/src/output_errors.js

@@ -37,10 +37,10 @@ function outputErrors(results) {
   //console.log(sortedByPageErrors);
   for (const page in sortedByPageErrors) {
     let pageFromRoot;
-    if (sharedData.options.root) {
-      pageFromRoot = page.split(sharedData.options.root)[1];
+    if (sharedData.options.docsroot) {
+      pageFromRoot = page.split(sharedData.options.docsroot)[1];
     } else {
-      pageFromRoot = page.split(sharedData.options.directory)[1];
+      pageFromRoot = page.split(sharedData.options.markdownroot)[1];
     }
     //console.log(`\nXX${page}`); //Root needs to full path - not '.' or whatever
     console.log(`\n${pageFromRoot}`); //Root needs to full path - not '.' or whatever

package/src/process_image_orphans.js

@@ -15,7 +15,7 @@ var otherFileTypes = []; // Just used for logging in function below.
 
 // Gets all image files in a directory.
 async function getAllImageFilesInDirectory(dir) {
-  logFunction(`Function: getAllImageFilesInDirectory(${dir})`)
+  logFunction(`Function: getAllImageFilesInDirectory(${dir})`);
 
   // TODO put this all in a try catch and return a better error.
   // Or perhaps put around parent.
@@ -42,14 +42,14 @@ async function getAllImageFilesInDirectory(dir) {
 
 // Checks if any images in the options.directory
 async function checkImageOrphansGlobal(results) {
-  logFunction(`Function: checkImageOrphansGlobal()`)
-  
+  logFunction(`Function: checkImageOrphansGlobal()`);
+
   const errors = [];
   let allImagesFound = [];
 
   if (sharedData.options.imagedir !== "") {
     const imagePath = path.resolve(
-      sharedData.options.root,
+      sharedData.options.docsroot,
       sharedData.options.imagedir
     );
 

package/src/process_local_image_links.js

@@ -16,8 +16,8 @@ async function checkLocalImageLinks(results) {
 
     page.relativeImageLinks.forEach((link, index, array) => {
       //console.log(`XYYXLINK: ${JSON.stringify(link, null, 2)}`);
-      //console.log(`sharedData.options.root: ${sharedData.options.root}`);
-      //console.log(`sharedData.options.directory: ${sharedData.options.directory}`);
+      //console.log(`sharedData.options.repo: ${sharedData.options.repo}`);
+      //console.log(`sharedData.options.subdir: ${sharedData.options.subdir}`);
       //console.log(`link.linkUrlt: ${link.url}`);
       //console.log(`dirname: ${path.dirname(page.page_file)}`);