mwn - npm Package Compare versions

Comparing version 0.3.0 to 0.4.0

package.json

 {
   "name": "mwn",
-  "version": "0.3.0",
+  "version": "0.4.0",
   "description": "MediaWiki bot framework for NodeJS",
@@ -18,2 +18,6 @@ "main": "./src/bot.js",
   "license": "GPL-3.0-or-later",
+  "bugs": {
+    "url": "https://github.com/siddharthvp/mwn/issues"
+  },
+  "homepage": "https://github.com/siddharthvp/mwn#readme",
   "files": [
@@ -20,0 +24,0 @@ "src/"

README.md

@@ -5,3 +5,3 @@ # mwn
 
-Development status: **Unstable**. mwn currently does not follow semantic versioning rules. For now, changes may be made to the public interface without a change in version number.
+Development status: **Unstable**. Versioning: while mwn is in version 0, changes may be made to the public interface with a change in the minor version number.
 
@@ -14,3 +14,7 @@ Documentation given below is incomplete. There are a number of additional classes such as `bot.title`, `bot.wikitext`, `bot.page`, etc that provide useful functionality but aren't documented.
 
-Until mwn is released on npm, enter the `node_modules` directory of your project and run:
+To install, run `npm install mwn`.
+
+[![Download stats](https://nodei.co/npm/mwn.png?downloads=true&downloadRank=true)](https://nodei.co/npm/mwn/)
+
+Or obtain the latest development copy:
 ```sh
@@ -17,0 +21,0 @@ git clone https://github.com/siddharthvp/mwn.git

src/wikitext.js

 module.exports = function(bot) {
 
+	/**
+	 * Class for some basic wikitext parsing, involving 
+	 * links, files, categories and templates.
+	 * 
+	 * For more advanced and sophisticated wikitext parsing, use can
+	 * mwparserfromhell <https://github.com/earwig/mwparserfromhell>
+	 * implemented in python (which you can use within node.js using
+	 * the child_process interface). However, mwparserfromhell doesn't
+	 * recognize localised namespaces and wiki-specific configs.
+	 */
 	class Wikitext {
 
-		/**
-		 * @constructor
-		 * @param {string} wikitext
-		 */
+		/** @param {string} wikitext */
 		constructor(wikitext) {
@@ -20,10 +27,13 @@ this.text = wikitext;
 			var n = this.text.length;
-			var startIdx, endIdx;
+			// files can have links in captions; use a stack to handle the nesting
+			var stack = new Stack();
 			for (let i=0; i<n; i++) {
 				if (this.text[i] === '[' && this.text[i+1] === '[') {
-					startIdx = i + 2;
-				} else if (this.text[i] === ']' && this.text[i+1] === ']') {
-					endIdx = i;
-					processLink(this, this.text.slice(startIdx, endIdx));
-					startIdx = null;
+					stack.push({startIdx: i });
+					i++;
+				} else if (this.text[i] === ']' && this.text[i+1] === ']' && stack.top()) {
+					stack.top().endIdx = i + 1;
+					processLink(this, stack.top().startIdx, stack.top().endIdx);
+					stack.pop();
+					i++; // necessary to handle cases like [[File:ImageName|thumb|A [[hill]]]]
 				}
@@ -47,11 +57,36 @@ }
 			}
-		 * @param {Boolean} recursive Set to `true` to also parse templates that occur
-		 * within other templates, rather than just top-level templates.
+		 * @param {number} [count] - maximum number of templates to parse (default infinite)
 	     * @return Template[]
 		 */
-		parseTemplates(recursive) {
-			return this.templates = parseTemplates(this.text, recursive);
+		parseTemplates(count) {
+			return this.templates = parseTemplates(this.text, false, count);
 		}
 
 		/**
+		 * Also parse templates that occur within other templates, rather than just top-level templates.
+		 * @param {number} [depth=true] - specify a number to limit recursive parsing to a the given recursion 
+		 * depth. For infinite depth, specify `true` (default). Eg. with recursive=1, all templates and 
+		 * sub-templates will be parsed, but not the templates within the sub-templates
+		 */
+		parseTemplatesRecursive(depth) {
+			return this.templates = parseTemplates(this.text, depth || true);
+		}
+
+		/**
+		 * Remove a template, link, file or category from the text
+		 * CAUTION: If an entity with the very same wikitext exists earlier in the text, 
+		 * that one will be removed instead.
+		 * @param {Object|Template} entity - anything with a wikitext attribute 
+		 * and end index
+		 */
+		removeEntity(entity) {
+			this.text = this.text.replace(entity.wikitext, '');
+		}
+
+		/** Get the updated text  @returns {string} */
+		getText() {
+			return this.text;
+		}
+
+		/**
 		 * Parse the text using the API.
@@ -103,4 +138,11 @@ * @see https://www.mediawiki.org/wiki/API:Parsing_wikitext
 
-	var processLink = function(self, linktext) {
-		var [target, displaytext] = linktext.split('|');
+	class Stack extends Array {
+		top() {
+			return this[this.length - 1];
+		}
+	}
+
+	var processLink = function(self, startIdx, endIdx) {
+		var linktext = self.text.slice(startIdx, endIdx + 1);
+		var [target, displaytext] = linktext.slice(2, -2).split('|');
 		var noSortkey = false;
@@ -115,18 +157,25 @@ if (!displaytext) {
 		}
+		var linkobj = {
+			wikitext: linktext, 
+			dsr: [startIdx, endIdx] // Note: data source ranges (dsr) are invalidated by any removeEntity() operation
+		};
 		if (target[0] !== ':') {
 			if (title.namespace === 6) {
-				self.files.push({
+				self.files.push(Object.assign({
 					target: title,
-					props: linktext.slice(linktext.indexOf('|') + 1)
-				});
+					props: linktext.slice(linktext.indexOf('|') + 1, -2)
+				}, linkobj));
 				return;
 			} else if (title.namespace === 14) {
-				self.categories.push({
+				self.categories.push(Object.assign({
 					target: title,
 					sortkey: noSortkey ? '' : displaytext
-				});
+				}, linkobj));
 				return;
 			}
 		}
-		self.links.push({target: title, displaytext: displaytext});
+		self.links.push(Object.assign({
+			target: title, 
+			displaytext: displaytext
+		}, linkobj));
 	};
@@ -154,4 +203,6 @@
 		 */
-		constructor(wikitext) {
+		constructor(wikitext, dsr) {
 			this.wikitext = wikitext;
+			// dsr stands for data source range, gives the starting and ending index in wikitext
+			this.dsr = dsr, // an array of two numbers
 			this.parameters = [];
@@ -177,3 +228,3 @@ }
 			this.name = name.trim();
-			// this.nameTitle = bot.title.newFromText(name, 10);
+			this.nameTitle = bot.title.newFromText(name, 10);
 		}
@@ -185,59 +236,15 @@ }
 	// https://en.wikipedia.org/wiki/User:SD0001/parseAllTemplates.js (cc-by-sa-3.0/GFDL)
-	var parseTemplates = function (wikitext, recursive) {
+	/**
+	 * 
+	 * @param {string} wikitext 
+	 * @param {boolean|number} [recursive=false] - also parse templates within templates,
+	 * give a number to specify recursion depth. If given as `true`, infinite recursion 
+	 * depth is assumed.
+	 * @param {number} [count] - stop parsing when this many templates have been found,
+	 * Recursive parsing does NOT work if count is specified.
+	 */
+	var parseTemplates = function (wikitext, recursive, count) {
 
-		var strReplaceAt = function (string, index, char) {
-			return string.slice(0, index) + char + string.slice(index + 1);
-		};
-
 		var result = [];
 
-		var processTemplateText = function (startIdx, endIdx) {
-			var text = wikitext.slice(startIdx, endIdx);
-
-			var template = new Template('{{' + text.replace(/\1/g, '|') + '}}');
-
-			// swap out pipe in links with \1 control character
-			// [[File: ]] can have multiple pipes, so might need multiple passes
-			while (/(\[\[[^\]]*?)\|(.*?\]\])/g.test(text)) {
-				text = text.replace(/(\[\[[^\]]*?)\|(.*?\]\])/g, '$1\1$2');
-			}
-
-			var chunks = text.split('|').map(function (chunk) {
-				// change '\1' control characters back to pipes
-				return chunk.replace(/\1/g, '|');
-			});
-
-			template.setName(chunks[0]);
-
-			var parameterChunks = chunks.slice(1);
-
-			var unnamedIdx = 1;
-			parameterChunks.forEach(function (chunk) {
-				var indexOfEqualTo = chunk.indexOf('=');
-				var indexOfOpenBraces = chunk.indexOf('{{');
-
-				var isWithoutEquals = !chunk.includes('=');
-				var hasBracesBeforeEquals = chunk.includes('{{') && indexOfOpenBraces < indexOfEqualTo;
-				var isUnnamedParam = (isWithoutEquals || hasBracesBeforeEquals);
-
-				var pName, pNum, pVal;
-				if (isUnnamedParam) {
-					// Get the next number not already used by either an unnamed parameter,
-					// or by a named parameter like `|1=val`
-					while (template.getParam(unnamedIdx)) {
-						unnamedIdx++;
-					}
-					pNum = unnamedIdx;
-					pVal = chunk.trim();
-				} else {
-					pName = chunk.slice(0, indexOfEqualTo).trim();
-					pVal = chunk.slice(indexOfEqualTo + 1).trim();
-				}
-				template.addParam(pName || pNum, pVal, chunk);
-			});
-
-			result.push(template);
-		};
-
-
 		var n = wikitext.length;
@@ -271,3 +278,7 @@
 						endIdx = i;
-						processTemplateText(startIdx, endIdx);
+						var templateWikitext = wikitext.slice(startIdx, endIdx); // without braces
+						result.push(processTemplateText(templateWikitext, [startIdx - 2, endIdx + 1]));
+						if (count && result.length === count) {
+							return result;
+						}
 					}
@@ -305,3 +316,3 @@ numUnclosed -= 2;
 
-		if (recursive) {
+		if (recursive && !count) {
 			var subtemplates = result.map(function (template) {
@@ -312,3 +323,3 @@ return template.wikitext.slice(2, -2);
 			}).map(function (templateWikitext) {
-				return parseTemplates(templateWikitext, true);
+				return parseTemplates(templateWikitext, recursive === true ? true : recursive - 1);
 			});
@@ -323,2 +334,59 @@
 
+	/**
+	 * @param {string} text - template wikitext without braces, with the pipes in 
+	 * nested templates replaced by \1
+	 * @param {Number[]} [dsr] - data source range (optional) for the template object 
+	 * Array of starting and ending indices of template in wikitext
+	 */
+	var processTemplateText = function (text, dsr) {
+
+		var template = new Template('{{' + text.replace(/\1/g, '|') + '}}', dsr);
+
+		// swap out pipe in links with \1 control character
+		// [[File: ]] can have multiple pipes, so might need multiple passes
+		while (/(\[\[[^\]]*?)\|(.*?\]\])/g.test(text)) {
+			text = text.replace(/(\[\[[^\]]*?)\|(.*?\]\])/g, '$1\1$2');
+		}
+
+		var chunks = text.split('|').map(function (chunk) {
+			// change '\1' control characters back to pipes
+			return chunk.replace(/\1/g, '|');
+		});
+
+		template.setName(chunks[0]);
+
+		var parameterChunks = chunks.slice(1);
+
+		var unnamedIdx = 1;
+		parameterChunks.forEach(function (chunk) {
+			var indexOfEqualTo = chunk.indexOf('=');
+			var indexOfOpenBraces = chunk.indexOf('{{');
+
+			var isWithoutEquals = !chunk.includes('=');
+			var hasBracesBeforeEquals = chunk.includes('{{') && indexOfOpenBraces < indexOfEqualTo;
+			var isUnnamedParam = (isWithoutEquals || hasBracesBeforeEquals);
+
+			var pName, pNum, pVal;
+			if (isUnnamedParam) {
+				// Get the next number not already used by either an unnamed parameter,
+				// or by a named parameter like `|1=val`
+				while (template.getParam(unnamedIdx)) {
+					unnamedIdx++;
+				}
+				pNum = unnamedIdx;
+				pVal = chunk.trim();
+			} else {
+				pName = chunk.slice(0, indexOfEqualTo).trim();
+				pVal = chunk.slice(indexOfEqualTo + 1).trim();
+			}
+			template.addParam(pName || pNum, pVal, chunk);
+		});
+
+		return template;
+	};
+
+	var strReplaceAt = function (string, index, char) {
+		return string.slice(0, index) + char + string.slice(index + 1);
+	};
+
 	return Wikitext;
@@ -325,0 +393,0 @@

New alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

Fixed alerts

License Policy Violation

License

This package is not allowed per your license policy. Review the package's license to ensure compliance.

Found 1 instance in 1 package

No bug tracker

Maintenance

Package does not have a linked bug tracker in package.json.

Found 1 instance in 1 package

No website

Quality

Package does not have a website.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

134035

increased by2.36%

Lines of code

3328

increased by1.99%

Number of low maintenance alerts

0

decreased by-100%

Number of low quality alerts

1

decreased by-50%

Number of lines in readme file

274

increased by1.48%

No dependency changes