gettext-parser - npm Package Compare versions

Comparing version 6.0.0 to 7.0.0

lib/poparser.js

@@ -6,11 +6,14 @@ const encoding = require('encoding');
 
+module.exports.parse = parse;
+module.exports.stream = stream;
+
 /**
  * Parses a PO object into translation table
  *
- * @param {Buffer|String} buffer PO object
- * @param {String} [defaultCharset] Default charset to use
- * @return {Object} Translation object
+ * @typedef {{ defaultCharset?: string, validation?: boolean }} Options
+ * @param {string | Buffer} input PO object
+ * @param {Options} [options] Optional options with defaultCharset and validation
  */
-module.exports.parse = function (buffer, defaultCharset) {
-  const parser = new Parser(buffer, defaultCharset);
+function parse (input, options = {}) {
+  const parser = new Parser(input, options);
 
@@ -23,8 +26,8 @@ return parser.parse();
  *
- * @param {String} [defaultCharset] Default charset to use
- * @param {String} [options] Stream options
- * @return {Stream} Transform stream
+ * @typedef {{ defaultCharset: strubg, validation: boolean }} Options
+ * @param {Options} [options] Optional options with defaultCharset and validation
+ * @param {import('readable-stream').TransformOptions} [transformOptions] Optional stream options
  */
-module.exports.stream = function (defaultCharset, options) {
-  return new PoParserTransform(defaultCharset, options);
+function stream (options = {}, transformOptions = {}) {
+  return new PoParserTransform(options, transformOptions);
 };
@@ -36,7 +39,9 @@
  *
+ * @typedef {{ defaultCharset?: string, validation?: boolean }} Options
  * @constructor
- * @param {Buffer|String} fileContents PO object
- * @param {String} [defaultCharset] Default charset to use
+ * @param {string | Buffer} fileContents PO object
+ * @param {Options} options Options with defaultCharset and validation
  */
-function Parser (fileContents, defaultCharset = 'iso-8859-1') {
+function Parser (fileContents, { defaultCharset = 'iso-8859-1', validation = false }) {
+  this._validation = validation;
   this._charset = defaultCharset;
@@ -384,2 +389,6 @@
       if (lastNode) {
+        if (this._validation && 'msgid_plural' in lastNode) {
+          throw new SyntaxError(`Multiple msgid_plural error: entry "${lastNode.msgid}" in "${lastNode.msgctxt || ''}" context has multiple msgid_plural declarations.`);
+        }
+
         lastNode.msgid_plural = tokens[i].value;
@@ -412,2 +421,37 @@ }
 /**
+ * Validate token
+ *
+ * @param {Object} token Parsed token
+ * @param {Object} translations Translation table
+ * @param {string} msgctxt Message entry context
+ * @param {number} nplurals Number of epected plural forms
+ * @throws Will throw an error if token validation fails
+ */
+Parser.prototype._validateToken = function (
+  {
+    msgid = '',
+    msgid_plural = '', // eslint-disable-line camelcase
+    msgstr = []
+  },
+  translations,
+  msgctxt,
+  nplurals
+) {
+  if (!this._validation) {
+    return;
+  }
+
+  if (msgid in translations[msgctxt]) {
+    throw new SyntaxError(`Duplicate msgid error: entry "${msgid}" in "${msgctxt}" context has already been declared.`);
+    // eslint-disable-next-line camelcase
+  } else if (msgid_plural && msgstr.length !== nplurals) {
+    // eslint-disable-next-line camelcase
+    throw new RangeError(`Plural forms range error: Expected to find ${nplurals} forms but got ${msgstr.length} for entry "${msgid_plural}" in "${msgctxt}" context.`);
+    // eslint-disable-next-line camelcase
+  } else if (!msgid_plural && msgstr.length !== 1) {
+    throw new RangeError(`Translation string range error: Extected 1 msgstr definitions associated with "${msgid}" in "${msgctxt}" context, found ${msgstr.length}.`);
+  }
+};
+
+/**
  * Compose a translation table from tokens object
@@ -424,2 +468,3 @@ *
   };
+  let nplurals = 1;
   let msgctxt;
@@ -452,4 +497,7 @@
       table.headers = sharedFuncs.parseHeader(tokens[i].msgstr[0]);
+      nplurals = sharedFuncs.parseNPluralFromHeadersSafely(table.headers, nplurals);
     }
 
+    this._validateToken(tokens[i], table.translations, msgctxt, nplurals);
+
     table.translations[msgctxt][tokens[i].msgid] = tokens[i];
@@ -481,13 +529,9 @@ }
  *
+ * @typedef {{ defaultCharset: strubg, validation: boolean }} Options
  * @constructor
- * @param {String} [defaultCharset] Default charset to use
- * @param {String} [options] Stream options
+ * @param {Options} options Optional options with defaultCharset and validation
+ * @param {import('readable-stream').TransformOptions} transformOptions Optional stream options
  */
-function PoParserTransform (defaultCharset, options) {
-  if (!options && defaultCharset && typeof defaultCharset === 'object') {
-    options = defaultCharset;
-    defaultCharset = undefined;
-  }
-
-  this.defaultCharset = defaultCharset;
+function PoParserTransform (options, transformOptions) {
+  this.options = options;
   this._parser = false;
@@ -499,5 +543,5 @@ this._tokens = {};
 
-  this.initialTreshold = options.initialTreshold || 2 * 1024;
+  this.initialTreshold = transformOptions.initialTreshold || 2 * 1024;
 
-  Transform.call(this, options);
+  Transform.call(this, transformOptions);
   this._writableState.objectMode = false;
@@ -532,3 +576,3 @@ this._readableState.objectMode = true;
 
-    this._parser = new Parser(chunk, this.defaultCharset);
+    this._parser = new Parser(chunk, this.options);
   } else if (this._cacheSize) {
@@ -586,3 +630,3 @@ // this only happens if we had an uncompleted 8bit sequence from the last iteration
   if (!this._parser && chunk) {
-    this._parser = new Parser(chunk, this.defaultCharset);
+    this._parser = new Parser(chunk, this.options);
   }
@@ -589,0 +633,0 @@

lib/shared.js

 module.exports.parseHeader = parseHeader;
+module.exports.parseNPluralFromHeadersSafely = parseNPluralFromHeadersSafely;
 module.exports.generateHeader = generateHeader;
@@ -8,2 +9,3 @@ module.exports.formatCharset = formatCharset;
 // see https://www.gnu.org/software/gettext/manual/html_node/Header-Entry.html
+const PLURAL_FORMS = 'Plural-Forms';
 const HEADERS = new Map([
@@ -19,3 +21,3 @@ ['project-id-version', 'Project-Id-Version'],
   ['content-transfer-encoding', 'Content-Transfer-Encoding'],
-  ['plural-forms', 'Plural-Forms']
+  ['plural-forms', PLURAL_FORMS]
 ]);
@@ -25,2 +27,4 @@
 
+const PLURAL_FORM_HEADER_NPLURALS_REGEX = /nplurals\s*=\s*(?<nplurals>\d+)/;
+
 /**
@@ -51,2 +55,22 @@ * Parses a header string into an object of key-value pairs
 /**
+ * Attempts to safely parse 'nplurals" value from "Plural-Forms" header
+ *
+ * @param {Object} [headers = {}] An object with parsed headers
+ * @returns {number} Parsed result
+ */
+function parseNPluralFromHeadersSafely (headers = {}, fallback = 1) {
+  const pluralForms = headers[PLURAL_FORMS];
+
+  if (!pluralForms) {
+    return fallback;
+  }
+
+  const {
+    groups: { nplurals } = { nplurals: '' + fallback }
+  } = pluralForms.match(PLURAL_FORM_HEADER_NPLURALS_REGEX) || {};
+
+  return parseInt(nplurals, 10) || fallback;
+}
+
+/**
  * Joins a header object of key value pairs into a header string
@@ -135,2 +159,3 @@ *
  * Comparator function for comparing msgid
+ *
  * @param {Object} object with msgid prev
@@ -137,0 +162,0 @@ * @param {Object} object with msgid next

package.json

 {
   "name": "gettext-parser",
   "description": "Parse and compile gettext po and mo files to/from json, nothing more, nothing less",
-  "version": "6.0.0",
+  "version": "7.0.0",
   "author": "Andris Reinman",
@@ -26,15 +26,15 @@ "contributors": [
   "dependencies": {
-    "content-type": "^1.0.4",
+    "content-type": "^1.0.5",
     "encoding": "^0.1.13",
-    "readable-stream": "^4.1.0",
+    "readable-stream": "^4.3.0",
     "safe-buffer": "^5.2.1"
   },
   "devDependencies": {
-    "chai": "^4.3.6",
-    "eslint": "^8.21.0",
+    "chai": "^4.3.7",
+    "eslint": "^8.39.0",
     "eslint-config-standard": "^17.0.0",
-    "eslint-plugin-import": "^2.26.0",
+    "eslint-plugin-import": "^2.27.5",
     "eslint-plugin-node": "^11.1.0",
-    "eslint-plugin-promise": "^6.0.0",
-    "mocha": "^10.0.0"
+    "eslint-plugin-promise": "^6.1.1",
+    "mocha": "^10.2.0"
   },
@@ -41,0 +41,0 @@ "keywords": [

README.md

@@ -14,3 +14,2 @@ gettext-parser [![ci](https://github.com/smhg/gettext-parser/actions/workflows/ci.yml/badge.svg)](https://github.com/smhg/gettext-parser/actions/workflows/ci.yml)
 
-
 ### Parse PO files
@@ -20,3 +19,3 @@
 
-    gettextParser.po.parse(input[, defaultCharset]) → Object
+    gettextParser.po.parse(input[, options]) → Object
 
@@ -26,4 +25,11 @@ Where
   * **input** is a *po* file as a Buffer or an unicode string. Charset is converted to unicode from other encodings only if the input is a Buffer, otherwise the charset information is discarded
-  * **defaultCharset** is the charset to use if charset is not defined or is the default `"CHARSET"` (applies only if *input* is a Buffer)
+  * **options** is an optional object with the following optional properties:
+    * **defaultCharset** is the charset to use if charset is not defined or is the default `"CHARSET"` (applies only if *input* is a Buffer)
+    * **validation** is a flag to turn on PO source file validation. The validation makes sure that:
 
+      * there is exactly zero or one `msgid_plural` definition per translation entry; a `Multiple msgid_plural error` error gets thrown otherwise.
+      * there are no duplicate entries with exact `msgid` values; a `Duplicate msgid error` error gets thrown otherwise.
+      * the number of plural forms matches exactly the number from `nplurals` defined in `Plural-Forms` header for entries that have plural forms; a `Plural forms range error` error gets thrown otherwise.
+      * the number of `msgstr` matches exacty the one (if `msgid_plural` is not defined) or the number from `nplurals` (if `msgid_plural` is defined); a `Translation string range error` error gets thrown otherwise.
+
 Method returns gettext-parser specific translation object (see below)
@@ -43,8 +49,8 @@
 
-    gettextParser.po.createParseStream([defaultCharset][, streamOptions]) → Transform Stream
+    gettextParser.po.createParseStream([options][, transformOptions]) → Transform Stream
 
 Where
 
-  * **defaultCharset** is the charset to use if charset is not defined or is the default `"CHARSET"`
-  * **streamOptions** are the standard stream options
+  * **options** is an optional object, same as in `parse`. See [Parse PO files](#parse-po-files) section for details.
+  * **transformOptions** are the standard stream options.
 
@@ -87,2 +93,4 @@ **Example**
 
+### 
+
 ### Parse MO files
@@ -89,0 +97,0 @@

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

Improved metrics

Total package byte prevSize

56775

increased by6.83%

Number of package files

12

increased by9.09%

Lines of code

1314

increased by4.78%

Number of lines in readme file

215

increased by3.86%

Dependency changes

• Updatedcontent-type@^1.0.5

• Updatedreadable-stream@^4.3.0