n3 - npm Package Compare versions

Comparing version 0.0.6 to 0.1.0

lib/n3lexer.js

 // **N3Lexer** tokenizes N3 documents.
 // ## Regular expressions
 var patterns = {
-  // These token expressions were taken from the [context-free grammar in N3](http://www.w3.org/2000/10/swap/grammar/n3.n3).
-  _explicituri: /^<([^>]*)>/,
-  _string: /^"[^"\\]*(?:\\.[^"\\]*)*"(?=[^"\\])/,
-  _tripleQuotedString: /^""("[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*")""/,
+  _explicituri: /^<((?:[^> \\]|\\[uU])*)>/,
+  _string: /^"[^"\\]*(?:\\.[^"\\]*)*"(?=[^"\\])|^'[^'\\]*(?:\\.[^'\\]*)*'(?=[^'\\])/,
+  _tripleQuotedString: /^""("[^"\\]*(?:(?:\\.|"(?!""))[^"\\]*)*")""|^''('[^'\\]*(?:(?:\\.|'(?!''))[^'\\]*)*')''/,
   _langcode: /^@([a-z]+(?:-[a-z0-9]+)*)(?=[^a-z0-9\-])/i,
-  _prefix: /^([A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff\u0370-\u037d\u037f-\u1fff\u200c-\u200d\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd][\-0-9A-Z_a-z\u00b7\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u037d\u037f-\u1fff\u200c-\u200d\u203f-\u2040\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd]*)?:(?=\s)/,
-  _qname:  /^([A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff\u0370-\u037d\u037f-\u1fff\u200c-\u200d\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd][\-0-9A-Z_a-z\u00b7\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u037d\u037f-\u1fff\u200c-\u200d\u203f-\u2040\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd]*)?:((?:[A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff\u0370-\u037d\u037f-\u1fff\u200c-\u200d\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd][\-0-9A-Z_a-z\u00b7\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u037d\u037f-\u1fff\u200c-\u200d\u203f-\u2040\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd]*)?)(?=[\s\.;,])/,
-  _number: /^(?:(-)|\+)?(\d+\.\d*|\.\d+|\d+)([eE](?:[\-\+])?\d+)?(?=\s*[,\.])/,
+  _prefix: /^((?:[A-Za-zÀ-ÖØ-öø-˿Ͱ-ͽ\u037f-\u1fff\u200c-\u200d⁰-\u218fⰀ-\u2fef、-\ud7ff豈-\ufdcfﷰ-�]|[\ud800-\udb7f][\udc00-\udfff])(?:[\.\-0-9A-Z_a-z·À-ÖØ-öø-ͽ\u037f-\u1fff\u200c-\u200d‿-⁀⁰-\u218fⰀ-\u2fef、-\ud7ff豈-\ufdcfﷰ-�]|[\ud800-\udb7f][\udc00-\udfff])*)?:(?=\s)/,
+  _qname:  /^((?:[A-Z_a-zÀ-ÖØ-öø-˿Ͱ-ͽ\u037f-\u1fff\u200c-\u200d⁰-\u218fⰀ-\u2fef、-\ud7ff豈-\ufdcfﷰ-�]|[\ud800-\udb7f][\udc00-\udfff])(?:[\.\-0-9A-Z_a-z·À-ÖØ-öø-ͽ\u037f-\u1fff\u200c-\u200d‿-⁀⁰-\u218fⰀ-\u2fef、-\ud7ff豈-\ufdcfﷰ-�]|[\ud800-\udb7f][\udc00-\udfff])*)?:((?:(?:[0-:A-Z_a-z·À-ÖØ-öø-ͽ\u037f-\u1fff\u200c-\u200d‿-⁀⁰-\u218fⰀ-\u2fef、-\ud7ff豈-\ufdcfﷰ-�]|[\ud800-\udb7f][\udc00-\udfff]|%[0-9a-fA-F]{2}|\\[!#-\/;=?\-@_~])(?:(?:[\.\-0-:A-Z_a-z·À-ÖØ-öø-ͽ\u037f-\u1fff\u200c-\u200d‿-⁀⁰-\u218fⰀ-\u2fef、-\ud7ff豈-\ufdcfﷰ-�]|[\ud800-\udb7f][\udc00-\udfff]|%[0-9a-fA-F]{2}|\\[!#-\/;=?\-@_~])*(?:[\-0-:A-Z_a-z·À-ÖØ-öø-ͽ\u037f-\u1fff\u200c-\u200d‿-⁀⁰-\u218fⰀ-\u2fef、-\ud7ff豈-\ufdcfﷰ-�]|[\ud800-\udb7f][\udc00-\udfff]|%[0-9a-fA-F]{2}|\\[!#-\/;=?\-@_~]))?)?)(?=[\s\.;,)])/,
+  _number: /^[\-+]?(?:\d+\.?\d*([eE](?:[\-\+])?\d+)|\d+\.\d+|\.\d+|\d+)(?=\s*[\s\.;,)])/,
   _boolean: /^(?:true|false)(?=\s+)/,
-  // The lexer needs these other token expressions as well.
   _punctuation: /^\.(?!\d)|^;|^,|^\[|^\]|^\(|^\)/, // If a digit follows a dot, it is a number, not punctuation.
   _fastString: /^"[^"\\]+"(?=[^"\\])/,
-  _keyword: /^@[a-z]+(?=\s)/,
-  _type: /^\^\^(?:<([^>]*)>|([A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff\u0370-\u037d\u037f-\u1fff\u200c-\u200d\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd][\-0-9A-Z_a-z\u00b7\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u037d\u037f-\u1fff\u200c-\u200d\u203f-\u2040\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd]*)?:([A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff\u0370-\u037d\u037f-\u1fff\u200c-\u200d\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd][\-0-9A-Z_a-z\u00b7\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u037d\u037f-\u1fff\u200c-\u200d\u203f-\u2040\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd]*)(?=[\s\.:,]))/,
+  _keyword: /^(?:@[a-z]+|[Pp][Rr][Ee][Ff][Ii][Xx]|[Bb][Aa][Ss][Ee])(?=\s)/,
+  _type: /^\^\^(?:<([^>]*)>|([A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff\u0370-\u037d\u037f-\u1fff\u200c-\u200d\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd][\-0-9A-Z_a-z\u00b7\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u037d\u037f-\u1fff\u200c-\u200d\u203f-\u2040\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd]*)?:([A-Z_a-z\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u02ff\u0370-\u037d\u037f-\u1fff\u200c-\u200d\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd][\-0-9A-Z_a-z\u00b7\u00c0-\u00d6\u00d8-\u00f6\u00f8-\u037d\u037f-\u1fff\u200c-\u200d\u203f-\u2040\u2070-\u218f\u2c00-\u2fef\u3001-\ud7ff\uf900-\ufdcf\ufdf0-\ufffd]*)(?=[\s\.;,)]))/,
   _shortPredicates: /^a(?=\s+|<)/,
-  // Whitespace, newlines, and comments are actually not specified yet in the current N3 grammar.
   _newline: /^[ \t]*(?:#[^\n\r]*)?(?:\r\n|\n|\r)[ \t]*/,
@@ -26,4 +23,9 @@ _whitespace: /^[ \t]+|^#[^\n\r]*/,
 // Regular expression and replacement string to escape N3 strings.
-var escapeSequence = /\\(\\|'|"|n|r|t|u([0-9abcdefABCDEF]{4}))/g;
-var escapeReplacements = { '\\': '\\', "'": "'", '"': '"', 'n': '\n', 'r': '\r', 't': '\t' };
+// Note how we catch invalid unicode sequences separately (they will trigger an error).
+var escapeSequence = /\\u([a-fA-F0-9]{4})|\\U([a-fA-F0-9]{8})|\\[uU]|\\(.)/g;
+var escapeReplacements = { '\\': '\\', "'": "'", '"': '"',
+                           'n': '\n', 'r': '\r', 't': '\t', 'f': '\f', 'b': '\b',
+                           '_': '_', '~': '~', '.': '.', '-': '-', '!': '!', '$': '$', '&': '&',
+                           '(': '(', ')': ')', '*': '*', '+': '+', ',': ',', ';': ';', '=': '=',
+                           '/': '/', '?': '?', '#': '#', '@': '@', '%': '%' };
 
@@ -83,2 +85,3 @@ // Different punctuation types.
                 };
+    var unescaped;
 
@@ -100,4 +103,7 @@ // Emit the EOF token if we're at the end and reading is complete.
     if (match = this._explicituri.exec(this._input)) {
+      unescaped = this._unescape(match[1]);
+      if (unescaped === null)
+        return reportSyntaxError(this);
       token.type = 'explicituri';
-      token.value = match[1];
+      token.value = unescaped;
     }
@@ -122,11 +128,18 @@ // Try to find a dot.
     else if (match = this._string.exec(this._input)) {
+      unescaped = this._unescape(match[0]);
+      if (unescaped === null)
+        return reportSyntaxError(this);
       token.type = 'literal';
-      token.value = this._unescapeString(match[0]);
+      token.value = unescaped.replace(/^'|'$/g, '"');
     }
     // Try to find a string literal wrapped in a pair of triple quotes.
     else if (match = this._tripleQuotedString.exec(this._input)) {
+      unescaped = match[1] || match[2];
+      // Count the newlines and advance line counter.
+      this._line += unescaped.split(/\r\n|\r|\n/).length - 1;
+      unescaped = this._unescape(unescaped);
+      if (unescaped === null)
+        return reportSyntaxError(this);
       token.type = 'literal';
-      // Count the newlines and advance line counter.
-      this._line += match[1].split(/\r\n|\r|\n/).length - 1;
-      token.value = this._unescapeString(match[1]);
+      token.value = unescaped.replace(/^'|'$/g, '"');
     }
@@ -136,13 +149,4 @@ // Try to find a number.
       token.type = 'literal';
-      var value = (match[1] === '-' ? '-' + match[2] : match[2]);
-      if (match[3]) {
-        token.value = '"' + value + match[3].replace('+', '').replace('E', 'e') +
-                      '"^^<http://www.w3.org/2001/XMLSchema#double>';
-      }
-      else {
-        if (value.match(/^-?\d+$/))
-          token.value = '"' + parseInt(value, 10) + '"^^<http://www.w3.org/2001/XMLSchema#integer>';
-        else
-          token.value = '"' + value + '"^^<http://www.w3.org/2001/XMLSchema#decimal>';
-      }
+      token.value = '"' + match[0] + '"^^<http://www.w3.org/2001/XMLSchema#' +
+                    (match[1] ? 'double>' : (/^[+-]?\d+$/.test(match[0]) ? 'integer>' : 'decimal>'));
     }
@@ -167,6 +171,8 @@ // Try to match a boolean.
     else if (match = this._keyword.exec(this._input)) {
-      token.type = match[0];
+      var keyword = match[0];
+      token.type = keyword[0] === '@' ? keyword : keyword.toUpperCase();
     }
     // Try to find a prefix.
-    else if (this._prevTokenType === '@prefix' && (match = this._prefix.exec(this._input))) {
+    else if ((this._prevTokenType === '@prefix' || this._prevTokenType === 'PREFIX') &&
+             (match = this._prefix.exec(this._input))) {
       token.type = 'prefix';
@@ -177,5 +183,8 @@ token.value = match[1] || '';
     else if (match = this._qname.exec(this._input)) {
+      unescaped = this._unescape(match[2]);
+      if (unescaped === null)
+        return reportSyntaxError(this);
       token.type = 'qname';
       token.prefix = match[1] || '';
-      token.value = match[2];
+      token.value = unescaped;
     }
@@ -191,7 +200,4 @@ // Try to find an abbreviated predicate.
       // Otherwise, a syntax error has occurred in the input.
-      if (this._inputComplete) {
-        match = this._nonwhitespace.exec(this._input);
-        delete this._input;
-        callback('Syntax error: unexpected "' + match[0] + '" on line ' + this._line + '.');
-      }
+      if (this._inputComplete)
+        reportSyntaxError(this);
       return false;
@@ -209,9 +215,42 @@ }
     return true;
+
+    function reportSyntaxError(self) {
+      match = self._nonwhitespace.exec(self._input);
+      delete self._input;
+      callback('Syntax error: unexpected "' + match[0] + '" on line ' + self._line + '.');
+      return false;
+    }
   },
 
-  // ### `unescapeString` replaces escape codes in N3 strings by the corresponding characters.
-  _unescapeString: function (string) {
-    return string.replace(escapeSequence, function (sequence, code, hexCode) {
-      return hexCode ? String.fromCharCode(parseInt(hexCode, 16)) : escapeReplacements[code];
-    });
+  // ### `unescape` replaces N3 escape codes by their corresponding characters.
+  _unescape: function (item) {
+    try {
+      return item.replace(escapeSequence, function (sequence, unicode4, unicode8, escapedChar) {
+        var charCode;
+        if (unicode4) {
+          charCode = parseInt(unicode4, 16);
+          if (isNaN(charCode))
+            throw "invalid character code";
+          return String.fromCharCode(charCode);
+        }
+        else if (unicode8) {
+          charCode = parseInt(unicode8, 16);
+          if (isNaN(charCode))
+            throw "invalid character code";
+          if (charCode < 0xFFFF)
+            return String.fromCharCode(charCode);
+          return String.fromCharCode(Math.floor((charCode - 0x10000) / 0x400) + 0xD800) +
+                 String.fromCharCode((charCode - 0x10000) % 0x400 + 0xDC00);
+        }
+        else {
+          var replacement = escapeReplacements[escapedChar];
+          if (!replacement)
+            throw "invalid escape sequence";
+          return replacement;
+        }
+      });
+    }
+    catch (error) {
+      return null;
+    }
   },
@@ -218,0 +257,0 @@

lib/n3parser.js

@@ -14,3 +14,3 @@ // **N3Parser** parses N3 documents.
 
-var undefined;
+var _undefined;
 
@@ -57,6 +57,14 @@ // ## Constructor
     case '@prefix':
+      this._sparqlStyle = false;
       return this._readPrefix;
+    case 'PREFIX':
+      this._sparqlStyle = true;
+      return this._readPrefix;
     // It could be a base declaration.
     case '@base':
+      this._sparqlStyle = false;
       return this._readBaseURI;
+    case 'BASE':
+      this._sparqlStyle = true;
+      return this._readBaseURI;
     // Otherwise, the next token must be a subject.
@@ -84,3 +92,3 @@ default:
         var prefix = this._prefixes[token.prefix];
-        if (prefix === undefined)
+        if (prefix === _undefined)
           return this._error('Undefined prefix "' + token.prefix + ':"', token);
@@ -103,2 +111,3 @@ this._subject = prefix + token.value;
     }
+    this._subjectHasPredicate = false;
     // The next token must be a predicate.
@@ -120,8 +129,7 @@ return this._readPredicate;
       if (token.prefix === '_') {
-        this._predicate = this._blankNodes[token.value] ||
-                          (this._blankNodes[token.value] = '_:b' + this._blankNodeCount++);
+        return this._error('Disallowed blank node as predicate', token);
       }
       else {
         var prefix = this._prefixes[token.prefix];
-        if (prefix === undefined)
+        if (prefix === _undefined)
           return this._error('Undefined prefix "' + token.prefix + ':"', token);
@@ -132,7 +140,17 @@ this._predicate = prefix + token.value;
     case 'bracketclose':
-      // Expected punctuation didn't come, must have been trailing semicolon.
+      // Expected predicate didn't come, must have been trailing semicolon.
       return this._readBlankNodeTail(token, true);
+    case 'dot':
+      // A dot is not allowed if the subject did not have a predicate yet
+      if (!this._subjectHasPredicate)
+        return this._error('Unexpected dot', token);
+      // Expected predicate didn't come, must have been trailing semicolon.
+      return this._readPunctuation(token, true);
+    case 'semicolon':
+      // Extra semicolons can be safely ignored
+      return this._readPredicate;
     default:
       return this._error('Expected predicate to follow "' + this._subject + '"', token);
     }
+    this._subjectHasPredicate = true;
     // The next token must be an object.
@@ -158,3 +176,3 @@ return this._readObject;
         var prefix = this._prefixes[token.prefix];
-        if (prefix === undefined)
+        if (prefix === _undefined)
           return this._error('Undefined prefix "' + token.prefix + ':"', token);
@@ -228,3 +246,3 @@ this._object = prefix + token.value;
         var prefix = this._prefixes[token.prefix];
-        if (prefix === undefined)
+        if (prefix === _undefined)
           return this._error('Undefined prefix "' + token.prefix + ':"', token);
@@ -263,3 +281,3 @@ value = prefix + token.value;
         var prefix = this._prefixes[token.prefix];
-        if (prefix === undefined)
+        if (prefix === _undefined)
           return this._error('Undefined prefix "' + token.prefix + ':"', token);
@@ -354,3 +372,3 @@ item = prefix + token.value;
   // ### `_readPunctuation` reads punctuation between triples or triple parts.
-  _readPunctuation: function (token) {
+  _readPunctuation: function (token, empty) {
     var next;
@@ -374,6 +392,7 @@ switch (token.type) {
     // A triple has been completed now, so return it.
-    this._callback(null, { subject: this._subject,
-                           predicate: this._predicate,
-                           object: this._object,
-                           context: 'n3/contexts#default' });
+    if (!empty)
+      this._callback(null, { subject: this._subject,
+                             predicate: this._predicate,
+                             object: this._object,
+                             context: 'n3/contexts#default' });
     return next;
@@ -417,2 +436,6 @@ },
   _readDeclarationPunctuation: function (token) {
+    // SPARQL-style declarations don't have punctuation.
+    if (this._sparqlStyle)
+      return this._readInTopContext(token);
+
     if (token.type !== 'dot')
@@ -449,3 +472,2 @@ return this._error('Expected declaration of to end with a dot', token);
     this._prefixes = Object.create(null);
-    this._prefixes[''] = this._documentURI ? this._documentURI + '#' : '#';
     // Set the triple callback.
@@ -458,3 +480,3 @@ this._callback = callback;
     this._lexer.tokenize(input, function (error, token) {
-      if (self._readCallback !== undefined) {
+      if (self._readCallback !== _undefined) {
         if (error !== null)
@@ -461,0 +483,0 @@ self._callback(error);

package.json

 {
   "name": "n3",
-  "version": "0.0.6",
-  "description": "Notation3 (N3) and RDF library.",
+  "version": "0.1.0",
+  "description": "Lightning fast, asynchronous, streaming Turtle / N3 / RDF library.",
   "author": "Ruben Verborgh <[e-mail]>",
-  "keywords": ["n3", "notation3", "turtle", "rdf"],
+  "keywords": ["turtle", "rdf", "n3", "streaming", "asynchronous"],
   "main": "./n3.js",
@@ -12,9 +12,10 @@ "engines": {
   "devDependencies": {
-    "vows": "~0.6.0",
+    "async": "~0.1.22",
     "chai": "~1.4.2",
     "chai-things": "~0.1.1",
+    "colors": "~0.6.0",
     "docco": "~0.3.0",
+    "jshint": "1.1.x",
     "request": "~2.9.203",
-    "colors": "~0.6.0",
-    "async": "~0.1.22"
+    "vows": "~0.6.0"
   },
@@ -21,0 +22,0 @@ "scripts": {

README.md

@@ -1,2 +0,2 @@
-# Node-n3 is a Notation3 and RDF library for node.js.
+# Lightning fast, asynchronous, streaming Turtle / N3 / RDF
 
@@ -7,14 +7,22 @@ [**Notation3 or N3**](http://www.w3.org/TeamSubmission/n3/) is a superset of [RDF](http://www.w3.org/TR/rdf-primer/), the [Semantic Web](http://www.w3.org/2001/sw/) language.
 Currently implemented:
+- streaming Turtle parser, [fully compliant](https://github.com/RubenVerborgh/node-n3/tree/master/spec) with the [latest candidate recommendation](http://www.w3.org/TR/turtle/)
 - high-performance N3 store
-- streaming Turtle parser
 
-[**Bringing reasoning to the Web**](http://reasoning.restdesc.org/) is the initiative with several open source projects (such as this one) that make N3 reasoning accessible.
+## Parsing Turtle
 
-# Use the node-n3 library.
+The node-n3 library features a streaming Turtle parser,
+processing Turtle documents as they grow.
 
-## Installation
-You can install the n3 library as an [npm](http://npmjs.org/) package.
-
-``` bash
-$ npm install n3
+``` js
+var parser = new n3.Parser();
+parser.parse('@prefix c: <http://example.org/cartoons#>.\n' +
+             'c:Tom a c:Cat.\n' +
+             'c:Jerry a c:Mouse;\n' +
+             '        c:smarterThan c:Tom.',
+             function (error, triple) {
+               if (triple)
+                 console.log(triple.subject, triple.predicate, triple.object, '.');
+               else
+                 console.log("# That's it, folks!")
+             });
 ```
@@ -39,23 +47,11 @@
 
-# Parsing Turtle
+## Installation
+You can install the n3 library as an [npm](http://npmjs.org/) package.
 
-The node-n3 library features a streaming Turtle parser,
-processing Turtle documents as they grow.
-
-``` js
-var parser = new n3.Parser();
-parser.parse('@prefix c: <http://example.org/cartoons#>.\n' +
-             'c:Tom a c:Cat.\n' +
-             'c:Jerry a c:Mouse;\n' +
-             '        c:smarterThan c:Tom.',
-             function (error, triple) {
-               if (triple)
-                 console.log(triple.subject, triple.predicate, triple.object, '.');
-               else
-                 console.log("# That's it, folks!")
-             });
+``` bash
+$ npm install n3
 ```
 
-# Learn more.
+# Learn more
 
 The [Bringing reasoning to the Web](http://reasoning.restdesc.org/) page explains the origins of this project and provides pointers to related resources.

test/n3lexer-test.js

@@ -42,2 +42,12 @@ var N3Lexer = require('../lib/n3lexer.js');
 
+    'should tokenize an explicituri with four-digit unicode characters':
+      shouldTokenize('<http://a.example/\\u0073>',
+                     { type: 'explicituri', value: 'http://a.example/s', line: 1 },
+                     { type: 'eof', line: 1 }),
+
+    'should tokenize an explicituri with eight-digit unicode characters':
+      shouldTokenize('<http://a.example/\\U00000073>',
+                     { type: 'explicituri', value: 'http://a.example/s', line: 1 },
+                     { type: 'eof', line: 1 }),
+
     'should tokenize two explicituris separated by whitespace':
@@ -88,3 +98,3 @@ shouldTokenize(' \n\t<http://ex.org/?bla#foo> \n\t<http://ex.org/?bla#bar> \n\t',
     'should tokenize a string with escape characters':
-      shouldTokenize('"\\\\ \\\' \\" \\n \\r \\t \\ua1b2" \n """\\\\ \\\' \\" \\n \\r \\t \\ua1b2"""',
+      shouldTokenize('"\\\\ \\\' \\" \\n \\r \\t \\ua1b2" \n """\\\\ \\\' \\" \\n \\r \\t \\U0000a1b2"""',
                      { type: 'literal', value: '"\\ \' " \n \r \t \ua1b2"', line: 1 },
@@ -105,6 +115,45 @@ { type: 'literal', value: '"\\ \' " \n \r \t \ua1b2"', line: 2 },
     'should tokenize a quoted string literal with type':
-      shouldTokenize('"string"^^<type> "string"^^ns:mytype ',
+      shouldTokenize('"stringA"^^<type> "stringB"^^ns:mytype ',
+                     { type: 'literal', value: '"stringA"', line: 1 },
+                     { type: 'type', value: 'type', line: 1 },
+                     { type: 'literal', value: '"stringB"', line: 1 },
+                     { type: 'type', value: 'mytype', prefix: 'ns', line: 1 },
+                     { type: 'eof', line: 1 }),
+
+    'should tokenize a single-quoted string literal':
+      shouldTokenize("'string' ",
                      { type: 'literal', value: '"string"', line: 1 },
+                     { type: 'eof', line: 1 }),
+
+    'should tokenize a triple single-quoted string literal':
+      shouldTokenize("'''string'''",
+                     { type: 'literal', value: '"string"', line: 1 },
+                     { type: 'eof', line: 1 }),
+
+    'should tokenize a triple single-quoted string literal with quotes newlines inside':
+      shouldTokenize("'''st'r\ni''ng'''",
+                     { type: 'literal', value: '"st\'r\ni\'\'ng"', line: 1 },
+                     { type: 'eof', line: 2 }),
+
+    'should tokenize a single-quoted string with escape characters':
+      shouldTokenize("'\\\\ \\\" \\' \\n \\r \\t \\ua1b2' \n '''\\\\ \\\" \\' \\n \\r \\t \\U0000a1b2'''",
+                     { type: 'literal', value: '"\\ " \' \n \r \t \ua1b2"', line: 1 },
+                     { type: 'literal', value: '"\\ " \' \n \r \t \ua1b2"', line: 2 },
+                     { type: 'eof', line: 2 }),
+
+    'should tokenize a single-quoted string literal with language code':
+      shouldTokenize("'string'@en 'string'@nl-be 'string'@EN ",
+                     { type: 'literal', value: '"string"', line: 1 },
+                     { type: 'langcode', value: 'en', line: 1 },
+                     { type: 'literal', value: '"string"', line: 1 },
+                     { type: 'langcode', value: 'nl-be', line: 1 },
+                     { type: 'literal', value: '"string"', line: 1 },
+                     { type: 'langcode', value: 'EN', line: 1 },
+                     { type: 'eof', line: 1 }),
+
+    'should tokenize a single-quoted string literal with type':
+      shouldTokenize("'stringA'^^<type> 'stringB'^^ns:mytype ",
+                     { type: 'literal', value: '"stringA"', line: 1 },
                      { type: 'type', value: 'type', line: 1 },
-                     { type: 'literal', value: '"string"', line: 1 },
+                     { type: 'literal', value: '"stringB"', line: 1 },
                      { type: 'type', value: 'mytype', prefix: 'ns', line: 1 },
@@ -116,7 +165,7 @@ { type: 'eof', line: 1 }),
                      { type: 'literal', value: '"10"^^<http://www.w3.org/2001/XMLSchema#integer>', line: 1 },
-                     { type: 'comma', line: 1},
-                     { type: 'literal', value: '"20"^^<http://www.w3.org/2001/XMLSchema#integer>', line: 1 },
-                     { type: 'dot', line: 1},
+                     { type: 'comma', line: 1 },
+                     { type: 'literal', value: '"+20"^^<http://www.w3.org/2001/XMLSchema#integer>', line: 1 },
+                     { type: 'dot', line: 1 },
                      { type: 'literal', value: '"-30"^^<http://www.w3.org/2001/XMLSchema#integer>', line: 1 },
-                     { type: 'comma', line: 1},
+                     { type: 'comma', line: 1 },
                      { type: 'literal', value: '"40"^^<http://www.w3.org/2001/XMLSchema#integer>', line: 1 },
@@ -127,11 +176,11 @@ { type: 'dot', line: 1 },
     'should tokenize a decimal literal':
-      shouldTokenize('1.. 2.0, .3. -0.4, -.5. ',
-                     { type: 'literal', value: '"1."^^<http://www.w3.org/2001/XMLSchema#decimal>', line: 1 },
-                     { type: 'dot', line: 1},
+      shouldTokenize('1. 2.0, .3. -0.4, -.5. ',
+                     { type: 'literal', value: '"1"^^<http://www.w3.org/2001/XMLSchema#integer>', line: 1 },
+                     { type: 'dot', line: 1 },
                      { type: 'literal', value: '"2.0"^^<http://www.w3.org/2001/XMLSchema#decimal>', line: 1 },
-                     { type: 'comma', line: 1},
+                     { type: 'comma', line: 1 },
                      { type: 'literal', value: '".3"^^<http://www.w3.org/2001/XMLSchema#decimal>', line: 1 },
-                     { type: 'dot', line: 1},
+                     { type: 'dot', line: 1 },
                      { type: 'literal', value: '"-0.4"^^<http://www.w3.org/2001/XMLSchema#decimal>', line: 1 },
-                     { type: 'comma', line: 1},
+                     { type: 'comma', line: 1 },
                      { type: 'literal', value: '"-.5"^^<http://www.w3.org/2001/XMLSchema#decimal>', line: 1 },
@@ -145,3 +194,3 @@ { type: 'dot', line: 1 },
                      { type: 'comma', line: 1},
-                     { type: 'literal', value: '"30.40e50"^^<http://www.w3.org/2001/XMLSchema#double>', line: 1 },
+                     { type: 'literal', value: '"+30.40E+50"^^<http://www.w3.org/2001/XMLSchema#double>', line: 1 },
                      { type: 'dot', line: 1},
@@ -219,3 +268,3 @@ { type: 'literal', value: '"-60.70e-80"^^<http://www.w3.org/2001/XMLSchema#double>', line: 1 },
 
-    'should tokenize prefix declarations':
+    'should tokenize @prefix declarations':
       shouldTokenize('@prefix : <http://uri.org/#>.\n@prefix abc: <http://uri.org/#>.',
@@ -232,2 +281,30 @@ { type: '@prefix', line: 1 },
 
+    'should tokenize @base declarations':
+      shouldTokenize('@base <http://uri.org/#>.\n@base <http://uri.org/#>.',
+                     { type: '@base', line: 1 },
+                     { type: 'explicituri', value: 'http://uri.org/#', line: 1 },
+                     { type: 'dot', line: 1 },
+                     { type: '@base', line: 2 },
+                     { type: 'explicituri', value: 'http://uri.org/#', line: 2 },
+                     { type: 'dot', line: 2 },
+                     { type: 'eof', line: 2 }),
+
+    'should tokenize PREFIX declarations':
+      shouldTokenize('PREFIX : <http://uri.org/#>\npreFiX abc: <http://uri.org/#>',
+                     { type: 'PREFIX', line: 1 },
+                     { type: 'prefix', value: '', line: 1 },
+                     { type: 'explicituri', value: 'http://uri.org/#', line: 1 },
+                     { type: 'PREFIX', line: 2 },
+                     { type: 'prefix', value: 'abc', line: 2 },
+                     { type: 'explicituri', value: 'http://uri.org/#', line: 2 },
+                     { type: 'eof', line: 2 }),
+
+    'should tokenize BASE declarations':
+      shouldTokenize('BASE <http://uri.org/#>\nbAsE <http://uri.org/#>',
+                     { type: 'BASE', line: 1 },
+                     { type: 'explicituri', value: 'http://uri.org/#', line: 1 },
+                     { type: 'BASE', line: 2 },
+                     { type: 'explicituri', value: 'http://uri.org/#', line: 2 },
+                     { type: 'eof', line: 2 }),
+
     'should tokenize qnames':
@@ -264,2 +341,13 @@ shouldTokenize(':a b:c d-dd:e-ee.',
 
+    'should tokenize mixed lists':
+      shouldTokenize('<a> <b> (1 "2" :o)',
+                     { type: 'explicituri', value: 'a', line: 1 },
+                     { type: 'explicituri', value: 'b', line: 1 },
+                     { type: 'liststart', line: 1 },
+                     { type: 'literal', value: '"1"^^<http://www.w3.org/2001/XMLSchema#integer>', line: 1 },
+                     { type: 'literal', value: '"2"', line: 1 },
+                     { type: 'qname', value: 'o', line: 1 },
+                     { type: 'listend', line: 1 },
+                     { type: 'eof', line: 1 }),
+
     'should tokenize the "a" predicate':
@@ -266,0 +354,0 @@ shouldTokenize('<x> a <y>.',

test/n3parser-test.js

@@ -91,2 +91,6 @@ var N3Parser = require('../lib/n3parser.js');
 
+    'should not parse undefined empty prefix in subject':
+      shouldNotParse(':a ',
+                     'Undefined prefix ":" at line 1.'),
+
     'should not parse undefined prefix in subject':
@@ -104,2 +108,8 @@ shouldNotParse('a:a ',
 
+    'should parse triples with SPARQL prefixes':
+      shouldParse('PREFIX : <#>\n' +
+                  'PrEfIX a: <a#> ' +
+                  ':x a:a a:b.',
+                  ['#x', 'a#a', 'a#b']),
+
     'should parse statements with shared subjects':
@@ -110,2 +120,12 @@ shouldParse('<a> <b> <c>;\n<d> <e>.',
 
+    'should parse statements with shared subjects and trailing semicolon':
+      shouldParse('<a> <b> <c>;\n<d> <e>;\n.',
+                  ['a', 'b', 'c'],
+                  ['a', 'd', 'e']),
+
+    'should parse statements with shared subjects and multiple semicolons':
+      shouldParse('<a> <b> <c>;;\n<d> <e>.',
+                  ['a', 'b', 'c'],
+                  ['a', 'd', 'e']),
+
     'should parse statements with shared subjects and predicates':
@@ -117,8 +137,8 @@ shouldParse('<a> <b> <c>, <d>.',
     'should parse statements with named blank nodes':
-      shouldParse('_:a _:b _:c.',
-                  ['_:b0', '_:b1', '_:b2']),
+      shouldParse('_:a <b> _:c.',
+                  ['_:b0', 'b', '_:b1']),
 
     'should parse statements with empty blank nodes':
-      shouldParse('[] _:b [].',
-                  ['_:b0', '_:b1', '_:b2']),
+      shouldParse('[] <b> [].',
+                  ['_:b0', 'b', '_:b1']),
 
@@ -262,9 +282,2 @@ 'should parse statements with unnamed blank nodes in the subject':
 
-    'should resolve the colon prefix against the hash URI':
-      shouldParse('@base <base/>.\n' +
-                  '<a> <b> <c>.\n' +
-                  ':x :y :z.',
-                  ['base/a', 'base/b', 'base/c'],
-                  ['#x', '#y', '#z']),
-
     'should resolve URIs against @base':
@@ -278,2 +291,10 @@ shouldParse('@base <http://ex.org/>.\n' +
 
+    'should resolve URIs against SPARQL base':
+      shouldParse('BASE <http://ex.org/>\n' +
+                  '<a> <b> <c>. ' +
+                  'BASE <d/> ' +
+                  '<e> <f> <g>.',
+                  ['http://ex.org/a', 'http://ex.org/b', 'http://ex.org/c'],
+                  ['http://ex.org/d/e', 'http://ex.org/d/f', 'http://ex.org/d/g']),
+
     'should not parse improperly nested square brackets':
@@ -283,6 +304,2 @@ shouldNotParse('<a> <b> [<c> <d>]].',
 
-    'should error when a predicate is not there':
-      shouldNotParse('<a>.',
-                     'Expected predicate to follow "a" at line 1.'),
-
     'should error when an object is not there':
@@ -315,9 +332,2 @@ shouldNotParse('<a> <b>.',
                   ['http://ex.org/d/h', 'http://ex.org/d/i', 'http://ex.org/d/j']),
-
-    'should resolve the colon prefix against the document URI':
-      shouldParse('@base <base/>.\n' +
-                  '<a> <b> <c>.\n' +
-                  ':x :y :z.',
-                  ['doc/base/a', 'doc/base/b', 'doc/base/c'],
-                  ['doc/file.ttl#x', 'doc/file.ttl#y', 'doc/file.ttl#z']),
   }
@@ -324,0 +334,0 @@ }).export(module);

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

Network access

Supply chain risk

This module accesses the network.

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

101869

increased by16.38%

Lines of code

2194

increased by16.39%

Worsened metrics

Dev dependency count

8

increased by14.29%

Number of lines in readme file

56

decreased by-6.67%

Number of medium supply chain risk alerts

4

increased by300%

No dependency changes