feedparser - npm Package Compare versions

Comparing version 0.9.15 to 0.10.0-beta

main.js

@@ -53,4 +53,16 @@ /**********************************************************************
 function handleAttributes (attrs, el) {
+  /*
+   * Using the sax.js option { xmlns: true }
+   * attrs is an array of objects (not strings) having the following properties
+   * name - e.g., xmlns:dc or href
+   * value
+   * prefix - the first part of the name of the attribute (before the colon)
+   * local - the second part of the name of the attribute (after the colon)
+   * uri - the uri of the namespace
+   *
+   */
+
   var parser = this
     , basepath = ''
+    , simplifiedAttributes = {}
     ;
@@ -62,19 +74,33 @@
 
-  Object.keys(attrs).forEach(function(name){
-    if (basepath && (name == 'href' || name == 'src' || name == 'uri')) {
+  Object.keys(attrs).forEach(function(key){
+    var attr = attrs[key]
+      , ns = {}
+      , prefix = ''
+      ;
+    if (attr.prefix === 'xmlns') {
+      ns[attr.name] = attr.value;
+      parser.meta['#ns'].push(ns);
+    }
+    // If the feed is using a non-default prefix, we'll use it, too
+    // But we force the use of the 'xml' prefix
+    if (attr.uri && attr.prefix && !utils.nslookup(attr.uri, attr.prefix) || utils.nslookup(attr.uri, 'xml')) {
+      prefix = ( utils.nsprefix(attr.uri) || attr.prefix ) + ( attr.local ? ':' : '' );
+    }
+    if (basepath && (attr.local == 'href' || attr.local == 'src' || attr.local == 'uri')) {
       // Apply xml:base to these elements as they appear
       // rather than leaving it to the ultimate parser
-      attrs[name] = utils.resolve(basepath, attrs[name]);
-    } else if (name == 'xml:base') {
+      attr.value = utils.resolve(basepath, attr.value);
+    } else if (attr.local === 'base' && utils.nslookup(attr.uri, 'xml')) {
+      // Keep track of the xml:base for the current node
       if (basepath) {
-        attrs[name] = utils.resolve(basepath, attrs[name]);
+        attr.value = utils.resolve(basepath, attr.value);
       }
-      parser.xmlbase.unshift({ '#name': el, '#': attrs[name]});
-    } else if (name == 'type' && attrs['type'] == 'xhtml') {
+      parser.xmlbase.unshift({ '#name': el, '#': attr.value});
+    } else if (attr.name === 'type' && attr.value === 'xhtml') {
       parser.in_xhtml = true;
       parser.xhtml = {'#name': el, '#': ''};
     }
-    attrs[name] = attrs[name].trim();
+    simplifiedAttributes[prefix + attr.local] = attr.value.trim();
   });
-  return attrs;
+  return simplifiedAttributes;
 }
@@ -100,2 +126,3 @@
     var el = node[name];
+
     if (normalize) {
@@ -568,3 +595,3 @@ switch(name){
   if (parser.options.feedurl) parser.xmlbase.unshift({ '#name': 'xml', '#': parser.options.feedurl});
-  parser.stream = sax.createStream(false /* strict mode - no */, {lowercase: true}); // https://github.com/isaacs/sax-js
+  parser.stream = sax.createStream(false /* strict mode - no */, {lowercase: true, xmlns: true }); // https://github.com/isaacs/sax-js
   parser.stream.on('error', function (e){ parser.handleSaxError(e, parser); });
@@ -696,3 +723,3 @@ parser.stream.on('opentag', function (n){ parser.handleOpenTag(n, parser); });
   }
-  if (!parser.xmlbase.length) { // .parseFile may have already populated this value
+  if (!parser.xmlbase.length) { // #parseFile may have already populated this value
     if (/^https?:/.test(url)) {
@@ -791,2 +818,5 @@ parser.xmlbase.unshift({ '#name': 'xml', '#': url});
   n['#name'] = node.name; // Avoid namespace collissions later...
+  n['#prefix'] = node.prefix; // The current ns prefix
+  n['#local'] = node.local; // The current element name, sans prefix
+  n['#uri'] = node.uri; // The current ns uri
   n['@'] = {};
@@ -806,16 +836,14 @@ n['#'] = '';
     parser.xhtml['#'] += '>';
-  } else if (parser.stack.length === 0 &&
-            (n['#name'] == 'rss' || n['#name'] == 'rdf:rdf' || n['#name'] == 'feed')) {
-    parser.meta['#ns'] = [];
-    parser.meta['@'] = [];
-    Object.keys(n['@']).forEach(function(name) {
+  } else if ( parser.stack.length === 0 &&
+              (n['#name'] === 'rss' ||
+              (n['#local'] === 'rdf' && utils.nslookup([n['#uri']], 'rdf')) ||
+              (n['#local'] === 'feed'&& utils.nslookup([n['#uri']], 'atom')) ) ) {
+      Object.keys(n['@']).forEach(function(name) {
       var o = {};
-      o[name] = n['@'][name];
-      if (name.indexOf('xmlns') === 0) {
-        parser.meta['#ns'].push(o);
-      } else if (name != 'version') {
+      if (name != 'version') {
+        o[name] = n['@'][name];
         parser.meta['@'].push(o);
       }
     });
-    switch(n['#name']) {
+    switch(n['#local']) {
     case 'rss':
@@ -825,3 +853,3 @@ parser.meta['#type'] = 'rss';
       break;
-    case 'rdf:rdf':
+    case 'rdf':
       parser.meta['#type'] = 'rdf';
@@ -841,2 +869,6 @@ parser.meta['#version'] = n['@']['version'] || '1.0';
   var parser = scope
+    , node = { '#name' : el
+             , '#prefix' : ''
+             , '#local' : '' }
+    , stdEl
     , item
@@ -846,3 +878,25 @@ , baseurl
   var n = parser.stack.shift();
+  el = el.split(':');
+
+  if (el.length > 1 && el[0] === n['#prefix']) {
+    if (utils.nslookup(n['#uri'], 'atom')) {
+      node['#prefix'] = el[0];
+      node['#local'] = el.slice(1).join(':');
+      node['#type'] = 'atom';
+    } else if (utils.nslookup(n['#uri'], 'rdf')) {
+      node['#prefix'] = el[0];
+      node['#local'] = el.slice(1).join(':');
+      node['#type'] = 'rdf';
+    } else {
+      node['#prefix'] = utils.nsprefix(n['#uri']) || n['#prefix'];
+      node['#local'] = el.slice(1).join(':');
+    }
+  } else {
+    node['#local'] = node['#name'];
+    node['#type'] = utils.nsprefix(n['#uri']) || n['#prefix'];
+  }
   delete n['#name'];
+  delete n['#local'];
+  delete n['#prefix'];
+  delete n['#uri'];
 
@@ -853,3 +907,3 @@ if (parser.xmlbase && parser.xmlbase.length) {
 
-  if (baseurl && (el == 'logo' || el == 'icon')) { // Via atom
+  if (baseurl && (node['#local'] === 'logo' || node['#local'] === 'icon') && node['#type'] === 'atom') {
     // Apply xml:base to these elements as they appear
@@ -865,3 +919,3 @@ // rather than leaving it to the ultimate parser
   if (parser.in_xhtml) {
-    if (el == parser.xhtml['#name']) { // The end of the XHTML
+    if (node['#name'] == parser.xhtml['#name']) { // The end of the XHTML
 
@@ -879,3 +933,3 @@ // Add xhtml data to the container element
     } else { // Somewhere in the middle of the XHTML
-      parser.xhtml['#'] += '</' + el + '>';
+      parser.xhtml['#'] += '</' + node['#name'] + '>';
     }
@@ -886,2 +940,3 @@ }
     if (n['#'].match(/^\s*$/)) {
+      // Delete text nodes with nothing by whitespace
       delete n['#'];
@@ -891,2 +946,3 @@ } else {
       if (Object.keys(n).length === 1) {
+        // If there is only one text node, hoist it
         n = n['#'];
@@ -897,3 +953,7 @@ }
 
-  if (el == 'item' || el == 'entry') { // We have an article!
+  if (node['#name'] === 'item' ||
+      node['#name'] === 'entry' ||
+      (node['#local'] === 'item' && (node['#prefix'] === '' || node['#type'] === 'rdf')) ||
+      (node['#local'] == 'entry' && (node['#prefix'] === '' || node['#type'] === 'atom'))) { // We have an article!
+
     if (!parser.meta.title) { // We haven't yet parsed all the metadata
@@ -913,3 +973,7 @@ utils.merge(parser.meta, handleMeta.call(parser, parser.stack[0], parser.meta['#type'], parser.options));
     parser.articles.push(item);
-  } else if ((el == 'channel' || el == 'feed') && !parser.meta.title) { // We haven't yet parsed all the metadata
+  } else if (!parser.meta.title && // We haven't yet parsed all the metadata
+              (node['#name'] === 'channel' ||
+               node['#name'] === 'feed' ||
+               (node['#local'] === 'channel' && (node['#prefix'] === '' || node['#type'] === 'rdf')) ||
+               (node['#local'] === 'feed' && (node['#prefix'] === '' || node['#type'] === 'atom')) ) ) {
     utils.merge(parser.meta, handleMeta(n, parser.meta['#type'], parser.options));
@@ -920,9 +984,14 @@ parser.emit('meta', parser.meta);
   if (parser.stack.length > 0) {
-    if (!parser.stack[0].hasOwnProperty(el)) {
-      parser.stack[0][el] = n;
-    } else if (parser.stack[0][el] instanceof Array) {
-      parser.stack[0][el].push(n);
+    if (node['#prefix'] && node['#local'] && !node['#type']) {
+      stdEl = node['#prefix'] + ':' + node['#local'];
     } else {
-      parser.stack[0][el] = [parser.stack[0][el], n];
+      stdEl = node['#local'] || node['#name'];
     }
+    if (!parser.stack[0].hasOwnProperty(stdEl)) {
+      parser.stack[0][stdEl] = n;
+    } else if (parser.stack[0][stdEl] instanceof Array) {
+      parser.stack[0][stdEl].push(n);
+    } else {
+      parser.stack[0][stdEl] = [parser.stack[0][stdEl], n];
+    }
   } else {
@@ -950,2 +1019,4 @@ parser.nodes = n;
   this.meta = {};
+  this.meta['#ns'] = [];
+  this.meta['@'] = [];
   this.articles = [];
@@ -952,0 +1023,0 @@ this.stack = [];

package.json

 { "name" : "feedparser"
 , "author" : "Dan MacTough <[e-mail]>"
 , "description" : "Robust RSS Atom and RDF feed parsing using sax js"
-, "version": "0.9.15"
+, "version": "0.10.0-beta"
 , "keywords" : ["rss", "feed", "atom", "rdf", "xml", "syndication"]
@@ -6,0 +6,0 @@ , "homepage" : "http://github.com/danmactough/node-feedparser"

utils.js

@@ -6,2 +6,3 @@
 var URL = require('url')
+  , NS = require('./namespaces')
   ;
@@ -98,2 +99,25 @@
 }
-exports.resolve = resolve;
+exports.resolve = resolve;
+
+/*
+ * Check whether a given namespace URI matches the given default
+ *
+ * @param {String} URI
+ * @param {String} default, e.g., 'atom'
+ * @return {Boolean}
+ */
+function nslookup (uri, def) {
+  return NS[uri] === def;
+}
+exports.nslookup = nslookup;
+
+/*
+ * Return the "default" namespace prefix for a given namespace URI
+ *
+ * @param {String} URI
+ * @return {String}
+ */
+function nsprefix (uri) {
+  return NS[uri];
+}
+exports.nsprefix = nsprefix;

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

Non-existent author

Supply chain risk

The package was published by an npm account that no longer exists.

Found 1 instance in 1 package

Improved metrics

Total package byte prevSize

442847

increased by320.49%

Number of package files

32

increased by146.15%

Lines of code

1482

increased by28.87%

Number of high supply chain risk alerts

0

decreased by-100%

No dependency changes