fix($sanitize): Use same whitelist mechanism as $compile does.

`$sanitize` now uses the same mechanism as `$compile` to validate uris.
By this, the validation in `$sanitize` is more general and can be
configured in the same way as the one in `$compile`.

Changes
- Creates the new private service `$$sanitizeUri`.
- Moves related specs from `compileSpec.js` into `sanitizeUriSpec.js`.
- Refactors the `linky` filter to be less dependent on `$sanitize`
  internal functions.

Fixes #3748.

1 files changed, 74 insertions, 0 deletions

diff --git a/src/ng/sanitizeUri.js b/src/ng/sanitizeUri.js
new file mode 100644
index 00000000..97325094
--- /dev/null
+++ b/src/ng/sanitizeUri.js
@@ -0,0 +1,74 @@
+'use strict';
+
+/**
+ * @description
+ * Private service to sanitize uris for links and images. Used by $compile and $sanitize.
+ */
+function $$SanitizeUriProvider() {
+  var aHrefSanitizationWhitelist = /^\s*(https?|ftp|mailto|tel|file):/,
+    imgSrcSanitizationWhitelist = /^\s*(https?|ftp|file):|data:image\//;
+
+  /**
+   * @description
+   * Retrieves or overrides the default regular expression that is used for whitelisting of safe
+   * urls during a[href] sanitization.
+   *
+   * The sanitization is a security measure aimed at prevent XSS attacks via html links.
+   *
+   * Any url about to be assigned to a[href] via data-binding is first normalized and turned into
+   * an absolute url. Afterwards, the url is matched against the `aHrefSanitizationWhitelist`
+   * regular expression. If a match is found, the original url is written into the dom. Otherwise,
+   * the absolute url is prefixed with `'unsafe:'` string and only then is it written into the DOM.
+   *
+   * @param {RegExp=} regexp New regexp to whitelist urls with.
+   * @returns {RegExp|ng.$compileProvider} Current RegExp if called without value or self for
+   *    chaining otherwise.
+   */
+  this.aHrefSanitizationWhitelist = function(regexp) {
+    if (isDefined(regexp)) {
+      aHrefSanitizationWhitelist = regexp;
+      return this;
+    }
+    return aHrefSanitizationWhitelist;
+  };
+
+
+  /**
+   * @description
+   * Retrieves or overrides the default regular expression that is used for whitelisting of safe
+   * urls during img[src] sanitization.
+   *
+   * The sanitization is a security measure aimed at prevent XSS attacks via html links.
+   *
+   * Any url about to be assigned to img[src] via data-binding is first normalized and turned into
+   * an absolute url. Afterwards, the url is matched against the `imgSrcSanitizationWhitelist`
+   * regular expression. If a match is found, the original url is written into the dom. Otherwise,
+   * the absolute url is prefixed with `'unsafe:'` string and only then is it written into the DOM.
+   *
+   * @param {RegExp=} regexp New regexp to whitelist urls with.
+   * @returns {RegExp|ng.$compileProvider} Current RegExp if called without value or self for
+   *    chaining otherwise.
+   */
+  this.imgSrcSanitizationWhitelist = function(regexp) {
+    if (isDefined(regexp)) {
+      imgSrcSanitizationWhitelist = regexp;
+      return this;
+    }
+    return imgSrcSanitizationWhitelist;
+  };
+
+  this.$get = function() {
+    return function sanitizeUri(uri, isImage) {
+      var regex = isImage ? imgSrcSanitizationWhitelist : aHrefSanitizationWhitelist;
+      var normalizedVal;
+      // NOTE: urlResolve() doesn't support IE < 8 so we don't sanitize for that case.
+      if (!msie || msie >= 8 ) {
+        normalizedVal = urlResolve(uri).href;
+        if (normalizedVal !== '' && !normalizedVal.match(regex)) {
+          return 'unsafe:'+normalizedVal;
+        }
+      }
+      return uri;
+    };
+  };
+}