[fix] Added support for URI canonicalization

libview/src/index.ts

@@ -21,7 +21,8 @@
 import * as application from "./application";
 import * as definition from "./view-def";
 import * as implementation from "./view-impl";
+import * as uris from "./uris";
 import * as rdfEntities from "./rdf-entities";
 import * as rdfMeta from "./rdf-meta";
 
-export { application, definition, implementation, rdfEntities, rdfMeta };
+export { application, definition, implementation, uris, rdfEntities, rdfMeta };

libview/src/uris.ts

+/*******************************************************************************
+ * Copyright 2003-2018 LOGILAB S.A. (Paris, FRANCE), all rights reserved.
+ * contact http://www.logilab.fr/ -- mailto:contact@logilab.fr
+ *
+ * This file is part of CubicWeb.
+ *
+ * CubicWeb is free software: you can redistribute it and/or modify it under the
+ * terms of the GNU Lesser General Public License as published by the Free
+ * Software Foundation, either version 2.1 of the License, or (at your option)
+ * any later version.
+ *
+ * CubicWeb is distributed in the hope that it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
+ * FOR A PARTICULAR PURPOSE.  See the GNU Lesser General Public License for more
+ * details.
+ *
+ * You should have received a copy of the GNU Lesser General Public License along
+ * with CubicWeb.  If not, see <http://www.gnu.org/licenses/>.
+ ******************************************************************************/
+
+/**
+ * Gets the equivalent uri with unicode escape sequences
+ * @param uri The original uri
+ */
+export function uriEscape(uri: string): string {
+  let result = "";
+  for (var i = 0; i != uri.length; i++) {
+    let cc = uri.charCodeAt(i);
+    if (cc >= 0x100) {
+      let offset = cc >= 0xd800 && cc <= 0xdbff ? 1 : 0;
+      let cp = uri.codePointAt(i).toString();
+      result += "\\u";
+      let leading = 4 + offset * 4 - cp.length;
+      while (leading > 0) {
+        result += "0";
+        leading--;
+      }
+      result += cp;
+      i += offset;
+    } else {
+      result += uri.charAt(i);
+    }
+  }
+  return result;
+}
+
+/**
+ * Gets the equivalent extended uri
+ * @param uri The original uri
+ */
+export function uriUnescape(uri: string): string {
+  let result = "";
+  for (var i = 0; i != uri.length; i++) {
+    let c = uri.charAt(i);
+    if (c == "\\") {
+      let n = uri.charAt(i + 1);
+      if (n == "u") {
+        // \ u XXXX for unicode characters in the BMP
+        let codepoint = Number.parseInt(uri.substring(i + 2, i + 6), 16);
+        result += String.fromCodePoint(codepoint);
+        i += 5;
+      } else if (n == "U") {
+        // \ U XXXXXXXX for unicode characters outside the BMP
+        let codepoint = Number.parseInt(uri.substring(i + 2, i + 10), 16);
+        result += String.fromCodePoint(codepoint);
+        i += 9;
+      } else {
+        // \C for C, where C is any character other than 0, a, t, b, r, n, f, u and U
+        result += n;
+        i++;
+      }
+    } else {
+      // not the start of an escape sequence, replace as is
+      result += c;
+    }
+  }
+  return result;
+}