+ add support of favicon in library manager

+ fix a bug in the snippet lenght computation in the search engin indexer

src/common/base64.cpp

@@ -0,0 +1,122 @@
+/* 
+   base64.cpp and base64.h
+
+   Copyright (C) 2004-2008 René Nyffenegger
+
+   This source code is provided 'as-is', without any express or implied
+   warranty. In no event will the author be held liable for any damages
+   arising from the use of this software.
+
+   Permission is granted to anyone to use this software for any purpose,
+   including commercial applications, and to alter it and redistribute it
+   freely, subject to the following restrictions:
+
+   1. The origin of this source code must not be misrepresented; you must not
+      claim that you wrote the original source code. If you use this source code
+      in a product, an acknowledgment in the product documentation would be
+      appreciated but is not required.
+
+   2. Altered source versions must be plainly marked as such, and must not be
+      misrepresented as being the original source code.
+
+   3. This notice may not be removed or altered from any source distribution.
+
+   René Nyffenegger rene.nyffenegger@adp-gmbh.ch
+*/
+
+#include "base64.h"
+#include <iostream>
+
+static const std::string base64_chars = 
+             "ABCDEFGHIJKLMNOPQRSTUVWXYZ"
+             "abcdefghijklmnopqrstuvwxyz"
+  "0123456789+/";
+
+
+static inline bool is_base64(unsigned char c) {
+  return (isalnum(c) || (c == '+') || (c == '/'));
+}
+
+std::string base64_encode(unsigned char const* bytes_to_encode, unsigned int in_len) {
+  std::string ret;
+  int i = 0;
+  int j = 0;
+  unsigned char char_array_3[3];
+  unsigned char char_array_4[4];
+
+  while (in_len--) {
+    char_array_3[i++] = *(bytes_to_encode++);
+    if (i == 3) {
+      char_array_4[0] = (char_array_3[0] & 0xfc) >> 2;
+      char_array_4[1] = ((char_array_3[0] & 0x03) << 4) + ((char_array_3[1] & 0xf0) >> 4);
+      char_array_4[2] = ((char_array_3[1] & 0x0f) << 2) + ((char_array_3[2] & 0xc0) >> 6);
+      char_array_4[3] = char_array_3[2] & 0x3f;
+
+      for(i = 0; (i <4) ; i++)
+        ret += base64_chars[char_array_4[i]];
+      i = 0;
+    }
+  }
+
+  if (i)
+    {
+      for(j = i; j < 3; j++)
+	char_array_3[j] = '\0';
+
+      char_array_4[0] = (char_array_3[0] & 0xfc) >> 2;
+      char_array_4[1] = ((char_array_3[0] & 0x03) << 4) + ((char_array_3[1] & 0xf0) >> 4);
+      char_array_4[2] = ((char_array_3[1] & 0x0f) << 2) + ((char_array_3[2] & 0xc0) >> 6);
+      char_array_4[3] = char_array_3[2] & 0x3f;
+
+      for (j = 0; (j < i + 1); j++)
+	ret += base64_chars[char_array_4[j]];
+
+      while((i++ < 3))
+	ret += '=';
+
+    }
+
+  return ret;
+
+}
+
+std::string base64_decode(std::string const& encoded_string) {
+  int in_len = encoded_string.size();
+  int i = 0;
+  int j = 0;
+  int in_ = 0;
+  unsigned char char_array_4[4], char_array_3[3];
+  std::string ret;
+
+  while (in_len-- && ( encoded_string[in_] != '=') && is_base64(encoded_string[in_])) {
+    char_array_4[i++] = encoded_string[in_]; in_++;
+    if (i ==4) {
+      for (i = 0; i <4; i++)
+        char_array_4[i] = base64_chars.find(char_array_4[i]);
+
+      char_array_3[0] = (char_array_4[0] << 2) + ((char_array_4[1] & 0x30) >> 4);
+      char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2);
+      char_array_3[2] = ((char_array_4[2] & 0x3) << 6) + char_array_4[3];
+
+      for (i = 0; (i < 3); i++)
+        ret += char_array_3[i];
+      i = 0;
+    }
+  }
+
+  if (i) {
+    for (j = i; j <4; j++)
+      char_array_4[j] = 0;
+
+    for (j = 0; j <4; j++)
+      char_array_4[j] = base64_chars.find(char_array_4[j]);
+
+    char_array_3[0] = (char_array_4[0] << 2) + ((char_array_4[1] & 0x30) >> 4);
+    char_array_3[1] = ((char_array_4[1] & 0xf) << 4) + ((char_array_4[2] & 0x3c) >> 2);
+    char_array_3[2] = ((char_array_4[2] & 0x3) << 6) + char_array_4[3];
+
+    for (j = 0; (j < i - 1); j++) ret += char_array_3[j];
+  }
+
+  return ret;
+}

src/common/base64.h

@@ -0,0 +1,4 @@
+#include <string>
+
+std::string base64_encode(unsigned char const* , unsigned int len);
+std::string base64_decode(std::string const& s);

src/common/kiwix/indexer.cpp

@@ -134,10 +134,10 @@ namespace kiwix {
 	  /* snippet */
 	  std::string snippet = std::string(this->htmlParser.dump, 0, 300);
 	  std::string::size_type last = snippet.find_last_of('.');
-	  if (last != snippet.npos)
+	  if (last == snippet.npos)
 	    last = snippet.find_last_of(' ');
 	  if (last != snippet.npos)
-	    snippet = snippet.substr(0, last+1);
+	    snippet = snippet.substr(0, last);
 
 	  /* size */
 	  stringstream sizeStringStream;

src/common/kiwix/library.cpp

@@ -37,7 +37,8 @@ namespace kiwix {
     articleCount(""),
     mediaCount(""),
     readOnly(false),
-    size("") {
+    size(""),
+    faviconMimeType("") {
   }
   
   /* Destructor */

src/common/kiwix/library.h

@@ -25,7 +25,7 @@
 #include <string>
 #include <vector>
 
-#define KIWIX_LIBRARY_VERSION "20110512"
+#define KIWIX_LIBRARY_VERSION "20110514"
 
 using namespace std;
 
@@ -56,6 +56,8 @@ namespace kiwix {
     string mediaCount;
     bool readOnly;
     string size;
+    string favicon;
+    string faviconMimeType;
   };
 
   class Library {

src/common/kiwix/manager.cpp

@@ -58,6 +58,8 @@ namespace kiwix {
       book.articleCount = bookNode.attribute("articleCount").value();
       book.mediaCount = bookNode.attribute("mediaCount").value();
       book.size = bookNode.attribute("size").value();
+      book.favicon = bookNode.attribute("favicon").value();
+      book.faviconMimeType = bookNode.attribute("faviconMimeType").value();
       
       /* Update the book properties with the new importer */
       if (libraryVersion.empty() || atoi(libraryVersion.c_str()) < atoi(KIWIX_LIBRARY_VERSION)) {
@@ -162,6 +164,12 @@ namespace kiwix {
 
 	if (itr->size != "")
 	  bookNode.append_attribute("size") = itr->size.c_str();
+
+	if (itr->favicon != "")
+	  bookNode.append_attribute("favicon") = itr->favicon.c_str();
+
+	if (itr->faviconMimeType != "")
+	  bookNode.append_attribute("faviconMimeType") = itr->faviconMimeType.c_str();
       }
     }
 
@@ -219,6 +227,12 @@ namespace kiwix {
       sprintf (csize, "%u", size);
       book.size = csize;
 
+      string favicon;
+      string faviconMimeType;
+      if (reader.getFavicon(favicon, faviconMimeType)) {
+	book.favicon = base64_encode(reinterpret_cast<const unsigned char*>(favicon.c_str()), favicon.length());
+	book.faviconMimeType = faviconMimeType;
+      }
     } catch (...) {
       return false;
     }

src/common/kiwix/manager.h

@@ -31,6 +31,7 @@
 
 #include <pugixml.hpp>
 
+#include <base64.h>
 #include <kiwix/library.h>
 #include <kiwix/reader.h>
 

src/common/kiwix/reader.cpp

@@ -129,6 +129,20 @@ namespace kiwix {
     return url;
   }
   
+  bool Reader::getFavicon(string &content, string &mimeType) {
+    unsigned int contentLength = 0;
+    
+    this->getContentByUrl( "/-/favicon.png", content, 
+			   contentLength, mimeType);
+    
+    if (content.empty()) {
+      this->getContentByUrl( "/I/favicon.png", content, 
+			     contentLength, mimeType);
+    }
+
+    return content.empty() ? false : true;
+  }
+
   /* Return a metatag value */
   bool Reader::getMetatag(const string &name, string &value) {
     unsigned int contentLength = 0;

src/common/kiwix/reader.h

@@ -51,6 +51,7 @@ namespace kiwix {
     string getLanguage();
     string getDate();
     string getCreator();
+    bool getFavicon(string &content, string &mimeType);
     bool getPageUrlFromTitle(const string &title, string &url);
     bool getContentByUrl(const string &url, string &content, unsigned int &contentLength, string &contentType);
     bool searchSuggestions(const string &prefix, unsigned int suggestionsCount);