From 8d39b0b3433255fc9ef7ef4336e26b5b979b6f5a Mon Sep 17 00:00:00 2001
From: Matthieu Gautier <mgautier@kymeria.fr>
Date: Wed, 5 Jul 2017 11:28:08 +0200
Subject: [PATCH] Search result objects now have a get_content method.

This was not necessary when searching in only one zim file as `url` was
enough to get the article (and so the content).

If we want to search in several zim in the same time, we need a way to get
the content directly.
---
 include/searcher.h       |  1 +
 include/xapianSearcher.h |  1 +
 src/searcher.cpp         |  8 ++++++++
 src/xapianSearcher.cpp   | 22 +++++++++++++++++-----
 4 files changed, 27 insertions(+), 5 deletions(-)

diff --git a/include/searcher.h b/include/searcher.h
index e5549778..af28e521 100644
--- a/include/searcher.h
+++ b/include/searcher.h
@@ -46,6 +46,7 @@ class Result
   virtual std::string get_title() = 0;
   virtual int get_score() = 0;
   virtual std::string get_snippet() = 0;
+  virtual std::string get_content() = 0;
   virtual int get_wordCount() = 0;
   virtual int get_size() = 0;
 };
diff --git a/include/xapianSearcher.h b/include/xapianSearcher.h
index 907ca733..dcbe5647 100644
--- a/include/xapianSearcher.h
+++ b/include/xapianSearcher.h
@@ -43,6 +43,7 @@ class XapianResult : public Result
   virtual std::string get_title();
   virtual int get_score();
   virtual std::string get_snippet();
+  virtual std::string get_content();
   virtual int get_wordCount();
   virtual int get_size();
 
diff --git a/src/searcher.cpp b/src/searcher.cpp
index 4bfeab35..d83adc7f 100644
--- a/src/searcher.cpp
+++ b/src/searcher.cpp
@@ -45,6 +45,7 @@ class _Result : public Result
   virtual std::string get_title();
   virtual int get_score();
   virtual std::string get_snippet();
+  virtual std::string get_content();
   virtual int get_wordCount();
   virtual int get_size();
 
@@ -241,6 +242,13 @@ std::string _Result::get_snippet()
 {
   return iterator.get_snippet();
 }
+std::string _Result::get_content()
+{
+  if (iterator->good()) {
+    return iterator->getData();
+  }
+  return "";
+}
 int _Result::get_size()
 {
   return iterator.get_size();
diff --git a/src/xapianSearcher.cpp b/src/xapianSearcher.cpp
index aa0223d9..20688815 100644
--- a/src/xapianSearcher.cpp
+++ b/src/xapianSearcher.cpp
@@ -177,11 +177,10 @@ std::string XapianResult::get_snippet()
      We parse it and use the html dump to avoid remove html tags in the
      content and be able to nicely cut the text at random place. */
   MyHtmlParser htmlParser;
-  std::string content;
-  unsigned int contentLength;
-  std::string contentType;
-  searcher->reader->getContentByUrl(
-      get_url(), content, contentLength, contentType);
+  std::string content = get_content();
+  if (content.empty()) {
+    return content;
+  }
   try {
     htmlParser.parse_html(content, "UTF-8", true);
   } catch (...) {
@@ -189,6 +188,19 @@ std::string XapianResult::get_snippet()
   return searcher->results.snippet(htmlParser.dump, 500);
 }
 
+std::string XapianResult::get_content()
+{
+  if (!searcher->reader) {
+    return "";
+  }
+  std::string content;
+  unsigned int contentLength;
+  std::string contentType;
+  searcher->reader->getContentByUrl(
+      get_url(), content, contentLength, contentType);
+  return content;
+}
+
 int XapianResult::get_size()
 {
   if (searcher->valuesmap.empty()) {