From 84e3719806751e128bbf6f3a2b8981ea9e8660a5 Mon Sep 17 00:00:00 2001
From: Matthieu Gautier <mgautier@kymeria.fr>
Date: Mon, 4 Apr 2022 18:05:38 +0200
Subject: [PATCH] Correctly detect the number of article for zim version <= 6

---
 src/book.cpp               |  2 +-
 src/tools/archiveTools.cpp | 24 ++++++++++++++++++++++++
 src/tools/archiveTools.h   |  1 +
 3 files changed, 26 insertions(+), 1 deletion(-)

diff --git a/src/book.cpp b/src/book.cpp
index c49ab2f19..32766b6f2 100644
--- a/src/book.cpp
+++ b/src/book.cpp
@@ -83,7 +83,7 @@ void Book::update(const zim::Archive& archive) {
   m_flavour = getMetaFlavour(archive);
   m_tags = getMetaTags(archive);
   m_category = getCategoryFromTags();
-  m_articleCount = archive.getArticleCount();
+  m_articleCount = getArchiveArticleCount(archive);
   m_mediaCount = getArchiveMediaCount(archive);
   m_size = static_cast<uint64_t>(getArchiveFileSize(archive)) << 10;
 
diff --git a/src/tools/archiveTools.cpp b/src/tools/archiveTools.cpp
index 5ec5bd9e9..5971ec495 100644
--- a/src/tools/archiveTools.cpp
+++ b/src/tools/archiveTools.cpp
@@ -125,6 +125,30 @@ unsigned int getArchiveMediaCount(const zim::Archive& archive) {
   return counter;
 }
 
+unsigned int getArchiveArticleCount(const zim::Archive& archive) {
+  // [HACK]
+  // getArticleCount() returns different things depending of the "version" of the zim.
+  // On old zim (<=6), it returns the number of entry in `A` namespace
+  // On recent zim (>=7), it returns:
+  //  - the number of entry in `C` namespace (==getEntryCount) if no frontArticleIndex is present
+  //  - the number of front article if a frontArticleIndex is present
+  // The use case >=7 without frontArticleIndex is pretty rare so we don't care
+  // We can detect if we are reading a zim <= 6 by checking if we have a newNamespaceScheme.
+  if (archive.hasNewNamespaceScheme()) {
+    //The articleCount is "good"
+    return archive.getArticleCount();
+  } else {
+    // We have to parse the `M/Counter` metadata
+    unsigned int counter = 0;
+    for(const auto& pair:parseArchiveCounter(archive)) {
+      if (startsWith(pair.first, "text/html")) {
+        counter += pair.second;
+      }
+    }
+    return counter;
+  }
+}
+
 unsigned int getArchiveFileSize(const zim::Archive& archive) {
   return archive.getFilesize() / 1024;
 }
diff --git a/src/tools/archiveTools.h b/src/tools/archiveTools.h
index cfcf1ced1..0e2108045 100644
--- a/src/tools/archiveTools.h
+++ b/src/tools/archiveTools.h
@@ -46,6 +46,7 @@ namespace kiwix
                            std::string& content, std::string& mimeType);
 
     unsigned int getArchiveMediaCount(const zim::Archive& archive);
+    unsigned int getArchiveArticleCount(const zim::Archive& archive);
     unsigned int getArchiveFileSize(const zim::Archive& archive);
 
     zim::Item getFinalItem(const zim::Archive& archive, const zim::Entry& entry);