Skip to content

Fix Counter metadata by normalizing MIME types and removing malformed entries (https://github.com/openzim/zim-tools/issues/473) #998

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
wants to merge 2 commits into
base: main
Choose a base branch
from
Open

Fix Counter metadata by normalizing MIME types and removing malformed entries (https://github.com/openzim/zim-tools/issues/473) #998

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
dd0d181
regex for counter
Aevil1 Jun 30, 2025
e43dd54
Update counterHandler.cpp
Aevil1 Jul 1, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
67 changes: 47 additions & 20 deletions src/writer/counterHandler.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,7 +19,7 @@

#include "counterHandler.h"
#include "creatordata.h"

#include <regex>
#include <zim/writer/contentProvider.h>
#include <zim/blob.h>
#include <zim/tools.h>
Expand All @@ -45,18 +45,30 @@ DirentHandler::Dirents CounterHandler::createDirents() const {
}

DirentHandler::ContentProviders CounterHandler::getContentProviders() const {
ContentProviders ret;
Formatter fmt;
bool first = true;
for(auto pair: m_mimetypeCounter) {
if (! first) {
fmt << ";";
ContentProviders ret;
Formatter fmt;
bool first = true;

// Only allow well-formed mime types: type/subtype
std::regex validMimeRegex("^[a-zA-Z0-9._+-]+/[a-zA-Z0-9._+-]+$");

for (const auto& pair : m_mimetypeCounter) {
const auto& mimetype = pair.first;
const auto& count = pair.second;

if (!std::regex_match(mimetype, validMimeRegex)) {
continue; // Skip invalid format
}

if (!first) {
fmt << ";";
}
fmt << mimetype << "=" << count;
first = false;
}
fmt << pair.first << "=" << pair.second;
first = false;
}
ret.push_back(std::unique_ptr<ContentProvider>(new StringProvider(fmt)));
return ret;

ret.push_back(std::unique_ptr<ContentProvider>(new StringProvider(fmt)));
return ret;
}

void CounterHandler::handle(Dirent* dirent, const Hints& hints)
Expand All @@ -65,12 +77,27 @@ void CounterHandler::handle(Dirent* dirent, const Hints& hints)

void CounterHandler::handle(Dirent* dirent, std::shared_ptr<Item> item)
{
if (dirent->getNamespace() != NS::C) {
return;
}
auto mimetype = item->getMimeType();
if (mimetype.empty()) {
return;
}
m_mimetypeCounter[mimetype] += 1;
if (dirent->getNamespace() != NS::C) {
return;
}

auto mimetype = item->getMimeType();
if (mimetype.empty()) {
return;
}

// Strip parameters after semicolon
auto semicolonPos = mimetype.find(';');
if (semicolonPos != std::string::npos) {
mimetype = mimetype.substr(0, semicolonPos);
}

// Trim whitespace (optional, based on zim::tools::trim)
zim::tools::trim(mimetype);

if (mimetype.empty()) {
return;
}

m_mimetypeCounter[mimetype] += 1;
}