lix/src/libutil/url-parts.hh
Maximilian Bosch ddcef3bcbb
Fix Nix to properly work with stores using a scoped IPv6 address
According to RFC4007[1], IPv6 addresses can have a so-called zone_id
separated from the actual address with `%` as delimiter. In contrast to
Nix 2.3, the version on `master` doesn't recognize it as such:

    $ nix ping-store --store ssh://root@fe80::1%18 --experimental-features nix-command
    warning: 'ping-store' is a deprecated alias for 'store ping'
    error: --- Error ----------------------------------------------------------------- nix
    don't know how to open Nix store 'ssh://root@fe80::1%18'

I modified the IPv6 match-regex accordingly to optionally detect this
part of the address. As we don't seem to do anything special with it, I
decided to leave it as part of the URL for now.

Fixes #4490

[1] https://tools.ietf.org/html/rfc4007
2021-03-16 19:14:42 +01:00

46 lines
2.3 KiB
C++

#pragma once
#include <string>
#include <regex>
namespace nix {
// URI stuff.
const static std::string pctEncoded = "(?:%[0-9a-fA-F][0-9a-fA-F])";
const static std::string schemeRegex = "(?:[a-z][a-z0-9+.-]*)";
const static std::string ipv6AddressSegmentRegex = "[0-9a-fA-F:]+(?:%\\w+)?";
const static std::string ipv6AddressRegex = "(?:\\[" + ipv6AddressSegmentRegex + "\\]|" + ipv6AddressSegmentRegex + ")";
const static std::string unreservedRegex = "(?:[a-zA-Z0-9-._~])";
const static std::string subdelimsRegex = "(?:[!$&'\"()*+,;=])";
const static std::string hostnameRegex = "(?:(?:" + unreservedRegex + "|" + pctEncoded + "|" + subdelimsRegex + ")*)";
const static std::string hostRegex = "(?:" + ipv6AddressRegex + "|" + hostnameRegex + ")";
const static std::string userRegex = "(?:(?:" + unreservedRegex + "|" + pctEncoded + "|" + subdelimsRegex + "|:)*)";
const static std::string authorityRegex = "(?:" + userRegex + "@)?" + hostRegex + "(?::[0-9]+)?";
const static std::string pcharRegex = "(?:" + unreservedRegex + "|" + pctEncoded + "|" + subdelimsRegex + "|[:@])";
const static std::string queryRegex = "(?:" + pcharRegex + "|[/? \"])*";
const static std::string segmentRegex = "(?:" + pcharRegex + "+)";
const static std::string absPathRegex = "(?:(?:/" + segmentRegex + ")*/?)";
const static std::string pathRegex = "(?:" + segmentRegex + "(?:/" + segmentRegex + ")*/?)";
// A Git ref (i.e. branch or tag name).
const static std::string refRegexS = "[a-zA-Z0-9][a-zA-Z0-9_.\\/-]*"; // FIXME: check
extern std::regex refRegex;
// Instead of defining what a good Git Ref is, we define what a bad Git Ref is
// This is because of the definition of a ref in refs.c in https://github.com/git/git
// See tests/fetchGitRefs.sh for the full definition
const static std::string badGitRefRegexS = "//|^[./]|/\\.|\\.\\.|[[:cntrl:][:space:]:?^~\[]|\\\\|\\*|\\.lock$|\\.lock/|@\\{|[/.]$|^@$|^$";
extern std::regex badGitRefRegex;
// A Git revision (a SHA-1 commit hash).
const static std::string revRegexS = "[0-9a-fA-F]{40}";
extern std::regex revRegex;
// A ref or revision, or a ref followed by a revision.
const static std::string refAndOrRevRegex = "(?:(" + revRegexS + ")|(?:(" + refRegexS + ")(?:/(" + revRegexS + "))?))";
const static std::string flakeIdRegexS = "[a-zA-Z][a-zA-Z0-9_-]*";
extern std::regex flakeIdRegex;
}