Read dpkg tables to handle architecture wildcards

Our implementation of wildcards was rudimentary. It worked for some
common ones, but it was also broken: For example, armel matched any-armel,
but should match any-arm.

With this commit, we load the correct tables from dpkg. Supported are
both triplets and quadruplet tables (the latter introduced in dpkg 1.18.11).

There are some odd things we have to deal with in the cache filter for
historical and API reasons:

* The character "*" must be accepted as an alternative to any - in fact
  it may appear anywhere in the wildcard as we also allow fnmatch() style
  wildcard matching on the commandline.

* The code might get passed an arch with a minus at the end, for example
  the cmdline "install apt:any-arm-" will first try to check if any-arm-
  is a valid architecture. We deal with this by rejecting any wildcard
  ending in a minus.

* Triplets are actually implemented by extending them to faux quadruplets
  - by prepending a "base" component for the architecture tuple, and "any"
  if there is a wildcard component.

Once we have constructed a wildcard, it is transformed into an fnmatch()
expression for historical reasons. In the future, we should really get a
tuple class and implement matching in a better, more explicit way.

This does for now though - it passes all the test cases and accepts all
things it should accept.

Closes: #748936
Thanks: James Clarke <jrtc27@jrtc27.com> for the initial patch

2 files changed, 158 insertions, 28 deletions

diff --git a/apt-pkg/cachefilter.cc b/apt-pkg/cachefilter.cc
index b1adf5de3..cc4cdf73c 100644
--- a/apt-pkg/cachefilter.cc
+++ b/apt-pkg/cachefilter.cc
@@ -14,7 +14,9 @@
 #include <apt-pkg/strutl.h>
 #include <apt-pkg/macros.h>
 
+#include <algorithm>
 #include <string>
+#include <unordered_map>
 #include <string.h>
 #include <regex.h>
 #include <fnmatch.h>
@@ -22,6 +24,9 @@
 #include <apti18n.h>
 									/*}}}*/
 namespace APT {
+
+APT_HIDDEN std::unordered_map<std::string, std::vector<std::string>> ArchToTupleMap;
+
 namespace CacheFilter {
 APT_CONST Matcher::~Matcher() {}
 APT_CONST PackageMatcher::~PackageMatcher() {}
@@ -68,38 +73,72 @@ bool PackageNameMatchesFnmatch::operator() (pkgCache::GrpIterator const &Grp) {
    return fnmatch(Pattern.c_str(), Grp.Name(), FNM_CASEFOLD) == 0;
 }
 									/*}}}*/
-// Architecture matches <libc>-<kernel>-<cpu> specification		/*{{{*/
+// Architecture matches <abi>-<libc>-<kernel>-<cpu> specification	/*{{{*/
 //----------------------------------------------------------------------
-/* The complete architecture, consisting of <libc>-<kernel>-<cpu>. */
-static std::string CompleteArch(std::string const &arch, bool const isPattern) {
-   auto const found = arch.find('-');
-   if (found != std::string::npos)
+
+static std::vector<std::string> ArchToTuple(std::string arch) {
+   // Strip leading linux- from arch if present
+   // dpkg says this may disappear in the future
+   if (APT::String::Startswith(arch, std::string("linux-")))
+      arch = arch.substr(6);
+
+   auto it = ArchToTupleMap.find(arch);
+   if (it != ArchToTupleMap.end())
+   {
+      std::vector<std::string> result = it->second;
+      // Hack in support for triplets
+      if (result.size() == 3)
+	 result.emplace(result.begin(), "base");
+      return result;
+   } else
    {
-      // ensure that only -any- is replaced and not something like company-
-      std::string complete = std::string("-").append(arch).append("-");
-      size_t pos = 0;
-      char const * const search = "-any-";
-      auto const search_len = strlen(search) - 2;
-      while((pos = complete.find(search, pos)) != std::string::npos) {
-	 complete.replace(pos + 1, search_len, "*");
-	 pos += 2;
+      return {};
+   }
+}
+
+static std::vector<std::string> PatternToTuple(std::string const &arch) {
+   std::vector<std::string> tuple = VectorizeString(arch, '-');
+   if (std::find(tuple.begin(), tuple.end(), std::string("any")) != tuple.end() ||
+       std::find(arch.begin(), arch.end(), '*') != arch.end()) {
+      while (tuple.size() < 4) {
+	 tuple.emplace(tuple.begin(), "any");
+      }
+      return tuple;
+   } else
+      return ArchToTuple(arch);
+}
+
+/* The complete architecture, consisting of <abi>-<libc>-<kernel>-<cpu>. */
+static std::string CompleteArch(std::string const &arch, bool const isPattern) {
+   auto tuple = isPattern ? PatternToTuple(arch) : ArchToTuple(arch);
+
+   // Bah, the commandline will try and pass us stuff like amd64- -- we need
+   // that not to match an architecture, but the code below would turn it into
+   // a valid tuple. Let's just use an invalid tuple here.
+   if (APT::String::Endswith(arch, "-") || APT::String::Startswith(arch, "-"))
+      return "invalid-invalid-invalid-invalid";
+
+   if (tuple.empty()) {
+      // Fallback for unknown architectures
+      // Patterns never fail if they contain wildcards, so by this point, arch
+      // has no wildcards.
+      tuple = VectorizeString(arch, '-');
+      switch (tuple.size()) {
+	 case 1:
+	    tuple.emplace(tuple.begin(), "linux");
+	    /* fall through */
+	 case 2:
+	    tuple.emplace(tuple.begin(), "gnu");
+	    /* fall through */
+	 case 3:
+	    tuple.emplace(tuple.begin(), "base");
+	    /* fall through */
+	    break;
       }
-      complete = complete.substr(1, complete.size()-2);
-      if (arch.find('-', found+1) != std::string::npos)
-	 // <libc>-<kernel>-<cpu> format
-	 return complete;
-      // <kernel>-<cpu> format
-      else if (isPattern)
-	 return "*-" + complete;
-      else
-	 return "gnu-" + complete;
    }
-   else if (arch == "any")
-      return "*-*-*";
-   else if (isPattern)
-      return "*-linux-" + arch;
-   else
-      return "gnu-linux-" + arch;
+
+   std::replace(tuple.begin(), tuple.end(), std::string("any"), std::string("*"));
+   return APT::String::Join(tuple, "-");
 }
 PackageArchitectureMatchesSpecification::PackageArchitectureMatchesSpecification(std::string const &pattern, bool const pisPattern) :
 					literal(pattern), complete(CompleteArch(pattern, pisPattern)), isPattern(pisPattern) {
diff --git a/apt-pkg/init.cc b/apt-pkg/init.cc
index 292d75071..8b25ca100 100644
--- a/apt-pkg/init.cc
+++ b/apt-pkg/init.cc
@@ -20,6 +20,11 @@
 
 #include <string.h>
 #include <cstdlib>
+#include <fstream>
+#include <sstream>
+#include <string>
+#include <unordered_map>
+#include <vector>
 
 #include <apti18n.h>
 									/*}}}*/
@@ -30,6 +35,89 @@ const char *pkgVersion = PACKAGE_VERSION;
 const char *pkgLibVersion = Stringfy(APT_PKG_MAJOR) "."
                             Stringfy(APT_PKG_MINOR) "." 
                             Stringfy(APT_PKG_RELEASE);
+namespace APT {
+   APT_HIDDEN extern std::unordered_map<std::string, std::vector<std::string>> ArchToTupleMap;
+}
+
+// Splits by whitespace. There may be continous spans of whitespace - they
+// will be considered as one.
+static std::vector<std::string> split(std::string const & s)
+{
+   std::vector<std::string> vec;
+   std::istringstream iss(s);
+   iss.imbue(std::locale::classic());
+   for(std::string current_s; iss >> current_s; )
+      vec.push_back(current_s);
+   return vec;
+}
+
+
+// pkgInitArchTupleMap - Initialize the architecture tuple map				/*{{{*/
+// ---------------------------------------------------------------------
+/* This initializes */
+static bool pkgInitArchTupleMap()
+{
+   auto tuplepath = _config->FindFile("Dir::dpkg::tupletable", DPKG_DATADIR "/tupletable");
+   auto tripletpath = _config->FindFile("Dir::dpkg::triplettable", DPKG_DATADIR "/triplettable");
+   auto cpupath = _config->FindFile("Dir::dpkg::cputable", DPKG_DATADIR "/cputable");
+
+   // Load a list of CPUs
+   std::vector<std::string> cpus;
+   std::ifstream cputable(cpupath);
+   for (std::string cpuline; std::getline(cputable, cpuline); )
+   {
+      if (cpuline[0] == '#' || cpuline[0] == '\0')
+         continue;
+      auto cpurow = split(cpuline);
+      auto cpu = APT::String::Strip(cpurow.at(0));
+
+      cpus.push_back(cpu);
+   }
+   if (!cputable.eof())
+      return _error->Error("Error reading the CPU table");
+
+   // Load the architecture tuple
+   std::ifstream tupletable;
+   if (FileExists(tuplepath))
+      tupletable.open(tuplepath);
+   else if (FileExists(tripletpath))
+      tupletable.open(tripletpath);
+   else
+      return _error->Error("Cannot find dpkg tuplet or triplet table");
+
+   APT::ArchToTupleMap.clear();
+   for (std::string tupleline; std::getline(tupletable, tupleline); )
+   {
+      if (tupleline[0] == '#' || tupleline[0] == '\0')
+         continue;
+
+      std::vector<std::string> tuplerow = split(tupleline);
+
+      auto tuple = APT::String::Strip(tuplerow.at(0));
+      auto arch = APT::String::Strip(tuplerow.at(1));
+
+      if (tuple.find("<cpu>") == tuple.npos && arch.find("<cpu>") == arch.npos)
+      {
+         APT::ArchToTupleMap.insert({arch, VectorizeString(tuple, '-')});
+      }
+      else
+      {
+         for (auto && cpu : cpus)
+         {
+            auto mytuple = SubstVar(tuple, std::string("<cpu>"), cpu);
+            auto myarch = SubstVar(arch, std::string("<cpu>"), cpu);
+
+            APT::ArchToTupleMap.insert({myarch, VectorizeString(mytuple, '-')});
+         }
+      }
+   }
+   if (!tupletable.eof())
+      return _error->Error("Error reading the Tuple table");
+
+   return true;
+}
+									/*}}}*/
+
     
 // pkgInitConfig - Initialize the configuration class			/*{{{*/
 // ---------------------------------------------------------------------
@@ -193,6 +281,9 @@ bool pkgInitSystem(Configuration &Cnf,pkgSystem *&Sys)
       if (Sys == 0)
 	 return _error->Error(_("Unable to determine a suitable packaging system type"));
    }
+
+   if (pkgInitArchTupleMap() == false)
+      return false;
    
    return Sys->Initialize(Cnf);
 }