Merge remote-tracking branch 'donkult/feature/clientmergepdiffs' into debian/experimental-no-abi-break

3 files changed, 257 insertions, 12 deletions

diff --git a/apt-pkg/acquire-item.cc b/apt-pkg/acquire-item.cc
index b76921312..b5b9577ef 100644
--- a/apt-pkg/acquire-item.cc
+++ b/apt-pkg/acquire-item.cc
@@ -426,16 +426,18 @@ bool pkgAcqDiffIndex::ParseDiffIndex(string IndexDiffFile)		/*{{{*/
       SHA1.AddFD(fd);
       string const local_sha1 = SHA1.Result();
 
-      if(local_sha1 == ServerSha1) 
+      if(local_sha1 == ServerSha1)
       {
-	 // we have the same sha1 as the server
+	 // we have the same sha1 as the server so we are done here
 	 if(Debug)
 	    std::clog << "Package file is up-to-date" << std::endl;
-	 // set found to true, this will queue a pkgAcqIndexDiffs with
-	 // a empty availabe_patches
-	 found = true;
-      } 
-      else 
+	 // list cleanup needs to know that this file as well as the already
+	 // present index is ours, so we create an empty diff to save it for us
+	 new pkgAcqIndexDiffs(Owner, RealURI, Description, Desc.ShortDesc,
+	       ExpectedHash, ServerSha1, available_patches);
+	 return true;
+      }
+      else
       {
 	 if(Debug)
 	    std::clog << "SHA1-Current: " << ServerSha1 << " and we start at "<< fd.Name() << " " << fd.Size() << " " << local_sha1 << std::endl;
@@ -496,14 +498,42 @@ bool pkgAcqDiffIndex::ParseDiffIndex(string IndexDiffFile)		/*{{{*/
       }
 
       // we have something, queue the next diff
-      if(found) 
+      if(found)
       {
 	 // queue the diffs
 	 string::size_type const last_space = Description.rfind(" ");
 	 if(last_space != string::npos)
 	    Description.erase(last_space, Description.size()-last_space);
-	 new pkgAcqIndexDiffs(Owner, RealURI, Description, Desc.ShortDesc,
-			      ExpectedHash, ServerSha1, available_patches);
+
+	 /* decide if we should download patches one by one or in one go:
+	    The first is good if the server merges patches, but many don't so client
+	    based merging can be attempt in which case the second is better.
+	    "bad things" will happen if patches are merged on the server,
+	    but client side merging is attempt as well */
+	 bool pdiff_merge = _config->FindB("Acquire::PDiffs::Merge", true);
+	 if (pdiff_merge == true)
+	 {
+	    // this perl script is provided by apt-file
+	    pdiff_merge = FileExists(_config->FindFile("Dir::Bin::rred", "/usr/bin/diffindex-rred"));
+	    if (pdiff_merge == true)
+	    {
+	       // reprepro adds this flag if it has merged patches on the server
+	       std::string const precedence = Tags.FindS("X-Patch-Precedence");
+	       pdiff_merge = (precedence != "merged");
+	    }
+	 }
+
+	 if (pdiff_merge == false)
+	    new pkgAcqIndexDiffs(Owner, RealURI, Description, Desc.ShortDesc,
+		  ExpectedHash, ServerSha1, available_patches);
+	 else
+	 {
+	    std::vector<pkgAcqIndexMergeDiffs*> *diffs = new std::vector<pkgAcqIndexMergeDiffs*>(available_patches.size());
+	    for(size_t i = 0; i < available_patches.size(); ++i)
+	       (*diffs)[i] = new pkgAcqIndexMergeDiffs(Owner, RealURI, Description, Desc.ShortDesc, ExpectedHash,
+		     available_patches[i], diffs);
+	 }
+
 	 Complete = false;
 	 Status = StatDone;
 	 Dequeue();
@@ -752,6 +782,123 @@ void pkgAcqIndexDiffs::Done(string Message,unsigned long long Size,string Md5Has
    }
 }
 									/*}}}*/
+// AcqIndexMergeDiffs::AcqIndexMergeDiffs - Constructor			/*{{{*/
+pkgAcqIndexMergeDiffs::pkgAcqIndexMergeDiffs(pkgAcquire *Owner,
+				   string const &URI, string const &URIDesc,
+				   string const &ShortDesc, HashString const &ExpectedHash,
+				   DiffInfo const &patch,
+				   std::vector<pkgAcqIndexMergeDiffs*> const * const allPatches)
+   : Item(Owner), RealURI(URI), ExpectedHash(ExpectedHash),
+     patch(patch),allPatches(allPatches), State(StateFetchDiff)
+{
+
+   DestFile = _config->FindDir("Dir::State::lists") + "partial/";
+   DestFile += URItoFileName(URI);
+
+   Debug = _config->FindB("Debug::pkgAcquire::Diffs",false);
+
+   Description = URIDesc;
+   Desc.Owner = this;
+   Desc.ShortDesc = ShortDesc;
+
+   Desc.URI = string(RealURI) + ".diff/" + patch.file + ".gz";
+   Desc.Description = Description + " " + patch.file + string(".pdiff");
+   DestFile = _config->FindDir("Dir::State::lists") + "partial/";
+   DestFile += URItoFileName(RealURI + ".diff/" + patch.file);
+
+   if(Debug)
+      std::clog << "pkgAcqIndexMergeDiffs: " << Desc.URI << std::endl;
+
+   QueueURI(Desc);
+}
+									/*}}}*/
+void pkgAcqIndexMergeDiffs::Failed(string Message,pkgAcquire::MethodConfig *Cnf)/*{{{*/
+{
+   if(Debug)
+      std::clog << "pkgAcqIndexMergeDiffs failed: " << Desc.URI << " with " << Message << std::endl;
+   Complete = false;
+   Status = StatDone;
+   Dequeue();
+
+   // check if we are the first to fail, otherwise we are done here
+   State = StateDoneDiff;
+   for (std::vector<pkgAcqIndexMergeDiffs *>::const_iterator I = allPatches->begin();
+	 I != allPatches->end(); ++I)
+      if ((*I)->State == StateErrorDiff)
+	 return;
+
+   // first failure means we should fallback
+   State = StateErrorDiff;
+   std::clog << "Falling back to normal index file aquire" << std::endl;
+   new pkgAcqIndex(Owner, RealURI, Description,Desc.ShortDesc,
+		   ExpectedHash);
+}
+									/*}}}*/
+void pkgAcqIndexMergeDiffs::Done(string Message,unsigned long long Size,string Md5Hash,	/*{{{*/
+			    pkgAcquire::MethodConfig *Cnf)
+{
+   if(Debug)
+      std::clog << "pkgAcqIndexMergeDiffs::Done(): " << Desc.URI << std::endl;
+
+   Item::Done(Message,Size,Md5Hash,Cnf);
+
+   string const FinalFile = _config->FindDir("Dir::State::lists") + URItoFileName(RealURI);
+
+   if (State == StateFetchDiff)
+   {
+      // rred expects the patch as $FinalFile.ed.$patchname.gz
+      Rename(DestFile, FinalFile + ".ed." + patch.file + ".gz");
+
+      // check if this is the last completed diff
+      State = StateDoneDiff;
+      for (std::vector<pkgAcqIndexMergeDiffs *>::const_iterator I = allPatches->begin();
+	    I != allPatches->end(); ++I)
+	 if ((*I)->State != StateDoneDiff)
+	 {
+	    if(Debug)
+	       std::clog << "Not the last done diff in the batch: " << Desc.URI << std::endl;
+	    return;
+	 }
+
+      // this is the last completed diff, so we are ready to apply now
+      State = StateApplyDiff;
+
+      if(Debug)
+	 std::clog << "Sending to rred method: " << FinalFile << std::endl;
+
+      Local = true;
+      Desc.URI = "rred:" + FinalFile;
+      QueueURI(Desc);
+      Mode = "rred";
+      return;
+   }
+   // success in download/apply all diffs, clean up
+   else if (State == StateApplyDiff)
+   {
+      // see if we really got the expected file
+      if(!ExpectedHash.empty() && !ExpectedHash.VerifyFile(DestFile))
+      {
+	 RenameOnError(HashSumMismatch);
+	 return;
+      }
+
+      // move the result into place
+      if(Debug)
+	 std::clog << "Moving patched file in place: " << std::endl
+		   << DestFile << " -> " << FinalFile << std::endl;
+      Rename(DestFile, FinalFile);
+      chmod(FinalFile.c_str(), 0644);
+
+      // otherwise lists cleanup will eat the file
+      DestFile = FinalFile;
+
+      // all set and done
+      Complete = true;
+      if(Debug)
+	 std::clog << "allDone: " << DestFile << "\n" << std::endl;
+   }
+}
+									/*}}}*/
 // AcqIndex::AcqIndex - Constructor					/*{{{*/
 // ---------------------------------------------------------------------
 /* The package file is added to the queue and a second class is 
diff --git a/apt-pkg/acquire-item.h b/apt-pkg/acquire-item.h
index 6b4f73708..5a1c7979c 100644
--- a/apt-pkg/acquire-item.h
+++ b/apt-pkg/acquire-item.h
@@ -429,7 +429,105 @@ class pkgAcqDiffIndex : public pkgAcquire::Item
 		   std::string ShortDesc, HashString ExpectedHash);
 };
 									/*}}}*/
-/** \brief An item that is responsible for fetching all the patches	{{{
+/** \brief An item that is responsible for fetching client-merge patches {{{
+ *  that need to be applied to a given package index file.
+ *
+ *  Instead of downloading and applying each patch one by one like its
+ *  sister #pkgAcqIndexDiffs this class will download all patches at once
+ *  and call rred with all the patches downloaded once. Rred will then
+ *  merge and apply them in one go, which should be a lot faster – but is
+ *  incompatible with server-based merges of patches like reprepro can do.
+ *
+ *  \sa pkgAcqDiffIndex, pkgAcqIndex
+ */
+class pkgAcqIndexMergeDiffs : public pkgAcquire::Item
+{
+   protected:
+
+   /** \brief If \b true, debugging output will be written to
+    *  std::clog.
+    */
+   bool Debug;
+
+   /** \brief description of the item that is currently being
+    *  downloaded.
+    */
+   pkgAcquire::ItemDesc Desc;
+
+   /** \brief URI of the package index file that is being
+    *  reconstructed.
+    */
+   std::string RealURI;
+
+   /** \brief HashSum of the package index file that is being
+    *  reconstructed.
+    */
+   HashString ExpectedHash;
+
+   /** \brief description of the file being downloaded. */
+   std::string Description;
+
+   /** \brief information about the current patch */
+   struct DiffInfo const patch;
+
+   /** \brief list of all download items for the patches */
+   std::vector<pkgAcqIndexMergeDiffs*> const * const allPatches;
+
+   /** The current status of this patch. */
+   enum DiffState
+   {
+      /** \brief The diff is currently being fetched. */
+      StateFetchDiff,
+
+      /** \brief The diff is currently being applied. */
+      StateApplyDiff,
+
+      /** \brief the work with this diff is done */
+      StateDoneDiff,
+
+      /** \brief something bad happened and fallback was triggered */
+      StateErrorDiff
+   } State;
+
+   public:
+   /** \brief Called when the patch file failed to be downloaded.
+    *
+    *  This method will fall back to downloading the whole index file
+    *  outright; its arguments are ignored.
+    */
+   virtual void Failed(std::string Message,pkgAcquire::MethodConfig *Cnf);
+
+   virtual void Done(std::string Message,unsigned long long Size,std::string Md5Hash,
+		     pkgAcquire::MethodConfig *Cnf);
+   virtual std::string DescURI() {return RealURI + "Index";};
+
+   /** \brief Create an index merge-diff item.
+    *
+    *  \param Owner The pkgAcquire object that owns this item.
+    *
+    *  \param URI The URI of the package index file being
+    *  reconstructed.
+    *
+    *  \param URIDesc A long description of this item.
+    *
+    *  \param ShortDesc A brief description of this item.
+    *
+    *  \param ExpectedHash The expected md5sum of the completely
+    *  reconstructed package index file; the index file will be tested
+    *  against this value when it is entirely reconstructed.
+    *
+    *  \param patch contains infos about the patch this item is supposed
+    *  to download which were read from the index
+    *
+    *  \param allPatches contains all related items so that each item can
+    *  check if it was the last one to complete the download step
+    */
+   pkgAcqIndexMergeDiffs(pkgAcquire *Owner,std::string const &URI,std::string const &URIDesc,
+		    std::string const &ShortDesc, HashString const &ExpectedHash,
+		    DiffInfo const &patch, std::vector<pkgAcqIndexMergeDiffs*> const * const allPatches);
+};
+									/*}}}*/
+/** \brief An item that is responsible for fetching server-merge patches {{{
  *  that need to be applied to a given package index file.
  *
  *  After downloading and applying a single patch, this item will
diff --git a/apt-pkg/contrib/fileutl.cc b/apt-pkg/contrib/fileutl.cc
index efbf7aaf4..ffb8b4b53 100644
--- a/apt-pkg/contrib/fileutl.cc
+++ b/apt-pkg/contrib/fileutl.cc
@@ -465,7 +465,7 @@ std::vector<string> GetListOfFilesInDir(string const &Dir, std::vector<string> c
       const char *C = Ent->d_name;
       for (; *C != 0; ++C)
 	 if (isalpha(*C) == 0 && isdigit(*C) == 0
-	     && *C != '_' && *C != '-') {
+	     && *C != '_' && *C != '-' && *C != ':') {
 	    // no required extension -> dot is a bad character
 	    if (*C == '.' && Ext.empty() == false)
 	       continue;