* Unify the treatment of sources copied to the store, and recursive

  SHA-256 outputs of fixed-output derivations.  I.e. they now produce
  the same store path:

  $ nix-store --add x
  /nix/store/j2fq9qxvvxgqymvpszhs773ncci45xsj-x

  $ nix-store --add-fixed --recursive sha256 x
  /nix/store/j2fq9qxvvxgqymvpszhs773ncci45xsj-x

  the latter being the same as the path that a derivation

    derivation {
      name = "x";
      outputHashAlgo = "sha256";
      outputHashMode = "recursive";
      outputHash = "...";
      ...
    };

  produces.

  This does change the output path for such fixed-output derivations.
  Fortunately they are quite rare.  The most common use is fetchsvn
  calls with SHA-256 hashes.  (There are a handful of those is
  Nixpkgs, mostly unstable development packages.)
  
* Documented the computation of store paths (in store-api.cc).

1 files changed, 84 insertions, 27 deletions

diff --git a/src/libstore/store-api.cc b/src/libstore/store-api.cc
index ced5fd0072e8..fe4ecfad5443 100644
--- a/src/libstore/store-api.cc
+++ b/src/libstore/store-api.cc
@@ -99,55 +99,112 @@ void checkStoreName(const string & name)
 }
 
 
+/* Store paths have the following form:
+
+   <store>/<h>-<name>
+
+   where
+
+   <store> = the location of the Nix store, usually /nix/store
+   
+   <name> = a human readable name for the path, typically obtained
+     from the name attribute of the derivation, or the name of the
+     source file from which the store path is created
+     
+   <h> = base-32 representation of the first 160 bits of a SHA-256
+     hash of <s>; the hash part of the store name
+     
+   <s> = the string "<type>:sha256:<h2>:<store>:<name>";
+     note that it includes the location of the store as well as the
+     name to make sure that changes to either of those are reflected
+     in the hash (e.g. you won't get /nix/store/<h>-name1 and
+     /nix/store/<h>-name2 with equal hash parts).
+     
+   <type> = one of:
+     "text:<r1>:<r2>:...<rN>"
+       for plain text files written to the store using
+       addTextToStore(); <r1> ... <rN> are the references of the
+       path.
+     "source"
+       for paths copied to the store using addToStore() when recursive
+       = true and hashAlgo = "sha256"
+     "output:out"
+       for either the outputs created by derivations, OR paths copied
+       to the store using addToStore() with recursive != true or
+       hashAlgo != "sha256" (in that case "source" is used; it's
+       silly, but it's done that way for compatibility).
+
+   <h2> = base-16 representation of a SHA-256 hash of:
+     if <type> = "text:...":
+       the string written to the resulting store path
+     if <type> = "source":
+       the serialisation of the path from which this store path is
+       copied, as returned by hashPath()
+     if <type> = "output:out":
+       for non-fixed derivation outputs:
+         the derivation (see hashDerivationModulo() in
+         primops.cc)
+       for paths copied by addToStore() or produced by fixed-output
+       derivations:
+         the string "fixed:out:<rec><algo>:<hash>:", where
+           <rec> = "r:" for recursive (path) hashes, or "" or flat
+             (file) hashes
+           <algo> = "md5", "sha1" or "sha256"
+           <hash> = base-16 representation of the path or flat hash of
+             the contents of the path (or expected contents of the
+             path for fixed-output derivations)
+
+   It would have been nicer to handle fixed-output derivations under
+   "source", e.g. have something like "source:<rec><algo>", but we're
+   stuck with this for now...
+
+   The main reason for this way of computing names is to prevent name
+   collisions (for security).  For instance, it shouldn't be feasible
+   to come up with a derivation whose output path collides with the
+   path for a copied source.  The former would have a <s> starting with
+   "output:out:", while the latter would have a <2> starting with
+   "source:".
+*/
+
+
 Path makeStorePath(const string & type,
-    const Hash & hash, const string & suffix)
+    const Hash & hash, const string & name)
 {
     /* e.g., "source:sha256:1abc...:/nix/store:foo.tar.gz" */
     string s = type + ":sha256:" + printHash(hash) + ":"
-        + nixStore + ":" + suffix;
+        + nixStore + ":" + name;
 
-    checkStoreName(suffix);
+    checkStoreName(name);
 
     return nixStore + "/"
         + printHash32(compressHash(hashString(htSHA256, s), 20))
-        + "-" + suffix;
+        + "-" + name;
 }
 
 
 Path makeFixedOutputPath(bool recursive,
     string hashAlgo, Hash hash, string name)
 {
-    /* !!! copy/paste from primops.cc */
-    Hash h = hashString(htSHA256, "fixed:out:"
-        + (recursive ? (string) "r:" : "") + hashAlgo + ":"
-        + printHash(hash) + ":"
-        + "");
-    return makeStorePath("output:out", h, name);
+    return hashAlgo == "sha256" && recursive
+        ? makeStorePath("source", hash, name)
+        : makeStorePath("output:out", hashString(htSHA256,
+                "fixed:out:" + (recursive ? (string) "r:" : "") + hashAlgo + ":" + printHash(hash) + ":"),
+            name);
 }
 
 
 std::pair<Path, Hash> computeStorePathForPath(const Path & srcPath,
-    bool fixed, bool recursive, string hashAlgo, PathFilter & filter)
+    bool recursive, string hashAlgo, PathFilter & filter)
 {
-    Hash h = hashPath(htSHA256, srcPath, filter);
-
-    string baseName = baseNameOf(srcPath);
-
-    Path dstPath;
-    
-    if (fixed) {
-        HashType ht(parseHashType(hashAlgo));
-        Hash h2 = recursive ? hashPath(ht, srcPath, filter) : hashFile(ht, srcPath);
-        dstPath = makeFixedOutputPath(recursive, hashAlgo, h2, baseName);
-    }
-        
-    else dstPath = makeStorePath("source", h, baseName);
-
+    HashType ht(parseHashType(hashAlgo));
+    Hash h = recursive ? hashPath(ht, srcPath, filter) : hashFile(ht, srcPath);
+    string name = baseNameOf(srcPath);
+    Path dstPath = makeFixedOutputPath(recursive, hashAlgo, h, name);
     return std::pair<Path, Hash>(dstPath, h);
 }
 
 
-Path computeStorePathForText(const string & suffix, const string & s,
+Path computeStorePathForText(const string & name, const string & s,
     const PathSet & references)
 {
     Hash hash = hashString(htSHA256, s);
@@ -159,7 +216,7 @@ Path computeStorePathForText(const string & suffix, const string & s,
         type += ":";
         type += *i;
     }
-    return makeStorePath(type, hash, suffix);
+    return makeStorePath(type, hash, name);
 }