Merge remote-tracking branch 'upstream/master' into derivation-header-include-order

src/libstore/derivations.hh

@@ -6,6 +6,7 @@
 #include "content-address.hh"
 
 #include <map>
+#include <variant>
 
 
 namespace nix {
@@ -13,30 +14,87 @@ namespace nix {
 
 /* Abstract syntax of derivations. */
 
+/* The traditional non-fixed-output derivation type. */
 struct DerivationOutputInputAddressed
 {
+    /* Will need to become `std::optional<StorePath>` once input-addressed
+       derivations are allowed to depend on cont-addressed derivations */
     StorePath path;
 };
 
-struct DerivationOutputFixed
+/* Fixed-output derivations, whose output paths are content addressed
+   according to that fixed output. */
+struct DerivationOutputCAFixed
 {
     FixedOutputHash hash; /* hash used for expected hash computation */
 };
 
+/* Floating-output derivations, whose output paths are content addressed, but
+   not fixed, and so are dynamically calculated from whatever the output ends
+   up being. */
+struct DerivationOutputCAFloating
+{
+    /* information used for expected hash computation */
+    FileIngestionMethod method;
+    HashType hashType;
+};
+
 struct DerivationOutput
 {
-    std::variant<DerivationOutputInputAddressed, DerivationOutputFixed> output;
-    StorePath path(const Store & store, std::string_view drvName) const;
+    std::variant<
+        DerivationOutputInputAddressed,
+        DerivationOutputCAFixed,
+        DerivationOutputCAFloating
+    > output;
+    std::optional<HashType> hashAlgoOpt(const Store & store) const;
+    /* Note, when you use this function you should make sure that you're passing
+       the right derivation name. When in doubt, you should use the safer
+       interface provided by BasicDerivation::outputsAndPaths */
+    std::optional<StorePath> pathOpt(const Store & store, std::string_view drvName) const;
+    /* DEPRECATED: Remove after CA drvs are fully implemented */
+    StorePath path(const Store & store, std::string_view drvName) const {
+        auto p = pathOpt(store, drvName);
+        if (!p) throw UnimplementedError("floating content-addressed derivations are not yet implemented");
+        return *p;
+    }
 };
 
 typedef std::map<string, DerivationOutput> DerivationOutputs;
 
+/* These are analogues to the previous DerivationOutputs data type, but they
+   also contains, for each output, the (optional) store path in which it would
+   be written. To calculate values of these types, see the corresponding
+   functions in BasicDerivation */
+typedef std::map<string, std::pair<DerivationOutput, StorePath>>
+  DerivationOutputsAndPaths;
+typedef std::map<string, std::pair<DerivationOutput, std::optional<StorePath>>>
+  DerivationOutputsAndOptPaths;
+
 /* For inputs that are sub-derivations, we specify exactly which
    output IDs we are interested in. */
 typedef std::map<StorePath, StringSet> DerivationInputs;
 
 typedef std::map<string, string> StringPairs;
 
+enum struct DerivationType : uint8_t {
+    InputAddressed,
+    CAFixed,
+    CAFloating,
+};
+
+/* Do the outputs of the derivation have paths calculated from their content,
+   or from the derivation itself? */
+bool derivationIsCA(DerivationType);
+
+/* Is the content of the outputs fixed a-priori via a hash? Never true for
+   non-CA derivations. */
+bool derivationIsFixed(DerivationType);
+
+/* Is the derivation impure and needs to access non-deterministic resources, or
+   pure and can be sandboxed? Note that whether or not we actually sandbox the
+   derivation is controlled separately. Never true for non-CA derivations. */
+bool derivationIsImpure(DerivationType);
+
 struct BasicDerivation
 {
     DerivationOutputs outputs; /* keyed on symbolic IDs */
@@ -53,7 +111,7 @@ struct BasicDerivation
     bool isBuiltin() const;
 
     /* Return true iff this is a fixed-output derivation. */
-    bool isFixedOutput() const;
+    DerivationType type() const;
 
     /* Return the output paths of a derivation. */
     StorePathSet outputPaths(const Store & store) const;
@@ -61,6 +119,13 @@ struct BasicDerivation
     /* Return the output names of a derivation. */
     StringSet outputNames() const;
 
+    /* Calculates the maps that contains all the DerivationOutputs, but
+       augmented with knowledge of the Store paths they would be written into.
+       The first one of these functions will be removed when the CA work is
+       completed */
+    DerivationOutputsAndPaths outputsAndPaths(const Store & store) const;
+    DerivationOutputsAndOptPaths outputsAndOptPaths(const Store & store) const;
+
     static std::string_view nameFromPath(const StorePath & storePath);
 };
 
@@ -82,7 +147,7 @@ enum RepairFlag : bool { NoRepair = false, Repair = true };
 
 /* Write a derivation to the Nix store, and return its path. */
 StorePath writeDerivation(ref<Store> store,
-    const Derivation & drv, std::string_view name, RepairFlag repair = NoRepair);
+    const Derivation & drv, RepairFlag repair = NoRepair);
 
 /* Read a derivation from a file. */
 Derivation parseDerivation(const Store & store, std::string && s, std::string_view name);
@@ -90,10 +155,42 @@ Derivation parseDerivation(const Store & store, std::string && s, std::string_vi
 // FIXME: remove
 bool isDerivation(const string & fileName);
 
-Hash hashDerivationModulo(Store & store, const Derivation & drv, bool maskOutputs);
+// known CA drv's output hashes, current just for fixed-output derivations
+// whose output hashes are always known since they are fixed up-front.
+typedef std::map<std::string, Hash> CaOutputHashes;
+
+typedef std::variant<
+    Hash, // regular DRV normalized hash
+    CaOutputHashes
+> DrvHashModulo;
+
+/* Returns hashes with the details of fixed-output subderivations
+   expunged.
+
+   A fixed-output derivation is a derivation whose outputs have a
+   specified content hash and hash algorithm. (Currently they must have
+   exactly one output (`out'), which is specified using the `outputHash'
+   and `outputHashAlgo' attributes, but the algorithm doesn't assume
+   this.) We don't want changes to such derivations to propagate upwards
+   through the dependency graph, changing output paths everywhere.
+
+   For instance, if we change the url in a call to the `fetchurl'
+   function, we do not want to rebuild everything depending on it---after
+   all, (the hash of) the file being downloaded is unchanged.  So the
+   *output paths* should not change. On the other hand, the *derivation
+   paths* should change to reflect the new dependency graph.
+
+   For fixed-output derivations, this returns a map from the name of
+   each output to its hash, unique up to the output's contents.
+
+   For regular derivations, it returns a single hash of the derivation
+   ATerm, after subderivations have been likewise expunged from that
+   derivation.
+ */
+DrvHashModulo hashDerivationModulo(Store & store, const Derivation & drv, bool maskOutputs);
 
 /* Memoisation of hashDerivationModulo(). */
-typedef std::map<StorePath, Hash> DrvHashes;
+typedef std::map<StorePath, DrvHashModulo> DrvHashes;
 
 extern DrvHashes drvHashes; // FIXME: global, not thread-safe