Revert "libfetchers: make attribute / URL query handling consistent"

This reverts commit 35eec921af1043fc6322edc0ad88c872d41623b8.

Reason for revert: Regressed nix-eval-jobs, and it appears to be this change is buggy/missing a case. It just needs another pass.

Code causing the problem in n-e-j, when invoked with `nix-eval-jobs --flake '.#hydraJobs'`:

```
n-e-j/tests/assets » ../../build/src/nix-eval-jobs --meta --workers 1 --flake .#hydraJobs
warning: unknown setting 'trusted-users'
warning: `--gc-roots-dir' not specified
error: unsupported Git input attribute 'dir'
error: worker error: error: unsupported Git input attribute 'dir'
```

```
  nix::Value *vRoot = [&]() {
        if (args.flake) {
            auto [flakeRef, fragment, outputSpec] =
                nix::parseFlakeRefWithFragmentAndExtendedOutputsSpec(
                    args.releaseExpr, nix::absPath("."));
            nix::InstallableFlake flake{
                {}, state, std::move(flakeRef), fragment, outputSpec,
                {}, {},    args.lockFlags};

            return flake.toValue(*state).first;
        } else {
            return releaseExprTopLevelValue(*state, autoArgs, args);
        }
    }();
```

Inspecting the program behaviour reveals that `dir` was in fact set in the URL going into the fetcher. This is in turn because unlike in the case changed in this commit, it was not erased before handing it to libfetchers, which is probably just a mistake.

```
(rr) up
3  0x00007ffff60262ae in nix::fetchers::Input::fromURL (url=..., requireTree=requireTree@entry=true) at src/libfetchers/fetchers.cc:39
warning: Source file is more recent than executable.
39              auto res = inputScheme->inputFromURL(url, requireTree);
(rr) p url
$1 = (const nix::ParsedURL &) @0x7fffdc874190: {url = "git+file:///home/jade/lix/nix-eval-jobs", 
  base = "git+file:///home/jade/lix/nix-eval-jobs", scheme = "git+file", authority = std::optional<std::string> = {[contained value] = ""}, 
  path = "/home/jade/lix/nix-eval-jobs", query = std::map with 1 element = {["dir"] = "tests/assets"}, fragment = ""}
(rr) up
4  0x00007ffff789d904 in nix::parseFlakeRefWithFragment (url=".#hydraJobs", baseDir=std::optional<std::string> = {...}, 
    allowMissing=allowMissing@entry=false, isFlake=isFlake@entry=true) at src/libexpr/flake/flakeref.cc:179
warning: Source file is more recent than executable.
179                                 FlakeRef(Input::fromURL(parsedURL, isFlake), getOr(parsedURL.query, "dir", "")),
(rr) p parsedURL
$2 = {url = "git+file:///home/jade/lix/nix-eval-jobs", base = "git+file:///home/jade/lix/nix-eval-jobs", scheme = "git+file", 
  authority = std::optional<std::string> = {[contained value] = ""}, path = "/home/jade/lix/nix-eval-jobs", query = std::map with 1 element = {
    ["dir"] = "tests/assets"}, fragment = ""}
(rr) list
174
175                             if (pathExists(flakeRoot + "/.git/shallow"))
176                                 parsedURL.query.insert_or_assign("shallow", "1");
177
178                             return std::make_pair(
179                                 FlakeRef(Input::fromURL(parsedURL, isFlake), getOr(parsedURL.query, "dir", "")),
180                                 fragment);
181                         }
```

Change-Id: Ib55a882eaeb3e59228857761dc1e3b2e366b0f5e

6 files changed, 94 insertions, 135 deletions

diff --git a/src/libfetchers/fetchers.hh b/src/libfetchers/fetchers.hh
index 40f2b6294..2bb4248be 100644
--- a/src/libfetchers/fetchers.hh
+++ b/src/libfetchers/fetchers.hh
@@ -159,37 +159,6 @@ struct InputScheme
         std::optional<std::string> commitMsg) const;
 
     virtual std::pair<StorePath, Input> fetch(ref<Store> store, const Input & input) = 0;
-
-protected:
-    void emplaceURLQueryIntoAttrs(
-        const ParsedURL & parsedURL,
-        Attrs & attrs,
-        const StringSet & numericParams,
-        const StringSet & booleanParams) const
-    {
-        for (auto &[name, value] : parsedURL.query) {
-            if (name == "url") {
-                throw BadURL(
-                    "URL '%s' must not override url via query param!",
-                    parsedURL.to_string()
-                );
-            } else if (numericParams.count(name) != 0) {
-                if (auto n = string2Int<uint64_t>(value)) {
-                    attrs.insert_or_assign(name, *n);
-                } else {
-                    throw BadURL(
-                        "URL '%s' has non-numeric parameter '%s'",
-                        parsedURL.to_string(),
-                        name
-                    );
-                }
-            } else if (booleanParams.count(name) != 0) {
-                attrs.emplace(name, Explicit<bool> { value == "1" });
-            } else {
-                attrs.emplace(name, value);
-            }
-        }
-    }
 };
 
 void registerInputScheme(std::shared_ptr<InputScheme> && fetcher);
diff --git a/src/libfetchers/git.cc b/src/libfetchers/git.cc
index 0cb826075..2817fde23 100644
--- a/src/libfetchers/git.cc
+++ b/src/libfetchers/git.cc
@@ -273,14 +273,17 @@ struct GitInputScheme : InputScheme
 
         Attrs attrs;
         attrs.emplace("type", "git");
-        attrs.emplace("url", url2.to_string());
 
-        emplaceURLQueryIntoAttrs(
-            url,
-            attrs,
-            {"lastModified", "revCount"},
-            {"shallow", "submodules", "allRefs"}
-        );
+        for (auto & [name, value] : url.query) {
+            if (name == "rev" || name == "ref")
+                attrs.emplace(name, value);
+            else if (name == "shallow" || name == "submodules" || name == "allRefs")
+                attrs.emplace(name, Explicit<bool> { value == "1" });
+            else
+                url2.query.emplace(name, value);
+        }
+
+        attrs.emplace("url", url2.to_string());
 
         return inputFromAttrs(attrs);
     }
diff --git a/src/libfetchers/github.cc b/src/libfetchers/github.cc
index b971781ae..60fefd1f3 100644
--- a/src/libfetchers/github.cc
+++ b/src/libfetchers/github.cc
@@ -1,4 +1,3 @@
-#include "attrs.hh"
 #include "filetransfer.hh"
 #include "cache.hh"
 #include "globals.hh"
@@ -37,11 +36,18 @@ struct GitArchiveInputScheme : InputScheme
 
         auto path = tokenizeString<std::vector<std::string>>(url.path, "/");
 
-        std::optional<std::string> refOrRev;
+        std::optional<Hash> rev;
+        std::optional<std::string> ref;
+        std::optional<std::string> host_url;
 
         auto size = path.size();
         if (size == 3) {
-            refOrRev = path[2];
+            if (std::regex_match(path[2], revRegex))
+                rev = Hash::parseAny(path[2], htSHA1);
+            else if (std::regex_match(path[2], refRegex))
+                ref = path[2];
+            else
+                throw BadURL("in URL '%s', '%s' is not a commit hash or branch/tag name", url.url, path[2]);
         } else if (size > 3) {
             std::string rs;
             for (auto i = std::next(path.begin(), 2); i != path.end(); i++) {
@@ -52,91 +58,61 @@ struct GitArchiveInputScheme : InputScheme
             }
 
             if (std::regex_match(rs, refRegex)) {
-                refOrRev = rs;
+                ref = rs;
             } else {
                 throw BadURL("in URL '%s', '%s' is not a branch/tag name", url.url, rs);
             }
         } else if (size < 2)
             throw BadURL("URL '%s' is invalid", url.url);
 
-        Attrs attrs;
-        attrs.emplace("type", type());
-        attrs.emplace("owner", path[0]);
-        attrs.emplace("repo", path[1]);
-
         for (auto &[name, value] : url.query) {
-            if (name == "rev" || name == "ref") {
-                if (refOrRev) {
-                    throw BadURL("URL '%s' already contains a ref or rev", url.url);
-                } else {
-                    refOrRev = value;
-                }
-            } else if (name == "lastModified") {
-                if (auto n = string2Int<uint64_t>(value)) {
-                    attrs.emplace(name, *n);
-                } else {
-                    throw Error(
-                        "Attribute 'lastModified' in URL '%s' must be an integer",
-                        url.to_string()
-                    );
-                }
-            } else {
-                attrs.emplace(name, value);
+            if (name == "rev") {
+                if (rev)
+                    throw BadURL("URL '%s' contains multiple commit hashes", url.url);
+                rev = Hash::parseAny(value, htSHA1);
             }
+            else if (name == "ref") {
+                if (!std::regex_match(value, refRegex))
+                    throw BadURL("URL '%s' contains an invalid branch/tag name", url.url);
+                if (ref)
+                    throw BadURL("URL '%s' contains multiple branch/tag names", url.url);
+                ref = value;
+            }
+            else if (name == "host") {
+                if (!std::regex_match(value, hostRegex))
+                    throw BadURL("URL '%s' contains an invalid instance host", url.url);
+                host_url = value;
+            }
+            // FIXME: barf on unsupported attributes
         }
 
-        if (refOrRev) attrs.emplace("refOrRev", *refOrRev);
+        if (ref && rev)
+            throw BadURL("URL '%s' contains both a commit hash and a branch/tag name %s %s", url.url, *ref, rev->gitRev());
 
-        return inputFromAttrs(attrs);
+        Input input;
+        input.attrs.insert_or_assign("type", type());
+        input.attrs.insert_or_assign("owner", path[0]);
+        input.attrs.insert_or_assign("repo", path[1]);
+        if (rev) input.attrs.insert_or_assign("rev", rev->gitRev());
+        if (ref) input.attrs.insert_or_assign("ref", *ref);
+        if (host_url) input.attrs.insert_or_assign("host", *host_url);
+
+        return input;
     }
 
     std::optional<Input> inputFromAttrs(const Attrs & attrs) const override
     {
-        // Attributes can contain refOrRev and it needs to be figured out
-        // which one it is (see inputFromURL for when that may happen).
-        // The correct one (ref or rev) will be written into finalAttrs and
-        // it needs to be mutable for that.
-        Attrs finalAttrs(attrs);
-        auto type_ = maybeGetStrAttr(finalAttrs, "type");
-        if (type_ != type()) return {};
-
-        auto owner = getStrAttr(finalAttrs, "owner");
-        auto repo = getStrAttr(finalAttrs, "repo");
-
-        auto url = fmt("%s:%s/%s", *type_, owner, repo);
-        if (auto host = maybeGetStrAttr(finalAttrs, "host")) {
-            if (!std::regex_match(*host, hostRegex)) {
-                throw BadURL("URL '%s' contains an invalid instance host", url);
-            }
-        }
-
-        if (auto refOrRev = maybeGetStrAttr(finalAttrs, "refOrRev")) {
-            finalAttrs.erase("refOrRev");
-            if (std::regex_match(*refOrRev, revRegex)) {
-                finalAttrs.emplace("rev", *refOrRev);
-            } else if (std::regex_match(*refOrRev, refRegex)) {
-                finalAttrs.emplace("ref", *refOrRev);
-            } else {
-                throw Error(
-                    "in URL '%s', '%s' is not a commit hash or a branch/tag name",
-                    url,
-                    *refOrRev
-                );
-            }
-        } else if (auto ref = maybeGetStrAttr(finalAttrs, "ref")) {
-            if (!std::regex_match(*ref, refRegex)) {
-                throw BadURL("URL '%s' contains an invalid branch/tag name", url);
-            }
-        }
+        if (maybeGetStrAttr(attrs, "type") != type()) return {};
 
-        for (auto & [name, value] : finalAttrs) {
-            if (name != "type" && name != "owner" && name != "repo" && name != "ref" && name != "rev" && name != "narHash" && name != "lastModified" && name != "host") {
+        for (auto & [name, value] : attrs)
+            if (name != "type" && name != "owner" && name != "repo" && name != "ref" && name != "rev" && name != "narHash" && name != "lastModified" && name != "host")
                 throw Error("unsupported input attribute '%s'", name);
-            }
-        }
+
+        getStrAttr(attrs, "owner");
+        getStrAttr(attrs, "repo");
 
         Input input;
-        input.attrs = finalAttrs;
+        input.attrs = attrs;
         return input;
     }
 
diff --git a/src/libfetchers/indirect.cc b/src/libfetchers/indirect.cc
index 8c0176e84..c73505b31 100644
--- a/src/libfetchers/indirect.cc
+++ b/src/libfetchers/indirect.cc
@@ -17,8 +17,6 @@ struct IndirectInputScheme : InputScheme
         std::optional<Hash> rev;
         std::optional<std::string> ref;
 
-        Attrs attrs;
-
         if (path.size() == 1) {
         } else if (path.size() == 2) {
             if (std::regex_match(path[1], revRegex))
@@ -28,21 +26,29 @@ struct IndirectInputScheme : InputScheme
             else
                 throw BadURL("in flake URL '%s', '%s' is not a commit hash or branch/tag name", url.url, path[1]);
         } else if (path.size() == 3) {
+            if (!std::regex_match(path[1], refRegex))
+                throw BadURL("in flake URL '%s', '%s' is not a branch/tag name", url.url, path[1]);
             ref = path[1];
+            if (!std::regex_match(path[2], revRegex))
+                throw BadURL("in flake URL '%s', '%s' is not a commit hash", url.url, path[2]);
             rev = Hash::parseAny(path[2], htSHA1);
         } else
             throw BadURL("GitHub URL '%s' is invalid", url.url);
 
         std::string id = path[0];
+        if (!std::regex_match(id, flakeRegex))
+            throw BadURL("'%s' is not a valid flake ID", id);
 
-        attrs.emplace("type", "indirect");
-        attrs.emplace("id", id);
-        if (rev) attrs.emplace("rev", rev->gitRev());
-        if (ref) attrs.emplace("ref", *ref);
+        // FIXME: forbid query params?
 
-        emplaceURLQueryIntoAttrs(url, attrs, {}, {});
+        Input input;
+        input.direct = false;
+        input.attrs.insert_or_assign("type", "indirect");
+        input.attrs.insert_or_assign("id", id);
+        if (rev) input.attrs.insert_or_assign("rev", rev->gitRev());
+        if (ref) input.attrs.insert_or_assign("ref", *ref);
 
-        return inputFromAttrs(attrs);
+        return input;
     }
 
     std::optional<Input> inputFromAttrs(const Attrs & attrs) const override
@@ -57,18 +63,6 @@ struct IndirectInputScheme : InputScheme
         if (!std::regex_match(id, flakeRegex))
             throw BadURL("'%s' is not a valid flake ID", id);
 
-        // TODO come up with a nicer error message for those two.
-        if (auto rev = maybeGetStrAttr(attrs, "rev")) {
-            if (!std::regex_match(*rev, revRegex)) {
-                throw BadURL("in flake '%s', '%s' is not a commit hash", id, *rev);
-            }
-        }
-        if (auto ref = maybeGetStrAttr(attrs, "ref")) {
-            if (!std::regex_match(*ref, refRegex)) {
-                throw BadURL("in flake '%s', '%s' is not a valid branch/tag name", id, *ref);
-            }
-        }
-
         Input input;
         input.direct = false;
         input.attrs = attrs;
diff --git a/src/libfetchers/mercurial.cc b/src/libfetchers/mercurial.cc
index 6015f8ec7..4fffa71d3 100644
--- a/src/libfetchers/mercurial.cc
+++ b/src/libfetchers/mercurial.cc
@@ -57,7 +57,12 @@ struct MercurialInputScheme : InputScheme
         Attrs attrs;
         attrs.emplace("type", "hg");
 
-        emplaceURLQueryIntoAttrs(url, attrs, {"revCount"}, {});
+        for (auto &[name, value] : url.query) {
+            if (name == "rev" || name == "ref")
+                attrs.emplace(name, value);
+            else
+                url2.query.emplace(name, value);
+        }
 
         attrs.emplace("url", url2.to_string());
 
diff --git a/src/libfetchers/tarball.cc b/src/libfetchers/tarball.cc
index 8dfdecda8..c903895e2 100644
--- a/src/libfetchers/tarball.cc
+++ b/src/libfetchers/tarball.cc
@@ -201,17 +201,29 @@ struct CurlInputScheme : InputScheme
         if (!isValidURL(_url, requireTree))
             return std::nullopt;
 
-        auto url = _url;
+        Input input;
 
-        Attrs attrs;
-        attrs.emplace("type", inputType());
+        auto url = _url;
 
         url.scheme = parseUrlScheme(url.scheme).transport;
 
-        emplaceURLQueryIntoAttrs(url, attrs, {"revCount"}, {});
+        auto narHash = url.query.find("narHash");
+        if (narHash != url.query.end())
+            input.attrs.insert_or_assign("narHash", narHash->second);
+
+        if (auto i = get(url.query, "rev"))
+            input.attrs.insert_or_assign("rev", *i);
 
-        attrs.emplace("url", url.to_string());
-        return inputFromAttrs(attrs);
+        if (auto i = get(url.query, "revCount"))
+            if (auto n = string2Int<uint64_t>(*i))
+                input.attrs.insert_or_assign("revCount", *n);
+
+        url.query.erase("rev");
+        url.query.erase("revCount");
+
+        input.attrs.insert_or_assign("type", inputType());
+        input.attrs.insert_or_assign("url", url.to_string());
+        return input;
     }
 
     std::optional<Input> inputFromAttrs(const Attrs & attrs) const override
@@ -223,7 +235,7 @@ struct CurlInputScheme : InputScheme
         std::set<std::string> allowedNames = {"type", "url", "narHash", "name", "unpack", "rev", "revCount", "lastModified"};
         for (auto & [name, value] : attrs)
             if (!allowedNames.count(name))
-                throw Error("unsupported %s input attribute '%s'. If you wanted to fetch a tarball with a query parameter, please use '{ type = \"tarball\"; url = \"...\"; }'", *type, name);
+                throw Error("unsupported %s input attribute '%s'", *type, name);
 
         Input input;
         input.attrs = attrs;