From d9e7758f4756c10592407b3fe99dc253ef56eac9 Mon Sep 17 00:00:00 2001
From: Eelco Dolstra <edolstra@gmail.com>
Date: Tue, 1 Aug 2023 16:07:20 +0200
Subject: [PATCH] Don't require .tar/.zip extension for tarball flakerefs

Special-casing the file name is rather ugly, so we shouldn't do
that. So now any {file,http,https} URL is handled by
TarballInputScheme, except for non-flake inputs (i.e. inputs that have
the attribute `flake = false`).
---
 src/libexpr/flake/flakeref.cc |  6 +++---
 src/libfetchers/fetchers.cc   |  8 ++++----
 src/libfetchers/fetchers.hh   |  6 +++---
 src/libfetchers/git.cc        |  2 +-
 src/libfetchers/github.cc     |  2 +-
 src/libfetchers/indirect.cc   |  2 +-
 src/libfetchers/mercurial.cc  |  2 +-
 src/libfetchers/path.cc       |  2 +-
 src/libfetchers/tarball.cc    | 18 +++++++++---------
 tests/fetchTree-file.sh       | 14 +++++++++++++-
 10 files changed, 37 insertions(+), 25 deletions(-)

diff --git a/src/libexpr/flake/flakeref.cc b/src/libexpr/flake/flakeref.cc
index 08adbe0c9..d3fa1d557 100644
--- a/src/libexpr/flake/flakeref.cc
+++ b/src/libexpr/flake/flakeref.cc
@@ -105,7 +105,7 @@ std::pair<FlakeRef, std::string> parseFlakeRefWithFragment(
         };
 
         return std::make_pair(
-            FlakeRef(Input::fromURL(parsedURL), ""),
+            FlakeRef(Input::fromURL(parsedURL, isFlake), ""),
             percentDecode(match.str(6)));
     }
 
@@ -176,7 +176,7 @@ std::pair<FlakeRef, std::string> parseFlakeRefWithFragment(
                             parsedURL.query.insert_or_assign("shallow", "1");
 
                         return std::make_pair(
-                            FlakeRef(Input::fromURL(parsedURL), getOr(parsedURL.query, "dir", "")),
+                            FlakeRef(Input::fromURL(parsedURL, isFlake), getOr(parsedURL.query, "dir", "")),
                             fragment);
                     }
 
@@ -204,7 +204,7 @@ std::pair<FlakeRef, std::string> parseFlakeRefWithFragment(
         std::string fragment;
         std::swap(fragment, parsedURL.fragment);
 
-        auto input = Input::fromURL(parsedURL);
+        auto input = Input::fromURL(parsedURL, isFlake);
         input.parent = baseDir;
 
         return std::make_pair(
diff --git a/src/libfetchers/fetchers.cc b/src/libfetchers/fetchers.cc
index f86c0604e..e683b9f80 100644
--- a/src/libfetchers/fetchers.cc
+++ b/src/libfetchers/fetchers.cc
@@ -13,9 +13,9 @@ void registerInputScheme(std::shared_ptr<InputScheme> && inputScheme)
     inputSchemes->push_back(std::move(inputScheme));
 }
 
-Input Input::fromURL(const std::string & url)
+Input Input::fromURL(const std::string & url, bool requireTree)
 {
-    return fromURL(parseURL(url));
+    return fromURL(parseURL(url), requireTree);
 }
 
 static void fixupInput(Input & input)
@@ -31,10 +31,10 @@ static void fixupInput(Input & input)
         input.locked = true;
 }
 
-Input Input::fromURL(const ParsedURL & url)
+Input Input::fromURL(const ParsedURL & url, bool requireTree)
 {
     for (auto & inputScheme : *inputSchemes) {
-        auto res = inputScheme->inputFromURL(url);
+        auto res = inputScheme->inputFromURL(url, requireTree);
         if (res) {
             res->scheme = inputScheme;
             fixupInput(*res);
diff --git a/src/libfetchers/fetchers.hh b/src/libfetchers/fetchers.hh
index d0738f619..6e10e9513 100644
--- a/src/libfetchers/fetchers.hh
+++ b/src/libfetchers/fetchers.hh
@@ -44,9 +44,9 @@ struct Input
     std::optional<Path> parent;
 
 public:
-    static Input fromURL(const std::string & url);
+    static Input fromURL(const std::string & url, bool requireTree = true);
 
-    static Input fromURL(const ParsedURL & url);
+    static Input fromURL(const ParsedURL & url, bool requireTree = true);
 
     static Input fromAttrs(Attrs && attrs);
 
@@ -129,7 +129,7 @@ struct InputScheme
     virtual ~InputScheme()
     { }
 
-    virtual std::optional<Input> inputFromURL(const ParsedURL & url) const = 0;
+    virtual std::optional<Input> inputFromURL(const ParsedURL & url, bool requireTree) const = 0;
 
     virtual std::optional<Input> inputFromAttrs(const Attrs & attrs) const = 0;
 
diff --git a/src/libfetchers/git.cc b/src/libfetchers/git.cc
index be5842d53..f8d89ab2f 100644
--- a/src/libfetchers/git.cc
+++ b/src/libfetchers/git.cc
@@ -256,7 +256,7 @@ std::pair<StorePath, Input> fetchFromWorkdir(ref<Store> store, Input & input, co
 
 struct GitInputScheme : InputScheme
 {
-    std::optional<Input> inputFromURL(const ParsedURL & url) const override
+    std::optional<Input> inputFromURL(const ParsedURL & url, bool requireTree) const override
     {
         if (url.scheme != "git" &&
             url.scheme != "git+http" &&
diff --git a/src/libfetchers/github.cc b/src/libfetchers/github.cc
index 80598e7f8..291f457f0 100644
--- a/src/libfetchers/github.cc
+++ b/src/libfetchers/github.cc
@@ -30,7 +30,7 @@ struct GitArchiveInputScheme : InputScheme
 
     virtual std::optional<std::pair<std::string, std::string>> accessHeaderFromToken(const std::string & token) const = 0;
 
-    std::optional<Input> inputFromURL(const ParsedURL & url) const override
+    std::optional<Input> inputFromURL(const ParsedURL & url, bool requireTree) const override
     {
         if (url.scheme != type()) return {};
 
diff --git a/src/libfetchers/indirect.cc b/src/libfetchers/indirect.cc
index b99504a16..4874a43ff 100644
--- a/src/libfetchers/indirect.cc
+++ b/src/libfetchers/indirect.cc
@@ -7,7 +7,7 @@ std::regex flakeRegex("[a-zA-Z][a-zA-Z0-9_-]*", std::regex::ECMAScript);
 
 struct IndirectInputScheme : InputScheme
 {
-    std::optional<Input> inputFromURL(const ParsedURL & url) const override
+    std::optional<Input> inputFromURL(const ParsedURL & url, bool requireTree) const override
     {
         if (url.scheme != "flake") return {};
 
diff --git a/src/libfetchers/mercurial.cc b/src/libfetchers/mercurial.cc
index 86e8f81f4..51fd1ed42 100644
--- a/src/libfetchers/mercurial.cc
+++ b/src/libfetchers/mercurial.cc
@@ -43,7 +43,7 @@ static std::string runHg(const Strings & args, const std::optional<std::string>
 
 struct MercurialInputScheme : InputScheme
 {
-    std::optional<Input> inputFromURL(const ParsedURL & url) const override
+    std::optional<Input> inputFromURL(const ParsedURL & url, bool requireTree) const override
     {
         if (url.scheme != "hg+http" &&
             url.scheme != "hg+https" &&
diff --git a/src/libfetchers/path.cc b/src/libfetchers/path.cc
index 61541e69d..01f1be978 100644
--- a/src/libfetchers/path.cc
+++ b/src/libfetchers/path.cc
@@ -6,7 +6,7 @@ namespace nix::fetchers {
 
 struct PathInputScheme : InputScheme
 {
-    std::optional<Input> inputFromURL(const ParsedURL & url) const override
+    std::optional<Input> inputFromURL(const ParsedURL & url, bool requireTree) const override
     {
         if (url.scheme != "path") return {};
 
diff --git a/src/libfetchers/tarball.cc b/src/libfetchers/tarball.cc
index a012234e0..107d38e92 100644
--- a/src/libfetchers/tarball.cc
+++ b/src/libfetchers/tarball.cc
@@ -194,11 +194,11 @@ struct CurlInputScheme : InputScheme
             || hasSuffix(path, ".tar.zst");
     }
 
-    virtual bool isValidURL(const ParsedURL & url) const = 0;
+    virtual bool isValidURL(const ParsedURL & url, bool requireTree) const = 0;
 
-    std::optional<Input> inputFromURL(const ParsedURL & _url) const override
+    std::optional<Input> inputFromURL(const ParsedURL & _url, bool requireTree) const override
     {
-        if (!isValidURL(_url))
+        if (!isValidURL(_url, requireTree))
             return std::nullopt;
 
         Input input;
@@ -265,13 +265,13 @@ struct FileInputScheme : CurlInputScheme
 {
     const std::string inputType() const override { return "file"; }
 
-    bool isValidURL(const ParsedURL & url) const override
+    bool isValidURL(const ParsedURL & url, bool requireTree) const override
     {
         auto parsedUrlScheme = parseUrlScheme(url.scheme);
         return transportUrlSchemes.count(std::string(parsedUrlScheme.transport))
             && (parsedUrlScheme.application
-                    ? parsedUrlScheme.application.value() == inputType()
-                    : !hasTarballExtension(url.path));
+                ? parsedUrlScheme.application.value() == inputType()
+                : (!requireTree && !hasTarballExtension(url.path)));
     }
 
     std::pair<StorePath, Input> fetch(ref<Store> store, const Input & input) override
@@ -285,14 +285,14 @@ struct TarballInputScheme : CurlInputScheme
 {
     const std::string inputType() const override { return "tarball"; }
 
-    bool isValidURL(const ParsedURL & url) const override
+    bool isValidURL(const ParsedURL & url, bool requireTree) const override
     {
         auto parsedUrlScheme = parseUrlScheme(url.scheme);
 
         return transportUrlSchemes.count(std::string(parsedUrlScheme.transport))
             && (parsedUrlScheme.application
-                    ? parsedUrlScheme.application.value() == inputType()
-                    : hasTarballExtension(url.path));
+                ? parsedUrlScheme.application.value() == inputType()
+                : (requireTree || hasTarballExtension(url.path)));
     }
 
     std::pair<StorePath, Input> fetch(ref<Store> store, const Input & _input) override
diff --git a/tests/fetchTree-file.sh b/tests/fetchTree-file.sh
index fe569cfb8..6395c133d 100644
--- a/tests/fetchTree-file.sh
+++ b/tests/fetchTree-file.sh
@@ -27,6 +27,7 @@ test_file_flake_input () {
 
     mkdir inputs
     echo foo > inputs/test_input_file
+    echo '{ outputs = { self }: { }; }' > inputs/flake.nix
     tar cfa test_input.tar.gz inputs
     cp test_input.tar.gz test_input_no_ext
     input_tarball_hash="$(nix hash path test_input.tar.gz)"
@@ -50,6 +51,9 @@ test_file_flake_input () {
             url = "file+file://$PWD/test_input.tar.gz";
             flake = false;
         };
+        inputs.flake_no_ext = {
+            url = "file://$PWD/test_input_no_ext";
+        };
         outputs = { ... }: {};
     }
 EOF
@@ -58,7 +62,7 @@ EOF
     nix eval --file - <<EOF
     with (builtins.fromJSON (builtins.readFile ./flake.lock));
 
-    # Url inputs whose extension doesn’t match a known archive format should
+    # Non-flake inputs whose extension doesn’t match a known archive format should
     # not be unpacked by default
     assert (nodes.no_ext_default_no_unpack.locked.type == "file");
     assert (nodes.no_ext_default_no_unpack.locked.unpack or false == false);
@@ -75,8 +79,16 @@ EOF
     # Explicitely passing the unpack parameter should enforce the desired behavior
     assert (nodes.no_ext_explicit_unpack.locked.narHash == nodes.tarball_default_unpack.locked.narHash);
     assert (nodes.tarball_explicit_no_unpack.locked.narHash == nodes.no_ext_default_no_unpack.locked.narHash);
+
+    # Flake inputs should always be tarballs
+    assert (nodes.flake_no_ext.locked.type == "tarball");
+
     true
 EOF
+
+    # Test tarball URLs on the command line.
+    [[ $(nix flake metadata --json file://$PWD/test_input_no_ext | jq -r .resolved.type) = tarball ]]
+
     popd
 
     [[ -z "${NIX_DAEMON_PACKAGE-}" ]] && return 0