Implement re-zipping unzipped wheels

This patch teaches Zapp! to introspect the `sources` of a manifest, and
look for the well-known `WHEEL` file(s) indicative of an
unzipped/installed wheel in the input sources. A wheel can be (somewhat*)
correctly reassembled by zipping its unzipped state, so in the presence
of unzipped wheels Zapp! will re-zip them and enter them into the
manifest appropriately for inclusion.

This fixes #6 the nasty way, as there's no good way to make
`rules_python` provide wheel dependencies or to translate unrolled
wheels back to wheels during rule execution as this would violate
Bazel's file dependency model.

example/BUILD

@@ -2,6 +2,8 @@ load("@rules_zapp//zapp:zapp.bzl",
      "zapp_binary",
 )
 
+load("@rules_python//python:defs.bzl", "py_library")
+
 load("@my_deps//:requirements.bzl",
      py_requirement="requirement",
 )
@@ -20,3 +22,19 @@ zapp_binary(
         py_requirement("pyyaml"),
     ]
 )
+
+py_library(
+    name = "lib_hello",
+    srcs = [],
+    deps = [
+        py_requirement("pyyaml"),
+    ]
+)
+
+zapp_binary(
+    name = "hello_lib_deps",
+    main = "hello.py",
+    deps = [
+        ":lib_hello",
+    ],
+)

example/WORKSPACE

@@ -26,11 +26,16 @@ git_repository(
     tag = "0.3.0",
 )
 
-git_repository(
+# git_repository(
+#     name = "rules_zapp",
+#     remote = "https://github.com/arrdem/rules_zapp.git",
+#     tag = "0.1.1",
+#     # branch = "trunk",
+# )
+
+local_repository(
     name = "rules_zapp",
-    remote = "https://github.com/arrdem/rules_zapp.git",
-    tag = "0.1.1",
-    # branch = "trunk",
+    path = "../",
 )
 
 load("@rules_python//python:pip.bzl", "pip_install")

example/hello.py

@@ -9,6 +9,7 @@ def main():
 
     try:
         import yaml
+
         print("I have YAML! and nothing to do with it.", yaml.__file__)
     except ImportError:
         print("Don't have YAML.")

zapp/BUILD

@@ -2,13 +2,6 @@ package(default_visibility = ["//visibility:public"])
 
 load("zapp.bzl", "zapp_binary")
 
-# Bootstrapping Zapp using py_binary
-py_binary(
-    name = "zappc",
-    main = "compiler/__main__.py",
-    srcs = ["compiler/__main__.py"],
-)
-
 # Zapp plugins used as a runtime library by rules_zapp
 py_library(
     name = "zapp_support",
@@ -18,8 +11,26 @@ py_library(
     ]
 )
 
+# Bootstrapping Zapp using py_binary
+py_binary(
+    name = "zappc",
+    main = "compiler/__main__.py",
+    srcs = glob(["support/**/*.py"]) + [
+      "compiler/__main__.py"
+    ],
+    imports = [
+        "..",
+    ],
+)
+
 # For testing of zappc
 zapp_binary(
     name = "zappzappc",
     main = "compiler/__main__.py",
+    srcs = glob(["support/**/*.py"]) + [
+      "compiler/__main__.py"
+    ],
+    imports = [
+        "..",
+    ],
 )

zapp/__main__.py

@@ -6,10 +6,10 @@ import argparse
 import io
 import json
 import os
-import sys
-import zipfile
 import pathlib
 import stat
+import sys
+import zipfile
 
 parser = argparse.ArgumentParser(description="The (bootstrap) Zapp compiler")
 parser.add_argument("-o", "--out", dest="output", help="Output target file")
@@ -100,17 +100,22 @@ def main():
 
     if opts.debug:
         from pprint import pprint
-        pprint({
-            "opts": {k: getattr(opts, k) for k in dir(opts) if not k.startswith("_")},
-            "manifest": manifest
-        })
 
-    with open(opts.output, 'w') as zapp:
+        pprint(
+            {
+                "opts": {
+                    k: getattr(opts, k) for k in dir(opts) if not k.startswith("_")
+                },
+                "manifest": manifest,
+            }
+        )
+
+    with open(opts.output, "w") as zapp:
         shebang = "#!" + manifest["shebang"] + "\n"
         zapp.write(shebang)
 
     # Now we're gonna build the zapp from the manifest
-    with zipfile.ZipFile(opts.output, 'a') as zapp:
+    with zipfile.ZipFile(opts.output, "a") as zapp:
 
         # Append the __main__.py generated record
         zapp.writestr("__main__.py", make_dunder_main(manifest))

zapp/compiler/__main__.py

@@ -6,10 +6,15 @@ import argparse
 import io
 import json
 import os
-import sys
-import zipfile
 import pathlib
 import stat
+import sys
+import zipfile
+from email.parser import Parser
+from shutil import move
+from tempfile import TemporaryDirectory
+
+from zapp.support.unpack import cache_wheel_path
 
 parser = argparse.ArgumentParser(description="The (bootstrap) Zapp compiler")
 parser.add_argument("-o", "--out", dest="output", help="Output target file")
@@ -47,6 +52,12 @@ for script in {scripts!r}:
 """
 
 
+def dsub(d1, d2):
+    """Dictionary subtraction. Remove k/vs from d1 if they occur in d2."""
+
+    return {k: v for k, v in d1.items() if k not in d2 or d2[k] != v}
+
+
 def make_dunder_main(manifest):
     """Generate a __main__.py file for the given manifest."""
 
@@ -55,6 +66,7 @@ def make_dunder_main(manifest):
     scripts = prelude + [main]
     return MAIN_TEMPLATE.format(**locals())
 
+
 def dir_walk_prefixes(path):
     """Helper. Walk all slices of a path."""
 
@@ -65,6 +77,102 @@ def dir_walk_prefixes(path):
         yield os.path.join(*segments)
 
 
+def load_wheel(opts, manifest, path):
+    """Load a single wheel, returning ..."""
+
+    def _parse_email(msg):
+        return dict(Parser().parsestr(msg).items())
+
+    # RECORD seems to just record file reference checksums for validation
+    # with open(os.path.join(path, "RECORD")) as recordf:
+    #     record = recordf.read()
+
+    with open(os.path.join(path, "METADATA")) as metaf:
+        meta = _parse_email(metaf.read())
+
+    with open(os.path.join(path, "WHEEL")) as wheelf:
+        wheel = _parse_email(wheelf.read())
+
+    prefix = os.path.dirname(path)
+
+    sources = {k: v for k, v in manifest["sources"].items() if v.startswith(prefix)}
+
+    return {
+        # "record": record,
+        "meta": meta,
+        "wheel": wheel,
+        "sources": sources,
+    }
+
+
+def wheel_name(wheel):
+    """Construct the "canonical" filename of the wheel."""
+
+    tags = wheel["wheel"].get("Tag")
+    if isinstance(tags, list):
+        tags = "-" + ".".join(sorted(wheel["wheel"]["Tag"]))
+    elif isinstance(tags, str):
+        tags = "-" + wheel["wheel"]["Tag"]
+    else:
+        tags = ""
+
+    return "".join(
+        [
+            wheel["meta"]["Name"],
+            "-",
+            wheel["meta"]["Version"],
+            tags,
+            ".whl",
+        ]
+    )
+
+
+def zip_wheel(tmpdir, wheel):
+    """Build a 'tempfile' containing the proper contents of the wheel."""
+
+    wheel_file = os.path.join(tmpdir, wheel_name(wheel))
+
+    with zipfile.ZipFile(wheel_file, "w") as whl:
+        for dest, src in wheel["sources"].items():
+            whl.write(src, dest)
+
+    return wheel_file
+
+
+def rezip_wheels(opts, manifest):
+    """Extract unzipped wheels from the manifest's inputs, simplifying the manifest.
+
+    Wheels which are unzipped should be re-zipped into the cache, if not present in the cache.
+
+    Files sourced from unzipped wheels should be removed, and a single wheel reference inserted."""
+
+    wheels = [
+        load_wheel(opts, manifest, os.path.dirname(p))
+        for p in manifest["sources"].values()
+        if p.endswith("/WHEEL")
+    ]
+
+    # Zip up the wheels and insert wheel records to the manifest
+    for w in wheels:
+        # Try to cheat and hit in the local cache first rather than building wheels every time
+        wf = cache_wheel_path(wheel_name(w))
+        if wf.exists():
+            try:
+                wf.touch()
+            except OSError:
+                pass
+        else:
+            wf = zip_wheel(opts.tmpdir, w)
+
+        # Insert a new wheel source
+        manifest["wheels"][wheel_name(w)] = {"hashes": [], "source": wf}
+
+        # Expunge sources available in the wheel
+        manifest["sources"] = dsub(manifest["sources"], w["sources"])
+
+    return manifest
+
+
 def generate_dunder_inits(manifest):
     """Hack the manifest to insert __init__ files as needed."""
 
@@ -106,6 +214,10 @@ def main():
     with open(opts.manifest) as fp:
         manifest = json.load(fp)
 
+    with TemporaryDirectory() as d:
+        setattr(opts, "tmpdir", d)
+
+        manifest = rezip_wheels(opts, manifest)
         manifest = insert_manifest_json(opts, manifest)
         manifest = enable_unzipping(manifest)
         # Patch the manifest to insert needed __init__ files
@@ -114,12 +226,17 @@ def main():
 
         if opts.debug:
             from pprint import pprint
-        pprint({
-            "opts": {k: getattr(opts, k) for k in dir(opts) if not k.startswith("_")},
-            "manifest": manifest
-        })
 
-    with open(opts.output, 'w') as zapp:
+            pprint(
+                {
+                    "opts": {
+                        k: getattr(opts, k) for k in dir(opts) if not k.startswith("_")
+                    },
+                    "manifest": manifest,
+                }
+            )
+
+        with open(opts.output, "w") as zapp:
             shebang = "#!" + manifest["shebang"] + "\n"
             zapp.write(shebang)
 
@@ -128,14 +245,13 @@ def main():
             exit(1)
 
         # Now we're gonna build the zapp from the manifest
-    with zipfile.ZipFile(opts.output, 'a') as zapp:
+        with zipfile.ZipFile(opts.output, "a") as zapp:
 
             # Append the __main__.py generated record
             zapp.writestr("__main__.py", make_dunder_main(manifest))
 
             # Append user-specified sources
-        for dest, src in sorted(manifest["sources"].items(),
-                                key=lambda x: x[0]):
+            for dest, src in sorted(manifest["sources"].items(), key=lambda x: x[0]):
                 if src is None:
                     zapp.writestr(dest, "")
                 else:

zapp/support/manifest.py

@@ -1,17 +1,38 @@
 """The Zapp runtime manifest API."""
 
+import json
 from copy import deepcopy
 from importlib.resources import open_text
-import json
-
-with open_text("zapp", "manifest.json") as fp:
-    _MANIFEST = json.load(fp)
 
 
+def once(f):
+    singleton = object()
+    state = singleton
+
+    def helper(*args, **kwargs):
+        nonlocal state
+        if state is singleton:
+            state = f(*args, **kwargs)
+        return state
+
+    return helper
+
+
+def copied(f):
+    def helper(*args, **kwargs):
+        val = f(*args, **kwargs)
+        return deepcopy(val)
+
+    return helper
+
+
+@copied
+@once
 def manifest():
     """Return (a copy) of the runtime manifest."""
 
-    return deepcopy(_MANIFEST)
+    with open_text("zapp", "manifest.json") as fp:
+        return json.load(fp)
 
 
 __all__ = ["manifest"]

zapp/support/unpack.py

@@ -1,14 +1,11 @@
 """Conditionally unpack a zapp (and its deps)."""
 
-import sys
 import os
+import sys
 from pathlib import Path
 from zipfile import ZipFile
 
-from .manifest import manifest
-
-
-MANIFEST = manifest()
+from zapp.support.manifest import manifest
 
 
 def cache_root() -> Path:
@@ -39,7 +36,7 @@ def unpack_deps():
 
     # For each wheel, touch the existing cached wheel or unpack this one.
     with ZipFile(sys.argv[0], "r") as zf:
-        for whl, config in MANIFEST["wheels"].items():
+        for whl, config in manifest()["wheels"].items():
             cached_whl = cache_wheel_path(whl)
             if cached_whl.exists():
                 cached_whl.touch()

zapp/zapp.bzl

@@ -67,8 +67,6 @@ def _zapp_impl(ctx):
     # TODO: also handle ctx.attr.src.data_runfiles.symlinks
     srcs = [
         f for f in ctx.attr.src.default_runfiles.files.to_list()
-        # Strip out transitive sources from PyPi archives
-        if f.path.find("/pypi__") == -1
     ]
 
     # Find the list of directories to add to sys