fix: parsing metadata with inline licenses (#2806)

keith · aignas · web-flow · commit 1d69ad68d795 · 2025-04-22T12:49:15.000Z
The wheel `METADATA` parsing implemented in 1.4 missed the fact that whitespace is significant and sometimes License is included inline in the `METADATA` file itself. This change ensures that we stop parsing the `METADATA` file only on first completely empty line. Fixes #2796 --------- Co-authored-by: Ignas Anikevicius <240938+aignas@users.noreply.github.com>
diff --git a/python/private/pypi/whl_metadata.bzl b/python/private/pypi/whl_metadata.bzl
@@ -52,7 +52,7 @@ def parse_whl_metadata(contents):
         "version": "",
     }
     for line in contents.strip().split("\n"):
-        if not line.strip():
+        if not line:
             # Stop parsing on first empty line, which marks the end of the
             # headers containing the metadata.
             break
diff --git a/tests/pypi/whl_metadata/whl_metadata_tests.bzl b/tests/pypi/whl_metadata/whl_metadata_tests.bzl
@@ -140,6 +140,37 @@ Requires-Dist: this will be ignored
 
 _tests.append(_test_parse_metadata_all)
 
+def _test_parse_metadata_multiline_license(env):
+    got = _parse_whl_metadata(
+        env,
+        # NOTE: The trailing whitespace here is meaningful as an empty line
+        # denotes the end of the header.
+        contents = """\
+Name: foo
+Version: 0.0.1
+License: some License
+        
+        some line
+        
+        another line
+        
+Requires-Dist: bar; extra == "all"
+Provides-Extra: all
+
+Requires-Dist: this will be ignored
+""",
+    )
+    got.name().equals("foo")
+    got.version().equals("0.0.1")
+    got.requires_dist().contains_exactly([
+        "bar; extra == \"all\"",
+    ])
+    got.provides_extra().contains_exactly([
+        "all",
+    ])
+
+_tests.append(_test_parse_metadata_multiline_license)
+
 def whl_metadata_test_suite(name):  # buildifier: disable=function-docstring
     test_suite(
         name = name,

Original file line number	Diff line number	Diff line change
`@@ -52,7 +52,7 @@ def parse_whl_metadata(contents):`
`52`	`52`	`"version": "",`
`53`	`53`	`}`
`54`	`54`	`for line in contents.strip().split("\n"):`
`55`		`- if not line.strip():`
	`55`	`+ if not line:`
`56`	`56`	`# Stop parsing on first empty line, which marks the end of the`
`57`	`57`	`# headers containing the metadata.`
`58`	`58`	`break`