Merge bitcoin#30147: contrib: Fixup verify-binaries OS platform parsing

3ab2520 contrib: Fixup verify-binaries OS platform parsing (Ben Westgate)

Pull request description:

  Closes bitcoin#30145.

  This PR solves two major issues in the `parse_version_string` function of verify-binaries:
  1. `-aarch64` binaries cannot be specifically downloaded. The -platform string gets interpreted as a release candidate that doesn't exist due to containing sub-string "rc".
  2. Specifying a platform with a "-" in the name causes the parser to ignore both "-platform" AND "-rcN" and download the potentially wrong (non-rc) version for every platform. This also prevented specifying just one platform binary the user wished to download.

  It also updates the accompanying `test.py` to cover problem two and adds two examples that were formerly broken to `README.md` to show what is now possible. Including the most useful case of downloading only 1 specific platform's binary.

  This improves the Bitcoin verify-binaries tools user experience by not:
  1. Failing to download for inexplicable reasons,
  2. Downloading more files than what the user told it to, or in the worst case
  3. Downloading only the wrong files.

  * A test was added to cover the command `verify-binaries/verify.py pub 22.0-x86_64-linux-gnu.tar.gz` which checks that _bitcoin-22.0-x86_64-linux-gnu.tar.gz_ downloads successfully AND ONLY _bitcoin-22.0-x86_64-linux-gnu.tar.gz_ downloads.
  * The steps to reproduce each bug are in the referenced issue bitcoin#30145. Explanation of the potential issue as well as reasoning for the way the bug was fixed are in my commit descriptions.
  * This delivers the promised feature of "only download the binaries for a certain platform", by allowing strings with '-' to be accepted, allowing for single file downloads for any specific platform which was not always possible before.
  * Removes 6 lines of code from the offending `parse_version_string` function, while fixing the bugs/errors, and extending the functionality to be practical for users with slow connections.
  * Makes the error message more helpful when no file matches the provided platform string, now prints "Did you mean: `closest-match`" to help correct typos.

  Thanks for reading my PR. I look forward to getting this helpful tool in its best shape yet.

  Log of this branch passing the new test.py:
  ```
  python3 test.py
  ✓ 'Nonexistent version should fail' passed
  ✓ 'Malformed version should fail' passed
  ✓ '--min-good-sigs 20 should fail' passed
  - testing verification (22.0-x86_64-linux-gnu.tar.gz)
  ✓ '22.0-x86_64-linux-gnu.tar.gz should succeed' passed
  - testing verification (22.0)
  ✓ '22.0 should succeed' passed
  ```

  Log of master failing the new test.py:
  ```
  python3 test.py
  ✓ 'Nonexistent version should fail' passed
  ✓ 'Malformed version should fail' passed
  ✓ '--min-good-sigs 20 should fail' passed
  - testing verification (22.0-x86_64-linux-gnu.tar.gz)
  ✓ '22.0-x86_64-linux-gnu.tar.gz should succeed' passed
  Traceback (most recent call last):
    File "/home/ben/Documents/GitHub/bitcoin/contrib/verify-binaries/test.py", line 74, in <module>
      main()
    File "/home/ben/Documents/GitHub/bitcoin/contrib/verify-binaries/test.py", line 27, in main
      assert len(v) == 1
             ^^^^^^^^^^^
  AssertionError
  ```

ACKs for top commit:
  stickies-v:
    re-ACK 3ab2520
  willcl-ark:
    re-ACK 3ab2520

Tree-SHA512: 6093228bb876cd0ac84d1cd2630074e17a3f09c4b23325b9419d859a5721a802f928844575233b135df52b882287dd18d6fadf4419d88ec0a2cdf82db315329e

Author: fanquake

contrib/verify-binaries/README.md

@@ -50,21 +50,23 @@ Get JSON output and don't prompt for user input (no auto key import):
 
 ```sh
 ./contrib/verify-binaries/verify.py --json pub 22.0-x86
+./contrib/verify-binaries/verify.py --json pub 23.0-rc5-linux-gnu
 ```
 
 Rely only on local GPG state and manually specified keys, while requiring a
 threshold of at least 10 trusted signatures:
 ```sh
 ./contrib/verify-binaries/verify.py \
     --trusted-keys 74E2DEF5D77260B98BC19438099BAD163C70FBFA,9D3CC86A72F8494342EA5FD10A41BDC3F4FAFF1C \
-    --min-good-sigs 10 pub 22.0-x86
+    --min-good-sigs 10 pub 22.0-linux
 ```
 
-If you only want to download the binaries for a certain platform, add the corresponding suffix, e.g.:
+If you only want to download the binaries for a certain architecture and/or platform, add the corresponding suffix, e.g.:
 
 ```sh
-./contrib/verify-binaries/verify.py pub 24.0.1-darwin
-./contrib/verify-binaries/verify.py pub 23.1-rc1-win64
+./contrib/verify-binaries/verify.py pub 25.2-x86_64-linux
+./contrib/verify-binaries/verify.py pub 24.1-rc1-darwin
+./contrib/verify-binaries/verify.py pub 27.0-win64-setup.exe
 ```
 
 If you do not want to keep the downloaded binaries, specify the cleanup option.

contrib/verify-binaries/test.py

@@ -12,6 +12,21 @@ def main():
     expect_code(run_verify("", "pub", '0.32.awefa.12f9h'), 11, "Malformed version should fail")
     expect_code(run_verify('--min-good-sigs 20', "pub", "22.0"), 9, "--min-good-sigs 20 should fail")
 
+    print("- testing verification (22.0-x86_64-linux-gnu.tar.gz)", flush=True)
+    _220_x86_64_linux_gnu = run_verify("--json", "pub", "22.0-x86_64-linux-gnu.tar.gz")
+    try:
+        result = json.loads(_220_x86_64_linux_gnu.stdout.decode())
+    except Exception:
+        print("failed on 22.0-x86_64-linux-gnu.tar.gz --json:")
+        print_process_failure(_220_x86_64_linux_gnu)
+        raise
+
+    expect_code(_220_x86_64_linux_gnu, 0, "22.0-x86_64-linux-gnu.tar.gz should succeed")
+    v = result['verified_binaries']
+    assert result['good_trusted_sigs']
+    assert len(v) == 1
+    assert v['bitcoin-22.0-x86_64-linux-gnu.tar.gz'] == '59ebd25dd82a51638b7a6bb914586201e67db67b919b2a1ff08925a7936d1b16'
+
     print("- testing verification (22.0)", flush=True)
     _220 = run_verify("--json", "pub", "22.0")
     try:

contrib/verify-binaries/verify.py

@@ -97,23 +97,17 @@ def bool_from_env(key, default=False) -> bool:
 
 
 VERSION_FORMAT = "<major>.<minor>[.<patch>][-rc[0-9]][-platform]"
-VERSION_EXAMPLE = "22.0-x86_64 or 23.1-rc1-darwin"
+VERSION_EXAMPLE = "22.0 or 23.1-rc1-darwin.dmg or 27.0-x86_64-linux-gnu"
 
 def parse_version_string(version_str):
-    parts = version_str.split('-')
-    version_base = parts[0]
-    version_rc = ""
-    version_os = ""
-    if len(parts) == 2:  # "<version>-rcN" or "version-platform"
-        if "rc" in parts[1]:
-            version_rc = parts[1]
-        else:
-            version_os = parts[1]
-    elif len(parts) == 3:  # "<version>-rcN-platform"
-        version_rc = parts[1]
-        version_os = parts[2]
+    # "<version>[-rcN][-platform]"
+    version_base, _, platform = version_str.partition('-')
+    rc = ""
+    if platform.startswith("rc"): # "<version>-rcN[-platform]"
+        rc, _, platform = platform.partition('-')
+    # else "<version>" or "<version>-platform"
 
-    return version_base, version_rc, version_os
+    return version_base, rc, platform
 
 
 def download_with_wget(remote_file, local_file):
@@ -514,7 +508,9 @@ def cleanup():
     # Extract hashes and filenames
     hashes_to_verify = parse_sums_file(SUMS_FILENAME, [os_filter])
     if not hashes_to_verify:
-        log.error("no files matched the platform specified")
+        available_versions = ["-".join(line[1].split("-")[2:]) for line in parse_sums_file(SUMS_FILENAME, [])]
+        closest_match = difflib.get_close_matches(os_filter, available_versions, cutoff=0, n=1)[0]
+        log.error(f"No files matched the platform specified. Did you mean: {closest_match}")
         return ReturnCode.NO_BINARIES_MATCH
 
     # remove binaries that are known not to be hosted by bitcoincore.org