Merge bitcoin/bitcoin#33702: contrib: Remove brittle, confusing and redundant UTF8 encoding from Python IO

fad6118586 test: Fix "typo" in written invalid content (MarcoFalke)
fab085c15f contrib: Use text=True in subprocess over manual encoding handling (MarcoFalke)
fa71c15f86 scripted-diff: Bump copyright headers after encoding changes (MarcoFalke)
fae612424b contrib: Remove confusing and redundant encoding from IO (MarcoFalke)
fa7d72bd1b lint: Drop check to enforce encoding to be specified in Python scripts (MarcoFalke)
faf39d8539 test: Clarify that Python UTF-8 mode is the default today for most systems (MarcoFalke)
fa83e3a81d lint: Do not allow locale dependent shell scripts (MarcoFalke)

Pull request description:

  Historically, there was an attempt via `test/lint/lint-python-utf8-encoding.py` to enforce explicit UTF8 in every Python IO statement (`open`, `subprocess`, ...). However, the lint check has many problems:

  * The check is incomplete and many IO statements lack the explicit UTF8 specification.
  * It was added at a time when some systems were not UTF8 by default.
  * The check is brittle, as it depends on a fragile regex.

  In theory, now that the minimum Python version is 3.10 (since commit 2123c94448), the check could be replaced by `PYTHONWARNDEFAULTENCODING=1` from https://docs.python.org/3/whatsnew/3.10.html#optional-encodingwarning-and-encoding-locale-option. However, this comes with many other problems:

  * All our Python scripts already assume and require UTF8 to be set externally. On almost all modern systems, this is already the default. Some Windows versions do not have UTF8 by default and require `PYTHONUTF8=1` to be set for the tests to run already today (with or without the changes in this pull). Also, the CI and many other Bash scripts force UTF8 via `LC_ALL`. Finally, Python 3.15 will likely enable UTF8 on *all* systems by default, per https://peps.python.org/pep-0686/#abstract.
  * So adding UTF8 to every single IO call is redundant, verbose, and confusing, given that it is the expected default.

  So fix all issues, by:

  * Removing the `test/lint/lint-python-utf8-encoding.py` check.
  * Removing the encoding on the individual IO calls.
  * Clarifying the existing docs around the existing UTF8 requirement and assumption.

  Obviously, every IO call is still free to specify UTF8 or any other encoding explicitly, if there is a documented need for it in the future.

ACKs for top commit:
  theStack:
    re-ACK fad6118586
  laanwj:
    Re-ACK fad6118586

Tree-SHA512: 78025ea3508597d2299490347614f0ee3e4c66e3ba559ff50e498045a9c8bbd92f3a5ced18719d8fcebbd1e47bdbb56a0c85a5b73b425adb0ea4f02fe69c3149

contrib/devtools/circular-dependencies.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# Copyright (c) 2018-2020 The Bitcoin Core developers
+# Copyright (c) 2018-present The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 
@@ -49,7 +49,7 @@ for arg in sys.argv[1:]:
 # TODO: implement support for multiple include directories
 for arg in sorted(files.keys()):
     module = files[arg]
-    with open(arg, 'r', encoding="utf8") as f:
+    with open(arg, 'r') as f:
         for line in f:
             match = RE.match(line)
             if match:

contrib/devtools/clang-format-diff.py

@@ -169,7 +169,7 @@ def main():
             sys.exit(p.returncode)
 
         if not args.i:
-            with open(filename, encoding="utf8") as f:
+            with open(filename) as f:
                 code = f.readlines()
             formatted_code = StringIO(stdout).readlines()
             diff = difflib.unified_diff(

contrib/devtools/copyright_header.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# Copyright (c) 2016-2022 The Bitcoin Core developers
+# Copyright (c) 2016-present The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 
@@ -54,12 +54,12 @@ GIT_LS_CMD = 'git ls-files --full-name'.split(' ')
 GIT_TOPLEVEL_CMD = 'git rev-parse --show-toplevel'.split(' ')
 
 def call_git_ls(base_directory):
-    out = subprocess.check_output([*GIT_LS_CMD, base_directory])
-    return [f for f in out.decode("utf-8").split('\n') if f != '']
+    out = subprocess.check_output([*GIT_LS_CMD, base_directory], text=True)
+    return [f for f in out.split('\n') if f != '']
 
 def call_git_toplevel():
     "Returns the absolute path to the project root"
-    return subprocess.check_output(GIT_TOPLEVEL_CMD).strip().decode("utf-8")
+    return subprocess.check_output(GIT_TOPLEVEL_CMD, text=True).strip()
 
 def get_filenames_to_examine(base_directory):
     "Returns an array of absolute paths to any project files in the base_directory that pass the include/exclude filters"
@@ -140,7 +140,7 @@ def file_has_without_c_style_copyright_for_holder(contents, holder_name):
 ################################################################################
 
 def read_file(filename):
-    return open(filename, 'r', encoding="utf8").read()
+    return open(filename, 'r').read()
 
 def gather_file_info(filename):
     info = {}
@@ -298,8 +298,8 @@ def report_cmd(argv):
 GIT_LOG_CMD = "git log --pretty=format:%%ai %s"
 
 def call_git_log(filename):
-    out = subprocess.check_output((GIT_LOG_CMD % filename).split(' '))
-    return out.decode("utf-8").split('\n')
+    out = subprocess.check_output((GIT_LOG_CMD % filename).split(' '), text=True)
+    return out.split('\n')
 
 def get_git_change_years(filename):
     git_log_lines = call_git_log(filename)
@@ -316,12 +316,12 @@ def get_most_recent_git_change_year(filename):
 ################################################################################
 
 def read_file_lines(filename):
-    with open(filename, 'r', encoding="utf8") as f:
+    with open(filename, 'r') as f:
         file_lines = f.readlines()
     return file_lines
 
 def write_file_lines(filename, file_lines):
-    with open(filename, 'w', encoding="utf8") as f:
+    with open(filename, 'w') as f:
         f.write(''.join(file_lines))
 
 ################################################################################

contrib/filter-lcov.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# Copyright (c) 2017-2020 The Bitcoin Core developers
+# Copyright (c) 2017-present The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 
@@ -16,8 +16,8 @@ pattern = args.pattern
 outfile = args.outfile
 
 in_remove = False
-with open(tracefile, 'r', encoding="utf8") as f:
-    with open(outfile, 'w', encoding="utf8") as wf:
+with open(tracefile, 'r') as f:
+    with open(outfile, 'w') as wf:
         for line in f:
             for p in pattern:
                 if line.startswith("SF:") and p in line:

contrib/linearize/linearize-data.py

@@ -2,7 +2,7 @@
 #
 # linearize-data.py: Construct a linear, no-fork version of the chain.
 #
-# Copyright (c) 2013-2022 The Bitcoin Core developers
+# Copyright (c) 2013-present The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 #
@@ -34,7 +34,7 @@ def get_blk_dt(blk_hdr):
 # When getting the list of block hashes, undo any byte reversals.
 def get_block_hashes(settings):
     blkindex = []
-    with open(settings['hashlist'], "r", encoding="utf8") as f:
+    with open(settings['hashlist'], "r") as f:
         for line in f:
             line = line.rstrip()
             if settings['rev_hash_bytes'] == 'true':
@@ -267,7 +267,7 @@ if __name__ == '__main__':
         print("Usage: linearize-data.py CONFIG-FILE")
         sys.exit(1)
 
-    with open(sys.argv[1], encoding="utf8") as f:
+    with open(sys.argv[1]) as f:
         for line in f:
             # skip comment lines
             m = re.search(r'^\s*#', line)

contrib/linearize/linearize-hashes.py

@@ -2,7 +2,7 @@
 #
 # linearize-hashes.py:  List blocks in a linear, no-fork version of the chain.
 #
-# Copyright (c) 2013-2022 The Bitcoin Core developers
+# Copyright (c) 2013-present The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 #
@@ -87,7 +87,7 @@ def get_block_hashes(settings, max_blocks_per_call=10000):
 
 def get_rpc_cookie():
     # Open the cookie file
-    with open(os.path.join(os.path.expanduser(settings['datadir']), '.cookie'), 'r', encoding="ascii") as f:
+    with open(os.path.join(os.path.expanduser(settings['datadir']), '.cookie'), 'r') as f:
         combined = f.readline()
         combined_split = combined.split(":")
         settings['rpcuser'] = combined_split[0]
@@ -98,7 +98,7 @@ if __name__ == '__main__':
         print("Usage: linearize-hashes.py CONFIG-FILE")
         sys.exit(1)
 
-    with open(sys.argv[1], encoding="utf8") as f:
+    with open(sys.argv[1]) as f:
         for line in f:
             # skip comment lines
             m = re.search(r'^\s*#', line)

contrib/message-capture/message-capture-parser.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# Copyright (c) 2020-2022 The Bitcoin Core developers
+# Copyright (c) 2020-present The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 """Parse message capture binary files.  To be used in conjunction with -capturemessages."""
@@ -205,7 +205,7 @@ def main():
 
     jsonrep = json.dumps(messages)
     if output:
-        with open(str(output), 'w+', encoding="utf8") as f_out:
+        with open(str(output), 'w+') as f_out:
             f_out.write(jsonrep)
     else:
         print(jsonrep)

contrib/seeds/generate-seeds.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# Copyright (c) 2014-2021 The Bitcoin Core developers
+# Copyright (c) 2014-present The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 '''
@@ -168,16 +168,16 @@ def main():
     g.write(' *\n')
     g.write(' * Each line contains a BIP155 serialized (networkID, addr, port) tuple.\n')
     g.write(' */\n')
-    with open(os.path.join(indir,'nodes_main.txt'), 'r', encoding="utf8") as f:
+    with open(os.path.join(indir,'nodes_main.txt'), 'r') as f:
         process_nodes(g, f, 'chainparams_seed_main')
     g.write('\n')
-    with open(os.path.join(indir,'nodes_signet.txt'), 'r', encoding="utf8") as f:
+    with open(os.path.join(indir,'nodes_signet.txt'), 'r') as f:
         process_nodes(g, f, 'chainparams_seed_signet')
     g.write('\n')
-    with open(os.path.join(indir,'nodes_test.txt'), 'r', encoding="utf8") as f:
+    with open(os.path.join(indir,'nodes_test.txt'), 'r') as f:
         process_nodes(g, f, 'chainparams_seed_test')
     g.write('\n')
-    with open(os.path.join(indir,'nodes_testnet4.txt'), 'r', encoding="utf8") as f:
+    with open(os.path.join(indir,'nodes_testnet4.txt'), 'r') as f:
         process_nodes(g, f, 'chainparams_seed_testnet4')
     g.write('#endif // BITCOIN_CHAINPARAMSSEEDS_H\n')
 

contrib/seeds/makeseeds.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# Copyright (c) 2013-2022 The Bitcoin Core developers
+# Copyright (c) 2013-present The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 #
@@ -211,7 +211,7 @@ def main():
     print('Done.', file=sys.stderr)
 
     print('Loading and parsing DNS seeds…', end='', file=sys.stderr, flush=True)
-    with open(args.seeds, 'r', encoding='utf8') as f:
+    with open(args.seeds, 'r') as f:
         lines = f.readlines()
     ips = [parseline(line) for line in lines]
     random.shuffle(ips)

contrib/verify-binaries/verify.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# Copyright (c) 2020-2021 The Bitcoin Core developers
+# Copyright (c) 2020-present The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 """Script for verifying Bitcoin Core release binaries.
@@ -246,8 +246,8 @@ def files_are_equal(filename1, filename2):
     eq = contents1 == contents2
 
     if not eq:
-        with open(filename1, 'r', encoding='utf-8') as f1, \
-                open(filename2, 'r', encoding='utf-8') as f2:
+        with open(filename1, 'r') as f1, \
+                open(filename2, 'r') as f2:
             f1lines = f1.readlines()
             f2lines = f2.readlines()
 
@@ -426,7 +426,7 @@ def verify_shasums_signature(
 def parse_sums_file(sums_file_path: str, filename_filter: list[str]) -> list[list[str]]:
     # extract hashes/filenames of binaries to verify from hash file;
     # each line has the following format: "<hash> <binary_filename>"
-    with open(sums_file_path, 'r', encoding='utf8') as hash_file:
+    with open(sums_file_path, 'r') as hash_file:
         return [line.split()[:2] for line in hash_file if len(filename_filter) == 0 or any(f in line for f in filename_filter)]
 
 

contrib/verify-commits/verify-commits.py

@@ -1,5 +1,5 @@
 #!/usr/bin/env python3
-# Copyright (c) 2018-2022 The Bitcoin Core developers
+# Copyright (c) 2018-present The Bitcoin Core developers
 # Distributed under the MIT software license, see the accompanying
 # file COPYING or http://www.opensource.org/licenses/mit-license.php.
 """Verify commits against a trusted keys list."""
@@ -82,17 +82,17 @@ def main():
     # get directory of this program and read data files
     dirname = os.path.dirname(os.path.abspath(__file__))
     print("Using verify-commits data from " + dirname)
-    with open(dirname + "/trusted-git-root", "r", encoding="utf8") as f:
+    with open(dirname + "/trusted-git-root", "r") as f:
         verified_root = f.read().splitlines()[0]
-    with open(dirname + "/trusted-sha512-root-commit", "r", encoding="utf8") as f:
+    with open(dirname + "/trusted-sha512-root-commit", "r") as f:
         verified_sha512_root = f.read().splitlines()[0]
-    with open(dirname + "/allow-revsig-commits", "r", encoding="utf8") as f:
+    with open(dirname + "/allow-revsig-commits", "r") as f:
         revsig_allowed = f.read().splitlines()
-    with open(dirname + "/allow-unclean-merge-commits", "r", encoding="utf8") as f:
+    with open(dirname + "/allow-unclean-merge-commits", "r") as f:
         unclean_merge_allowed = f.read().splitlines()
-    with open(dirname + "/allow-incorrect-sha512-commits", "r", encoding="utf8") as f:
+    with open(dirname + "/allow-incorrect-sha512-commits", "r") as f:
         incorrect_sha512_allowed = f.read().splitlines()
-    with open(dirname + "/trusted-keys", "r", encoding="utf8") as f:
+    with open(dirname + "/trusted-keys", "r") as f:
         trusted_keys = f.read().splitlines()
 
     # Set commit and variables
@@ -140,8 +140,8 @@ def main():
 
         # Check that the commit (and parents) was signed with a trusted key
         valid_sig = False
-        verify_res = subprocess.run([GIT, '-c', 'gpg.program={}/gpg.sh'.format(dirname), 'verify-commit', "--raw", current_commit], capture_output=True)
-        for line in verify_res.stderr.decode().splitlines():
+        verify_res = subprocess.run([GIT, '-c', 'gpg.program={}/gpg.sh'.format(dirname), 'verify-commit', "--raw", current_commit], text=True, capture_output=True)
+        for line in verify_res.stderr.splitlines():
             if line.startswith("[GNUPG:] VALIDSIG "):
                 key = line.split(" ")[-1]
                 valid_sig = key in trusted_keys
@@ -152,7 +152,7 @@ def main():
             if prev_commit != "":
                 print("No parent of {} was signed with a trusted key!".format(prev_commit), file=sys.stderr)
                 print("Parents are:", file=sys.stderr)
-                parents = subprocess.check_output([GIT, 'show', '-s', '--format=format:%P', prev_commit]).decode('utf8').splitlines()[0].split(' ')
+                parents = subprocess.check_output([GIT, 'show', '-s', '--format=format:%P', prev_commit], text=True).splitlines()[0].split(' ')
                 for parent in parents:
                     subprocess.call([GIT, 'show', '-s', parent], stdout=sys.stderr)
             else:
@@ -162,29 +162,29 @@ def main():
         # Check the Tree-SHA512
         if (verify_tree or prev_commit == "") and current_commit not in incorrect_sha512_allowed:
             tree_hash = tree_sha512sum(current_commit)
-            if ("Tree-SHA512: {}".format(tree_hash)) not in subprocess.check_output([GIT, 'show', '-s', '--format=format:%B', current_commit]).decode('utf8').splitlines():
+            if ("Tree-SHA512: {}".format(tree_hash)) not in subprocess.check_output([GIT, 'show', '-s', '--format=format:%B', current_commit], text=True).splitlines():
                 print("Tree-SHA512 did not match for commit " + current_commit, file=sys.stderr)
                 sys.exit(1)
 
         # Merge commits should only have two parents
-        parents = subprocess.check_output([GIT, 'show', '-s', '--format=format:%P', current_commit]).decode('utf8').splitlines()[0].split(' ')
+        parents = subprocess.check_output([GIT, 'show', '-s', '--format=format:%P', current_commit], text=True).splitlines()[0].split(' ')
         if len(parents) > 2:
             print("Commit {} is an octopus merge".format(current_commit), file=sys.stderr)
             sys.exit(1)
 
         # Check that the merge commit is clean
-        commit_time = int(subprocess.check_output([GIT, 'show', '-s', '--format=format:%ct', current_commit]).decode('utf8').splitlines()[0])
+        commit_time = int(subprocess.check_output([GIT, 'show', '-s', '--format=format:%ct', current_commit], text=True).splitlines()[0])
         check_merge = commit_time > time.time() - args.clean_merge * 24 * 60 * 60  # Only check commits in clean_merge days
         allow_unclean = current_commit in unclean_merge_allowed
         if len(parents) == 2 and check_merge and not allow_unclean:
-            current_tree = subprocess.check_output([GIT, 'show', '--format=%T', current_commit]).decode('utf8').splitlines()[0]
+            current_tree = subprocess.check_output([GIT, 'show', '--format=%T', current_commit], text=True).splitlines()[0]
 
             # This merge-tree functionality requires git >= 2.38. The
             # --write-tree option was added in order to opt-in to the new
             # behavior. Older versions of git will not recognize the option and
             # will instead exit with code 128.
             try:
-                recreated_tree = subprocess.check_output([GIT, "merge-tree", "--write-tree", parents[0], parents[1]]).decode('utf8').splitlines()[0]
+                recreated_tree = subprocess.check_output([GIT, "merge-tree", "--write-tree", parents[0], parents[1]], text=True).splitlines()[0]
             except subprocess.CalledProcessError as e:
                 if e.returncode == 128:
                     print("git v2.38+ is required for this functionality.", file=sys.stderr)