summaryrefslogtreecommitdiffstats
path: root/scripts/check_repeated_token.py
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-04 11:33:32 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-05-04 11:33:32 +0000
commit1f403ad2197fc7442409f434ee574f3e6b46fb73 (patch)
tree0299c6dd11d5edfa918a29b6456bc1875f1d288c /scripts/check_repeated_token.py
parentInitial commit. (diff)
downloadpygments-1f403ad2197fc7442409f434ee574f3e6b46fb73.tar.xz
pygments-1f403ad2197fc7442409f434ee574f3e6b46fb73.zip
Adding upstream version 2.14.0+dfsg.upstream/2.14.0+dfsgupstream
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'scripts/check_repeated_token.py')
-rwxr-xr-xscripts/check_repeated_token.py77
1 files changed, 77 insertions, 0 deletions
diff --git a/scripts/check_repeated_token.py b/scripts/check_repeated_token.py
new file mode 100755
index 0000000..1636281
--- /dev/null
+++ b/scripts/check_repeated_token.py
@@ -0,0 +1,77 @@
+#!/usr/bin/env python
+"""
+ Checker for repeated tokens
+ ~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+ Helper script to find suspicious lexers which produce the same token
+ repeatedly, i.e. for example:
+
+ .. code::
+
+ 'd' Text
+ 'a' Text
+ 't' Text
+ 'a' Text
+ 'b' Text
+ 'a' Text
+ 's' Text
+ 'e' Text
+
+ This script has two test modes: Check for tokens repeating more often than
+ a given threshold, and exclude anything but single-character tokens.
+ Repeated single-character tokens are quite problematic as they result in
+ bloated output and are usually an indication that someone is missing
+ a + or * in the regex.
+
+ :copyright: Copyright 2006-2022 by the Pygments team, see AUTHORS.
+ :license: BSD, see LICENSE for details.
+"""
+import argparse
+import sys
+
+from utility import unpack_output_file, process_output_files
+
+
+def check_file(path, threshold, single_only):
+ current_token = ''
+ current_token_repeat_count = 1
+
+ for value, token, linenumber in unpack_output_file(path):
+ if single_only and len(value) > 1:
+ token = ''
+ current_token_repeat_count = 1
+ continue
+
+ if token != current_token:
+ current_token = token
+ current_token_repeat_count = 1
+ else:
+ current_token_repeat_count += 1
+
+ if current_token_repeat_count > threshold:
+ print(f'{path}:{linenumber}')
+ return False
+
+ return True
+
+
+def main(args):
+ def check_file_callback(path):
+ return check_file(path, args.threshold, args.single)
+
+ if process_output_files(args.TEST_ROOT, check_file_callback) > 0:
+ return 1
+ return 0
+
+
+if __name__ == '__main__':
+ parser = argparse.ArgumentParser()
+ parser.add_argument('TEST_ROOT',
+ help='Root directory containing the tests')
+ parser.add_argument('-t', '--threshold', type=int, default=5,
+ help='Warn if a token repeats itself more often then '
+ 'this number.')
+ parser.add_argument('-s', '--single', action='store_true', default=False,
+ help='Only look at tokens matching a single character')
+ args = parser.parse_args()
+ sys.exit(main(args))