diff options
author | Yuki Izumi <kivikakk@github.com> | 2016-11-05 09:04:48 +1100 |
---|---|---|
committer | John MacFarlane <jgm@berkeley.edu> | 2016-11-04 23:04:48 +0100 |
commit | 64e1394ae76409f02b00c254f119a64a2d1ce11e (patch) | |
tree | 4ad30178f0a166666dce869ea5efeb3537cbd61e /test/entity_tests.py | |
parent | 14fe768690b3948c7c1f67f463eb4620fc5746c9 (diff) |
Fix for non-matching entities (#161)
* Add test to illustrate issue
* Provide some test fixes
* Don't neglect CounterClockwiseContourIntegral
* Fix ~10% of cases not matching
strncmp returns 0 if the first 'len' bytes of cmark_entities[i].entity
match s; we check equal length in the first if by checking if
cmark_entities[i].entity[len] == 0, but we neglect the case where cmp ==
0 && cmark_entities[i].entity[len] != 0. This should be treated as the
same as cmp < 0, because strcmp("abc", "abcd") < 0.
* Don't depend on py3.3 in tests
Diffstat (limited to 'test/entity_tests.py')
-rw-r--r-- | test/entity_tests.py | 68 |
1 files changed, 68 insertions, 0 deletions
diff --git a/test/entity_tests.py b/test/entity_tests.py new file mode 100644 index 0000000..0e3daad --- /dev/null +++ b/test/entity_tests.py @@ -0,0 +1,68 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- + +import re +import os +import argparse +import sys +import platform +import html +from cmark import CMark + +def get_entities(): + regex = r'^{\(unsigned char\*\)"([^"]+)", \{([^}]+)\}' + with open(os.path.join(os.path.dirname(__file__), '..', 'src', 'entities.inc')) as f: + code = f.read() + entities = [] + for entity, utf8 in re.findall(regex, code, re.MULTILINE): + utf8 = bytes(map(int, utf8.split(", ")[:-1])).decode('utf-8') + entities.append((entity, utf8)) + return entities + +if __name__ == "__main__": + parser = argparse.ArgumentParser(description='Run cmark tests.') + parser.add_argument('--program', dest='program', nargs='?', default=None, + help='program to test') + parser.add_argument('--library-dir', dest='library_dir', nargs='?', + default=None, help='directory containing dynamic library') + args = parser.parse_args(sys.argv[1:]) + +cmark = CMark(prog=args.program, library_dir=args.library_dir) + +entities = get_entities() + +passed = 0 +errored = 0 +failed = 0 + +exceptions = { + 'quot': '"', + 'QUOT': '"', + + # These are broken, but I'm not too worried about them. + 'nvlt': '<⃒', + 'nvgt': '>⃒', +} + +print("Testing entities:") +for entity, utf8 in entities: + [rc, actual, err] = cmark.to_html("&{};".format(entity)) + check = exceptions.get(entity, utf8) + + if rc != 0: + errored += 1 + print(entity, '[ERRORED (return code {})]'.format(rc)) + print(err) + elif check in actual: + print(entity, '[PASSED]') + passed += 1 + else: + print(entity, '[FAILED]') + print(repr(actual)) + failed += 1 + +print("{} passed, {} failed, {} errored".format(passed, failed, errored)) +if failed == 0 and errored == 0: + exit(0) +else: + exit(1) |