md4c

C Markdown parser. Fast. SAX-like interface. Compliant to CommonMark specification.
git clone https://noulin.net/git/md4c.git
Log | Files | Refs | README | LICENSE

spec_tests.py (5865B)


      1 #!/usr/bin/env python3
      2 # -*- coding: utf-8 -*-
      3 
      4 import sys
      5 from difflib import unified_diff
      6 import argparse
      7 import re
      8 import json
      9 from cmark import CMark
     10 from normalize import normalize_html
     11 
     12 if __name__ == "__main__":
     13     parser = argparse.ArgumentParser(description='Run cmark tests.')
     14     parser.add_argument('-p', '--program', dest='program', nargs='?', default=None,
     15             help='program to test')
     16     parser.add_argument('-s', '--spec', dest='spec', nargs='?', default='spec.txt',
     17             help='path to spec')
     18     parser.add_argument('-P', '--pattern', dest='pattern', nargs='?',
     19             default=None, help='limit to sections matching regex pattern')
     20     parser.add_argument('--library-dir', dest='library_dir', nargs='?',
     21             default=None, help='directory containing dynamic library')
     22     parser.add_argument('--no-normalize', dest='normalize',
     23             action='store_const', const=False, default=True,
     24             help='do not normalize HTML')
     25     parser.add_argument('-d', '--dump-tests', dest='dump_tests',
     26             action='store_const', const=True, default=False,
     27             help='dump tests in JSON format')
     28     parser.add_argument('--debug-normalization', dest='debug_normalization',
     29             action='store_const', const=True,
     30             default=False, help='filter stdin through normalizer for testing')
     31     parser.add_argument('-n', '--number', type=int, default=None,
     32             help='only consider the test with the given number')
     33     args = parser.parse_args(sys.argv[1:])
     34 
     35 def out(str):
     36     sys.stdout.buffer.write(str.encode('utf-8')) 
     37 
     38 def print_test_header(headertext, example_number, start_line, end_line):
     39     out("Example %d (lines %d-%d) %s\n" % (example_number,start_line,end_line,headertext))
     40 
     41 def do_test(test, normalize, result_counts):
     42     [retcode, actual_html, err] = cmark.to_html(test['markdown'])
     43     if retcode == 0:
     44         expected_html = test['html']
     45         unicode_error = None
     46         if normalize:
     47             try:
     48                 passed = normalize_html(actual_html) == normalize_html(expected_html)
     49             except UnicodeDecodeError as e:
     50                 unicode_error = e
     51                 passed = False
     52         else:
     53             passed = actual_html == expected_html
     54         if passed:
     55             result_counts['pass'] += 1
     56         else:
     57             print_test_header(test['section'], test['example'], test['start_line'], test['end_line'])
     58             out(test['markdown'] + '\n')
     59             if unicode_error:
     60                 out("Unicode error: " + str(unicode_error) + '\n')
     61                 out("Expected: " + repr(expected_html) + '\n')
     62                 out("Got:      " + repr(actual_html) + '\n')
     63             else:
     64                 expected_html_lines = expected_html.splitlines(True)
     65                 actual_html_lines = actual_html.splitlines(True)
     66                 for diffline in unified_diff(expected_html_lines, actual_html_lines,
     67                                 "expected HTML", "actual HTML"):
     68                     out(diffline)
     69             out('\n')
     70             result_counts['fail'] += 1
     71     else:
     72         print_test_header(test['section'], test['example'], test['start_line'], test['end_line'])
     73         out("program returned error code %d\n" % retcode)
     74         sys.stdout.buffer.write(err)
     75         result_counts['error'] += 1
     76 
     77 def get_tests(specfile):
     78     line_number = 0
     79     start_line = 0
     80     end_line = 0
     81     example_number = 0
     82     markdown_lines = []
     83     html_lines = []
     84     state = 0  # 0 regular text, 1 markdown example, 2 html output
     85     headertext = ''
     86     tests = []
     87 
     88     header_re = re.compile('#+ ')
     89 
     90     with open(specfile, 'r', encoding='utf-8', newline='\n') as specf:
     91         for line in specf:
     92             line_number = line_number + 1
     93             l = line.strip()
     94             if l == "`" * 32 + " example":
     95                 state = 1
     96             elif state == 2 and l == "`" * 32:
     97                 state = 0
     98                 example_number = example_number + 1
     99                 end_line = line_number
    100                 tests.append({
    101                     "markdown":''.join(markdown_lines).replace('→',"\t"),
    102                     "html":''.join(html_lines).replace('→',"\t"),
    103                     "example": example_number,
    104                     "start_line": start_line,
    105                     "end_line": end_line,
    106                     "section": headertext})
    107                 start_line = 0
    108                 markdown_lines = []
    109                 html_lines = []
    110             elif l == ".":
    111                 state = 2
    112             elif state == 1:
    113                 if start_line == 0:
    114                     start_line = line_number - 1
    115                 markdown_lines.append(line)
    116             elif state == 2:
    117                 html_lines.append(line)
    118             elif state == 0 and re.match(header_re, line):
    119                 headertext = header_re.sub('', line).strip()
    120     return tests
    121 
    122 if __name__ == "__main__":
    123     if args.debug_normalization:
    124         out(normalize_html(sys.stdin.read()))
    125         exit(0)
    126 
    127     all_tests = get_tests(args.spec)
    128     if args.pattern:
    129         pattern_re = re.compile(args.pattern, re.IGNORECASE)
    130     else:
    131         pattern_re = re.compile('.')
    132     tests = [ test for test in all_tests if re.search(pattern_re, test['section']) and (not args.number or test['example'] == args.number) ]
    133     if args.dump_tests:
    134         out(json.dumps(tests, ensure_ascii=False, indent=2))
    135         exit(0)
    136     else:
    137         skipped = len(all_tests) - len(tests)
    138         cmark = CMark(prog=args.program, library_dir=args.library_dir)
    139         result_counts = {'pass': 0, 'fail': 0, 'error': 0, 'skip': skipped}
    140         for test in tests:
    141             do_test(test, args.normalize, result_counts)
    142         out("{pass} passed, {fail} failed, {error} errored, {skip} skipped\n".format(**result_counts))
    143         exit(result_counts['fail'] + result_counts['error'])