def test_match_root_files(self):
basedirPath = 'root'
matchrules = []
matchrules.append(MatchRule(r'root\\[^\\]*match[^\\]*$'))
matchrules.append(
MatchRule(r'root\\[^\\]*doesnt[^\\]*$', polarity=False))
crawler = FilesystemCrawler(matchrules)
matchedPaths = crawler.search(basedirPath, True)
self.assertEqual(len(matchedPaths), 1)
self.assertEqual(matchedPaths[0][0], 'root\\match.txt')
def test_match_all_levels(self):
basedirPath = 'root'
matchrules = []
matchrules.append(MatchRule(r'root\\.*match[^\\]*$'))
matchrules.append(MatchRule(r'root\\.*doesnt[^\\]*$', polarity=False))
crawler = FilesystemCrawler(matchrules)
matchedPaths = crawler.search(basedirPath, True)
self.assertEqual(len(matchedPaths), 6)
for matchedPath in matchedPaths:
self.assertTrue('\\match.txt' in matchedPath[0])
def parse_match_rules(basedir, rawRules):
basedir = re.escape(basedir)
rules = []
errors = []
rawLines = None
rawLines = rawRules.splitlines()
for lineCount, rawLine in enumerate(rawLines):
rawLine = rawLine.strip()
# continue uppon comments or empty lines?
if not rawLine or rawLine[0] == '#':
continue
patternsLine, (isRegex, isNegated, filesOnly,
dirsOnly) = (_extract_flags_from_rawline(
rawLine, 'r', '!i', 'f', 'd'))
pathPattern, contentPattern = (
_extract_patterns_form_patters_line(patternsLine))
pathPattern = _path_pattern_to_regex(pathPattern, isRegex)
try:
rules.append(
MatchRule(basedir + pathPattern + '$', not isNegated, dirsOnly,
filesOnly, contentPattern))
except Exception as e:
errors.append((lineCount + 1, e))
return rules, errors
def test_match_callback(self):
basedirPath = 'root'
matchrules = []
matchrules.append(MatchRule(r'root\\[^\\]*match[^\\]*$'))
matchrules.append(
MatchRule(r'root\\[^\\]*doesnt[^\\]*$', polarity=False))
matchedCallbacks = []
def matchCallback(match):
matchedCallbacks.append(match[0])
crawler = FilesystemCrawler(matchrules, matchCallback=matchCallback)
matchedPaths = crawler.search(basedirPath, True)
self.assertEqual(len(matchedPaths), len(matchedCallbacks))
self.assertEqual(matchedCallbacks[0], 'root\\match.txt')
def test_parse_match_rules_from_file(self):
basedirPath = 'x:\\root'
expectedRules = []
expectedRules.append(MatchRule(r'x\:\\root\\[^\\]*match[^\\]*$'))
expectedRules.append(
MatchRule(r'x\:\\root\\[^\\]*doesnt[^\\]*$', polarity=False))
actualRules, actualErrors = parse_match_rules_from_file(
basedirPath, self.fileRulesName)
self.assertEqual(len(actualErrors), 0)
self.assertEqual(len(expectedRules), len(actualRules))
actualRulesPatterns = [str(p.pattern) for p in actualRules]
for expectedRule in expectedRules:
self.assertTrue(str(expectedRule.pattern) in actualRulesPatterns)
def test_match_files_with_content(self):
basedirPath = 'root'
matchrules = []
matchrules.append(
MatchRule(r'root\\[^\\]*$', contentPattern='matching text'))
crawler = FilesystemCrawler(matchrules)
matchedPaths = crawler.search(basedirPath, True)
self.assertEqual(len(matchedPaths), 1)
self.assertEqual(matchedPaths[0][0], 'root\\valid content.txt')