def replace_date_values(string):
string = Regex.Replace(string, r"(?<=/)\d+(?=/)", r"(?<=/)\d+(?=/)",
RegexOptions.IgnoreCase)
string = Regex.Replace(
string,
r"(?<=/)(?:jan(?:uary)?|feb(?:ruary)?|mar(?:ch)?|apr(?:il)?|may|june?|july?|aug(?:ust)?|sep(?:tember)?|oct(?:ober)?|nov(?:ember)?|dec(?:ember)?)(?=/)",
r"(?<=/)(?:jan(?:uary)?|feb(?:ruary)?|mar(?:ch)?|apr(?:il)?|may|june?|july?|aug(?:ust)?|sep(?:tember)?|oct(?:ober)?|nov(?:ember)?|dec(?:ember)?)(?=/)",
RegexOptions.IgnoreCase)
return string
def regexReplace(self, myString, myVals):
'''
todo: this *might* work!
'''
#myString = 'der Hugo'
#oldVal = r'\w*'
#newVal = r'$&$&'
regexp = Regex(myVals[0],
RegexOptions.IgnoreCase | RegexOptions.Singleline)
return regexp.Replace(myString, myVals[1])
def onSave():
try:
fs = None
sr = None
sw = None
try:
fs = FileStream(__file__, FileMode.Open,
FileAccess.ReadWrite,
FileShare.Read)
encoding = UTF8Encoding(False)
sr = StreamReader(fs, encoding, True)
lines = Regex.Replace(
Regex.Replace(
sr.ReadToEnd(), "username\\s*=\\s*\"\"",
String.Format("username = \"{0}\"",
username),
RegexOptions.CultureInvariant),
"password\\s*=\\s*\"\"",
String.Format("password = \"{0}\"", password),
RegexOptions.CultureInvariant)
fs.SetLength(0)
sw = StreamWriter(fs, encoding)
sw.Write(lines)
finally:
if sw is not None:
sw.Close()
if sr is not None:
sr.Close()
if fs is not None:
fs.Close()
except Exception, e:
Trace.WriteLine(e.clsException.Message)
Trace.WriteLine(e.clsException.StackTrace)
def FindScanners(worker, books):
#Load the various settings. settings is a dict
settings = LoadSettings()
#Load the scanners
unformatedscanners = LoadListFromFile(SCANNERSFILE)
#Sort the scanners by length and reverse it. For example cl will come after clickwheel allowing them to be matched correctly.
unformatedscanners.sort(key=len, reverse=True)
#Format the scanners for use in the regex
scanners = "|".join(unformatedscanners)
scanners = "(?<Tags>" + scanners + ")"
#Load the blacklist and format it
blacklist = LoadListFromFile(BLACKLISTFILE)
blacklist.extend(LoadUserBlackListFromFile(USERBLACKLISTFILE))
formatedblacklist = "|".join(blacklist)
#Add in the blacklist
#These amazing regex are designed by the amazing Helmic.
pattern = r"(?:(?:__(?!.*__[^_]))|[(\[])(?!(?:" + formatedblacklist + r"|[\s_\-\|/,])+[)\]])(?<Tags>(?=[^()\[\]]*[^()\[\]\W\d_])[^()\[\]]{2,})[)\]]?"
replacePattern = r"(?:[^\w]|_|^)(?:" + formatedblacklist + r")(?:[^\w]|_|$)"
#Create the regex
regex = Regex(pattern, RegexOptions.IgnoreCase)
regexScanners = Regex(scanners, RegexOptions.IgnoreCase)
regexReplace = Regex(replacePattern, RegexOptions.IgnoreCase)
ComicBookFields = ComicRack.App.GetComicFields()
ComicBookFields.Remove("Scan Information")
ComicBookFields.Add("Language", "LanguageAsText")
for book in books:
#.net Regex
#Note that every possible match is found and then the last one is used.
#This is because in some rare cases more than one thing is mistakenly matched and the scanner is almost always the last match.
matches = regex.Matches(book.FileName)
unknowntag = ""
try:
match = matches[matches.Count - 1]
except ValueError:
#No match
#print "Trying the Scanners.txt list"
#Check the defined scanner names
match = regexScanners.Match(book.FileName)
#Still no match
if match.Success == False:
if settings["Unknown"] != "":
unknowntag = settings["Unknown"]
else:
continue
#Check if what was grabbed is a field in the comic
fields = []
for field in ComicBookFields.Values:
fields.append(unicode(getattr(book, field)).lower())
if match.Groups["Tags"].Value.lower() in fields:
print "Uh oh. That matched tag is in the info somewhere."
newmatch = False
for n in reversed(range(0, matches.Count - 1)):
if not matches[n].Groups["Tags"].Value.lower() in fields:
match = matches[n]
newmatch = True
break
if newmatch == False:
if settings["Unknown"] != "":
unknowntag = settings["Unknown"]
else:
continue
#Check if the match can be found in () in the series, title or altseries
titlefields = [
book.ShadowSeries, book.ShadowTitle, book.AlternateSeries
]
abort = False
for title in titlefields:
titleresult = re.search("\((?P<match>.*)\)", title)
if titleresult != None and titleresult.group(
"match").lower() == match.Groups["Tags"].Value.lower():
#The match is part of the title, series or altseries so skip it
print "The match is part of the title, series or altseries"
abort = True
break
if abort == True:
if settings["Unknown"] != "":
unknowntag = settings["Unknown"]
else:
continue
#Get a list of the old ScanInformation
oldtags = book.ScanInformation
ListOfTagsTemp = oldtags.split(",")
if '' in ListOfTagsTemp:
ListOfTagsTemp.remove('')
ListOfTags = []
if ListOfTagsTemp != []:
for indtag in ListOfTagsTemp:
ListOfTags.append(indtag.strip())
#Create our new tag
if unknowntag != "":
newtag = settings["Prefix"] + unknowntag
else:
newtag = settings["Prefix"] + regexReplace.Replace(
match.Groups["Tags"].Value.strip("_, "), "")
if newtag not in ListOfTags:
ListOfTags.append(newtag)
#Sort alphabeticaly to be neat
ListOfTags.sort()
#Add to ScanInformation field
book.ScanInformation = ", ".join(ListOfTags)
def create_image_regex(first_image_url, second_image_url):
if debug:
print "Starting to create an image regex with urls:\n" + first_image_url + "\n" + second_image_url
base = get_string_intersect(first_image_url, second_image_url)
baseuri = Uri(base)
relativeuri = first_page_uri.MakeRelativeUri(baseuri)
if relativeuri.IsAbsoluteUri:
domain = relativeuri.Scheme + "://" + relativeuri.Host
relative = relativeuri.AbsolutePath
else:
domain = baseuri.Scheme + "://" + baseuri.Host
relative = relativeuri.OriginalString
domain = escape_regex_characters(domain)
relative = relative.lstrip("/")
relative = escape_regex_characters(relative)
relative = replace_date_values(relative)
domain = Regex.Replace(domain, "www\\\\.", "(?:www\\.)?",
RegexOptions.IgnoreCase)
baseregex = "(?:" + domain + ")?\\.*/?" + relative
if debug: print "baseregex is: " + baseregex
regex = "src\\s*=\\s*(?([\"'])[\"'](?<link>" + baseregex + "[^\"']+)[\"']|(?<link>" + baseregex + "[^\\s<>]+))"
result, matches = check_created_image_regex(first_image_url,
second_image_url, regex)
if not result:
regex = "(?([\"'])[\"'](?<link>" + baseregex + "[^\"']+)[\"']|(?<link>" + baseregex + "[^\\s<>]+))"
result, matches = check_created_image_regex(first_image_url,
second_image_url, regex)
if not result:
#Sometimes the relative link creator makes a bad split, in that case try one other way:
#Check if we made the split before:
if baseuri.Host == first_page_uri.Host:
domain = baseuri.Scheme + "://" + baseuri.Host
relative = baseuri.AbsolutePath
relative = relative.lstrip("/")
domain = escape_regex_characters(domain)
relative = escape_regex_characters(relative)
relative = replace_date_values(relative)
domain = Regex.Replace(domain, "www\\\\.", "(?:www\\.)?",
RegexOptions.IgnoreCase)
baseregex = "(?:" + domain + ")?\\.*/?" + relative
if debug: print "baseregex is: " + baseregex
regex = "src\\s*=\\s*(?([\"'])[\"'](?<link>" + baseregex + "[^\"']+)[\"']|(?<link>" + baseregex + "[^\\s<>]+))"
result, matches = check_created_image_regex(
first_image_url, second_image_url, regex)
if not result:
regex = "(?([\"'])[\"'](?<link>" + baseregex + "[^\"']+)[\"']|(?<link>" + baseregex + "[^\\s<>]+))"
result, matches = check_created_image_regex(
first_image_url, second_image_url, regex)
if not result:
if debug: print "Unable create a working image regex"
return None
if debug: print "Found a working image regex: " + regex
imgregex = ImageRegex(regex)
imgregex._matches = matches
return imgregex