def consolicateSeriesToSingleDir():
print(
"Looking for series directories that can be flattened to a single dir")
idLut = nt.MtNamesMapWrapper("buId->fsName")
db = DbInterface()
for key, luDict in nt.dirNameProxy.iteritems():
# print("Key = ", key)
mId = db.getIdFromDirName(key)
# Skip cases where we have no match
if not mId:
continue
dups = set()
for name in idLut[mId]:
cName = nt.prepFilenameForMatching(name)
# Skip if it's one of the manga names that falls apart under the directory name cleaning mechanism
if not cName:
continue
if cName in nt.dirNameProxy:
dups.add(cName)
db.getIdFromDirName(cName)
if len(dups) > 1:
row = db.getRowByValue(buId=mId)
targetName = nt.prepFilenameForMatching(row["buName"])
dest = nt.dirNameProxy[targetName]
if luDict["dirKey"] != targetName and dest["fqPath"]:
print("baseName = ", row["buName"], ", id = ", mId,
", names = ", dups)
print(" URL: https://www.mangaupdates.com/series.html?id=%s" %
(mId, ))
print(" Dir 1 ", luDict["fqPath"])
print(" Dir 2 ", dest["fqPath"])
dirName = os.path.split(luDict["fqPath"])[-1]
dir2Name = os.path.split(dest["fqPath"])[-1]
print(" 1: ", dirName, ' ->',
nt.getCanonicalMangaUpdatesName(dirName))
print(" 2: ", dir2Name, ' ->',
nt.getCanonicalMangaUpdatesName(dir2Name))
print(" 1: ({num} items)".format(
num=len(os.listdir(luDict["fqPath"]))))
print(" 2: ({num} items)".format(
num=len(os.listdir(dest["fqPath"]))))
doMove = query_response(
"move files ('f' dir 1 -> dir 2. 'r' dir 2 -> dir 1. 'n' do not move)?"
)
if doMove == "forward":
moveFiles(luDict["fqPath"], dest["fqPath"])
os.rmdir(luDict["fqPath"])
elif doMove == "reverse":
moveFiles(dest["fqPath"], luDict["fqPath"])
os.rmdir(dest["fqPath"])
def consolicateSeriesToSingleDir():
print("Looking for series directories that can be flattened to a single dir")
idLut = nt.MtNamesMapWrapper("buId->fsName")
db = DbInterface()
for key, luDict in nt.dirNameProxy.iteritems():
# print("Key = ", key)
mId = db.getIdFromDirName(key)
# Skip cases where we have no match
if not mId:
continue
dups = set()
for name in idLut[mId]:
cName = nt.prepFilenameForMatching(name)
# Skip if it's one of the manga names that falls apart under the directory name cleaning mechanism
if not cName:
continue
if cName in nt.dirNameProxy:
dups.add(cName)
db.getIdFromDirName(cName)
if len(dups) > 1:
row = db.getRowByValue(buId=mId)
targetName = nt.prepFilenameForMatching(row["buName"])
dest = nt.dirNameProxy[targetName]
if luDict["dirKey"] != targetName and dest["fqPath"]:
print("baseName = ", row["buName"], ", id = ", mId, ", names = ", dups)
print(" URL: https://www.mangaupdates.com/series.html?id=%s" % (mId, ))
print(" Dir 1 ", luDict["fqPath"])
print(" Dir 2 ", dest["fqPath"])
dirName = os.path.split(luDict["fqPath"])[-1]
dir2Name = os.path.split(dest["fqPath"])[-1]
print(" 1: ", dirName, ' ->', nt.getCanonicalMangaUpdatesName(dirName))
print(" 2: ", dir2Name, ' ->', nt.getCanonicalMangaUpdatesName(dir2Name))
print(" 1: ({num} items)".format(num=len(os.listdir(luDict["fqPath"]))))
print(" 2: ({num} items)".format(num=len(os.listdir(dest["fqPath"]))))
doMove = query_response("move files ('f' dir 1 -> dir 2. 'r' dir 2 -> dir 1. 'n' do not move)?")
if doMove == "forward":
moveFiles(luDict["fqPath"], dest["fqPath"])
os.rmdir(luDict["fqPath"])
elif doMove == "reverse":
moveFiles(dest["fqPath"], luDict["fqPath"])
os.rmdir(dest["fqPath"])
def consolidateMangaFolders(dirPath, smartMode=True):
idLut = nt.MtNamesMapWrapper("fsName->buId")
pc = PathCleaner()
pc.openDB()
count = 0
print("Dir", dirPath)
items = os.listdir(dirPath)
items.sort()
for item in items:
item = os.path.join(dirPath, item)
if os.path.isdir(item):
fPath, dirName = os.path.split(item)
lookup = nt.dirNameProxy[dirName]
if lookup["fqPath"] != item:
print()
print()
print("------------------------------------------------------")
canonName = nt.getCanonicalMangaUpdatesName(dirName)
print("Duplicate Directory '%s' - Canon = '%s'" %
(dirName, canonName))
count += 1
mtId = idLut[nt.prepFilenameForMatching(dirName)]
for num in mtId:
print(
" URL: https://www.mangaupdates.com/series.html?id=%s"
% (num, ))
fPath, dir2Name = os.path.split(lookup["fqPath"])
if not os.path.exists(item):
print("'%s' has been removed. Skipping" % item)
continue
if not os.path.exists(lookup["fqPath"]):
print("'%s' has been removed. Skipping" % lookup["fqPath"])
continue
n1 = lv.distance(dirName, canonName)
n2 = lv.distance(dir2Name, canonName)
r1 = abs(nt.extractRatingToFloat(dirName))
r2 = abs(nt.extractRatingToFloat(dir2Name))
if "[complete]" in dirName.lower():
r1 += 0.1
if "[complete]" in dir2Name.lower():
r2 += 0.1
if "[wtf]" in dirName.lower():
r1 += 0.2
if "[wtf]" in dir2Name.lower():
r2 += 0.2
print(" 1: ", item)
print(" 2: ", lookup["fqPath"])
print(" 1: ", dirName, ' ->',
nt.getCanonicalMangaUpdatesName(dirName))
print(" 2: ", dir2Name, ' ->',
nt.getCanonicalMangaUpdatesName(dir2Name))
print(
" 1: ({num} items)(distance {dist})(rating {rat})".format(
num=len(os.listdir(item)), dist=n1, rat=r1))
print(
" 2: ({num} items)(distance {dist})(rating {rat})".format(
num=len(os.listdir(lookup["fqPath"])), dist=n2,
rat=r2))
mtId2 = idLut[nt.prepFilenameForMatching(dir2Name)]
if mtId != mtId2:
print("DISCORDANT ID NUMBERS - {num1}, {num2}!".format(
num1=mtId, num2=mtId2))
for num in mtId2:
print(
" URL: https://www.mangaupdates.com/series.html?id=%s"
% (num, ))
continue
if r1 > r2:
doMove = "reverse"
elif r2 > r1:
doMove = "forward"
else:
doMove = ''
if not doMove or not smartMode:
doMove = query_response(
"move files ('f' dir 1 -> dir 2. 'r' dir 1 <- dir 2. 'l' use levenshtein distance. 'n' do not move)?"
)
if doMove == "forward":
print("Forward move")
fromDir = item
toDir = lookup["fqPath"]
elif doMove == "reverse":
print("Reverse move")
fromDir = lookup["fqPath"]
toDir = item
elif doMove == "levenshtein":
print("Levenshtein distance chooser")
# I'm using less then or equal, so situations where
# both names are equadistant get aggregated anyways.
if n1 <= n2:
fromDir = lookup["fqPath"]
toDir = item
else:
fromDir = item
toDir = lookup["fqPath"]
else:
print("Skipping")
continue
print("moving from: '%s' " % fromDir)
print(" to: '%s' " % toDir)
items = os.listdir(fromDir)
for item in items:
fromPath = os.path.join(fromDir, item)
toPath = os.path.join(toDir, item)
loop = 2
while os.path.exists(toPath):
pathBase, ext = os.path.splitext(toPath)
print(" Duplicate file!")
toPath = "{start} ({loop}){ext}".format(start=pathBase,
loop=loop,
ext=ext)
print(" Moving: ", item)
print(" From: ", fromPath)
print(" To: ", toPath)
pc.moveFile(fromPath, toPath)
try:
pc.moveFile(fromPath, toPath)
except psycopg2.IntegrityError:
print("Error moving item in dedup database")
# pc.deletePath(toPath)
shutil.move(fromPath, toPath)
print("Deleting directory")
os.rmdir(fromDir)
print("total items", count)
def consolidateMangaFolders(dirPath, smartMode=True):
idLut = nt.MtNamesMapWrapper("fsName->buId")
pc = PathCleaner()
count = 0
print("Dir", dirPath)
items = os.listdir(dirPath)
items.sort()
for item in items:
item = os.path.join(dirPath, item)
if os.path.isdir(item):
fPath, dirName = os.path.split(item)
lookup = nt.dirNameProxy[dirName]
if lookup["fqPath"] != item:
print()
print()
print("------------------------------------------------------")
canonName = nt.getCanonicalMangaUpdatesName(dirName)
print("Duplicate Directory '%s' - Canon = '%s'" % (dirName, canonName))
count += 1
mtId = idLut[nt.prepFilenameForMatching(dirName)]
for num in mtId:
print(" URL: https://www.mangaupdates.com/series.html?id=%s" % (num, ))
fPath, dir2Name = os.path.split(lookup["fqPath"])
if not os.path.exists(item):
print("'%s' has been removed. Skipping" % item)
continue
if not os.path.exists(lookup["fqPath"]):
print("'%s' has been removed. Skipping" % lookup["fqPath"])
continue
n1 = lv.distance(dirName, canonName)
n2 = lv.distance(dir2Name, canonName)
r1 = abs(nt.extractRatingToFloat(dirName))
r2 = abs(nt.extractRatingToFloat(dir2Name))
if "[complete]" in dirName.lower():
r1 += 0.1
if "[complete]" in dir2Name.lower():
r2 += 0.1
if "[wtf]" in dirName.lower():
r1 += 0.2
if "[wtf]" in dir2Name.lower():
r2 += 0.2
print(" 1: ", item)
print(" 2: ", lookup["fqPath"])
print(" 1: ", dirName, ' ->', nt.getCanonicalMangaUpdatesName(dirName))
print(" 2: ", dir2Name, ' ->', nt.getCanonicalMangaUpdatesName(dir2Name))
print(" 1: ({num} items)(distance {dist})(rating {rat})".format(num=len(os.listdir(item)), dist=n1, rat=r1))
print(" 2: ({num} items)(distance {dist})(rating {rat})".format(num=len(os.listdir(lookup["fqPath"])), dist=n2, rat=r2))
mtId2 = idLut[nt.prepFilenameForMatching(dir2Name)]
if mtId != mtId2:
print("DISCORDANT ID NUMBERS - {num1}, {num2}!".format(num1=mtId, num2=mtId2))
for num in mtId2:
print(" URL: https://www.mangaupdates.com/series.html?id=%s" % (num, ))
continue
if r1 > r2:
doMove = "reverse"
elif r2 > r1:
doMove = "forward"
else:
doMove = ''
if not doMove or not smartMode:
doMove = query_response("move files ('f' dir 1 -> dir 2. 'r' dir 1 <- dir 2. 'l' use levenshtein distance. 'n' do not move)?")
if doMove == "forward":
print("Forward move")
fromDir = item
toDir = lookup["fqPath"]
elif doMove == "reverse":
print("Reverse move")
fromDir = lookup["fqPath"]
toDir = item
elif doMove == "levenshtein":
print("Levenshtein distance chooser")
# I'm using less then or equal, so situations where
# both names are equadistant get aggregated anyways.
if n1 <= n2:
fromDir = lookup["fqPath"]
toDir = item
else:
fromDir = item
toDir = lookup["fqPath"]
else:
print("Skipping")
continue
print("moving from: '%s' " % fromDir)
print(" to: '%s' " % toDir)
items = os.listdir(fromDir)
for item in items:
fromPath = os.path.join(fromDir, item)
toPath = os.path.join(toDir, item)
loop = 2
while os.path.exists(toPath):
pathBase, ext = os.path.splitext(toPath)
print(" Duplicate file!")
toPath = "{start} ({loop}){ext}".format(start=pathBase, loop=loop, ext=ext)
print(" Moving: ", item)
print(" From: ", fromPath)
print(" To: ", toPath)
pc.moveFile(fromPath, toPath)
try:
pc.moveFile(fromPath, toPath)
except psycopg2.IntegrityError:
print("Error moving item in dedup database")
# pc.deletePath(toPath)
shutil.move(fromPath, toPath)
print("Deleting directory")
os.rmdir(fromDir)
print("total items", count)
