Fixed CBR parsing anomalies (close #133)

kcc/cbxarchive.py

@@ -22,6 +22,7 @@ from zipfile import is_zipfile, ZipFile
 from subprocess import STDOUT, PIPE
 from psutil import Popen
 from shutil import move, copy
+from scandir import walk
 from . import rarfile
 from .shared import check7ZFile as is_7zfile, saferReplace
 
@@ -45,7 +46,7 @@ class CBxArchive:
         cbzFile = ZipFile(self.origFileName)
         filelist = []
         for f in cbzFile.namelist():
-            if f.startswith('__MACOSX') or f.endswith('.DS_Store') or f.endswith('thumbs.db'):
+            if f.startswith('__MACOSX') or f.endswith('.DS_Store') or f.endswith('humbs.db'):
                 pass    # skip MacOS special files
             elif f.endswith('/'):
                 try:
@@ -58,25 +59,18 @@ class CBxArchive:
 
     def extractCBR(self, targetdir):
         cbrFile = rarfile.RarFile(self.origFileName)
-        filelist = []
-        for f in cbrFile.namelist():
-            if f.startswith('__MACOSX') or f.endswith('.DS_Store') or f.endswith('thumbs.db'):
-                pass  # skip MacOS special files
-            elif f.endswith('/'):
-                try:
-                    os.makedirs(os.path.join(targetdir, f))
-                except Exception:
-                    pass  # the dir exists so we are going to extract the images only.
-            else:
-                filelist.append(f)
-        cbrFile.extractall(targetdir, filelist)
+        cbrFile.extractall(targetdir)
+        for root, dirnames, filenames in walk(targetdir):
+            for filename in filenames:
+                if filename.startswith('__MACOSX') or filename.endswith('.DS_Store') or filename.endswith('humbs.db'):
+                    os.remove(os.path.join(root, filename))
 
     def extractCB7(self, targetdir):
         # Workaround for some wide UTF-8 + Popen abnormalities
         if sys.platform.startswith('darwin'):
             copy(self.origFileName, os.path.join(os.path.dirname(self.origFileName), 'TMP_KCC_TMP'))
             self.origFileName = os.path.join(os.path.dirname(self.origFileName), 'TMP_KCC_TMP')
-        output = Popen('7za x "' + self.origFileName + '" -xr!__MACOSX -xr!.DS_Store -xr!thumbs.db -o"'
+        output = Popen('7za x "' + self.origFileName + '" -xr!__MACOSX -xr!.DS_Store -xr!thumbs.db -xr!Thumbs.db -o"'
                        + targetdir + '"', stdout=PIPE, stderr=STDOUT, shell=True)
         extracted = False
         for line in output.stdout:

kcc/comic2ebook.py

@@ -579,7 +579,7 @@ def getWorkFolder(afile):
     if len(afile) > 240:
         raise UserWarning("Path is too long.")
     if os.path.isdir(afile):
-        workdir = mkdtemp('', 'KCC-TMP-')
+        workdir = mkdtemp('', 'KCC-')
         try:
             os.rmdir(workdir)
             fullPath = os.path.join(workdir, 'OEBPS', 'Images')
@@ -598,7 +598,7 @@ def getWorkFolder(afile):
             rmtree(path, True)
             raise UserWarning("Failed to extract images.")
     else:
-        workdir = mkdtemp('', 'KCC-TMP-')
+        workdir = mkdtemp('', 'KCC-')
         cbx = cbxarchive.CBxArchive(afile)
         if cbx.isCbxFile():
             try:
@@ -935,7 +935,7 @@ def detectMargins(path):
 
 
 def createNewTome():
-    tomePathRoot = mkdtemp('', 'KCC-TMP-')
+    tomePathRoot = mkdtemp('', 'KCC-')
     tomePath = os.path.join(tomePathRoot, 'OEBPS', 'Images')
     os.makedirs(tomePath)
     return tomePath, tomePathRoot

kcc/metadata.py

@@ -64,7 +64,7 @@ class MetadataParser:
                             self.rawdata = parse(xml_file)
             elif is_7zfile(self.source):
                 self.compressor = '7z'
-                workdir = mkdtemp('', 'KCC-TMP-')
+                workdir = mkdtemp('', 'KCC-')
                 tmpXML = os.path.join(workdir, 'ComicInfo.xml')
                 output = Popen('7za e "' + self.source + '" ComicInfo.xml -o"' + workdir + '"',
                                stdout=PIPE, stderr=STDOUT, shell=True)
@@ -147,7 +147,7 @@ class MetadataParser:
             with open(self.source, 'w', encoding='utf-8') as f:
                 self.rawdata.writexml(f, encoding='utf-8')
         else:
-            workdir = mkdtemp('', 'KCC-TMP-')
+            workdir = mkdtemp('', 'KCC-')
             tmpXML = os.path.join(workdir, 'ComicInfo.xml')
             with open(tmpXML, 'w', encoding='utf-8') as f:
                 self.rawdata.writexml(f, encoding='utf-8')

kcc/pdfjpgextract.py

@@ -29,7 +29,7 @@ class PdfJpgExtract:
         self.origFileName = origFileName
         self.filename = os.path.splitext(origFileName)
         # noinspection PyUnusedLocal
-        self.path = self.filename[0] + "-KCC-TMP-" + ''.join(choice(ascii_uppercase + digits) for x in range(3))
+        self.path = self.filename[0] + "-KCC-" + ''.join(choice(ascii_uppercase + digits) for x in range(3))
 
     def getPath(self):
         return self.path

kcc/shared.py

@@ -104,9 +104,9 @@ def saferReplace(old, new):
 
 
 def removeFromZIP(zipfname, *filenames):
-    tempdir = mkdtemp('', 'KCC-TMP-')
+    tempdir = mkdtemp('', 'KCC-')
     try:
-        tempname = os.path.join(tempdir, 'KCC-TMP.zip')
+        tempname = os.path.join(tempdir, 'KCC.zip')
         with ZipFile(zipfname, 'r') as zipread:
             with ZipFile(tempname, 'w', compression=ZIP_DEFLATED) as zipwrite:
                 for item in zipread.infolist():