Replace SOPDS_FB2PARSE to SOPDS_FB2SAX setting

book_tools/LICENSE

-The MIT License (MIT)
-
-Copyright (c) 2014 FBReader.ORG Limited
-
-Permission is hereby granted, free of charge, to any person obtaining a copy
-of this software and associated documentation files (the "Software"), to deal
-in the Software without restriction, including without limitation the rights
-to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
-copies of the Software, and to permit persons to whom the Software is
-furnished to do so, subject to the following conditions:
-
-The above copyright notice and this permission notice shall be included in all
-copies or substantial portions of the Software.
-
-THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
-IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
-FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
-AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
-LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
-OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
-SOFTWARE.
-

book_tools/format/__init__.py

@@ -11,15 +11,9 @@ from book_tools.format.epub import EPub
 from book_tools.format.fb2 import FB2, FB2Zip
 from book_tools.format.fb2sax import FB2sax
 from book_tools.format.other import Dummy
-#from fbreader.format.pdf import PDF
-#from fbreader.format.msword import MSWord
 from book_tools.format.mobi import Mobipocket
-#from fbreader.format.rtf import RTF
-#from fbreader.format.djvu import DjVu
-#from fbreader.format.dummy import Dummy
 
-#__detector = magic.open(magic.MAGIC_MIME_TYPE)
-#__detector.load()
+from constance import config
 
 class __detector:
     @staticmethod
@@ -83,8 +77,7 @@ def create_bookfile(file, original_filename):
     if mimetype == Mimetype.EPUB:
         return EPub(file, original_filename)
     elif mimetype == Mimetype.FB2:
-        #return FB2(file, original_filename)
-        return FB2sax(file, original_filename)
+        return FB2sax(file, original_filename) if config.SOPDS_FB2SAX else FB2(file, original_filename)
     elif mimetype == Mimetype.FB2_ZIP:
         return FB2Zip(file, original_filename)
     elif mimetype == Mimetype.MOBI:

book_tools/format/aes.py

-import gzip, os
+#import gzip, os
 #from Crypto.Cipher import AES
-from tempfile import mktemp
+#from tempfile import mktemp
 
 def encrypt(file_name, key, working_dir):
     '''

book_tools/format/util.py

 #import PythonMagick
-from PIL import Image, ImageFile
+#from PIL import Image, ImageFile
 
 strip_symbols = ' »«\'\"\&\n-.#\\\`'
 

opds_catalog/sopdscan.py

@@ -48,10 +48,12 @@ class opdsScanner:
     def log_options(self):
         self.logger.info(' ***** Starting sopds-scan...')
         self.logger.debug('OPTIONS SET')
-        if config.SOPDS_ROOT_LIB!=None:       self.logger.debug('root_lib = '+config.SOPDS_ROOT_LIB)
-        if config.SOPDS_FB2TOEPUB!=None: self.logger.debug('fb2toepub = '+config.SOPDS_FB2TOEPUB)
-        if config.SOPDS_FB2TOMOBI!=None: self.logger.debug('fb2tomobi = '+config.SOPDS_FB2TOMOBI)
-        if config.SOPDS_TEMP_DIR!=None:       self.logger.debug('temp_dir = '+config.SOPDS_TEMP_DIR)
+        if config.SOPDS_ROOT_LIB!=None:       self.logger.debug('root_lib = %s'%config.SOPDS_ROOT_LIB)
+        if config.SOPDS_FB2TOEPUB!=None: self.logger.debug('fb2toepub = %s'%config.SOPDS_FB2TOEPUB)
+        if config.SOPDS_FB2TOMOBI!=None: self.logger.debug('fb2tomobi = %s'%config.SOPDS_FB2TOMOBI)
+        if config.SOPDS_TEMP_DIR!=None:       self.logger.debug('temp_dir = %s'%config.SOPDS_TEMP_DIR)
+        if config.SOPDS_FB2SAX != None:       self.logger.debug('FB2SAX = %s'%config.SOPDS_FB2SAX)
+
 
     def log_stats(self):
         self.t2=datetime.timedelta(seconds=time.time())
@@ -195,7 +197,6 @@ class opdsScanner:
                 zip_process_error = 1
             self.bad_archives+=zip_process_error
 
-    # Новая версия (0.42) процедуры извлечения метаданных из файлов книг fb2, epub, mobi
     def processfile(self,name,full_path,file,cat,archive=0,file_size=0):
         (n, e) = os.path.splitext(name)
         if e.lower() in config.SOPDS_BOOK_EXTENSIONS.split():
@@ -246,76 +247,3 @@ class opdsScanner:
             else:
                 self.books_skipped+=1
                 self.logger.debug("Book "+rel_path+"/"+name+" Already in DB.")
-
-    # Старая версия (до 0.41) процедуры извлечения метаданных из файлов книг только fb2
-    def processfile0(self,name,full_path,file,cat,archive=0,file_size=0):
-        (n,e)=os.path.splitext(name)
-        if e.lower() in config.SOPDS_BOOK_EXTENSIONS.split():
-            rel_path=os.path.relpath(full_path,config.SOPDS_ROOT_LIB)
-            self.logger.debug("Attempt to add book "+rel_path+"/"+name)
-            self.fb2parser.reset()
-            if opdsdb.findbook(name,rel_path,1)==None:
-                if archive==0:
-                    cat=opdsdb.addcattree(rel_path,archive)
-                title=''
-                lang=''
-                annotation=''
-                docdate=''
-                book_is_valid = True
-
-                if e.lower()=='.fb2' and config.SOPDS_FB2PARSE:
-                    if isinstance(file, str):
-                        f=open(file,'rb')
-                    else:
-                        f=file
-                    self.fb2parser.parse(f)
-                    f.close()
-
-                    if len(self.fb2parser.lang.getvalue())>0:
-                        lang=self.fb2parser.lang.getvalue()[0].strip(strip_symbols)
-                    if len(self.fb2parser.book_title.getvalue())>0:
-                        title=self.fb2parser.book_title.getvalue()[0].strip(strip_symbols)
-                    if len(self.fb2parser.annotation.getvalue())>0:
-                        annotation=('\n'.join(self.fb2parser.annotation.getvalue()))
-                    if len(self.fb2parser.docdate.getvalue())>0:
-                        docdate=self.fb2parser.docdate.getvalue()[0].strip();
-
-                    if self.fb2parser.parse_error!=0:
-                        errormsg=''
-                        self.logger.warning(rel_path+' - '+name+' fb2 parse error ['+errormsg+']')
-                        book_is_valid = False
-                        self.bad_books+=1
-
-                if book_is_valid:
-                    if title=='': title=n
-
-                    book=opdsdb.addbook(name,rel_path,cat,e[1:],title,annotation,docdate,lang,file_size,archive)
-                    self.books_added+=1
-
-                    if archive!=0:
-                        self.books_in_archives+=1
-                    self.logger.debug("Book "+rel_path+"/"+name+" Added ok.")
-
-                    idx=0
-                    for l in self.fb2parser.author_last.getvalue():
-                        last_name=l.strip(strip_symbols)
-                        first_name=self.fb2parser.author_first.getvalue()[idx].strip(strip_symbols)
-                        #author=opdsdb.addauthor(first_name,last_name)
-                        author=opdsdb.addauthor("%s %s"%(last_name,first_name))
-                        opdsdb.addbauthor(book,author)
-                        idx+=1
-                    for l in self.fb2parser.genre.getvalue():
-                        opdsdb.addbgenre(book,opdsdb.addgenre(l.lower().strip(strip_symbols)))
-                    for l in self.fb2parser.series.attrss:
-                        ser_name=l.get('name')
-                        if ser_name:
-                            ser=opdsdb.addseries(ser_name.strip())
-                            sser_no=l.get('number','0').strip()
-                            if sser_no.isdigit():
-                                ser_no=int(sser_no)
-                            else:
-                                ser_no=0
-                            opdsdb.addbseries(book,ser,ser_no)
-            else:
-                self.books_skipped+=1
-                self.logger.debug("Book "+rel_path+"/"+name+" Already in DB.")

sopds/settings.py

@@ -177,7 +177,7 @@ CONSTANCE_CONFIG = OrderedDict([
     ('SOPDS_NOCOVER_PATH', (os.path.join(BASE_DIR,'static/images/nocover.jpg'),_('Path to image file showing for book without embedded cover'))),    
         
     
-    ('SOPDS_FB2PARSE', (True,_('This flag activate extraction metadata from fb2 files'))),
+    ('SOPDS_FB2SAX', (True,_('This flag activate SAX Parser for FB2 instead of lxml.xpath'))),
     ('SOPDS_ZIPSCAN', (True,_('This flag activate zip files scanning'))),
     ('SOPDS_ZIPCODEPAGE', ('cp866',_('Set codepage for filenames inside zipfile'))),
     ('SOPDS_INPX_ENABLE', (False,_('Enables read metadata from inpx-file (and stop scanning deeper from ipx-file place)'))),
@@ -205,7 +205,7 @@ CONSTANCE_CONFIG = OrderedDict([
 CONSTANCE_CONFIG_FIELDSETS = {
     '1. General Options': ('SOPDS_LANGUAGE', 'SOPDS_ROOT_LIB', 'SOPDS_BOOK_EXTENSIONS','SOPDS_SCAN_START_DIRECTLY'),
     '2. Server Options': ('SOPDS_AUTH', 'SOPDS_ALPHABET_MENU', 'SOPDS_DOUBLES_HIDE', 'SOPDS_COVER_SHOW', 'SOPDS_SPLITITEMS', 'SOPDS_MAXITEMS', 'SOPDS_TITLE_AS_FILENAME', 'SOPDS_NOCOVER_PATH'),    
-    '3. Scanner Options': ('SOPDS_FB2PARSE','SOPDS_ZIPSCAN','SOPDS_ZIPCODEPAGE', 'SOPDS_INPX_ENABLE', 'SOPDS_INPX_SKIP_UNCHANGED', 'SOPDS_INPX_TEST_ZIP', 'SOPDS_INPX_TEST_FILES', 'SOPDS_DELETE_LOGICAL'),
+    '3. Scanner Options': ('SOPDS_FB2SAX','SOPDS_ZIPSCAN','SOPDS_ZIPCODEPAGE', 'SOPDS_INPX_ENABLE', 'SOPDS_INPX_SKIP_UNCHANGED', 'SOPDS_INPX_TEST_ZIP', 'SOPDS_INPX_TEST_FILES', 'SOPDS_DELETE_LOGICAL'),
     '4. Scanner Shedule': ('SOPDS_SCAN_SHED_MIN', 'SOPDS_SCAN_SHED_HOUR', 'SOPDS_SCAN_SHED_DAY','SOPDS_SCAN_SHED_DOW'),
     '5. Converters Options': ('SOPDS_FB2TOEPUB', 'SOPDS_FB2TOMOBI', 'SOPDS_TEMP_DIR'),   
     '6. Log & PID Files': ('SOPDS_SERVER_LOG', 'SOPDS_SCANNER_LOG', 'SOPDS_SERVER_PID','SOPDS_SCANNER_PID'),