Merge+RTF cleaning

src/calibre/devices/android/driver.py

@@ -49,6 +49,15 @@ class ANDROID(USBMS):
                        0x7086 : [0x0226], 0x70a8: [0x9999], 0x42c4 : [0x216],
                        0x70c6 : [0x226]
                      },
+            # Freescale
+            0x15a2 : {
+                0x0c01 : [0x226]
+            },
+
+            # Alcatel
+            0x05c6 : {
+                0x9018 : [0x0226],
+            },
 
             # Sony Ericsson
             0xfce : {
@@ -139,7 +148,8 @@ class ANDROID(USBMS):
     VENDOR_NAME      = ['HTC', 'MOTOROLA', 'GOOGLE_', 'ANDROID', 'ACER',
             'GT-I5700', 'SAMSUNG', 'DELL', 'LINUX', 'GOOGLE', 'ARCHOS',
             'TELECHIP', 'HUAWEI', 'T-MOBILE', 'SEMC', 'LGE', 'NVIDIA',
-            'GENERIC-', 'ZTE', 'MID', 'QUALCOMM', 'PANDIGIT', 'HYSTON', 'VIZIO']
+            'GENERIC-', 'ZTE', 'MID', 'QUALCOMM', 'PANDIGIT', 'HYSTON',
+            'VIZIO', 'GOOGLE', 'FREESCAL']
     WINDOWS_MAIN_MEM = ['ANDROID_PHONE', 'A855', 'A853', 'INC.NEXUS_ONE',
             '__UMS_COMPOSITE', '_MB200', 'MASS_STORAGE', '_-_CARD', 'SGH-I897',
             'GT-I9000', 'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID',
@@ -150,7 +160,7 @@ class ANDROID(USBMS):
             'MB860', 'MULTI-CARD', 'MID7015A', 'INCREDIBLE', 'A7EB', 'STREAK',
             'MB525', 'ANDROID2.3', 'SGH-I997', 'GT-I5800_CARD', 'MB612',
             'GT-S5830_CARD', 'GT-S5570_CARD', 'MB870', 'MID7015A',
-            'ALPANDIGITAL', 'ANDROID_MID', 'VTAB1008']
+            'ALPANDIGITAL', 'ANDROID_MID', 'VTAB1008', 'EMX51_BBG_ANDROI']
     WINDOWS_CARD_A_MEM = ['ANDROID_PHONE', 'GT-I9000_CARD', 'SGH-I897',
             'FILE-STOR_GADGET', 'SGH-T959', 'SAMSUNG_ANDROID', 'GT-P1000_CARD',
             'A70S', 'A101IT', '7', 'INCREDIBLE', 'A7EB', 'SGH-T849_CARD',

src/calibre/ebooks/conversion/plumber.py

@@ -693,6 +693,8 @@ OptionRecommendation(name='sr3_replace',
     def unarchive(self, path, tdir):
         extract(path, tdir)
         files = list(walk(tdir))
+        files = [f if isinstance(f, unicode) else f.decode(filesystem_encoding)
+                for f in files]
         from calibre.customize.ui import available_input_formats
         fmts = available_input_formats()
         for x in ('htm', 'html', 'xhtm', 'xhtml'): fmts.remove(x)

src/calibre/ebooks/rtf2xml/convert_to_tags.py

@@ -1,4 +1,5 @@
 import os, tempfile, sys
+from codecs import EncodedFile
 
 from calibre.ebooks.rtf2xml import copy, check_encoding
 
@@ -40,6 +41,7 @@ class ConvertToTags:
         self.__run_level = run_level
         self.__write_to = tempfile.mktemp()
         self.__convert_utf = False
+        self.__bad_encoding = False
 
     def __initiate_values(self):
         """
@@ -219,6 +221,7 @@ class ConvertToTags:
             self.__write_obj.write('<?xml version="1.0" encoding="US-ASCII" ?>')
             sys.stderr.write('Bad RTF encoding, revert to US-ASCII chars and'
                     ' hope for the best')
+            self.__bad_encoding = True
         self.__new_line = 0
         self.__write_new_line()
         if self.__no_dtd:
@@ -246,7 +249,7 @@ class ConvertToTags:
         the appropriate function.
         The functions that are called:
             a text function for text
-            an open funciton for open tags
+            an open function for open tags
             an open with attribute function for tags with attributes
             an empty with attribute function for tags that are empty but have
             attribtes.
@@ -262,20 +265,28 @@ class ConvertToTags:
                     action = self.__state_dict.get(self.__token_info)
                     if action is not None:
                         action(line)
-        self.__write_obj.close()
+        #convert all encodings to UTF8 or ASCII to avoid unsupported encodings in lxml
-        #convert all encodings to UTF8 to avoid unsupported encodings in lxml
+        if self.__convert_utf or self.__bad_encoding:
-        if self.__convert_utf:
             copy_obj = copy.Copy(bug_handler = self.__bug_handler)
             copy_obj.rename(self.__write_to, self.__file)
+            file_encoding = "utf-8"
+            if self.__bad_encoding:
+                file_encoding = "us-ascii"
             with open(self.__file, 'r') as read_obj:
                 with open(self.__write_to, 'w') as write_obj:
-                    file = read_obj.read()
                     try:
-                        file = file.decode(self.__encoding)
+                        write_objenc = EncodedFile(write_obj, self.__encoding,
-                        write_obj.write(file.encode('utf-8'))
+                                        file_encoding, 'strict')
+                        for line in read_obj:
+                            write_objenc.write(line)
                     except:
-                        sys.stderr.write('Conversion to UTF-8 is not possible,'
+                        if self.__convert_utf:
+                            sys.stderr.write('Conversion to UTF-8 is problematic,'
                             ' encoding should be very carefully checked')
+                        write_objenc = EncodedFile(write_obj, self.__encoding,
+                                        file_encoding, 'replace')
+                        for line in read_obj:
+                            write_objenc.write(line)
         copy_obj = copy.Copy(bug_handler = self.__bug_handler)
         if self.__copy:
             copy_obj.copy_file(self.__write_to, "convert_to_tags.data")

src/calibre/ebooks/rtf2xml/output.py

@@ -10,7 +10,9 @@
 #                                                                       #
 #                                                                       #
 #########################################################################
-import sys, os, codecs
+import sys, os
+# , codecs
+
 class Output:
     """
     Output file
@@ -19,7 +21,8 @@ class Output:
             file,
             orig_file,
             output_dir = None,
-            out_file = None
+            out_file = None,
+            no_ask = True
             ):
         """
         Required:
@@ -33,8 +36,9 @@ class Output:
         self.__file = file
         self.__orig_file = orig_file
         self.__output_dir = output_dir
-        self.__no_ask = 1
+        self.__no_ask = no_ask
         self.__out_file = out_file
+
     def output(self):
         """
         Required:
@@ -45,13 +49,14 @@ class Output:
             output the line to the screen if no output file given. Otherwise, output to
             the file.
         """
-        # self.__output_xml(self.__file, self.__out_file)
         if self.__output_dir:
             self.__output_to_dir_func()
         elif self.__out_file:
-            self.__output_xml(self.__file, self.__out_file)
+            self.__output_to_file_func()
+            # self.__output_xml(self.__file, self.__out_file)
         else:
             self.__output_to_standard_func()
+
     def __output_to_dir_func(self):
         """
         Requires:
@@ -64,32 +69,25 @@ class Output:
         """
         base_name = os.path.basename(self.__orig_file)
         base_name, ext  = os.path.splitext(base_name)
-        output_file = '%s.xml' % base_name
+        output_file = os.path.join(self.__output_dir, '%s.xml' % base_name)
-        output_file = os.path.join(self.__output_dir, output_file)
         # change if user wants to output to a specific file
         if self.__out_file:
             output_file = os.path.join(self.__output_dir, self.__out_file)
         user_response = 'o'
-        if os.path.isfile(output_file):
+        if os.path.isfile(output_file) and not self.__no_ask:
-            if self.__no_ask:
+            msg = 'Do you want to overwrite %s?\n' % output_file
-                user_response = 'o'
+            msg += ('Type "o" to overwrite.\n'
-            else:
+                    'Type any other key to print to standard output.\n')
-                msg = 'Do you want to over-write %s?\n' % output_file
-                msg += 'Type "o" to over-write.\n'
-                msg += 'Type any other key to print to standard output.\n'
             sys.stderr.write(msg)
             user_response = raw_input()
         if user_response == 'o':
-            read_obj = open(self.__file, 'r')
+            with open(self.__file, 'r') as read_obj:
-            write_obj = open(output_file, 'w')
+                with open(self.output_file, 'w') as write_obj:
-            line = 1
+                    for line in read_obj:
-            while line:
-                line = read_obj.readline()
                         write_obj.write(line)
-            read_obj.close()
-            write_obj.close()
         else:
             self.__output_to_standard_func()
+
     def __output_to_file_func(self):
         """
         Required:
@@ -99,14 +97,11 @@ class Output:
         Logic:
             read one line at a time. Output to standard
         """
-        read_obj = open(self.__file, 'r')
+        with open(self.__file, 'r') as read_obj:
-        write_obj = open(self.__out_file, 'w')
+            with open(self.__out_file, 'w') as write_obj:
-        line = 1
+                for line in read_obj:
-        while line:
-            line = read_obj.readline()
                     write_obj.write(line)
-        read_obj.close()
+
-        write_obj.close()
     def __output_to_standard_func(self):
         """
         Required:
@@ -116,26 +111,24 @@ class Output:
         Logic:
             read one line at a time. Output to standard
         """
-        read_obj = open(self.__file, 'r')
+        with open(self.__file, 'r') as read_obj:
-        line = 1
+            for line in read_obj:
-        while line:
-            line = read_obj.readline()
                 sys.stdout.write(line)
-        read_obj.close()
+
-    def __output_xml(self, in_file, out_file):
+    # def __output_xml(self, in_file, out_file):
-        """
+        # """
-        output the ill-formed xml file
+        # output the ill-formed xml file
-        """
+        # """
-        (utf8_encode, utf8_decode, utf8_reader, utf8_writer) = codecs.lookup("utf-8")
+        # (utf8_encode, utf8_decode, utf8_reader, utf8_writer) = codecs.lookup("utf-8")
-        write_obj = utf8_writer(open(out_file, 'w'))
+        # write_obj = utf8_writer(open(out_file, 'w'))
-        write_obj = open(out_file, 'w')
+        # write_obj = open(out_file, 'w')
-        read_obj = utf8_writer(open(in_file, 'r'))
+        # read_obj = utf8_writer(open(in_file, 'r'))
-        read_obj = open(in_file, 'r')
+        # read_obj = open(in_file, 'r')
-        line = 1
+        # line = 1
-        while line:
+        # while line:
-            line = read_obj.readline()
+            # line = read_obj.readline()
-            if isinstance(line, type(u"")):
+            # if isinstance(line, type(u"")):
-                line = line.encode("utf-8")
+                # line = line.encode("utf-8")
-            write_obj.write(line)
+            # write_obj.write(line)
-        read_obj.close()
+        # read_obj.close()
-        write_obj.close()
+        # write_obj.close()

src/calibre/library/database2.py

@@ -2103,7 +2103,9 @@ class LibraryDatabase2(LibraryDatabase, SchemaUpgrade, CustomColumns):
         user_mi = mi.get_all_user_metadata(make_copy=False)
         for key in user_mi.iterkeys():
             if key in self.field_metadata and \
-                    user_mi[key]['datatype'] == self.field_metadata[key]['datatype']:
+                    user_mi[key]['datatype'] == self.field_metadata[key]['datatype'] and \
+                    (user_mi[key]['datatype'] != 'text' or
+                     user_mi[key]['is_multiple'] == self.field_metadata[key]['is_multiple']):
                 val = mi.get(key, None)
                 if force_changes or val is not None:
                     doit(self.set_custom, id, val=val, extra=mi.get_extra(key),