Refactoring.

setup.py

@@ -89,7 +89,7 @@ if __name__ == '__main__':
                              include_dirs=['src/calibre/utils/msdes']),
 
                     Extension('calibre.plugins.cPalmdoc',
-                        sources=['src/calibre/ebooks/mobi/palmdoc.c']),
+                        sources=['src/calibre/ebooks/compression/palmdoc.c']),
 
                     PyQtExtension('calibre.plugins.pictureflow',
                                   ['src/calibre/gui2/pictureflow/pictureflow.cpp',

src/calibre/ebooks/compression/__init__.py

@@ -0,0 +1,5 @@
+# -*- coding: utf-8 -*-
+
+__license__ = 'GPL 3'
+__copyright__ = '2009, John Schember <john@nachtimwald.com>'
+__docformat__ = 'restructuredtext en'

src/calibre/ebooks/fb2/fb2ml.py

@@ -25,15 +25,9 @@ TAG_MAP = {
     'div' : 'p',
 }
 
-STYLE_MAP = {
-    'bold'   : 'strong',
-    'bolder' : 'strong',
-    'italic' : 'emphasis',
-}
-
 STYLES = [
-    'font-weight',
+    ('font-weight', {'bold'   : 'strong', 'bolder' : 'strong'}),
-    'font-style',
+    ('font-style', {'italic' : 'emphasis'}),
 ]
 
 class FB2MLizer(object):
@@ -107,8 +101,9 @@ class FB2MLizer(object):
                 fb2_text += '<%s>' % fb2_tag
                 tag_stack.append(fb2_tag)
 
+            # Processes style information
             for s in STYLES:
-                style_tag = STYLE_MAP.get(style[s], None)
+                style_tag = s[1].get(style[s[0]], None)
                 if style_tag:
                     tag_count += 1
                     fb2_text += '<%s>' % style_tag

src/calibre/ebooks/mobi/reader.py

@@ -1,11 +1,17 @@
-from __future__ import with_statement
 __license__   = 'GPL v3'
 __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
 '''
 Read data from .mobi files
 '''
 
-import struct, os, cStringIO, re, functools, datetime, textwrap
+import datetime
+import functools
+import os
+import re
+import struct
+import textwrap
+
+import cStringIO
 
 try:
     from PIL import Image as PILImage
@@ -21,8 +27,8 @@ from calibre.ebooks import DRMError
 from calibre.ebooks.chardet import ENCODING_PATS
 from calibre.ebooks.mobi import MobiError
 from calibre.ebooks.mobi.huffcdic import HuffReader
-from calibre.ebooks.mobi.palmdoc import decompress_doc
 from calibre.ebooks.mobi.langcodes import main_language, sub_language
+from calibre.ebooks.compression.palmdoc import decompress_doc
 from calibre.ebooks.metadata import MetaInformation
 from calibre.ebooks.metadata.opf2 import OPFCreator, OPF
 from calibre.ebooks.metadata.toc import TOC

src/calibre/ebooks/mobi/writer.py

@@ -1,27 +1,32 @@
 '''
 Write content to Mobipocket books.
 '''
-from __future__ import with_statement
 
 __license__   = 'GPL v3'
 __copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.cam>'
 
+from collections import defaultdict
+from itertools import count
+from itertools import izip
+import random
+import re
 from struct import pack
 import time
-import random
-from cStringIO import StringIO
-import re
-from itertools import izip, count
-from collections import defaultdict
 from urlparse import urldefrag
+
 from PIL import Image
-from calibre.ebooks.oeb.base import XML_NS, XHTML, XHTML_NS, OEB_DOCS, \
+from cStringIO import StringIO
-    OEB_RASTER_IMAGES
-from calibre.ebooks.oeb.base import namespace, prefixname
-from calibre.ebooks.oeb.base import urlnormalize
-from calibre.ebooks.mobi.palmdoc import compress_doc
 from calibre.ebooks.mobi.langcodes import iana2mobi
 from calibre.ebooks.mobi.mobiml import MBP_NS
+from calibre.ebooks.oeb.base import OEB_DOCS
+from calibre.ebooks.oeb.base import OEB_RASTER_IMAGES
+from calibre.ebooks.oeb.base import XHTML
+from calibre.ebooks.oeb.base import XHTML_NS
+from calibre.ebooks.oeb.base import XML_NS
+from calibre.ebooks.oeb.base import namespace
+from calibre.ebooks.oeb.base import prefixname
+from calibre.ebooks.oeb.base import urlnormalize
+from calibre.ebooks.compression.palmdoc import compress_doc
 
 # TODO:
 # - Allow override CSS (?)

src/calibre/ebooks/pdb/__init__.py

@@ -1,5 +1,4 @@
 # -*- coding: utf-8 -*-
-from __future__ import with_statement
 
 __license__   = 'GPL v3'
 __copyright__ = '2009, John Schember <john@nachtimwald.com>'
@@ -10,8 +9,8 @@ class PDBError(Exception):
 
 
 from calibre.ebooks.pdb.ereader.reader import Reader as ereader_reader
-from calibre.ebooks.pdb.ztxt.reader import Reader as ztxt_reader
 from calibre.ebooks.pdb.palmdoc.reader import Reader as palmdoc_reader
+from calibre.ebooks.pdb.ztxt.reader import Reader as ztxt_reader
 
 FORMAT_READERS = {
     'PNPdPPrs': ereader_reader,

src/calibre/ebooks/pdb/ereader/reader.py

@@ -8,16 +8,19 @@ __license__   = 'GPL v3'
 __copyright__ = '2009, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
 
-import os, re, struct, zlib
+import os
+import re
+import struct
+import zlib
 
 from calibre import CurrentDir
 from calibre.ebooks import DRMError
-from calibre.ebooks.pdb.formatreader import FormatReader
-from calibre.ebooks.pdb.ereader import EreaderError
-from calibre.ebooks.pml.pmlconverter import pml_to_html, \
-    footnote_sidebar_to_html
-from calibre.ebooks.mobi.palmdoc import decompress_doc
 from calibre.ebooks.metadata.opf2 import OPFCreator
+from calibre.ebooks.compression.palmdoc import decompress_doc
+from calibre.ebooks.pdb.ereader import EreaderError
+from calibre.ebooks.pdb.formatreader import FormatReader
+from calibre.ebooks.pml.pmlconverter import footnote_sidebar_to_html
+from calibre.ebooks.pml.pmlconverter import pml_to_html
 
 class HeaderRecord(object):
     '''

src/calibre/ebooks/pdb/ereader/writer.py

@@ -8,9 +8,11 @@ __license__   = 'GPL v3'
 __copyright__ = '2009, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
 
-import struct, zlib
+import struct
+import zlib
 
-import Image, cStringIO
+import Image
+import cStringIO
 
 from calibre.ebooks.pdb.formatwriter import FormatWriter
 from calibre.ebooks.oeb.base import OEB_IMAGES

src/calibre/ebooks/pdb/header.py

@@ -1,5 +1,4 @@
 # -*- coding: utf-8 -*-
-from __future__ import with_statement
 '''
 Read the header data from a pdb file.
 '''
@@ -8,7 +7,9 @@ __license__   = 'GPL v3'
 __copyright__ = '2009, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
 
-import re, struct, time
+import re
+import struct
+import time
 
 class PdbHeaderReader(object):
 

src/calibre/ebooks/pdb/palmdoc/reader.py

@@ -8,11 +8,13 @@ __license__   = 'GPL v3'
 __copyright__ = '2009, John Schember <john@nachtimwald.com>'
 __docformat__ = 'restructuredtext en'
 
-import os, struct, zlib
+import os
+import struct
 
+from calibre.ebooks.compression.palmdoc import decompress_doc
 from calibre.ebooks.pdb.formatreader import FormatReader
-from calibre.ebooks.mobi.palmdoc import decompress_doc
+from calibre.ebooks.txt.processor import opf_writer
-from calibre.ebooks.txt.processor import txt_to_markdown, opf_writer
+from calibre.ebooks.txt.processor import txt_to_markdown
 
 class HeaderRecord(object):
     '''

src/calibre/ebooks/pdb/palmdoc/writer.py

@@ -10,10 +10,11 @@ __docformat__ = 'restructuredtext en'
 
 import struct
 
+from calibre.ebooks.compression.palmdoc import compress_doc
 from calibre.ebooks.pdb.formatwriter import FormatWriter
-from calibre.ebooks.txt.writer import TxtWriter, TxtNewlines
-from calibre.ebooks.mobi.palmdoc import compress_doc
 from calibre.ebooks.pdb.header import PdbHeaderBuilder
+from calibre.ebooks.txt.writer import TxtNewlines
+from calibre.ebooks.txt.writer import TxtWriter
 
 MAX_RECORD_SIZE = 4096
 

src/calibre/ebooks/pml/pmlml.py

@@ -8,7 +8,8 @@ __docformat__ = 'restructuredtext en'
 Transform OEB content into PML markup
 '''
 
-import os, re
+import os
+import re
 
 from calibre.ebooks.oeb.base import XHTML, XHTML_NS, barename, namespace
 from calibre.ebooks.oeb.stylizer import Stylizer
@@ -40,6 +41,31 @@ STYLES = [
     ('text-align', {'right' : 'r', 'center' : 'c'}),
 ]
 
+BLOCK_TAGS = [
+    'p',
+]
+
+BLOCK_STYLES = [
+    'block',
+]
+
+LINK_TAGS = [
+    'a',
+]
+
+SEPARATE_TAGS = [
+    'h1',
+    'h2',
+    'h3',
+    'h4',
+    'h5',
+    'h6',
+    'p',
+    'div',
+    'li',
+    'tr',
+]
+
 class PMLMLizer(object):
     def __init__(self, ignore_tables=False):
         self.ignore_tables = ignore_tables
@@ -104,7 +130,7 @@ class PMLMLizer(object):
         tag_count = 0
 
         # Are we in a paragraph block?
-        if tag == 'p' or style['display'] in ('block'):
+        if tag in BLOCK_TAGS or style['display'] in BLOCK_STYLES:
             if 'block' not in tag_stack:
                 tag_count += 1
                 tag_stack.append('block')
@@ -136,7 +162,7 @@ class PMLMLizer(object):
                 
             # Special processing of tags that require an argument.
             # Anchors links
-            if tag == 'a' and 'q' not in tag_stack:
+            if tag in LINK_TAGS and 'q' not in tag_stack:
                 href = elem.get('href')
                 if href and '://' not in href:
                     if '#' in href:
@@ -168,7 +194,7 @@ class PMLMLizer(object):
         for i in range(0, tag_count):
             close_tag_list.insert(0, tag_stack.pop())
         text += self.close_tags(close_tag_list)
-        if tag in ('h1', 'h2', 'h3', 'h4', 'h5', 'h6', 'p', 'div', 'li', 'tr'):
+        if tag in SEPARATE_TAGS:
             text += os.linesep + os.linesep
         
         if 'block' not in tag_stack: