Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Debug messages for a number of ebook conversion plugins.

Browse Source
This commit is contained in:
John Schember 2009-06-21 08:11:33 -04:00
parent 25911a8598
commit 7eef5c40e3
17 changed files with 65 additions and 31 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/calibre/ebooks/conversion/preprocess.py
View File

@ -57,7 +57,6 @@ def line_length(raw, percent):
return 0
total = sum(lengths)
print total
avg = total / len(lengths)
max_line = avg * 2

10
src/calibre/ebooks/fb2/fb2ml.py
View File

@ -9,12 +9,10 @@ Transform OEB content into FB2 markup
'''
import os
import re
from base64 import b64encode
from lxml import etree
from calibre import entity_to_unicode
from calibre.ebooks.oeb.base import XHTML, XHTML_NS, barename, namespace
from calibre.ebooks.oeb.stylizer import Stylizer
from calibre.ebooks.oeb.base import OEB_IMAGES
@ -33,11 +31,11 @@ STYLES = [
]
class FB2MLizer(object):
def __init__(self, ignore_tables=False):
self.ignore_tables = ignore_tables
def __init__(self, log):
self.log = log
def extract_content(self, oeb_book, opts):
oeb_book.logger.info('Converting XHTML to FB2 markup...')
self.log.info('Converting XHTML to FB2 markup...')
self.oeb_book = oeb_book
self.opts = opts
return self.fb2mlize_spine()
@ -45,12 +43,14 @@ class FB2MLizer(object):
def fb2mlize_spine(self):
output = self.fb2_header()
if 'titlepage' in self.oeb_book.guide:
self.log.debug('Generating cover page...')
href = self.oeb_book.guide['titlepage'].href
item = self.oeb_book.manifest.hrefs[href]
if item.spine_position is None:
stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile)
output += self.dump_text(item.data.find(XHTML('body')), stylizer)
for item in self.oeb_book.spine:
self.log.debug('Converting %s to FictionBook2 XML' % item.href)
stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile)
output += self.dump_text(item.data.find(XHTML('body')), stylizer)
output += self.fb2_body_footer()

2
src/calibre/ebooks/fb2/output.py
View File

@ -16,7 +16,7 @@ class FB2Output(OutputFormatPlugin):
file_type = 'fb2'
def convert(self, oeb_book, output_path, input_plugin, opts, log):
fb2mlizer = FB2MLizer(ignore_tables=opts.linearize_tables)
fb2mlizer = FB2MLizer(log)
fb2_content = fb2mlizer.extract_content(oeb_book, opts)
close = False

4
src/calibre/ebooks/pdf/input.py
View File

@ -24,10 +24,12 @@ class PDFInput(InputFormatPlugin):
def convert(self, stream, options, file_ext, log,
accelerators):
log.debug('Converting file to html...')
# The main html file will be named index.html
pdftohtml(os.getcwd(), stream.name, options.no_images)
from calibre.ebooks.metadata.meta import get_metadata
log.debug('Retrieving document metadata...')
mi = get_metadata(stream, 'pdf')
opf = OPFCreator(os.getcwd(), mi)
@ -42,9 +44,11 @@ class PDFInput(InputFormatPlugin):
new_i = i.replace('-', '')
os.rename(i, new_i)
manifest.append((new_i, None))
log.debug('Generating manifest...')
opf.create_manifest(manifest)
opf.create_spine(['index.html'])
log.debug('Rendering manifest...')
with open('metadata.opf', 'wb') as opffile:
opf.render(opffile)

10
src/calibre/ebooks/pdf/output.py
View File

@ -1,5 +1,4 @@
# -*- coding: utf-8 -*-
from __future__ import with_statement
__license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>'
@ -9,9 +8,8 @@ __docformat__ = 'restructuredtext en'
Convert OEB ebook format to PDF.
'''
#unit, papersize, orientation, custom_size, profile
import os, glob
import glob
import os
from calibre.customize.conversion import OutputFormatPlugin, \
OptionRecommendation
@ -54,14 +52,17 @@ class PDFOutput(OutputFormatPlugin):
self.metadata = oeb_book.metadata
if input_plugin.is_image_collection:
log.debug('Converting input as an image collection...')
self.convert_images(input_plugin.get_images())
else:
log.debug('Converting input as a text based book...')
self.convert_text(oeb_book)
def convert_images(self, images):
self.write(ImagePDFWriter, images)
def convert_text(self, oeb_book):
self.log.debug('Serializing oeb input to disk for processing...')
with TemporaryDirectory('_pdf_out') as oeb_dir:
from calibre.customize.ui import plugin_for_output_format
oeb_output = plugin_for_output_format('oeb')
@ -86,6 +87,7 @@ class PDFOutput(OutputFormatPlugin):
out_stream.seek(0)
out_stream.truncate()
self.log.debug('Rendering pages to PDF...')
writer.dump(items, out_stream, PDFMetadata(self.metadata))
if close:

6
src/calibre/ebooks/pdf/writer.py
View File

@ -1,5 +1,4 @@
# -*- coding: utf-8 -*-
from __future__ import with_statement
__license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>'
@ -9,11 +8,12 @@ __docformat__ = 'restructuredtext en'
Write content to PDF.
'''
import os, shutil
import os
import shutil
from calibre.ptempfile import PersistentTemporaryDirectory
from calibre.ebooks.pdf.pageoptions import unit, paper_size, \
orientation, size
orientation
from calibre.ebooks.metadata import authors_to_string
from PyQt4 import QtCore

11
src/calibre/ebooks/pml/input.py
View File

@ -4,7 +4,9 @@ __license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
import glob, os, shutil
import glob
import os
import shutil
from calibre.customize.conversion import InputFormatPlugin
from calibre.ptempfile import TemporaryDirectory
@ -40,6 +42,7 @@ class PMLInput(InputFormatPlugin):
if self.options.input_encoding:
ienc = self.options.input_encoding
self.log.debug('Converting PML to HTML...')
html = pml_to_html(pml_stream.read().decode(ienc))
html_stream.write('<html><head><title /></head><body>' + html.encode('utf-8') + '</body></html>')
@ -51,9 +54,11 @@ class PMLInput(InputFormatPlugin):
def convert(self, stream, options, file_ext, log,
accelerators):
self.options = options
self.log = log
pages, images = [], []
if file_ext == 'pmlz':
log.debug('De-compressing content to temporary directory...')
with TemporaryDirectory('_unpmlz') as tdir:
zf = ZipFile(stream)
zf.extractall(tdir)
@ -64,6 +69,7 @@ class PMLInput(InputFormatPlugin):
html_path = os.path.join(os.getcwd(), html_name)
pages.append(html_name)
log.debug('Processing PML item %s...' % pml)
self.process_pml(pml, html_path)
imgs = glob.glob(os.path.join(tdir, '*.png'))
@ -90,12 +96,13 @@ class PMLInput(InputFormatPlugin):
manifest_items.append((item, None))
from calibre.ebooks.metadata.meta import get_metadata
log.debug('Reading metadata from input file...')
mi = get_metadata(stream, 'pml')
opf = OPFCreator(os.getcwd(), mi)
log.debug('Generating manifest...')
opf.create_manifest(manifest_items)
opf.create_spine(pages)
with open('metadata.opf', 'wb') as opffile:
opf.render(opffile)
return os.path.join(os.getcwd(), 'metadata.opf')

3
src/calibre/ebooks/pml/output.py
View File

@ -37,13 +37,14 @@ class PMLOutput(OutputFormatPlugin):
def convert(self, oeb_book, output_path, input_plugin, opts, log):
with TemporaryDirectory('_pmlz_output') as tdir:
pmlmlizer = PMLMLizer(ignore_tables=opts.linearize_tables)
pmlmlizer = PMLMLizer(log)
content = pmlmlizer.extract_content(oeb_book, opts)
with open(os.path.join(tdir, 'index.pml'), 'wb') as out:
out.write(content.encode(opts.output_encoding, 'replace'))
self.write_images(oeb_book.manifest, tdir)
log.debug('Compressing output...')
pmlz = ZipFile(output_path, 'w')
pmlz.add_dir(tdir)

2
src/calibre/ebooks/pml/pmlconverter.py
View File

@ -10,8 +10,6 @@ __docformat__ = 'restructuredtext en'
import re
from htmlentitydefs import codepoint2name
from calibre.ebooks.pdb.ereader import image_name
PML_HTML_RULES = [

10
src/calibre/ebooks/pml/pmlml.py
View File

@ -67,24 +67,26 @@ SEPARATE_TAGS = [
]
class PMLMLizer(object):
def __init__(self, ignore_tables=False):
self.ignore_tables = ignore_tables
def __init__(self, log):
self.log = log
def extract_content(self, oeb_book, opts):
oeb_book.logger.info('Converting XHTML to PML markup...')
self.log.info('Converting XHTML to PML markup...')
self.oeb_book = oeb_book
self.opts = opts
return self.pmlmlize_spine()
def pmlmlize_spine(self):
output = u''
if 'titlepage' in self.oeb_book.guide:
if 'titlepage' in self.oeb_book.guide
self.log.debug('Generating title page...')
href = self.oeb_book.guide['titlepage'].href
item = self.oeb_book.manifest.hrefs[href]
if item.spine_position is None:
stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile)
output += self.dump_text(item.data.find(XHTML('body')), stylizer)
for item in self.oeb_book.spine:
self.log.debug('Converting %s to PML markup...' % item.href)
stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile)
output += self.add_page_anchor(item.href)
output += self.dump_text(item.data.find(XHTML('body')), stylizer)

8
src/calibre/ebooks/rb/rbml.py
View File

@ -52,12 +52,12 @@ STYLES = [
class RBMLizer(object):
def __init__(self, name_map={}, ignore_tables=False):
def __init__(self, log, name_map={}):
self.log = log
self.name_map = name_map
self.ignore_tables = ignore_tables
def extract_content(self, oeb_book, opts):
oeb_book.logger.info('Converting XHTML to RB markup...')
self.log.info('Converting XHTML to RB markup...')
self.oeb_book = oeb_book
self.opts = opts
return self.mlize_spine()
@ -66,12 +66,14 @@ class RBMLizer(object):
def mlize_spine(self):
output = u'<HTML><HEAD><TITLE></TITLE></HEAD><BODY>'
if 'titlepage' in self.oeb_book.guide:
self.log.debug('Generating cover page...')
href = self.oeb_book.guide['titlepage'].href
item = self.oeb_book.manifest.hrefs[href]
if item.spine_position is None:
stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile)
output += self.dump_text(item.data.find(XHTML('body')), stylizer)
for item in self.oeb_book.spine:
self.log.debug('Converting %s to RocketBook HTML...' % item.href)
stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile)
output += self.add_page_anchor(item.href)
output += self.dump_text(item.data.find(XHTML('body')), stylizer)

3
src/calibre/ebooks/rb/reader.py
View File

@ -102,14 +102,17 @@ class Reader(object):
img.write(data)
def extract_content(self, output_dir):
self.log.debug('Extracting content from file...')
html = []
images = []
for item in self.toc:
if item.name.lower().endswith('html'):
self.log.debug('HTML item %s found...' % item.name)
html.append(item.name)
self.get_text(item, output_dir)
if item.name.lower().endswith('png'):
self.log.debug('PNG item %s found...' % item.name)
images.append(item.name)
self.get_image(item, output_dir)

5
src/calibre/ebooks/rb/writer.py
View File

@ -64,6 +64,7 @@ class RBWriter(object):
flags = 0
toc_items.append(TocItem(name.ljust(32, '\x00')[:32], size, flags))
self.log.debug('Writing file header...')
out_stream.write(HEADER)
out_stream.write(struct.pack('<I', 0))
out_stream.write(struct.pack('<IH', 0, 0))
@ -82,6 +83,7 @@ class RBWriter(object):
out_stream.write(info[0][1])
self.log.debug('Writing compressed RB HTHML...')
# Compressed text with proper heading
out_stream.write(struct.pack('<I', len(text[0][1])))
out_stream.write(struct.pack('<I', text_size))
@ -90,6 +92,7 @@ class RBWriter(object):
for chunck in text[0][1]:
out_stream.write(chunck)
self.log.debug('Writing images...')
for item in hidx+images:
out_stream.write(item[1])
@ -98,7 +101,7 @@ class RBWriter(object):
out_stream.write(struct.pack('<I', total_size))
def _text(self, oeb_book):
rbmlizer = RBMLizer(name_map=self.name_map, ignore_tables=self.opts.linearize_tables)
rbmlizer = RBMLizer(log, name_map=self.name_map)
text = rbmlizer.extract_content(oeb_book, self.opts).encode('cp1252', 'xmlcharrefreplace')
size = len(text)

2
src/calibre/ebooks/rtf/output.py
View File

@ -16,7 +16,7 @@ class RTFOutput(OutputFormatPlugin):
file_type = 'rtf'
def convert(self, oeb_book, output_path, input_plugin, opts, log):
rtfmlitzer = RTFMLizer(ignore_tables=opts.linearize_tables)
rtfmlitzer = RTFMLizer(log)
content = rtfmlitzer.extract_content(oeb_book, opts)
close = False

7
src/calibre/ebooks/rtf/rtfml.py
View File

@ -79,11 +79,11 @@ TODO:
'''
class RTFMLizer(object):
def __init__(self, ignore_tables=False):
self.ignore_tables = ignore_tables
def __init__(self, log):
self.log = log
def extract_content(self, oeb_book, opts):
oeb_book.logger.info('Converting XHTML to RTF markup...')
self.log.info('Converting XHTML to RTF markup...')
self.oeb_book = oeb_book
self.opts = opts
return self.mlize_spine()
@ -98,6 +98,7 @@ class RTFMLizer(object):
output += self.dump_text(item.data.find(XHTML('body')), stylizer)
output += '{\\page } '
for item in self.oeb_book.spine:
self.log.debug('Converting %s to RTF markup...' % item.href)
stylizer = Stylizer(item.data, item.href, self.oeb_book, self.opts.output_profile)
output += self.dump_text(item.data.find(XHTML('body')), stylizer)
output += self.footer()

6
src/calibre/ebooks/txt/input.py
View File

@ -21,20 +21,26 @@ class TXTInput(InputFormatPlugin):
ienc = stream.encoding if stream.encoding else 'utf-8'
if options.input_encoding:
ienc = options.input_encoding
log.debug('Reading text from file...')
txt = stream.read().decode(ienc)
log.debug('Running text though markdown conversion...')
try:
html = txt_to_markdown(txt)
except RuntimeError:
raise ValueError('This txt file has malformed markup, it cannot be'
'converted by calibre. See http://daringfireball.net/projects/markdown/syntax')
log.debug('Writing html output...')
with open('index.html', 'wb') as index:
index.write(html.encode('utf-8'))
from calibre.ebooks.metadata.meta import get_metadata
log.debug('Retrieving source document metadata...')
mi = get_metadata(stream, 'txt')
manifest = [('index.html', None)]
spine = ['index.html']
log.debug('Generating manifest...')
opf_writer(os.getcwd(), 'metadata.opf', manifest, spine, mi)
return os.path.join(os.getcwd(), 'metadata.opf')

6
src/calibre/ebooks/txt/writer.py
View File

@ -24,6 +24,7 @@ class TxtWriter(object):
def dump(self, spine):
out = u''
for item in spine:
self.log.debug('Processing %s...' % item.href)
content = unicode(etree.tostring(item.data.find(XHTML('body')), encoding=unicode))
content = self.remove_newlines(content)
content = self.strip_html(content)
@ -40,6 +41,7 @@ class TxtWriter(object):
return out
def strip_html(self, text):
self.log.debug('\tStripping html...')
stripped = u''
# Remove unnecessary tags
@ -77,6 +79,7 @@ class TxtWriter(object):
return stripped
def replace_html_symbols(self, content):
self.log.debug('\tReplacing entities with unicode...')
for entity in set(re.findall('&.+?;', content)):
mo = re.search('(%s)' % entity[1:-1], content)
content = content.replace(entity, entity_to_unicode(mo))
@ -84,6 +87,7 @@ class TxtWriter(object):
return content
def cleanup_text(self, text):
self.log.debug('\tClean up text...')
# Replace bad characters.
text = text.replace(u'\xc2', '')
text = text.replace(u'\xa0', ' ')
@ -114,6 +118,7 @@ class TxtWriter(object):
return text
def remove_newlines(self, text):
self.log.debug('\tRemove newlines for processing...')
text = text.replace('\r\n', ' ')
text = text.replace('\n', ' ')
text = text.replace('\r', ' ')
@ -121,6 +126,7 @@ class TxtWriter(object):
return text
def specified_newlines(self, text):
self.log.debug('\tReplacing newlines with selected type...')
if self.newline == '\n':
return text