def convert(self, oeb_book, output_path, input_plugin, opts, log):
from calibre.ebooks.txt.txtml import TXTMLizer
from calibre.ebooks.compression.tcr import compress
close = False
if not hasattr(output_path, 'write'):
close = True
if not os.path.exists(os.path.dirname(output_path)) and os.path.dirname(output_path):
os.makedirs(os.path.dirname(output_path))
out_stream = lopen(output_path, 'wb')
else:
out_stream = output_path
setattr(opts, 'flush_paras', False)
setattr(opts, 'max_line_length', 0)
setattr(opts, 'force_max_line_length', False)
setattr(opts, 'indent_paras', False)
writer = TXTMLizer(log)
txt = writer.extract_content(oeb_book, opts).encode(opts.tcr_output_encoding, 'replace')
log.info('Compressing text...')
txt = compress(txt)
out_stream.seek(0)
out_stream.truncate()
out_stream.write(txt)
if close:
out_stream.close()
def convert(self, oeb_book, output_path, input_plugin, opts, log):
from calibre.ebooks.txt.txtml import TXTMLizer
from calibre.utils.cleantext import clean_ascii_chars
from calibre.ebooks.txt.newlines import specified_newlines, TxtNewlines
if opts.txt_output_formatting.lower() == 'markdown':
from calibre.ebooks.txt.markdownml import MarkdownMLizer
self.writer = MarkdownMLizer(log)
elif opts.txt_output_formatting.lower() == 'textile':
from calibre.ebooks.txt.textileml import TextileMLizer
self.writer = TextileMLizer(log)
else:
self.writer = TXTMLizer(log)
txt = self.writer.extract_content(oeb_book, opts)
txt = clean_ascii_chars(txt)
log.debug('\tReplacing newlines with selected type...')
txt = specified_newlines(TxtNewlines(opts.newline).newline, txt)
close = False
if not hasattr(output_path, 'write'):
close = True
if not os.path.exists(os.path.dirname(output_path)) and os.path.dirname(output_path) != '':
os.makedirs(os.path.dirname(output_path))
out_stream = open(output_path, 'wb')
else:
out_stream = output_path
out_stream.seek(0)
out_stream.truncate()
out_stream.write(txt.encode(opts.txt_output_encoding, 'replace'))
if close:
out_stream.close()
def convert(self, oeb_book, output_path, input_plugin, opts, log):
from calibre.ebooks.txt.txtml import TXTMLizer
from calibre.utils.cleantext import clean_ascii_chars
from calibre.ebooks.txt.newlines import specified_newlines, TxtNewlines
if opts.txt_output_formatting.lower() == 'markdown':
from calibre.ebooks.txt.markdownml import MarkdownMLizer
self.writer = MarkdownMLizer(log)
elif opts.txt_output_formatting.lower() == 'textile':
from calibre.ebooks.txt.textileml import TextileMLizer
self.writer = TextileMLizer(log)
else:
self.writer = TXTMLizer(log)
txt = self.writer.extract_content(oeb_book, opts)
txt = clean_ascii_chars(txt)
log.debug('\tReplacing newlines with selected type...')
txt = specified_newlines(TxtNewlines(opts.newline).newline, txt)
close = False
if not hasattr(output_path, 'write'):
close = True
if not os.path.exists(os.path.dirname(output_path)) and os.path.dirname(output_path) != '':
os.makedirs(os.path.dirname(output_path))
out_stream = open(output_path, 'wb')
else:
out_stream = output_path
out_stream.seek(0)
out_stream.truncate()
out_stream.write(txt.encode(opts.txt_output_encoding, 'replace'))
if close:
out_stream.close()
def _generate_text(self, oeb_book):
writer = TXTMLizer(self.log)
txt = writer.extract_content(oeb_book, self.opts)
self.log.debug('\tReplacing newlines with selected type...')
txt = specified_newlines(TxtNewlines('windows').newline,
txt).encode(self.opts.pdb_output_encoding, 'replace')
txt_length = len(txt)
txt_records = []
for i in range(0, (len(txt) / MAX_RECORD_SIZE) + 1):
txt_records.append(txt[i * MAX_RECORD_SIZE: (i * MAX_RECORD_SIZE) + MAX_RECORD_SIZE])
return txt_records, txt_length
def _generate_text(self, oeb_book):
writer = TXTMLizer(self.log)
txt = writer.extract_content(oeb_book, self.opts)
self.log.debug('\tReplacing newlines with selected type...')
txt = specified_newlines(TxtNewlines('windows').newline,
txt).encode(self.opts.pdb_output_encoding, 'replace')
txt_length = len(txt)
txt_records = []
for i in range(0, (len(txt) // MAX_RECORD_SIZE) + 1):
txt_records.append(txt[i * MAX_RECORD_SIZE: (i * MAX_RECORD_SIZE) + MAX_RECORD_SIZE])
return txt_records, txt_length
class TXTOutput(OutputFormatPlugin):
name = 'TXT Output'
author = 'John Schember'
file_type = 'txt'
commit_name = 'txt_output'
ui_data = {
'newline_types': NEWLINE_TYPES,
'formatting_types': {
'plain': _('Plain text'),
'markdown': _('Markdown formatted text'),
'textile': _('TexTile formatted text')
},
}
options = {
OptionRecommendation(name='newline', recommended_value='system',
level=OptionRecommendation.LOW,
short_switch='n', choices=NEWLINE_TYPES,
help=_('Type of newline to use. Options are %s. Default is \'system\'. '
'Use \'old_mac\' for compatibility with Mac OS 9 and earlier. '
'For macOS use \'unix\'. \'system\' will default to the newline '
'type used by this OS.') % sorted(NEWLINE_TYPES)),
OptionRecommendation(name='txt_output_encoding', recommended_value='utf-8',
level=OptionRecommendation.LOW,
help=_('Specify the character encoding of the output document. '
'The default is utf-8.')),
OptionRecommendation(name='inline_toc',
recommended_value=False, level=OptionRecommendation.LOW,
help=_('Add Table of Contents to beginning of the book.')),
OptionRecommendation(name='max_line_length',
recommended_value=0, level=OptionRecommendation.LOW,
help=_('The maximum number of characters per line. This splits on '
'the first space before the specified value. If no space is found '
'the line will be broken at the space after and will exceed the '
'specified value. Also, there is a minimum of 25 characters. '
'Use 0 to disable line splitting.')),
OptionRecommendation(name='force_max_line_length',
recommended_value=False, level=OptionRecommendation.LOW,
help=_('Force splitting on the max-line-length value when no space '
'is present. Also allows max-line-length to be below the minimum')),
OptionRecommendation(name='txt_output_formatting',
recommended_value='plain',
choices=list(ui_data['formatting_types']),
help=_('Formatting used within the document.\n'
'* plain: {plain}\n'
'* markdown: {markdown}\n'
'* textile: {textile}').format(**ui_data['formatting_types'])),
OptionRecommendation(name='keep_links',
recommended_value=False, level=OptionRecommendation.LOW,
help=_('Do not remove links within the document. This is only '
'useful when paired with a txt-output-formatting option that '
'is not none because links are always removed with plain text output.')),
OptionRecommendation(name='keep_image_references',
recommended_value=False, level=OptionRecommendation.LOW,
help=_('Do not remove image references within the document. This is only '
'useful when paired with a txt-output-formatting option that '
'is not none because links are always removed with plain text output.')),
OptionRecommendation(name='keep_color',
recommended_value=False, level=OptionRecommendation.LOW,
help=_('Do not remove font color from output. This is only useful when '
'txt-output-formatting is set to textile. Textile is the only '
'formatting that supports setting font color. If this option is '
'not specified font color will not be set and default to the '
'color displayed by the reader (generally this is black).')),
}
def convert(self, oeb_book, output_path, input_plugin, opts, log):
from calibre.ebooks.txt.txtml import TXTMLizer
from calibre.utils.cleantext import clean_ascii_chars
from calibre.ebooks.txt.newlines import specified_newlines, TxtNewlines
if opts.txt_output_formatting.lower() == 'markdown':
from calibre.ebooks.txt.markdownml import MarkdownMLizer
self.writer = MarkdownMLizer(log)
elif opts.txt_output_formatting.lower() == 'textile':
from calibre.ebooks.txt.textileml import TextileMLizer
self.writer = TextileMLizer(log)
else:
self.writer = TXTMLizer(log)
txt = self.writer.extract_content(oeb_book, opts)
txt = clean_ascii_chars(txt)
log.debug('\tReplacing newlines with selected type...')
txt = specified_newlines(TxtNewlines(opts.newline).newline, txt)
close = False
if not hasattr(output_path, 'write'):
close = True
if not os.path.exists(os.path.dirname(output_path)) and os.path.dirname(output_path) != '':
os.makedirs(os.path.dirname(output_path))
out_stream = open(output_path, 'wb')
else:
out_stream = output_path
out_stream.seek(0)
out_stream.truncate()
out_stream.write(txt.encode(opts.txt_output_encoding, 'replace'))
if close:
out_stream.close()
class TXTOutput(OutputFormatPlugin):
name = 'TXT Output'
author = 'John Schember'
file_type = 'txt'
commit_name = 'txt_output'
ui_data = {
'newline_types': NEWLINE_TYPES,
'formatting_types': {
'plain': _('Plain text'),
'markdown': _('Markdown formatted text'),
'textile': _('TexTile formatted text')
},
}
options = {
OptionRecommendation(
name='newline',
recommended_value='system',
level=OptionRecommendation.LOW,
short_switch='n',
choices=NEWLINE_TYPES,
help=
_('Type of newline to use. Options are %s. Default is \'system\'. '
'Use \'old_mac\' for compatibility with Mac OS 9 and earlier. '
'For macOS use \'unix\'. \'system\' will default to the newline '
'type used by this OS.') % sorted(NEWLINE_TYPES)),
OptionRecommendation(
name='txt_output_encoding',
recommended_value='utf-8',
level=OptionRecommendation.LOW,
help=_('Specify the character encoding of the output document. '
'The default is utf-8.')),
OptionRecommendation(
name='inline_toc',
recommended_value=False,
level=OptionRecommendation.LOW,
help=_('Add Table of Contents to beginning of the book.')),
OptionRecommendation(
name='max_line_length',
recommended_value=0,
level=OptionRecommendation.LOW,
help=
_('The maximum number of characters per line. This splits on '
'the first space before the specified value. If no space is found '
'the line will be broken at the space after and will exceed the '
'specified value. Also, there is a minimum of 25 characters. '
'Use 0 to disable line splitting.')),
OptionRecommendation(
name='force_max_line_length',
recommended_value=False,
level=OptionRecommendation.LOW,
help=_(
'Force splitting on the max-line-length value when no space '
'is present. Also allows max-line-length to be below the minimum'
)),
OptionRecommendation(name='txt_output_formatting',
recommended_value='plain',
choices=list(ui_data['formatting_types']),
help=_('Formatting used within the document.\n'
'* plain: {plain}\n'
'* markdown: {markdown}\n'
'* textile: {textile}').format(
**ui_data['formatting_types'])),
OptionRecommendation(
name='keep_links',
recommended_value=False,
level=OptionRecommendation.LOW,
help=_(
'Do not remove links within the document. This is only '
'useful when paired with a TXT output formatting option that '
'is not none because links are always removed with plain text output.'
)),
OptionRecommendation(
name='keep_image_references',
recommended_value=False,
level=OptionRecommendation.LOW,
help=
_('Do not remove image references within the document. This is only '
'useful when paired with a TXT output formatting option that '
'is not none because links are always removed with plain text output.'
)),
OptionRecommendation(
name='keep_color',
recommended_value=False,
level=OptionRecommendation.LOW,
help=
_('Do not remove font color from output. This is only useful when '
'TXT output formatting is set to textile. Textile is the only '
'formatting that supports setting font color. If this option is '
'not specified font color will not be set and default to the '
'color displayed by the reader (generally this is black).')),
}
def convert(self, oeb_book, output_path, input_plugin, opts, log):
from calibre.ebooks.txt.txtml import TXTMLizer
from calibre.utils.cleantext import clean_ascii_chars
from calibre.ebooks.txt.newlines import specified_newlines, TxtNewlines
if opts.txt_output_formatting.lower() == 'markdown':
from calibre.ebooks.txt.markdownml import MarkdownMLizer
self.writer = MarkdownMLizer(log)
elif opts.txt_output_formatting.lower() == 'textile':
from calibre.ebooks.txt.textileml import TextileMLizer
self.writer = TextileMLizer(log)
else:
self.writer = TXTMLizer(log)
txt = self.writer.extract_content(oeb_book, opts)
txt = clean_ascii_chars(txt)
log.debug('\tReplacing newlines with selected type...')
txt = specified_newlines(TxtNewlines(opts.newline).newline, txt)
close = False
if not hasattr(output_path, 'write'):
close = True
if not os.path.exists(os.path.dirname(
output_path)) and os.path.dirname(output_path) != '':
os.makedirs(os.path.dirname(output_path))
out_stream = open(output_path, 'wb')
else:
out_stream = output_path
out_stream.seek(0)
out_stream.truncate()
out_stream.write(txt.encode(opts.txt_output_encoding, 'replace'))
if close:
out_stream.close()
