gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-03-15 22:23:42 +01:00
Code Issues Projects Releases Wiki Activity

Next portion of logging adapt.

Browse Source
This commit is contained in:
gryf
2021-06-24 19:42:51 +02:00
parent 84abd62a61
commit 6dfcaea2dd
20 changed files with 105 additions and 122 deletions
Download Patch File Download Diff File Expand all files Collapse all files

8
ebook_converter/ebooks/conversion/plugins/chm_input.py
View File

@@ -28,7 +28,7 @@ class CHMInput(InputFormatPlugin):
from ebook_converter.ebooks.chm.reader import CHMReader
log.debug('Opening CHM file')
rdr = CHMReader(chm_path, log, input_encoding=self.opts.input_encoding)
log.debug('Extracting CHM to %s' % output_dir)
log.debug('Extracting CHM to %s', output_dir)
rdr.extract_content(output_dir, debug_dump=debug_dump)
self._chm_reader = rdr
return rdr.hhc_path
@@ -53,8 +53,8 @@ class CHMInput(InputFormatPlugin):
# closing stream so CHM can be opened by external library
stream.close()
log.debug('tdir=%s' % tdir)
log.debug('stream.name=%s' % stream.name)
log.debug('tdir=%s', tdir)
log.debug('stream.name=%s', stream.name)
debug_dump = False
odi = options.debug_pipeline
if odi:
@@ -121,7 +121,7 @@ class CHMInput(InputFormatPlugin):
resolve_entities=True)[0]
hhcroot = html.fromstring(hhcdata)
toc = self._process_nodes(hhcroot)
log.debug('Found %d section nodes' % toc.count())
log.debug('Found %d section nodes', toc.count())
htmlpath = os.path.splitext(hhcpath)[0] + ".html"
base = os.path.dirname(os.path.abspath(htmlpath))

7
ebook_converter/ebooks/conversion/plugins/comic_input.py
View File

@@ -9,11 +9,6 @@ from ebook_converter.ptempfile import PersistentTemporaryDirectory
from ebook_converter.utils import directory
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
class ComicInput(InputFormatPlugin):
name = 'Comic Input'
@@ -152,7 +147,7 @@ class ComicInput(InputFormatPlugin):
self.log.warning('Could not process the following pages '
'(run with --verbose to see why):')
for f in failures:
self.log.warning('\t', f)
self.log.warning('\t%s', f)
if not new_pages:
raise ValueError('Could not find any valid pages in comic: %s'
% comic)

4
ebook_converter/ebooks/conversion/plugins/fb2_input.py
View File

@@ -90,7 +90,7 @@ class FB2Input(InputFormatPlugin):
ss = f.read()
ss = ss.replace("__FB_NS__", fb_ns)
if options.no_inline_fb2_toc:
log('Disabling generation of inline FB2 TOC')
log.info('Disabling generation of inline FB2 TOC')
ss = re.compile(r'<!-- BUILD TOC -->.*<!-- END BUILD TOC -->',
re.DOTALL).sub('', ss)
@@ -180,7 +180,7 @@ class FB2Input(InputFormatPlugin):
data = base64_decode(raw)
except TypeError:
self.log.exception('Binary data with id=%s is corrupted, '
'ignoring' % elem.get('id'))
'ignoring', elem.get('id'))
else:
with open(fname, 'wb') as f:
f.write(data)

8
ebook_converter/ebooks/conversion/plugins/fb2_output.py
View File

@@ -3,11 +3,6 @@ import os
from ebook_converter.customize.conversion import OutputFormatPlugin, OptionRecommendation
__license__ = 'GPL 3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
class FB2Output(OutputFormatPlugin):
name = 'FB2 Output'
@@ -177,7 +172,8 @@ class FB2Output(OutputFormatPlugin):
rasterizer = SVGRasterizer()
rasterizer(oeb_book, opts)
except Unavailable:
log.warn('SVG rasterizer unavailable, SVG will not be converted')
log.warning('SVG rasterizer unavailable, SVG will not be '
'converted')
linearize_jacket(oeb_book)

22
ebook_converter/ebooks/conversion/plugins/html_input.py
View File

@@ -101,7 +101,7 @@ class HTMLInput(InputFormatPlugin):
if not metadata.language:
l = canonicalize_lang(getattr(opts, 'language', None))
if not l:
oeb.logger.warn('Language not specified')
oeb.logger.warning('Language not specified')
l = get_lang().replace('_', '-')
metadata.add('language', l)
if not metadata.creator:
@@ -109,12 +109,12 @@ class HTMLInput(InputFormatPlugin):
if a:
a = string_to_authors(a)
if not a:
oeb.logger.warn('Creator not specified')
oeb.logger.warning('Creator not specified')
a = [self.oeb.translate('Unknown')]
for aut in a:
metadata.add('creator', aut)
if not metadata.title:
oeb.logger.warn('Title not specified')
oeb.logger.warning('Title not specified')
metadata.add('title', self.oeb.translate('Unknown'))
bookid = str(uuid.uuid4())
metadata.add('identifier', bookid, id='uuid_id', scheme='uuid')
@@ -141,14 +141,14 @@ class HTMLInput(InputFormatPlugin):
self.added_resources = {}
self.log = log
self.log('Normalizing filename cases')
self.log.info('Normalizing filename cases')
for path, href in htmlfile_map.items():
self.added_resources[path] = href
self.urlnormalize, self.DirContainer = urlnormalize, DirContainer
self.urldefrag = urllib.parse.urldefrag
self.BINARY_MIME = BINARY_MIME
self.log('Rewriting HTML links')
self.log.info('Rewriting HTML links')
for f in filelist:
path = f.path
dpath = os.path.dirname(path)
@@ -208,12 +208,12 @@ class HTMLInput(InputFormatPlugin):
try:
link_ = link_.decode('utf-8', 'error')
except:
self.log.warn('Failed to decode link %r. Ignoring'%link_)
self.log.warning('Failed to decode link %r. Ignoring', link_)
return None, None
try:
l = Link(link_, base if base else os.getcwd())
except:
self.log.exception('Failed to process link: %r'%link_)
self.log.exception('Failed to process link: %r', link_)
return None, None
if l.path is None:
# Not a local resource
@@ -237,7 +237,7 @@ class HTMLInput(InputFormatPlugin):
if not os.access(link, os.R_OK):
return link_
if os.path.isdir(link):
self.log.warn(link_, 'is a link to a directory. Ignoring.')
self.log.warning(link_, 'is a link to a directory. Ignoring.')
return link_
if link not in self.added_resources:
bhref = os.path.basename(link)
@@ -245,7 +245,7 @@ class HTMLInput(InputFormatPlugin):
guessed = mimetypes.guess_type(href)[0]
media_type = guessed or self.BINARY_MIME
if media_type == 'text/plain':
self.log.warn('Ignoring link to text file %r'%link_)
self.log.warning('Ignoring link to text file %r', link_)
return None
if media_type == self.BINARY_MIME:
# Check for the common case, images
@@ -257,7 +257,7 @@ class HTMLInput(InputFormatPlugin):
if img:
media_type = mimetypes.guess_type('dummy.'+img)[0] or self.BINARY_MIME
self.oeb.log.debug('Added', link)
self.oeb.log.debug('Added %s', link)
self.oeb.container = self.DirContainer(os.path.dirname(link),
self.oeb.log, ignore_opf=True)
# Load into memory
@@ -287,6 +287,6 @@ class HTMLInput(InputFormatPlugin):
raw = f.read().decode('utf-8', 'replace')
raw = self.oeb.css_preprocessor(raw, add_namespace=False)
except:
self.log.exception('Failed to read CSS file: %r'%link)
self.log.exception('Failed to read CSS file: %r', link)
return (None, None)
return (None, raw)

2
ebook_converter/ebooks/conversion/plugins/html_output.py
View File

@@ -228,7 +228,7 @@ class HTMLOutput(OutputFormatPlugin):
shutil.rmtree(opts.extract_to)
os.makedirs(opts.extract_to)
zfile.extractall(opts.extract_to)
self.log('Zip file extracted to', opts.extract_to)
self.log.info('Zip file extracted to %s', opts.extract_to)
zfile.close()

4
ebook_converter/ebooks/conversion/plugins/htmlz_input.py
View File

@@ -55,8 +55,8 @@ class HTMLZInput(InputFormatPlugin):
# HTMLZ archive probably won't turn out as the user expects. With
# Multiple HTML files ZIP input should be used in place of HTMLZ.
if multiple_html:
log.warn('Multiple HTML files found in the archive. Only %s will '
'be used.' % index)
log.warning('Multiple HTML files found in the archive. Only %s '
'will be used.', index)
if index:
with open(index, 'rb') as tf:

4
ebook_converter/ebooks/conversion/plugins/lit_input.py
View File

@@ -40,8 +40,8 @@ class LITInput(InputFormatPlugin):
from ebook_converter.ebooks.txt.processor import \
convert_basic, separate_paragraphs_single_line
from ebook_converter.ebooks.chardet import xml_to_unicode
self.log('LIT file with all text in singe <pre> tag '
'detected')
self.log.info('LIT file with all text in singe <pre> tag '
'detected')
html = separate_paragraphs_single_line(pre.text)
html = convert_basic(html).replace('<html>',
'<html xmlns="%s">' %

7
ebook_converter/ebooks/conversion/plugins/mobi_input.py
View File

@@ -3,11 +3,6 @@ import os
from ebook_converter.customize.conversion import InputFormatPlugin
__license__ = 'GPL 3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
class MOBIInput(InputFormatPlugin):
name = 'MOBI Input'
@@ -37,7 +32,7 @@ class MOBIInput(InputFormatPlugin):
mr.extract_content('.', parse_cache)
if mr.kf8_type is not None:
log('Found KF8 MOBI of type %r'%mr.kf8_type)
log.info('Found KF8 MOBI of type %r', mr.kf8_type)
if mr.kf8_type == 'joint':
self.mobi_is_joint = True
from ebook_converter.ebooks.mobi.reader.mobi8 import Mobi8Reader

23
ebook_converter/ebooks/conversion/plugins/mobi_output.py
View File

@@ -2,11 +2,6 @@ from ebook_converter.customize.conversion import (OutputFormatPlugin,
OptionRecommendation)
__license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
def remove_html_cover(oeb, log):
from ebook_converter.ebooks.oeb.base import OEB_DOCS
@@ -17,10 +12,10 @@ def remove_html_cover(oeb, log):
del oeb.guide['cover']
item = oeb.manifest.hrefs[href]
if item.spine_position is not None:
log.warn('Found an HTML cover: ', item.href, 'removing it.',
'If you find some content missing from the output MOBI, it '
'is because you misidentified the HTML cover in the input '
'document')
log.warning('Found an HTML cover: %s', 'removing it. If you find some '
'content missing from the output MOBI, it is because you '
'misidentified the HTML cover in the input document',
item.href)
oeb.spine.remove(item)
if item.media_type in OEB_DOCS:
oeb.manifest.remove(item)
@@ -117,7 +112,8 @@ class MOBIOutput(OutputFormatPlugin):
found = 'masthead' in self.oeb.guide
if not found:
from ebook_converter.ebooks import generate_masthead
self.oeb.log.debug('No masthead found in manifest, generating default mastheadImage...')
self.oeb.log.debug('No masthead found in manifest, generating '
'default mastheadImage...')
raw = generate_masthead(str(self.oeb.metadata['title'][0]))
id, href = self.oeb.manifest.generate('masthead', 'masthead')
self.oeb.manifest.add(id, href, 'image/gif', data=raw)
@@ -132,7 +128,7 @@ class MOBIOutput(OutputFormatPlugin):
return
if toc and toc[0].klass != 'periodical':
one, two = self.oeb.spine[0], self.oeb.spine[1]
self.log('Converting TOC for MOBI periodical indexing...')
self.log.info('Converting TOC for MOBI periodical indexing...')
articles = {}
if toc.depth() < 3:
@@ -206,7 +202,7 @@ class MOBIOutput(OutputFormatPlugin):
extract_mobi(output_path, opts)
return
self.log('Creating MOBI 6 output')
self.log.info('Creating MOBI 6 output')
self.write_mobi(input_plugin, output_path, kf8, resources)
def create_kf8(self, resources, for_joint=False):
@@ -232,7 +228,8 @@ class MOBIOutput(OutputFormatPlugin):
rasterizer = SVGRasterizer()
rasterizer(oeb, opts)
except Unavailable:
self.log.warn('SVG rasterizer unavailable, SVG will not be converted')
self.log.warning('SVG rasterizer unavailable, SVG will not be '
'converted')
else:
# Add rasterized SVG images
resources.add_extra_images()

18
ebook_converter/ebooks/conversion/plugins/oeb_output.py
View File

@@ -34,13 +34,16 @@ class OEBOutput(OutputFormatPlugin):
try:
self.workaround_nook_cover_bug(root)
except:
self.log.exception('Something went wrong while trying to'
' workaround Nook cover bug, ignoring')
self.log.exception('Something went wrong while '
'trying to workaround Nook '
'cover bug, ignoring')
try:
self.workaround_pocketbook_cover_bug(root)
except:
self.log.exception('Something went wrong while trying to'
' workaround Pocketbook cover bug, ignoring')
self.log.exception('Something went wrong while '
'trying to workaround '
'Pocketbook cover bug, '
'ignoring')
self.migrate_lang_code(root)
raw = etree.tostring(root, pretty_print=True,
encoding='utf-8', xml_declaration=True)
@@ -80,9 +83,10 @@ class OEBOutput(OutputFormatPlugin):
manifest_item = manifest_items_with_id(covid)
if len(manifest_item) == 1 and \
manifest_item[0].get('media-type',
'').startswith('image/'):
self.log.warn('The cover image has an id != "cover". Renaming'
' to work around bug in Nook Color')
'').startswith('image/'):
self.log.warning('The cover image has an id != "cover". '
'Renaming to work around bug in Nook '
'Color')
from ebook_converter.ebooks.oeb.base import uuid_id
newid = uuid_id()

4
ebook_converter/ebooks/conversion/plugins/pdb_input.py
View File

@@ -25,8 +25,8 @@ class PDBInput(InputFormatPlugin):
(header.ident,
IDENTITY_TO_NAME.get(header.ident, 'Unknown')))
log.debug('Detected ebook format as: %s with identity: %s' %
(IDENTITY_TO_NAME[header.ident], header.ident))
log.debug('Detected ebook format as: %s with identity: %s',
IDENTITY_TO_NAME[header.ident], header.ident)
reader = Reader(header, stream, log, options)
opf = reader.extract_content(os.getcwd())

7
ebook_converter/ebooks/conversion/plugins/pml_input.py
View File

@@ -6,11 +6,6 @@ from ebook_converter.customize.conversion import InputFormatPlugin
from ebook_converter.ptempfile import TemporaryDirectory
__license__ = 'GPL v3'
__copyright__ = '2009, John Schember <john@nachtimwald.com>'
__docformat__ = 'restructuredtext en'
class PMLInput(InputFormatPlugin):
name = 'PML Input'
@@ -107,7 +102,7 @@ class PMLInput(InputFormatPlugin):
html_path = os.path.join(os.getcwd(), html_name)
pages.append(html_name)
log.debug('Processing PML item %s...' % pml)
log.debug('Processing PML item %s...', pml)
ttoc = self.process_pml(pml, html_path)
toc += ttoc
images = self.get_images(stream, tdir, True)

18
ebook_converter/ebooks/conversion/plugins/recipe_input.py
View File

@@ -63,7 +63,7 @@ class RecipeInput(InputFormatPlugin):
if os.environ.get('CALIBRE_RECIPE_URN'):
from ebook_converter.web.feeds.recipes.collection import get_custom_recipe, get_builtin_recipe_by_id
urn = os.environ['CALIBRE_RECIPE_URN']
log('Downloading recipe urn: ' + urn)
log.info('Downloading recipe urn: %s', urn)
rtype, recipe_id = urn.partition(':')[::2]
if not recipe_id:
raise ValueError('Invalid recipe urn: ' + urn)
@@ -80,7 +80,7 @@ class RecipeInput(InputFormatPlugin):
with open(recipe_or_file, 'rb') as f:
self.recipe_source = f.read()
recipe = compile_recipe(self.recipe_source)
log('Using custom recipe')
log.info('Using custom recipe')
else:
from ebook_converter.web.feeds.recipes.collection import (
get_builtin_recipe_by_title, get_builtin_recipe_titles)
@@ -98,16 +98,16 @@ class RecipeInput(InputFormatPlugin):
recipe = compile_recipe(raw)
self.recipe_source = raw
if recipe.requires_version > numeric_version:
log.warn(
'Downloaded recipe needs calibre version at least: %s' %
('.'.join(recipe.requires_version)))
log.warning('Downloaded recipe needs calibre version '
'at least: %s',
'.'.join(recipe.requires_version))
builtin = True
except:
log.exception('Failed to compile downloaded recipe. Falling '
'back to builtin one')
log.exception('Failed to compile downloaded recipe. '
'Falling back to builtin one')
builtin = True
if builtin:
log('Using bundled builtin recipe')
log.info('Using bundled builtin recipe')
raw = get_builtin_recipe_by_title(title, log=log,
download_recipe=False)
if raw is None:
@@ -115,7 +115,7 @@ class RecipeInput(InputFormatPlugin):
recipe = compile_recipe(raw)
self.recipe_source = raw
else:
log('Using downloaded builtin recipe')
log.info('Using downloaded builtin recipe')
if recipe is None:
raise ValueError('%r is not a valid recipe file or builtin recipe' %

16
ebook_converter/ebooks/conversion/plugins/rtf_input.py
View File

@@ -64,9 +64,9 @@ class RTFInput(InputFormatPlugin):
debug_dir = u'rtfdebug'
run_lev = 4
indent_out = 1
self.log('Running RTFParser in debug mode')
self.log.info('Running RTFParser in debug mode')
except Exception:
self.log.warn('Impossible to run RTFParser in debug mode')
self.log.warning('Impossible to run RTFParser in debug mode')
parser = ParseRtf(
in_file=stream,
out_file=ofile,
@@ -122,7 +122,7 @@ class RTFInput(InputFormatPlugin):
def extract_images(self, picts):
from ebook_converter.utils.imghdr import what
from binascii import unhexlify
self.log('Extracting images...')
self.log.info('Extracting images...')
with open(picts, 'rb') as f:
raw = f.read()
@@ -154,7 +154,7 @@ class RTFInput(InputFormatPlugin):
try:
imap[count] = self.convert_image(val)
except Exception:
self.log.exception('Failed to convert', val)
self.log.exception('Failed to convert %s', val)
return imap
def convert_image(self, name):
@@ -163,7 +163,7 @@ class RTFInput(InputFormatPlugin):
try:
return self.rasterize_wmf(name)
except Exception:
self.log.exception('Failed to convert WMF image %r' % name)
self.log.exception('Failed to convert WMF image %r', name)
return self.replace_wmf(name)
def replace_wmf(self, name):
@@ -258,7 +258,7 @@ class RTFInput(InputFormatPlugin):
from ebook_converter.ebooks.rtf.input import InlineClass
self.opts = options
self.log = log
self.log('Converting RTF to XML...')
self.log.info('Converting RTF to XML...')
try:
xml = self.generate_xml(stream.name)
except RtfInvalidCodeException as e:
@@ -275,7 +275,7 @@ class RTFInput(InputFormatPlugin):
except Exception:
self.log.exception('Failed to extract images...')
self.log('Parsing XML...')
self.log.info('Parsing XML...')
doc = etree.fromstring(xml)
border_styles = self.convert_borders(doc)
for pict in doc.xpath('//rtf:pict[@num]',
@@ -286,7 +286,7 @@ class RTFInput(InputFormatPlugin):
if name is not None:
pict.set('num', name)
self.log('Converting XML to HTML...')
self.log.info('Converting XML to HTML...')
inline_class = InlineClass(self.log)
with open(pkg_resources.resource_filename('ebook_converter',
'data/rtf.xsl')) as fobj:

28
ebook_converter/ebooks/conversion/plugins/snb_output.py
View File

@@ -5,11 +5,6 @@ from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.constants_old import __appname__, __version__
__license__ = 'GPL 3'
__copyright__ = '2010, Li Fanxi <lifanxi@freemindworld.com>'
__docformat__ = 'restructuredtext en'
class SNBOutput(OutputFormatPlugin):
name = 'SNB Output'
@@ -57,7 +52,8 @@ class SNBOutput(OutputFormatPlugin):
rasterizer = SVGRasterizer()
rasterizer(oeb_book, opts)
except Unavailable:
log.warn('SVG rasterizer unavailable, SVG will not be converted')
log.warning('SVG rasterizer unavailable, SVG will not be '
'converted')
# Create temp dir
with TemporaryDirectory('_snb_output') as tdir:
@@ -120,8 +116,8 @@ class SNBOutput(OutputFormatPlugin):
tocBody = etree.SubElement(tocInfoTree, "body")
outputFiles = {}
if oeb_book.toc.count() == 0:
log.warn('This SNB file has no Table of Contents. '
'Creating a default TOC')
log.warning('This SNB file has no Table of Contents. Creating '
'a default TOC')
first = next(iter(oeb_book.spine))
oeb_book.toc.add('Start page', first.href)
else:
@@ -141,7 +137,7 @@ class SNBOutput(OutputFormatPlugin):
if tocitem.href.find('#') != -1:
item = tocitem.href.split('#')
if len(item) != 2:
log.error('Error in TOC item: %s' % tocitem)
log.error('Error in TOC item: %s', tocitem)
else:
if item[0] in outputFiles:
outputFiles[item[0]].append((item[1], tocitem.title))
@@ -178,16 +174,18 @@ class SNBOutput(OutputFormatPlugin):
from ebook_converter.ebooks.oeb.base import OEB_DOCS, OEB_IMAGES
if m.hrefs[item.href].media_type in OEB_DOCS:
if item.href not in outputFiles:
log.debug('File %s is unused in TOC. Continue in last chapter' % item.href)
log.debug('File %s is unused in TOC. Continue in last '
'chapter', item.href)
mergeLast = True
else:
if oldTree is not None and mergeLast:
log.debug('Output the modified chapter again: %s' % lastName)
log.debug('Output the modified chapter again: %s',
lastName)
with open(os.path.join(snbcDir, lastName), 'wb') as f:
f.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
mergeLast = False
log.debug('Converting %s to snbc...' % item.href)
log.debug('Converting %s to snbc...', item.href)
snbwriter = SNBMLizer(log)
snbcTrees = None
if not mergeLast:
@@ -201,12 +199,12 @@ class SNBOutput(OutputFormatPlugin):
with open(os.path.join(snbcDir, lastName), 'wb') as f:
f.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
else:
log.debug('Merge %s with last TOC item...' % item.href)
log.debug('Merge %s with last TOC item...', item.href)
snbwriter.merge_content(oldTree, oeb_book, item,
[('', "Start")], opts)
# Output the last one if needed
log.debug('Output the last modified chapter again: %s' % lastName)
log.debug('Output the last modified chapter again: %s', lastName)
if oldTree is not None and mergeLast:
with open(os.path.join(snbcDir, lastName), 'wb') as f:
f.write(etree.tostring(oldTree, pretty_print=True, encoding='utf-8'))
@@ -214,7 +212,7 @@ class SNBOutput(OutputFormatPlugin):
for item in m:
if m.hrefs[item.href].media_type in OEB_IMAGES:
log.debug('Converting image: %s ...' % item.href)
log.debug('Converting image: %s ...', item.href)
content = m.hrefs[item.href].data
# Convert & Resize image
self.HandleImage(content, os.path.join(snbiDir, ProcessFileName(item.href)))

20
ebook_converter/ebooks/conversion/plugins/txt_input.py
View File

@@ -167,13 +167,14 @@ class TXTInput(InputFormatPlugin):
if file_ext in {'md', 'textile', 'markdown'}:
options.formatting_type = {'md': 'markdown'}.get(file_ext, file_ext)
log.info('File extension indicates particular formatting. '
'Forcing formatting type to: %s'%options.formatting_type)
'Forcing formatting type to: %s',
options.formatting_type)
options.paragraph_type = 'off'
# Get the encoding of the document.
if options.input_encoding:
ienc = options.input_encoding
log.debug('Using user specified input encoding of %s' % ienc)
log.debug('Using user specified input encoding of %s', ienc)
else:
det_encoding = detect(txt[:4096])
det_encoding, confidence = det_encoding['encoding'], det_encoding['confidence']
@@ -184,10 +185,12 @@ class TXTInput(InputFormatPlugin):
# gb2312 instead of gbk. gbk is a superset of gb2312, anyway.
det_encoding = 'gbk'
ienc = det_encoding
log.debug('Detected input encoding as %s with a confidence of %s%%' % (ienc, confidence * 100))
log.debug('Detected input encoding as %s with a confidence of '
'%s%%', ienc, confidence * 100)
if not ienc:
ienc = 'utf-8'
log.debug('No input encoding specified and could not auto detect using %s' % ienc)
log.debug('No input encoding specified and could not auto detect '
'using %s', ienc)
# Remove BOM from start of txt as its presence can confuse markdown
import codecs
for bom in (codecs.BOM_UTF16_LE, codecs.BOM_UTF16_BE, codecs.BOM_UTF8, codecs.BOM_UTF32_LE, codecs.BOM_UTF32_BE):
@@ -206,15 +209,18 @@ class TXTInput(InputFormatPlugin):
if options.paragraph_type == 'auto':
options.paragraph_type = detect_paragraph_type(txt)
if options.paragraph_type == 'unknown':
log.debug('Could not reliably determine paragraph type using block')
log.debug('Could not reliably determine paragraph type using '
'block')
options.paragraph_type = 'block'
else:
log.debug('Auto detected paragraph type as %s' % options.paragraph_type)
log.debug('Auto detected paragraph type as %s',
options.paragraph_type)
# Detect formatting
if options.formatting_type == 'auto':
options.formatting_type = detect_formatting_type(txt)
log.debug('Auto detected formatting as %s' % options.formatting_type)
log.debug('Auto detected formatting as %s',
options.formatting_type)
if options.formatting_type == 'heuristic':
setattr(options, 'enable_heuristics', True)