gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2025-12-18 13:10:17 +01:00
Code Issues Projects Releases Wiki Activity

Finalizing logging transition.

Browse Source
This commit is contained in:
gryf
2021-06-24 20:31:37 +02:00
parent 230fe90e69
commit 0a9536b180
16 changed files with 74 additions and 94 deletions
Download Patch File Download Diff File Expand all files Collapse all files

11
ebook_converter/ebooks/lrf/__init__.py
View File

@@ -10,11 +10,6 @@ from ebook_converter.ebooks.lrf.fonts import FONT_FILE_MAP
from ebook_converter.ebooks import ConversionError
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
__docformat__ = "epytext"
class LRFParseError(Exception):
pass
@@ -46,17 +41,17 @@ def find_custom_fonts(options, logger):
f = family(options.serif_family)
fonts['serif'] = font_scanner.legacy_fonts_for_family(f)
if not fonts['serif']:
logger.warn('Unable to find serif family %s'%f)
logger.warning('Unable to find serif family %s', f)
if options.sans_family:
f = family(options.sans_family)
fonts['sans'] = font_scanner.legacy_fonts_for_family(f)
if not fonts['sans']:
logger.warn('Unable to find sans family %s'%f)
logger.warning('Unable to find sans family %s', f)
if options.mono_family:
f = family(options.mono_family)
fonts['mono'] = font_scanner.legacy_fonts_for_family(f)
if not fonts['mono']:
logger.warn('Unable to find mono family %s'%f)
logger.warning('Unable to find mono family %s', f)
return fonts

8
ebook_converter/ebooks/mobi/mobiml.py
View File

@@ -15,9 +15,6 @@ from ebook_converter.ebooks.mobi.utils import convert_color_for_font_tag
from ebook_converter.utils.imghdr import identify
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.cam>'
MBP_NS = 'http://mobipocket.com/ns/mbp'
@@ -455,13 +452,12 @@ class MobiMLizer(object):
try:
item = self.oeb.manifest.hrefs[base.urlnormalize(href)]
except:
self.oeb.logger.warn('Failed to find image:',
href)
self.oeb.logger.warning('Failed to find image:', href)
else:
try:
width, height = identify(item.data)[1:]
except Exception:
self.oeb.logger.warn('Invalid image:', href)
self.oeb.logger.warning('Invalid image:', href)
else:
if 'width' not in istate.attrib and 'height' not in \
istate.attrib:

4
ebook_converter/ebooks/mobi/reader/headers.py
View File

@@ -215,8 +215,8 @@ class BookHeader(object):
}[self.codepage]
except (IndexError, KeyError):
self.codec = 'cp1252' if not user_encoding else user_encoding
log.warn('Unknown codepage %d. Assuming %s' % (self.codepage,
self.codec))
log.warning('Unknown codepage %d. Assuming %s', self.codepage,
self.codec)
# Some KF8 files have header length == 264 (generated by kindlegen
# 2.9?). See https://bugs.launchpad.net/bugs/1179144
max_header_length = 500 # We choose 500 for future versions of kindlegen

35
ebook_converter/ebooks/mobi/reader/markup.py
View File

@@ -36,7 +36,8 @@ def update_internal_links(mobi8_reader, log):
filename, idtag = mr.get_id_tag_by_pos_fid(
int(posfid, 32), int(offset, 32))
except ValueError:
log.warn('Invalid link, points to nowhere, ignoring')
log.warning('Invalid link, points to nowhere, '
'ignoring')
replacement = b'#'
else:
suffix = (b'#' + idtag) if idtag else b''
@@ -49,7 +50,8 @@ def update_internal_links(mobi8_reader, log):
try:
parts.append(raw.decode(mr.header.codec))
except UnicodeDecodeError:
log.warn('Failed to decode text in KF8 part, replacing bad bytes')
log.warning('Failed to decode text in KF8 part, replacing bad '
'bytes')
parts.append(raw.decode(mr.header.codec, 'replace'))
# All parts are now unicode and have no internal links
@@ -130,7 +132,8 @@ def update_flow_links(mobi8_reader, resource_map, log):
try:
flow = flow.decode(mr.header.codec)
except UnicodeDecodeError:
log.error('Flow part has invalid %s encoded bytes'%mr.header.codec)
log.error('Flow part has invalid %s encoded bytes',
mr.header.codec)
flow = flow.decode(mr.header.codec, 'replace')
# links to raster image files from image tags
@@ -146,8 +149,8 @@ def update_flow_links(mobi8_reader, resource_map, log):
replacement = '"%s"'%('../'+ href)
tag = img_index_pattern.sub(replacement, tag, 1)
else:
log.warn('Referenced image %s was not recognized '
'as a valid image in %s' % (num, tag))
log.warning('Referenced image %s was not recognized '
'as a valid image in %s', num, tag)
srcpieces[j] = tag
flow = "".join(srcpieces)
@@ -164,16 +167,16 @@ def update_flow_links(mobi8_reader, resource_map, log):
replacement = '"%s"'%('../'+ href)
tag = url_img_index_pattern.sub(replacement, tag, 1)
else:
log.warn('Referenced image %s was not recognized as a '
'valid image in %s' % (num, tag))
log.warning('Referenced image %s was not recognized as a '
'valid image in %s', num, tag)
# process links to fonts
for m in font_index_pattern.finditer(tag):
num = int(m.group(1), 32)
href = resource_map[num-1]
if href is None:
log.warn('Referenced font %s was not recognized as a '
'valid font in %s' % (num, tag))
log.warning('Referenced font %s was not recognized as a '
'valid font in %s', num, tag)
else:
replacement = '"%s"'%('../'+ href)
if href.endswith('.failed'):
@@ -200,7 +203,8 @@ def update_flow_links(mobi8_reader, resource_map, log):
num = int(m.group(1), 32)
fi = mr.flowinfo[num]
except IndexError:
log.warn('Ignoring invalid flow reference in tag', tag)
log.warning('Ignoring invalid flow reference in '
'tag %s', tag)
tag = ''
else:
if fi.format == 'inline':
@@ -237,7 +241,8 @@ def insert_flows_into_markup(parts, flows, mobi8_reader, log):
try:
fi = mr.flowinfo[num]
except IndexError:
log.warn('Ignoring invalid flow reference: %s'%m.group())
log.warning('Ignoring invalid flow reference: %s',
m.group())
tag = ''
else:
if fi.format == 'inline':
@@ -273,8 +278,8 @@ def insert_images_into_markup(parts, resource_map, log):
replacement = '"%s"'%('../' + href)
tag = img_index_pattern.sub(replacement, tag, 1)
else:
log.warn('Referenced image %s was not recognized as '
'a valid image in %s' % (num, tag))
log.warning('Referenced image %s was not recognized '
'as a valid image in %s', num, tag)
srcpieces[j] = tag
part = "".join(srcpieces)
# store away modified version
@@ -296,8 +301,8 @@ def insert_images_into_markup(parts, resource_map, log):
replacement = '%s%s%s'%(osep, '../' + href, csep)
tag = img_index_pattern.sub(replacement, tag, 1)
else:
log.warn('Referenced image %s was not recognized as '
'a valid image in %s' % (num, tag))
log.warning('Referenced image %s was not recognized '
'as a valid image in %s', num, tag)
srcpieces[j] = tag
part = "".join(srcpieces)
# store away modified version

10
ebook_converter/ebooks/mobi/reader/mobi6.py
View File

@@ -231,7 +231,7 @@ class MobiReader(object):
keep_doctype=False, sanitize_names=True)
if root.tag != 'html':
self.log.warn('File does not have opening <html> tag')
self.log.warning('File does not have opening <html> tag')
nroot = html.fromstring('<html><head></head><body></body></html>')
bod = nroot.find('body')
for child in list(root):
@@ -242,7 +242,7 @@ class MobiReader(object):
htmls = list(root.xpath('//html'))
if len(htmls) > 1:
self.log.warn('Markup contains multiple <html> tags, merging.')
self.log.warning('Markup contains multiple <html> tags, merging.')
# Merge all <head> and <body> sections
for h in htmls:
p = h.getparent()
@@ -833,9 +833,9 @@ class MobiReader(object):
def warn_about_trailing_entry_corruption(self):
if not self.warned_about_trailing_entry_corruption:
self.warned_about_trailing_entry_corruption = True
self.log.warn('The trailing data entries in this MOBI file are '
'corrupted, you might see corrupted text in the '
'output')
self.log.warning('The trailing data entries in this MOBI file are '
'corrupted, you might see corrupted text in the '
'output')
def text_section(self, index):
data = self.sections[index][0]

18
ebook_converter/ebooks/mobi/reader/mobi8.py
View File

@@ -205,9 +205,9 @@ class Mobi8Reader(object):
# This can happen for some badly formed KF8 files, see for
# example, https://bugs.launchpad.net/bugs/1082669
if not inspos_warned:
self.log.warn('The div table for %s has incorrect '
'insert positions. Calculating '
'manually.' % skelname)
self.log.warning('The div table for %s has incorrect '
'insert positions. Calculating '
'manually.', skelname)
inspos_warned = True
bp, ep = locate_beg_end_of_tag(skeleton, aidtext if
isinstance(aidtext, bytes)
@@ -396,8 +396,8 @@ class Mobi8Reader(object):
try:
href, idtag = self.get_id_tag_by_pos_fid(*pos_fid)
except ValueError:
self.log.warn('Invalid entry in NCX (title: %s), '
'ignoring' % entry['text'])
self.log.warning('Invalid entry in NCX (title: %s), '
'ignoring', entry['text'])
remove.append(entry)
continue
@@ -436,10 +436,10 @@ class Mobi8Reader(object):
font = read_font_record(data)
href = "fonts/%05d.%s" % (fname_idx, font['ext'])
if font['err']:
self.log.warn('Reading font record %d failed: %s' %
(fname_idx, font['err']))
self.log.warning('Reading font record %d failed: %s',
fname_idx, font['err'])
if font['headers']:
self.log.debug('Font record headers: %s' %
self.log.debug('Font record headers: %s',
font['headers'])
with open(href.replace('/', os.sep), 'wb') as f:
f.write(font['font_data'] if font['font_data'] else
@@ -484,7 +484,7 @@ class Mobi8Reader(object):
mi.cover = resource_map[self.cover_offset]
if len(list(toc)) < 2:
self.log.warn('KF8 has no metadata Table of Contents')
self.log.warning('KF8 has no metadata Table of Contents')
for ref in guide:
if ref.type == 'toc':

22
ebook_converter/ebooks/mobi/utils.py
View File

@@ -351,7 +351,7 @@ def align_block(raw, multiple=4, pad=b'\0'):
return raw + pad*(multiple - extra)
def detect_periodical(toc, log=None):
def detect_periodical(toc, log):
'''
Detect if the TOC object toc contains a periodical that conforms to the
structure required by kindlegen to generate a periodical.
@@ -360,25 +360,19 @@ def detect_periodical(toc, log=None):
return False
for node in toc.iterdescendants():
if node.depth() == 1 and node.klass != 'article':
if log is not None:
log.debug(
'Not a periodical: Deepest node does not have '
'class="article"')
log.debug('Not a periodical: Deepest node does not have '
'class="article"')
return False
if node.depth() == 2 and node.klass != 'section':
if log is not None:
log.debug(
'Not a periodical: Second deepest node does not have'
' class="section"')
log.debug('Not a periodical: Second deepest node does not have '
'class="section"')
return False
if node.depth() == 3 and node.klass != 'periodical':
if log is not None:
log.debug('Not a periodical: Third deepest node'
' does not have class="periodical"')
log.debug('Not a periodical: Third deepest node does not have '
'class="periodical"')
return False
if node.depth() > 3:
if log is not None:
log.debug('Not a periodical: Has nodes of depth > 3')
log.debug('Not a periodical: Has nodes of depth > 3')
return False
return True

8
ebook_converter/ebooks/mobi/writer2/indexer.py
View File

@@ -444,8 +444,8 @@ class Indexer(object): # {{{
if self.is_periodical and self.masthead_offset is None:
raise ValueError('Periodicals must have a masthead')
self.log('Generating MOBI index for a %s'%('periodical' if
self.is_periodical else 'book'))
self.log('Generating MOBI index for a %s', 'periodical' if
self.is_periodical else 'book')
self.is_flat_periodical = False
if self.is_periodical:
periodical_node = next(iter(oeb.toc))
@@ -634,8 +634,8 @@ class Indexer(object): # {{{
offset = id_offsets[node.href]
label = self.cncx[node.title]
except:
self.log.warn('TOC item %s [%s] not found in document'%(
node.title, node.href))
self.log.warn('TOC item %s [%s] not found in document',
node.title, node.href)
continue
if offset in seen:

6
ebook_converter/ebooks/mobi/writer2/main.py
View File

@@ -12,10 +12,6 @@ from ebook_converter.ebooks.mobi.utils import (encint, encode_trailing_data,
from ebook_converter.ebooks.mobi.writer2.indexer import Indexer
__license__ = 'GPL v3'
__copyright__ = '2011, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
# Disabled as I dont care about uncrossable breaks
WRITE_UNCROSSABLE_BREAKS = False
NULL_INDEX = 0xffffffff
@@ -89,7 +85,7 @@ class MobiWriter(object):
def generate_index(self):
self.primary_index_record_idx = None
if self.oeb.toc.count() < 1:
self.log.warn('No TOC, MOBI index not generated')
self.log.warning('No TOC, MOBI index not generated')
return
try:
self.indexer = Indexer(self.serializer, self.last_text_record_idx,

6
ebook_converter/ebooks/mobi/writer2/resources.py
View File

@@ -97,7 +97,7 @@ class Resources(object):
try:
data = self.process_image(item.data)
except:
self.log.warn('Bad image file %r' % item.href)
self.log.warning('Bad image file %r', item.href)
continue
else:
if mh_href and item.href == mh_href:
@@ -117,7 +117,7 @@ class Resources(object):
data = rescale_image(item.data, dimen=MAX_THUMB_DIMEN,
maxsizeb=MAX_THUMB_SIZE)
except:
self.log.warn('Failed to generate thumbnail')
self.log.warning('Failed to generate thumbnail')
else:
self.image_indices.add(len(self.records))
self.records.append(data)
@@ -145,7 +145,7 @@ class Resources(object):
try:
data = self.process_image(item.data)
except:
self.log.warn('Bad image file %r' % item.href)
self.log.warning('Bad image file %r', item.href)
else:
self.records.append(data)
self.item_map[item.href] = len(self.records)

2
ebook_converter/ebooks/mobi/writer2/serializer.py
View File

@@ -380,7 +380,7 @@ class Serializer(object):
is_start = (href and href == start_href)
# Iterate over all filepos items
if href not in id_offsets:
self.logger.warn('Hyperlink target %r not found' % href)
self.logger.warning('Hyperlink target %r not found', href)
# Link to the top of the document, better than just ignoring
href, _ = urllib.parse.urldefrag(href)
if href in self.id_offsets:

7
ebook_converter/ebooks/mobi/writer8/cleanup.py
View File

@@ -1,11 +1,6 @@
from ebook_converter.ebooks.oeb.base import XPath
__license__ = 'GPL v3'
__copyright__ = '2012, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
class CSSCleanup(object):
def __init__(self, log, opts):
@@ -34,7 +29,7 @@ def remove_duplicate_anchors(oeb):
anchor = tag.get(attr)
if anchor is not None:
if anchor in seen:
oeb.log.debug('Removing duplicate anchor:', anchor)
oeb.log.debug('Removing duplicate anchor: %s', anchor)
tag.attrib.pop(attr)
else:
seen.add(anchor)

2
ebook_converter/ebooks/oeb/transforms/htmltoc.py
View File

@@ -62,7 +62,7 @@ class HTMLTOCAdder(object):
title = self.title or oeb.translate(DEFAULT_TITLE)
style = self.style
if style not in STYLE_CSS:
oeb.logger.error('Unknown TOC style %r' % style)
oeb.logger.error('Unknown TOC style %r', style)
style = 'nested'
id, css_href = oeb.manifest.generate('tocstyle', 'tocstyle.css')
oeb.manifest.add(id, css_href, base.CSS_MIME, data=STYLE_CSS[style])

20
ebook_converter/ebooks/oeb/transforms/rasterize.py
View File

@@ -65,17 +65,19 @@ class SVGRasterizer(object):
box = [float(x) for x in filter(None, re.split('[, ]', view_box))]
sizes = [box[2]-box[0], box[3] - box[1]]
except (TypeError, ValueError, IndexError):
logger.warn('SVG image has invalid viewBox="%s", ignoring the viewBox' % view_box)
logger.warning('SVG image has invalid viewBox="%s", ignoring '
'the viewBox', view_box)
else:
for image in elem.xpath('descendant::*[local-name()="image" and '
'@height and contains(@height, "%")]'):
logger.info('Found SVG image height in %, trying to convert...')
logger.info('Found SVG image height in %, trying to '
'convert...')
try:
h = float(image.get('height').replace('%', ''))/100.
image.set('height', str(h*sizes[1]))
except:
logger.exception('Failed to convert percentage height:',
image.get('height'))
logger.exception('Failed to convert percentage '
'height: %s', image.get('height'))
data = QByteArray(xml2str(elem, with_tail=False))
svg = QSvgRenderer(data)
@@ -85,8 +87,8 @@ class SVGRasterizer(object):
size.setHeight(sizes[1])
if width or height:
size.scale(width, height, Qt.KeepAspectRatio)
logger.info('Rasterizing %r to %dx%d'
% (elem, size.width(), size.height()))
logger.info('Rasterizing %r to %dx%d', elem, size.width(),
size.height())
image = QImage(size, QImage.Format_ARGB32_Premultiplied)
image.fill(QColor("white").rgb())
painter = QPainter(image)
@@ -186,8 +188,8 @@ class SVGRasterizer(object):
href = self.images[key]
else:
logger = self.oeb.logger
logger.info('Rasterizing %r to %dx%d'
% (svgitem.href, size.width(), size.height()))
logger.info('Rasterizing %r to %dx%d', svgitem.href, size.width(),
size.height())
image = QImage(size, QImage.Format_ARGB32_Premultiplied)
image.fill(QColor("white").rgb())
painter = QPainter(image)
@@ -219,7 +221,7 @@ class SVGRasterizer(object):
if not covers:
return
if str(covers[0]) not in self.oeb.manifest.ids:
self.oeb.logger.warn('Cover not in manifest, skipping.')
self.oeb.logger.warning('Cover not in manifest, skipping.')
self.oeb.metadata.clear('cover')
return
cover = self.oeb.manifest.ids[str(covers[0])]

6
ebook_converter/ebooks/oeb/transforms/trimmanifest.py
View File

@@ -7,10 +7,6 @@ from ebook_converter.ebooks.oeb.base import CSS_MIME, OEB_DOCS
from ebook_converter.ebooks.oeb.base import urlnormalize, iterlinks
__license__ = 'GPL v3'
__copyright__ = '2008, Marshall T. Vandegrift <llasram@gmail.com>'
class ManifestTrimmer(object):
@classmethod
@@ -69,5 +65,5 @@ class ManifestTrimmer(object):
unchecked = new
for item in oeb.manifest.values():
if item not in used:
oeb.logger.info('Trimming %r from manifest' % item.href)
oeb.logger.info('Trimming %r from manifest', item.href)
oeb.manifest.remove(item)

3
ebook_converter/ebooks/txt/textileml.py
View File

@@ -53,7 +53,8 @@ class TextileMLizer(OEB2HTML):
def mlize_spine(self, oeb_book):
output = ['']
for item in oeb_book.spine:
self.log.debug('Converting %s to Textile formatted TXT...', item.href)
self.log.debug('Converting %s to Textile formatted TXT...',
item.href)
self.rewrite_ids(item.data, item)
rewrite_links(item.data, partial(self.rewrite_link, page=item))
stylizer = Stylizer(item.data, item.href, oeb_book, self.opts, self.opts.output_profile)