gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-03-31 09:23:32 +02:00
Code Issues Projects Releases Wiki Activity

Re added (probably) right formating codes.

Browse Source
This commit is contained in:
gryf
2021-06-22 22:06:09 +02:00
parent 546cc26652
commit 84abd62a61
18 changed files with 39 additions and 58 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ebook_converter/ebooks/conversion/cli.py
View File

@@ -285,7 +285,7 @@ def create_option_parser(args, log):
log.info('Available recipes:') log.info('Available recipes:')
titles = sorted(get_builtin_recipe_titles()) titles = sorted(get_builtin_recipe_titles())
for title in titles: for title in titles:
log.info('\t%s', title) log.info('\t%r', title)
log.info('%d recipes available', len(titles)) log.info('%d recipes available', len(titles))
raise SystemExit(0) raise SystemExit(0)

2
ebook_converter/ebooks/conversion/plumber.py
View File

@@ -1108,7 +1108,7 @@ OptionRecommendation(name='search_replace',
try: try:
fkey = list(map(float, fkey.split(','))) fkey = list(map(float, fkey.split(',')))
except Exception: except Exception:
self.log.error('Invalid font size key: %s ignoring', fkey) self.log.error('Invalid font size key: %r ignoring', fkey)
fkey = self.opts.dest.fkey fkey = self.opts.dest.fkey
if self.opts.debug_pipeline is not None: if self.opts.debug_pipeline is not None:

4
ebook_converter/ebooks/oeb/base.py
View File

@@ -957,11 +957,11 @@ class Manifest(object):
def _fetch_css(self, path): def _fetch_css(self, path):
hrefs = self.oeb.manifest.hrefs hrefs = self.oeb.manifest.hrefs
if path not in hrefs: if path not in hrefs:
self.oeb.logger.warning('CSS import of missing file %s', path) self.oeb.logger.warning('CSS import of missing file %r', path)
return (None, None) return (None, None)
item = hrefs[path] item = hrefs[path]
if item.media_type not in OEB_STYLES: if item.media_type not in OEB_STYLES:
self.oeb.logger.warning('CSS import of non-CSS file %s', path) self.oeb.logger.warning('CSS import of non-CSS file %r', path)
return (None, None) return (None, None)
data = item.data.cssText data = item.data.cssText
enc = None if isinstance(data, str) else 'utf-8' enc = None if isinstance(data, str) else 'utf-8'

4
ebook_converter/ebooks/oeb/parse_utils.py
View File

@@ -239,7 +239,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
if barename(data.tag) != 'html': if barename(data.tag) != 'html':
if barename(data.tag) in non_html_file_tags: if barename(data.tag) in non_html_file_tags:
raise NotHTML(data.tag) raise NotHTML(data.tag)
log.warning('File %s does not appear to be (X)HTML', filename) log.warning('File %r does not appear to be (X)HTML', filename)
nroot = etree.fromstring('<html></html>') nroot = etree.fromstring('<html></html>')
has_body = False has_body = False
for child in list(data): for child in list(data):
@@ -248,7 +248,7 @@ def parse_html(data, log=None, decoder=None, preprocessor=None,
break break
parent = nroot parent = nroot
if not has_body: if not has_body:
log.warning('File %s appears to be a HTML fragment', filename) log.warning('File %r appears to be a HTML fragment', filename)
nroot = etree.fromstring('<html><body/></html>') nroot = etree.fromstring('<html><body/></html>')
parent = nroot[0] parent = nroot[0]
for child in list(data.iter()): for child in list(data.iter()):

24
ebook_converter/ebooks/oeb/reader.py
View File

@@ -216,7 +216,7 @@ class OEBReader(object):
scheme = urllib.parse.urlparse(href).scheme scheme = urllib.parse.urlparse(href).scheme
except Exception: except Exception:
self.oeb.log.exception('Skipping invalid href: ' self.oeb.log.exception('Skipping invalid href: '
'%s', href) '%r', href)
continue continue
if not scheme and href not in known: if not scheme and href not in known:
new.add(href) new.add(href)
@@ -244,12 +244,12 @@ class OEBReader(object):
continue continue
if not self.oeb.container.exists(href): if not self.oeb.container.exists(href):
if href not in warned: if href not in warned:
self.logger.warning('Referenced file %s not found', self.logger.warning('Referenced file %r not found',
href) href)
warned.add(href) warned.add(href)
continue continue
if href not in warned: if href not in warned:
self.logger.warning('Referenced file %s not in manifest', self.logger.warning('Referenced file %r not in manifest',
href) href)
warned.add(href) warned.add(href)
id, _ = manifest.generate(id='added') id, _ = manifest.generate(id='added')
@@ -276,13 +276,13 @@ class OEBReader(object):
media_type = media_type.lower() media_type = media_type.lower()
fallback = elem.get('fallback') fallback = elem.get('fallback')
if href in manifest.hrefs: if href in manifest.hrefs:
self.logger.warning('Duplicate manifest entry for %s', href) self.logger.warning('Duplicate manifest entry for %r', href)
continue continue
if not self.oeb.container.exists(href): if not self.oeb.container.exists(href):
self.logger.warning('Manifest item %s not found', href) self.logger.warning('Manifest item %r not found', href)
continue continue
if id in manifest.ids: if id in manifest.ids:
self.logger.warning('Duplicate manifest id %s', id) self.logger.warning('Duplicate manifest id %r', id)
id, href = manifest.generate(id, href) id, href = manifest.generate(id, href)
manifest.add(id, href, media_type, fallback) manifest.add(id, href, media_type, fallback)
invalid = self._manifest_prune_invalid() invalid = self._manifest_prune_invalid()
@@ -324,7 +324,7 @@ class OEBReader(object):
if item.href in removed_items_to_ignore: if item.href in removed_items_to_ignore:
continue continue
if version >= 2: if version >= 2:
self.logger.warning('Spine-referenced file %s not in spine', self.logger.warning('Spine-referenced file %r not in spine',
item.href) item.href)
spine.add(item, linear=False) spine.add(item, linear=False)
@@ -334,7 +334,7 @@ class OEBReader(object):
for elem in base.xpath(opf, '/o2:package/o2:spine/o2:itemref'): for elem in base.xpath(opf, '/o2:package/o2:spine/o2:itemref'):
idref = elem.get('idref') idref = elem.get('idref')
if idref not in manifest.ids: if idref not in manifest.ids:
self.logger.warning('Spine item %s not found', idref) self.logger.warning('Spine item %r not found', idref)
continue continue
item = manifest.ids[idref] item = manifest.ids[idref]
if (item.media_type.lower() in base.OEB_DOCS and if (item.media_type.lower() in base.OEB_DOCS and
@@ -370,7 +370,7 @@ class OEBReader(object):
corrected_href = href corrected_href = href
break break
if corrected_href is None: if corrected_href is None:
self.logger.warning('Guide reference %s not found', self.logger.warning('Guide reference %r not found',
ref_href) ref_href)
continue continue
ref_href = corrected_href ref_href = corrected_href
@@ -413,7 +413,7 @@ class OEBReader(object):
if path and path not in self.oeb.manifest.hrefs: if path and path not in self.oeb.manifest.hrefs:
path = base.urlnormalize(path) path = base.urlnormalize(path)
if href and path not in self.oeb.manifest.hrefs: if href and path not in self.oeb.manifest.hrefs:
self.logger.warning('TOC reference %s not found', href) self.logger.warning('TOC reference %r not found', href)
gc = base.xpath(child, 'ncx:navPoint') gc = base.xpath(child, 'ncx:navPoint')
if not gc: if not gc:
# This node is useless # This node is useless
@@ -490,7 +490,7 @@ class OEBReader(object):
continue continue
path, _ = urllib.parse.urldefrag(base.urlnormalize(href)) path, _ = urllib.parse.urldefrag(base.urlnormalize(href))
if path not in self.oeb.manifest.hrefs: if path not in self.oeb.manifest.hrefs:
self.logger.warning('TOC reference %s not found', href) self.logger.warning('TOC reference %r not found', href)
continue continue
id = site.get('id') id = site.get('id')
toc.add(title, href, id=id) toc.add(title, href, id=id)
@@ -658,7 +658,7 @@ class OEBReader(object):
if item is not None and item.media_type in base.OEB_IMAGES: if item is not None and item.media_type in base.OEB_IMAGES:
return item return item
else: else:
self.logger.warning('Invalid cover image @id %s', id) self.logger.warning('Invalid cover image @id %r', id)
hcover = self.oeb.spine[0] hcover = self.oeb.spine[0]
if 'cover' in self.oeb.guide: if 'cover' in self.oeb.guide:
href = self.oeb.guide['cover'].href href = self.oeb.guide['cover'].href

10
ebook_converter/ebooks/oeb/stylizer.py
View File

@@ -248,7 +248,7 @@ class Stylizer(object):
sitem = hrefs[ihref] sitem = hrefs[ihref]
if sitem.media_type not in base.OEB_STYLES: if sitem.media_type not in base.OEB_STYLES:
self.logger.warning('CSS @import of non-CSS ' self.logger.warning('CSS @import of non-CSS '
'file %s', rule.href) 'file %r', rule.href)
continue continue
stylesheets.append(sitem.data) stylesheets.append(sitem.data)
# Make links to resources absolute, since these rules will # Make links to resources absolute, since these rules will
@@ -264,11 +264,11 @@ class Stylizer(object):
path = item.abshref(href) path = item.abshref(href)
sitem = oeb.manifest.hrefs.get(path, None) sitem = oeb.manifest.hrefs.get(path, None)
if sitem is None: if sitem is None:
self.logger.warning('Stylesheet %s referenced by file %s ' self.logger.warning('Stylesheet %r referenced by file %r '
'not in manifest', path, item.href) 'not in manifest', path, item.href)
continue continue
if not hasattr(sitem.data, 'cssRules'): if not hasattr(sitem.data, 'cssRules'):
self.logger.warning('Stylesheet %s referenced by file %s ' self.logger.warning('Stylesheet %r referenced by file %r '
'is not CSS', path, item.href) 'is not CSS', path, item.href)
continue continue
stylesheets.append(sitem.data) stylesheets.append(sitem.data)
@@ -304,7 +304,7 @@ class Stylizer(object):
matches = tuple(select(text)) matches = tuple(select(text))
except SelectorError as err: except SelectorError as err:
self.logger.error('Ignoring CSS rule with invalid selector: ' self.logger.error('Ignoring CSS rule with invalid selector: '
'%s (%s)', text, err) '%r (%s)', text, err)
continue continue
if fl is not None: if fl is not None:
@@ -368,7 +368,7 @@ class Stylizer(object):
def _fetch_css_file(self, path): def _fetch_css_file(self, path):
hrefs = self.oeb.manifest.hrefs hrefs = self.oeb.manifest.hrefs
if path not in hrefs: if path not in hrefs:
self.logger.warning('CSS import of missing file %s', path) self.logger.warning('CSS import of missing file %r', path)
return (None, None) return (None, None)
item = hrefs[path] item = hrefs[path]
if item.media_type not in base.OEB_STYLES: if item.media_type not in base.OEB_STYLES:

5
ebook_converter/ebooks/oeb/transforms/filenames.py
View File

@@ -6,11 +6,6 @@ from lxml import etree
from ebook_converter.ebooks.oeb.base import rewrite_links, urlnormalize from ebook_converter.ebooks.oeb.base import rewrite_links, urlnormalize
__license__ = 'GPL v3'
__copyright__ = '2010, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en'
class RenameFiles(object): # {{{ class RenameFiles(object): # {{{
''' '''

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

@@ -149,7 +149,7 @@ class RemoveFakeMargins(object):
remove = set() remove = set()
for k, v in self.levels.items(): for k, v in self.levels.items():
num = len(v) num = len(v)
self.log.debug('Found %s items of level: %s', num, k) self.log.debug('Found %d items of level: %s', num, k)
level = int(k.split('_')[-1]) level = int(k.split('_')[-1])
tag = k.split('_')[0] tag = k.split('_')[0]
if tag == 'p' and num < 25: if tag == 'p' and num < 25:

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

@@ -60,7 +60,7 @@ class RescaleImages(object):
if scaled: if scaled:
new_width = max(1, new_width) new_width = max(1, new_width)
new_height = max(1, new_height) new_height = max(1, new_height)
self.log('Rescaling image from %sx%s to %sx%s %s', width, self.log('Rescaling image from %dx%d to %dx%d %s', width,
height, new_width, new_height, item.href) height, new_width, new_height, item.href)
try: try:
img = img.resize((new_width, new_height)) img = img.resize((new_width, new_height))

11
ebook_converter/ebooks/oeb/transforms/split.py
View File

@@ -22,9 +22,6 @@ from ebook_converter.css_selectors import Select, SelectorError
from ebook_converter.utils import encoding as uenc from ebook_converter.utils import encoding as uenc
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal kovid@kovidgoyal.net'
__docformat__ = 'restructuredtext en'
XPath = functools.partial(_XPath, namespaces=const.XPNSMAP) XPath = functools.partial(_XPath, namespaces=const.XPNSMAP)
SPLIT_POINT_ATTR = 'csp' SPLIT_POINT_ATTR = 'csp'
@@ -128,7 +125,7 @@ class Split(object):
page_breaks.add(elem) page_breaks.add(elem)
except SelectorError as err: except SelectorError as err:
self.log.warn('Ignoring page breaks specified with invalid ' self.log.warn('Ignoring page breaks specified with invalid '
'CSS selector: %s (%s)', selector, err) 'CSS selector: %r (%s)', selector, err)
for i, elem in enumerate(item.data.iter('*')): for i, elem in enumerate(item.data.iter('*')):
try: try:
@@ -227,7 +224,7 @@ class FlowSplitter(object):
for i, tree in enumerate(trees): for i, tree in enumerate(trees):
size = len(tostring(tree.getroot())) size = len(tostring(tree.getroot()))
if size > self.max_flow_size: if size > self.max_flow_size:
self.log.info('\tFound large tree #%s', i) self.log.info('\tFound large tree #%d', i)
lt_found = True lt_found = True
self.split_trees = [] self.split_trees = []
self.split_to_size(tree) self.split_to_size(tree)
@@ -240,7 +237,7 @@ class FlowSplitter(object):
self.was_split = len(self.trees) > 1 self.was_split = len(self.trees) > 1
if self.was_split: if self.was_split:
self.log('\tSplit into %s parts', len(self.trees)) self.log('\tSplit into %d parts', len(self.trees))
self.commit() self.commit()
def split_on_page_breaks(self, orig_tree): def split_on_page_breaks(self, orig_tree):
@@ -380,7 +377,7 @@ class FlowSplitter(object):
continue continue
elif size <= self.max_flow_size: elif size <= self.max_flow_size:
self.split_trees.append(t) self.split_trees.append(t)
self.log.debug('\t\t\tCommitted sub-tree #%s (%s KB)', self.log.debug('\t\t\tCommitted sub-tree #%d (%d KB)',
len(self.split_trees), size/1024.) len(self.split_trees), size/1024.)
else: else:
self.log.debug('\t\t\tSplit tree still too large: %d KB', self.log.debug('\t\t\tSplit tree still too large: %d KB',

4
ebook_converter/ebooks/oeb/transforms/structure.py
View File

@@ -67,7 +67,7 @@ class DetectStructure(object):
self.oeb.toc = orig_toc self.oeb.toc = orig_toc
else: else:
self.oeb.auto_generated_toc = True self.oeb.auto_generated_toc = True
self.log.info('Auto generated TOC with %s entries.', self.log.info('Auto generated TOC with %d entries.',
self.oeb.toc.count()) self.oeb.toc.count())
if opts.toc_filter is not None: if opts.toc_filter is not None:
@@ -240,7 +240,7 @@ class DetectStructure(object):
play_order=self.oeb.toc.next_play_order()) play_order=self.oeb.toc.next_play_order())
num += 1 num += 1
except ValueError: except ValueError:
self.oeb.log.critical('Failed to process link: %s', self.oeb.log.critical('Failed to process link: %r',
href) href)
# Most likely an incorrectly URL encoded link # Most likely an incorrectly URL encoded link
continue continue

6
ebook_converter/ebooks/pdb/ereader/reader132.py
View File

@@ -112,7 +112,7 @@ class Reader132(FormatReader):
pml = '' pml = ''
for i in range(1, self.header_record.num_text_pages + 1): for i in range(1, self.header_record.num_text_pages + 1):
self.log.debug('Extracting text page %s', i) self.log.debug('Extracting text page %i', i)
pml += self.get_text_page(i) pml += self.get_text_page(i)
hizer = PML_HTMLizer() hizer = PML_HTMLizer()
html += hizer.parse_pml(pml, 'index.html') html += hizer.parse_pml(pml, 'index.html')
@@ -123,7 +123,7 @@ class Reader132(FormatReader):
footnoteids = re.findall( footnoteids = re.findall(
'\\w+(?=\x00)', self.section_data(self.header_record.footnote_offset).decode('cp1252' if self.encoding is None else self.encoding)) '\\w+(?=\x00)', self.section_data(self.header_record.footnote_offset).decode('cp1252' if self.encoding is None else self.encoding))
for fid, i in enumerate(range(self.header_record.footnote_offset + 1, self.header_record.footnote_offset + self.header_record.footnote_count)): for fid, i in enumerate(range(self.header_record.footnote_offset + 1, self.header_record.footnote_offset + self.header_record.footnote_count)):
self.log.debug('Extracting footnote page %s', i) self.log.debug('Extracting footnote page %i', i)
if fid < len(footnoteids): if fid < len(footnoteids):
fid = footnoteids[fid] fid = footnoteids[fid]
else: else:
@@ -135,7 +135,7 @@ class Reader132(FormatReader):
sidebarids = re.findall( sidebarids = re.findall(
'\\w+(?=\x00)', self.section_data(self.header_record.sidebar_offset).decode('cp1252' if self.encoding is None else self.encoding)) '\\w+(?=\x00)', self.section_data(self.header_record.sidebar_offset).decode('cp1252' if self.encoding is None else self.encoding))
for sid, i in enumerate(range(self.header_record.sidebar_offset + 1, self.header_record.sidebar_offset + self.header_record.sidebar_count)): for sid, i in enumerate(range(self.header_record.sidebar_offset + 1, self.header_record.sidebar_offset + self.header_record.sidebar_count)):
self.log.debug('Extracting sidebar page %s', i) self.log.debug('Extracting sidebar page %i', i)
if sid < len(sidebarids): if sid < len(sidebarids):
sid = sidebarids[sid] sid = sidebarids[sid]
else: else:

2
ebook_converter/ebooks/pdb/ereader/reader202.py
View File

@@ -87,7 +87,7 @@ class Reader202(FormatReader):
pml = '' pml = ''
for i in range(1, self.header_record.num_text_pages + 1): for i in range(1, self.header_record.num_text_pages + 1):
self.log.debug('Extracting text page %s', i) self.log.debug('Extracting text page %i', i)
pml += self.get_text_page(i) pml += self.get_text_page(i)
title = self.mi.title title = self.mi.title

2
ebook_converter/ebooks/pdb/haodoo/reader.py
View File

@@ -118,7 +118,7 @@ class Reader(FormatReader):
self.log.info('Decompressing text...') self.log.info('Decompressing text...')
for i in range(1, self.header_record.num_records + 1): for i in range(1, self.header_record.num_records + 1):
self.log.debug('\tDecompressing text section %s', i) self.log.debug('\tDecompressing text section %i', i)
title = self.header_record.chapter_titles[i-1] title = self.header_record.chapter_titles[i-1]
lines = [] lines = []
title_added = False title_added = False

2
ebook_converter/ebooks/pdb/palmdoc/reader.py
View File

@@ -55,7 +55,7 @@ class Reader(FormatReader):
self.log.info('Decompressing text...') self.log.info('Decompressing text...')
for i in range(1, self.header_record.num_records + 1): for i in range(1, self.header_record.num_records + 1):
self.log.debug('\tDecompressing text section %s', i) self.log.debug('\tDecompressing text section %i', i)
raw_txt += self.decompress_text(i) raw_txt += self.decompress_text(i)
self.log.info('Converting text to OEB...') self.log.info('Converting text to OEB...')

4
ebook_converter/ebooks/pdb/ztxt/reader.py
View File

@@ -54,7 +54,7 @@ class Reader(FormatReader):
if (self.header_record.flags & 0x01) == 0: if (self.header_record.flags & 0x01) == 0:
raise zTXTError('Only compression method 1 (random access) is supported') raise zTXTError('Only compression method 1 (random access) is supported')
self.log.debug('Foud ztxt version: %s.%s', vmajor, vminor) self.log.debug('Foud ztxt version: %i.%i', vmajor, vminor)
# Initalize the decompressor # Initalize the decompressor
self.uncompressor = zlib.decompressobj() self.uncompressor = zlib.decompressobj()
@@ -73,7 +73,7 @@ class Reader(FormatReader):
self.log.info('Decompressing text...') self.log.info('Decompressing text...')
for i in range(1, self.header_record.num_records + 1): for i in range(1, self.header_record.num_records + 1):
self.log.debug('\tDecompressing text section %s', i) self.log.debug('\tDecompressing text section %i', i)
raw_txt += self.decompress_text(i) raw_txt += self.decompress_text(i)
self.log.info('Converting text to OEB...') self.log.info('Converting text to OEB...')

6
ebook_converter/ebooks/txt/markdownml.py
View File

@@ -11,12 +11,6 @@ from ebook_converter.ebooks.oeb.base import XHTML, barename, namespace, rewrite_
from ebook_converter.ebooks.oeb.stylizer import Stylizer from ebook_converter.ebooks.oeb.stylizer import Stylizer
__license__ = 'GPL 3'
__copyright__ = ('2011, John Schember <john@nachtimwald.com> 2011, '
'Leigh Parry <leighparry@blueyonder.co.uk>')
__docformat__ = 'restructuredtext en'
class MarkdownMLizer(OEB2HTML): class MarkdownMLizer(OEB2HTML):
def extract_content(self, oeb_book, opts): def extract_content(self, oeb_book, opts):

5
ebook_converter/ebooks/txt/textileml.py
View File

@@ -14,11 +14,6 @@ from ebook_converter.ebooks import unit_convert
from ebook_converter.ebooks.textile.unsmarten import unsmarten from ebook_converter.ebooks.textile.unsmarten import unsmarten
__license__ = 'GPL 3'
__copyright__ = '2011, Leigh Parry <leighparry@blueyonder.co.uk>'
__docformat__ = 'restructuredtext en'
class TextileMLizer(OEB2HTML): class TextileMLizer(OEB2HTML):
MAX_EM = 10 MAX_EM = 10