gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-03-12 20:45:47 +01:00
Code Issues Projects Releases Wiki Activity

Some misc cleanups

Browse Source
This commit is contained in:
gryf
2020-05-24 12:10:13 +02:00
parent 0fc6e3b081
commit 17c52a14a4
4 changed files with 35 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
ebook_converter/__init__.py
View File

@@ -7,12 +7,9 @@ import sys
import time import time
import urllib.parse import urllib.parse
import urllib.request import urllib.request
import warnings
from functools import partial from functools import partial
if os.getenv('CALIBRE_SHOW_DEPRECATION_WARNINGS') is None:
warnings.simplefilter('ignore', DeprecationWarning)
try: try:
os.getcwd() os.getcwd()
except EnvironmentError: except EnvironmentError:
@@ -140,9 +137,6 @@ def sanitize_file_name(name, substitute='_'):
return one return one
sanitize_file_name2 = sanitize_file_name_unicode = sanitize_file_name
def prints(*args, **kwargs): def prints(*args, **kwargs):
''' '''
Print unicode arguments safely by encoding them to preferred_encoding Print unicode arguments safely by encoding them to preferred_encoding
@@ -551,12 +545,12 @@ def entity_to_unicode(match, exceptions=[], encoding='cp1252',
_ent_pat = re.compile(r'&(\S+?);') _ent_pat = re.compile(r'&(\S+?);')
xml_entity_to_unicode = partial(entity_to_unicode, result_exceptions={ xml_entity_to_unicode = partial(entity_to_unicode,
'"' : '"', result_exceptions={'"': '"',
"'" : ''', "'": ''',
'<' : '&lt;', '<': '&lt;',
'>' : '&gt;', '>': '&gt;',
'&' : '&amp;'}) '&': '&amp;'})
def replace_entities(raw, encoding='cp1252'): def replace_entities(raw, encoding='cp1252'):
@@ -586,7 +580,7 @@ def force_unicode(obj, enc=preferred_encoding):
except Exception: except Exception:
try: try:
obj = obj.decode(filesystem_encoding if enc == obj = obj.decode(filesystem_encoding if enc ==
preferred_encoding else preferred_encoding) preferred_encoding else preferred_encoding)
except Exception: except Exception:
try: try:
obj = obj.decode('utf-8') obj = obj.decode('utf-8')
@@ -628,11 +622,6 @@ def human_readable(size, sep=' '):
return size + sep + suffix return size + sep + suffix
def ipython(user_ns=None):
from ebook_converter.utils.ipython import ipython
ipython(user_ns=user_ns)
def fsync(fileobj): def fsync(fileobj):
fileobj.flush() fileobj.flush()
os.fsync(fileobj.fileno()) os.fsync(fileobj.fileno())

4
ebook_converter/customize/ui.py
View File

@@ -12,6 +12,7 @@ from ebook_converter.customize import profiles
from ebook_converter.customize import builtins from ebook_converter.customize import builtins
from ebook_converter.ebooks import metadata from ebook_converter.ebooks import metadata
from ebook_converter.utils import config as cfg from ebook_converter.utils import config as cfg
from ebook_converter import prints
builtin_names = frozenset(p.name for p in builtins.plugins) builtin_names = frozenset(p.name for p in builtins.plugins)
@@ -348,7 +349,6 @@ def set_file_type_metadata(stream, mi, ftype, report_error=None):
break break
except Exception: except Exception:
if report_error is None: if report_error is None:
from ebook_converter import prints
prints('Failed to set metadata for the', ftype.upper(), prints('Failed to set metadata for the', ftype.upper(),
'format of:', getattr(mi, 'title', ''), 'format of:', getattr(mi, 'title', ''),
file=sys.stderr) file=sys.stderr)
@@ -481,8 +481,6 @@ def initialize_plugins():
_initialized_plugins.append(plugin) _initialized_plugins.append(plugin)
except Exception: except Exception:
print('Failed to initialize plugin:', repr(zfp)) print('Failed to initialize plugin:', repr(zfp))
# Prevent a custom plugin from overriding stdout/stderr as this breaks
# ipython
sys.stdout, sys.stderr = ostdout, ostderr sys.stdout, sys.stderr = ostdout, ostderr
_initialized_plugins.sort(key=lambda x: x.priority, reverse=True) _initialized_plugins.sort(key=lambda x: x.priority, reverse=True)
reread_filetype_plugins() reread_filetype_plugins()

48
ebook_converter/ebooks/conversion/plugins/chm_input.py
View File

@@ -3,6 +3,7 @@ CHM File decoding support
""" """
import os import os
from lxml import html from lxml import html
from lxml.html import builder
from ebook_converter.polyglot.urllib import unquote as _unquote from ebook_converter.polyglot.urllib import unquote as _unquote
from ebook_converter.ebooks.oeb.base import urlquote from ebook_converter.ebooks.oeb.base import urlquote
@@ -19,13 +20,16 @@ __copyright__ = ('2008, Kovid Goyal <kovid at kovidgoyal.net>, '
class CHMInput(InputFormatPlugin): class CHMInput(InputFormatPlugin):
name = 'CHM Input' name = 'CHM Input'
author = 'Kovid Goyal and Alex Bramley' author = 'Kovid Goyal and Alex Bramley'
description = 'Convert CHM files to OEB' description = 'Convert CHM files to OEB'
file_types = {'chm'} file_types = {'chm'}
commit_name = 'chm_input' commit_name = 'chm_input'
def _chmtohtml(self, output_dir, chm_path, no_images, log, debug_dump=False): def _chmtohtml(self, output_dir, chm_path, no_images, log,
debug_dump=False):
# NOTE(gryf): for some reason, this import cannot be moved to the top
# of module.
from ebook_converter.ebooks.chm.reader import CHMReader from ebook_converter.ebooks.chm.reader import CHMReader
log.debug('Opening CHM file') log.debug('Opening CHM file')
rdr = CHMReader(chm_path, log, input_encoding=self.opts.input_encoding) rdr = CHMReader(chm_path, log, input_encoding=self.opts.input_encoding)
@@ -35,6 +39,8 @@ class CHMInput(InputFormatPlugin):
return rdr.hhc_path return rdr.hhc_path
def convert(self, stream, options, file_ext, log, accelerators): def convert(self, stream, options, file_ext, log, accelerators):
# NOTE(gryf): for some reason, those import cannot be moved to the top
# of module.
from ebook_converter.ebooks.chm.metadata import get_metadata_from_reader from ebook_converter.ebooks.chm.metadata import get_metadata_from_reader
from ebook_converter.customize.ui import plugin_for_input_format from ebook_converter.customize.ui import plugin_for_input_format
self.opts = options self.opts = options
@@ -59,7 +65,7 @@ class CHMInput(InputFormatPlugin):
if odi: if odi:
debug_dump = os.path.join(odi, 'input') debug_dump = os.path.join(odi, 'input')
mainname = self._chmtohtml(tdir, chm_name, no_images, log, mainname = self._chmtohtml(tdir, chm_name, no_images, log,
debug_dump=debug_dump) debug_dump=debug_dump)
mainpath = os.path.join(tdir, mainname) mainpath = os.path.join(tdir, mainname)
try: try:
@@ -68,11 +74,9 @@ class CHMInput(InputFormatPlugin):
log.exception('Failed to read metadata, using filename') log.exception('Failed to read metadata, using filename')
from ebook_converter.ebooks.metadata.book.base import Metadata from ebook_converter.ebooks.metadata.book.base import Metadata
metadata = Metadata(os.path.basename(chm_name)) metadata = Metadata(os.path.basename(chm_name))
encoding = self._chm_reader.get_encoding() or options.input_encoding or 'cp1252' encoding = (self._chm_reader.get_encoding() or
options.input_encoding or 'cp1252')
self._chm_reader.CloseCHM() self._chm_reader.CloseCHM()
# print((tdir, mainpath))
# from ebook_converter import ipython
# ipython()
options.debug_pipeline = None options.debug_pipeline = None
options.input_encoding = 'utf-8' options.input_encoding = 'utf-8'
@@ -80,7 +84,8 @@ class CHMInput(InputFormatPlugin):
if os.path.abspath(mainpath) in self._chm_reader.re_encoded_files: if os.path.abspath(mainpath) in self._chm_reader.re_encoded_files:
uenc = 'utf-8' uenc = 'utf-8'
htmlpath, toc = self._create_html_root(mainpath, log, uenc) htmlpath, toc = self._create_html_root(mainpath, log, uenc)
oeb = self._create_oebbook_html(htmlpath, tdir, options, log, metadata) oeb = self._create_oebbook_html(htmlpath, tdir, options, log,
metadata)
options.debug_pipeline = odi options.debug_pipeline = odi
if toc.count() > 1: if toc.count() > 1:
oeb.toc = self.parse_html_toc(oeb.spine[0]) oeb.toc = self.parse_html_toc(oeb.spine[0])
@@ -117,13 +122,10 @@ class CHMInput(InputFormatPlugin):
hhcdata = self._read_file(hhcpath) hhcdata = self._read_file(hhcpath)
hhcdata = hhcdata.decode(encoding) hhcdata = hhcdata.decode(encoding)
hhcdata = xml_to_unicode(hhcdata, verbose=True, hhcdata = xml_to_unicode(hhcdata, verbose=True,
strip_encoding_pats=True, resolve_entities=True)[0] strip_encoding_pats=True,
resolve_entities=True)[0]
hhcroot = html.fromstring(hhcdata) hhcroot = html.fromstring(hhcdata)
toc = self._process_nodes(hhcroot) toc = self._process_nodes(hhcroot)
# print("=============================")
# print("Printing hhcroot")
# print(etree.tostring(hhcroot, pretty_print=True))
# print("=============================")
log.debug('Found %d section nodes' % toc.count()) log.debug('Found %d section nodes' % toc.count())
htmlpath = os.path.splitext(hhcpath)[0] + ".html" htmlpath = os.path.splitext(hhcpath)[0] + ".html"
base = os.path.dirname(os.path.abspath(htmlpath)) base = os.path.dirname(os.path.abspath(htmlpath))
@@ -135,7 +137,8 @@ class CHMInput(InputFormatPlugin):
def unquote_path(x): def unquote_path(x):
y = unquote(x) y = unquote(x)
if (not os.path.exists(os.path.join(base, x)) and os.path.exists(os.path.join(base, y))): if (not os.path.exists(os.path.join(base, x)) and
os.path.exists(os.path.join(base, y))):
x = y x = y
return x return x
@@ -147,28 +150,29 @@ class CHMInput(InputFormatPlugin):
raw = unquote_path(child.href or '') raw = unquote_path(child.href or '')
rsrcname = os.path.basename(raw) rsrcname = os.path.basename(raw)
rsrcpath = os.path.join(subpath, rsrcname) rsrcpath = os.path.join(subpath, rsrcname)
if (not os.path.exists(os.path.join(base, rsrcpath)) and os.path.exists(os.path.join(base, raw))): if (not os.path.exists(os.path.join(base, rsrcpath)) and
os.path.exists(os.path.join(base, raw))):
rsrcpath = raw rsrcpath = raw
if '%' not in rsrcpath: if '%' not in rsrcpath:
rsrcpath = urlquote(rsrcpath) rsrcpath = urlquote(rsrcpath)
if not raw: if not raw:
rsrcpath = '' rsrcpath = ''
c = DIV(A(title, href=rsrcpath)) c = builder.DIV(builder.A(title, href=rsrcpath))
donode(child, c, base, subpath) donode(child, c, base, subpath)
parent.append(c) parent.append(c)
with open(htmlpath, 'wb') as f: with open(htmlpath, 'wb') as f:
if toc.count() > 1: if toc.count() > 1:
from lxml.html.builder import HTML, BODY, DIV, A
path0 = toc[0].href path0 = toc[0].href
path0 = unquote_path(path0) path0 = unquote_path(path0)
subpath = os.path.dirname(path0) subpath = os.path.dirname(path0)
base = os.path.dirname(f.name) base = os.path.dirname(f.name)
root = DIV() root = builder.DIV()
donode(toc, root, base, subpath) donode(toc, root, base, subpath)
raw = html.tostring(HTML(BODY(root)), encoding='utf-8', raw = html.tostring(builder.HTML(builder.BODY(root)),
pretty_print=True) encoding='utf-8',
pretty_print=True)
f.write(raw) f.write(raw)
else: else:
f.write(as_bytes(hhcdata)) f.write(as_bytes(hhcdata))

2
ebook_converter/ebooks/txt/processor.py
View File

@@ -171,7 +171,7 @@ def convert_markdown_with_metadata(txt, title='', extensions=DEFAULT_MD_EXTENSIO
def convert_textile(txt, title=''): def convert_textile(txt, title=''):
from ebook_converter.ebooks.textile import textile from ebook_converter.ebooks.textile.functions import textile
html = textile(txt, encoding='utf-8') html = textile(txt, encoding='utf-8')
return HTML_TEMPLATE % (title, html) return HTML_TEMPLATE % (title, html)