gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-03-17 07:13:42 +01:00
Code Issues Projects Releases Wiki Activity

Use the real constants module.

Browse Source 
This is progressing refactor of the calibre code to make it more
readable, and transform it to something more coherent.

In this patch, there are changes regarding imports for some modules,
instead of polluting namespace of each module with some other modules
symbols, which often were imported from other modules. Yuck.
This commit is contained in:
gryf
2020-05-29 17:04:53 +02:00
parent ee4801228f
commit ce89f5c9d1
54 changed files with 2383 additions and 2081 deletions
Download Patch File Download Diff File Expand all files Collapse all files

74
ebook_converter/ebooks/conversion/plugins/snb_input.py
View File

@@ -1,27 +1,33 @@
import os
from lxml import etree
from ebook_converter.customize.conversion import InputFormatPlugin
from ebook_converter.ptempfile import TemporaryDirectory
from ebook_converter.utils.filenames import ascii_filename
__license__ = 'GPL 3'
__copyright__ = '2010, Li Fanxi <lifanxi@freemindworld.com>'
__docformat__ = 'restructuredtext en'
HTML_TEMPLATE = '<html><head><meta http-equiv="Content-Type" content="text/html; charset=utf-8"/><title>%s</title></head><body>\n%s\n</body></html>'
HTML_TEMPLATE = ('<html><head><meta http-equiv="Content-Type" '
'content="text/html; charset=utf-8"/><title>%s</title>'
'</head><body>\n%s\n</body></html>')
def html_encode(s):
return s.replace('&', '&amp;').replace('<', '&lt;').replace('>', '&gt;').replace('"', '&quot;').replace("'", '&apos;').replace('\n', '<br/>').replace(' ', '&nbsp;') # noqa
return (s.replace('&', '&amp;')
.replace('<', '&lt;')
.replace('>', '&gt;')
.replace('"', '&quot;')
.replace("'", '&apos;')
.replace('\n', '<br/>')
.replace(' ', '&nbsp;'))
class SNBInput(InputFormatPlugin):
name = 'SNB Input'
author = 'Li Fanxi'
name = 'SNB Input'
author = 'Li Fanxi'
description = 'Convert SNB files to OEB'
file_types = {'snb'}
file_types = {'snb'}
commit_name = 'snb_input'
options = set()
@@ -32,13 +38,12 @@ class SNBInput(InputFormatPlugin):
from ebook_converter.ebooks.oeb.base import DirContainer
from ebook_converter.ebooks.snb.snbfile import SNBFile
from ebook_converter.utils.xml_parse import safe_xml_fromstring
log.debug("Parsing SNB file...")
snbFile = SNBFile()
try:
snbFile.Parse(stream)
except:
except Exception:
raise ValueError("Invalid SNB file")
if not snbFile.IsValid():
log.debug("Invalid SNB file")
@@ -46,27 +51,28 @@ class SNBInput(InputFormatPlugin):
log.debug("Handle meta data ...")
from ebook_converter.ebooks.conversion.plumber import create_oebbook
oeb = create_oebbook(log, None, options,
encoding=options.input_encoding, populate=False)
encoding=options.input_encoding, populate=False)
meta = snbFile.GetFileStream('snbf/book.snbf')
if meta is not None:
meta = safe_xml_fromstring(meta)
l = {'title' : './/head/name',
'creator' : './/head/author',
'language' : './/head/language',
'generator': './/head/generator',
'publisher': './/head/publisher',
'cover' : './/head/cover', }
meta = etree.fromstring(meta)
item_map = {'title': './/head/name',
'creator': './/head/author',
'language': './/head/language',
'generator': './/head/generator',
'publisher': './/head/publisher',
'cover': './/head/cover'}
d = {}
for item in l:
node = meta.find(l[item])
for key, item in item_map.items():
node = meta.find(item)
if node is not None:
d[item] = node.text if node.text is not None else ''
d[key] = node.text if node.text is not None else ''
else:
d[item] = ''
d[key] = ''
oeb.metadata.add('title', d['title'])
oeb.metadata.add('creator', d['creator'], attrib={'role':'aut'})
oeb.metadata.add('language', d['language'].lower().replace('_', '-'))
oeb.metadata.add('creator', d['creator'], attrib={'role': 'aut'})
oeb.metadata.add('language',
d['language'].lower().replace('_', '-'))
oeb.metadata.add('generator', d['generator'])
oeb.metadata.add('publisher', d['publisher'])
if d['cover'] != '':
@@ -84,7 +90,7 @@ class SNBInput(InputFormatPlugin):
toc = snbFile.GetFileStream('snbf/toc.snbf')
oeb.container = DirContainer(tdir, log)
if toc is not None:
toc = safe_xml_fromstring(toc)
toc = etree.fromstring(toc)
i = 1
for ch in toc.find('.//body'):
chapterName = ch.text
@@ -93,18 +99,22 @@ class SNBInput(InputFormatPlugin):
data = snbFile.GetFileStream('snbc/' + chapterSrc)
if data is None:
continue
snbc = safe_xml_fromstring(data)
snbc = etree.fromstring(data)
lines = []
for line in snbc.find('.//body'):
if line.tag == 'text':
lines.append('<p>%s</p>' % html_encode(line.text))
elif line.tag == 'img':
lines.append('<p><img src="%s" /></p>' % html_encode(line.text))
lines.append('<p><img src="%s" /></p>' %
html_encode(line.text))
with open(os.path.join(tdir, fname), 'wb') as f:
f.write((HTML_TEMPLATE % (chapterName, '\n'.join(lines))).encode('utf-8', 'replace'))
f.write((HTML_TEMPLATE %
(chapterName,
'\n'.join(lines))).encode('utf-8',
'replace'))
oeb.toc.add(ch.text, fname)
id, href = oeb.manifest.generate(id='html',
href=ascii_filename(fname))
id, href = oeb.manifest.generate(
id='html', href=ascii_filename(fname))
item = oeb.manifest.add(id, href, 'text/html')
item.html_input_href = fname
oeb.spine.add(item, True)
@@ -112,7 +122,7 @@ class SNBInput(InputFormatPlugin):
imageFiles = snbFile.OutputImageFiles(tdir)
for f, m in imageFiles:
id, href = oeb.manifest.generate(id='image',
href=ascii_filename(f))
href=ascii_filename(f))
item = oeb.manifest.add(id, href, m)
item.html_input_href = f