Cutlery/calibre
1
0
Fork 0
mirror of https://github.com/kovidgoyal/calibre.git synced 2025-07-09 03:04:10 -04:00
Code Issues Packages Projects Releases Wiki Activity

Sync to trunk.

Browse Source
This commit is contained in:
John Schember 2009-07-30 19:18:33 -04:00
commit f10852a43c
6 changed files with 117 additions and 28 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
src/calibre/__init__.py
View File

@ -36,6 +36,7 @@ mimetypes.add_type('application/ereader', '.pdb')
mimetypes.add_type('application/mobi', '.mobi')
mimetypes.add_type('application/mobi', '.prc')
mimetypes.add_type('application/mobi', '.azw')
mimetypes.add_type('image/wmf', '.wmf')
guess_type = mimetypes.guess_type
import cssutils
cssutils.log.setLevel(logging.WARN)

48
src/calibre/ebooks/rtf/input.py
View File

@ -2,7 +2,7 @@ from __future__ import with_statement
__license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
import os
import os, glob, re
from lxml import etree
@ -61,6 +61,39 @@ class RTFInput(InputFormatPlugin):
os.remove('out.xml')
return ans
def extract_images(self, picts):
self.log('Extracting images...')
count = 0
raw = open(picts, 'rb').read()
starts = []
for match in re.finditer(r'\{\\pict([^}]+)\}', raw):
starts.append(match.start(1))
imap = {}
for start in starts:
pos, bc = start, 1
while bc > 0:
if raw[pos] == '}': bc -= 1
elif raw[pos] == '{': bc += 1
pos += 1
pict = raw[start:pos+1]
enc = re.sub(r'[^a-zA-Z0-9]', '', pict)
if len(enc) % 2 == 1:
enc = enc[:-1]
data = enc.decode('hex')
ext = '.jpg'
if 'EMF' in data[:200]:
ext = '.wmf'
elif 'PNG' in data[:200]:
ext = '.png'
count += 1
name = (('%4d'%count).replace(' ', '0'))+ext
open(name, 'wb').write(data)
imap[count] = name
#open(name+'.hex', 'wb').write(enc)
return imap
def convert(self, stream, options, file_ext, log,
accelerators):
from calibre.ebooks.rtf.xsl import xhtml
@ -74,9 +107,22 @@ class RTFInput(InputFormatPlugin):
except RtfInvalidCodeException:
raise ValueError(_('This RTF file has a feature calibre does not '
'support. Convert it to HTML first and then try it.'))
d = glob.glob(os.path.join('*_rtf_pict_dir', 'picts.rtf'))
if d:
imap = {}
try:
imap = self.extract_images(d[0])
except:
self.log.exception('Failed to extract images...')
self.log('Parsing XML...')
parser = etree.XMLParser(recover=True, no_network=True)
doc = etree.fromstring(xml, parser=parser)
for pict in doc.xpath('//rtf:pict[@num]',
namespaces={'rtf':'http://rtf2xml.sourceforge.net/'}):
num = int(pict.get('num'))
name = imap.get(num, None)
if name is not None:
pict.set('num', name)
self.log('Converting XML to HTML...')
styledoc = etree.fromstring(xhtml)

54
src/calibre/ebooks/rtf/xsl.py
View File

@ -18,11 +18,11 @@
xhtml = '''\
<?xml version="1.0"?>
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
<xsl:stylesheet version="1.0"
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:html="http://www.w3.org/1999/xhtml"
xmlns:rtf="http://rtf2xml.sourceforge.net/"
exclude-result-prefixes="rtf"
exclude-result-prefixes="rtf"
>
<xsl:template match = "rtf:para">
@ -36,7 +36,7 @@ xhtml = '''\
parent::rtf:paragraph-definition[@name='heading 7']|
parent::rtf:paragraph-definition[@name='heading 8']|
parent::rtf:paragraph-definition[@name='heading 9']
">
<xsl:variable name="head-number" select="substring(parent::rtf:paragraph-definition/@name, 9)"/>
<xsl:element name="h{$head-number}">
@ -64,7 +64,7 @@ xhtml = '''\
parent::rtf:paragraph-definition[@name='heading 7']|
parent::rtf:paragraph-definition[@name='heading 8']|
parent::rtf:paragraph-definition[@name='heading 9']
">
<xsl:apply-templates/>
</xsl:when>
@ -108,17 +108,17 @@ xhtml = '''\
<xsl:when test = "@italics = 'true' ">
<emph rend = "paragraph-emph-italics">
<xsl:apply-templates/>
</emph>
</emph>
</xsl:when>
<xsl:when test = "@bold = 'true' ">
<emph rend = "paragraph-emph-bold">
<xsl:apply-templates/>
</emph>
</emph>
</xsl:when>
<xsl:when test = "@underlined">
<emph rend = "paragraph-emph-underlined">
<xsl:apply-templates/>
</emph>
</emph>
</xsl:when>
<xsl:when test = "(@strike-through = 'true')
or (@double-strike-through = 'true')
@ -128,18 +128,18 @@ xhtml = '''\
or (@shadow = 'true')
or (@hidden = 'true')
or (@outline = 'true')
">
<emph rend = "paragraph-emph">
<xsl:apply-templates/>
</emph>
</emph>
</xsl:when>
<xsl:otherwise>
<xsl:apply-templates/>
</xsl:otherwise>
</xsl:choose>
</xsl:template>
<xsl:template name="make-header">
<head>
<xsl:element name="meta">
@ -150,7 +150,7 @@ xhtml = '''\
<xsl:text>http://rtf2xml.sourceforge.net/</xsl:text>
</xsl:attribute>
</xsl:element>
<xsl:choose>
<xsl:when test="/rtf:doc/rtf:preamble/rtf:doc-information">
<xsl:apply-templates select="/rtf:doc/rtf:preamble/rtf:doc-information" mode="header"/>
@ -333,7 +333,7 @@ xhtml = '''\
</xsl:otherwise>
</xsl:choose>
</xsl:template>
<xsl:template match="rtf:inline">
<xsl:variable name="num-attrs" select="count(@*)"/>
<xsl:choose>
@ -387,7 +387,7 @@ xhtml = '''\
</xsl:attribute>
<xsl:apply-templates/>
</xsl:element>
</xsl:otherwise>
</xsl:choose>
</xsl:template>
@ -401,9 +401,9 @@ xhtml = '''\
</xsl:attribute>
<xsl:apply-templates/>
</xsl:element>
</xsl:template>
<xsl:template match="rtf:list[@list-type='unordered']">
<xsl:element name="ul">
<xsl:apply-templates/>
@ -479,13 +479,13 @@ xhtml = '''\
<xsl:template match="rtf:preamble">
<xsl:apply-templates/>
</xsl:template>
<xsl:template match="rtf:page-break">
<xsl:element name="br">
<xsl:attribute name="style">page-break-after:always</xsl:attribute>
</xsl:element>
</xsl:template>
<xsl:template match="rtf:rtf-definition|rtf:font-table|rtf:color-table|rtf:style-table|rtf:page-definition|rtf:list-table|rtf:override-table|rtf:override-list|rtf:list-text"/>
<xsl:template match="rtf:body">
@ -505,11 +505,11 @@ xhtml = '''\
<xsl:apply-templates/>
</xsl:element>
</xsl:template>
<xsl:template match = "rtf:field-block">
<xsl:apply-templates/>
</xsl:template>
<xsl:template match = "rtf:field[@type='hyperlink']">
<xsl:element name ="a">
<xsl:attribute name = "href">
@ -522,9 +522,13 @@ xhtml = '''\
<xsl:template match = "rtf:field">
<xsl:apply-templates/>
</xsl:template>
<xsl:template match="rtf:pict" />
<xsl:template match="rtf:pict">
<xsl:element name="img">
<xsl:attribute name="src"><xsl:value-of select="@num" /></xsl:attribute>
</xsl:element>
</xsl:template>
<xsl:template match="*">
<xsl:message>
<xsl:text>no match for element: "</xsl:text>
@ -533,6 +537,6 @@ xhtml = '''\
</xsl:message>
<xsl:apply-templates/>
</xsl:template>
</xsl:stylesheet>
'''
'''

2
src/calibre/ebooks/rtf2xml/pict.py
View File

@ -55,7 +55,7 @@ class Pict:
return "}\n"
def __text_func(self, line):
#tx<nu<__________<true text
return line[18:]
return line[17:]
def __make_dir(self):
""" Make a dirctory to put the image data in"""
base_name = os.path.basename(getattr(self.__orig_file, 'name',

3
src/calibre/gui2/wizard/send_email.py
View File

@ -112,7 +112,8 @@ class SendEmail(QWidget, Ui_Form):
self.relay_tls.setChecked(True)
info_dialog(self, _('Finish gmail setup'),
_('Dont forget to enter your gmail username and password')).exec_()
_('Dont forget to enter your gmail username and password. '
'You can sign up for a free gmail account at http://gmail.com')).exec_()
self.relay_username.setFocus(Qt.OtherFocusReason)
self.relay_username.setCursorPosition(0)

37
src/calibre/web/feeds/recipes/recipe_newsweek.py
View File

@ -4,6 +4,7 @@ __license__ = 'GPL v3'
__copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
import re
from calibre import strftime
from calibre.ebooks.BeautifulSoup import BeautifulSoup
from calibre.web.feeds.news import BasicNewsRecipe
class Newsweek(BasicNewsRecipe):
@ -128,3 +129,39 @@ class Newsweek(BasicNewsRecipe):
return cover_url
def postprocess_book(self, oeb, opts, log) :
def extractByline(href) :
soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
byline = soup.find(True,attrs={'class':'authorInfo'})
byline = self.tag_to_string(byline) if byline is not None else ''
issueDate = soup.find(True,attrs={'class':'issueDate'})
issueDate = self.tag_to_string(issueDate) if issueDate is not None else ''
issueDate = re.sub(',','', issueDate)
if byline > '' and issueDate > '' :
return byline + ' | ' + issueDate
else :
return byline + issueDate
def extractDescription(href) :
soup = BeautifulSoup(str(oeb.manifest.hrefs[href]))
description = soup.find(True,attrs={'name':'description'})
if description is not None and description.has_key('content'):
description = description['content']
if description.startswith('Newsweek magazine online plus') :
description = soup.find(True, attrs={'class':'story'})
firstPara = soup.find('p')
description = self.tag_to_string(firstPara)
else :
description = soup.find(True, attrs={'class':'story'})
firstPara = soup.find('p')
description = self.tag_to_string(firstPara)
return description
for section in oeb.toc :
for article in section :
if article.author is None :
article.author = extractByline(article.href)
if article.description is None :
article.description = extractDescription(article.href)
return