gryf/ebook-converter
1
0
Fork 0
mirror of https://github.com/gryf/ebook-converter.git synced 2026-04-19 20:53:35 +02:00
Code Issues Projects Releases Wiki Activity

Cleanup get_path usage in favor of pkg_resources.

Browse Source
This commit is contained in:
gryf
2020-04-12 18:33:23 +02:00
parent 0bf43ec6e8
commit 5aa0b1a0eb
17 changed files with 532 additions and 277 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
ebook_converter/utils/default_tweaks.py → ebook_converter/data/default_tweaks.py
View File

149
ebook_converter/data/jacket/stylesheet.css Normal file
View File

@@ -0,0 +1,149 @@
/*
** Book Jacket generation
**
** The template for Book Jackets is template.xhtml
** This CSS is inserted into the generated HTML at conversion time
**
** Users can control parts of the presentation of a generated book jacket by
** editing this file and template.xhtml
**
** The general form of a generated Book Jacket:
**
** Title
** Series: series [series_index]
** Published: year_of_publication
** Rating: #_of_stars
** Tags: tag1, tag2, tag3 ...
**
** Comments
**
** If a book does not have Series information, a date of publication, a rating or tags
** the corresponding row is automatically removed from the generated book jacket.
*/
/*
** Banner
** Only affects EPUB, kindle ignores this type of formatting
*/
.cbj_banner {
background: #eee;
color: black;
border: thin solid black;
margin: 1em;
padding: 1em;
border-radius:8px;
}
/*
** Title
*/
table.cbj_header td.cbj_title {
font-size: 1.5em;
font-style: italic;
text-align: center;
}
/*
** Series
*/
table.cbj_header td.cbj_series {
text-align: center;
}
/*
** Author
*/
table.cbj_header td.cbj_author {
text-align: center;
}
/*
** Publisher/published
*/
table.cbj_header td.cbj_pubdata {
text-align: center;
}
/*
** Table containing Rating and Tags
*/
table.cbj_header {
width: 100%;
}
/*
** General formatting for banner labels
*/
table.cbj_header td.cbj_label {
font-family: sans-serif;
text-align: right;
width: 33%;
}
/*
** General formatting for banner content
*/
table.cbj_header td.cbj_content {
font-family: sans-serif;
text-align: left;
width:67%;
}
/*
** Metadata divider
*/
hr.metadata_divider {
width:90%;
margin-left:5%;
border-top: solid white 0px;
border-right: solid white 0px;
border-bottom: solid black 1px;
border-left: solid white 0px;
}
/*
** To skip a banner item (Series|Published|Rating|Tags),
** edit the appropriate CSS rule below.
*/
table.cbj_header tr.cbj_series {
/* Uncomment the next line to remove 'Series' from banner section */
/* display:none; */
}
table.cbj_header tr.cbj_pubdata {
/* Uncomment the next line to remove 'Published (year of publication)' from banner section */
/* display:none; */
}
table.cbj_header tr.cbj_rating {
/* Uncomment the next line to remove 'Rating' from banner section */
/* display:none; */
}
table.cbj_header tr.cbj_tags {
/* Uncomment the next line to remove 'Tags' from banner section */
/* display:none; */
}
hr {
/* This rule controls formatting for any hr elements contained in the jacket */
border-top: 0px solid white;
border-right: 0px solid white;
border-bottom: 2px solid black;
border-left: 0px solid white;
margin-left: 10%;
width: 80%;
}
.cbj_footer {
font-family: sans-serif;
font-size: 0.8em;
margin-top: 8px;
text-align: center;
}
.cbj_comments {
font-family: sans-serif;
}

58
ebook_converter/data/jacket/template.xhtml Normal file
View File

@@ -0,0 +1,58 @@
<html xmlns="{xmlns}">
<head>
<title>{title_str}</title>
<meta name="calibre-content" content="jacket"/>
<style type="text/css">{css}</style>
</head>
<body>
<div class="cbj_banner">
<table class="cbj_header">
<tr>
<td class="cbj_title" colspan="2">{title}</td>
</tr>
<tr>
<!-- If you do not want the series number to be formatted using roman numerals
change {series.roman} to {series}. You can also access the raw series name and number
using {series.name}, {series.number} or {series.roman_number} -->
<td class="cbj_series" colspan="2">{series.roman}</td>
</tr>
<tr>
<td class="cbj_author" colspan="2">{author}</td>
</tr>
<tr>
<td class="cbj_pubdata" colspan="2">{publisher} ({pubdate})</td>
</tr>
<tr>
<td class="cbj_author" colspan="2"><hr class="metadata_divider" /></td>
</tr>
<tr class="cbj_rating">
<td class="cbj_label">{rating_label}:</td>
<td class="cbj_content">{rating}</td>
</tr>
<tr class="cbj_tags">
<td class="cbj_label">{tags_label}:</td>
<!-- If you want the tags to be alphabetical, change {tags} to
{tags.alphabetical} -->
<td class="cbj_content">{tags}</td>
</tr>
<tr data-calibre-jacket-searchable-tags="1" style="color:white; display:none"><td colspan="2">{searchable_tags}</td></tr>
</table>
<div class="cbj_footer">{footer}</div>
</div>
<hr class="cbj_kindle_banner_hr" />
<!--
In addition you can add code to show the values of custom columns here.
The value is available as _column_name and the title as
_column_name_label. For example, if you have a custom column with
label #genre, you can add it to this template with _genre_label and
_genre. Note that the # is replaced by an underscore. For example
<div><b>{_genre_label}:</b> {_genre}</div>
-->
<div class="cbj_comments">{comments}</div>
</body>
</html>

210
ebook_converter/data/lrf.xsl Normal file
View File

@@ -0,0 +1,210 @@
<?xml version="1.0"?>
<xsl:stylesheet
xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
xmlns:c="calibre"
xmlns:dc="http://purl.org/dc/elements/1.1/"
xmlns:opf="http://www.idpf.org/2007/opf"
xmlns:calibre="http://calibre.kovidgoyal.net/2009/metadata"
extension-element-prefixes="c"
xsl:version = "1.1"
>
<xsl:output method="xml" indent="yes"/>
<xsl:template match="/">
<package version="2.0">
<metadata>
<xsl:call-template name="make-metadata"/>
</metadata>
<manifest>
<xsl:call-template name="make-manifest"/>
</manifest>
<spine toc="ncx">
<xsl:call-template name="make-spine"/>
</spine>
</package>
<xsl:call-template name="make-ncx"/>
<xsl:call-template name="make-css"/>
<xsl:for-each select="//Page">
<xsl:call-template name="make-page"/>
</xsl:for-each>
</xsl:template>
<xsl:template name="make-css">
<xsl:for-each select="//TextStyle|//BlockStyle">
<c:styles/>
</xsl:for-each>
</xsl:template>
<xsl:template name="make-page">
<xsl:variable name="pid" select="@objid"/>
<xsl:document href="{$pid}.xhtml" method="xml" indent="yes">
<html>
<head>
<title><xsl:value-of select="//Title"/></title>
<link rel="stylesheet" type="text/css" href="styles.css"/>
</head>
<body class="body">
<xsl:apply-templates />
</body>
</html>
</xsl:document>
</xsl:template>
<xsl:template match="RuledLine">
<c:ruled-line/>
</xsl:template>
<xsl:template match="TextBlock">
<c:text-block/>
</xsl:template>
<xsl:template match="ImageBlock">
<c:image-block/>
</xsl:template>
<xsl:template match="Canvas">
<c:canvas/>
</xsl:template>
<xsl:template name="make-metadata">
<xsl:for-each select='//BookInformation/Info/BookInfo'>
<xsl:apply-templates select="Title"/>
<xsl:apply-templates select="Author"/>
<xsl:apply-templates select="Publisher"/>
<xsl:apply-templates select="Category|Classification"/>
</xsl:for-each>
<xsl:for-each select='//BookInformation/Info/DocInfo'>
<xsl:apply-templates select="Language"/>
<xsl:apply-templates select="Producer"/>
</xsl:for-each>
</xsl:template>
<xsl:template match="Title">
<xsl:element name="dc:title">
<xsl:if test="@reading and @reading != ''">
<xsl:attribute name="opf:file-as"><xsl:value-of select="@reading"/></xsl:attribute>
</xsl:if>
<xsl:value-of select="."/>
</xsl:element>
</xsl:template>
<xsl:template match="Author">
<xsl:element name="dc:creator">
<xsl:attribute name="opf:role">aut</xsl:attribute>
<xsl:if test="@reading and @reading != ''">
<xsl:attribute name="opf:file-as"><xsl:value-of select="@reading"/></xsl:attribute>
</xsl:if>
<xsl:value-of select="."/>
</xsl:element>
</xsl:template>
<xsl:template match="Publisher">
<xsl:element name="dc:publisher">
<xsl:if test="@reading and @reading != ''">
<xsl:attribute name="opf:file-as"><xsl:value-of select="@reading"/></xsl:attribute>
</xsl:if>
<xsl:value-of select="."/>
</xsl:element>
</xsl:template>
<xsl:template match="Producer">
<xsl:element name="dc:creator">
<xsl:attribute name="opf:role">bkp</xsl:attribute>
<xsl:if test="@reading and @reading != ''">
<xsl:attribute name="opf:file-as"><xsl:value-of select="@reading"/></xsl:attribute>
</xsl:if>
<xsl:value-of select="."/>
</xsl:element>
</xsl:template>
<xsl:template match="Language">
<xsl:element name="dc:language">
<xsl:value-of select="."/>
</xsl:element>
</xsl:template>
<xsl:template match="Category|Classification">
<xsl:if test=".!=''">
<xsl:element name="dc:subject">
<xsl:value-of select="."/>
</xsl:element>
</xsl:if>
</xsl:template>
<xsl:template name="make-manifest">
<xsl:for-each select='//Page'>
<xsl:element name="item">
<xsl:attribute name="id"><xsl:value-of select="@objid"/></xsl:attribute>
<xsl:attribute name="media-type"><xsl:text>application/xhtml+xml</xsl:text></xsl:attribute>
<xsl:attribute name="href"><xsl:value-of select="@objid"/><xsl:text>.xhtml</xsl:text></xsl:attribute>
</xsl:element>
</xsl:for-each>
<xsl:for-each select="//ImageStream">
<xsl:element name="item">
<xsl:attribute name="id"><xsl:value-of select="@objid"/></xsl:attribute>
<xsl:attribute name="media-type"><c:media-type/></xsl:attribute>
<xsl:attribute name="href"><xsl:value-of select="@file"/></xsl:attribute>
</xsl:element>
</xsl:for-each>
<xsl:for-each select="//RegistFont">
<xsl:element name="item">
<xsl:attribute name="id"><xsl:value-of select="@objid"/></xsl:attribute>
<xsl:attribute name="media-type"><c:media-type/></xsl:attribute>
<xsl:attribute name="href"><xsl:value-of select="@file"/></xsl:attribute>
</xsl:element>
</xsl:for-each>
<item id="ncx" href="toc.ncx" media-type="application/x-dtbncx+xml" />
<item id="styles" href="styles.css" media-type="text/css" />
</xsl:template>
<xsl:template name="make-spine">
<xsl:for-each select='//Page'>
<xsl:element name="itemref">
<xsl:attribute name="idref"><xsl:value-of select="@objid"/></xsl:attribute>
</xsl:element>
</xsl:for-each>
</xsl:template>
<xsl:template match="*">
<xsl:message>
<xsl:text>no match for element: "</xsl:text>
<xsl:value-of select="name(.)"/>
<xsl:text>" &#xA;</xsl:text>
</xsl:message>
<xsl:apply-templates/>
</xsl:template>
<xsl:template name="make-ncx">
<xsl:document href="toc.ncx" method="xml" indent="yes">
<ncx version="2005-1"
xmlns="http://www.daisy.org/z3986/2005/ncx/"
xmlns:calibre="http://calibre.kovidgoyal.net/2009/metadata"
>
<head>
<meta name="dtb:uid" content="uid"/>
<meta name="dtb:depth" content="1"/>
<meta name="dtb:generator" content="calibre"/>
<meta name="dtb:totalPageCount" content="0"/>
<meta name="dtb:maxPageNumber" content="0"/>
</head>
<docTitle><text>Table of Contents</text></docTitle>
<navMap>
<xsl:for-each select="//TOC/TocLabel">
<xsl:element name="navPoint">
<xsl:attribute name="id"><xsl:value-of select="count(preceding-sibling::*)"/></xsl:attribute>
<xsl:attribute name="playOrder"><xsl:value-of select="count(preceding-sibling::*)+1"/></xsl:attribute>
<navLabel><text><xsl:value-of select="."/></text></navLabel>
<xsl:element name="content">
<xsl:attribute name="src">
<xsl:value-of select="@refpage"/>.xhtml#<xsl:value-of select="@refobj"/>
</xsl:attribute>
</xsl:element>
</xsl:element>
</xsl:for-each>
</navMap>
</ncx>
</xsl:document>
</xsl:template>
</xsl:stylesheet>

9
ebook_converter/data/new_nav.html Normal file
View File

@@ -0,0 +1,9 @@
<?xml version='1.0' encoding='utf-8'?>
<html xmlns="http://www.w3.org/1999/xhtml" xmlns:epub="http://www.idpf.org/2007/ops">
<head>
<title>Navigation</title>
</head>
<body>
</body>
</html>

6
ebook_converter/ebooks/conversion/plugins/fb2_input.py
View File

@@ -6,6 +6,7 @@ __copyright__ = '2008, Anatoly Shipitsin <norguhtar at gmail.com>'
Convert .fb2 files to .lrf Convert .fb2 files to .lrf
""" """
import os, re import os, re
import pkg_resources
from ebook_converter.customize.conversion import InputFormatPlugin, OptionRecommendation from ebook_converter.customize.conversion import InputFormatPlugin, OptionRecommendation
from ebook_converter import guess_type from ebook_converter import guess_type
@@ -86,8 +87,9 @@ class FB2Input(InputFormatPlugin):
css = re.sub(r'name\s*=\s*', 'class=', css) css = re.sub(r'name\s*=\s*', 'class=', css)
self.extract_embedded_content(doc) self.extract_embedded_content(doc)
log.debug('Converting XML to HTML...') log.debug('Converting XML to HTML...')
with open(P('templates/fb2.xsl'), 'rb') as f: with open(pkg_resources.resource_filename('ebook_converter',
ss = f.read().decode('utf-8') 'data/fb2.xsl')) as f:
ss = f.read().decode()
ss = ss.replace("__FB_NS__", fb_ns) ss = ss.replace("__FB_NS__", fb_ns)
if options.no_inline_fb2_toc: if options.no_inline_fb2_toc:
log('Disabling generation of inline FB2 TOC') log('Disabling generation of inline FB2 TOC')

19
ebook_converter/ebooks/conversion/plugins/html_output.py
View File

@@ -6,6 +6,7 @@ __docformat__ = 'restructuredtext en'
import os, re, shutil import os, re, shutil
from os.path import dirname, abspath, relpath as _relpath, exists, basename from os.path import dirname, abspath, relpath as _relpath, exists, basename
import pkg_resources
from ebook_converter.customize.conversion import OutputFormatPlugin, OptionRecommendation from ebook_converter.customize.conversion import OutputFormatPlugin, OptionRecommendation
from ebook_converter import CurrentDir from ebook_converter import CurrentDir
@@ -95,19 +96,31 @@ class HTMLOutput(OutputFormatPlugin):
with open(opts.template_html_index, 'rb') as f: with open(opts.template_html_index, 'rb') as f:
template_html_index_data = f.read() template_html_index_data = f.read()
else: else:
template_html_index_data = P('templates/html_export_default_index.tmpl', data=True) with open(pkg_resources.
resource_filename('ebook_converter',
'data/html_export_default_index.tmpl')
) as fobj:
template_html_index_data = fobj.read().decode()
if opts.template_html is not None: if opts.template_html is not None:
with open(opts.template_html, 'rb') as f: with open(opts.template_html, 'rb') as f:
template_html_data = f.read() template_html_data = f.read()
else: else:
template_html_data = P('templates/html_export_default.tmpl', data=True) with open(pkg_resources.
resource_filename('ebook_converter',
'data/html_export_default.tmpl')
) as fobj:
template_html_data = fobj.read().decode()
if opts.template_css is not None: if opts.template_css is not None:
with open(opts.template_css, 'rb') as f: with open(opts.template_css, 'rb') as f:
template_css_data = f.read() template_css_data = f.read()
else: else:
template_css_data = P('templates/html_export_default.css', data=True) with open(pkg_resources.
resource_filename('ebook_converter',
'data/html_export_default.css')
) as fobj:
template_css_data = fobj.read().decode()
template_html_index_data = template_html_index_data.decode('utf-8') template_html_index_data = template_html_index_data.decode('utf-8')
template_html_data = template_html_data.decode('utf-8') template_html_data = template_html_data.decode('utf-8')

9
ebook_converter/ebooks/conversion/plugins/lrf_input.py
View File

@@ -7,6 +7,8 @@ __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import os, sys import os, sys
import pkg_resources
from ebook_converter.customize.conversion import InputFormatPlugin from ebook_converter.customize.conversion import InputFormatPlugin
@@ -54,7 +56,12 @@ class LRFInput(InputFormatPlugin):
plot_map[ro] = imgstr[0].get('file') plot_map[ro] = imgstr[0].get('file')
self.log('Converting XML to HTML...') self.log('Converting XML to HTML...')
styledoc = safe_xml_fromstring(P('templates/lrf.xsl', data=True))
with open(pkg_resources.
resource_filename('ebook_converter',
'data/lrf.xsl')) as fobj:
# TODO(gryf): change this nonsense to etree.parse() instead.
styledoc = safe_xml_fromstring(fobj.read())
media_type = MediaType() media_type = MediaType()
styles = Styles() styles = Styles()
text_block = TextBlock(styles, char_button_map, plot_map, log) text_block = TextBlock(styles, char_button_map, plot_map, log)

33
ebook_converter/ebooks/lrf/fonts.py
View File

@@ -5,29 +5,40 @@ __copyright__ = '2008, Kovid Goyal <kovid at kovidgoyal.net>'
from PIL import ImageFont from PIL import ImageFont
from ebook_converter.utils.fonts.scanner import font_scanner
''' '''
Default fonts used in the PRS500 Default fonts used in the PRS500
''' '''
LIBERATION_FONT_MAP = { LIBERATION_FONT_MAP = {'Swis721 BT Roman': 'Liberation Sans Regular',
'Swis721 BT Roman' : 'LiberationSans-Regular', 'Dutch801 Rm BT Roman': 'Liberation Serif Regular',
'Dutch801 Rm BT Roman' : 'LiberationSerif-Regular', 'Courier10 BT Roman': 'Liberation Mono Regular'}
'Courier10 BT Roman' : 'LiberationMono-Regular', _LIB_CACHE = {}
}
FONT_FILE_MAP = {} FONT_FILE_MAP = {}
def get_font(name, size, encoding='unic'): def get_font(name, size, encoding='unic'):
''' """
Get an ImageFont object by name. Get an ImageFont object by name.
@param size: Font height in pixels. To convert from pts: @param size: Font height in pixels. To convert from pts:
sz in pixels = (dpi/72) * size in pts sz in pixels = (dpi/72) * size in pts
@param encoding: Font encoding to use. E.g. 'unic', 'symbol', 'ADOB', 'ADBE', 'aprm' @param encoding: Font encoding to use. E.g. 'unic', 'symbol', 'ADOB',
@param manager: A dict that will store the PersistentTemporary 'ADBE', 'aprm'
''' """
if name in LIBERATION_FONT_MAP: if name in LIBERATION_FONT_MAP:
return ImageFont.truetype(P('fonts/liberation/%s.ttf' % LIBERATION_FONT_MAP[name]), size, encoding=encoding) if not _LIB_CACHE:
for key in font_scanner.cache['fonts']:
record = font_scanner.cache['fonts'][key]
_LIB_CACHE[record['family_name'] + ' ' +
record['subfamily_name']] = record['path']
fpath = _LIB_CACHE.get(LIBERATION_FONT_MAP[name])
if not fpath:
raise ValueError('There is no liberation font existing in the '
'system. Please install them before converter '
'use.')
return ImageFont.truetype(fpath, size, encoding=encoding)
elif name in FONT_FILE_MAP: elif name in FONT_FILE_MAP:
return ImageFont.truetype(FONT_FILE_MAP[name], size, encoding=encoding) return ImageFont.truetype(FONT_FILE_MAP[name], size, encoding=encoding)

6
ebook_converter/ebooks/oeb/polish/toc.py
View File

@@ -10,6 +10,7 @@ import re
from collections import Counter, OrderedDict from collections import Counter, OrderedDict
from functools import partial from functools import partial
from operator import itemgetter from operator import itemgetter
import pkg_resources
from lxml import etree from lxml import etree
from lxml.builder import ElementMaker from lxml.builder import ElementMaker
@@ -690,7 +691,10 @@ def commit_nav_toc(container, toc, lang=None, landmarks=None, previous_nav=None)
if previous_nav is not None: if previous_nav is not None:
root = previous_nav[1] root = previous_nav[1]
else: else:
root = container.parse_xhtml(P('templates/new_nav.html', data=True).decode('utf-8')) with open(pkg_resources.
resource_filename('ebook_converter',
'data/new_nav.html')) as fobj:
root = container.parse_xhtml(fobj.read())
container.replace(tocname, root) container.replace(tocname, root)
else: else:
root = container.parsed(tocname) root = container.parsed(tocname)

14
ebook_converter/ebooks/oeb/transforms/jacket.py
View File

@@ -9,13 +9,13 @@ __docformat__ = 'restructuredtext en'
import sys, os, re import sys, os, re
from xml.sax.saxutils import escape from xml.sax.saxutils import escape
from string import Formatter from string import Formatter
import pkg_resources
from ebook_converter import guess_type, strftime from ebook_converter import guess_type, strftime
from ebook_converter.constants import iswindows from ebook_converter.constants import iswindows
from ebook_converter.ebooks.oeb.base import XPath, XHTML_NS, XHTML, xml2text, urldefrag, urlnormalize from ebook_converter.ebooks.oeb.base import XPath, XHTML_NS, XHTML, xml2text, urldefrag, urlnormalize
from ebook_converter.library.comments import comments_to_html, markdown from ebook_converter.library.comments import comments_to_html, markdown
from ebook_converter.utils.date import is_date_undefined, as_local_time from ebook_converter.utils.date import is_date_undefined, as_local_time
from ebook_converter.utils.icu import sort_key
from ebook_converter.ebooks.chardet import strip_encoding_declarations from ebook_converter.ebooks.chardet import strip_encoding_declarations
from ebook_converter.ebooks.metadata import fmt_sidx, rating_to_stars from ebook_converter.ebooks.metadata import fmt_sidx, rating_to_stars
from ebook_converter.polyglot.builtins import unicode_type, map from ebook_converter.polyglot.builtins import unicode_type, map
@@ -196,7 +196,7 @@ class Tags(unicode_type):
def __new__(self, tags, output_profile): def __new__(self, tags, output_profile):
tags = [escape(x) for x in tags or ()] tags = [escape(x) for x in tags or ()]
t = unicode_type.__new__(self, ', '.join(tags)) t = unicode_type.__new__(self, ', '.join(tags))
t.alphabetical = ', '.join(sorted(tags, key=sort_key)) t.alphabetical = ', '.join(sorted(tags))
t.tags_list = tags t.tags_list = tags
return t return t
@@ -232,8 +232,14 @@ def postprocess_jacket(root, output_profile, has_data):
def render_jacket(mi, output_profile, def render_jacket(mi, output_profile,
alt_title=_('Unknown'), alt_tags=[], alt_comments='', alt_title=_('Unknown'), alt_tags=[], alt_comments='',
alt_publisher='', rescale_fonts=False, alt_authors=None): alt_publisher='', rescale_fonts=False, alt_authors=None):
css = P('jacket/stylesheet.css', data=True).decode('utf-8') with open(pkg_resources.resource_filename('ebook_converter',
template = P('jacket/template.xhtml', data=True).decode('utf-8') 'data/jacket/stylesheet.css'),
'rb') as fobj:
css = fobj.read().decode()
with open(pkg_resources.resource_filename('ebook_converter',
'data/jacket/template.xhtml'),
'rb') as fobj:
template = fobj.read().decode()
template = re.sub(r'<!--.*?-->', '', template, flags=re.DOTALL) template = re.sub(r'<!--.*?-->', '', template, flags=re.DOTALL)
css = re.sub(r'/\*.*?\*/', '', css, flags=re.DOTALL) css = re.sub(r'/\*.*?\*/', '', css, flags=re.DOTALL)

30
ebook_converter/spell/__init__.py
View File

@@ -6,6 +6,8 @@ __license__ = 'GPL v3'
__copyright__ = '2014, Kovid Goyal <kovid at kovidgoyal.net>' __copyright__ = '2014, Kovid Goyal <kovid at kovidgoyal.net>'
from collections import namedtuple from collections import namedtuple
import json
import pkg_resources
from ebook_converter.utils.localization import canonicalize_lang from ebook_converter.utils.localization import canonicalize_lang
@@ -17,9 +19,31 @@ ccodes, ccodemap, country_names = None, None, None
def get_codes(): def get_codes():
global ccodes, ccodemap, country_names global ccodes, ccodemap, country_names
if ccodes is None: if ccodes is None:
from ebook_converter.utils.serialize import msgpack_loads src = pkg_resources.resource_filename('ebook_converter',
data = msgpack_loads(P('localization/iso3166.calibre_msgpack', allow_user_override=False, data=True)) 'data/iso_3166-1.json')
ccodes, ccodemap, country_names = data['codes'], data['three_map'], data['names'] with open(src, 'rb') as f:
db = json.load(f)
codes = set()
three_map = {}
name_map = {}
unicode_type = type(u'')
for x in db['3166-1']:
two = x.get('alpha_2')
if two:
two = unicode_type(two)
codes.add(two)
name_map[two] = x.get('name')
if name_map[two]:
name_map[two] = unicode_type(name_map[two])
three = x.get('alpha_3')
if three:
three_map[unicode_type(three)] = two
data = {'names': name_map,
'codes': frozenset(codes),
'three_map': three_map}
ccodes, ccodemap, country_names = (data['codes'], data['three_map'],
data['names'])
return ccodes, ccodemap return ccodes, ccodemap

5
ebook_converter/utils/config_base.py
View File

@@ -6,6 +6,7 @@ import os, re, traceback, numbers
from functools import partial from functools import partial
from collections import defaultdict from collections import defaultdict
from copy import deepcopy from copy import deepcopy
import pkg_resources
from ebook_converter.utils.lock import ExclusiveFile from ebook_converter.utils.lock import ExclusiveFile
from ebook_converter.constants import config_dir, CONFIG_DIR_MODE, ispy3, preferred_encoding, filesystem_encoding, iswindows from ebook_converter.constants import config_dir, CONFIG_DIR_MODE, ispy3, preferred_encoding, filesystem_encoding, iswindows
@@ -634,7 +635,9 @@ def read_custom_tweaks():
def default_tweaks_raw(): def default_tweaks_raw():
return P('default_tweaks.py', data=True, allow_user_override=False) with open(pkg_resources.resource_filename('ebook_converter',
'data/default_tweaks.py')) as f:
return f.read().encode()
def read_tweaks(): def read_tweaks():

3
ebook_converter/utils/fonts/scanner.py
View File

@@ -195,8 +195,7 @@ class FontScanner(Thread):
def __init__(self, folders=[], allowed_extensions={'ttf', 'otf'}): def __init__(self, folders=[], allowed_extensions={'ttf', 'otf'}):
Thread.__init__(self) Thread.__init__(self)
self.folders = folders + font_dirs() + [os.path.join(config_dir, 'fonts'), self.folders = folders + font_dirs()
P('fonts/liberation')]
self.folders = [os.path.normcase(os.path.abspath(font)) for font in self.folders = [os.path.normcase(os.path.abspath(font)) for font in
self.folders] self.folders]
self.font_families = () self.font_families = ()

3
ebook_converter/utils/fonts/utils.py
View File

@@ -451,6 +451,7 @@ def get_font_for_text(text, candidate_font_data=None):
def test_glyph_ids(): def test_glyph_ids():
from ebook_converter.utils.fonts.free_type import FreeType from ebook_converter.utils.fonts.free_type import FreeType
# TODO(gryf): move this test to test files
data = P('fonts/liberation/LiberationSerif-Regular.ttf', data=True) data = P('fonts/liberation/LiberationSerif-Regular.ttf', data=True)
ft = FreeType() ft = FreeType()
font = ft.load_font(data) font = ft.load_font(data)
@@ -462,6 +463,7 @@ def test_glyph_ids():
def test_supports_text(): def test_supports_text():
# TODO(gryf): move this test to test files
data = P('fonts/calibreSymbols.otf', data=True) data = P('fonts/calibreSymbols.otf', data=True)
if not supports_text(data, '.★½'): if not supports_text(data, '.★½'):
raise RuntimeError('Incorrectly returning that text is not supported') raise RuntimeError('Incorrectly returning that text is not supported')
@@ -470,6 +472,7 @@ def test_supports_text():
def test_find_font(): def test_find_font():
# TODO(gryf): move this test to test files
from ebook_converter.utils.fonts.scanner import font_scanner from ebook_converter.utils.fonts.scanner import font_scanner
abcd = '诶比西迪' abcd = '诶比西迪'
family = font_scanner.find_font_for_text(abcd)[0] family = font_scanner.find_font_for_text(abcd)[0]

254
ebook_converter/utils/localization.py
View File

@@ -2,7 +2,7 @@ __license__ = 'GPL v3'
__copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>' __copyright__ = '2009, Kovid Goyal <kovid@kovidgoyal.net>'
__docformat__ = 'restructuredtext en' __docformat__ = 'restructuredtext en'
import os, locale, re, io, sys import re, io, sys
import json import json
from gettext import GNUTranslations, NullTranslations from gettext import GNUTranslations, NullTranslations
import pkg_resources import pkg_resources
@@ -12,64 +12,6 @@ from ebook_converter.polyglot.builtins import is_py3, iteritems, unicode_type
_available_translations = None _available_translations = None
def available_translations():
global _available_translations
if _available_translations is None:
stats = P('localization/stats.calibre_msgpack', allow_user_override=False)
if os.path.exists(stats):
from ebook_converter.utils.serialize import msgpack_loads
with open(stats, 'rb') as f:
stats = msgpack_loads(f.read())
else:
stats = {}
_available_translations = [x for x in stats if stats[x] > 0.1]
return _available_translations
def get_system_locale():
from ebook_converter.constants import iswindows, isosx, plugins
lang = None
if iswindows:
try:
from ebook_converter.constants import get_windows_user_locale_name
lang = get_windows_user_locale_name()
lang = lang.strip()
if not lang:
lang = None
except:
pass # Windows XP does not have the GetUserDefaultLocaleName fn
elif isosx:
try:
lang = plugins['usbobserver'][0].user_locale() or None
except:
# Fallback to environment vars if something bad happened
import traceback
traceback.print_exc()
if lang is None:
try:
envvars = ['LANGUAGE', 'LC_ALL', 'LC_CTYPE', 'LC_MESSAGES', 'LANG']
lang = locale.getdefaultlocale(envvars)[0]
# lang is None in two cases: either the environment variable is not
# set or it's "C". Stop looking for a language in the latter case.
if lang is None:
for var in envvars:
if os.environ.get(var) == 'C':
lang = 'en_US'
break
except:
pass # This happens on Ubuntu apparently
if lang is None and 'LANG' in os.environ: # Needed for OS X
try:
lang = os.environ['LANG']
except:
pass
if lang:
lang = lang.replace('-', '_')
lang = '_'.join(lang.split('_')[:2])
return lang
def sanitize_lang(lang): def sanitize_lang(lang):
if lang: if lang:
match = re.match('[a-z]{2,3}(_[A-Z]{2}){0,1}', lang) match = re.match('[a-z]{2,3}(_[A-Z]{2}){0,1}', lang)
@@ -83,101 +25,16 @@ def sanitize_lang(lang):
def get_lang(): def get_lang():
'Try to figure out what language to display the interface in' return 'en_US'
from ebook_converter.utils.config_base import prefs
lang = prefs['language']
lang = os.environ.get('CALIBRE_OVERRIDE_LANG', lang)
if lang:
return lang
try:
lang = get_system_locale()
except:
import traceback
traceback.print_exc()
lang = None
return sanitize_lang(lang)
def is_rtl(): def is_rtl():
return get_lang()[:2].lower() in {'he', 'ar'} return get_lang()[:2].lower() in {'he', 'ar'}
def get_lc_messages_path(lang):
hlang = None
if zf_exists():
if lang in available_translations():
hlang = lang
else:
xlang = lang.split('_')[0].lower()
if xlang in available_translations():
hlang = xlang
return hlang
def zf_exists():
return os.path.exists(P('localization/locales.zip',
allow_user_override=False))
_lang_trans = None _lang_trans = None
def get_all_translators():
from zipfile import ZipFile
with ZipFile(P('localization/locales.zip', allow_user_override=False), 'r') as zf:
for lang in available_translations():
mpath = get_lc_messages_path(lang)
if mpath is not None:
buf = io.BytesIO(zf.read(mpath + '/messages.mo'))
yield lang, GNUTranslations(buf)
def get_single_translator(mpath, which='messages'):
from zipfile import ZipFile
with ZipFile(P('localization/locales.zip', allow_user_override=False), 'r') as zf:
path = '{}/{}.mo'.format(mpath, which)
data = zf.read(path)
buf = io.BytesIO(data)
try:
return GNUTranslations(buf)
except Exception as e:
import traceback
traceback.print_exc()
import hashlib
sig = hashlib.sha1(data).hexdigest()
raise ValueError('Failed to load translations for: {} (size: {} and signature: {}) with error: {}'.format(
path, len(data), sig, e))
def get_iso639_translator(lang):
lang = sanitize_lang(lang)
mpath = get_lc_messages_path(lang) if lang else None
return get_single_translator(mpath, 'iso639') if mpath else None
def get_translator(bcp_47_code):
parts = bcp_47_code.replace('-', '_').split('_')[:2]
parts[0] = lang_as_iso639_1(parts[0].lower()) or 'en'
if len(parts) > 1:
parts[1] = parts[1].upper()
lang = '_'.join(parts)
lang = {'pt':'pt_BR', 'zh':'zh_CN'}.get(lang, lang)
available = available_translations()
found = True
if lang == 'en' or lang.startswith('en_'):
return found, lang, NullTranslations()
if lang not in available:
lang = {'pt':'pt_BR', 'zh':'zh_CN'}.get(parts[0], parts[0])
if lang not in available:
lang = get_lang()
if lang not in available:
lang = 'en'
found = False
if lang == 'en':
return True, lang, NullTranslations()
return found, lang, get_single_translator(lang)
lcdata = { lcdata = {
'abday': ('Sun', 'Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat'), 'abday': ('Sun', 'Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat'),
'abmon': ('Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'), 'abmon': ('Jan', 'Feb', 'Mar', 'Apr', 'May', 'Jun', 'Jul', 'Aug', 'Sep', 'Oct', 'Nov', 'Dec'),
@@ -208,62 +65,9 @@ def load_po(path):
def set_translators(): def set_translators():
global _lang_trans, lcdata t = NullTranslations()
# To test different translations invoke as set_translators.lang = t.info().get('language')
# CALIBRE_OVERRIDE_LANG=de_DE.utf8 program t.install(names=('ngettext',))
lang = get_lang()
t = buf = iso639 = None
if 'CALIBRE_TEST_TRANSLATION' in os.environ:
buf = load_po(os.path.expanduser(os.environ['CALIBRE_TEST_TRANSLATION']))
if lang:
mpath = get_lc_messages_path(lang)
if buf is None and mpath and os.access(mpath + '.po', os.R_OK):
buf = load_po(mpath + '.po')
if mpath is not None:
from zipfile import ZipFile
with ZipFile(P('localization/locales.zip',
allow_user_override=False), 'r') as zf:
if buf is None:
buf = io.BytesIO(zf.read(mpath + '/messages.mo'))
if mpath == 'nds':
mpath = 'de'
isof = mpath + '/iso639.mo'
try:
iso639 = io.BytesIO(zf.read(isof))
except:
pass # No iso639 translations for this lang
if buf is not None:
from ebook_converter.utils.serialize import msgpack_loads
try:
lcdata = msgpack_loads(zf.read(mpath + '/lcdata.calibre_msgpack'))
except:
pass # No lcdata
if buf is not None:
t = GNUTranslations(buf)
if iso639 is not None:
iso639 = _lang_trans = GNUTranslations(iso639)
t.add_fallback(iso639)
if t is None:
t = NullTranslations()
try:
set_translators.lang = t.info().get('language')
except Exception:
pass
if is_py3:
t.install(names=('ngettext',))
else:
t.install(unicode=True, names=('ngettext',))
# Now that we have installed a translator, we have to retranslate the help
# for the global prefs object as it was instantiated in get_lang(), before
# the translator was installed.
from ebook_converter.utils.config_base import prefs
prefs.retranslate_help()
set_translators.lang = None set_translators.lang = None
@@ -535,53 +339,5 @@ def get_udc():
return _udc return _udc
def user_manual_stats():
stats = getattr(user_manual_stats, 'stats', None)
if stats is None:
import json
try:
stats = json.loads(P('user-manual-translation-stats.json', allow_user_override=False, data=True))
except EnvironmentError:
stats = {}
user_manual_stats.stats = stats
return stats
def localize_user_manual_link(url): def localize_user_manual_link(url):
#lc = lang_as_iso639_1(get_lang())
# if lc == 'en':
return url return url
# stats = user_manual_stats()
# if stats.get(lc, 0) < 0.3:
# return url
# from polyglot.urllib import urlparse, urlunparse
# parts = urlparse(url)
# path = re.sub(r'/generated/[a-z]+/', '/generated/%s/' % lc, parts.path or '')
# path = '/%s%s' % (lc, path)
# parts = list(parts)
# parts[2] = path
# return urlunparse(parts)
def website_languages():
stats = getattr(website_languages, 'stats', None)
if stats is None:
try:
stats = frozenset(P('localization/website-languages.txt', allow_user_override=False, data=True).split())
except EnvironmentError:
stats = frozenset()
website_languages.stats = stats
return stats
def localize_website_link(url):
lc = lang_as_iso639_1(get_lang())
langs = website_languages()
if lc == 'en' or lc not in langs:
return url
from ebook_converter.polyglot.urllib import urlparse, urlunparse
parts = urlparse(url)
path = '/{}{}'.format(lc, parts.path)
parts = list(parts)
parts[2] = path
return urlunparse(parts)

1
setup.cfg
View File

@@ -34,6 +34,7 @@ install_requires =
msgpack msgpack
html5-parser html5-parser
odfpy odfpy
setuptools
[options.entry_points] [options.entry_points]
console_scripts = console_scripts =