* [Django 1.0](http://djangoproject.com/) (application framework)
* [lxml 2.0.0](http://codespeak.net/lxml/) (for importing books)
+ * [librarian 1.1](http://redmine.nowoczesnapolska.org.pl/projects/show/librarian) (for importing books)
* Python libraries from lib directory
* Django applications from apps directory
+++ /dev/null
-#!/usr/bin/env python
-import os
-import optparse
-
-from librarian import html
-
-
-if __name__ == '__main__':
- # Parse commandline arguments
- usage = """Usage: %prog [options] SOURCE [SOURCE...]
- Convert SOURCE files to HTML format."""
-
- parser = optparse.OptionParser(usage=usage)
-
- parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=False,
- help='print status messages to stdout')
-
- options, input_filenames = parser.parse_args()
-
- if len(input_filenames) < 1:
- parser.print_help()
- exit(1)
-
- # Do some real work
- for input_filename in input_filenames:
- if options.verbose:
- print input_filename
-
- output_filename = os.path.splitext(input_filename)[0] + '.html'
- html.transform(input_filename, output_filename)
-
+++ /dev/null
-#!/usr/bin/env python
-import os
-import optparse
-
-from librarian import text
-
-
-if __name__ == '__main__':
- # Parse commandline arguments
- usage = """Usage: %prog [options] SOURCE [SOURCE...]
- Convert SOURCE files to TXT format."""
-
- parser = optparse.OptionParser(usage=usage)
-
- parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=False,
- help='print status messages to stdout')
-
- options, input_filenames = parser.parse_args()
-
- if len(input_filenames) < 1:
- parser.print_help()
- exit(1)
-
- # Do some real work
- for input_filename in input_filenames:
- if options.verbose:
- print input_filename
-
- output_filename = os.path.splitext(input_filename)[0] + '.txt'
- text.transform(input_filename, output_filename)
-
+++ /dev/null
-#!/usr/bin/env python
-import os
-import optparse
-
-from librarian import html
-
-
-if __name__ == '__main__':
- # Parse commandline arguments
- usage = """Usage: %prog [options] SOURCE [SOURCE...]
- Extract theme fragments from SOURCE."""
-
- parser = optparse.OptionParser(usage=usage)
-
- parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=False,
- help='print status messages to stdout')
-
- options, input_filenames = parser.parse_args()
-
- if len(input_filenames) < 1:
- parser.print_help()
- exit(1)
-
- # Do some real work
- for input_filename in input_filenames:
- if options.verbose:
- print input_filename
-
- output_filename = os.path.splitext(input_filename)[0] + '.fragments.html'
-
- closed_fragments, open_fragments = html.extract_fragments(input_filename)
-
- for fragment_id in open_fragments:
- print '%s:warning:unclosed fragment #%s' % (input_filename, fragment_id)
-
- output_file = open(output_filename, 'w')
- output_file.write("""
- <!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.1//EN" "http://www.w3.org/TR/xhtml11/DTD/xhtml11.dtd">
- <html><head>
- <title>bookfragments output</title>
- <meta http-equiv="content-type" content="text/html;charset=utf-8"/>
- <link rel="stylesheet" href="master.css" type="text/css" media="screen" charset="utf-8" />
- </head>
- <body>""")
- for fragment in closed_fragments.values():
- fragment_html = u'<div class="fragment"><h3>[#%s] %s</h3>%s</div>' % (fragment.id, fragment.themes, fragment)
- output_file.write(fragment_html.encode('utf-8'))
- output_file.write('</body></html>')
- output_file.close()
-
+++ /dev/null
-#!/usr/bin/env python
-# -*- coding: utf-8 -*-
-import os
-import optparse
-
-from lxml import etree
-from librarian import html
-from slughifi import slughifi
-
-
-BOOK_URL = 'http://wolnelektury.pl/katalog/lektura/'
-
-
-if __name__ == '__main__':
- # Parse commandline arguments
- usage = """Usage: %prog [options] SOURCE [SOURCE...]
- Generate slugs for SOURCE."""
-
- parser = optparse.OptionParser(usage=usage)
-
- parser.add_option('-v', '--verbose', action='store_true', dest='verbose', default=False,
- help='print status messages to stdout')
- parser.add_option('-f', '--force', action='store_true', dest='force', default=False,
- help='overwrite current identifiers')
-
- options, input_filenames = parser.parse_args()
-
- if len(input_filenames) < 1:
- parser.print_help()
- exit(1)
-
- # Do some real work
- for input_filename in input_filenames:
- if options.verbose:
- print input_filename
-
- doc = etree.parse(input_filename)
- try:
- title = doc.find('//{http://purl.org/dc/elements/1.1/}title').text
- except AttributeError:
- print '%s:error:Book title not found. Skipping.' % input_filename
- continue
-
- parent = ''
- try:
- parent_url = doc.find('//{http://purl.org/dc/elements/1.1/}relation.isPartOf').text
- parent = parent_url.rsplit('/', 1)[1] + ' '
- except AttributeError:
- pass
- except IndexError:
- print '%s:error:Invalid parent URL "%s". Skipping.' % (input_filename, parent_url)
-
- book_url = doc.find('//{http://purl.org/dc/elements/1.1/}identifier.url')
- if book_url is None:
- book_description = doc.find('//{http://www.w3.org/1999/02/22-rdf-syntax-ns#}Description')
- book_url = etree.SubElement(book_description, '{http://purl.org/dc/elements/1.1/}identifier.url')
- if not options.force and book_url.text.startswith('http://'):
- print '%s:Notice:Book already has identifier URL "%s". Skipping.' % (input_filename, book_url.text)
- continue
-
- book_url.text = BOOK_URL + slughifi(parent + title)[:60]
-
- doc.write(input_filename, xml_declaration=True, pretty_print=True, encoding='utf-8')
-
+++ /dev/null
-body {
- font-size: 16px;
- font: Georgia, "Times New Roman", serif;
- line-height: 1.5em;
- margin: 3em;
- max-width: 36em;
-}
-
-a {
- color: blue;
- text-decoration: none;
-}
-
-/* =================================================== */
-/* = Common elements: headings, paragraphs and lines = */
-/* =================================================== */
-h1 {
- font-size: 3em;
- margin: 1.5em 0;
- text-align: center;
- line-height: 1.5em;
- font-weight: bold;
-}
-
-h2 {
- font-size: 2em;
- margin: 1.5em 0 0;
- font-weight: bold;
- line-height: 1.5em;
-}
-
-h3 {
- font-size: 1.5em;
- margin: 1.5em 0 0;
- font-weight: normal;
- line-height: 1.5em;
-}
-
-h4 {
- font-size: 1em;
- margin: 1.5em 0 0;
- line-height: 1.5em;
-}
-
-p {
- margin: 0;
-}
-
-/* ======================== */
-/* = Footnotes and themes = */
-/* ======================== */
-.theme-begin {
- border-left: 0.1em solid #DDDDDD;
- color: #777;
- padding: 0 0.5em;
- width: 7.5em;
- font-style: normal;
- font-weight: normal;
- font-size: 16px;
- position: absolute;
- left: 40em;
- line-height: 1.5em;
- text-align: left;
-}
-
-.annotation {
- font-style: normal;
- font-weight: normal;
- font-size: 12px;
-}
-
-#footnotes .annotation {
- display: block;
- float: left;
- width: 2.5em;
- clear: both;
-}
-
-#footnotes div {
- margin: 1.5em 0 0 0;
-}
-
-#footnotes p {
- margin-left: 2.5em;
-}
-
-
-/* ============= */
-/* = Numbering = */
-/* ============= */
-.anchor {
- float: left;
- margin: -0.2em -0.5em -0.2em -3.5em;
- color: #777;
- font-size: 12px;
- width: 2em;
- text-align: center;
- padding: 0.2em 0.5em;
-}
-
-.anchor:hover, .anchor:active {
- color: #FFF;
- background-color: #CCC;
-}
-
-
-/* =================== */
-/* = Custom elements = */
-/* =================== */
-span.author {
- font-size: 0.75em;
- display: block;
- line-height: 1.5em;
- margin-bottom: 0.25em;
-}
-
-span.collection {
- font-size: 0.75em;
- display: block;
- line-height: 1.5em;
- margin-bottom: -0.25em;
-}
-
-span.subtitle {
- font-size: 0.75em;
- display: block;
- line-height: 1.5em;
- margin-top: -0.25em;
-}
-
-div.didaskalia {
- font-style: italic;
- margin: 0.5em 0 0;
-}
-
-div.kwestia {
- margin: 0.5em 0 0;
-}
-
-div.stanza {
- margin: 1.5em 0 0;
-}
-
-div.kwestia div.stanza {
- margin: 0;
-}
-
-p.paragraph {
- text-align: justify;
- margin: 1.5em 0 0;
-}
-
-p.motto {
- text-align: justify;
- font-style: italic;
- margin: 1.5em 0 0;
-}
-
-p.motto_podpis {
- font-size: 0.875em;
-}
-
-div.fragment {
- border-bottom: 0.1em solid #999;
- padding-bottom: 1.5em;
-}
-
-div.note p, div.dedication p, div.note p.paragraph, div.dedication p.paragraph {
- text-align: right;
- font-style: italic;
-}
-
-hr.spacer {
- height: 3em;
- visibility: hidden;
-}
-
-hr.spacer-line {
- margin: 1.5em 0;
- border: none;
- border-bottom: 0.1em solid #000;
-}
-
-p.spacer-asterisk {
- padding: 0;
- margin: 1.5em 0;
- text-align: center;
-}
-
-div.person-list ol {
- list-style: none;
- padding: 0 0 0 1.5em;
-}
-
-p.place-and-time {
- font-style: italic;
-}
-
-em.math, em.foreign-word, em.book-title, em.didaskalia, em.author-emphasis {
- font-style: italic;
-}
-
-em.person {
- font-style: normal;
- font-variant: small-caps;
-}
-
+++ /dev/null
-body {
- font-size: 16px;
- font: Georgia, "Times New Roman", serif;
- line-height: 1.5em;
- margin: 3em;
- max-width: 36em;
-}
-
-a {
- color: blue;
- text-decoration: none;
-}
-
-/* =================================================== */
-/* = Common elements: headings, paragraphs and lines = */
-/* =================================================== */
-h1 {
- font-size: 3em;
- margin: 1.5em 0;
- text-align: center;
- line-height: 1.5em;
- font-weight: bold;
-}
-
-h2 {
- font-size: 2em;
- margin: 1.5em 0 0;
- font-weight: bold;
- line-height: 1.5em;
-}
-
-h3 {
- font-size: 1.5em;
- margin: 1.5em 0 0;
- font-weight: normal;
- line-height: 1.5em;
-}
-
-h4 {
- font-size: 1em;
- margin: 1.5em 0 0;
- line-height: 1.5em;
-}
-
-p {
- margin: 0;
-}
-
-/* ======================== */
-/* = Footnotes and themes = */
-/* ======================== */
-.theme-begin {
- border-left: 0.1em solid #DDDDDD;
- color: #666;
- float: right;
- margin: 0 -9.5em 0 0;
- padding: 0 0.5em;
- width: 7.5em;
- font-style: normal;
- font-weight: normal;
- font-size: 16px;
- display: none;
-}
-
-.annotation {
- font-style: normal;
- font-weight: normal;
- font-size: 16px;
- display: none;
-}
-
-#footnotes {
- display: none;
-}
-
-#footnotes .annotation {
- display: block;
- float: left;
- width: 2.5em;
- clear: both;
-}
-
-#footnotes div {
- margin: 1.5em 0 0 0;
-}
-
-#footnotes p {
- margin-left: 2.5em;
-}
-
-/* =================== */
-/* = Custom elements = */
-/* =================== */
-span.author {
- font-size: 0.75em;
- display: block;
- line-height: 1.5em;
- margin-bottom: 0.25em;
-}
-
-span.collection {
- font-size: 0.75em;
- display: block;
- line-height: 1.5em;
- margin-bottom: -0.25em;
-}
-
-span.subtitle {
- font-size: 0.75em;
- display: block;
- line-height: 1.5em;
- margin-top: -0.25em;
-}
-
-div.didaskalia {
- font-style: italic;
- margin: 0.5em 0 0;
-}
-
-div.kwestia {
- margin: 0.5em 0 0;
-}
-
-div.stanza {
- margin: 1.5em 0 0;
-}
-
-div.kwestia div.stanza {
- margin: 0;
-}
-
-p.paragraph {
- text-align: justify;
- margin: 1.5em 0 0;
-}
-
-p.motto {
- text-align: justify;
- font-style: italic;
- margin: 1.5em 0 0;
-}
-
-p.motto_podpis {
- font-size: 0.875em;
-}
-
-div.fragment {
- border-bottom: 0.1em solid #999;
- padding-bottom: 1.5em;
-}
-
-div.note p, div.note p.paragraph {
- text-align: right;
- font-style: italic;
-}
-
-hr.spacer {
- height: 3em;
- visibility: hidden;
-}
+++ /dev/null
-<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
- xmlns:wl="http://wolnelektury.pl/functions" >
-
-<xsl:output encoding="utf-8" indent="yes" omit-xml-declaration = "yes" version="2.0" />
-
-
-<xsl:template match="utwor">
- <!-- <html>
- <head>
- <title>Książka z serwisu WolneLektury.pl</title>
- <meta http-equiv="content-type" content="text/html;charset=utf-8"/>
- </head>
- <style>
- body {
- font-size: 16px;
- font: Georgia, "Times New Roman", serif;
- line-height: 1.5em;
- margin: 0;
- }
-
- a {
- color: blue;
- text-decoration: none;
- }
-
- #book-text {
- margin: 3em;
- max-width: 36em;
- }
-
- /* ================================== */
- /* = Header with logo and menu = */
- /* ================================== */
- #header {
- margin: 3.4em 0 0 1.4em;
- }
-
- img {
- border: none;
- }
-
-
- #menu {
- position: fixed;
- left: 0em;
- top: 0em;
- width: 100%;
- height: 1.5em;
- background: #333;
- color: #FFF;
- opacity: 0.9;
- }
-
- #menu ul {
- list-style: none;
- padding: 0;
- margin: 0;
- }
-
- #menu li a {
- display: block;
- float: left;
- width: 7.5em;
- height: 1.5em;
- margin-left: 0.5em;
- text-align: center;
- color: #FFF;
- }
-
- #menu li a:hover, #menu li a:active {
- color: #000;
- background: #FFF url(/media/img/arrow-down.png) no-repeat center right;
- }
-
- #menu li a.selected {
- color: #000;
- background: #FFF url(/media/img/arrow-up.png) no-repeat center right;
- }
-
- #toc, #themes {
- position: fixed;
- left: 0em;
- top: 1.5em;
- width: 37em;
- padding: 1.5em;
- background: #FFF;
- border-bottom: 0.25em solid #DDD;
- border-right: 0.25em solid #DDD;
- display: none;
- height: 16em;
- overflow-x: hidden;
- overflow-y: auto;
- opacity: 0.9;
- }
-
- #toc ol, #themes ol {
- list-style: none;
- padding: 0;
- margin: 0;
- }
-
- #toc ol li {
- font-weight: bold;
- }
-
- #toc ol ol {
- padding: 0 0 1.5em 1.5em;
- margin: 0;
- }
-
- #toc ol ol li {
- font-weight: normal;
- }
-
- #toc h2 {
- display: none;
- }
-
- #toc .anchor {
- float: none;
- margin: 0;
- color: blue;
- font-size: 16px;
- position: inherit;
- }
-
- /* =================================================== */
- /* = Common elements: headings, paragraphs and lines = */
- /* =================================================== */
- h1 {
- font-size: 3em;
- margin: 1.5em 0;
- text-align: center;
- line-height: 1.5em;
- font-weight: bold;
- }
-
- h2 {
- font-size: 2em;
- margin: 1.5em 0 0;
- font-weight: bold;
- line-height: 1.5em;
- }
-
- h3 {
- font-size: 1.5em;
- margin: 1.5em 0 0;
- font-weight: normal;
- line-height: 1.5em;
- }
-
- h4 {
- font-size: 1em;
- margin: 1.5em 0 0;
- line-height: 1.5em;
- }
-
- p {
- margin: 0;
- }
-
- /* ======================== */
- /* = Footnotes and themes = */
- /* ======================== */
- .theme-begin {
- border-left: 0.1em solid #DDDDDD;
- color: #777;
- padding: 0 0.5em;
- width: 7.5em;
- font-style: normal;
- font-weight: normal;
- font-size: 16px;
- float: right;
- margin-right: -9.5em;
- clear: both;
- left: 40em;
- line-height: 1.5em;
- text-align: left;
- }
-
- .annotation {
- font-style: normal;
- font-weight: normal;
- font-size: 12px;
- }
-
- #footnotes .annotation {
- display: block;
- float: left;
- width: 2.5em;
- clear: both;
- }
-
- #footnotes div {
- margin: 1.5em 0 0 0;
- }
-
- #footnotes p {
- margin-left: 2.5em;
- font-size: 0.875em;
- }
-
- blockquote {
- font-size: 0.875em;
- }
-
- /* ============= */
- /* = Numbering = */
- /* ============= */
- .anchor {
- position: absolute;
- margin: -0.25em -0.5em;
- left: 1em;
- color: #777;
- font-size: 12px;
- width: 2em;
- text-align: center;
- padding: 0.25em 0.5em;
- line-height: 1.5em;
- }
-
- .anchor:hover, #book-text .anchor:active {
- color: #FFF;
- background-color: #CCC;
- }
-
- /* =================== */
- /* = Custom elements = */
- /* =================== */
- span.author {
- font-size: 0.5em;
- display: block;
- line-height: 1.5em;
- margin-bottom: 0.25em;
- }
-
- span.collection {
- font-size: 0.375em;
- display: block;
- line-height: 1.5em;
- margin-bottom: -0.25em;
- }
-
- span.subtitle {
- font-size: 0.5em;
- display: block;
- line-height: 1.5em;
- margin-top: -0.25em;
- }
-
- div.didaskalia {
- font-style: italic;
- margin: 0.5em 0 0 1.5em;
- }
-
- div.kwestia {
- margin: 0.5em 0 0;
- }
-
- div.stanza {
- margin: 1.5em 0 0;
- }
-
- div.kwestia div.stanza {
- margin: 0;
- }
-
- p.paragraph {
- text-align: justify;
- margin: 1.5em 0 0;
- }
-
- p.motto {
- text-align: justify;
- font-style: italic;
- margin: 1.5em 0 0;
- }
-
- p.motto_podpis {
- font-size: 0.875em;
- text-align: right;
- }
-
- div.fragment {
- border-bottom: 0.1em solid #999;
- padding-bottom: 1.5em;
- }
-
- div.note p, div.dedication p, div.note p.paragraph, div.dedication p.paragraph {
- text-align: right;
- font-style: italic;
- }
-
- hr.spacer {
- height: 3em;
- visibility: hidden;
- }
-
- hr.spacer-line {
- margin: 1.5em 0;
- border: none;
- border-bottom: 0.1em solid #000;
- }
-
- p.spacer-asterisk {
- padding: 0;
- margin: 1.5em 0;
- text-align: center;
- }
-
- div.person-list ol {
- list-style: none;
- padding: 0 0 0 1.5em;
- }
-
- p.place-and-time {
- font-style: italic;
- }
-
- em.math, em.foreign-word, em.book-title, em.didaskalia {
- font-style: italic;
- }
-
- em.author-emphasis {
- letter-spacing: 0.1em;
- }
-
- em.person {
- font-style: normal;
- font-variant: small-caps;
- }
- </style>
- <body> -->
- <div id="book-text">
- <xsl:apply-templates select="powiesc|opowiadanie|liryka_l|liryka_lp|dramat_wierszowany_l|dramat_wierszowany_lp|dramat_wspolczesny" />
- <xsl:if test="count(descendant::*[self::pe or self::pa or self::pr or self::pt][not(parent::extra)])">
- <div id="footnotes">
- <h3>Przypisy</h3>
- <xsl:for-each select="descendant::*[self::pe or self::pa or self::pr or self::pt][not(parent::extra)]">
- <div>
- <a name="{concat('footnote-', generate-id(.))}" />
- <a href="{concat('#anchor-', generate-id(.))}" class="annotation">[<xsl:number value="count(preceding::*[self::pa or self::pe or self::pr or self::pt]) + 1" />]</a>
- <xsl:choose>
- <xsl:when test="count(akap|akap_cd|strofa) = 0">
- <p><xsl:apply-templates select="text()|*" mode="inline" /></p>
- </xsl:when>
- <xsl:otherwise>
- <xsl:apply-templates select="text()|*" mode="inline" />
- </xsl:otherwise>
- </xsl:choose>
- </div>
- </xsl:for-each>
- </div>
- </xsl:if>
- </div>
- <!-- </body>
- </html> -->
-</xsl:template>
-
-
-<!-- ============================================================================== -->
-<!-- = MASTER TAG = -->
-<!-- = (can contain block tags, paragraph tags, standalone tags and special tags) = -->
-<!-- ============================================================================== -->
-<xsl:template match="powiesc|opowiadanie|liryka_l|liryka_lp|dramat_wierszowany_l|dramat_wierszowany_lp|dramat_wspolczesny">
- <xsl:if test="nazwa_utworu">
- <h1>
- <xsl:apply-templates select="autor_utworu|dzielo_nadrzedne|nazwa_utworu|podtytul" mode="header" />
- </h1>
- </xsl:if>
- <xsl:apply-templates />
-</xsl:template>
-
-
-<!-- ==================================================================================== -->
-<!-- = BLOCK TAGS = -->
-<!-- = (can contain other block tags, paragraph tags, standalone tags and special tags) = -->
-<!-- ==================================================================================== -->
-<xsl:template match="nota">
- <div class="note"><xsl:apply-templates /></div>
-</xsl:template>
-
-<xsl:template match="lista_osob">
- <div class="person-list">
- <h3><xsl:value-of select="naglowek_listy" /></h3>
- <ol>
- <xsl:apply-templates select="lista_osoba" />
- </ol>
- </div>
-</xsl:template>
-
-<xsl:template match="dedykacja">
- <div class="dedication"><xsl:apply-templates /></div>
-</xsl:template>
-
-<xsl:template match="kwestia">
- <div class="kwestia">
- <xsl:apply-templates select="strofa|akap|didaskalia" />
- </div>
-</xsl:template>
-
-<xsl:template match="dlugi_cytat|poezja_cyt">
- <blockquote><xsl:apply-templates /></blockquote>
-</xsl:template>
-
-<xsl:template match="motto">
- <div class="motto"><xsl:apply-templates mode="inline" /></div>
-</xsl:template>
-
-
-<!-- ========================================== -->
-<!-- = PARAGRAPH TAGS = -->
-<!-- = (can contain inline and special tags) = -->
-<!-- ========================================== -->
-<!-- Title page -->
-<xsl:template match="autor_utworu" mode="header">
- <span class="author"><xsl:apply-templates mode="inline" /></span>
-</xsl:template>
-
-<xsl:template match="nazwa_utworu" mode="header">
- <span class="title"><xsl:apply-templates mode="inline" /></span>
-</xsl:template>
-
-<xsl:template match="dzielo_nadrzedne" mode="header">
- <span class="collection"><xsl:apply-templates mode="inline" /></span>
-</xsl:template>
-
-<xsl:template match="podtytul" mode="header">
- <span class="subtitle"><xsl:apply-templates mode="inline" /></span>
-</xsl:template>
-
-<!-- Section headers (included in index)-->
-<xsl:template match="naglowek_akt|naglowek_czesc|srodtytul">
- <h2><xsl:apply-templates mode="inline" /></h2>
-</xsl:template>
-
-<xsl:template match="naglowek_scena|naglowek_rozdzial">
- <h3><xsl:apply-templates mode="inline" /></h3>
-</xsl:template>
-
-<xsl:template match="naglowek_osoba|naglowek_podrozdzial">
- <h4><xsl:apply-templates mode="inline" /></h4>
-</xsl:template>
-
-<!-- Other paragraph tags -->
-<xsl:template match="miejsce_czas">
- <p class="place-and-time"><xsl:apply-templates mode="inline" /></p>
-</xsl:template>
-
-<xsl:template match="didaskalia">
- <div class="didaskalia"><xsl:apply-templates mode="inline" /></div>
-</xsl:template>
-
-<xsl:template match="lista_osoba">
- <li><xsl:apply-templates mode="inline" /></li>
-</xsl:template>
-
-<xsl:template match="akap|akap_dialog|akap_cd">
- <p class="paragraph"><xsl:apply-templates mode="inline" /></p>
-</xsl:template>
-
-<xsl:template match="strofa">
- <div class="stanza">
- <xsl:choose>
- <xsl:when test="count(br) > 0">
- <xsl:call-template name="verse">
- <xsl:with-param name="verse-content" select="br[1]/preceding-sibling::text() | br[1]/preceding-sibling::node()" />
- <xsl:with-param name="verse-type" select="br[1]/preceding-sibling::*[name() = 'wers_wciety' or name() = 'wers_akap' or name() = 'wers_cd'][1]" />
- </xsl:call-template>
- <xsl:for-each select="br">
- <!-- Each BR tag "consumes" text after it -->
- <xsl:variable name="lnum" select="count(preceding-sibling::br)" />
- <xsl:call-template name="verse">
- <xsl:with-param name="verse-content"
- select="following-sibling::text()[count(preceding-sibling::br) = $lnum+1] | following-sibling::node()[count(preceding-sibling::br) = $lnum+1]" />
- <xsl:with-param name="verse-type" select="following-sibling::*[count(preceding-sibling::br) = $lnum+1 and (name() = 'wers_wciety' or name() = 'wers_akap' or name() = 'wers_cd')][1]" />
- </xsl:call-template>
- </xsl:for-each>
- </xsl:when>
- <xsl:otherwise>
- <xsl:call-template name="verse">
- <xsl:with-param name="verse-content" select="text() | node()" />
- <xsl:with-param name="verse-type" select="wers_wciety|wers_akap|wers_cd[1]" />
- </xsl:call-template>
- </xsl:otherwise>
- </xsl:choose>
- </div>
-</xsl:template>
-
-<xsl:template name="verse">
- <xsl:param name="verse-content" />
- <xsl:param name="verse-type" />
- <p class="verse">
- <xsl:choose>
- <xsl:when test="name($verse-type) = 'wers_akap'">
- <xsl:attribute name="style">padding-left: 1em</xsl:attribute>
- </xsl:when>
- <xsl:when test="name($verse-type) = 'wers_wciety'">
- <xsl:choose>
- <xsl:when test="$verse-content/@typ">
- <xsl:attribute name="style">padding-left: <xsl:value-of select="$verse-content/@typ" />em</xsl:attribute>
- </xsl:when>
- <xsl:otherwise>
- <xsl:attribute name="style">padding-left: 1em</xsl:attribute>
- </xsl:otherwise>
- </xsl:choose>
- </xsl:when>
- <xsl:when test="name($verse-type) = 'wers_cd'">
- <xsl:attribute name="style">padding-left: 12em</xsl:attribute>
- </xsl:when>
- </xsl:choose>
- <xsl:apply-templates select="$verse-content" mode="inline" />
- </p>
-</xsl:template>
-
-<xsl:template match="motto_podpis">
- <p class="motto_podpis"><xsl:apply-templates mode="inline" /></p>
-</xsl:template>
-
-
-<!-- ================================================ -->
-<!-- = INLINE TAGS = -->
-<!-- = (contain other inline tags and special tags) = -->
-<!-- ================================================ -->
-<!-- Annotations -->
-<xsl:template match="pa|pe|pr|pt" mode="inline">
- <a name="{concat('anchor-', generate-id(.))}" />
- <a href="{concat('#footnote-', generate-id(.))}" class="annotation">[<xsl:number value="count(preceding::*[self::pa or self::pe or self::pr or self::pt]) + 1" />]</a>
-</xsl:template>
-
-<!-- Other inline tags -->
-<xsl:template match="mat" mode="inline">
- <em class="math"><xsl:apply-templates mode="inline" /></em>
-</xsl:template>
-
-<xsl:template match="didask_tekst" mode="inline">
- <em class="didaskalia"><xsl:apply-templates mode="inline" /></em>
-</xsl:template>
-
-<xsl:template match="slowo_obce" mode="inline">
- <em class="foreign-word"><xsl:apply-templates mode="inline" /></em>
-</xsl:template>
-
-<xsl:template match="tytul_dziela" mode="inline">
- <em class="book-title">
- <xsl:if test="@typ = '1'">„</xsl:if><xsl:apply-templates mode="inline" /><xsl:if test="@typ = '1'">”</xsl:if>
- </em>
-</xsl:template>
-
-<xsl:template match="wyroznienie" mode="inline">
- <em class="author-emphasis"><xsl:apply-templates mode="inline" /></em>
-</xsl:template>
-
-<xsl:template match="osoba" mode="inline">
- <em class="person"><xsl:apply-templates mode="inline" /></em>
-</xsl:template>
-
-
-<!-- ============================================== -->
-<!-- = STANDALONE TAGS = -->
-<!-- = (cannot contain any other tags) = -->
-<!-- ============================================== -->
-<xsl:template match="sekcja_swiatlo">
- <hr class="spacer" />
-</xsl:template>
-
-<xsl:template match="sekcja_asterysk">
- <p class="spacer-asterisk">*</p>
-</xsl:template>
-
-<xsl:template match="separator_linia">
- <hr class="spacer-line" />
-</xsl:template>
-
-
-<!-- ================ -->
-<!-- = SPECIAL TAGS = -->
-<!-- ================ -->
-<!-- Themes -->
-<xsl:template match="begin" mode="inline">
- <xsl:variable name="mnum" select="concat('m', substring(@id, 2))" />
- <a name="m{substring(@id, 2)}" class="theme-begin" fid="{substring(@id, 2)}">
- <xsl:value-of select="string(following::motyw[@id=$mnum]/text())" />
- </a>
-</xsl:template>
-
-<xsl:template match="end" mode="inline">
- <span class="theme-end" fid="{substring(@id, 2)}"> </span>
-</xsl:template>
-
-<xsl:template match="begin|end">
- <xsl:apply-templates select='.' mode="inline" />
-</xsl:template>
-
-<xsl:template match="motyw" mode="inline" />
-
-
-<!-- ================ -->
-<!-- = IGNORED TAGS = -->
-<!-- ================ -->
-<xsl:template match="extra|uwaga" />
-<xsl:template match="extra|uwaga" mode="inline" />
-
-
-<!-- ======== -->
-<!-- = TEXT = -->
-<!-- ======== -->
-<xsl:template match="text()" />
-<xsl:template match="text()" mode="inline">
- <xsl:value-of select="wl:substitute_entities(.)" />
-</xsl:template>
-
-
-</xsl:stylesheet>
-
+++ /dev/null
-<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform"
- xmlns:wl="http://wolnelektury.pl/functions" >
-
-<xsl:output encoding="utf-8" method="text" />
-
-<!-- ============================================================================== -->
-<!-- = MASTER TAG = -->
-<!-- = (can contain block tags, paragraph tags, standalone tags and special tags) = -->
-<!-- ============================================================================== -->
-<xsl:template match="powiesc|opowiadanie|liryka_l|liryka_lp|dramat_wierszowany_l|dramat_wierszowany_lp|dramat_wspolczesny">
-<xsl:text>Kodowanie znaków w dokumencie: UTF-8.
------
-Publikacja zrealizowana w ramach projektu Wolne Lektury (http://wolnelektury.pl/). Reprodukcja cyfrowa wykonana przez
-Bibliotekę Narodową z egzemplarza pochodzącego ze zbiorów BN. Ten utwór nie jest chroniony prawem autorskim i znajduje
-się w domenie publicznej, co oznacza, że możesz go swobodnie wykorzystywać, publikować i rozpowszechniać.
-
-Wersja lektury w opracowaniu merytorycznym i krytycznym (przypisy i motywy) dostępna jest na stronie %s.
------
-
-
-</xsl:text>
-<xsl:if test="nazwa_utworu"><xsl:apply-templates select="autor_utworu|dzielo_nadrzedne|nazwa_utworu|podtytul" mode="header" /></xsl:if>
-<xsl:text>
-
-</xsl:text>
-<xsl:apply-templates />
-</xsl:template>
-
-
-<!-- ==================================================================================== -->
-<!-- = BLOCK TAGS = -->
-<!-- = (can contain other block tags, paragraph tags, standalone tags and special tags) = -->
-<!-- ==================================================================================== -->
-<xsl:template match="nota">
-<xsl:apply-templates />
-</xsl:template>
-
-<xsl:template match="lista_osob">
-<xsl:text>
-
-
-</xsl:text>
-<xsl:value-of select="naglowek_listy" />
-<xsl:apply-templates select="lista_osoba" />
-<xsl:text>
-</xsl:text>
-</xsl:template>
-
-<xsl:template match="dedykacja">
-<xsl:text>
-
-</xsl:text>
-<xsl:apply-templates />
-</xsl:template>
-
-<xsl:template match="kwestia">
-<xsl:apply-templates select="strofa|akap|didaskalia" />
-</xsl:template>
-
-<xsl:template match="dlugi_cytat|poezja_cyt">
-<xsl:text>
-</xsl:text>
-<xsl:apply-templates />
-</xsl:template>
-
-<xsl:template match="motto">
-<xsl:text>
-
-</xsl:text>
-<xsl:apply-templates mode="inline" /><xsl:text>
-
-</xsl:text>
-</xsl:template>
-
-
-<!-- ========================================== -->
-<!-- = PARAGRAPH TAGS = -->
-<!-- = (can contain inline and special tags) = -->
-<!-- ========================================== -->
-<!-- Title page -->
-<xsl:template match="autor_utworu" mode="header">
-<xsl:text>
-
-</xsl:text>
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-<xsl:template match="nazwa_utworu" mode="header">
-<xsl:text>
-
-</xsl:text>
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-<xsl:template match="dzielo_nadrzedne" mode="header">
-<xsl:text>
-</xsl:text>
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-<xsl:template match="podtytul" mode="header">
-<xsl:text>
-</xsl:text>
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-<!-- Section headers (included in index)-->
-<xsl:template match="naglowek_akt|naglowek_czesc|srodtytul">
-<xsl:text>
-
-
-
-
-</xsl:text>
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-<xsl:template match="naglowek_scena|naglowek_rozdzial">
-<xsl:text>
-
-
-
-</xsl:text>
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-<xsl:template match="naglowek_osoba|naglowek_podrozdzial">
-<xsl:text>
-
-
-</xsl:text>
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-<!-- Other paragraph tags -->
-<xsl:template match="miejsce_czas">
-<xsl:text>
-
-
-
-</xsl:text>
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-<xsl:template match="didaskalia">
-<xsl:text>
-
-/ </xsl:text><xsl:apply-templates mode="inline" /><xsl:text> /</xsl:text>
-</xsl:template>
-
-<xsl:template match="lista_osoba">
-<xsl:text>
- * </xsl:text>
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-<xsl:template match="akap|akap_dialog|akap_cd">
-<xsl:text>
-
-</xsl:text>
-<xsl:value-of select="wl:wrap_words(text())" />
-</xsl:template>
-
-<xsl:template match="strofa">
-<xsl:text>
-
-</xsl:text>
- <xsl:choose>
- <xsl:when test="count(br) > 0">
- <xsl:call-template name="verse">
- <xsl:with-param name="verse-content" select="br[1]/preceding-sibling::text() | br[1]/preceding-sibling::node()" />
- <xsl:with-param name="verse-type" select="br[1]/preceding-sibling::*[name() = 'wers_wciety' or name() = 'wers_akap' or name() = 'wers_cd'][1]" />
- </xsl:call-template>
- <xsl:for-each select="br">
- <!-- Each BR tag "consumes" text after it -->
- <xsl:variable name="lnum" select="count(preceding-sibling::br)" />
- <xsl:call-template name="verse">
- <xsl:with-param name="verse-content"
- select="following-sibling::text()[count(preceding-sibling::br) = $lnum+1] | following-sibling::node()[count(preceding-sibling::br) = $lnum+1]" />
- <xsl:with-param name="verse-type" select="following-sibling::*[count(preceding-sibling::br) = $lnum+1 and (name() = 'wers_wciety' or name() = 'wers_akap' or name() = 'wers_cd')][1]" />
- </xsl:call-template>
- </xsl:for-each>
- </xsl:when>
- <xsl:otherwise>
- <xsl:call-template name="verse">
- <xsl:with-param name="verse-content" select="text() | node()" />
- <xsl:with-param name="verse-type" select="wers_wciety|wers_akap|wers_cd[1]" />
- </xsl:call-template>
- </xsl:otherwise>
- </xsl:choose>
-</xsl:template>
-
-<xsl:template name="verse">
- <xsl:param name="verse-content" />
- <xsl:param name="verse-type" />
- <xsl:choose>
- <xsl:when test="name($verse-type) = 'wers_akap'">
- <xsl:text> </xsl:text>
- </xsl:when>
- <xsl:when test="name($verse-type) = 'wers_wciety'">
- <xsl:choose>
- <xsl:when test="$verse-content/@typ">
- <xsl:text> </xsl:text>
- </xsl:when>
- <xsl:otherwise>
- <xsl:text> </xsl:text>
- </xsl:otherwise>
- </xsl:choose>
- </xsl:when>
- <xsl:when test="name($verse-type) = 'wers_cd'">
- <xsl:text> </xsl:text>
- </xsl:when>
- </xsl:choose>
- <xsl:apply-templates select="$verse-content" mode="inline" />
-</xsl:template>
-
-<xsl:template match="motto_podpis">
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-
-<!-- ================================================ -->
-<!-- = INLINE TAGS = -->
-<!-- = (contain other inline tags and special tags) = -->
-<!-- ================================================ -->
-<!-- Annotations -->
-<xsl:template match="pa|pe|pr|pt" mode="inline" />
-
-<!-- Other inline tags -->
-<xsl:template match="mat" mode="inline"><xsl:apply-templates mode="inline" /></xsl:template>
-
-<xsl:template match="didask_tekst" mode="inline"><xsl:apply-templates mode="inline" /></xsl:template>
-
-<xsl:template match="slowo_obce" mode="inline"><xsl:apply-templates mode="inline" /></xsl:template>
-
-<xsl:template match="tytul_dziela" mode="inline">
-<xsl:if test="@typ = '1'">„</xsl:if><xsl:apply-templates mode="inline" /><xsl:if test="@typ = '1'">”</xsl:if>
-</xsl:template>
-
-<xsl:template match="wyroznienie" mode="inline">
-<xsl:text>*</xsl:text><xsl:apply-templates mode="inline" /><xsl:text>*</xsl:text>
-</xsl:template>
-
-<xsl:template match="osoba" mode="inline">
-<xsl:apply-templates mode="inline" />
-</xsl:template>
-
-
-<!-- ============================================== -->
-<!-- = STANDALONE TAGS = -->
-<!-- = (cannot contain any other tags) = -->
-<!-- ============================================== -->
-<xsl:template match="sekcja_swiatlo">
-<xsl:text>
-
-
-
-</xsl:text>
-</xsl:template>
-
-<xsl:template match="sekcja_asterysk">
-<xsl:text>
-
-*
-
-</xsl:text>
-</xsl:template>
-
-<xsl:template match="separator_linia">
-<xsl:text>
-
-------------------------------------------------
-
-</xsl:text>
-</xsl:template>
-
-
-<!-- ================ -->
-<!-- = SPECIAL TAGS = -->
-<!-- ================ -->
-<!-- Themes -->
-<xsl:template match="begin" mode="inline" />
-
-<xsl:template match="end" mode="inline" />
-
-<xsl:template match="begin|end" />
-
-<xsl:template match="motyw" mode="inline" />
-
-
-<!-- ================ -->
-<!-- = IGNORED TAGS = -->
-<!-- ================ -->
-<xsl:template match="extra|uwaga" />
-<xsl:template match="extra|uwaga" mode="inline" />
-
-
-<!-- ======== -->
-<!-- = TEXT = -->
-<!-- ======== -->
-<xsl:template match="text()" />
-<xsl:template match="text()" mode="inline">
- <xsl:value-of select="wl:substitute_entities(.)" />
-</xsl:template>
-
-
-</xsl:stylesheet>
-
+++ /dev/null
-# -*- coding: utf-8 -*-
-from xml.parsers.expat import ExpatError
-from datetime import date
-import time
-
-# Import ElementTree from anywhere
-try:
- import xml.etree.ElementTree as etree # Python >= 2.5
-except ImportError:
- try:
- import elementtree.ElementTree as etree # effbot's pure Python module
- except ImportError:
- import lxml.etree as etree # ElementTree API using libxml2
-
-
-# ==============
-# = Converters =
-# ==============
-class Person(object):
- """Single person with last name and a list of first names."""
- def __init__(self, last_name, *first_names):
- self.last_name = last_name
- self.first_names = first_names
-
-
- def __eq__(self, right):
- return self.last_name == right.last_name and self.first_names == right.first_names
-
-
- def __unicode__(self):
- if len(self.first_names) > 0:
- return '%s, %s' % (self.last_name, ' '.join(self.first_names))
- else:
- return self.last_name
-
-
- def __repr__(self):
- return 'Person(last_name=%r, first_names=*%r)' % (self.last_name, self.first_names)
-
-
-def str_to_unicode(value, previous):
- return unicode(value)
-
-
-def str_to_unicode_list(value, previous):
- if previous is None:
- previous = []
- previous.append(str_to_unicode(value, None))
- return previous
-
-
-def str_to_person(value, previous):
- comma_count = value.count(',')
-
- if comma_count == 0:
- last_name, first_names = value, []
- elif comma_count == 1:
- last_name, first_names = value.split(',')
- first_names = [name for name in first_names.split(' ') if len(name)]
- else:
- raise ValueError("value contains more than one comma: %r" % value)
-
- return Person(last_name.strip(), *first_names)
-
-
-def str_to_date(value, previous):
- try:
- t = time.strptime(value, '%Y-%m-%d')
- except ValueError:
- t = time.strptime(value, '%Y')
- return date(t[0], t[1], t[2])
-
-
-# ==========
-# = Parser =
-# ==========
-class ParseError(Exception):
- def __init__(self, message):
- super(ParseError, self).__init__(message)
-
-
-class XMLNamespace(object):
- '''Represents XML namespace.'''
-
- def __init__(self, uri):
- self.uri = uri
-
- def __call__(self, tag):
- return '{%s}%s' % (self.uri, tag)
-
- def __contains__(self, tag):
- return tag.startswith(str(self))
-
- def __repr__(self):
- return 'XMLNamespace(%r)' % self.uri
-
- def __str__(self):
- return '%s' % self.uri
-
-
-class BookInfo(object):
- RDF = XMLNamespace('http://www.w3.org/1999/02/22-rdf-syntax-ns#')
- DC = XMLNamespace('http://purl.org/dc/elements/1.1/')
-
- mapping = {
- DC('creator') : ('author', str_to_person),
- DC('title') : ('title', str_to_unicode),
- DC('subject.period') : ('epoch', str_to_unicode),
- DC('subject.type') : ('kind', str_to_unicode),
- DC('subject.genre') : ('genre', str_to_unicode),
- DC('date') : ('created_at', str_to_date),
- DC('date.pd') : ('released_to_public_domain_at', str_to_date),
- DC('contributor.translator') : ('translator', str_to_person),
- DC('contributor.technical_editor') : ('technical_editor', str_to_person),
- DC('publisher') : ('publisher', str_to_unicode),
- DC('source') : ('source_name', str_to_unicode),
- DC('source.URL') : ('source_url', str_to_unicode),
- DC('identifier.url') : ('url', str_to_unicode),
- DC('relation.hasPart') : ('parts', str_to_unicode_list),
- DC('rights.license') : ('license', str_to_unicode),
- DC('rights') : ('license_description', str_to_unicode),
- }
-
- @classmethod
- def from_string(cls, xml):
- from StringIO import StringIO
- return cls.from_file(StringIO(xml))
-
- @classmethod
- def from_file(cls, xml_file):
- book_info = cls()
-
- try:
- tree = etree.parse(xml_file)
- except ExpatError, e:
- raise ParseError(e)
-
- description = tree.find('//' + book_info.RDF('Description'))
- book_info.wiki_url = description.get(cls.RDF('about'), None)
-
- if description is None:
- raise ParseError('no Description tag found in document')
-
- for element in description.findall('*'):
- book_info.parse_element(element)
-
- return book_info
-
- def parse_element(self, element):
- try:
- attribute, converter = self.mapping[element.tag]
- setattr(self, attribute, converter(element.text, getattr(self, attribute, None)))
- except KeyError:
- pass
-
- def to_xml(self):
- """XML representation of this object."""
- etree._namespace_map[str(self.RDF)] = 'rdf'
- etree._namespace_map[str(self.DC)] = 'dc'
-
- root = etree.Element(self.RDF('RDF'))
- description = etree.SubElement(root, self.RDF('Description'))
-
- if self.wiki_url:
- description.set(self.RDF('about'), self.wiki_url)
-
- for tag, (attribute, converter) in self.mapping.iteritems():
- if hasattr(self, attribute):
- e = etree.Element(tag)
- e.text = unicode(getattr(self, attribute))
- description.append(e)
-
- return unicode(etree.tostring(root, 'utf-8'), 'utf-8')
-
- def to_dict(self):
- etree._namespace_map[str(self.RDF)] = 'rdf'
- etree._namespace_map[str(self.DC)] = 'dc'
-
- result = {'about': self.wiki_url}
- for tag, (attribute, converter) in self.mapping.iteritems():
- if hasattr(self, attribute):
- result[attribute] = unicode(getattr(self, attribute))
-
- return result
-
-
-def parse(file_name):
- return BookInfo.from_file(file_name)
-
-
-if __name__ == '__main__':
- import sys
-
- info = parse(sys.argv[1])
- for attribute, _ in BookInfo.mapping.values():
- print '%s: %r' % (attribute, getattr(info, attribute, None))
-
+++ /dev/null
-# -*- coding: utf-8 -*-
-import os
-import cStringIO
-import re
-import copy
-import pkgutil
-
-from lxml import etree
-
-
-ENTITY_SUBSTITUTIONS = [
- (u'---', u'—'),
- (u'--', u'–'),
- (u'...', u'…'),
- (u',,', u'„'),
- (u'"', u'”'),
-]
-
-
-def substitute_entities(context, text):
- """XPath extension function converting all entites in passed text."""
- if isinstance(text, list):
- text = ''.join(text)
- for entity, substitutution in ENTITY_SUBSTITUTIONS:
- text = text.replace(entity, substitutution)
- return text
-
-
-# Register substitute_entities function with lxml
-ns = etree.FunctionNamespace('http://wolnelektury.pl/functions')
-ns['substitute_entities'] = substitute_entities
-
-
-def transform(input_filename, output_filename):
- """Transforms file input_filename in XML to output_filename in XHTML."""
- # Parse XSLT
- style_filename = os.path.join(os.path.dirname(__file__), 'book2html.xslt')
- style = etree.parse(style_filename)
-
- doc_file = cStringIO.StringIO()
- expr = re.compile(r'/\s', re.MULTILINE | re.UNICODE);
-
- f = open(input_filename, 'r')
- for line in f:
- line = line.decode('utf-8')
- line = expr.sub(u'<br/>\n', line)
- doc_file.write(line.encode('utf-8'))
- f.close()
-
- doc_file.seek(0);
-
- parser = etree.XMLParser(remove_blank_text=True)
- doc = etree.parse(doc_file, parser)
-
- result = doc.xslt(style)
- if result.find('//p') is not None:
- add_anchors(result.getroot())
- add_table_of_contents(result.getroot())
- result.write(output_filename, xml_declaration=False, pretty_print=True, encoding='utf-8')
- return True
- else:
- return False
-
-
-class Fragment(object):
- def __init__(self, id, themes):
- super(Fragment, self).__init__()
- self.id = id
- self.themes = themes
- self.events = []
-
- def append(self, event, element):
- self.events.append((event, element))
-
- def closed_events(self):
- stack = []
- for event, element in self.events:
- if event == 'start':
- stack.append(('end', element))
- elif event == 'end':
- try:
- stack.pop()
- except IndexError:
- print 'CLOSED NON-OPEN TAG:', element
-
- stack.reverse()
- return self.events + stack
-
- def to_string(self):
- result = []
- for event, element in self.closed_events():
- if event == 'start':
- result.append(u'<%s %s>' % (element.tag, ' '.join('%s="%s"' % (k, v) for k, v in element.attrib.items())))
- if element.text:
- result.append(element.text)
- elif event == 'end':
- result.append(u'</%s>' % element.tag)
- if element.tail:
- result.append(element.tail)
- else:
- result.append(element)
-
- return ''.join(result)
-
- def __unicode__(self):
- return self.to_string()
-
-
-def extract_fragments(input_filename):
- """Extracts theme fragments from input_filename."""
- open_fragments = {}
- closed_fragments = {}
-
- for event, element in etree.iterparse(input_filename, events=('start', 'end')):
- # Process begin and end elements
- if element.get('class', '') in ('theme-begin', 'theme-end'):
- if not event == 'end': continue # Process elements only once, on end event
-
- # Open new fragment
- if element.get('class', '') == 'theme-begin':
- fragment = Fragment(id=element.get('fid'), themes=element.text)
-
- # Append parents
- if element.getparent().get('id', None) != 'book-text':
- parents = [element.getparent()]
- while parents[-1].getparent().get('id', None) != 'book-text':
- parents.append(parents[-1].getparent())
-
- parents.reverse()
- for parent in parents:
- fragment.append('start', parent)
-
- open_fragments[fragment.id] = fragment
-
- # Close existing fragment
- else:
- try:
- fragment = open_fragments[element.get('fid')]
- except KeyError:
- print '%s:closed not open fragment #%s' % (input_filename, element.get('fid'))
- else:
- closed_fragments[fragment.id] = fragment
- del open_fragments[fragment.id]
-
- # Append element tail to lost_text (we don't want to lose any text)
- if element.tail:
- for fragment_id in open_fragments:
- open_fragments[fragment_id].append('text', element.tail)
-
-
- # Process all elements except begin and end
- else:
- # Omit annotation tags
- if len(element.get('name', '')) or element.get('class', '') == 'annotation':
- if event == 'end' and element.tail:
- for fragment_id in open_fragments:
- open_fragments[fragment_id].append('text', element.tail)
- else:
- for fragment_id in open_fragments:
- open_fragments[fragment_id].append(event, copy.copy(element))
-
- return closed_fragments, open_fragments
-
-
-def add_anchor(element, prefix, with_link=True, with_target=True, link_text=None):
- if with_link:
- if link_text is None:
- link_text = prefix
- anchor = etree.Element('a', href='#%s' % prefix)
- anchor.set('class', 'anchor')
- anchor.text = unicode(link_text)
- if element.text:
- anchor.tail = element.text
- element.text = u''
- element.insert(0, anchor)
-
- if with_target:
- anchor_target = etree.Element('a', name='%s' % prefix)
- anchor_target.set('class', 'target')
- anchor_target.text = u' '
- if element.text:
- anchor_target.tail = element.text
- element.text = u''
- element.insert(0, anchor_target)
-
-
-def any_ancestor(element, test):
- for ancestor in element.iterancestors():
- if test(ancestor):
- return True
- return False
-
-
-def add_anchors(root):
- counter = 1
- for element in root.iterdescendants():
- if any_ancestor(element, lambda e: e.get('class') in ('note', 'motto', 'motto_podpis', 'dedication')
- or e.tag == 'blockquote'):
- continue
-
- if element.tag == 'p' and 'verse' in element.get('class', ''):
- if counter == 1 or counter % 5 == 0:
- add_anchor(element, "f%d" % counter, link_text=counter)
- counter += 1
- elif 'paragraph' in element.get('class', ''):
- add_anchor(element, "f%d" % counter, link_text=counter)
- counter += 1
-
-
-def add_table_of_contents(root):
- sections = []
- counter = 1
- for element in root.iterdescendants():
- if element.tag in ('h2', 'h3'):
- if any_ancestor(element, lambda e: e.get('id') in ('footnotes',) or e.get('class') in ('person-list',)):
- continue
-
- if element.tag == 'h3' and len(sections) and sections[-1][1] == 'h2':
- sections[-1][3].append((counter, element.tag, ''.join(element.xpath('text()')), []))
- else:
- sections.append((counter, element.tag, ''.join(element.xpath('text()')), []))
- add_anchor(element, "s%d" % counter, with_link=False)
- counter += 1
-
- toc = etree.Element('div')
- toc.set('id', 'toc')
- toc_header = etree.SubElement(toc, 'h2')
- toc_header.text = u'Spis treści'
- toc_list = etree.SubElement(toc, 'ol')
-
- for n, section, text, subsections in sections:
- section_element = etree.SubElement(toc_list, 'li')
- add_anchor(section_element, "s%d" % n, with_target=False, link_text=text)
-
- if len(subsections):
- subsection_list = etree.SubElement(section_element, 'ol')
- for n, subsection, text, _ in subsections:
- subsection_element = etree.SubElement(subsection_list, 'li')
- add_anchor(subsection_element, "s%d" % n, with_target=False, link_text=text)
-
- root.insert(0, toc)
-
+++ /dev/null
-# -*- coding: utf-8 -*-
-import unittest
-from os.path import dirname, join, realpath
-
-from lxml import etree
-from librarian import dcparser, html
-
-
-def test_file_path(dir_name, file_name):
- return realpath(join(dirname(__file__), 'files', dir_name, file_name))
-
-
-class TestDCParser(unittest.TestCase):
- KNOWN_RESULTS = (
- ('dcparser', 'andersen_brzydkie_kaczatko.xml', {
- 'publisher': u'Fundacja Nowoczesna Polska',
- 'about': u'http://wiki.wolnepodreczniki.pl/Lektury:Andersen/Brzydkie_kaczątko',
- 'source_name': u'Andersen, Hans Christian (1805-1875), Baśnie, Gebethner i Wolff, wyd. 7, Kraków, 1925',
- 'author': u'Andersen, Hans Christian',
- 'url': u'http://wolnelektury.pl/katalog/lektura/brzydkie-kaczatko',
- 'created_at': u'2007-08-14',
- 'title': u'Brzydkie kaczątko',
- 'kind': u'Epika',
- 'source_url': u'http://www.polona.pl/dlibra/doccontent2?id=3563&dirids=4',
- 'translator': u'Niewiadomska, Cecylia',
- 'released_to_public_domain_at': u'1925-01-01',
- 'epoch': u'Romantyzm',
- 'genre': u'Baśń',
- 'technical_editor': u'Gałecki, Dariusz',
- 'license_description': u'Domena publiczna - tłumacz Cecylia Niewiadomska zm. 1925',
- }),
- ('dcparser', 'kochanowski_piesn7.xml', {
- 'publisher': u'Fundacja Nowoczesna Polska',
- 'about': u'http://wiki.wolnepodreczniki.pl/Lektury:Kochanowski/Pieśni/Pieśń_VII_(1)',
- 'source_name': u'Kochanowski, Jan (1530-1584), Dzieła polskie, tom 1, oprac. Julian Krzyżanowski, wyd. 8, Państwowy Instytut Wydawniczy, Warszawa, 1976',
- 'author': u'Kochanowski, Jan',
- 'url': u'http://wolnelektury.pl/katalog/lektura/piesni-ksiegi-pierwsze-piesn-vii-trudna-rada-w-tej-mierze-pr',
- 'created_at': u'2007-08-31',
- 'title': u'Pieśń VII (Trudna rada w tej mierze: przyjdzie się rozjechać...)',
- 'kind': u'Liryka',
- 'source_url': u'http://www.polona.pl/Content/1499',
- 'released_to_public_domain_at': u'1584-01-01',
- 'epoch': u'Renesans',
- 'genre': u'Pieśń',
- 'technical_editor': u'Gałecki, Dariusz',
- 'license_description': u'Domena publiczna - Jan Kochanowski zm. 1584 ',
- }),
- ('dcparser', 'mickiewicz_rybka.xml', {
- 'publisher': u'Fundacja Nowoczesna Polska',
- 'about': 'http://wiki.wolnepodreczniki.pl/Lektury:Mickiewicz/Ballady/Rybka',
- 'source_name': u'Mickiewicz, Adam (1798-1855), Poezje, tom 1 (Wiersze młodzieńcze - Ballady i romanse - Wiersze do r. 1824), Krakowska Spółdzielnia Wydawnicza, wyd. 2 zwiększone, Kraków, 1922',
- 'author': u'Mickiewicz, Adam',
- 'url': u'http://wolnelektury.pl/katalog/lektura/ballady-i-romanse-rybka',
- 'created_at': u'2007-09-06',
- 'title': u'Rybka',
- 'kind': u'Liryka',
- 'source_url': u'http://www.polona.pl/Content/2222',
- 'released_to_public_domain_at': u'1855-01-01',
- 'epoch': u'Romantyzm',
- 'genre': u'Ballada',
- 'technical_editor': u'Sutkowska, Olga',
- 'license_description': u'Domena publiczna - Adam Mickiewicz zm. 1855',
- }),
- ('dcparser', 'sofokles_antygona.xml', {
- 'publisher': u'Fundacja Nowoczesna Polska',
- 'about': 'http://wiki.wolnepodreczniki.pl/Lektury:Sofokles/Antygona',
- 'source_name': u'Sofokles (496-406 a.C.), Antygona, Zakład Narodowy im. Ossolińskich, wyd. 7, Lwów, 1939',
- 'author': u'Sofokles',
- 'url': u'http://wolnelektury.pl/katalog/lektura/antygona',
- 'created_at': u'2007-08-30',
- 'title': u'Antygona',
- 'kind': u'Dramat',
- 'source_url': u'http://www.polona.pl/Content/3768',
- 'translator': u'Morawski, Kazimierz',
- 'released_to_public_domain_at': u'1925-01-01',
- 'epoch': u'Starożytność',
- 'genre': u'Tragedia',
- 'technical_editor': u'Gałecki, Dariusz',
- 'license_description': u'Domena publiczna - tłumacz Kazimierz Morawski zm. 1925',
- }),
- ('dcparser', 'biedrzycki_akslop.xml', {
- 'publisher': u'Fundacja Nowoczesna Polska',
- 'about': 'http://wiki.wolnepodreczniki.pl/Lektury:Biedrzycki/Akslop',
- 'source_name': u'Miłosz Biedrzycki, * ("Gwiazdka"), Fundacja "brulion", Kraków-Warszawa, 1993',
- 'author': u'Biedrzycki, Miłosz',
- 'url': u'http://wolnelektury.pl/katalog/lektura/akslop',
- 'created_at': u'2009-06-04',
- 'title': u'Akslop',
- 'kind': u'Liryka',
- 'source_url': u'http://free.art.pl/mlb/gwiazdka.html#t1',
- 'epoch': u'Współczesność',
- 'genre': u'Wiersz',
- 'technical_editor': u'Sutkowska, Olga',
- 'license': u'http://creativecommons.org/licenses/by-sa/3.0/',
- 'license_description': u'Creative Commons Uznanie Autorstwa - Na Tych Samych Warunkach 3.0.PL'
- }),
- )
-
- def test_parse(self):
- for dir_name, file_name, result in self.KNOWN_RESULTS:
- self.assertEqual(dcparser.parse(test_file_path(dir_name, file_name)).to_dict(), result)
-
-
-class TestParserErrors(unittest.TestCase):
- def test_error(self):
- try:
- html.transform(test_file_path('erroneous', 'asnyk_miedzy_nami.xml'),
- test_file_path('erroneous', 'asnyk_miedzy_nami.html'))
- self.fail()
- except etree.XMLSyntaxError, e:
- self.assertEqual(e.position, (25, 13))
-
-
-if __name__ == '__main__':
- unittest.main()
\ No newline at end of file
+++ /dev/null
-<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:dc="http://purl.org/dc/elements/1.1/">
- <rdf:Description rdf:about="http://wiki.wolnepodreczniki.pl/Lektury:Andersen/Brzydkie_kaczątko">
- <dc:creator xml:lang="pl">Andersen, Hans Christian</dc:creator>
- <dc:title xml:lang="pl">Brzydkie kaczątko</dc:title>
- <dc:contributor.translator xml:lang="pl">Niewiadomska, Cecylia</dc:contributor.translator>
- <dc:contributor.technical_editor xml:lang="pl">Gałecki, Dariusz</dc:contributor.technical_editor>
- <dc:publisher xml:lang="pl">Fundacja Nowoczesna Polska</dc:publisher>
- <dc:subject.period xml:lang="pl">Romantyzm</dc:subject.period>
- <dc:subject.type xml:lang="pl">Epika</dc:subject.type>
- <dc:subject.genre xml:lang="pl">Baśń</dc:subject.genre>
- <dc:description xml:lang="pl">Publikacja zrealizowana w ramach projektu Wolne Lektury (http://wolnelektury.pl). Reprodukcja cyfrowa wykonana przez Bibliotekę Narodową z egzemplarza pochodzącego ze zbiorów BN.</dc:description>
- <dc:identifier.url xml:lang="pl">http://wolnelektury.pl/katalog/lektura/brzydkie-kaczatko</dc:identifier.url>
- <dc:source.URL xml:lang="pl">http://www.polona.pl/dlibra/doccontent2?id=3563&dirids=4</dc:source.URL>
- <dc:source xml:lang="pl">Andersen, Hans Christian (1805-1875), Baśnie, Gebethner i Wolff, wyd. 7, Kraków, 1925</dc:source>
- <dc:rights xml:lang="pl">Domena publiczna - tłumacz Cecylia Niewiadomska zm. 1925</dc:rights>
- <dc:date.pd xml:lang="pl">1925</dc:date.pd>
- <dc:format xml:lang="pl">xml</dc:format>
- <dc:type xml:lang="pl">text</dc:type>
- <dc:type xml:lang="en">text</dc:type>
- <dc:date xml:lang="pl">2007-08-14</dc:date>
- <dc:audience xml:lang="pl">SP1</dc:audience>
- <dc:language xml:lang="pl">pol</dc:language>
- </rdf:Description>
-</rdf:RDF>
\ No newline at end of file
+++ /dev/null
-<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"
-xmlns:dc="http://purl.org/dc/elements/1.1/">
- <rdf:Description rdf:about="http://wiki.wolnepodreczniki.pl/Lektury:Biedrzycki/Akslop">
- <dc:creator xml:lang="pl">Biedrzycki, Miłosz</dc:creator>
- <dc:title xml:lang="pl">Akslop</dc:title>
- <dc:contributor.editor xml:lang="pl">Sekuła, Aleksandra</dc:contributor.editor>
- <dc:contributor.technical_editor xml:lang="pl">Sutkowska, Olga</dc:contributor.technical_editor>
- <dc:publisher xml:lang="pl">Fundacja Nowoczesna Polska</dc:publisher>
- <dc:subject.period xml:lang="pl">Współczesność</dc:subject.period>
- <dc:subject.type xml:lang="pl">Liryka</dc:subject.type>
- <dc:subject.genre xml:lang="pl">Wiersz</dc:subject.genre>
- <dc:description xml:lang="pl">Publikacja zrealizowana w ramach projektu Wolne Lektury (http://wolnelektury.pl).</dc:description>
- <dc:identifier.url xml:lang="pl">http://wolnelektury.pl/katalog/lektura/akslop</dc:identifier.url>
- <dc:source.URL xml:lang="pl">http://free.art.pl/mlb/gwiazdka.html#t1</dc:source.URL>
- <dc:source xml:lang="pl">Miłosz Biedrzycki, * ("Gwiazdka"), Fundacja "brulion", Kraków-Warszawa, 1993</dc:source>
- <dc:rights xml:lang="pl">Creative Commons Uznanie Autorstwa - Na Tych Samych Warunkach 3.0.PL</dc:rights>
- <dc:rights.license>http://creativecommons.org/licenses/by-sa/3.0/</dc:rights.license>
- <dc:format xml:lang="pl">xml</dc:format>
- <dc:type xml:lang="pl">text</dc:type>
- <dc:type xml:lang="en">text</dc:type>
- <dc:date xml:lang="pl">2009-06-04</dc:date>
- <dc:audience xml:lang="pl">L</dc:audience>
- <dc:language xml:lang="pl">pol</dc:language>
- </rdf:Description>
-</rdf:RDF>
\ No newline at end of file
+++ /dev/null
-<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:dc="http://purl.org/dc/elements/1.1/">
- <rdf:Description rdf:about="http://wiki.wolnepodreczniki.pl/Lektury:Kochanowski/Pieśni/Pieśń_VII_(1)">
- <dc:creator xml:lang="pl">Kochanowski, Jan</dc:creator>
- <dc:title xml:lang="pl">Pieśń VII (Trudna rada w tej mierze: przyjdzie się rozjechać...)</dc:title>
- <dc:relation.isPartOf xml:lang="pl">http://www.wolnelektury.pl/lektura/piesni-ksiegi-pierwsze</dc:relation.isPartOf>
- <dc:contributor.editor xml:lang="pl">Sekuła, Aleksandra</dc:contributor.editor>
- <dc:contributor.editor xml:lang="pl">Krzyżanowski, Julian</dc:contributor.editor>
- <dc:contributor.editor xml:lang="pl">Otwinowska, Barbara</dc:contributor.editor>
- <dc:contributor.technical_editor xml:lang="pl">Gałecki, Dariusz</dc:contributor.technical_editor>
- <dc:publisher xml:lang="pl">Fundacja Nowoczesna Polska</dc:publisher>
- <dc:subject.period xml:lang="pl">Renesans</dc:subject.period>
- <dc:subject.type xml:lang="pl">Liryka</dc:subject.type>
- <dc:subject.genre xml:lang="pl">Pieśń</dc:subject.genre>
- <dc:description xml:lang="pl">Publikacja zrealizowana w ramach projektu Wolne Lektury (http://wolnelektury.pl). Reprodukcja cyfrowa wykonana przez Bibliotekę Narodową z egzemplarza pochodzącego ze zbiorów BN.</dc:description>
- <dc:identifier.url xml:lang="pl">http://wolnelektury.pl/katalog/lektura/piesni-ksiegi-pierwsze-piesn-vii-trudna-rada-w-tej-mierze-pr</dc:identifier.url>
- <dc:source.URL xml:lang="pl">http://www.polona.pl/Content/1499</dc:source.URL>
- <dc:source xml:lang="pl">Kochanowski, Jan (1530-1584), Dzieła polskie, tom 1, oprac. Julian Krzyżanowski, wyd. 8, Państwowy Instytut Wydawniczy, Warszawa, 1976</dc:source>
- <dc:rights xml:lang="pl">Domena publiczna - Jan Kochanowski zm. 1584 </dc:rights>
- <dc:date.pd xml:lang="pl">1584</dc:date.pd>
- <dc:format xml:lang="pl">xml</dc:format>
- <dc:type xml:lang="pl">text</dc:type>
- <dc:type xml:lang="en">text</dc:type>
- <dc:date xml:lang="pl">2007-08-31</dc:date>
- <dc:audience xml:lang="pl">L</dc:audience>
- <dc:language xml:lang="pl">pol</dc:language>
- </rdf:Description>
-</rdf:RDF>
\ No newline at end of file
+++ /dev/null
-<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:dc="http://purl.org/dc/elements/1.1/">
- <rdf:Description rdf:about="http://wiki.wolnepodreczniki.pl/Lektury:Mickiewicz/Ballady/Rybka">
- <dc:creator xml:lang="pl">Mickiewicz, Adam</dc:creator>
- <dc:title xml:lang="pl">Rybka</dc:title>
- <dc:relation.isPartOf xml:lang="pl">http://www.wolnelektury.pl/lektura/ballady-i-romanse</dc:relation.isPartOf>
- <dc:contributor.editor xml:lang="pl">Sekuła, Aleksandra</dc:contributor.editor>
- <dc:contributor.editor xml:lang="pl">Kallenbach, Józef</dc:contributor.editor>
- <dc:contributor.technical_editor xml:lang="pl">Sutkowska, Olga</dc:contributor.technical_editor>
- <dc:publisher xml:lang="pl">Fundacja Nowoczesna Polska</dc:publisher>
- <dc:subject.period xml:lang="pl">Romantyzm</dc:subject.period>
- <dc:subject.type xml:lang="pl">Liryka</dc:subject.type>
- <dc:subject.genre xml:lang="pl">Ballada</dc:subject.genre>
- <dc:description xml:lang="pl">Publikacja zrealizowana w ramach projektu Wolne Lektury (http://wolnelektury.pl). Reprodukcja cyfrowa wykonana przez Bibliotekę Narodową z egzemplarza pochodzącego ze zbiorów BN.</dc:description>
- <dc:identifier.url xml:lang="pl">http://wolnelektury.pl/katalog/lektura/ballady-i-romanse-rybka</dc:identifier.url>
- <dc:source.URL xml:lang="pl">http://www.polona.pl/Content/2222</dc:source.URL>
- <dc:source xml:lang="pl">Mickiewicz, Adam (1798-1855), Poezje, tom 1 (Wiersze młodzieńcze - Ballady i romanse - Wiersze do r. 1824), Krakowska Spółdzielnia Wydawnicza, wyd. 2 zwiększone, Kraków, 1922</dc:source>
- <dc:rights xml:lang="pl">Domena publiczna - Adam Mickiewicz zm. 1855</dc:rights>
- <dc:date.pd xml:lang="pl">1855</dc:date.pd>
- <dc:format xml:lang="pl">xml</dc:format>
- <dc:type xml:lang="pl">text</dc:type>
- <dc:type xml:lang="en">text</dc:type>
- <dc:date xml:lang="pl">2007-09-06</dc:date>
- <dc:audience xml:lang="pl">SP2</dc:audience>
- <dc:audience xml:lang="pl">G</dc:audience>
- <dc:audience xml:lang="pl">L</dc:audience>
- <dc:language xml:lang="pl">pol</dc:language>
- </rdf:Description>
-</rdf:RDF>
\ No newline at end of file
+++ /dev/null
-<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:dc="http://purl.org/dc/elements/1.1/">
- <rdf:Description rdf:about="http://wiki.wolnepodreczniki.pl/Lektury:Sofokles/Antygona">
- <dc:creator xml:lang="pl">Sofokles</dc:creator>
- <dc:title xml:lang="pl">Antygona</dc:title>
- <dc:contributor.editor xml:lang="pl">Sekuła, Aleksandra</dc:contributor.editor>
- <dc:contributor.translator xml:lang="pl">Morawski, Kazimierz</dc:contributor.translator>
- <dc:contributor.technical_editor xml:lang="pl">Gałecki, Dariusz</dc:contributor.technical_editor>
- <dc:publisher xml:lang="pl">Fundacja Nowoczesna Polska</dc:publisher>
- <dc:subject.period xml:lang="pl">Starożytność</dc:subject.period>
- <dc:subject.type xml:lang="pl">Dramat</dc:subject.type>
- <dc:subject.genre xml:lang="pl">Tragedia</dc:subject.genre>
- <dc:description xml:lang="pl">Publikacja zrealizowana w ramach projektu Wolne Lektury (http://wolnelektury.pl). Reprodukcja cyfrowa wykonana przez Bibliotekę Narodową z egzemplarza pochodzącego ze zbiorów BN.</dc:description>
- <dc:identifier.url xml:lang="pl">http://wolnelektury.pl/katalog/lektura/antygona</dc:identifier.url>
- <dc:source.URL xml:lang="pl">http://www.polona.pl/Content/3768</dc:source.URL>
- <dc:source xml:lang="pl">Sofokles (496-406 a.C.), Antygona, Zakład Narodowy im. Ossolińskich, wyd. 7, Lwów, 1939</dc:source>
- <dc:rights xml:lang="pl">Domena publiczna - tłumacz Kazimierz Morawski zm. 1925</dc:rights>
- <dc:date.pd xml:lang="pl">1925</dc:date.pd>
- <dc:format xml:lang="pl">xml</dc:format>
- <dc:type xml:lang="pl">text</dc:type>
- <dc:type xml:lang="en">text</dc:type>
- <dc:date xml:lang="pl">2007-08-30</dc:date>
- <dc:audience xml:lang="pl">G</dc:audience>
- <dc:language xml:lang="pl">pol</dc:language>
- </rdf:Description>
-</rdf:RDF>
\ No newline at end of file
+++ /dev/null
-<div xmlns:wl="http://wolnelektury.pl/functions" id="book-text">
- <div id="toc">
- <h2>Spis treści</h2>
- <ol/>
- </div>
- <h1>
- <span class="author">Adam Asnyk</span>
- <span class="title">Między nami nic nie było</span>
- </h1>
- <div class="stanza">
- <p class="verse"><a name="f1" class="target"> </a><a href="#f1" class="anchor">1</a>Między nami nic nie było!</p>
- <p class="verse">
- Żadnych zwierzeń, wyznań żadnych!</p>
- <p class="verse">
- Nic nas z sobą nie łączyło —</p>
- <p class="verse">
- Prócz wiosennych marzeń zdradnych;</p>
- </div>
- <div class="stanza">
- <p class="verse"><a name="f5" class="target"> </a><a href="#f5" class="anchor">5</a>Prócz tych woni, barw i blasków,</p>
- <p class="verse">
- Unoszących się w przestrzeni;</p>
- <p class="verse">
- Prócz szumiących śpiewem lasków</p>
- <p class="verse">
- I tej świeżej łąk zieleni;</p>
- </div>
- <div class="stanza">
- <p class="verse">Prócz tych kaskad i potoków,</p>
- <p class="verse"><a name="f10" class="target"> </a><a href="#f10" class="anchor">10</a>
- Zraszających każdy parów,</p>
- <p class="verse">
- Prócz girlandy tęcz, obłoków,</p>
- <p class="verse">
- Prócz natury słodkich czarów;</p>
- </div>
- <div class="stanza">
- <p class="verse">Prócz tych wspólnych, jasnych zdrojów,</p>
- <p class="verse">
- Z których serce zachwyt piło;</p>
- <p class="verse"><a name="f15" class="target"> </a><a href="#f15" class="anchor">15</a>
- Prócz pierwiosnków i powojów,—</p>
- <p class="verse">
- Między nami nic nie było!</p>
- </div>
-</div>
+++ /dev/null
-<?xml version='1.0' encoding='utf-8'?>
-<utwor><liryka_lp>
- <autor_utworu>Adam Asnyk</autor_utworu>
- <nazwa_utworu>Między nami nic nie było</nazwa_utworu>
-
- <strofa>Między nami nic nie było!/
- Żadnych zwierzeń, wyznań żadnych!/
- Nic nas z sobą nie łączyło ---/
- Prócz wiosennych marzeń zdradnych;</strofa>
-
- <strofa>Prócz tych woni, barw i blasków,/
- Unoszących się w przestrzeni;/
- Prócz szumiących śpiewem lasków/
- I tej świeżej łąk zieleni;
-
- <strofa>Prócz tych kaskad i potoków,/
- Zraszających każdy parów,/
- Prócz girlandy tęcz, obłoków,/
- Prócz natury słodkich czarów;</strofa>
-
- <strofa>Prócz tych wspólnych, jasnych zdrojów,/
- Z których serce zachwyt piło;/
- Prócz pierwiosnków i powojów,---/
- Między nami nic nie było!</strofa>
-</liryka_lp></utwor>
+++ /dev/null
-# -*- coding: utf-8 -*-
-import os
-import cStringIO
-import re
-import codecs
-
-from lxml import etree
-
-from librarian import dcparser
-
-
-ENTITY_SUBSTITUTIONS = [
- (u'---', u'—'),
- (u'--', u'–'),
- (u'...', u'…'),
- (u',,', u'„'),
- (u'"', u'”'),
-]
-
-
-MAX_LINE_LENGTH = 80
-
-
-def substitute_entities(context, text):
- """XPath extension function converting all entites in passed text."""
- if isinstance(text, list):
- text = ''.join(text)
- for entity, substitutution in ENTITY_SUBSTITUTIONS:
- text = text.replace(entity, substitutution)
- return text
-
-
-def wrap_words(context, text):
- """XPath extension function automatically wrapping words in passed text"""
- if isinstance(text, list):
- text = ''.join(text)
- words = re.split(r'\s', text)
-
- line_length = 0
- lines = [[]]
- for word in words:
- line_length += len(word) + 1
- if line_length > MAX_LINE_LENGTH:
- # Max line length was exceeded. We create new line
- lines.append([])
- line_length = len(word)
- lines[-1].append(word)
- return '\n'.join(' '.join(line) for line in lines)
-
-
-# Register substitute_entities function with lxml
-ns = etree.FunctionNamespace('http://wolnelektury.pl/functions')
-ns['substitute_entities'] = substitute_entities
-ns['wrap_words'] = wrap_words
-
-
-def transform(input_filename, output_filename):
- """Transforms file input_filename in XML to output_filename in TXT."""
- # Parse XSLT
- style_filename = os.path.join(os.path.dirname(__file__), 'book2txt.xslt')
- style = etree.parse(style_filename)
-
- doc_file = cStringIO.StringIO()
- expr = re.compile(r'/\s', re.MULTILINE | re.UNICODE);
-
- f = open(input_filename, 'r')
- for line in f:
- line = line.decode('utf-8')
- line = expr.sub(u'<br/>\n', line)
- doc_file.write(line.encode('utf-8'))
- f.close()
-
- doc_file.seek(0)
-
- parser = etree.XMLParser(remove_blank_text=True)
- doc = etree.parse(doc_file, parser)
-
- result = doc.xslt(style)
- output_file = codecs.open(output_filename, 'wb', encoding='utf-8')
- output_file.write(unicode(result) % dcparser.parse(input_filename).url)
-
fnp / wolnelektury.git / commitdiff