fnp
/
librarian.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
nowa -> 2017
[librarian.git]
/
librarian
/
html.py
diff --git
a/librarian/html.py
b/librarian/html.py
index
39e5a01
..
848935a
100644
(file)
--- a/
librarian/html.py
+++ b/
librarian/html.py
@@
-8,7
+8,7
@@
import cStringIO
import copy
from lxml import etree
import copy
from lxml import etree
-from librarian import XHTMLNS, ParseError,
Output
File
+from librarian import XHTMLNS, ParseError,
IO
File
from librarian import functions
from lxml.etree import XMLSyntaxError, XSLTApplyError
from librarian import functions
from lxml.etree import XMLSyntaxError, XSLTApplyError
@@
-22,12
+22,15
@@
STYLESHEETS = {
'partial': 'xslt/wl2html_partial.xslt'
}
'partial': 'xslt/wl2html_partial.xslt'
}
+
def get_stylesheet(name):
return os.path.join(os.path.dirname(__file__), STYLESHEETS[name])
def get_stylesheet(name):
return os.path.join(os.path.dirname(__file__), STYLESHEETS[name])
+
def html_has_content(text):
return etree.ETXPath('//p|//{%(ns)s}p|//h1|//{%(ns)s}h1' % {'ns': str(XHTMLNS)})(text)
def html_has_content(text):
return etree.ETXPath('//p|//{%(ns)s}p|//h1|//{%(ns)s}h1' % {'ns': str(XHTMLNS)})(text)
+
def transform(wldoc, stylesheet='legacy', options=None, flags=None):
"""Transforms the WL document to XHTML.
def transform(wldoc, stylesheet='legacy', options=None, flags=None):
"""Transforms the WL document to XHTML.
@@
-53,14
+56,14
@@
def transform(wldoc, stylesheet='legacy', options=None, flags=None):
if not options:
options = {}
result = document.transform(style, **options)
if not options:
options = {}
result = document.transform(style, **options)
- del document # no longer needed large object :)
+ del document
# no longer needed large object :)
if html_has_content(result):
add_anchors(result.getroot())
add_table_of_contents(result.getroot())
if html_has_content(result):
add_anchors(result.getroot())
add_table_of_contents(result.getroot())
- return
OutputFile.from_string(etree.tostring(result, method='html',
- xml_declaration=False, pretty_print=True, encoding='utf-8'))
+ return
IOFile.from_string(
+
etree.tostring(result, method='html',
xml_declaration=False, pretty_print=True, encoding='utf-8'))
else:
return None
except KeyError:
else:
return None
except KeyError:
@@
-68,6
+71,7
@@
def transform(wldoc, stylesheet='legacy', options=None, flags=None):
except (XMLSyntaxError, XSLTApplyError), e:
raise ParseError(e)
except (XMLSyntaxError, XSLTApplyError), e:
raise ParseError(e)
+
class Fragment(object):
def __init__(self, id, themes):
super(Fragment, self).__init__()
class Fragment(object):
def __init__(self, id, themes):
super(Fragment, self).__init__()
@@
-96,7
+100,8
@@
class Fragment(object):
result = []
for event, element in self.closed_events():
if event == 'start':
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())))
+ 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':
if element.text:
result.append(element.text)
elif event == 'end':
@@
-126,7
+131,8
@@
def extract_fragments(input_filename):
for event, element in etree.iterparse(buf, events=('start', 'end')):
# Process begin and end elements
if element.get('class', '') in ('theme-begin', 'theme-end'):
for event, element in etree.iterparse(buf, 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
+ if not event == 'end':
+ continue # Process elements only once, on end event
# Open new fragment
if element.get('class', '') == 'theme-begin':
# Open new fragment
if element.get('class', '') == 'theme-begin':
@@
-159,11
+165,11
@@
def extract_fragments(input_filename):
for fragment_id in open_fragments:
open_fragments[fragment_id].append('text', 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
# Process all elements except begin and end
else:
# Omit annotation tags
- if len(element.get('name', '')) or element.get('class', '') == 'annotation':
+ if (len(element.get('name', '')) or
+ element.get('class', '') in ('annotation', 'anchor')):
if event == 'end' and element.tail:
for fragment_id in open_fragments:
open_fragments[fragment_id].append('text', element.tail)
if event == 'end' and element.tail:
for fragment_id in open_fragments:
open_fragments[fragment_id].append('text', element.tail)
@@
-205,10
+211,13
@@
def any_ancestor(element, test):
def add_anchors(root):
counter = 1
def add_anchors(root):
counter = 1
+
+ def is_side_text(e):
+ side_classes = ('note', 'motto', 'motto_podpis', 'dedication')
+ return e.get('class') in side_classes or e.get('id') == 'nota_red' or e.tag == 'blockquote'
+
for element in root.iterdescendants():
for element in root.iterdescendants():
- if any_ancestor(element, lambda e: e.get('class') in ('note', 'motto', 'motto_podpis', 'dedication')
- or e.get('id') == 'nota_red'
- or e.tag == 'blockquote'):
+ if any_ancestor(element, is_side_text):
continue
if element.tag == 'p' and 'verse' in element.get('class', ''):
continue
if element.tag == 'p' and 'verse' in element.get('class', ''):
@@
-220,16
+229,27
@@
def add_anchors(root):
counter += 1
counter += 1
+def raw_printable_text(element):
+ working = copy.deepcopy(element)
+ for e in working.findall('a'):
+ if e.get('class') == 'annotation':
+ e.text = ''
+ return etree.tostring(working, method='text', encoding=unicode).strip()
+
+
def add_table_of_contents(root):
sections = []
counter = 1
def add_table_of_contents(root):
sections = []
counter = 1
+
+ def is_side_text(e):
+ return e.get('id') in ('footnotes', 'nota_red') or e.get('class') == 'person-list'
+
for element in root.iterdescendants():
if element.tag in ('h2', 'h3'):
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',)
):
+ if any_ancestor(element,
is_side_text
):
continue
continue
- element_text = etree.tostring(element, method='text',
- encoding=unicode).strip()
+ element_text = raw_printable_text(element)
if element.tag == 'h3' and len(sections) and sections[-1][1] == 'h2':
sections[-1][3].append((counter, element.tag, element_text, []))
else:
if element.tag == 'h3' and len(sections) and sections[-1][1] == 'h2':
sections[-1][3].append((counter, element.tag, element_text, []))
else:
@@
-249,9
+269,9
@@
def add_table_of_contents(root):
if len(subsections):
subsection_list = etree.SubElement(section_element, 'ol')
if len(subsections):
subsection_list = etree.SubElement(section_element, 'ol')
- for n
, subsection, text
, _ in subsections:
+ for n
1, subsection, text1
, _ in subsections:
subsection_element = etree.SubElement(subsection_list, 'li')
subsection_element = etree.SubElement(subsection_list, 'li')
- add_anchor(subsection_element, "s%d" % n
, with_target=False, link_text=text
)
+ add_anchor(subsection_element, "s%d" % n
1, with_target=False, link_text=text1
)
root.insert(0, toc)
root.insert(0, toc)
@@
-268,4
+288,3
@@
def extract_annotations(html_path):
text_str = etree.tostring(footnote, method='text', encoding='utf-8').strip()
html_str = etree.tostring(footnote, method='html', encoding='utf-8')
yield anchor, text_str, html_str
text_str = etree.tostring(footnote, method='text', encoding='utf-8').strip()
html_str = etree.tostring(footnote, method='html', encoding='utf-8')
yield anchor, text_str, html_str
-