fnp
/
librarian.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
epub: subtitle fix
[librarian.git]
/
librarian
/
pdf.py
diff --git
a/librarian/pdf.py
b/librarian/pdf.py
index
5debb68
..
baf7be4
100644
(file)
--- a/
librarian/pdf.py
+++ b/
librarian/pdf.py
@@
-21,7
+21,7
@@
from lxml.etree import XMLSyntaxError, XSLTApplyError
from librarian.dcparser import Person
from librarian.parser import WLDocument
from librarian.dcparser import Person
from librarian.parser import WLDocument
-from librarian import ParseError, DCNS
+from librarian import ParseError, DCNS
, get_resource
from librarian import functions
from librarian import functions
@@
-32,11
+32,11
@@
functions.reg_ends_white()
functions.reg_texcommand()
STYLESHEETS = {
functions.reg_texcommand()
STYLESHEETS = {
- 'wl2tex': '
xslt
/wl2tex.xslt',
+ 'wl2tex': '
pdf
/wl2tex.xslt',
}
}
-def insert_tags(doc, split_re, tagname):
+def insert_tags(doc, split_re, tagname
, exclude=None
):
""" inserts <tagname> for every occurence of `split_re' in text nodes in the `doc' tree
>>> t = etree.fromstring('<a><b>A-B-C</b>X-Y-Z</a>');
""" inserts <tagname> for every occurence of `split_re' in text nodes in the `doc' tree
>>> t = etree.fromstring('<a><b>A-B-C</b>X-Y-Z</a>');
@@
-46,6
+46,8
@@
def insert_tags(doc, split_re, tagname):
"""
for elem in doc.iter(tag=etree.Element):
"""
for elem in doc.iter(tag=etree.Element):
+ if exclude and elem.tag in exclude:
+ continue
if elem.text:
chunks = split_re.split(elem.text)
while len(chunks) > 1:
if elem.text:
chunks = split_re.split(elem.text)
while len(chunks) > 1:
@@
-67,13
+69,17
@@
def insert_tags(doc, split_re, tagname):
def substitute_hyphens(doc):
insert_tags(doc,
re.compile("(?<=[^-\s])-(?=[^-\s])"),
def substitute_hyphens(doc):
insert_tags(doc,
re.compile("(?<=[^-\s])-(?=[^-\s])"),
- "dywiz")
+ "dywiz",
+ exclude=[DCNS("identifier.url"), DCNS("rights.license")]
+ )
def fix_hanging(doc):
insert_tags(doc,
re.compile("(?<=\s\w)\s+"),
def fix_hanging(doc):
insert_tags(doc,
re.compile("(?<=\s\w)\s+"),
- "nbsp")
+ "nbsp",
+ exclude=[DCNS("identifier.url"), DCNS("rights.license")]
+ )
def move_motifs_inside(doc):
def move_motifs_inside(doc):
@@
-131,9
+137,6
@@
def parse_creator(doc):
creator.getparent().insert(0, creator_parsed)
creator.getparent().insert(0, creator_parsed)
-def get_resource(path):
- return os.path.join(os.path.dirname(__file__), path)
-
def get_stylesheet(name):
return get_resource(STYLESHEETS[name])
def get_stylesheet(name):
return get_resource(STYLESHEETS[name])
@@
-221,7
+224,7
@@
def transform(provider, slug=None, file_path=None,
# LaTeX -> PDF
shutil.copy(get_resource('pdf/wl.sty'), temp)
# LaTeX -> PDF
shutil.copy(get_resource('pdf/wl.sty'), temp)
- shutil.copy(get_resource('
pdf
/wl-logo.png'), temp)
+ shutil.copy(get_resource('
res
/wl-logo.png'), temp)
cwd = os.getcwd()
os.chdir(temp)
cwd = os.getcwd()
os.chdir(temp)
@@
-276,9
+279,11
@@
def load_including_children(provider, slug=None, uri=None, file_path=None):
else:
raise ValueError('Neither slug, URI nor file path provided for a book.')
else:
raise ValueError('Neither slug, URI nor file path provided for a book.')
- document = WLDocument.from_file(f, True,
- parse_dublincore=True,
- preserve_lines=False)
+ text = f.read().decode('utf-8')
+ text = re.sub(ur"([\u0400-\u04ff]+)", ur"<alien>\1</alien>", text)
+
+ document = WLDocument.from_string(text, True,
+ parse_dublincore=True)
f.close()
f.close()