fnp
/
librarian.git
/ blobdiff
commit
grep
author
committer
pickaxe
?
search:
re
summary
|
shortlog
|
log
|
commit
|
commitdiff
|
tree
raw
|
inline
| side by side
almost done, kerning todo
[librarian.git]
/
librarian
/
pdf.py
diff --git
a/librarian/pdf.py
b/librarian/pdf.py
index
7bba9d2
..
eb3f942
100644
(file)
--- a/
librarian/pdf.py
+++ b/
librarian/pdf.py
@@
-3,10
+3,17
@@
# This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
#
# This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
#
+"""PDF creation library.
+
+Creates one big XML from the book and its children, converts it to LaTeX
+with TeXML, then runs it by XeLaTeX.
+
+"""
from __future__ import with_statement
import os
import os.path
import shutil
from __future__ import with_statement
import os
import os.path
import shutil
+from distutils.dir_util import copy_tree # shutil.copytree is so uncapable.
from StringIO import StringIO
from tempfile import mkdtemp, NamedTemporaryFile
import re
from StringIO import StringIO
from tempfile import mkdtemp, NamedTemporaryFile
import re
@@
-77,7
+84,7
@@
def substitute_hyphens(doc):
insert_tags(doc,
re.compile("(?<=[^-\s])-(?=[^-\s])"),
"dywiz",
insert_tags(doc,
re.compile("(?<=[^-\s])-(?=[^-\s])"),
"dywiz",
- exclude=[DCNS("identifier.url"), DCNS("rights.license")]
+ exclude=[DCNS("identifier.url"), DCNS("rights.license")
, "www"
]
)
)
@@
-135,9
+142,13
@@
def hack_motifs(doc):
def parse_creator(doc):
def parse_creator(doc):
- """ find all dc:creator and dc.contributor tags and add *_parsed versions with forenames first """
+ """Generates readable versions of creator and translator tags.
+
+ Finds all dc:creator and dc.contributor.translator tags
+ and adds *_parsed versions with forenames first.
+ """
for person in doc.xpath("|".join('//dc:'+(tag) for tag in (
for person in doc.xpath("|".join('//dc:'+(tag) for tag in (
- 'creator', 'contributor.translator'
, 'contributor.editor', 'contributor.technical_editor'
)),
+ 'creator', 'contributor.translator')),
namespaces = {'dc': str(DCNS)})[::-1]:
if not person.text:
continue
namespaces = {'dc': str(DCNS)})[::-1]:
if not person.text:
continue
@@
-173,47
+184,59
@@
def package_available(package, args='', verbose=False):
return p == 0
return p == 0
-def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
- cover=None, flags=None, customizations=None):
+def transform(wldoc, verbose=False, save_tex=None,
save_texml=None,
morefloats=None,
+ cover=None, flags=None, customizations=None
, documentclass='wl', resources=None
):
""" produces a PDF file with XeLaTeX
wldoc: a WLDocument
verbose: prints all output from LaTeX
save_tex: path to save the intermediary LaTeX file to
""" produces a PDF file with XeLaTeX
wldoc: a WLDocument
verbose: prints all output from LaTeX
save_tex: path to save the intermediary LaTeX file to
+ save_texml: path to save the intermediary TeXML file to
morefloats (old/new/none): force specific morefloats
cover: a cover.Cover factory or True for default
flags: less-advertising,
customizations: user requested customizations regarding various formatting parameters (passed to wl LaTeX class)
morefloats (old/new/none): force specific morefloats
cover: a cover.Cover factory or True for default
flags: less-advertising,
customizations: user requested customizations regarding various formatting parameters (passed to wl LaTeX class)
+ documentclass: LaTeX document class, defaults to wl
+ resources: a directory with resources, copied to place where LaTeX compilation is made
"""
# Parse XSLT
try:
"""
# Parse XSLT
try:
+ book_info = wldoc.book_info
document = load_including_children(wldoc)
document = load_including_children(wldoc)
+ root = document.edoc.getroot()
if cover:
if cover is True:
cover = WLCover
if cover:
if cover is True:
cover = WLCover
- bound_cover = cover(
document.
book_info)
-
document.edoc.getroot()
.set('data-cover-width', str(bound_cover.width))
-
document.edoc.getroot()
.set('data-cover-height', str(bound_cover.height))
+ bound_cover = cover(book_info)
+
root
.set('data-cover-width', str(bound_cover.width))
+
root
.set('data-cover-height', str(bound_cover.height))
if bound_cover.uses_dc_cover:
if bound_cover.uses_dc_cover:
- if document.book_info.cover_by:
- document.edoc.getroot().set('data-cover-by', document.book_info.cover_by)
- if document.book_info.cover_source:
- document.edoc.getroot().set('data-cover-source', document.book_info.cover_source)
+ if book_info.cover_by:
+ root.set('data-cover-by', book_info.cover_by)
+ if book_info.cover_source:
+ root.set('data-cover-source',
+ book_info.cover_source)
if flags:
for flag in flags:
if flags:
for flag in flags:
-
document.edoc.getroot()
.set('flag-' + flag, 'yes')
+
root
.set('flag-' + flag, 'yes')
# check for LaTeX packages
if morefloats:
# check for LaTeX packages
if morefloats:
-
document.edoc.getroot()
.set('morefloats', morefloats.lower())
+
root
.set('morefloats', morefloats.lower())
elif package_available('morefloats', 'maxfloats=19'):
elif package_available('morefloats', 'maxfloats=19'):
-
document.edoc.getroot()
.set('morefloats', 'new')
+
root
.set('morefloats', 'new')
# add customizations
if customizations is not None:
# add customizations
if customizations is not None:
- document.edoc.getroot().set('customizations', u','.join(customizations))
+ root.set('customizations', u','.join(customizations))
+
+ root.set('documentclass', documentclass or 'wl')
+
+ # add editors info
+ root.set('editors', u', '.join(sorted(
+ editor.readable() for editor in document.editors())))
# hack the tree
move_motifs_inside(document.edoc)
# hack the tree
move_motifs_inside(document.edoc)
@@
-228,6
+251,9
@@
def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
texml = document.transform(style)
texml = document.transform(style)
+ if save_texml:
+ texml.write(save_texml)
+
# TeXML -> LaTeX
temp = mkdtemp('-wl2pdf')
# TeXML -> LaTeX
temp = mkdtemp('-wl2pdf')
@@
-248,9
+274,16
@@
def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
# LaTeX -> PDF
shutil.copy(get_resource('pdf/wl.cls'), temp)
# LaTeX -> PDF
shutil.copy(get_resource('pdf/wl.cls'), temp)
+ shutil.copy(get_resource('pdf/wlpub.cls'), temp)
shutil.copy(get_resource('res/wl-logo.png'), temp)
shutil.copy(get_resource('res/wl-logo.png'), temp)
-
- cwd = os.getcwd()
+ shutil.copy(get_resource('res/cover.jpg'), temp)
+ if resources:
+ copy_tree(resources, temp)
+
+ try:
+ cwd = os.getcwd()
+ except OSError:
+ cwd = None
os.chdir(temp)
if verbose:
os.chdir(temp)
if verbose:
@@
-260,7
+293,8
@@
def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
if p:
raise ParseError("Error parsing .tex file")
if p:
raise ParseError("Error parsing .tex file")
- os.chdir(cwd)
+ if cwd is not None:
+ os.chdir(cwd)
output_file = NamedTemporaryFile(prefix='librarian', suffix='.pdf', delete=False)
pdf_path = os.path.join(temp, 'doc.pdf')
output_file = NamedTemporaryFile(prefix='librarian', suffix='.pdf', delete=False)
pdf_path = os.path.join(temp, 'doc.pdf')
@@
-290,7
+324,8
@@
def load_including_children(wldoc=None, provider=None, uri=None):
text = re.sub(ur"([\u0400-\u04ff]+)", ur"<alien>\1</alien>", text)
text = re.sub(ur"([\u0400-\u04ff]+)", ur"<alien>\1</alien>", text)
- document = WLDocument.from_string(text, parse_dublincore=True)
+ document = WLDocument.from_string(text,
+ parse_dublincore=True, provider=provider)
document.swap_endlines()
for child_uri in document.book_info.parts:
document.swap_endlines()
for child_uri in document.book_info.parts: