Remove direct verse styling from html.

[librarian.git] / src / librarian / pdf.py

diff --git a/src/librarian/pdf.py b/src/librarian/pdf.py
index 31dfe1e..94d14cf 100644 (file)
--- a/src/librarian/pdf.py
+++ b/src/librarian/pdf.py
@@ -1,7 +1,5 @@
-# -*- coding: utf-8 -*-
-#

 # This file is part of Librarian, licensed under GNU Affero GPLv3 or later.
 # This file is part of Librarian, licensed under GNU Affero GPLv3 or later.

-# Copyright © Fundacja Nowoczesna Polska. See NOTICE for more information.
+# Copyright © Fundacja Wolne Lektury. See NOTICE for more information.

 #
 """PDF creation library.
 
 #
 """PDF creation library.
 


@@ -9,8 +7,7 @@ Creates one big XML from the book and its children, converts it to LaTeX
 with TeXML, then runs it by XeLaTeX.
 
 """
 with TeXML, then runs it by XeLaTeX.
 
 """

-from __future__ import print_function, unicode_literals
-
+import io

 import os
 import os.path
 import shutil
 import os
 import os.path
 import shutil


@@ -19,12 +16,13 @@ import re
 from copy import deepcopy
 from subprocess import call, PIPE
 from itertools import chain
 from copy import deepcopy
 from subprocess import call, PIPE
 from itertools import chain

+import urllib.parse
+import urllib.request

 
 from PIL import Image
 from Texml.processor import process
 from lxml import etree
 from lxml.etree import XMLSyntaxError, XSLTApplyError
 
 from PIL import Image
 from Texml.processor import process
 from lxml import etree
 from lxml.etree import XMLSyntaxError, XSLTApplyError

-import six

 
 from librarian.dcparser import Person
 from librarian.parser import WLDocument
 
 from librarian.dcparser import Person
 from librarian.parser import WLDocument


@@ -294,15 +292,15 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
 
         # add customizations
         if customizations is not None:
 
         # add customizations
         if customizations is not None:

-            root.set('customizations', u','.join(customizations))
+            root.set('customizations', ','.join(customizations))

 
         # add editors info
         editors = document.editors()
         if editors:
 
         # add editors info
         editors = document.editors()
         if editors:

-            root.set('editors', u', '.join(sorted(
+            root.set('editors', ', '.join(sorted(

                 editor.readable() for editor in editors)))
         if document.book_info.funders:
                 editor.readable() for editor in editors)))
         if document.book_info.funders:

-            root.set('funders', u', '.join(document.book_info.funders))
+            root.set('funders', ', '.join(document.book_info.funders))

         if document.book_info.thanks:
             root.set('thanks', document.book_info.thanks)
 
         if document.book_info.thanks:
             root.set('thanks', document.book_info.thanks)
 


@@ -325,11 +323,11 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
         temp = mkdtemp('-wl2pdf')
 
         for i, ilustr in enumerate(document.edoc.findall('//ilustr')):
         temp = mkdtemp('-wl2pdf')
 
         for i, ilustr in enumerate(document.edoc.findall('//ilustr')):

-            url = six.moves.urllib.parse.urljoin(
+            url = urllib.parse.urljoin(

                 base_url,
                 ilustr.get('src')
             )
                 base_url,
                 ilustr.get('src')
             )

-            imgfile = six.moves.urllib.request.urlopen(url)
+            imgfile = urllib.request.urlopen(url)

             img = Image.open(imgfile)
 
             th_format, ext, media_type = {
             img = Image.open(imgfile)
 
             th_format, ext, media_type = {


@@ -371,7 +369,7 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
 
         tex_path = os.path.join(temp, 'doc.tex')
         fout = open(tex_path, 'wb')
 
         tex_path = os.path.join(temp, 'doc.tex')
         fout = open(tex_path, 'wb')

-        process(six.BytesIO(texml), fout, 'utf-8')
+        process(io.BytesIO(texml), fout, 'utf-8')

         fout.close()
         del texml
 
         fout.close()
         del texml
 


@@ -425,7 +423,7 @@ def load_including_children(wldoc=None, provider=None, uri=None):
     """
 
     if uri and provider:
     """
 
     if uri and provider:

-        f = provider.by_uri(uri)
+        f = provider.by_slug(uri.slug)

         text = f.read().decode('utf-8')
         f.close()
     elif wldoc is not None:
         text = f.read().decode('utf-8')
         f.close()
     elif wldoc is not None:


@@ -436,7 +434,10 @@ def load_including_children(wldoc=None, provider=None, uri=None):
             'Neither a WLDocument, nor provider and URI were provided.'
         )
 
             'Neither a WLDocument, nor provider and URI were provided.'
         )
 

+    # Cyrrilic

     text = re.sub(r"([\u0400-\u04ff]+)", r"<alien>\1</alien>", text)
     text = re.sub(r"([\u0400-\u04ff]+)", r"<alien>\1</alien>", text)

+    # Geometric shapes.
+    text = re.sub(r"([\u25a0-\u25ff]+)", r"<alien>\1</alien>", text)

 
     document = WLDocument.from_bytes(text.encode('utf-8'),
                                      parse_dublincore=True, provider=provider)
 
     document = WLDocument.from_bytes(text.encode('utf-8'),
                                      parse_dublincore=True, provider=provider)