Add UAT file.

[librarian.git] / librarian / pdf.py

diff --git a/librarian/pdf.py b/librarian/pdf.py
index 20ab8bb..e6d897d 100644 (file)
--- a/librarian/pdf.py
+++ b/librarian/pdf.py
@@ -9,11 +9,11 @@ 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 with_statement
+from __future__ import print_function, unicode_literals
+

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

-from StringIO import StringIO

 from tempfile import mkdtemp, NamedTemporaryFile
 import re
 from copy import deepcopy
 from tempfile import mkdtemp, NamedTemporaryFile
 import re
 from copy import deepcopy


@@ -23,12 +23,13 @@ from itertools import chain
 from Texml.processor import process
 from lxml import etree
 from lxml.etree import XMLSyntaxError, XSLTApplyError
 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

-from librarian import ParseError, DCNS, get_resource, OutputFile
+from librarian import ParseError, DCNS, get_resource, OutputFile, RDFNS

 from librarian import functions
 from librarian import functions

-from librarian.cover import DefaultEbookCover
+from librarian.cover import make_cover

 from .sponsor import sponsor_logo
 
 
 from .sponsor import sponsor_logo
 
 


@@ -57,7 +58,7 @@ def insert_tags(doc, split_re, tagname, exclude=None):
 
     >>> t = etree.fromstring('<a><b>A-B-C</b>X-Y-Z</a>')
     >>> insert_tags(t, re.compile('-'), 'd')
 
     >>> t = etree.fromstring('<a><b>A-B-C</b>X-Y-Z</a>')
     >>> insert_tags(t, re.compile('-'), 'd')

-    >>> print etree.tostring(t)
+    >>> print(etree.tostring(t, encoding='unicode'))

     <a><b>A<d/>B<d/>C</b>X<d/>Y<d/>Z</a>
     """
 
     <a><b>A<d/>B<d/>C</b>X<d/>Y<d/>Z</a>
     """
 


@@ -86,7 +87,7 @@ 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"), "meta"]

                 )
 
 
                 )
 
 


@@ -110,6 +111,18 @@ def fix_tables(doc):
             table.set('_format', 'X' * len(table[0]))
 
 
             table.set('_format', 'X' * len(table[0]))
 
 

+def mark_subauthors(doc):
+    root_author = ', '.join(elem.text for elem in doc.findall('./' + RDFNS('RDF') + '//' + DCNS('creator_parsed')))
+    last_author = None
+    # jeśli autor jest inny niż autor całości i niż poprzedni autor
+    # to wstawiamy jakiś znacznik w rdf?
+    for subutwor in doc.xpath('/utwor/utwor'):
+        author = ', '.join(elem.text for elem in subutwor.findall('.//' + DCNS('creator_parsed')))
+        if author not in (last_author, root_author):
+            subutwor.find('.//' + RDFNS('RDF')).append(etree.Element('use_subauthor'))
+        last_author = author
+
+

 def move_motifs_inside(doc):
     """ moves motifs to be into block elements """
     for master in doc.xpath('//powiesc|//opowiadanie|//liryka_l|//liryka_lp|'
 def move_motifs_inside(doc):
     """ moves motifs to be into block elements """
     for master in doc.xpath('//powiesc|//opowiadanie|//liryka_l|//liryka_lp|'


@@ -184,11 +197,11 @@ def package_available(package, args='', verbose=False):
     tempdir = mkdtemp('-wl2pdf-test')
     fpath = os.path.join(tempdir, 'test.tex')
     f = open(fpath, 'w')
     tempdir = mkdtemp('-wl2pdf-test')
     fpath = os.path.join(tempdir, 'test.tex')
     f = open(fpath, 'w')

-    f.write(r"""
-        \documentclass{wl}
-        \usepackage[%s]{%s}
-        \begin{document}
-        \end{document}
+    f.write("""
+        \\documentclass{wl}
+        \\usepackage[%s]{%s}
+        \\begin{document}
+        \\end{document}

         """ % (args, package))
     f.close()
     if verbose:
         """ % (args, package))
     f.close()
     if verbose:


@@ -220,7 +233,7 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
 
         if cover:
             if cover is True:
 
         if cover:
             if cover is True:

-                cover = DefaultEbookCover
+                cover = make_cover

             bound_cover = cover(book_info, width=1200)
             root.set('data-cover-width', str(bound_cover.width))
             root.set('data-cover-height', str(bound_cover.height))
             bound_cover = cover(book_info, width=1200)
             root.set('data-cover-width', str(bound_cover.width))
             root.set('data-cover-height', str(bound_cover.height))


@@ -260,6 +273,7 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
         substitute_hyphens(document.edoc)
         fix_hanging(document.edoc)
         fix_tables(document.edoc)
         substitute_hyphens(document.edoc)
         fix_hanging(document.edoc)
         fix_tables(document.edoc)

+        mark_subauthors(document.edoc)

 
         # wl -> TeXML
         style_filename = get_stylesheet("wl2tex")
 
         # wl -> TeXML
         style_filename = get_stylesheet("wl2tex")


@@ -293,8 +307,8 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
         del document  # no longer needed large object :)
 
         tex_path = os.path.join(temp, 'doc.tex')
         del document  # no longer needed large object :)
 
         tex_path = os.path.join(temp, 'doc.tex')

-        fout = open(tex_path, 'w')
-        process(StringIO(texml), fout, 'utf-8')
+        fout = open(tex_path, 'wb')
+        process(six.BytesIO(texml), fout, 'utf-8')

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


@@ -315,8 +329,8 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
         os.chdir(temp)
 
         # some things work better when compiled twice
         os.chdir(temp)
 
         # some things work better when compiled twice

-        # but they are not enabled now (line numbers)
-        for run in xrange(1):
+        # (table of contents, [line numbers - disabled])
+        for run in range(2):

             if verbose:
                 p = call(['xelatex', tex_path])
             else:
             if verbose:
                 p = call(['xelatex', tex_path])
             else:


@@ -333,7 +347,7 @@ def transform(wldoc, verbose=False, save_tex=None, morefloats=None,
         shutil.rmtree(temp)
         return OutputFile.from_filename(output_file.name)
 
         shutil.rmtree(temp)
         return OutputFile.from_filename(output_file.name)
 

-    except (XMLSyntaxError, XSLTApplyError), e:
+    except (XMLSyntaxError, XSLTApplyError) as e:

         raise ParseError(e)
 
 
         raise ParseError(e)
 
 


@@ -348,14 +362,14 @@ def load_including_children(wldoc=None, provider=None, uri=None):
         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:

-        text = etree.tostring(wldoc.edoc, encoding=unicode)
+        text = etree.tostring(wldoc.edoc, encoding='unicode')

         provider = wldoc.provider
     else:
         raise ValueError('Neither a WLDocument, nor provider and URI were provided.')
 
         provider = wldoc.provider
     else:
         raise ValueError('Neither a WLDocument, nor provider and URI were provided.')
 

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

 
 

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