accept missing dc tags

[librarian.git] / librarian / pdf.py

diff --git a/librarian/pdf.py b/librarian/pdf.py
index 10afdf3..c02e98c 100644 (file)
--- a/librarian/pdf.py
+++ b/librarian/pdf.py
@@ -21,7 +21,6 @@ from subprocess import call, PIPE
 
 from Texml.processor import process
 from lxml import etree
 
 from Texml.processor import process
 from lxml import etree

-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


@@ -39,11 +38,12 @@ STYLESHEETS = {
     'wl2tex': 'pdf/wl2tex.xslt',
 }
 
     'wl2tex': 'pdf/wl2tex.xslt',
 }
 

+

 def insert_tags(doc, split_re, tagname, exclude=None):
     """ inserts <tagname> for every occurence of `split_re' in text nodes in the `doc' tree
 
 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>');
-    >>> 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)
     <a><b>A<d/>B<d/>C</b>X<d/>Y<d/>Z</a>
     """
     >>> print etree.tostring(t)
     <a><b>A<d/>B<d/>C</b>X<d/>Y<d/>Z</a>
     """


@@ -81,16 +81,20 @@ def fix_hanging(doc):
     insert_tags(doc,
                 re.compile("(?<=\s\w)\s+"),
                 "nbsp",
     insert_tags(doc,
                 re.compile("(?<=\s\w)\s+"),
                 "nbsp",

-                exclude=[DCNS("identifier.url"), DCNS("rights.license")]
+                exclude=[DCNS("identifier.url"), DCNS("rights.license"), DCNS("title"), DCNS("description")]

                 )
 
 
 def move_motifs_inside(doc):
     """ moves motifs to be into block elements """
                 )
 
 
 def move_motifs_inside(doc):
     """ moves motifs to be into block elements """

-    for master in doc.xpath('//powiesc|//opowiadanie|//liryka_l|//liryka_lp|//dramat_wierszowany_l|//dramat_wierszowany_lp|//dramat_wspolczesny'):
+    main_tags = ('powiesc', 'opowiadanie', 'liryka_l', 'liryka_lp',
+                 'dramat_wierszowany_l', 'dramat_wierszowany_lp', 'dramat_wspolczesny')
+    for master in doc.xpath('|'.join('//' + tag for tag in main_tags)):

         for motif in master.xpath('motyw'):
             for sib in motif.itersiblings():
         for motif in master.xpath('motyw'):
             for sib in motif.itersiblings():

-                if sib.tag not in ('sekcja_swiatlo', 'sekcja_asterysk', 'separator_linia', 'begin', 'end', 'motyw', 'extra', 'uwaga'):
+                special_tags = ('sekcja_swiatlo', 'sekcja_asterysk', 'separator_linia',
+                                'begin', 'end', 'motyw', 'extra', 'uwaga')
+                if sib.tag not in special_tags:

                     # motif shouldn't have a tail - it would be untagged text
                     motif.tail = None
                     motif.getparent().remove(motif)
                     # motif shouldn't have a tail - it would be untagged text
                     motif.tail = None
                     motif.getparent().remove(motif)


@@ -136,9 +140,10 @@ def parse_creator(doc):
     Finds all dc:creator and dc.contributor.translator tags
     and adds *_parsed versions with forenames first.
     """
     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 (
-                    'creator', 'contributor.translator')),
-                    namespaces = {'dc': str(DCNS)})[::-1]:
+    persons = doc.xpath(
+        "|".join('//dc:' + tag for tag in ('creator', 'contributor.translator')),
+        namespaces={'dc': str(DCNS)})[::-1]
+    for person in persons:

         if not person.text:
             continue
         p = Person.from_text(person.text)
         if not person.text:
             continue
         p = Person.from_text(person.text)


@@ -173,6 +178,7 @@ def package_available(package, args='', verbose=False):
     return p == 0
 
 
     return p == 0
 
 

+# not used

 def load_including_children(wldoc=None, provider=None, uri=None):
     """ Makes one big xml file with children inserted at end.
 
 def load_including_children(wldoc=None, provider=None, uri=None):
     """ Makes one big xml file with children inserted at end.
 


@@ -181,6 +187,7 @@ def load_including_children(wldoc=None, provider=None, uri=None):
 
     if uri and provider:
         f = provider.by_uri(uri)
 
     if uri and provider:
         f = provider.by_uri(uri)

+        # WTF DocProvider.by_uri() returns IOFile, so no .read() there

         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:


@@ -191,8 +198,7 @@ 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, provider=provider)
+    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:


@@ -229,29 +235,8 @@ class PDFFormat(Format):
         """ For use in XSLT. """
         return u','.join(k for k, v in self.customization.items() if v)
 
         """ For use in XSLT. """
         return u','.join(k for k, v in self.customization.items() if v)
 

-    def get_document(self):
-        document = load_including_children(self.wldoc)
-        root = document.edoc.getroot()
-        root.set('editors', u', '.join(sorted(
-            editor.readable() for editor in document.editors())))
-
-        # hack the tree
-        move_motifs_inside(document.edoc)
-        hack_motifs(document.edoc)
-        parse_creator(document.edoc)
-        substitute_hyphens(document.edoc)
-        fix_hanging(document.edoc)
-        return document
-

     def get_texml(self):
     def get_texml(self):

-        style_filename = get_stylesheet("wl2tex")
-        functions.reg_get(self)
-        try:
-            style = etree.parse(style_filename)
-            texml = self.get_document().transform(style)
-            return texml
-        except (XMLSyntaxError, XSLTApplyError), e:
-            raise ParseError(e)
+        raise NotImplementedError

 
     def get_tex_dir(self):
         texml = self.get_texml()
 
     def get_tex_dir(self):
         texml = self.get_texml()


@@ -265,8 +250,8 @@ class PDFFormat(Format):
         # Copy style
         shutil.copy(get_resource('pdf/wl.cls'), temp)
         shutil.copy(self.style, os.path.join(temp, 'style.sty'))
         # Copy style
         shutil.copy(get_resource('pdf/wl.cls'), temp)
         shutil.copy(self.style, os.path.join(temp, 'style.sty'))

-        for sfile in ['wasysym.sty', 'uwasyvar.fd', 'uwasy.fd']:
-            shutil.copy(get_resource(os.path.join('styles/wasysym', sfile)), temp)
+        # for sfile in ['wasysym.sty', 'uwasyvar.fd', 'uwasy.fd']:
+        #     shutil.copy(get_resource(os.path.join('res/wasysym', sfile)), temp)

 
         # Save attachments
         if self.cover:
 
         # Save attachments
         if self.cover:


@@ -282,15 +267,15 @@ class PDFFormat(Format):
             cwd = None
         os.chdir(temp)
 
             cwd = None
         os.chdir(temp)
 

+        p = None

         if self.verbose:
         if self.verbose:

-            for i in range(self.tex_passes):
+            for i in xrange(self.tex_passes):

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

-            for i in range(self.tex_passes):
-                p = call(['xelatex', '-interaction=batchmode', tex_path],
-                            stdout=PIPE, stderr=PIPE)
+            for i in xrange(self.tex_passes):
+                p = call(['xelatex', '-interaction=batchmode', tex_path], stdout=PIPE, stderr=PIPE)

         if p:
         if p:

-            raise ParseError("Error parsing .tex file")
+            raise ParseError("Error parsing .tex file: %s" % tex_path)

 
         if cwd is not None:
             os.chdir(cwd)
 
         if cwd is not None:
             os.chdir(cwd)