updated from Docutils

docutils/parsers/rst/directives/__init__.py

@@ -122,29 +122,37 @@ _directives = {}
 def directive(directive_name, language_module, document):
     """
     Locate and return a directive function from its language-dependent name.
-    If not found in the current language, check English.
+    If not found in the current language, check English.  Return None if the
+    named directive cannot be found.
     """
     normname = directive_name.lower()
     messages = []
+    msg_text = []
     if _directives.has_key(normname):
         return _directives[normname], messages
+    canonicalname = None
     try:
         canonicalname = language_module.directives[normname]
-    except (KeyError, AttributeError):
+    except AttributeError, error:
-        msg_text = ('No directive entry for "%s" in module "%s".'
+        msg_text.append('Problem retrieving directive entry from language '
+                        'module %r: %s.' % (language_module, error))
+    except KeyError:
+        msg_text.append('No directive entry for "%s" in module "%s".'
                         % (directive_name, language_module.__name__))
+    if not canonicalname:
         try:
             canonicalname = _fallback_language_module.directives[normname]
-            msg_text += ('\nUsing English fallback for directive "%s".'
+            msg_text.append('Using English fallback for directive "%s".'
                             % directive_name)
         except KeyError:
-            msg_text += ('\nTrying "%s" as canonical directive name.'
+            msg_text.append('Trying "%s" as canonical directive name.'
                             % directive_name)
             # The canonical name should be an English name, but just in case:
             canonicalname = normname
-        warning = document.reporter.warning(
+    if msg_text:
-            msg_text, line=document.current_line)
+        message = document.reporter.info(
-        messages.append(warning)
+            '\n'.join(msg_text), line=document.current_line)
+        messages.append(message)
     try:
         modulename, functionname = _directive_registry[canonicalname]
     except KeyError:

docutils/parsers/rst/languages/__init__.py

@@ -16,6 +16,9 @@ _languages = {}
 def get_language(language_code):
     if _languages.has_key(language_code):
         return _languages[language_code]
+    try:
         module = __import__(language_code, globals(), locals())
+    except ImportError:
+        return None
     _languages[language_code] = module
     return module

docutils/parsers/rst/languages/sk.py

@@ -0,0 +1,46 @@
+# Author: Miroslav Vasko
+# Contact: zemiak@zoznam.sk
+# Revision: $Revision$
+# Date: $Date$
+# Copyright: This module has been placed in the public domain.
+
+"""
+Slovak-language mappings for language-dependent features of
+reStructuredText.
+"""
+
+__docformat__ = 'reStructuredText'
+
+
+directives = {
+      u'pozor': 'attention',
+      u'opatrne': 'caution',
+      u'nebezpe\xe8enstvo': 'danger',
+      u'chyba': 'error',
+      u'rada': 'hint',
+      u'd\xf4le\x9eit\xe9': 'important',
+      u'pozn\xe1mka': 'note',
+      u'tip': 'tip',
+      u'varovanie': 'warning',
+      u't\xe9ma': 'topic',
+      u'blok-riadkov': 'line-block',
+      u'parsed-literal': 'parsed-literal',
+      #u'questions': 'questions',
+      #u'qa': 'questions',
+      #u'faq': 'questions',
+      u'meta': 'meta',
+      #u'imagemap': 'imagemap',
+      u'obr\xe1zok': 'image',
+      u'tvar': 'figure',
+      u'vlo\x9ei\x9d': 'include',
+      u'raw': 'raw',
+      u'nahradi\x9d': 'replace',
+      u'obsah': 'contents',
+      u'\xe8as\x9d': 'sectnum',
+      u'\xe8as\x9d-\xe8\xedslovanie': 'sectnum',
+      u'cie\xbeov\xe9-pozn\xe1mky': 'target-notes',
+      #u'footnotes': 'footnotes',
+      #u'citations': 'citations',
+      }
+"""Slovak name to registered (in directives/__init__.py) directive name
+mapping."""

docutils/parsers/rst/languages/sv.py

@@ -21,19 +21,18 @@ directives = {
       u'notera': 'note',
       u'tips': 'tip',
       u'varning': 'warning',
-      u'fr\u00e5gor': 'questions',
+      # u'fr\u00e5gor': 'questions',
       # NOTE: A bit long, but recommended by http://www.nada.kth.se/dataterm/:
-      u'fr\u00e5gor-och-svar': 'questions',
+      # u'fr\u00e5gor-och-svar': 'questions',
-      u'vanliga-fr\u00e5gor': 'questions',  
+      # u'vanliga-fr\u00e5gor': 'questions',  
       u'meta': 'meta',
       # u'bildkarta': 'imagemap',   # FIXME: Translation might be too literal.
       u'bild': 'image',
       u'figur': 'figure',
-      # u'r\u00e5': 'raw',          # FIXME: Translation might be too literal.
+      u'r\u00e5': 'raw',            # FIXME: Translation might be too literal.
       u'inneh\u00e5ll': 'contents',
       # u'fotnoter': 'footnotes',
       # u'citeringar': 'citations',
-      # u'\u00e4mne': 'topic',
+      u'\u00e4mne': 'topic'}
-      u'restructuredtext-test-directive': 'restructuredtext-test-directive' }
 """Swedish name to registered (in directives/__init__.py) directive name
 mapping."""

docutils/parsers/rst/states.py

@@ -534,9 +534,17 @@ class Inliner:
     non_whitespace_after = r'(?![ \n])'
     # Alphanumerics with isolated internal [-._] chars (i.e. not 2 together):
     simplename = r'(?:(?!_)\w)+(?:[-._](?:(?!_)\w)+)*'
+    # Valid URI characters (see RFC 2396 & RFC 2732):
     uric = r"""[-_.!~*'()[\];/:@&=+$,%a-zA-Z0-9]"""
-    urilast = r"""[_~/\]a-zA-Z0-9]"""   # no punctuation
+    # Last URI character; same as uric but no punctuation:
+    urilast = r"""[_~/a-zA-Z0-9]"""
     emailc = r"""[-_!~*'{|}/#?^`&=+$%a-zA-Z0-9]"""
+    email_pattern = r"""
+          %(emailc)s+(?:\.%(emailc)s+)*   # name
+          @                               # at
+          %(emailc)s+(?:\.%(emailc)s*)*   # host
+          %(urilast)s                     # final URI char
+          """
     parts = ('initial_inline', start_string_prefix, '',
              [('start', '', non_whitespace_after,  # simple start-strings
                [r'\*\*',                # strong
@@ -581,6 +589,18 @@ class Inliner:
               )
               %(end_string_suffix)s
               """ % locals(), re.VERBOSE | re.UNICODE),
+          embedded_uri=re.compile(
+              r"""
+              (
+                [ \n]+                  # spaces or beginning of line
+                <                       # open bracket
+                %(non_whitespace_after)s
+                ([^<>\0]+)              # anything but angle brackets & nulls
+                %(non_whitespace_before)s
+                >                       # close bracket w/o whitespace before
+              )
+              $                         # end of string
+              """ % locals(), re.VERBOSE),
           literal=re.compile(non_whitespace_before + '(``)'
                              + end_string_suffix),
           target=re.compile(non_whitespace_escape_before
@@ -588,8 +608,9 @@ class Inliner:
           substitution_ref=re.compile(non_whitespace_escape_before
                                       + r'(\|_{0,2})'
                                       + end_string_suffix),
+          email=re.compile(email_pattern % locals() + '$', re.VERBOSE),
           uri=re.compile(
-                r"""
+                (r"""
                 %(start_string_prefix)s
                 (?P<whole>
                   (?P<absolute>           # absolute URI
@@ -615,14 +636,11 @@ class Inliner:
                   )
                 |                       # *OR*
                   (?P<email>              # email address
-                    %(emailc)s+(\.%(emailc)s+)*  # name
+                    """ + email_pattern + r"""
-                    @                            # at
-                    %(emailc)s+(\.%(emailc)s*)*  # host
-                    %(urilast)s                  # final URI char
                   )
                 )
                 %(end_string_suffix)s
-                """ % locals(), re.VERBOSE),
+                """) % locals(), re.VERBOSE),
           pep=re.compile(
                 r"""
                 %(start_string_prefix)s
@@ -736,7 +754,7 @@ class Inliner:
                     prb = self.problematic(text, text, msg)
                     return string[:rolestart], [prb], string[textend:], [msg]
                 return self.phrase_ref(string[:matchstart], string[textend:],
-                                       rawsource, text)
+                                       rawsource, escaped, text)
             else:
                 return self.interpreted(string[:rolestart], string[textend:],
                                         rawsource, text, role, position)
@@ -747,16 +765,46 @@ class Inliner:
         prb = self.problematic(text, text, msg)
         return string[:matchstart], [prb], string[matchend:], [msg]
 
-    def phrase_ref(self, before, after, rawsource, text):
+    def phrase_ref(self, before, after, rawsource, escaped, text):
+        match = self.patterns.embedded_uri.search(escaped)
+        if match:
+            text = unescape(escaped[:match.start(0)])
+            uri_text = match.group(2)
+            uri = ''.join(uri_text.split())
+            uri = self.adjust_uri(uri)
+            if uri:
+                target = nodes.target(match.group(1), refuri=uri)
+            else:
+                raise ApplicationError('problem with URI: %r' % uri_text)
+        else:
+            target = None
         refname = normalize_name(text)
         reference = nodes.reference(rawsource, text)
+        node_list = [reference]
         if rawsource[-2:] == '__':
+            if target:
+                reference['refuri'] = uri
+            else:
                 reference['anonymous'] = 1
                 self.document.note_anonymous_ref(reference)
+        else:
+            if target:
+                reference['refuri'] = uri
+                target['name'] = refname
+                self.document.note_external_target(target)
+                self.document.note_explicit_target(target, self.parent)
+                node_list.append(target)
             else:
                 reference['refname'] = refname
                 self.document.note_refname(reference)
-        return before, [reference], after, []
+        return before, node_list, after, []
+
+    def adjust_uri(self, uri):
+        match = self.patterns.email.match(uri)
+        if match:
+            return 'mailto:' + uri
+        else:
+            return uri
 
     def interpreted(self, before, after, rawsource, text, role, position):
         if role:
@@ -1639,8 +1687,12 @@ class Body(RSTState):
             name = normalize_name(unescape(targetname))
             target['name'] = name
             if refuri:
-                target['refuri'] = refuri
+                uri = self.inliner.adjust_uri(refuri)
+                if uri:
+                    target['refuri'] = uri
                     self.document.note_external_target(target)
+                else:
+                    raise ApplicationError('problem with URI: %r' % refuri)
             else:
                 self.document.note_internal_target(target)
             self.document.note_explicit_target(target, self.parent)

docutils/transforms/peps.py

@@ -170,6 +170,7 @@ class TargetNotes(Transform):
         if not refsect:
             refsect = nodes.section()
             refsect += nodes.title('', 'References')
+            doc.set_id(refsect)
             if copyright:
                 # Put the new "References" section before "Copyright":
                 doc.insert(copyright, refsect)

docutils/writers/html4css1.py

@@ -134,12 +134,13 @@ class HTMLTranslator(nodes.NodeVisitor):
     option) disables list whitespace optimization.
     """
 
-    xml_declaration = '<?xml version="1.0" encoding="%s"?>\n'
+    xml_declaration = '<?xml version="1.0" encoding="%s" ?>\n'
     doctype = ('<!DOCTYPE html' 
                ' PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"'
                ' "http://www.w3.org/TR/xhtml1/DTD/'
                'xhtml1-transitional.dtd">\n')
-    html_head = '<html lang="%s">\n<head>\n'
+    html_head = ('<html xmlns="http://www.w3.org/1999/xhtml" xml:lang="%s" '
+                 'lang="%s">\n<head>\n')
     content_type = ('<meta http-equiv="Content-Type" content="text/html; '
                     'charset=%s" />\n')
     generator = ('<meta name="generator" content="Docutils %s: '
@@ -153,11 +154,12 @@ class HTMLTranslator(nodes.NodeVisitor):
     def __init__(self, document):
         nodes.NodeVisitor.__init__(self, document)
         self.settings = settings = document.settings
-        self.language = languages.get_language(settings.language_code)
+        lcode = settings.language_code
+        self.language = languages.get_language(lcode)
         self.head_prefix = [
               self.xml_declaration % settings.output_encoding,
               self.doctype,
-              self.html_head % settings.language_code,
+              self.html_head % (lcode, lcode),
               self.content_type % settings.output_encoding,
               self.generator % docutils.__version__]
         self.head = []
@@ -167,7 +169,10 @@ class HTMLTranslator(nodes.NodeVisitor):
             self.stylesheet = [self.embedded_stylesheet % stylesheet_text]
         else:
             stylesheet = self.get_stylesheet_reference()
+            if stylesheet:
                 self.stylesheet = [self.stylesheet_link % stylesheet]
+            else:
+                self.stylesheet = []
         self.body_prefix = ['</head>\n<body>\n']
         self.body_pre_docinfo = []
         self.docinfo = []