dded docutils library to allow RST to HTML transformation. See ietf-tools#908

 - Legacy-Id: 5076

Author: emiliosanchez

docutils/__init__.py

@@ -0,0 +1,214 @@
+# $Id: __init__.py 7446 2012-06-17 20:47:10Z grubert $
+# Author: David Goodger <goodger@python.org>
+# Copyright: This module has been placed in the public domain.
+
+"""
+This is the Docutils (Python Documentation Utilities) package.
+
+Package Structure
+=================
+
+Modules:
+
+- __init__.py: Contains component base classes, exception classes, and
+  Docutils version information.
+
+- core.py: Contains the ``Publisher`` class and ``publish_*()`` convenience
+  functions.
+
+- frontend.py: Runtime settings (command-line interface, configuration files)
+  processing, for Docutils front-ends.
+
+- io.py: Provides a uniform API for low-level input and output.
+
+- nodes.py: Docutils document tree (doctree) node class library.
+
+- statemachine.py: A finite state machine specialized for
+  regular-expression-based text filters.
+
+- urischemes.py: Contains a complete mapping of known URI addressing
+  scheme names to descriptions.
+
+Subpackages:
+
+- languages: Language-specific mappings of terms.
+
+- parsers: Syntax-specific input parser modules or packages.
+
+- readers: Context-specific input handlers which understand the data
+  source and manage a parser.
+
+- transforms: Modules used by readers and writers to modify DPS
+  doctrees.
+
+- utils: Contains the ``Reporter`` system warning class and miscellaneous
+  utilities used by readers, writers, and transforms.
+
+- writers: Format-specific output translators.
+"""
+
+__docformat__ = 'reStructuredText'
+
+__version__ = '0.9.1'
+"""``major.minor.micro`` version number.  The micro number is bumped for API
+changes, for new functionality, and for interim project releases.  The minor
+number is bumped whenever there is a significant project release.  The major
+number will be bumped when the project is feature-complete, and perhaps if
+there is a major change in the design."""
+
+__version_details__ = 'release'
+"""Extra version details (e.g. 'snapshot 2005-05-29, r3410', 'repository',
+'release'), modified automatically & manually."""
+
+import sys
+
+class ApplicationError(StandardError):
+    # Workaround:
+    # In Python < 2.6, unicode(<exception instance>) calls `str` on the
+    # arg and therefore, e.g., unicode(StandardError(u'\u234')) fails
+    # with UnicodeDecodeError.
+    if sys.version_info < (2,6):
+        def __unicode__(self):
+            return u', '.join(self.args)
+
+class DataError(ApplicationError): pass
+
+
+class SettingsSpec:
+
+    """
+    Runtime setting specification base class.
+
+    SettingsSpec subclass objects used by `docutils.frontend.OptionParser`.
+    """
+
+    settings_spec = ()
+    """Runtime settings specification.  Override in subclasses.
+
+    Defines runtime settings and associated command-line options, as used by
+    `docutils.frontend.OptionParser`.  This is a tuple of:
+
+    - Option group title (string or `None` which implies no group, just a list
+      of single options).
+
+    - Description (string or `None`).
+
+    - A sequence of option tuples.  Each consists of:
+
+      - Help text (string)
+
+      - List of option strings (e.g. ``['-Q', '--quux']``).
+
+      - Dictionary of keyword arguments sent to the OptionParser/OptionGroup
+        ``add_option`` method.
+
+        Runtime setting names are derived implicitly from long option names
+        ('--a-setting' becomes ``settings.a_setting``) or explicitly from the
+        'dest' keyword argument.
+
+        Most settings will also have a 'validator' keyword & function.  The
+        validator function validates setting values (from configuration files
+        and command-line option arguments) and converts them to appropriate
+        types.  For example, the ``docutils.frontend.validate_boolean``
+        function, **required by all boolean settings**, converts true values
+        ('1', 'on', 'yes', and 'true') to 1 and false values ('0', 'off',
+        'no', 'false', and '') to 0.  Validators need only be set once per
+        setting.  See the `docutils.frontend.validate_*` functions.
+
+        See the optparse docs for more details.
+
+    - More triples of group title, description, options, as many times as
+      needed.  Thus, `settings_spec` tuples can be simply concatenated.
+    """
+
+    settings_defaults = None
+    """A dictionary of defaults for settings not in `settings_spec` (internal
+    settings, intended to be inaccessible by command-line and config file).
+    Override in subclasses."""
+
+    settings_default_overrides = None
+    """A dictionary of auxiliary defaults, to override defaults for settings
+    defined in other components.  Override in subclasses."""
+
+    relative_path_settings = ()
+    """Settings containing filesystem paths.  Override in subclasses.
+    Settings listed here are to be interpreted relative to the current working
+    directory."""
+
+    config_section = None
+    """The name of the config file section specific to this component
+    (lowercase, no brackets).  Override in subclasses."""
+
+    config_section_dependencies = None
+    """A list of names of config file sections that are to be applied before
+    `config_section`, in order (from general to specific).  In other words,
+    the settings in `config_section` are to be overlaid on top of the settings
+    from these sections.  The "general" section is assumed implicitly.
+    Override in subclasses."""
+
+
+class TransformSpec:
+
+    """
+    Runtime transform specification base class.
+
+    TransformSpec subclass objects used by `docutils.transforms.Transformer`.
+    """
+
+    def get_transforms(self):
+        """Transforms required by this class.  Override in subclasses."""
+        if self.default_transforms != ():
+            import warnings
+            warnings.warn('default_transforms attribute deprecated.\n'
+                          'Use get_transforms() method instead.',
+                          DeprecationWarning)
+            return list(self.default_transforms)
+        return []
+
+    # Deprecated; for compatibility.
+    default_transforms = ()
+
+    unknown_reference_resolvers = ()
+    """List of functions to try to resolve unknown references.  Unknown
+    references have a 'refname' attribute which doesn't correspond to any
+    target in the document.  Called when the transforms in
+    `docutils.tranforms.references` are unable to find a correct target.  The
+    list should contain functions which will try to resolve unknown
+    references, with the following signature::
+
+        def reference_resolver(node):
+            '''Returns boolean: true if resolved, false if not.'''
+
+    If the function is able to resolve the reference, it should also remove
+    the 'refname' attribute and mark the node as resolved::
+
+        del node['refname']
+        node.resolved = 1
+
+    Each function must have a "priority" attribute which will affect the order
+    the unknown_reference_resolvers are run::
+
+        reference_resolver.priority = 100
+
+    Override in subclasses."""
+
+
+class Component(SettingsSpec, TransformSpec):
+
+    """Base class for Docutils components."""
+
+    component_type = None
+    """Name of the component type ('reader', 'parser', 'writer').  Override in
+    subclasses."""
+
+    supported = ()
+    """Names for this component.  Override in subclasses."""
+
+    def supports(self, format):
+        """
+        Is `format` supported by this component?
+
+        To be used by transforms to ask the dependent component if it supports
+        a certain input context or output format.
+        """
+        return format in self.supported

docutils/_compat.py

@@ -0,0 +1,37 @@
+# $Id: _compat.py 7316 2012-01-19 11:31:58Z milde $
+# Author: Georg Brandl <georg@python.org>
+# Copyright: This module has been placed in the public domain.
+
+"""
+Python 2/3 compatibility definitions.
+
+This module currently provides the following helper symbols:
+
+* bytes (name of byte string type; str in 2.x, bytes in 3.x)
+* b (function converting a string literal to an ASCII byte string;
+  can be also used to convert a Unicode string into a byte string)
+* u_prefix (unicode repr prefix: 'u' in 2.x, '' in 3.x)
+  (Required in docutils/test/test_publisher.py)
+* BytesIO (a StringIO class that works with bytestrings)
+"""
+
+import sys
+
+if sys.version_info < (3,0):
+    b = bytes = str
+    u_prefix = 'u'
+    from StringIO import StringIO as BytesIO
+else:
+    import builtins
+    bytes = builtins.bytes
+    u_prefix = ''
+    def b(s):
+        if isinstance(s, str):
+            return s.encode('latin1')
+        elif isinstance(s, bytes):
+            return s
+        else:
+            raise TypeError("Invalid argument %r for b()" % (s,))
+    # using this hack since 2to3 "fixes" the relative import
+    # when using ``from io import BytesIO``
+    BytesIO = __import__('io').BytesIO

docutils/_string_template_compat.py

@@ -0,0 +1,133 @@
+#!/usr/bin/env python
+# -*- coding: utf8 -*-
+
+# string_template_compat.py: string.Template for Python <= 2.4
+# =====================================================
+
+# This is just an excerpt of the standard string module to provide backwards
+# compatibility.
+
+import re as _re
+
+class _multimap:
+    """Helper class for combining multiple mappings.
+
+    Used by .{safe_,}substitute() to combine the mapping and keyword
+    arguments.
+    """
+    def __init__(self, primary, secondary):
+        self._primary = primary
+        self._secondary = secondary
+
+    def __getitem__(self, key):
+        try:
+            return self._primary[key]
+        except KeyError:
+            return self._secondary[key]
+
+
+class _TemplateMetaclass(type):
+    pattern = r"""
+    %(delim)s(?:
+      (?P<escaped>%(delim)s) |   # Escape sequence of two delimiters
+      (?P<named>%(id)s)      |   # delimiter and a Python identifier
+      {(?P<braced>%(id)s)}   |   # delimiter and a braced identifier
+      (?P<invalid>)              # Other ill-formed delimiter exprs
+    )
+    """
+
+    def __init__(cls, name, bases, dct):
+        super(_TemplateMetaclass, cls).__init__(name, bases, dct)
+        if 'pattern' in dct:
+            pattern = cls.pattern
+        else:
+            pattern = _TemplateMetaclass.pattern % {
+                'delim' : _re.escape(cls.delimiter),
+                'id'    : cls.idpattern,
+                }
+        cls.pattern = _re.compile(pattern, _re.IGNORECASE | _re.VERBOSE)
+
+
+class Template:
+    """A string class for supporting $-substitutions."""
+    __metaclass__ = _TemplateMetaclass
+
+    delimiter = '$'
+    idpattern = r'[_a-z][_a-z0-9]*'
+
+    def __init__(self, template):
+        self.template = template
+
+    # Search for $$, $identifier, ${identifier}, and any bare $'s
+
+    def _invalid(self, mo):
+        i = mo.start('invalid')
+        lines = self.template[:i].splitlines(True)
+        if not lines:
+            colno = 1
+            lineno = 1
+        else:
+            colno = i - len(''.join(lines[:-1]))
+            lineno = len(lines)
+        raise ValueError('Invalid placeholder in string: line %d, col %d' %
+                         (lineno, colno))
+
+    def substitute(self, *args, **kws):
+        if len(args) > 1:
+            raise TypeError('Too many positional arguments')
+        if not args:
+            mapping = kws
+        elif kws:
+            mapping = _multimap(kws, args[0])
+        else:
+            mapping = args[0]
+        # Helper function for .sub()
+        def convert(mo):
+            # Check the most common path first.
+            named = mo.group('named') or mo.group('braced')
+            if named is not None:
+                val = mapping[named]
+                # We use this idiom instead of str() because the latter will
+                # fail if val is a Unicode containing non-ASCII characters.
+                return '%s' % (val,)
+            if mo.group('escaped') is not None:
+                return self.delimiter
+            if mo.group('invalid') is not None:
+                self._invalid(mo)
+            raise ValueError('Unrecognized named group in pattern',
+                             self.pattern)
+        return self.pattern.sub(convert, self.template)
+
+    def safe_substitute(self, *args, **kws):
+        if len(args) > 1:
+            raise TypeError('Too many positional arguments')
+        if not args:
+            mapping = kws
+        elif kws:
+            mapping = _multimap(kws, args[0])
+        else:
+            mapping = args[0]
+        # Helper function for .sub()
+        def convert(mo):
+            named = mo.group('named')
+            if named is not None:
+                try:
+                    # We use this idiom instead of str() because the latter
+                    # will fail if val is a Unicode containing non-ASCII
+                    return '%s' % (mapping[named],)
+                except KeyError:
+                    return self.delimiter + named
+            braced = mo.group('braced')
+            if braced is not None:
+                try:
+                    return '%s' % (mapping[braced],)
+                except KeyError:
+                    return self.delimiter + '{' + braced + '}'
+            if mo.group('escaped') is not None:
+                return self.delimiter
+            if mo.group('invalid') is not None:
+                return self.delimiter
+            raise ValueError('Unrecognized named group in pattern',
+                             self.pattern)
+        return self.pattern.sub(convert, self.template)
+