SF.net SVN: docutils:[9730] trunk/docutils
milde--- via Docutils-checkins <[email protected]>
| Newsgroups | gmane.text.docutils.cvs |
|---|---|
| Message-ID | <[email protected]> |
Revision: 9730
http://sourceforge.net/p/docutils/code/9730
Author: milde
Date: 2024-06-05 15:54:07 +0000 (Wed, 05 Jun 2024)
Log Message:
-----------
Doctree validation: validate content (part 1, simple models)
Check simple content models (without nested sequences).
Modified Paths:
--------------
trunk/docutils/docutils/nodes.py
trunk/docutils/test/test_nodes.py
trunk/docutils/test/test_writers/test_latex2e.py
Modified: trunk/docutils/docutils/nodes.py
===================================================================
--- trunk/docutils/docutils/nodes.py 2024-06-05 12:05:56 UTC (rev 9729)
+++ trunk/docutils/docutils/nodes.py 2024-06-05 15:54:07 UTC (rev 9730)
@@ -1142,6 +1142,58 @@
+ '\n '.join(messages),
problematic_element=self)
+ def validate_content(self, model=None, elements=None):
+ """Test compliance of `elements` with `model`.
+
+ :model: content model description, default `self.content_model`,
+ :elements: list of doctree elements, default `self.children`.
+
+ Return list of children that do not fit in the model or raise
+ `ValidationError` if the content does not comply with the `model`.
+
+ Provisional.
+ """
+ if model is None:
+ model = self.content_model
+ if elements is None:
+ elements = self.children
+ ichildren = iter(elements)
+ child = next(ichildren, None)
+ for category, quantifier in model:
+ if not isinstance(child, category):
+ if quantifier in ('.', '+'):
+ raise ValidationError(self._report_child(child, category),
+ problematic_element=child)
+ else: # quantifier in ('?', '*') -> optional child
+ continue # try same child with next part of content model
+ # TODO: check additional placement constraints (if applicable)
+ # child.check_position()
+ # advance:
+ if quantifier in ('.', '?'): # go to next element
+ child = next(ichildren, None)
+ else: # if quantifier in ('*', '+'): # pass all matching elements
+ for child in ichildren:
+ if not isinstance(child, category):
+ break
+ else:
+ child = None
+ return [] if child is None else [child, *ichildren]
+
+ def _report_child(self, child, category):
+ # Return a str reporting a missing child or child of wrong category.
+ try:
+ type = category.__name__
+ except AttributeError:
+ type = '> or <'.join(c.__name__ for c in category)
+ msg = f'Element {self.starttag()} invalid:\n'
+ if child is None:
+ return f'{msg} Missing child of type <{type}>.'
+ if isinstance(child, Text):
+ return (f'{msg} Expecting child of type <{type}>, '
+ f'not text data "{child.astext()}".')
+ return (f'{msg} Expecting child of type <{type}>, '
+ f'not {child.starttag()}.')
+
def validate(self, recursive=True):
"""Validate Docutils Document Tree element ("doctree").
@@ -1156,9 +1208,19 @@
Provisional (work in progress).
"""
self.validate_attributes()
-
- # TODO: validate content
+ leftover_childs = self.validate_content()
+ for child in leftover_childs:
+ if isinstance(child, Text):
+ raise ValidationError(f'Element {self.starttag()} invalid:\n'
+ f' Spurious text: "{child.astext()}".',
+ problematic_element=self)
+ else:
+ raise ValidationError(f'Element {self.starttag()} invalid:\n'
+ f' Child element {child.starttag()} '
+ 'not allowed at this position.',
+ problematic_element=child)
+
if recursive:
for child in self:
child.validate(recursive=recursive)
Modified: trunk/docutils/test/test_nodes.py
===================================================================
--- trunk/docutils/test/test_nodes.py 2024-06-05 12:05:56 UTC (rev 9729)
+++ trunk/docutils/test/test_nodes.py 2024-06-05 15:54:07 UTC (rev 9730)
@@ -514,7 +514,262 @@
'.*Valid units: em ex '):
node.validate()
+ def test_validate_spurious_element(self):
+ label = nodes.label('', '*')
+ label.append(nodes.strong())
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Element <label> invalid:\n'
+ ' Child element <strong> not allowed '):
+ label.validate()
+ def test_validate_content(self):
+ """Check, whether an element's children fit into its content model.
+
+ Return empty lists for valid elements,
+ lists with warnings and spurious children if children don't match.
+ """
+ # sample elements
+ inline = nodes.inline() # inline element
+ text = nodes.Text('explanation') # <#text>
+ hint = nodes.hint() # body element
+
+ # empty element: (EMPTY)
+ image = nodes.image('')
+ self.assertEqual(image.validate_content(), [])
+ image.append(text)
+ self.assertEqual(image.validate_content(), [text])
+ # ValueError, "Spurious Element <#text: 'explanation'>"):
+
+ # TextElement: (#PCDATA | %inline.elements;)*
+ paragraph = nodes.paragraph() # empty element
+ self.assertEqual(paragraph.validate_content(), [])
+ paragraph = nodes.paragraph('', 'text') # just text
+ self.assertEqual(paragraph.validate_content(), [])
+ paragraph.extend([inline, nodes.Text('text 2'), nodes.math()])
+ self.assertEqual(paragraph.validate_content(), [])
+ paragraph.append(hint) # body element (sic!)
+ paragraph.append(text)
+ self.assertEqual(paragraph.validate_content(), [hint, text])
+ # validate() reports "relics" as ValueError:
+ with self.assertRaisesRegex(nodes.ValidationError,
+ '<paragraph> invalid:\n'
+ ' Child element <hint> not allowed '):
+ paragraph.validate()
+
+ # PureTextElement: (#PCDATA)
+ label = nodes.label() # empty element
+ self.assertEqual(label.validate_content(), [])
+ label = nodes.label('', '†')
+ self.assertEqual(label.validate_content(), [])
+ label.append(inline) # sic!
+ self.assertEqual(label.validate_content(), [inline])
+
+ # docinfo: (%bibliographic.elements;)+
+ docinfo = nodes.docinfo() # empty element (sic!)
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Missing child of type <Bibliographic>.'):
+ docinfo.validate_content()
+ docinfo.append(nodes.paragraph())
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Expecting .* <Bibliographic>, not '):
+ docinfo.validate_content()
+ docinfo = nodes.docinfo('', nodes.authors(), nodes.contact())
+ self.assertEqual(docinfo.validate_content(), [])
+ docinfo.append(hint) # sic!
+ self.assertEqual(docinfo.validate_content(), [hint])
+
+ # decoration: (header?, footer?)
+ decoration = nodes.decoration() # empty element
+ self.assertEqual(decoration.validate_content(), [])
+ decoration = nodes.decoration('', nodes.header(), nodes.footer())
+ self.assertEqual(decoration.validate_content(), [])
+ header = nodes.header()
+ decoration.append(header) # 3rd element (sic!)
+ self.assertEqual(decoration.validate_content(), [header])
+ decoration = nodes.decoration('', nodes.footer())
+ self.assertEqual(decoration.validate_content(), [])
+ decoration.append(header) # wrong order!
+ self.assertEqual(decoration.validate_content(), [header])
+
+ # Body elements have a range of different content models.
+
+ # container: (%body.elements;)+
+ container = nodes.container() # empty (sic!)
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Missing child of type <Body>.'):
+ container.validate_content()
+ container.append(inline) # sic!
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Expecting child of type <Body>, not <in'):
+ container.validate_content()
+ container = nodes.container('', nodes.paragraph()) # one body element
+ self.assertEqual(container.validate_content(), []) # valid
+ container.append(nodes.tip()) # more body elements
+ self.assertEqual(container.validate_content(), []) # valid
+ container.append(inline) # sic!
+ self.assertEqual(container.validate_content(), [inline])
+
+ # block_quote: ((%body.elements;)+, attribution?)
+ block_quote = nodes.block_quote('', hint, nodes.table())
+ self.assertEqual(block_quote.validate_content(), [])
+ block_quote.append(nodes.attribution())
+ self.assertEqual(block_quote.validate_content(), [])
+ block_quote.append(hint) # element after attribution (sic!)
+ self.assertEqual(block_quote.validate_content(), [hint])
+
+ # list item (%body.elements;)*
+ list_item = nodes.list_item() # empty list item is valid
+ self.assertEqual(list_item.validate_content(), [])
+ list_item.append(nodes.bullet_list()) # lists may be nested
+ list_item.append(paragraph)
+ self.assertEqual(list_item.validate_content(), [])
+ list_item.append(inline) # sic!
+ self.assertEqual(list_item.validate_content(), [inline])
+
+ # bullet_list, enumerated_list: (list_item+)
+ bullet_list = nodes.bullet_list() # empty (sic!)
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Missing child of type <list_item>.'):
+ bullet_list.validate_content()
+ bullet_list.extend([list_item, list_item, list_item])
+ self.assertEqual(bullet_list.validate_content(), [])
+ bullet_list.append(hint) # must nest in <list_item>
+ self.assertEqual(bullet_list.validate_content(), [hint])
+
+ # definition_list_item: (term, classifier*, definition)
+ definition_list_item = nodes.definition_list_item()
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Element <definition_list_item> invalid:\n'
+ ' Missing child of type <term>.'):
+ definition_list_item.validate_content(),
+ definition_list_item.append(nodes.term())
+ definition_list_item.append(nodes.definition())
+ self.assertEqual(definition_list_item.validate_content(), [])
+ definition_list_item.children.insert(1, nodes.classifier())
+ definition_list_item.children.insert(1, nodes.classifier())
+ self.assertEqual(definition_list_item.validate_content(), [])
+
+ # field: (field_name, field_body)
+ field = nodes.field()
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Missing child of type <field_name>.'):
+ field.validate_content()
+ field.extend([nodes.field_name(), nodes.field_body()])
+ self.assertEqual(field.validate_content(), [])
+ field = nodes.field('', nodes.field_body(), nodes.field_name())
+ # wrong order!
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Expecting child of type <field_name>,'
+ ' not <field_body>.'):
+ field.validate_content()
+
+ # option: (option_string, option_argument*)
+ option = nodes.option()
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Missing child of type <option_string>.'):
+ option.validate_content()
+ option.append(nodes.paragraph()) # sic!
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Expecting child of type <option_string>,'
+ ' not <paragraph>.'):
+ option.validate_content()
+ option = nodes.option('', nodes.option_string())
+ self.assertEqual(option.validate_content(), [])
+ option.append(nodes.option_argument())
+ self.assertEqual(option.validate_content(), [])
+
+ # line_block: (line | line_block)+
+ line_block = nodes.line_block() # sic!
+ with self.assertRaisesRegex(nodes.ValidationError,
+ ' child of type <line> or <line_block>.'):
+ line_block.validate_content()
+ line_block.append(nodes.line_block())
+ self.assertEqual(line_block.validate_content(), [])
+ line_block = nodes.line_block('', nodes.paragraph(), nodes.line())
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Expecting child of type <line> or '
+ '<line_block>, not <paragraph>.'):
+ line_block.validate_content()
+
+ # admonition: (title, (%body.elements;)+)
+ admonition = nodes.admonition('', nodes.paragraph())
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Expecting child of type <title>,'
+ ' not <paragraph>.'):
+ admonition.validate_content()
+ admonition = nodes.admonition('', nodes.title(), nodes.paragraph())
+ self.assertEqual(admonition.validate_content(), [])
+
+ # specific admonitions: (%body.elements;)+
+ note = nodes.note()
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Missing child of type <Body>.'):
+ note.validate_content()
+ note.append(nodes.enumerated_list())
+ self.assertEqual(note.validate_content(), [])
+
+ # footnote: (label?, (%body.elements;)+)
+ # TODO: use case for footnote without label (make it required?)
+ # rST parser can generate footnotes without body elements!
+ footnote = nodes.footnote('', hint)
+ self.assertEqual(footnote.validate_content(), [])
+
+ # citation: (label, (%body.elements;)+)
+ # TODO: rST parser allows empty citation
+ # (see test_rst/test_citations.py). Is this sensible?
+ citation = nodes.citation('', hint)
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Expecting child of type <label>,'
+ ' not <hint>.'):
+ citation.validate_content()
+
+ # Table group: (colspec*, thead?, tbody)
+ tgroup = nodes.tgroup() # empty (sic!)
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Missing child of type <tbody>.'):
+ tgroup.validate_content()
+ tgroup = nodes.tgroup('', nodes.colspec(), nodes.colspec(),
+ nodes.thead(), nodes.tbody())
+ self.assertEqual(tgroup.validate_content(), [])
+ thead = nodes.thead()
+ tgroup = nodes.tgroup('', nodes.tbody(), thead) # wrong order!
+ self.assertEqual(tgroup.validate_content(), [thead])
+
+ def test_validate_content_authors(self):
+ """Return empty list for valid elements, raise ValidationError else.
+
+ Specific method for `authors` instances: complex content model
+ requires repeated application of `authors.content_model`.
+ """
+ authors = nodes.authors()
+ with self.assertRaisesRegex(nodes.ValidationError,
+ 'Missing child of type <author>.'):
+ authors.validate_content()
+ authors.extend([nodes.author(), nodes.address(), nodes.contact()])
+ self.assertEqual(authors.validate_content(), [])
+ # TODO: check content model again, with next set of elements
+
+ def test_validate_content_subtitle(self):
+ """<subtitle> must follow a <title>.
+ """
+ subtitle = nodes.subtitle()
+ paragraph = nodes.paragraph()
+ sidebar = nodes.sidebar('', subtitle, paragraph)
+ # TODO additional restriction "only after title"
+ sidebar.validate_content()
+
+ def test_validate_content_transition(self):
+ """Test additional constraints on <transition> placement:
+ Not at begin or end of a section or document,
+ not after another transition.
+ """
+ transition = nodes.transition()
+ paragraph = nodes.paragraph()
+ section = nodes.section('', nodes.title(), transition, paragraph)
+ # TODO: additional restrictions on transition placement.
+ section.validate_content()
+
+
class MiscTests(unittest.TestCase):
def test_node_class_names(self):
Modified: trunk/docutils/test/test_writers/test_latex2e.py
===================================================================
--- trunk/docutils/test/test_writers/test_latex2e.py 2024-06-05 12:05:56 UTC (rev 9729)
+++ trunk/docutils/test/test_writers/test_latex2e.py 2024-06-05 15:54:07 UTC (rev 9730)
@@ -55,7 +55,9 @@
self.assertEqual(expected, output)
def test_defaults(self):
- self.run_samples(samples_default, self.settings)
+ settings = self.settings.copy()
+ settings['validate'] = False # we test an invalid footnote
+ self.run_samples(samples_default, settings)
def test_docutils_toc(self):
settings = self.settings.copy()
This was sent by the SourceForge.net collaborative development platform, the world's largest Open Source development site.
_______________________________________________
Docutils-checkins mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/docutils-checkins