tests/test-minirst.py
author Manuel Jacob <me@manueljacob.de>
Mon, 11 Jul 2022 01:51:20 +0200
branchstable
changeset 49378 094a5fa3cf52
parent 48875 6000f5b25c9b
child 50333 805d4a462abb
permissions -rw-r--r--
procutil: make stream detection in make_line_buffered more correct and strict In make_line_buffered(), we don’t want to wrap the stream if we know that lines get flushed to the underlying raw stream already. Previously, the heuristic was too optimistic. It assumed that any stream which is not an instance of io.BufferedIOBase doesn’t need wrapping. However, there are buffered streams that aren’t instances of io.BufferedIOBase, like Mercurial’s own winstdout. The new logic is different in two ways: First, only for the check, if unwraps any combination of WriteAllWrapper and winstdout. Second, it skips wrapping the stream only if it is an instance of io.RawIOBase (or already wrapped). If it is an instance of io.BufferedIOBase, it gets wrapped. In any other case, the function raises an exception. This ensures that, if an unknown stream is passed or we add another wrapper in the future, we don’t wrap the stream if it’s already line buffered or not wrap the stream if it’s not line buffered. In fact, this was already helpful during development of this change. Without it, I possibly would have forgot that WriteAllWrapper needs to be ignored for the check, leading to unnecessary wrapping if stdout is unbuffered. The alternative would have been to always wrap unknown streams. However, I don’t think that anyone would benefit from being less strict. We can expect streams from the standard library to be subclassing either io.RawIOBase or io.BufferedIOBase, so running Mercurial in the standard way should not regress by this change. Py2exe might replace sys.stdout and sys.stderr, but that currently breaks Mercurial anyway and also these streams don’t claim to be interactive, so this function is not called for them.

from mercurial import minirst
from mercurial.utils import stringutil


def debugformat(text, form, **kwargs):
    blocks, pruned = minirst.parse(text, **kwargs)
    if form == b'html':
        print("html format:")
        out = minirst.format(text, style=form, **kwargs)
    else:
        print("%d column format:" % form)
        out = minirst.format(text, width=form, **kwargs)

    print("-" * 70)
    print(out[:-1].decode('utf8'))
    if kwargs.get('keep'):
        print("-" * 70)
        print(stringutil.pprint(pruned).decode('utf8'))
    print("-" * 70)
    print()


def debugformats(title, text, **kwargs):
    print("== %s ==" % title)
    debugformat(text, 60, **kwargs)
    debugformat(text, 30, **kwargs)
    debugformat(text, b'html', **kwargs)


paragraphs = b"""
This is some text in the first paragraph.

  A small indented paragraph.
  It is followed by some lines
  containing random whitespace.
 \n  \n   \nThe third and final paragraph.
"""

debugformats('paragraphs', paragraphs)

definitions = b"""
A Term
  Definition. The indented
  lines make up the definition.
Another Term
  Another definition. The final line in the
   definition determines the indentation, so
    this will be indented with four spaces.

  A Nested/Indented Term
    Definition.
"""

debugformats('definitions', definitions)

literals = br"""
The fully minimized form is the most
convenient form::

  Hello
    literal
      world

In the partially minimized form a paragraph
simply ends with space-double-colon. ::

  ////////////////////////////////////////
  long un-wrapped line in a literal block
  \\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\\

::

  This literal block is started with '::',
    the so-called expanded form. The paragraph
      with '::' disappears in the final output.
"""

debugformats('literals', literals)

lists = b"""
- This is the first list item.

  Second paragraph in the first list item.

- List items need not be separated
  by a blank line.
- And will be rendered without
  one in any case.

We can have indented lists:

  - This is an indented list item

  - Another indented list item::

      - A literal block in the middle
            of an indented list.

      (The above is not a list item since we are in the literal block.)

::

  Literal block with no indentation (apart from
  the two spaces added to all literal blocks).

1. This is an enumerated list (first item).
2. Continuing with the second item.

(1) foo
(2) bar

1) Another
2) List

Line blocks are also a form of list:

| This is the first line.
  The line continues here.
| This is the second line.

Bullet lists are also detected:

* This is the first bullet
* This is the second bullet
  It has 2 lines
* This is the third bullet
"""

debugformats('lists', lists)

options = b"""
There is support for simple option lists,
but only with long options:

-X, --exclude  filter  an option with a short and long option with an argument
-I, --include          an option with both a short option and a long option
--all                  Output all.
--both                 Output both (this description is
                       quite long).
--long                 Output all day long.

--par                 This option has two paragraphs in its description.
                      This is the first.

                      This is the second.  Blank lines may be omitted between
                      options (as above) or left in (as here).


The next paragraph looks like an option list, but lacks the two-space
marker after the option. It is treated as a normal paragraph:

--foo bar baz
"""

debugformats('options', options)

fields = b"""
:a: First item.
:ab: Second item. Indentation and wrapping
     is handled automatically.
:c\:d: a key with colon
:efg\:\:hh: a key with many colon

Next list:

:small: The larger key below triggers full indentation here.
:much too large: This key is big enough to get its own line.
"""

debugformats('fields', fields)

containers = b"""
Normal output.

.. container:: debug

   Initial debug output.

.. container:: verbose

   Verbose output.

   .. container:: debug

      Debug output.
"""

debugformats('containers (normal)', containers)
debugformats('containers (verbose)', containers, keep=[b'verbose'])
debugformats('containers (debug)', containers, keep=[b'debug'])
debugformats(
    'containers (verbose debug)', containers, keep=[b'verbose', b'debug']
)

roles = b"""Please see :hg:`add`."""
debugformats('roles', roles)


sections = b"""
Title
=====

Section
-------

Subsection
''''''''''

Markup: ``foo`` and :hg:`help`
------------------------------
"""
debugformats('sections', sections)


admonitions = b"""
.. note::

   This is a note

   - Bullet 1
   - Bullet 2

   .. warning:: This is a warning Second
      input line of warning

.. danger::
   This is danger
"""

debugformats('admonitions', admonitions)

comments = b"""
Some text.

.. A comment

   .. An indented comment

   Some indented text.

..

Empty comment above
"""

debugformats('comments', comments)


data = [
    [b'a', b'b', b'c'],
    [b'1', b'2', b'3'],
    [b'foo', b'bar', b'baz this list is very very very long man'],
]

rst = minirst.maketable(data, 2, True)
table = b''.join(rst)

print(table.decode('utf8'))

debugformats('table', table)

data = [
    [b's', b'long', b'line\ngoes on here'],
    [b'', b'xy', b'tried to fix here\n        by indenting'],
]

rst = minirst.maketable(data, 1, False)
table = b''.join(rst)

print(table.decode('utf8'))

debugformats('table+nl', table)