minirst: improved support for option lists.

This enables minirst to parse and print option lists which have both
long and short options. Before, we could only parse option lists with
long options.

mercurial/minirst.py

@@ -1,434 +1,482 b''
 # minirst.py - minimal reStructuredText parser
 #
 # Copyright 2009, 2010 Matt Mackall <[e-mail]> and others
 #
 # This software may be used and distributed according to the terms of the
 # GNU General Public License version 2 or any later version.
 
 """simplified reStructuredText parser.
 
 This parser knows just enough about reStructuredText to parse the
 Mercurial docstrings.
 
 It cheats in a major way: nested blocks are not really nested. They
 are just indented blocks that look like they are nested. This relies
 on the user to keep the right indentation for the blocks.
 
 Remember to update http://mercurial.selenic.com/wiki/HelpStyleGuide
 when adding support for new constructs.
 """
 
 import re, sys
 import util, encoding
 from i18n import _
 
 
 def replace(text, substs):
     utext = text.decode(encoding.encoding)
     for f, t in substs:
         utext = utext.replace(f, t)
     return utext.encode(encoding.encoding)
 
 
 _blockre = re.compile(r"\n(?:\s*\n)+")
 
 def findblocks(text):
     """Find continuous blocks of lines in text.
 
     Returns a list of dictionaries representing the blocks. Each block
     has an 'indent' field and a 'lines' field.
     """
     blocks = []
     for b in _blockre.split(text.strip()):
         lines = b.splitlines()
         indent = min((len(l) - len(l.lstrip())) for l in lines)
         lines = [l[indent:] for l in lines]
         blocks.append(dict(indent=indent, lines=lines))
     return blocks
 
 
 def findliteralblocks(blocks):
     """Finds literal blocks and adds a 'type' field to the blocks.
 
     Literal blocks are given the type 'literal', all other blocks are
     given type the 'paragraph'.
     """
     i = 0
     while i < len(blocks):
         # Searching for a block that looks like this:
         #
         # +------------------------------+
         # | paragraph                    |
         # | (ends with "::")             |
         # +------------------------------+
         #    +---------------------------+
         #    | indented literal block    |
         #    +---------------------------+
         blocks[i]['type'] = 'paragraph'
         if blocks[i]['lines'][-1].endswith('::') and i + 1 < len(blocks):
             indent = blocks[i]['indent']
             adjustment = blocks[i + 1]['indent'] - indent
 
             if blocks[i]['lines'] == ['::']:
                 # Expanded form: remove block
                 del blocks[i]
                 i -= 1
             elif blocks[i]['lines'][-1].endswith(' ::'):
                 # Partially minimized form: remove space and both
                 # colons.
                 blocks[i]['lines'][-1] = blocks[i]['lines'][-1][:-3]
             else:
                 # Fully minimized form: remove just one colon.
                 blocks[i]['lines'][-1] = blocks[i]['lines'][-1][:-1]
 
             # List items are formatted with a hanging indent. We must
             # correct for this here while we still have the original
             # information on the indentation of the subsequent literal
             # blocks available.
             m = _bulletre.match(blocks[i]['lines'][0])
             if m:
                 indent += m.end()
                 adjustment -= m.end()
 
             # Mark the following indented blocks.
             while i + 1 < len(blocks) and blocks[i + 1]['indent'] > indent:
                 blocks[i + 1]['type'] = 'literal'
                 blocks[i + 1]['indent'] -= adjustment
                 i += 1
         i += 1
     return blocks
 
 _bulletre = re.compile(r'(-|[0-9A-Za-z]+\.|\(?[0-9A-Za-z]+\)|\|) ')
-_optionre = re.compile(r'^(--[a-z-]+)((?:[ =][a-zA-Z][\w-]*)?  +)(.*)$')
+_optionre = re.compile(r'^(-([a-zA-Z0-9]), )?(--[a-z0-9-]+)'
+                       r'((.*)  +)(.*)$')
 _fieldre = re.compile(r':(?![: ])([^:]*)(?<! ):[ ]+(.*)')
 _definitionre = re.compile(r'[^ ]')
 
 def splitparagraphs(blocks):
     """Split paragraphs into lists."""
     # Tuples with (list type, item regexp, single line items?). Order
     # matters: definition lists has the least specific regexp and must
     # come last.
     listtypes = [('bullet', _bulletre, True),
                  ('option', _optionre, True),
                  ('field', _fieldre, True),
                  ('definition', _definitionre, False)]
 
     def match(lines, i, itemre, singleline):
         """Does itemre match an item at line i?
 
         A list item can be followed by an idented line or another list
         item (but only if singleline is True).
         """
         line1 = lines[i]
         line2 = i + 1 < len(lines) and lines[i + 1] or ''
         if not itemre.match(line1):
             return False
         if singleline:
             return line2 == '' or line2[0] == ' ' or itemre.match(line2)
         else:
             return line2.startswith(' ')
 
     i = 0
     while i < len(blocks):
         if blocks[i]['type'] == 'paragraph':
             lines = blocks[i]['lines']
             for type, itemre, singleline in listtypes:
                 if match(lines, 0, itemre, singleline):
                     items = []
                     for j, line in enumerate(lines):
                         if match(lines, j, itemre, singleline):
                             items.append(dict(type=type, lines=[],
                                               indent=blocks[i]['indent']))
                         items[-1]['lines'].append(line)
                     blocks[i:i + 1] = items
                     break
         i += 1
     return blocks
 
 
 _fieldwidth = 12
 
 def updatefieldlists(blocks):
     """Find key and maximum key width for field lists."""
     i = 0
     while i < len(blocks):
         if blocks[i]['type'] != 'field':
             i += 1
             continue
 
         keywidth = 0
         j = i
         while j < len(blocks) and blocks[j]['type'] == 'field':
             m = _fieldre.match(blocks[j]['lines'][0])
             key, rest = m.groups()
             blocks[j]['lines'][0] = rest
             blocks[j]['key'] = key
             keywidth = max(keywidth, len(key))
             j += 1
 
         for block in blocks[i:j]:
             block['keywidth'] = keywidth
         i = j + 1
 
     return blocks
 
 
+def updateoptionlists(blocks):
+    i = 0
+    while i < len(blocks):
+        if blocks[i]['type'] != 'option':
+            i += 1
+            continue
+
+        optstrwidth = 0
+        j = i
+        while j < len(blocks) and blocks[j]['type'] == 'option':
+            m = _optionre.match(blocks[j]['lines'][0])
+
+            shortoption = m.group(2)
+            group3 = m.group(3)
+            longoption = group3[2:].strip()
+            desc = m.group(6).strip()
+            longoptionarg = m.group(5).strip()
+            blocks[j]['lines'][0] = desc
+
+            noshortop = ''
+            if not shortoption:
+                noshortop = '   '
+
+            opt = "%s%s" %   (shortoption and "-%s " % shortoption or '',
+                            ("%s--%s %s") % (noshortop, longoption,
+                                             longoptionarg))
+            opt = opt.rstrip()
+            blocks[j]['optstr'] = opt
+            optstrwidth = max(optstrwidth, encoding.colwidth(opt))
+            j += 1
+
+        for block in blocks[i:j]:
+            block['optstrwidth'] = optstrwidth
+        i = j + 1
+    return blocks
+
 def prunecontainers(blocks, keep):
     """Prune unwanted containers.
 
     The blocks must have a 'type' field, i.e., they should have been
     run through findliteralblocks first.
     """
     pruned = []
     i = 0
     while i + 1 < len(blocks):
         # Searching for a block that looks like this:
         #
         # +-------+---------------------------+
         # | ".. container ::" type            |
         # +---+                               |
         #     | blocks                        |
         #     +-------------------------------+
         if (blocks[i]['type'] == 'paragraph' and
             blocks[i]['lines'][0].startswith('.. container::')):
             indent = blocks[i]['indent']
             adjustment = blocks[i + 1]['indent'] - indent
             containertype = blocks[i]['lines'][0][15:]
             prune = containertype not in keep
             if prune:
                 pruned.append(containertype)
 
             # Always delete "..container:: type" block
             del blocks[i]
             j = i
             while j < len(blocks) and blocks[j]['indent'] > indent:
                 if prune:
                     del blocks[j]
                     i -= 1 # adjust outer index
                 else:
                     blocks[j]['indent'] -= adjustment
                     j += 1
         i += 1
     return blocks, pruned
 
 
 _sectionre = re.compile(r"""^([-=`:.'"~^_*+#])\1+$""")
 
 def findsections(blocks):
     """Finds sections.
 
     The blocks must have a 'type' field, i.e., they should have been
     run through findliteralblocks first.
     """
     for block in blocks:
         # Searching for a block that looks like this:
         #
         # +------------------------------+
         # | Section title                |
         # | -------------                |
         # +------------------------------+
         if (block['type'] == 'paragraph' and
             len(block['lines']) == 2 and
             encoding.colwidth(block['lines'][0]) == len(block['lines'][1]) and
             _sectionre.match(block['lines'][1])):
             block['underline'] = block['lines'][1][0]
             block['type'] = 'section'
             del block['lines'][1]
     return blocks
 
 
 def inlineliterals(blocks):
     substs = [('``', '"')]
     for b in blocks:
         if b['type'] in ('paragraph', 'section'):
             b['lines'] = [replace(l, substs) for l in b['lines']]
     return blocks
 
 
 def hgrole(blocks):
     substs = [(':hg:`', '"hg '), ('`', '"')]
     for b in blocks:
         if b['type'] in ('paragraph', 'section'):
             # Turn :hg:`command` into "hg command". This also works
             # when there is a line break in the command and relies on
             # the fact that we have no stray back-quotes in the input
             # (run the blocks through inlineliterals first).
             b['lines'] = [replace(l, substs) for l in b['lines']]
     return blocks
 
 
 def addmargins(blocks):
     """Adds empty blocks for vertical spacing.
 
     This groups bullets, options, and definitions together with no vertical
     space between them, and adds an empty block between all other blocks.
     """
     i = 1
     while i < len(blocks):
         if (blocks[i]['type'] == blocks[i - 1]['type'] and
             blocks[i]['type'] in ('bullet', 'option', 'field')):
             i += 1
         else:
             blocks.insert(i, dict(lines=[''], indent=0, type='margin'))
             i += 2
     return blocks
 
 def prunecomments(blocks):
     """Remove comments."""
     i = 0
     while i < len(blocks):
         b = blocks[i]
         if b['type'] == 'paragraph' and (b['lines'][0].startswith('.. ') or
                                          b['lines'] == ['..']):
             del blocks[i]
             if i < len(blocks) and blocks[i]['type'] == 'margin':
                 del blocks[i]
         else:
             i += 1
     return blocks
 
 _admonitionre = re.compile(r"\.\. (admonition|attention|caution|danger|"
                            r"error|hint|important|note|tip|warning)::",
                            flags=re.IGNORECASE)
 
 def findadmonitions(blocks):
     """
     Makes the type of the block an admonition block if
     the first line is an admonition directive
     """
     i = 0
     while i < len(blocks):
         m = _admonitionre.match(blocks[i]['lines'][0])
         if m:
             blocks[i]['type'] = 'admonition'
             admonitiontitle = blocks[i]['lines'][0][3:m.end() - 2].lower()
 
             firstline = blocks[i]['lines'][0][m.end() + 1:]
             if firstline:
                 blocks[i]['lines'].insert(1, '   ' + firstline)
 
             blocks[i]['admonitiontitle'] = admonitiontitle
             del blocks[i]['lines'][0]
         i = i + 1
     return blocks
 
 _admonitiontitles = {'attention': _('Attention:'),
                      'caution': _('Caution:'),
                      'danger': _('!Danger!')  ,
                      'error': _('Error:'),
                      'hint': _('Hint:'),
                      'important': _('Important:'),
                      'note': _('Note:'),
                      'tip': _('Tip:'),
                      'warning': _('Warning!')}
 
+def formatoption(block, width):
+    desc = ' '.join(map(str.strip, block['lines']))
+    colwidth = encoding.colwidth(block['optstr'])
+    usablewidth = width - 1
+    hanging = block['optstrwidth']
+    initindent = '%s%s  ' % (block['optstr'], ' ' * ((hanging - colwidth)))
+    hangindent = ' ' * (encoding.colwidth(initindent) + 1)
+    return ' %s' % (util.wrap(desc, usablewidth,
+                                           initindent=initindent,
+                                           hangindent=hangindent))
+
 def formatblock(block, width):
     """Format a block according to width."""
     if width <= 0:
         width = 78
     indent = ' ' * block['indent']
     if block['type'] == 'admonition':
         admonition = _admonitiontitles[block['admonitiontitle']]
         hang = len(block['lines'][-1]) - len(block['lines'][-1].lstrip())
 
         defindent = indent + hang * ' '
         text = ' '.join(map(str.strip, block['lines']))
         return '%s\n%s' % (indent + admonition, util.wrap(text, width=width,
                                            initindent=defindent,
                                            hangindent=defindent))
     if block['type'] == 'margin':
         return ''
     if block['type'] == 'literal':
         indent += '  '
         return indent + ('\n' + indent).join(block['lines'])
     if block['type'] == 'section':
         underline = encoding.colwidth(block['lines'][0]) * block['underline']
         return "%s%s\n%s%s" % (indent, block['lines'][0],indent, underline)
     if block['type'] == 'definition':
         term = indent + block['lines'][0]
         hang = len(block['lines'][-1]) - len(block['lines'][-1].lstrip())
         defindent = indent + hang * ' '
         text = ' '.join(map(str.strip, block['lines'][1:]))
         return '%s\n%s' % (term, util.wrap(text, width=width,
                                            initindent=defindent,
                                            hangindent=defindent))
     subindent = indent
     if block['type'] == 'bullet':
         if block['lines'][0].startswith('| '):
             # Remove bullet for line blocks and add no extra
             # indention.
             block['lines'][0] = block['lines'][0][2:]
         else:
             m = _bulletre.match(block['lines'][0])
             subindent = indent + m.end() * ' '
     elif block['type'] == 'field':
         keywidth = block['keywidth']
         key = block['key']
 
         subindent = indent + _fieldwidth * ' '
         if len(key) + 2 > _fieldwidth:
             # key too large, use full line width
             key = key.ljust(width)
         elif keywidth + 2 < _fieldwidth:
             # all keys are small, add only two spaces
             key = key.ljust(keywidth + 2)
             subindent = indent + (keywidth + 2) * ' '
         else:
             # mixed sizes, use fieldwidth for this one
             key = key.ljust(_fieldwidth)
         block['lines'][0] = key + block['lines'][0]
     elif block['type'] == 'option':
-        m = _optionre.match(block['lines'][0])
-        option, arg, rest = m.groups()
-        subindent = indent + (len(option) + len(arg)) * ' '
+        return formatoption(block, width)
 
     text = ' '.join(map(str.strip, block['lines']))
     return util.wrap(text, width=width,
                      initindent=indent,
                      hangindent=subindent)
 
 
 def format(text, width, indent=0, keep=None):
     """Parse and format the text according to width."""
     blocks = findblocks(text)
     for b in blocks:
         b['indent'] += indent
     blocks = findliteralblocks(blocks)
     blocks, pruned = prunecontainers(blocks, keep or [])
     blocks = findsections(blocks)
     blocks = inlineliterals(blocks)
     blocks = hgrole(blocks)
     blocks = splitparagraphs(blocks)
     blocks = updatefieldlists(blocks)
+    blocks = updateoptionlists(blocks)
     blocks = addmargins(blocks)
     blocks = prunecomments(blocks)
     blocks = findadmonitions(blocks)
     text = '\n'.join(formatblock(b, width) for b in blocks)
     if keep is None:
         return text
     else:
         return text, pruned
 
 
 if __name__ == "__main__":
     from pprint import pprint
 
     def debug(func, *args):
         blocks = func(*args)
         print "*** after %s:" % func.__name__
         pprint(blocks)
         print
         return blocks
 
     text = open(sys.argv[1]).read()
     blocks = debug(findblocks, text)
     blocks = debug(findliteralblocks, blocks)
     blocks, pruned = debug(prunecontainers, blocks, sys.argv[2:])
     blocks = debug(inlineliterals, blocks)
     blocks = debug(splitparagraphs, blocks)
     blocks = debug(updatefieldlists, blocks)
+    blocks = debug(updateoptionlists, blocks)
     blocks = debug(findsections, blocks)
     blocks = debug(addmargins, blocks)
     blocks = debug(prunecomments, blocks)
     blocks = debug(findadmonitions, blocks)
     print '\n'.join(formatblock(b, 30) for b in blocks)

tests/test-convert.t

@@ -1,392 +1,392 b''
 
   $ cat >> $HGRCPATH <<EOF
   > [extensions]
   > convert=
   > [convert]
   > hg.saverev=False
   > EOF
   $ hg help convert
   hg convert [OPTION]... SOURCE [DEST [REVMAP]]
   
   convert a foreign SCM repository to a Mercurial one.
   
       Accepted source formats [identifiers]:
   
       - Mercurial [hg]
       - CVS [cvs]
       - Darcs [darcs]
       - git [git]
       - Subversion [svn]
       - Monotone [mtn]
       - GNU Arch [gnuarch]
       - Bazaar [bzr]
       - Perforce [p4]
   
       Accepted destination formats [identifiers]:
   
       - Mercurial [hg]
       - Subversion [svn] (history on branches is not preserved)
   
       If no revision is given, all revisions will be converted. Otherwise,
       convert will only import up to the named revision (given in a format
       understood by the source).
   
       If no destination directory name is specified, it defaults to the basename
       of the source with "-hg" appended. If the destination repository doesn't
       exist, it will be created.
   
       By default, all sources except Mercurial will use --branchsort. Mercurial
       uses --sourcesort to preserve original revision numbers order. Sort modes
       have the following effects:
   
       --branchsort  convert from parent to child revision when possible, which
-                    means branches are usually converted one after the other. It
-                    generates more compact repositories.
+                    means branches are usually converted one after the other.
+                    It generates more compact repositories.
       --datesort    sort revisions by date. Converted repositories have good-
                     looking changelogs but are often an order of magnitude
                     larger than the same ones generated by --branchsort.
       --sourcesort  try to preserve source revisions order, only supported by
                     Mercurial sources.
   
       If "REVMAP" isn't given, it will be put in a default location
       ("<dest>/.hg/shamap" by default). The "REVMAP" is a simple text file that
       maps each source commit ID to the destination ID for that revision, like
       so:
   
         <source ID> <destination ID>
   
       If the file doesn't exist, it's automatically created. It's updated on
       each commit copied, so "hg convert" can be interrupted and can be run
       repeatedly to copy new commits.
   
       The authormap is a simple text file that maps each source commit author to
       a destination commit author. It is handy for source SCMs that use unix
       logins to identify authors (eg: CVS). One line per author mapping and the
       line format is:
   
         source author = destination author
   
       Empty lines and lines starting with a "#" are ignored.
   
       The filemap is a file that allows filtering and remapping of files and
       directories. Each line can contain one of the following directives:
   
         include path/to/file-or-dir
   
         exclude path/to/file-or-dir
   
         rename path/to/source path/to/destination
   
       Comment lines start with "#". A specified path matches if it equals the
       full relative name of a file or one of its parent directories. The
       "include" or "exclude" directive with the longest matching path applies,
       so line order does not matter.
   
       The "include" directive causes a file, or all files under a directory, to
       be included in the destination repository, and the exclusion of all other
       files and directories not explicitly included. The "exclude" directive
       causes files or directories to be omitted. The "rename" directive renames
       a file or directory if it is converted. To rename from a subdirectory into
       the root of the repository, use "." as the path to rename to.
   
       The splicemap is a file that allows insertion of synthetic history,
       letting you specify the parents of a revision. This is useful if you want
       to e.g. give a Subversion merge two parents, or graft two disconnected
       series of history together. Each entry contains a key, followed by a
       space, followed by one or two comma-separated values:
   
         key parent1, parent2
   
       The key is the revision ID in the source revision control system whose
       parents should be modified (same format as a key in .hg/shamap). The
       values are the revision IDs (in either the source or destination revision
       control system) that should be used as the new parents for that node. For
       example, if you have merged "release-1.0" into "trunk", then you should
       specify the revision on "trunk" as the first parent and the one on the
       "release-1.0" branch as the second.
   
       The branchmap is a file that allows you to rename a branch when it is
       being brought in from whatever external repository. When used in
       conjunction with a splicemap, it allows for a powerful combination to help
       fix even the most badly mismanaged repositories and turn them into nicely
       structured Mercurial repositories. The branchmap contains lines of the
       form:
   
         original_branch_name new_branch_name
   
       where "original_branch_name" is the name of the branch in the source
       repository, and "new_branch_name" is the name of the branch is the
       destination repository. No whitespace is allowed in the branch names. This
       can be used to (for instance) move code in one repository from "default"
       to a named branch.
   
       Mercurial Source
       ''''''''''''''''
   
       The Mercurial source recognizes the following configuration options, which
       you can set on the command line with "--config":
   
       convert.hg.ignoreerrors
                   ignore integrity errors when reading. Use it to fix Mercurial
                   repositories with missing revlogs, by converting from and to
                   Mercurial. Default is False.
       convert.hg.saverev
                   store original. revision ID in changeset (forces target IDs to
                   change). It takes and boolean argument and defaults to False.
       convert.hg.startrev
                   convert start revision and its descendants. It takes a hg
                   revision identifier and defaults to 0.
   
       CVS Source
       ''''''''''
   
       CVS source will use a sandbox (i.e. a checked-out copy) from CVS to
       indicate the starting point of what will be converted. Direct access to
       the repository files is not needed, unless of course the repository is
       ":local:". The conversion uses the top level directory in the sandbox to
       find the CVS repository, and then uses CVS rlog commands to find files to
       convert. This means that unless a filemap is given, all files under the
       starting directory will be converted, and that any directory
       reorganization in the CVS sandbox is ignored.
   
       The following options can be used with "--config":
   
       convert.cvsps.cache
                   Set to False to disable remote log caching, for testing and
                   debugging purposes. Default is True.
       convert.cvsps.fuzz
                   Specify the maximum time (in seconds) that is allowed between
                   commits with identical user and log message in a single
                   changeset. When very large files were checked in as part of a
                   changeset then the default may not be long enough. The default
                   is 60.
       convert.cvsps.mergeto
                   Specify a regular expression to which commit log messages are
                   matched. If a match occurs, then the conversion process will
                   insert a dummy revision merging the branch on which this log
                   message occurs to the branch indicated in the regex. Default
                   is "{{mergetobranch ([-\w]+)}}"
       convert.cvsps.mergefrom
                   Specify a regular expression to which commit log messages are
                   matched. If a match occurs, then the conversion process will
                   add the most recent revision on the branch indicated in the
                   regex as the second parent of the changeset. Default is
                   "{{mergefrombranch ([-\w]+)}}"
       hook.cvslog
                   Specify a Python function to be called at the end of gathering
                   the CVS log. The function is passed a list with the log
                   entries, and can modify the entries in-place, or add or delete
                   them.
       hook.cvschangesets
                   Specify a Python function to be called after the changesets
                   are calculated from the the CVS log. The function is passed a
                   list with the changeset entries, and can modify the changesets
                   in-place, or add or delete them.
   
       An additional "debugcvsps" Mercurial command allows the builtin changeset
       merging code to be run without doing a conversion. Its parameters and
       output are similar to that of cvsps 2.1. Please see the command help for
       more details.
   
       Subversion Source
       '''''''''''''''''
   
       Subversion source detects classical trunk/branches/tags layouts. By
       default, the supplied "svn://repo/path/" source URL is converted as a
       single branch. If "svn://repo/path/trunk" exists it replaces the default
       branch. If "svn://repo/path/branches" exists, its subdirectories are
       listed as possible branches. If "svn://repo/path/tags" exists, it is
       looked for tags referencing converted branches. Default "trunk",
       "branches" and "tags" values can be overridden with following options. Set
       them to paths relative to the source URL, or leave them blank to disable
       auto detection.
   
       The following options can be set with "--config":
   
       convert.svn.branches
                   specify the directory containing branches. The defaults is
                   "branches".
       convert.svn.tags
                   specify the directory containing tags. The default is "tags".
       convert.svn.trunk
                   specify the name of the trunk branch The defauls is "trunk".
   
       Source history can be retrieved starting at a specific revision, instead
       of being integrally converted. Only single branch conversions are
       supported.
   
       convert.svn.startrev
                   specify start Subversion revision number. The default is 0.
   
       Perforce Source
       '''''''''''''''
   
       The Perforce (P4) importer can be given a p4 depot path or a client
       specification as source. It will convert all files in the source to a flat
       Mercurial repository, ignoring labels, branches and integrations. Note
       that when a depot path is given you then usually should specify a target
       directory, because otherwise the target may be named "...-hg".
   
       It is possible to limit the amount of source history to be converted by
       specifying an initial Perforce revision:
   
       convert.p4.startrev
                   specify initial Perforce revision, a Perforce changelist
                   number).
   
       Mercurial Destination
       '''''''''''''''''''''
   
       The following options are supported:
   
       convert.hg.clonebranches
                   dispatch source branches in separate clones. The default is
                   False.
       convert.hg.tagsbranch
                   branch name for tag revisions, defaults to "default".
       convert.hg.usebranchnames
                   preserve branch names. The default is True
   
   options:
   
    -s --source-type TYPE  source repository type
    -d --dest-type TYPE    destination repository type
    -r --rev REV           import up to target revision REV
    -A --authormap FILE    remap usernames using this file
       --filemap FILE      remap file names using contents of file
       --splicemap FILE    splice synthesized history into place
       --branchmap FILE    change branch names while converting
       --branchsort        try to sort changesets by branches
       --datesort          try to sort changesets by date
       --sourcesort        preserve source changesets order
   
   use "hg -v help convert" to show global options
   $ hg init a
   $ cd a
   $ echo a > a
   $ hg ci -d'0 0' -Ama
   adding a
   $ hg cp a b
   $ hg ci -d'1 0' -mb
   $ hg rm a
   $ hg ci -d'2 0' -mc
   $ hg mv b a
   $ hg ci -d'3 0' -md
   $ echo a >> a
   $ hg ci -d'4 0' -me
   $ cd ..
   $ hg convert a 2>&1 | grep -v 'subversion python bindings could not be loaded'
   assuming destination a-hg
   initializing destination a-hg repository
   scanning source...
   sorting...
   converting...
   4 a
   3 b
   2 c
   1 d
   0 e
   $ hg --cwd a-hg pull ../a
   pulling from ../a
   searching for changes
   no changes found
   $ touch bogusfile
 
 should fail
 
   $ hg convert a bogusfile
   initializing destination bogusfile repository
   abort: cannot create new bundle repository
   [255]
   $ mkdir bogusdir
   $ chmod 000 bogusdir
 
 should fail
 
   $ hg convert a bogusdir
   abort: Permission denied: bogusdir
   [255]
 
 should succeed
 
   $ chmod 700 bogusdir
   $ hg convert a bogusdir
   initializing destination bogusdir repository
   scanning source...
   sorting...
   converting...
   4 a
   3 b
   2 c
   1 d
   0 e
 
 test pre and post conversion actions
 
   $ echo 'include b' > filemap
   $ hg convert --debug --filemap filemap a partialb | \
   >     grep 'run hg'
   run hg source pre-conversion action
   run hg sink pre-conversion action
   run hg sink post-conversion action
   run hg source post-conversion action
 
 converting empty dir should fail "nicely
 
   $ mkdir emptydir
 
 override $PATH to ensure p4 not visible; use $PYTHON in case we're
 running from a devel copy, not a temp installation
 
   $ PATH="$BINDIR" $PYTHON "$BINDIR"/hg convert emptydir
   assuming destination emptydir-hg
   initializing destination emptydir-hg repository
   emptydir does not look like a CVS checkout
   emptydir does not look like a Git repository
   emptydir does not look like a Subversion repository
   emptydir is not a local Mercurial repository
   emptydir does not look like a darcs repository
   emptydir does not look like a monotone repository
   emptydir does not look like a GNU Arch repository
   emptydir does not look like a Bazaar repository
   cannot find required "p4" tool
   abort: emptydir: missing or unsupported repository
   [255]
 
 convert with imaginary source type
 
   $ hg convert --source-type foo a a-foo
   initializing destination a-foo repository
   abort: foo: invalid source repository type
   [255]
 
 convert with imaginary sink type
 
   $ hg convert --dest-type foo a a-foo
   abort: foo: invalid destination repository type
   [255]
 
 testing: convert must not produce duplicate entries in fncache
 
   $ hg convert a b
   initializing destination b repository
   scanning source...
   sorting...
   converting...
   4 a
   3 b
   2 c
   1 d
   0 e
 
 contents of fncache file:
 
   $ cat b/.hg/store/fncache
   data/a.i
   data/b.i
 
 test bogus URL
 
   $ hg convert -q bzr+ssh://[e-mail]/baz baz
   abort: bzr+ssh://[e-mail]/baz: missing or unsupported repository
   [255]

tests/test-minirst.py

@@ -1,230 +1,233 b''
 from pprint import pprint
 from mercurial import minirst
 
 def debugformat(title, text, width, **kwargs):
     print "%s formatted to fit within %d characters:" % (title, width)
     print "-" * 70
     formatted = minirst.format(text, width, **kwargs)
     if type(formatted) == tuple:
         print formatted[0]
         print "-" * 70
         pprint(formatted[1])
     else:
         print formatted
     print "-" * 70
     print
 
 paragraphs = """
 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.
 """
 
 debugformat('paragraphs', paragraphs, 60)
 debugformat('paragraphs', paragraphs, 30)
 
 
 definitions = """
 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.
 """
 
 debugformat('definitions', definitions, 60)
 debugformat('definitions', definitions, 30)
 
 
 literals = r"""
 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.
 """
 
 debugformat('literals', literals, 60)
 debugformat('literals', literals, 30)
 
 
 lists = """
 - 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.
 """
 
 debugformat('lists', lists, 60)
 debugformat('lists', lists, 30)
 
 
 options = """
 There is support for simple option lists,
 but only with long options:
 
---all      Output all.
---both     Output both (this description is
-           quite long).
---long     Output all day long.
+-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.
+--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).
+                      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
 """
 
 debugformat('options', options, 60)
 debugformat('options', options, 30)
 
 
 fields = """
 :a: First item.
 :ab: Second item. Indentation and wrapping
      is handled automatically.
 
 Next list:
 
 :small: The larger key below triggers full indentation here.
 :much too large: This key is big enough to get its own line.
 """
 
 debugformat('fields', fields, 60)
 debugformat('fields', fields, 30)
 
 containers = """
 Normal output.
 
 .. container:: debug
 
    Initial debug output.
 
 .. container:: verbose
 
    Verbose output.
 
    .. container:: debug
 
       Debug output.
 """
 
 debugformat('containers (normal)', containers, 60)
 debugformat('containers (verbose)', containers, 60, keep=['verbose'])
 debugformat('containers (debug)', containers, 60, keep=['debug'])
 debugformat('containers (verbose debug)', containers, 60,
             keep=['verbose', 'debug'])
 
 roles = """Please see :hg:`add`."""
 debugformat('roles', roles, 60)
 
 
 sections = """
 Title
 =====
 
 Section
 -------
 
 Subsection
 ''''''''''
 
 Markup: ``foo`` and :hg:`help`
 ------------------------------
 """
 debugformat('sections', sections, 20)
 
 
 admonitions = """
 .. note::
    This is a note
 
    - Bullet 1
    - Bullet 2
 
    .. warning:: This is a warning Second
       input line of warning
 
 .. danger::
    This is danger
 """
 
 debugformat('admonitions', admonitions, 30)
 
 comments = """
 Some text.
 
 .. A comment
 
    .. An indented comment
 
    Some indented text.
 
 ..
 
 Empty comment above
 """
 
 debugformat('comments', comments, 30)

tests/test-minirst.py.out

@@ -1,345 +1,390 b''
 paragraphs formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 This is some text in the first paragraph.
 
   A small indented paragraph. It is followed by some lines
   containing random whitespace.
 
 The third and final paragraph.
 ----------------------------------------------------------------------
 
 paragraphs formatted to fit within 30 characters:
 ----------------------------------------------------------------------
 This is some text in the first
 paragraph.
 
   A small indented paragraph.
   It is followed by some lines
   containing random
   whitespace.
 
 The third and final paragraph.
 ----------------------------------------------------------------------
 
 definitions formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 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.
 ----------------------------------------------------------------------
 
 definitions formatted to fit within 30 characters:
 ----------------------------------------------------------------------
 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.
 ----------------------------------------------------------------------
 
 literals formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 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.
 ----------------------------------------------------------------------
 
 literals formatted to fit within 30 characters:
 ----------------------------------------------------------------------
 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.
 ----------------------------------------------------------------------
 
 lists formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 - 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.
 ----------------------------------------------------------------------
 
 lists formatted to fit within 30 characters:
 ----------------------------------------------------------------------
 - 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.
 ----------------------------------------------------------------------
 
 options formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 There is support for simple option lists, but only with long
 options:
 
---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.
+ -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).
+                      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
 ----------------------------------------------------------------------
 
 options formatted to fit within 30 characters:
 ----------------------------------------------------------------------
 There is support for simple
 option lists, but only with
 long options:
 
---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.
+ -X --exclude filter  an
+                      option
+                      with a
+                      short
+                      and
+                      long
+                      option
+                      with an
+                      argumen
+                      t
+ -I --include         an
+                      option
+                      with
+                      both a
+                      short
+                      option
+                      and a
+                      long
+                      option
+    --all             Output
+                      all.
+    --both            Output
+                      both
+                      (this d
+                      escript
+                      ion is
+                      quite
+                      long).
+    --long            Output
+                      all day
+                      long.
+    --par             This
+                      option
+                      has two
+                      paragra
+                      phs in
+                      its des
+                      criptio
+                      n. This
+                      is the
+                      first.
 
-           This is the second.
-           Blank lines may be
-           omitted between
-           options (as above)
-           or left in (as
-           here).
+                      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
 ----------------------------------------------------------------------
 
 fields formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 a   First item.
 ab  Second item. Indentation and wrapping is handled
     automatically.
 
 Next list:
 
 small       The larger key below triggers full indentation
             here.
 much too large
             This key is big enough to get its own line.
 ----------------------------------------------------------------------
 
 fields formatted to fit within 30 characters:
 ----------------------------------------------------------------------
 a   First item.
 ab  Second item. Indentation
     and wrapping is handled
     automatically.
 
 Next list:
 
 small       The larger key
             below triggers
             full indentation
             here.
 much too large
             This key is big
             enough to get its
             own line.
 ----------------------------------------------------------------------
 
 containers (normal) formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 Normal output.
 ----------------------------------------------------------------------
 
 containers (verbose) formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 Normal output.
 
 Verbose output.
 ----------------------------------------------------------------------
 ['debug', 'debug']
 ----------------------------------------------------------------------
 
 containers (debug) formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 Normal output.
 
 Initial debug output.
 ----------------------------------------------------------------------
 ['verbose']
 ----------------------------------------------------------------------
 
 containers (verbose debug) formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 Normal output.
 
 Initial debug output.
 
 Verbose output.
 
 Debug output.
 ----------------------------------------------------------------------
 []
 ----------------------------------------------------------------------
 
 roles formatted to fit within 60 characters:
 ----------------------------------------------------------------------
 Please see "hg add".
 ----------------------------------------------------------------------
 
 sections formatted to fit within 20 characters:
 ----------------------------------------------------------------------
 Title
 =====
 
 Section
 -------
 
 Subsection
 ''''''''''
 
 Markup: "foo" and "hg help"
 ---------------------------
 ----------------------------------------------------------------------
 
 admonitions formatted to fit within 30 characters:
 ----------------------------------------------------------------------
 Note:
    This is a note
 
    - Bullet 1
    - Bullet 2
 
    Warning!
       This is a warning Second
       input line of warning
 
 !Danger!
    This is danger
 ----------------------------------------------------------------------
 
 comments formatted to fit within 30 characters:
 ----------------------------------------------------------------------
 Some text.
 
    Some indented text.
 
 Empty comment above
 ----------------------------------------------------------------------