contrib/hgfixes/fix_bytes.py
author FUJIWARA Katsunori <foozy@lares.dti.ne.jp>
Wed, 25 Jul 2012 16:40:38 +0900
branchstable
changeset 17267 979b107eaea2
parent 11748 37a70a784397
child 17299 e51d4aedace9
permissions -rw-r--r--
doc: unify section level between help topics Some help topics use "-" for the top level underlining section mark, but "-" is used also for the top level categorization in generated documents: "hg.1.html", for example. So, TOC in such documents contain "sections in each topics", too. This patch changes underlining section mark in some help topics to unify section level in generated documents. After this patching, levels of each section marks are: level0 """""" level1 ====== level2 ------ level3 ...... level4 ###### And use of section markers in each documents are: - mercurial/help/*.txt can use level1 or more (now these use level1 and level2) - help for core commands can use level2 or more (now these use no section marker) - descriptions of extensions can use level2 or more (now hgext/acl uses level2) - help for commands defined in extension can use level4 or more (now "convert" of hgext/convert uses level4) "Level0" is used as top level categorization only in "doc/hg.1.txt" and the intermediate file generated by "doc/gendoc.py", so end users don't see it in "hg help" outoput and so on.

"""Fixer that changes plain strings to bytes strings."""

import re

from lib2to3 import fixer_base
from lib2to3.pgen2 import token
from lib2to3.fixer_util import Name
from lib2to3.pygram import python_symbols as syms

_re = re.compile(r'[rR]?[\'\"]')

# XXX: Implementing a blacklist in 2to3 turned out to be more troublesome than
# blacklisting some modules inside the fixers. So, this is what I came with.

blacklist = ['mercurial/demandimport.py',
             'mercurial/py3kcompat.py', # valid python 3 already
             'mercurial/i18n.py',
            ]

def isdocstring(node):
    def isclassorfunction(ancestor):
        symbols = (syms.funcdef, syms.classdef)
        # if the current node is a child of a function definition, a class
        # definition or a file, then it is a docstring
        if ancestor.type == syms.simple_stmt:
            try:
                while True:
                    if ancestor.type in symbols:
                        return True
                    ancestor = ancestor.parent
            except AttributeError:
                return False
        return False

    def ismodule(ancestor):
        # Our child is a docstring if we are a simple statement, and our
        # ancestor is file_input. In other words, our child is a lone string in
        # the source file.
        try:
            if (ancestor.type == syms.simple_stmt and
                ancestor.parent.type == syms.file_input):
                    return True
        except AttributeError:
            return False

    def isdocassignment(ancestor):
        # Assigning to __doc__, definitely a string
        try:
            while True:
                if (ancestor.type == syms.expr_stmt and
                    Name('__doc__') in ancestor.children):
                        return True
                ancestor = ancestor.parent
        except AttributeError:
            return False

    if ismodule(node.parent) or \
       isdocassignment(node.parent) or \
       isclassorfunction(node.parent):
        return True
    return False

def shouldtransform(node):
    specialnames = ['__main__']

    if node.value in specialnames:
        return False

    ggparent = node.parent.parent.parent
    sggparent = str(ggparent)

    if 'getattr' in sggparent or \
       'hasattr' in sggparent or \
       'setattr' in sggparent or \
       'encode' in sggparent or \
       'decode' in sggparent:
           return False

    return True

class FixBytes(fixer_base.BaseFix):

    PATTERN = 'STRING'

    def transform(self, node, results):
        if self.filename in blacklist:
            return
        if node.type == token.STRING:
            if _re.match(node.value):
                if isdocstring(node):
                    return
                if not shouldtransform(node):
                    return
                new = node.clone()
                new.value = 'b' + new.value
                return new