view contrib/plan9/9diff @ 42919:6ccf539aec71

hgweb: fix websub regex flag syntax on Python 3

The `websub` config section for hgweb is broken under Python 3
when using regex flags syntax (ie the optional `i` in the example
from `hg help config.websub`:

    patternname = s/SEARCH_REGEX/REPLACE_EXPRESSION/[i]

Flags are pulled out of the specified byte-string using a regular
expression, and uppercased. The flags are then iterated over and
passed to the `re` module using `re.__dict__[item]`, to get the
object attribute of the same name from the `re` module. So on Python
2 if the `il` flags are passed, this transition looks like:

    `'il'` -> `'IL'` -> `'I'` -> `re.__dict__['I']` -> `re.I`

However on Python 3, these are bytes objects. When we iterate over
a bytes object in Python 3, instead of getting the individual characters
in the string as string objects of length one, we get the integer \
value corresponding to that byte. So the same transition looks like:

    `b'il'` -> `b'IL'` -> `73` -> `re.__dict__[73]` -> `KeyError`

This commit fixes the type mismatch by converting the bytes to a
system string before iterating over each element to pass to `re`.
The transition will now look like:

    `b'il'` -> `u'IL'` -> `u'I'` -> `re.__dict__[u'I']` -> `re.I`

In addition we expand `test-websub.t` to cover the regex flag case
(for both the `websub` section and `interhg`).

Differential Revision: https://phab.mercurial-scm.org/D6788

#!/bin/rc
# 9diff - Mercurial extdiff wrapper for diff(1)

rfork e

fn getfiles {
	cd $1 &&
	for(f in `{du -as | awk '{print $2}'})
		test -f $f && echo `{cleanname $f}
}

fn usage {
	echo >[1=2] usage: 9diff [diff options] parent child root
	exit usage
}

opts=()
while(~ $1 -*){
	opts=($opts $1)
	shift
}
if(! ~ $#* 3)
	usage

# extdiff will set the parent and child to a single file if there is
# only one change. If there are multiple changes, directories will be
# set. diff(1) does not cope particularly with directories; instead we
# do the recursion ourselves and diff each file individually.
if(test -f $1)
	diff $opts $1 $2
if not{
	# extdiff will create a snapshot of the working copy to prevent
	# conflicts during the diff. We circumvent this behavior by
	# diffing against the repository root to produce plumbable
	# output. This is antisocial.
	for(f in `{sort -u <{getfiles $1} <{getfiles $2}}){
		file1=$1/$f; test -f $file1 || file1=/dev/null
		file2=$3/$f; test -f $file2 || file2=/dev/null
		diff $opts $file1 $file2
	}
}
exit ''