view tests/pdiff @ 50400:95acba2c29f6

encoding: avoid quadratic time complexity when json-encoding non-UTF8 strings

Apparently the code uses "+=" with a bytes object, which is linear-time, so the
whole encoding is quadratic-time. This patch makes us use a bytearray object,
instead, which has a(n amortized-)constant-time append operation.

The encoding is still not particularly fast, but at least a 10MB file
takes tens of seconds, not many hours to encode.

#!/bin/sh

# Script to get stable diff output on any platform.
#
# Output of this script is almost equivalent to GNU diff with "-Nru".
#
# Use this script as "hg pdiff" via extdiff extension with preparation
# below in test scripts:
#
#   $ cat >> $HGRCPATH <<EOF
#   > [extdiff]
#   > pdiff = sh "$RUNTESTDIR/pdiff"
#   > EOF

filediff(){
    # USAGE: filediff file1 file2 [header]

    # compare with /dev/null if file doesn't exist (as "-N" option)
    file1="$1"
    if test ! -f "$file1"; then
        file1=/dev/null
    fi
    file2="$2"
    if test ! -f "$file2"; then
        file2=/dev/null
    fi

    if cmp -s "$file1" "$file2" 2> /dev/null; then
        # Return immediately, because comparison isn't needed. This
        # also avoids redundant message of diff like "No differences
        # encountered" (on Solaris)
        return
    fi

    if test -n "$3"; then
        # show header only in recursive case
        echo "$3"
    fi

    # replace "/dev/null" by corresponded filename (as "-N" option)
    diff -u "$file1" "$file2" |
    sed "s@^--- /dev/null\(.*\)\$@--- $1\1@" |
    sed "s@^\+\+\+ /dev/null\(.*\)\$@+++ $2\1@"

    # in this case, files differ from each other
    return 1
}

if test -d "$1" -o -d "$2"; then
    # ensure comparison in dictionary order
    (
    if test -d "$1"; then (cd "$1" && find . -type f); fi
    if test -d "$2"; then (cd "$2" && find . -type f); fi
    ) |
    sed 's@^\./@@g' | sort | uniq |
    while read file; do
        filediff "$1/$file" "$2/$file" "diff -Nru $1/$file $2/$file"
    done

    # TODO: there is no portable way for current while-read based
    # implementation to return 1 at detecting changes.
    #
    # On bash and dash, assignment to variable inside while-block
    # doesn't affect outside, because inside while-block is executed
    # in sub-shell. BTW, it affects outside while-block on ksh (as sh
    # on Solaris).
else
    filediff "$1" "$2"
fi