1
0
Fork 0
mirror of git://git.code.sf.net/p/zsh/code synced 2024-05-13 11:06:17 +02:00
zsh/Functions/Misc/regexp-replace
2021-11-12 23:54:34 +01:00

92 lines
2.4 KiB
Plaintext

# Replace all occurrences of a regular expression in a variable. The
# variable is modified directly. Respects the setting of the
# option RE_MATCH_PCRE.
#
# First argument: *name* (not contents) of variable.
# Second argument: regular expression
# Third argument: replacement string. This can contain all forms of
# $ and backtick substitutions; in particular, $MATCH will be replaced
# by the portion of the string matched by the regular expression.
# we use positional parameters instead of variables to avoid
# clashing with the user's variable. Make sure we start with 3 and only
# 3 elements:
argv=("$1" "$2" "$3")
# $4 records whether pcre is enabled as that information would otherwise
# be lost after emulate -L zsh
4=0
[[ -o re_match_pcre ]] && 4=1
emulate -L zsh
local MATCH MBEGIN MEND
local -a match mbegin mend
if (( $4 )); then
# if using pcre, we're using pcre_match and a running offset
# That's needed for ^, \A, \b, and look-behind operators to work
# properly.
zmodload zsh/pcre || return 2
pcre_compile -- "$2" && pcre_study || return 2
# $4 is the current *byte* offset, $5, $6 reserved for later use
4=0 6=
local ZPCRE_OP
while pcre_match -b -n $4 -- "${(P)1}"; do
# append offsets and computed replacement to the array
# we need to perform the evaluation in a scalar assignment so that if
# it generates an array, the elements are converted to string (by
# joining with the first character of $IFS as usual)
5=${(e)3}
argv+=(${(s: :)ZPCRE_OP} "$5")
# for 0-width matches, increase offset by 1 to avoid
# infinite loop
4=$((argv[-2] + (argv[-3] == argv[-2])))
done
(($# > 6)) || return # no match
set +o multibyte
# $5 contains the result, $6 the current offset
5= 6=1
for 2 3 4 in "$@[7,-1]"; do
5+=${(P)1[$6,$2]}$4
6=$(($3 + 1))
done
5+=${(P)1[$6,-1]}
else
# in ERE, we can't use an offset so ^, (and \<, \b, \B, [[:<:]] where
# available) won't work properly.
# $4 is the string to be matched
4=${(P)1}
while [[ -n $4 ]]; do
if [[ $4 =~ $2 ]]; then
# append initial part and substituted match
5+=${4[1,MBEGIN-1]}${(e)3}
# truncate remaining string
if ((MEND < MBEGIN)); then
# zero-width match, skip one character for the next match
((MEND++))
5+=${4[1]}
fi
4=${4[MEND+1,-1]}
# indicate we did something
6=1
else
break
fi
done
[[ -n $6 ]] || return # no match
5+=$4
fi
eval $1=\$5