45180: clarify doc for POSIX EREs, fix an issue with PCRE when the replacement was empty or generated more than one element

1 files changed, 73 insertions, 25 deletions

diff --git a/Functions/Misc/regexp-replace b/Functions/Misc/regexp-replace
index dec105524..0d5948075 100644
--- a/Functions/Misc/regexp-replace
+++ b/Functions/Misc/regexp-replace
@@ -8,36 +8,84 @@
 # $ and backtick substitutions; in particular, $MATCH will be replaced
 # by the portion of the string matched by the regular expression.
 
-integer pcre
+# 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")
 
-[[ -o re_match_pcre ]] && pcre=1
+# $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
-(( pcre )) && setopt re_match_pcre
 
-# $4 is the string to be matched
-4=${(P)1}
-# $5 is the final string
-5=
-# 6 indicates if we made a change
-6=
+
 local MATCH MBEGIN MEND
 local -a match mbegin mend
 
-while [[ -n $4 ]]; do
-  if [[ $4 =~ $2 ]]; then
-    # append initial part and subsituted match
-    5+=${4[1,MBEGIN-1]}${(e)3}
-    # truncate remaining string
-    4=${4[MEND+1,-1]}
-    # indicate we did something
-    6=1
-  else
-    break
-  fi
-done
-5+=$4
+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 chararacter of $IFS as usual)