[PATCH v2] regexp-replace and ^, word boundary or look-behind operators

[Stephane Chazelas <stephane.chazelas@xxxxxxxxx>]

2019-12-18 00:22:53 +0000, Daniel Shahaf:
[...]
> > +
> > +Note that if not using PCRE, using the tt(^) or word boundary operators
> > +(where available) may not work properly.
> 
> Suggest to avoid the double negative:
> 
> 1. s/not using PCRE/using POSIX ERE's/
> 
> 2. Add "(ERE's)" after "POSIX extended regular expressions" in the first paragraph
> 
> I'll push a minor change to that first paragraph in a moment.
[...]

Thanks, I've incorporated that suggesting and fixed an issue
with PCRE when the replacement was empty or generated more than
one element.

diff --git a/Doc/Zsh/contrib.yo b/Doc/Zsh/contrib.yo
index 558342711..9a804fc11 100644
--- a/Doc/Zsh/contrib.yo
+++ b/Doc/Zsh/contrib.yo
@@ -4284,7 +4284,7 @@ See also the tt(pager), tt(prompt) and tt(rprompt) styles below.
 findex(regexp-replace)
 item(tt(regexp-replace) var(var) var(regexp) var(replace))(
 Use regular expressions to perform a global search and replace operation
-on a variable.  POSIX extended regular expressions are used,
+on a variable.  POSIX extended regular expressions (ERE) are used,
 unless the option tt(RE_MATCH_PCRE) has been set, in which case
 Perl-compatible regular expressions are used
 (this requires the shell to be linked against the tt(pcre)
@@ -4302,6 +4302,9 @@ and arithmetic expressions which will be replaced:  in particular, a
 reference to tt($MATCH) will be replaced by the text matched by the pattern.
 
 The return status is 0 if at least one match was performed, else 1.
+
+Note that if using POSIX EREs, the tt(^) or word boundary operators
+(where available) may not work properly.
 )
 findex(run-help)
 item(tt(run-help) var(cmd))(
diff --git a/Functions/Example/zpgrep b/Functions/Example/zpgrep
index 8b1edaa1c..556e58cd6 100644
--- a/Functions/Example/zpgrep
+++ b/Functions/Example/zpgrep
@@ -2,24 +2,31 @@
 #
 
 zpgrep() {
-local file pattern
+local file pattern ret
 
 pattern=$1
 shift
+ret=1
 
 if ((! ARGC)) then
 	set -- -
 fi
 
-pcre_compile $pattern
+zmodload zsh/pcre || return
+pcre_compile -- "$pattern"
 pcre_study
 
 for file
 do
 	if [[ "$file" == - ]] then
-		while read -u0 buf; do pcre_match $buf && print $buf; done
+		while IFS= read -ru0 buf; do
+			pcre_match -- "$buf" && ret=0 && print -r -- "$buf"
+		done
 	else
-		while read -u0 buf; do pcre_match $buf && print $buf; done < "$file"
+		while IFS= read -ru0 buf; do
+			pcre_match -- "$buf" && ret=0 && print -r -- "$buf"
+		done < "$file"
 	fi
 done
+return "$ret"
 }
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
-
-eval ${1}=${(q)5}
-# status 0 if we did something, else 1.
-[[ -n $6 ]]
+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 $IFS as usual)
+    5=${(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