From 9f7684f6fe7a7889d1ebaded03b446c007d605ea Mon Sep 17 00:00:00 2001
From: step <step-@users.noreply.github.com>
Date: Fri, 22 Sep 2023 10:37:34 +0200
Subject: [PATCH] [bash] History, use perl if installed otherwise awk (#3313)

While awk is POSIX, perl isn't pre-installed on all *nix flavors.
This commit eliminates the mandatory dependency on perl by using awk
when perl is not available.

Related: #3295, #3309, #3310.

Test suite passed:
* `make error` all test sections 'PASS'
* `make docker-test` 215 runs, 1884 assertions, 0 failures, 0 errors, 0 skips.

Manually tested in the following environments:
* Linux amd64 with bash 3.2, 4.4, 5.2; gawk -P, one true awk, mawk, busybox awk.
* macOS Catalina, bash 3.2, macOS awk 20070501.

**Performance comparison:**

Mawk turned out the fastest, then perl.
One true awk's implementation should be the closest to macOS awk.
Test data: 230 KB history, 15102 entries, including multi-line and duplicates.
Linux, bash 4.4. Times in milliseconds.

| Command                 | Mean | Min  | Max  | Relative |
| :---                    | ---: | ---: | ---: | -------: |
| `mawk 1.3.4`            | 22.9 | 22.3 | 25.6 | **1.00** |
| `perl 5.26.1`           | 34.3 | 33.6 | 35.1 |   1.49   |
| `one true awk 20221215` | 41.9 | 40.6 | 46.3 |   1.83   |
| `gawk 5.1.0`            | 46.1 | 44.4 | 50.3 |   2.01   |
| `busybox awk 1.27.0`    | 64.8 | 63.2 | 70.0 |   2.82   |

**Other Notes**

A bug affects bash, which fails restoring a saved multi-line history entry as a single entry. Bug fixed in version 5.0.[^1]

While developing this PR I discovered two unsubmitted issues affecting the current perl script. The output stream ends with `$'\n\0000'` instead of `$'\0000'`. Because of this, the script does not deduplicate a duplicated entry located at the end of the history list; therefore fzf displays two identical (not necessarily adjacent) entries. A minor point about the first issue is that the top fzf entry ends with a dangling line feed symbol, which is visible in the terminal.

[^1]: https://github.com/bminor/bash/blob/ec8113b9861375e4e17b3307372569d429dec814/CHANGES#L1511
  To enable: `shopt -s cmdhist lithist; HISTTIMEFORMAT='%F %T '`.
---
 shell/key-bindings.bash | 67 ++++++++++++++++++++++++++++++-----------
 1 file changed, 50 insertions(+), 17 deletions(-)

diff --git a/shell/key-bindings.bash b/shell/key-bindings.bash
index 98273b8..aa0b8ac 100644
--- a/shell/key-bindings.bash
+++ b/shell/key-bindings.bash
@@ -48,23 +48,56 @@ __fzf_cd__() {
   dir=$(set +o pipefail; eval "$cmd" | FZF_DEFAULT_OPTS="$opts" $(__fzfcmd)) && printf 'builtin cd -- %q' "$dir"
 }
 
-__fzf_history__() {
-  local output opts script
-  opts="--height ${FZF_TMUX_HEIGHT:-40%} --bind=ctrl-z:ignore ${FZF_DEFAULT_OPTS-} -n2..,.. --scheme=history --bind=ctrl-r:toggle-sort ${FZF_CTRL_R_OPTS-} +m --read0"
-  script='BEGIN { getc; $/ = "\n\t"; $HISTCOUNT = $ENV{last_hist} + 1 } s/^[ *]//; print $HISTCOUNT - $. . "\t$_" if !$seen{$_}++'
-  output=$(
-    set +o pipefail
-    builtin fc -lnr -2147483648 |
-      last_hist=$(HISTTIMEFORMAT='' builtin history 1) perl -n -l0 -e "$script" |
-      FZF_DEFAULT_OPTS="$opts" $(__fzfcmd) --query "$READLINE_LINE"
-  ) || return
-  READLINE_LINE=${output#*$'\t'}
-  if [[ -z "$READLINE_POINT" ]]; then
-    echo "$READLINE_LINE"
-  else
-    READLINE_POINT=0x7fffffff
-  fi
-}
+if command -v perl > /dev/null; then
+  __fzf_history__() {
+    local output opts script
+    opts="--height ${FZF_TMUX_HEIGHT:-40%} --bind=ctrl-z:ignore ${FZF_DEFAULT_OPTS-} -n2..,.. --scheme=history --bind=ctrl-r:toggle-sort ${FZF_CTRL_R_OPTS-} +m --read0"
+    script='BEGIN { getc; $/ = "\n\t"; $HISTCOUNT = $ENV{last_hist} + 1 } s/^[ *]//; print $HISTCOUNT - $. . "\t$_" if !$seen{$_}++'
+    output=$(
+      set +o pipefail
+      builtin fc -lnr -2147483648 |
+        last_hist=$(HISTTIMEFORMAT='' builtin history 1) perl -n -l0 -e "$script" |
+        FZF_DEFAULT_OPTS="$opts" $(__fzfcmd) --query "$READLINE_LINE"
+    ) || return
+    READLINE_LINE=${output#*$'\t'}
+    if [[ -z "$READLINE_POINT" ]]; then
+      echo "$READLINE_LINE"
+    else
+      READLINE_POINT=0x7fffffff
+    fi
+  }
+else # awk
+  __fzf_history__() {
+    local output opts script
+    if [[ -z $__fzf_awk ]]; then
+      __fzf_awk=awk
+      # if installed, mawk is faster
+      command -v mawk > /dev/null &&
+        mawk --version |          # at least 1.3.4
+          awk 'NR == 1 { split($2, a, "."); v=(a[1]*1000000+ a[2]*1000+ a[3]*1); exit !(v >= 1003004) }' &&
+          __fzf_awk=mawk
+    fi
+    opts="--height ${FZF_TMUX_HEIGHT:-40%} --bind=ctrl-z:ignore ${FZF_DEFAULT_OPTS-} -n2..,.. --scheme=history --bind=ctrl-r:toggle-sort ${FZF_CTRL_R_OPTS-} +m --read0"
+    [[ $(HISTTIMEFORMAT='' builtin history 1) =~ [[:digit:]]+ ]]    # how many history entries
+    script='function P(b) { ++n; sub(/^[ *]/, "", b); if (!seen[b]++) { printf "%d\t%s%c", '$((BASH_REMATCH + 1))' - n, b, 0 } }
+    NR==1 { b = substr($0, 2); next }
+    /^\t/ { P(b); b = substr($0, 2); next }
+    { b = b RS $0 }
+    END { if (NR) P(b) }'
+    output=$(
+      set +o pipefail
+      builtin fc -lnr -2147483648 2> /dev/null |   # ( $'\t '<lines>$'\n' )* ; <lines> ::= [^\n]* ( $'\n'<lines> )*
+        $__fzf_awk "$script"                          |   # ( <counter>$'\t'<lines>$'\000' )*
+        FZF_DEFAULT_OPTS="$opts" $(__fzfcmd) --query "$READLINE_LINE"
+    ) || return
+    READLINE_LINE=${output#*$'\t'}
+    if [[ -z "$READLINE_POINT" ]]; then
+      echo "$READLINE_LINE"
+    else
+      READLINE_POINT=0x7fffffff
+    fi
+  }
+fi
 
 # Required to refresh the prompt after fzf
 bind -m emacs-standard '"\er": redraw-current-line'