X-Git-Url: https://git.plutz.net/?a=blobdiff_plain;f=macros%2Fsearch;fp=macros%2Fsearch;h=b3d06e85a86fbc33274b48b298b4af9b926bd48b;hb=20c6ce6a3de621383d1b6d985757366590722005;hp=0000000000000000000000000000000000000000;hpb=3260c24fcce2db7d0b0eb98234c5ba385c6f55a9;p=shellwiki

diff --git a/macros/search b/macros/search
new file mode 100755
index 0000000..b3d06e8
--- /dev/null
+++ b/macros/search
@@ -0,0 +1,148 @@
+#!/bin/sh
+
+# Copyright 2023, 2024 Paul Hänsch
+# 
+# Permission to use, copy, modify, and/or distribute this software for any
+# purpose with or without fee is hereby granted, provided that the above
+# copyright notice and this permission notice appear in all copies.
+# 
+# THE SOFTWARE IS PROVIDED “AS IS” AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+# WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+# MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+# SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+# WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
+# ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR
+# IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+
+I="$_DATA/index"
+
+. "$_EXEC/cgilite/cgilite.sh"
+. "$_EXEC/cgilite/storage.sh"
+. "$_EXEC/cgilite/db23.sh"
+. "$_EXEC/tools.sh"
+. "$_EXEC/acl.sh"
+
+_(){ printf %s\\n "$*"; }
+[ "${LANGUAGE}" -a -r "${_EXEC}/l10n/${LANGUAGE}.sh" ] && . "${_EXEC}/l10n/${LANGUAGE}.sh"
+
+show_form=true show_hits='' action=''
+
+set -- "$@" --
+while [ $# -gt 0 ]; do case $1 in
+  --no-form|--noform)
+    show_form=''; shift 1;;
+  --hits|--results)
+    show_hits='true'; shift 1;;
+  --action)
+    action="$(HTML "$2")"; shift 2;;
+  --action=*|action=*)
+    action="$(HTML "${2#*=}")"; shift 1;;
+  --) shift 1; break;;
+  *) set -- "$@" "$1"; shift 1;;
+esac; done
+
+searchteaser() {
+  local file="$1" words db3_data
+  local w l nc nl hits mhits cont mcont
+  shift 1; words="$*"
+
+  for w in ${words}; do
+    grep -hiwnF "$w" "$file"
+  done \
+  | sort -t: -k1 -n \
+  | { nc=-1 hits=0 mhits=0
+    while read -r l; do
+      nl="$nc" nc="${l%%:*}"
+      if [ $nc -eq $nl ]; then
+        hits=$((hits + 1))
+      elif [ $nc -eq $((nl + 1 )) ]; then
+        hits=$((hits + 1))
+        cont="${cont}${BR}${l#*:}"
+      elif [ $hits -gt $mhits ]; then
+        mhits="$hits" mcont="$cont"
+        hits=1 cont="${l#*:}"
+      else
+        hits=1 cont="${l#*:}"
+      fi
+    done
+
+    [ $hits -gt $mhits ] \
+    && STRING "$cont" \
+    || STRING "$mcont"
+  }
+}
+
+if [ ! "$action" -a "$LANGUAGE_DEFAULT" ]; then
+  action="./:${LANGUAGE}/[search]"
+elif [ ! "$action" ]; then
+  action="./[search]"
+fi
+
+if [ "${show_form}" = true ]; then
+  printf '<form class="macro search" method="GET" action="%s">
+  <input type="search" placeholder="%s" name="q" value="%s"><button type="submit" class="search">%s</button>
+</form>' "$action" "$(_ Search)" "$([ "$show_hits" = true ] && GET q |HTML)" "$(_ Search)"
+fi
+
+if [ "${show_hits}" = true ]; then
+  { read tags; read ntags; read words; } <<-EOF
+	$(GET q | awk '
+	BEGIN { # Field separator FS should include punctuation, including Unicode Block U+2000 - U+206F
+	        if ( length("¡") == 1 )  # Utf-8 aware AWK
+	        FS = "([] \\t\\n\\r\"'\''()*+,./:;<=>?\\\\^_`{|}~[-]|%[0-9A-Fa-f]{2}|'"$(printf '[\342\200\200-\342\201\257]')"')+";
+	        else                     # UTF-8 Hack
+	        FS = "([] \\t\\n\\r\"'\''()*+,./:;<=>?\\\\^_`{|}~[-]|%[0-9A-Fa-f]{2}|'"$(printf '\342\200[\200-\277]|\342\201[\201-\257]')"')+";
+	        fi
+	      }
+	{ t=0; for (n = 1; n <= NF; n++) if ($n  ~ /#[[:alnum:]_]+/)  tags[t++] = toupper($n);
+	  t=0; for (n = 1; n <= NF; n++) if ($n  ~ /![[:alnum:]_]+/) ntags[t++] = toupper($n);
+	  t=0; for (n = 1; n <= NF; n++) if ($n !~ /![[:alnum:]_]+/) words[t++] = tolower($n);
+	  for (t in  tags) { sub(/^#/, "",  tags[t]); printf "%s	",  tags[t]; } print "";
+	  for (t in ntags) { sub(/^!/, "", ntags[t]); printf "%s	", ntags[t]; } print "";
+	  for (t in words) { sub(/^[!#]/, "", words[t]); printf "%s	", words[t]; } print "";
+	}
+	')
+	EOF
+
+  printf '<ul class="macro search hits">'
+  for w in ${words}; do
+    [ ! -f "$I/$w" ] && continue
+  
+    while read date doc freq num total; do
+      P="$_DATA/pages$(UNSTRING "$doc")"
+      d="$(stat -c %Y -- "$P/#index.flag" 2>&-)"
+      [ "$d" -le "$date" -a -f "$P/#page.md" ] 2>&- || continue
+  
+      printf '%s	%f\n' "$doc" "$freq"
+    done <"$I/$w"
+  done \
+  | awk '
+        { cnt[$1]++; weight[$1] = weight[$1] ? weight[$1] + $2 : $2; }
+    END { m = 0; for (d in cnt) m = ( m < cnt[d] ) ? cnt[d] : m;
+          for (d in cnt) if ( cnt[d] == m ) printf "%f	%s\n", weight[d], d;
+        }
+  ' \
+  | sort -nr \
+  | while read freq doc; do
+    page="$(UNSTRING "$doc")"
+    [ "${page%*/\[*\]/*}" != "$page" ] && continue
+    if [ "$LANGUAGE_DEFAULT" ]; then
+      [ -d "${_DATA}/pages/${page}/:${LANGUAGE}/" ] && continue
+      [ "${page%/:*/}" = "${page%/:${LANGUAGE}/}" ] || continue
+    fi
+    acl_read "$page" || continue
+    has_tags "$page" $tags || continue
+    has_tag "$page" $ntags && continue
+    printf '%s	%s\n' "$doc" "$(searchteaser "$(mdfile "$page")" $words)"
+  done \
+  | while read -r p t; do
+    path="$(UNSTRING "$p")" pfrag="${path%/}" title=''
+    while [ "$pfrag" ]; do
+      title="$(page_title "$pfrag")/$title"
+      pfrag="${pfrag%/*}"
+    done
+    printf '<li><a href="%s">%s</a><p>%s</p></li>' \
+      "$(URL "$path")" "$(HTML "/$title")" "$(UNSTRING "$t" |HTML)"
+  done
+  printf '</ul>'
+fi