From b06dd8ddf1ee1df36535facc89b24c9e60f74e44 Mon Sep 17 00:00:00 2001
From: Hans <stirredaround@yahoo.com>
Date: Tue, 4 Apr 2023 17:00:55 +0200
Subject: [PATCH] Rewrite of unicode scanner and renaming of file

---
 usr/bin/grep-find-unicode-wrapper | 35 ---------------------------
 usr/bin/scan-text-file            | 39 +++++++++++++++++++++++++++++++
 2 files changed, 39 insertions(+), 35 deletions(-)
 delete mode 100755 usr/bin/grep-find-unicode-wrapper
 create mode 100755 usr/bin/scan-text-file

diff --git a/usr/bin/grep-find-unicode-wrapper b/usr/bin/grep-find-unicode-wrapper
deleted file mode 100755
index 055aa64..0000000
--- a/usr/bin/grep-find-unicode-wrapper
+++ /dev/null
@@ -1,35 +0,0 @@
-#!/bin/bash
-
-## Copyright (C) 2022 - 2022 ENCRYPTED SUPPORT LP <adrelanos@whonix.org>
-## See the file COPYING for copying conditions.
-
-grep_args="\
-   --exclude=changelog.upstream \
-   --exclude-dir=.git
-   --binary-files=without-match \
-   -l \
-   -P \
-   -n"
-
-one=$(LC_ALL=C grep $grep_args '[^\x00-\x7F]' "$@")
-
-two=$(LC_ALL=C grep $grep_args "[^[:ascii:]]" "$@")
-
-## https://access.redhat.com/security/vulnerabilities/RHSB-2021-007
-## https://lintian.debian.org/tags/unicode-trojan
-three=$(LC_ALL=C grep $grep_args $'[\u061C\u200E\u200F\u202A\u202B\u202C\u202D\u202E\u2066\u2067\u2068\u2069]' "$@")
-
-result="\
-$one
-$two
-$three"
-
-output_message=$(echo "$result" | sort --unique)
-
-if [ "$output_message" = "" ]; then
-   exit 1
-else
-   echo "$output_message"
-fi
-
-exit 0
diff --git a/usr/bin/scan-text-file b/usr/bin/scan-text-file
new file mode 100755
index 0000000..780f272
--- /dev/null
+++ b/usr/bin/scan-text-file
@@ -0,0 +1,39 @@
+#!/bin/bash
+## Copyright (C) 2022 - 2023 ENCRYPTED SUPPORT LP <adrelanos@whonix.org>
+## See the file COPYING for copying conditions.
+
+## Search pattern for suspicious characters by negation of allowed characters
+SEARCH_PATTERN='[^[:ascii:]]|[\x{061C}\x{200E}\x{200F}\x{202A}\x{202B}\x{202C}\x{202D}\x{202E}\x{2066}\x{2067}\x{2068}\x{2069}]'
+
+found=0
+## Loop over input files
+while [ "$#" -gt 0 ]; do
+  current_file="$1"
+  contains_suspicious_characters=$(LC_ALL=C perl -nle "print \$ARGV if /$SEARCH_PATTERN/" "$current_file")
+  
+  echo "==================="
+  echo "File: $current_file"
+  
+  if [ -n "$contains_suspicious_characters" ]; then
+    found=1
+    echo "-- Warning : Suspicious characters were found"
+    ## Printing out suspicious characters in Unicode escape sequence \u... with their line and position
+    perl -C -ne "while (/$SEARCH_PATTERN/g) {
+      printf \"Line %d, Position %d: \\\u%04x\n\", \$., \$-[0] + 1, ord(\$&);
+    }" "$current_file"
+  else
+    echo "++ OK : No suspicous characters were found"
+  fi
+
+  ## Remove the processed filename from the list of arguments to satisfy while loop
+  shift
+done
+
+if [ $found -ne 0 ]; then
+  echo -e "-------------------\n-------------------"
+  echo "NOTE: For safety reasons these characters are shown in their Unicode escape sequence '\u...'. To inspect these characters search a 'Unicode character inspector' online and paste the Unicode escape sequence there"
+  exit 1
+fi
+
+exit 0
+