New script in helpers to find UTF in doc files.

2 files changed, 57 insertions, 0 deletions

diff --git a/helpers/ChangeLog b/helpers/ChangeLog
index d8e12b46..6b59f26c 100644
--- a/helpers/ChangeLog
+++ b/helpers/ChangeLog
@@ -1,3 +1,7 @@
+2021-10-09         Arnold D. Robbins     <arnold@skeeve.com>
+
+	* find-utf.sh: New script.
+
 2021-07-15         Arnold D. Robbins     <arnold@skeeve.com>
 
 	* testdfa.c (main): Bug fix and new -b option.
diff --git a/helpers/find-utf.sh b/helpers/find-utf.sh
new file mode 100755
index 00000000..b608a6fa
--- /dev/null
+++ b/helpers/find-utf.sh
@@ -0,0 +1,53 @@
+#! /bin/sh
+export LC_ALL=C
+gawk '
+# ord.awk --- do ord and chr
+
+# Global identifiers:
+#    _ord_:        numerical values indexed by characters
+#    _ord_init:    function to initialize _ord_
+#
+# Arnold Robbins, arnold@skeeve.com, Public Domain
+# 16 January, 1992
+# 20 July, 1992, revised
+
+BEGIN    { _ord_init() }
+
+function _ord_init(    low, high, i, t)
+{
+    low = sprintf("%c", 7) # BEL is ascii 7
+    if (low == "\a") {    # regular ascii
+        low = 0
+        high = 255
+    } else if (sprintf("%c", 128 + 7) == "\a") {
+        # ascii, mark parity
+        low = 128
+        high = 255
+    } else {        # ebcdic(!)
+        low = 0
+        high = 255
+    }
+
+    for (i = low; i <= high; i++) {
+        t = sprintf("%c", i)
+        _ord_[t] = i
+    }
+}
+function ord(str,    c)
+{
+    # only first character is of interest
+    c = substr(str, 1, 1)
+    return _ord_[c]
+}
+
+function chr(c)
+{
+    # force c to be numeric by adding 0
+    return sprintf("%c", c + 0)
+}
+{
+	n = split($0, c, "")
+	for (i = 1; i <= n; i++)
+		if (ord(c[i]) > 127)
+			printf("%d: char: \\%o\n", NR, ord(c[i]))
+}' "$@"