Shell Programming and Scripting

awk '
{	while(length)
		if(soh) {
			# We have already seen SOH...
			# Copy text until we find ETX.
			if(etx = index($0, "ETX")) {
				# ETX found...  print through ETX, close output
				# file, clear soh, and throw away te part of the
				# line we have already processed.
				printf("%s\n", substr($0, soh, etx - soh + 3)) > f
				close(f)
				soh = 0
				$0 = substr($0, etx + 3)
			} else {# ETX not found...  print rest of the line.
				printf("%s\n", substr($0, soh)) > f
				soh = 1
				next
			}
		} else {# Look for SOH...
			if(soh = index($0, "SOH")) {
				# SOH found... set output filename...
				f = "file" ++nof ".txt"
				continue
			} else {# SOH not found...
				next
			}
		}
}' file

SOH
...
ETX
SOH
...
ETX
.
.
.
ETX

#!/usr/bin/env bash

# @(#) s1       Demonstrate context splitting, csplit.

# Utility functions: print-as-echo, print-line-with-visual-space, debug.
# export PATH="/usr/local/bin:/usr/bin:/bin"
LC_ALL=C ; LANG=C ; export LC_ALL LANG
pe() { for _i;do printf "%s" "$_i";done; printf "\n"; }
pl() { pe;pe "-----" ;pe "$*"; }
db() { ( printf " db, ";for _i;do printf "%s" "$_i";done;printf "\n" ) >&2 ; }
db() { : ; }
C=$HOME/bin/context && [ -f $C ] && $C csplit

# Remove debris from previous runs.
rm -f xx*

FILE=${1-data1}

pl " Input data file $FILE:"
cat $FILE

pl " Results:"
# -z only in GNU/Linux.
# csplit -k -z $FILE '/^SOH/' '{*}'
csplit -k $FILE '/^SOH/' '{*}'
ls -lgo xx*

EXAMPLE=xx02
pl " Content for example file $EXAMPLE:"
cat $EXAMPLE

exit 0

$ ./s1

Environment: LC_ALL = C, LANG = C
(Versions displayed with local utility "version")
OS, ker|rel, machine: HP-UX, B.11.11, 9000/785
Distribution        : GenericSysName [HP Release B.11.11] (see /etc/issue)
GNU bash 4.2.37
csplit - ( /usr/bin/csplit Nov 14 2000 )

-----
 Input data file data1:
SOH
Stuff in first section.
ETX
SOH
Stuff in second section.
ETX
SOH
Stuff in last section.
ETX

-----
 Results:
0
32
33
31
-rw-r--r--   1       0 Oct  8 18:29 xx00
-rw-r--r--   1      32 Oct  8 18:29 xx01
-rw-r--r--   1      33 Oct  8 18:29 xx02
-rw-r--r--   1      31 Oct  8 18:29 xx03

-----
 Content for example file xx02:
SOH
Stuff in second section.
ETX

SOH
bla bla bla
bla bla bla
ETX                SOH
bla bla bla
ETX
SOH
bla bla bla
ETX

awk '
length {
  sub("ETX.*", "ETX")
  print RS $0 > "file" ++n ".txt"
  close ("file" n ".txt")
}' RS="SOH" infile

SOH
bla bla bla
bla bla bla
ETX IGNORE THIS    SOH
bla bla bla
ETX
SOH
bla bla bla
ETX

----file1.txt---
SOH
bla bla bla
bla bla bla
ETX

----file2.txt---
SOH
bla bla bla
ETX

----file3.txt---
SOH
bla bla bla
ETX