replace-file-fragments

#!/usr/bin/awk -f
# Written by Michal Kosmulski <mkosmul _at_ users _dot_ sourceforge _dot_ net>
# This script is hereby put in the public domain.
#
# THIS SOFTWARE IS PROVIDED BY THE AUTHOR ``AS IS'' AND ANY EXPRESS OR IMPLIED
# WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
# MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.  IN NO
# EVENT SHALL THE AUTHOR BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
# SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
# PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS;
# OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
# WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR
# OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF
# ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
#
# Usage:
# replace-file-fragments template=template_file content_file > output_file
#
# Replace fragments of one file with corresponding fragments from a template
# file. Parts to be replaced are marked with special tags. The tags used
# by default are in form of HTML/XML comments, as one typical use is
# editing HTML files. Some parts of the file are the content and vary from
# file to file, while others, e.g. menus and page footers, are the same
# in many documents and can be updated with this script whenever the template
# changes. Of course, this can be much easier achieved using SSI; However,
# sometimes SSI is not available.
#
# The meaning of default tags is as follows: Each tag is a HTML comment and
# should start the line it is in. All text after the tag, up to the end of
# line is ignored. Text located between <!--REPLACE--> and <!--ENDREPLACE-->
# tags in the content file is replaced by the corresponding block of text
# located between <!--COPY--> and <!--ENDCOPY--> in the template file.
# Lines not located between REPLACE and ENDREPLACE tags in content file
# are copied verbatim to standard output, unless they start with <!--IGNORE-->
# (such lines are ignored when they appear in either file).
#
# Example:
#
# --- template file ---
# Some text
# <!--COPY-->
# Menu
# <!-- IGNORE --> This line is ignored
# <!--ENDCOPY-->
# Something
#
# --- and content file ---
# Text
# <!--IGNORE This line is also ignored -->
# <!--REPLACE-->
# The menu will be inserted here
# <!--ENDREPLACE-->
# Page content
#
# --- result in the following output ---
# Text
# <!--REPLACE-->
# Menu
# <!--ENDREPLACE-->
# Page content
#
# REPLACE tags are copied to output as to allow processing the result over
# and over again, should the template change.

BEGIN {
	ignore_regex="^[[:space:]]*<!--[[:space:]]*IGNORE"
	copy_regex="^[[:space:]]*<!--[[:space:]]*COPY"
	endcopy_regex="^[[:space:]]*<!--[[:space:]]*ENDCOPY"
	replace_regex="^[[:space:]]*<!--[[:space:]]*REPLACE"
	endreplace_regex="^[[:space:]]*<!--[[:space:]]*ENDREPLACE"
	replacing=0
}

$0~ignore_regex{next}
$0~replace_regex {
	print
	replacing=1
	# Read template line by line until the replacement for current
	# REPLACE block is found
	copying=0
	while(1) {
		getline < template
		if ($0~copy_regex) {
			copying=1
		} else if ($0~endcopy_regex) {
			copying=0
			break
		} else {
			if (copying && !($0~ignore_regex)) {
				print
			}
		}
	}
	next
}
$0~endreplace_regex {
	print
	replacing=0
	next
}

{
	if (replacing) {
		next
	}
	print	
}