After the changes in necessary to support full XHTML files, including those produced from Docbook source, I decided the put the web source pages under CVS. This necessitated more modifications to the web publishing makefiles, originally described in Web Publishing using make.
The latest state of the makefiles, and the python script create_html.py is shown below:
# Makefile to process and publish hydrus web contents
#
#
# make compile - create pages by placing page contents into the standard
# page template.
#
# make publish - copy processed pages to web directory, and cgi-bin scripts
#
#
# MODIFICATION HISTORY
# Mnemonic Date Rel Who
# www-publish 040615 1.0 mpw
# Written.
# www-publish 050103 1.1 mpw
# Copy contents of cgi-bin directory under ${ROOT} to ${HTTPD-ROOT}
# when publishing
# www-publish 050107 1.2 mpw
# Added distclean option to clean contents of live www directories data
# and cgi-bin
# www-publish 050127 1.3 mpw
# Supporting linking of html files within multiple directories
# www-publish 050702 1.4 mpw
# Remove any .bak files left by ispell
# www-publish 050909 1.5 mpw
# Revised to handle Docbook output in XHTML
# www-publish 051001 1.6 mpw
# Support for CVS project (i.e. ignore cvs directories)
# ww-publish 051101 1.7 mpw
# Ensure that make compile fails immediately on error
# ww-publish 051101 1.8 mpw
# Replace explict use of gmake with ${MAKE}
ROOT-DIR=${PWD}
SRC := ${ROOT-DIR}/src
OBJ := ${HOME}/public_html
CGI-BIN-DIR := ${ROOT-DIR}/cgi-bin
LINK-DIRS := journal articles
HTTPD-ROOT := /home/www
PUB-DIR := ${HTTPD-ROOT}/data
TEMPLATE-NORMAL := page-template.html
CATALOG=${HOME}/dtd/CATALOG
.PHONY: compile publish clean template link cgi-bin
compile: link
cp ${TEMPLATE-NORMAL} ${OBJ}
chmod 644 ${OBJ}/${TEMPLATE-NORMAL}
find ${SRC} -type f -name "*.bak" -exec rm {} \;
DIRLIST=`find ${SRC} -name "CVS" -prune -or -type d -print` ; \
for dir in $${DIRLIST} ; do \
${MAKE} ${MKFLAGS} -C $${dir} -f ${CURDIR}/compile.mk \
SRC=${SRC} \
OBJ=${OBJ} \
CATALOG=${CATALOG} \
TEMPLATE-NORMAL=${CURDIR}/${TEMPLATE-NORMAL} \
ROOT=${CURDIR} || exit 1; \
done
publish: cgi-bin
find ${OBJ} -type d -exec ${MAKE} ${MKFLAGS} -C {} \
-f ${CURDIR}/publish.mk \
OBJ=${OBJ} ROOT=${CURDIR} PUB-DIR=${PUB-DIR} \;
# update internal links in directories which contain linked html files
link:
for dir in ${LINK-DIRS}; do \
cd ${SRC}/$${dir}; \
newlink.py $${dir}; \
done
clean:
rm -rf ${OBJ}/*
distclean: clean
rm -rf ${HTTPD-ROOT}/cgi-bin/*
rm -rf ${PUB-DIR}/*
# update cgi-bin binaries if required
cgi-bin:
find $@ -name "CVS" -prune -or -type d \
-exec ${MAKE} ${MKFLAGS} -C {} -f ${CURDIR}/publish.mk \
OBJ=${OBJ} ROOT=${CURDIR} PUB-DIR=${HTTPD-ROOT} \;
# Makefile for constructing publishable html file from source html
# files and a template. The variable TEMPLATE-NORMAL
# should be passed as an argument to the make
# directive. All files are dependent on the template.
#
# MODIFICATION HISTORY
# Mnemonic Date Rel Who
# www-publish 040615 1.0 mpw
# Written.
# www-publish 050904 1.1 mpw
# Add checking for valid XHTML (via chk_xhtml.py)
# www-publish 050909 1.2 mpw
# Revised to handle XHTML conformant Docbook output
# www-publish 051001 1.3 mpw
# SRC and OBJ dirctories passed on make invokation line
# www-publish 051101 1.4 mpw
# remove created html file on error (ensures rebuild on next run)
#
# set target directory
TD := ${subst ${SRC},${OBJ},${CURDIR}}
# define pattern rule for producing .html files in the target
# directory.
${TD}/%.html : %.html
${ROOT}/create-html.py ${TEMPLATE-NORMAL} $< $@
chk_xml.py -f ${CATALOG} $@ || (rm $@; exit 1)
# pattern rule to make non-html targets (images, support files, etc)
# note we ignore directories
${TD}/% : %
if [ ! -d $< ]; then \
cp $< $@; \
fi
# define list of targets (based on list of .html files in current directory)
OBJS := ${patsubst %,${TD}/%,${wildcard *.html}}
# define list of non-html targets
OTHER := ${patsubst %,${TD}/%,${filter-out %.html,${wildcard *}}}
all: ${TD} ${OBJS} ${OTHER}
${OBJS}: ${TEMPLATE-NORMAL}
# make target directory if necessary
${TD}:
mkdir -p ${TD}
# Makefile for publishing html files from processed html pages
#
# MODIFICATION HISTORY
# Mnemonic Date Rel Who
# www-publish 040615 1.0 mpw
# Written.
# www-publish 051001 1.1 mpw
# OBJ dir passed in on make command line
#
# set target directory
# note, OBJ, PUB-DIR and ROOT are passed on invokation line
TD := ${subst ${OBJ},${PUB-DIR},${CURDIR}}
# pattern rule to make all targets (directories are ignored)
${TD}/% : %
if [ ! -d $< ]; then \
cp $< $@ ; \
chmod 644 $@ ; \
fi
# define list of targets (that's everything)
OBJS := ${patsubst %,${TD}/%,${wildcard *}}
all: ${TD} ${OBJS}
# make target directory if necessary
${TD}:
mkdir -p ${TD}
#!/usr/local/bin/python
"""
NAME
create-html.py - wraps HTML page contents with HTML page template
SYNOPSYS
create-html.py template_file source_page_contents output_page
DESCRIPTION
create-html.py will insert the contents of an HTML page into a supplied
page template, outputing the results as a final HTML page.
The title of the resulting page is determined by the first <h1>
or <h2> header encountered in the page contents.
MODIFICATION HISTORY
Mnemonic Rel Date Who
create-html 1.0 040614 mpw
Written.
create-html 1.1 050909 mpw
Handle source with existing <body> (Docbook generated)
"""
import sys
import re
default_title = "hydrus.org.uk"
template_file = sys.argv[1]
html_in_file = sys.argv[2]
html_out_file = sys.argv[3]
template = open(template_file).read()
html_in = open(html_in_file).read()
html_out = open(html_out_file,mode="w")
# attempt to modify title to reflect page contents
re_title = re.compile(r'<title>.*?</title>')
re_header = re.compile(r'<h[12]>(.*)</h[12]>')
re_body = re.compile(r'<body>(.*)</body>',re.DOTALL)
match = re_body.search(html_in)
if match != None:
# page already has body; insert menu template
page = match.group(1)
match = re_body.search(template)
if match == None:
print >>sys.stderr,"%s: missing <body> in template file: %s" % \
(sys.argv[0],template_file)
sys.exit(1)
menupage = match.group(1)
page = menupage.replace("<!-- page contents go here -->",page)
re_body.search(html_in)
content = re_body.sub("<body>"+page+"</body>",html_in)
else:
# needs full page template
match = re_header.search(html_in)
if match != None:
header = match.group(1)
page_title = "<title>"+default_title+" - "+header+"</title>"
else:
page_title = "<title>"+default_title+"</title>"
if re_title.search(template):
template = re_title.sub(page_title,template)
content = template.replace("<!-- page contents go here -->",html_in)
html_out.write(content)
$Id: webpublish1.html,v 1.3 2023/03/27 08:07:33 mark Exp $
