myersjustinc · November 4, 2011 22:00
diff --git a/README.md b/README.md
diff --git a/convert_aff.py b/convert_aff.py
 #!/usr/bin/env python
 import sys
 from xml.etree.ElementTree import parse

 def main(input_filename):
    new_url_base = 'http://factfinder2.census.gov/bkmk/table/1.0/en'
    document = parse(input_filename)
    
    product = document.find('product')
    url = '/'.join([
        new_url_base,
        product.attrib['program-id'],
        product.attrib['dataset-id'],
        product.attrib['table-id']
    ])
    
    geo_ids = []
    code_types = {}
    selection = document.find('selection')
    if selection is not None and len(selection):
        for dimension in selection.findall('dimension'):
            dimension_type = dimension.attrib['type']
            if dimension_type == 'geo':
                for cat_id in dimension.findall('cat-id'):
                    geo_ids.append(cat_id.text)
            else:
                codes = []
                if dimension_type in code_types:
                    codes = code_types[dimension_type]
                for cat_id in dimension.findall('cat-id'):
                    codes.append(cat_id.text)
                code_types[dimension_type] = codes
    if geo_ids:
        url = '%s/%s' % (url, '|'.join(geo_ids))
    
    if code_types:
        for code_type in code_types.keys():
            url = '%s/%s~%s' % (url, code_type, '|'.join(code_types[code_type]))
    
    print url

 if __name__ == "__main__":
    if len(sys.argv) != 2:
        print "Usage: %s foo.aff" % sys.argv[0]
    else:
        main(sys.argv[1])

diff --git a/deep_link.py b/deep_link.py
 #!/usr/bin/env python
 import cgi
 import web
 from xml.etree.ElementTree import parse

 cgi.maxlen = 1048576 * 1  # no files more than 1 MB

 urls = (
    r'/', 'upload',
 )
 app = web.application(urls, globals())
 app.internalerror = web.debugerror
 application = app.wsgifunc()

 class upload:
    def GET(self):
        return """<!DOCTYPE html>
        <html>
            <head>
                <title>Census bookmark generator</title>
                <meta http-equiv="Content-Type" content="text/html;charset=ISO-8859-1" />
            </head>
            <body>
                <form method="POST" enctype="multipart/form-data" action="">
                    <label for="aff">AFF (query) file:</label>
                    <input type="file" name="aff" />
                    <br /><br />
                    <input type="submit" value="Go" />
                </form>
            </body>
        </html>"""
    
    def POST(self):
        try:
            data = web.input(aff={})
        except ValueError:
            return "File too large"
        
        new_url_base = 'http://factfinder2.census.gov/bkmk/table/1.0/en'
        document = parse(data['aff'].file)
        
        product = document.find('product')
        url = '/'.join([
            new_url_base,
            product.attrib['program-id'],
            product.attrib['dataset-id'],
            product.attrib['table-id']
        ])
        
        geo_ids = []
        code_types = {}
        selection = document.find('selection')
        if selection is not None and len(selection):
            for dimension in selection.findall('dimension'):
                dimension_type = dimension.attrib['type']
                if dimension_type == 'geo':
                    for cat_id in dimension.findall('cat-id'):
                        geo_ids.append(cat_id.text)
                else:
                    codes = []
                    if dimension_type in code_types:
                        codes = code_types[dimension_type]
                    for cat_id in dimension.findall('cat-id'):
                        codes.append(cat_id.text)
                    code_types[dimension_type] = codes
        if geo_ids:
            url = '%s/%s' % (url, '|'.join(geo_ids))
        
        if code_types:
            for code_type in code_types.keys():
                url = '%s/%s~%s' % (url, code_type, '|'.join(code_types[code_type]))
        
        return """<!DOCTYPE html>
        <html>
            <head>
                <title>Census bookmark generator</title>
                <meta http-equiv="Content-Type" content="text/html;charset=ISO-8859-1" />
            </head>
            <body>
                <p>Here's your link: <a href="%(url)s">%(url)s</a></p>
                <p><a href="/">Again?</a></p>
            </body>
        </html>""" % {'url': url}

 if __name__ == "__main__":
    app.run()

diff --git a/epio.ini b/epio.ini
 [wsgi]

 requirements = requirements.txt
 entrypoint = deep_link:application
diff --git a/requirements.txt b/requirements.txt
 https://github.com/webpy/webpy/tarball/master
	#!/usr/bin/env python
	import sys
	from xml.etree.ElementTree import parse

	def main(input_filename):
	new_url_base = 'http://factfinder2.census.gov/bkmk/table/1.0/en'
	document = parse(input_filename)

	product = document.find('product')
	url = '/'.join([
	new_url_base,
	product.attrib['program-id'],
	product.attrib['dataset-id'],
	product.attrib['table-id']
	])

	geo_ids = []
	code_types = {}
	selection = document.find('selection')
	if selection is not None and len(selection):
	for dimension in selection.findall('dimension'):
	dimension_type = dimension.attrib['type']
	if dimension_type == 'geo':
	for cat_id in dimension.findall('cat-id'):
	geo_ids.append(cat_id.text)
	else:
	codes = []
	if dimension_type in code_types:
	codes = code_types[dimension_type]
	for cat_id in dimension.findall('cat-id'):
	codes.append(cat_id.text)
	code_types[dimension_type] = codes
	if geo_ids:
	url = '%s/%s' % (url, '\|'.join(geo_ids))

	if code_types:
	for code_type in code_types.keys():
	url = '%s/%s~%s' % (url, code_type, '\|'.join(code_types[code_type]))

	print url

	if __name__ == "__main__":
	if len(sys.argv) != 2:
	print "Usage: %s foo.aff" % sys.argv[0]
	else:
	main(sys.argv[1])
	#!/usr/bin/env python
	import cgi
	import web
	from xml.etree.ElementTree import parse

	cgi.maxlen = 1048576 * 1 # no files more than 1 MB

	urls = (
	r'/', 'upload',
	)
	app = web.application(urls, globals())
	app.internalerror = web.debugerror
	application = app.wsgifunc()

	class upload:
	def GET(self):
	return """<!DOCTYPE html>
	<html>
	<head>
	<title>Census bookmark generator</title>
	<meta http-equiv="Content-Type" content="text/html;charset=ISO-8859-1" />
	</head>
	<body>
	<form method="POST" enctype="multipart/form-data" action="">
	<label for="aff">AFF (query) file:</label>
	<input type="file" name="aff" />
	<br /><br />
	<input type="submit" value="Go" />
	</form>
	</body>
	</html>"""

	def POST(self):
	try:
	data = web.input(aff={})
	except ValueError:
	return "File too large"

	new_url_base = 'http://factfinder2.census.gov/bkmk/table/1.0/en'
	document = parse(data['aff'].file)

	product = document.find('product')
	url = '/'.join([
	new_url_base,
	product.attrib['program-id'],
	product.attrib['dataset-id'],
	product.attrib['table-id']
	])

	geo_ids = []
	code_types = {}
	selection = document.find('selection')
	if selection is not None and len(selection):
	for dimension in selection.findall('dimension'):
	dimension_type = dimension.attrib['type']
	if dimension_type == 'geo':
	for cat_id in dimension.findall('cat-id'):
	geo_ids.append(cat_id.text)
	else:
	codes = []
	if dimension_type in code_types:
	codes = code_types[dimension_type]
	for cat_id in dimension.findall('cat-id'):
	codes.append(cat_id.text)
	code_types[dimension_type] = codes
	if geo_ids:
	url = '%s/%s' % (url, '\|'.join(geo_ids))

	if code_types:
	for code_type in code_types.keys():
	url = '%s/%s~%s' % (url, code_type, '\|'.join(code_types[code_type]))

	return """<!DOCTYPE html>
	<html>
	<head>
	<title>Census bookmark generator</title>
	<meta http-equiv="Content-Type" content="text/html;charset=ISO-8859-1" />
	</head>
	<body>
	<p>Here's your link: <a href="%(url)s">%(url)s</a></p>
	<p><a href="/">Again?</a></p>
	</body>
	</html>""" % {'url': url}

	if __name__ == "__main__":
	app.run()
	[wsgi]

	requirements = requirements.txt
	entrypoint = deep_link:application