def get(self, page_key=None):
"modify a specific page"
if not page_key:
return self.get()
page = scan_data.read_page(page_key, db)
doc = page.document()
doc_name = doc.name
filename = page.filename
doc_key = doc.key()
# where are we in the document?
loc = filter(lambda x: page.key() == x[1].key(),
enumerate(doc.pages()))
index = loc[0][0] + 1
n_pages = len(doc.pages())
prev_link = ""
next_link = ""
if index > 1:
prev_link = "<a href=\"/page/%s\"><<</a>" % doc.pages()[
index - 2].key()
if index != n_pages:
next_link = "<a href=\"/page/%s\">>></a>" % doc.pages(
)[index].key()
# build a page sized image if necessary
pagesized_path = make_pagesized_thumbnail(page.key(), filename)
controls = """
<a href="/document/%(doc_key)s">Back to Document</a><br/>
<a href="/%(filename)s">Full resolution image</a><br/>
%(prev_link)s         %(next_link)s<br/>
""" % locals()
self.set_header("Content-Type", "text/html")
self.write("""
<html><head><title>%(doc_name)s page %(index)d of %(n_pages)d</title></head>
<body>
<h1>%(doc_name)s</h1>
<h2>Page %(index)d of %(n_pages)d</h2>
%(controls)s
<hr/>
<img src="/%(pagesized_path)s" />
<hr/>
%(controls)s
</body>
</html>""" % locals())
def get(self, page_key=None):
"modify a specific page"
if not page_key:
return self.get()
page = scan_data.read_page(page_key, db)
doc = page.document()
doc_name = doc.name
filename = page.filename
doc_key = doc.key()
# where are we in the document?
loc = filter(lambda x: page.key() == x[1].key(), enumerate(doc.pages()))
index = loc[0][0] + 1
n_pages = len(doc.pages())
prev_link = ""
next_link = ""
if index > 1:
prev_link = "<a href=\"/page/%s\"><<</a>" % doc.pages()[index-2].key()
if index != n_pages:
next_link = "<a href=\"/page/%s\">>></a>" % doc.pages()[index].key()
# build a page sized image if necessary
pagesized_path = make_pagesized_thumbnail(page.key(), filename)
controls = """
<a href="/document/%(doc_key)s">Back to Document</a><br/>
<a href="/%(filename)s">Full resolution image</a><br/>
%(prev_link)s         %(next_link)s<br/>
""" % locals()
self.set_header("Content-Type", "text/html")
self.write("""
<html><head><title>%(doc_name)s page %(index)d of %(n_pages)d</title></head>
<body>
<h1>%(doc_name)s</h1>
<h2>Page %(index)d of %(n_pages)d</h2>
%(controls)s
<hr/>
<img src="/%(pagesized_path)s" />
<hr/>
%(controls)s
</body>
</html>""" % locals())
def get(self):
"retrieve all pages"
pages = []
for key in db.keys():
if key.startswith("page-"):
pages.append(scan_data.read_page(key, db))
pages_html = []
for page in pages:
pages_html.append("<img src=\"%s\" width=400 />" % page.filename)
pages_html = "\n".join(pages_html)
self.set_header("Content-Type", "text/html")
self.write("""
<html><head><title>All pages</title></head>
<body>
<h1>All Pages</h1>
%(pages_html)s
</body>
</html>""" % locals())
def get(self):
"retrieve all pages"
pages = []
for key in db.keys():
if key.startswith("page-"):
pages.append(scan_data.read_page(key, db))
pages_html = []
for page in pages:
pages_html.append("<img src=\"%s\" width=400 />" % page.filename)
pages_html = "\n".join(pages_html)
self.set_header("Content-Type", "text/html")
self.write("""
<html><head><title>All pages</title></head>
<body>
<h1>All Pages</h1>
%(pages_html)s
</body>
</html>""" % locals())
def main(args):
db = dbm.open("scan_data", "r")
print "loaded database"
mdb = pymongo.Connection()
print "connected to mongo"
docs = scan_data.get_documents(db)
print "loaded %d documents" % len(docs)
mdb_docs = mdb.scanserver.documents
# go through each document and build a set of pagekeys
pagekeys = set()
for doc in docs:
docstr = scan_data.doc2json(doc)
pagekeys.update([page.key() for page in doc.pages()])
mdb_docs.insert(docstr)
print "found %d pages" % len(pagekeys)
mdb_pages = mdb.scanserver.pages
for pk in pagekeys:
page = scan_data.read_page(pk, db)
pagestr = scan_data.page2json(page)
mdb_pages.insert(pagestr)
dirpks = set()
for (base, dirs, files) in os.walk("static", topdown=True):
# don't recurse any further
del dirs[0:-1]
for fname in files:
pk = os.path.splitext(fname)[0]
if pk.startswith("page-"):
dirpks.add(pk)
notindb = dirpks - pagekeys
print "found %d page keys on disk that aren't in the database" % len(
notindb)
def main(args):
db = dbm.open("scan_data", "r")
print "loaded database"
mdb = pymongo.Connection()
print "connected to mongo"
docs = scan_data.get_documents(db)
print "loaded %d documents" % len(docs)
mdb_docs = mdb.scanserver.documents
# go through each document and build a set of pagekeys
pagekeys = set()
for doc in docs:
docstr = scan_data.doc2json(doc)
pagekeys.update( [ page.key() for page in doc.pages() ] )
mdb_docs.insert(docstr)
print "found %d pages" % len(pagekeys)
mdb_pages = mdb.scanserver.pages
for pk in pagekeys:
page = scan_data.read_page(pk, db)
pagestr = scan_data.page2json(page)
mdb_pages.insert(pagestr)
dirpks = set()
for (base, dirs, files) in os.walk("static", topdown=True):
# don't recurse any further
del dirs[0:-1]
for fname in files:
pk = os.path.splitext(fname)[0]
if pk.startswith("page-"):
dirpks.add(pk)
notindb = dirpks - pagekeys
print "found %d page keys on disk that aren't in the database" % len(notindb)