def load_content (path) :
transcripts.printf_information ('Parsing file [%s]...', path)
stream = file (path, 'rt')
if path.lower () .endswith ('.pdf') :
content = execute_load_content (['/usr/bin/pdftotext', path, '-'])
elif path.lower () .endswith ('.ps') :
content = execute_load_content (['/usr/bin/pstotext', path])
else :
transcripts.printf_error ('File extension is unknown; ignoring.')
content = None
return content
def execute_load_content (arguments) :
process = subprocess.Popen (
arguments,
stdin = subprocess.PIPE, stdout = subprocess.PIPE, stderr = None,
close_fds = True, bufsize = (32 * 1024), universal_newlines = True)
process.stdin.close ()
content = process.stdout.read ()
process.stdout.close ()
outcome = process.wait ()
if outcome != 0 :
transcripts.printf_error ('Subprocess returned an error code, thus the file seems broken; ignoring.')
content = None
if content is not None and len (content) == 0 :
transcripts.printf_error ('Subprocess returned an empty content, thus the file seems broken; ignoring.')
content = None
return content
def dump (self, title, content) :
if not isinstance (title, types.StringType) :
title = title.encode ("utf-8")
title_size = len (title)
if not isinstance (title, types.StringType) :
content = content.encode ("utf-8")
content_size = len (content)
if (title_size != 0) and (content_size != 0) :
total_size = 4 + title_size + 4 + content_size
self.stream.write (struct.pack (">L", total_size))
self.stream.write (struct.pack (">L", title_size))
self.stream.write (title)
self.stream.write (struct.pack (">L", content_size))
self.stream.write (content)
else :
transcripts.printf_error ('Title or content is empty for [%s]; ignoring.', title)
self.stepper.step ()
def dump(map, dumper):
id = map["id"][0]
if "topic" in map:
topic = map["topic"][0]
else:
transcripts.printf_warning("Missing topic(s) from article with id [%s]; assuming unknown.", id)
topic = "{unknown}"
if "title" in map:
title = map["title"][0]
else:
transcripts.printf_error("Missing title from article with id [%s]; assuming id.", id)
title = "(%s)" % (id)
if "content" in map:
content = "\n".join(map["content"])
else:
transcripts.printf_error("Missing content from article with id [%s]; ignoring.", id)
return
title = "[%s] %s" % (topic, title)
dumper.dump(title, content)
def __call__ (self, message = '', context = '?', severity = 0, traceback = False) :
transcripts.printf_error ('Cherrypy: %s [%d]: %s', context, severity, message)
