def __get_item_data(self, item):
"""
gets information out of <item>..</item>
@return: output, note, properties, tags
variables for orgwriter.append_org_subitem
"""
try:
#logging.debug(item)
properties = OrgProperties()
guid = item['id']
if not guid:
logging.error("got no id")
unformatted_link = item['link']
short_link = OrgFormat.link(unformatted_link, "link")
# if we found a url in title
# then append the url in front of subject
if re.search("http[s]?://", item['title']) != None:
output = short_link + ": " + item['title']
else:
output = OrgFormat.link(unformatted_link, item['title'])
note = item['description']
# converting updated_parsed UTC --> LOCALTIME
timestamp = OrgFormat.datetime(
time.localtime(calendar.timegm(item['updated_parsed'])))
properties.add("guid", guid)
except KeyError:
logging.error("input is not a RSS 2.0")
sys.exit(1)
tags = []
dont_parse = [
'title', 'description', 'updated', 'summary', 'updated_parsed',
'link', 'links'
]
for i in item:
logging.debug(i)
if i not in dont_parse:
if (type(i) == unicode or type(i) == str) and \
type(item[i]) == unicode and item[i] != "":
if i == "id":
i = "guid"
properties.add(i, item[i])
else:
if i == "tags":
for tag in item[i]:
logging.debug("found tag: %s", tag['term'])
tags.append(tag['term'])
return output, note, properties, tags, timestamp
def __get_item_data(self, item):
"""
gets information out of <item>..</item>
@return: output, note, properties, tags
variables for orgwriter.append_org_subitem
"""
try:
#logging.debug(item)
properties = OrgProperties()
guid = item['id']
if not guid:
logging.error("got no id")
unformatted_link = item['link']
short_link = OrgFormat.link(unformatted_link, "link")
# if we found a url in title
# then append the url in front of subject
if re.search("http[s]?://", item['title']) != None:
output = short_link + ": " + item['title']
else:
output = OrgFormat.link(unformatted_link, item['title'])
note = item['description']
# converting updated_parsed UTC --> LOCALTIME
timestamp = OrgFormat.datetime(
time.localtime(calendar.timegm(item['updated_parsed'])))
properties.add("guid", guid)
except KeyError:
logging.error("input is not a RSS 2.0")
sys.exit(1)
tags = []
dont_parse = ['title', 'description', 'updated', 'summary',
'updated_parsed', 'link', 'links']
for i in item:
logging.debug(i)
if i not in dont_parse:
if (type(i) == unicode or type(i) == str) and \
type(item[i]) == unicode and item[i] != "":
if i == "id":
i = "guid"
properties.add(i, item[i])
else:
if i == "tags":
for tag in item[i]:
logging.debug("found tag: %s", tag['term'])
tags.append(tag['term'])
return output, note, properties, tags, timestamp
def __handle_file(self, photo_file, filename):
"""
checks if file is an image, try to get exif data and
write to org file
"""
logging.debug("handling file %s", filename)
# check if file is an image:
if imghdr.what(filename) != None:
datetime = get_exif_datetime(filename)
if datetime == None:
logging.debug("skipping: %s has no EXIF information", filename)
else:
try:
datetime = time.strptime(datetime, "%Y:%m:%d %H:%M:%S")
timestamp = OrgFormat.datetime(datetime)
output = OrgFormat.link(filename, photo_file)
properties = OrgProperties(photo_file + timestamp)
self._writer.write_org_subitem(timestamp=timestamp,
output=output,
properties=properties)
except ValueError, e:
logging.warning("skipping: Could not parse " + \
"timestamp for %s : %s", filename, e)
def __parse_and_write_file(self, file, link):
"""
Parses the date+time and writes entry to outputfile
@param file: filename
@param link: path
"""
if TIMESTAMP_REGEX.match(file):
# if we found a timestamp too,take hours,min
# and optionally seconds from this timestamp
timestamp = TIMESTAMP_REGEX.match(file).group()
orgdate = OrgFormat.strdatetimeiso8601(timestamp)
logging.debug("found timestamp: " + orgdate)
else:
datestamp = DATESTAMP_REGEX.match(file).group()
orgdate = OrgFormat.strdate(datestamp)
orgdate_time_tupel = OrgFormat.datetupeliso8601(datestamp)
file_datetime = time.localtime(os.path.getmtime(link))
# check if the file - time information matches year,month,day,
# then update time
if file_datetime.tm_year == orgdate_time_tupel.tm_year and \
file_datetime.tm_mon == orgdate_time_tupel.tm_mon and \
file_datetime.tm_mday == orgdate_time_tupel.tm_mday:
logging.debug("found a time in file.setting %s-->%s", orgdate,
OrgFormat.date(file_datetime, True))
orgdate = OrgFormat.date(file_datetime, True)
# write entry to org file
output = OrgFormat.link(link=link, description=file)
# we need optional data for hashing due it can be, that more
# than one file have the same timestamp
properties = OrgProperties(data_for_hashing=output)
self._writer.write_org_subitem(timestamp=orgdate,
output=output,
properties=properties)
def __handle_file(self, photo_file, filename):
"""
checks if file is an image, try to get exif data and
write to org file
"""
logging.debug("handling file %s", filename)
# check if file is an image:
if imghdr.what(filename) != None:
datetime = get_exif_datetime(filename)
if datetime == None:
logging.debug("skipping: %s has no EXIF information", filename)
else:
try:
datetime = time.strptime(datetime, "%Y:%m:%d %H:%M:%S")
timestamp = OrgFormat.datetime(datetime)
output = OrgFormat.link(filename, photo_file)
properties = OrgProperties(photo_file + timestamp)
self._writer.write_org_subitem(timestamp=timestamp,
output=output,
properties=properties)
except ValueError, e:
logging.warning("skipping: Could not parse " + \
"timestamp for %s : %s", filename, e)
def __parse_and_write_file(self, file, link):
"""
Parses the date+time and writes entry to outputfile
@param file: filename
@param link: path
"""
if TIMESTAMP_REGEX.match(file):
# if we found a timestamp too,take hours,min
# and optionally seconds from this timestamp
timestamp = TIMESTAMP_REGEX.match(file).group()
orgdate = OrgFormat.strdatetimeiso8601(timestamp)
logging.debug("found timestamp: " + orgdate)
else:
datestamp = DATESTAMP_REGEX.match(file).group()
orgdate = OrgFormat.strdate(datestamp)
orgdate_time_tupel = OrgFormat.datetupeliso8601(datestamp)
file_datetime = time.localtime(os.path.getmtime(link))
# check if the file - time information matches year,month,day,
# then update time
if file_datetime.tm_year == orgdate_time_tupel.tm_year and \
file_datetime.tm_mon == orgdate_time_tupel.tm_mon and \
file_datetime.tm_mday == orgdate_time_tupel.tm_mday:
logging.debug("found a time in file.setting %s-->%s",
orgdate, OrgFormat.date(file_datetime, True))
orgdate = OrgFormat.date(file_datetime, True)
# write entry to org file
output = OrgFormat.link(link=link, description=file)
# we need optional data for hashing due it can be, that more
# than one file have the same timestamp
properties = OrgProperties(data_for_hashing=output)
self._writer.write_org_subitem(timestamp=orgdate,
output=output,
properties=properties)
def __write_file(self, file, link, timestamp):
"""
write entry to org file (omit replacement of spaces in file names)
"""
output = OrgFormat.link(link=link,
description=file,
replacespaces=False)
# we need optional data for hashing due it can be, that more
# than one file have the same timestamp
properties = OrgProperties(data_for_hashing=output)
self._writer.write_org_subitem(timestamp=timestamp,
output=output,
properties=properties)
def __write(self):
"""
write attributes to writer (make an org_sub_item)
"""
logging.debug("msg:%s", self.__msg)
#getting tags
if self.__attrtags:
tags = self.__attrtags
if self.__split:
tags = tags.split(self.__split)
else:
tags = tags.split(' ')
tags = tags[1:]
elif self.__taging:
tags = self.__taging
if self.__split:
tags = tags.split(self.__split)
else:
tags = tags.split(' ')
else:
tags = []
for item in tags:
if item == '':
tags.remove(item)
#getting output
if not self.__attroutput:
output = "%s: %s" % (self.__author, self.__msg)
else:
output = self.__attroutput
part = output.split(" ")
output = ""
for item in part:
if re.search("http[s]?://", item) != None:
unformatted_link = item
short_link = OrgFormat.link(unformatted_link, "link")
output = output + " " + short_link + ": " + item
else:
output = output + " " + item
output = output[1:]
#getting properties
if not self.__attrproperties:
properties = OrgProperties(data_for_hashing=self.__author \
+ self.__msg + self.__date)
else:
properties = OrgProperties(data_for_hashing=self.__attrproperties)
#getting notes
if self.__attrnote:
notes = self.__attrnote
elif self.__notes:
notes = self.__notes
else:
notes = ""
if notes:
parts = notes.split(" ")
notes = ""
for item in parts:
if re.search("http[s]?://", item) != None:
unformatted_link = item
short_link = OrgFormat.link(unformatted_link,
"link")
notes = notes + " " + short_link + ": " + item
else:
notes = notes + " " + item
notes = notes[1:]
#prepare for most time formats + getting timestamp
if self.__attrtime:
self.__date = self.attrtime
try:
if (self.__time == 'YYYYMMDD' or self.__time == 'YYYY'
or self.__time == 'YYYYMMDDTHHMMSSZ'
or self.__time == 'YYYYMMDDTHHMMSST'):
timestamp = OrgFormat.datetime(
OrgFormat.datetupelutctimestamp(
self.__date))
elif (self.__time == ('YYYY-MM-DD')):
timestamp = OrgFormat.datetime(
OrgFormat.datetupeliso8601(
self.__date))
elif (self.__time == 'YYYY-MM-DDTHH.MM.SS' or
self.__time == 'YYYY-MM-DDTHH.MM'):
timestamp = OrgFormat.datetime(
OrgFormat.datetimetupeliso8601(
self.__date))
elif (self.__time == 'timetuple'):
time_tupel = time.localtime(time.mktime(
parsedate(self.__date)))
timestamp = OrgFormat.datetime(time_tupel)
except:
logging.debug("Write functione @timestamp timestamp=%s",
self.__date)
logging.error("A timestamp problem occured")
sys.exit(2)
self._writer.write_org_subitem(output=output,
timestamp=timestamp,
note=notes,
tags=tags,
properties=properties)
def __read_store_and_write(self, store_file):
"""
Reads needed infos of .tagstore/store.tgs,
parse the infos,
write to outputfile
@param store_file: string contains the input from store.tgs
"""
parser = SafeConfigParser()
parser.read(store_file)
sections = parser.sections()
options = parser.options(sections[1])
for i in range(0, len(options), 3):
filename = options[i].split('\\')
filename = filename[0]
tags = parser.get(sections[1], options[i])
timestamp = parser.get(sections[1], options[i + 1])
category = parser.get(sections[1], options[i + 2])
tags = tags.replace('"', '')
tags = tags.replace(' ', '_')
tags = tags.replace(':', '_')
category = category.replace('"', '')
category = category.replace(' ', '_')
category = category.replace(':', '_')
tags = tags.split(",")
category = category.split(",")
timestamp = timestamp[0:16]
tagstoring = []
tagstoring.extend(tags)
tagstoring.extend(category)
x = 0
while x < len(tagstoring):
if tagstoring[x] == '':
tagstoring.pop(x)
else:
y = x + 1
while y < len(tagstoring):
if tagstoring[x] == tagstoring[y]:
tagstoring.pop(y)
else:
y = y + 1
x = x + 1
unformatted_link = self.__path + "/" + filename
short_link = OrgFormat.link(unformatted_link, "link")
link = ":FILEPATH: " + short_link
timestamp = OrgFormat.strdatetime(timestamp)
output = filename.decode("utf-8", "replace")
data_for_hashing = output.decode("utf-8", "replace")
properties = OrgProperties(data_for_hashing=data_for_hashing)
self._writer.write_org_subitem(timestamp=timestamp,
output=output,
note=link,
tags=tagstoring,
properties=properties)
