mirror of
https://github.com/paperless-ngx/paperless-ngx.git
synced 2025-08-14 00:26:21 +00:00
Modifications for support for dates
This commit is contained in:
Daniel Quinn
@@ -1,8 +1,11 @@
|
||||
import dateutil.parser
|
||||
import logging
|
||||
import os
|
||||
import re
|
||||
import uuid
|
||||
|
||||
from collections import OrderedDict
|
||||
|
||||
from django.conf import settings
|
||||
from django.core.urlresolvers import reverse
|
||||
from django.db import models
|
||||
@@ -12,97 +15,6 @@ from django.utils import timezone
|
||||
from .managers import LogManager
|
||||
|
||||
|
||||
class FileInfo(object):
|
||||
def __init__(self, title, suffix,
|
||||
correspondent=None, tags=None):
|
||||
self._title = title
|
||||
self._suffix = suffix
|
||||
self._correspondent = correspondent
|
||||
self._tags = tags
|
||||
|
||||
REGEX_TITLE = re.compile(
|
||||
r"^.*/(.*)\.(pdf|jpe?g|png|gif|tiff)$",
|
||||
flags=re.IGNORECASE
|
||||
)
|
||||
REGEX_CORRESPONDENT_TITLE = re.compile(
|
||||
r"^.*/(.+) - (.*)\.(pdf|jpe?g|png|gif|tiff)$",
|
||||
flags=re.IGNORECASE
|
||||
)
|
||||
REGEX_CORRESPONDENT_TITLE_TAGS = re.compile(
|
||||
r"^.*/(.*) - (.*) - ([a-z0-9\-,]*)\.(pdf|jpe?g|png|gif|tiff)$",
|
||||
flags=re.IGNORECASE
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def from_path(cls, path):
|
||||
"""
|
||||
We use a crude naming convention to make handling the correspondent,
|
||||
title, and tags easier:
|
||||
"<correspondent> - <title> - <tags>.<suffix>"
|
||||
"<correspondent> - <title>.<suffix>"
|
||||
"<title>.<suffix>"
|
||||
"""
|
||||
|
||||
def get_correspondent(correspondent_name):
|
||||
return Correspondent.objects.get_or_create(
|
||||
name=correspondent_name,
|
||||
defaults={"slug": slugify(correspondent_name)}
|
||||
)[0]
|
||||
|
||||
def get_tags(tags):
|
||||
r = []
|
||||
for t in tags.split(","):
|
||||
r.append(
|
||||
Tag.objects.get_or_create(slug=t, defaults={"name": t})[0])
|
||||
return tuple(r)
|
||||
|
||||
def get_suffix(suffix):
|
||||
suffix = suffix.lower()
|
||||
if suffix == "jpeg":
|
||||
return "jpg"
|
||||
return suffix
|
||||
|
||||
# First attempt: "<correspondent> - <title> - <tags>.<suffix>"
|
||||
m = re.match(cls.REGEX_CORRESPONDENT_TITLE_TAGS, path)
|
||||
if m:
|
||||
return cls(
|
||||
title=m.group(2),
|
||||
correspondent=get_correspondent(m.group(1)),
|
||||
tags=get_tags(m.group(3)),
|
||||
suffix=get_suffix(m.group(4))
|
||||
)
|
||||
|
||||
# Second attempt: "<correspondent> - <title>.<suffix>"
|
||||
m = re.match(cls.REGEX_CORRESPONDENT_TITLE, path)
|
||||
if m:
|
||||
return cls(
|
||||
title=m.group(2),
|
||||
correspondent=get_correspondent(m.group(1)),
|
||||
tags=(),
|
||||
suffix=get_suffix(m.group(3))
|
||||
)
|
||||
|
||||
# That didn't work, so we assume correspondent and tags are None
|
||||
m = re.match(cls.REGEX_TITLE, path)
|
||||
return FileInfo(
|
||||
title=m.group(1), tags=(), suffix=get_suffix(m.group(2)))
|
||||
|
||||
@property
|
||||
def title(self):
|
||||
return self._title
|
||||
|
||||
@property
|
||||
def correspondent(self):
|
||||
return self._correspondent
|
||||
|
||||
@property
|
||||
def tags(self):
|
||||
return self._tags
|
||||
|
||||
@property
|
||||
def suffix(self):
|
||||
return self._suffix
|
||||
|
||||
class SluggedModel(models.Model):
|
||||
|
||||
name = models.CharField(max_length=128, unique=True)
|
||||
@@ -341,3 +253,136 @@ class Log(models.Model):
|
||||
self.group = uuid.uuid4()
|
||||
|
||||
models.Model.save(self, *args, **kwargs)
|
||||
|
||||
|
||||
class FileInfo(object):
|
||||
|
||||
# This epic regex *almost* worked for our needs, so I'm keeping it here for
|
||||
# posterity, in the hopes that we might find a way to make it work one day.
|
||||
ALMOST_REGEX = re.compile(
|
||||
r"^((?P<date>\d\d\d\d\d\d\d\d\d\d\d\d\d\dZ){separator})?"
|
||||
r"((?P<correspondent>{non_separated_word}+){separator})??"
|
||||
r"(?P<title>{non_separated_word}+)"
|
||||
r"({separator}(?P<tags>[a-z,0-9-]+))?"
|
||||
r"\.(?P<extension>[a-zA-Z.-]+)$".format(
|
||||
separator=r"\s+-\s+",
|
||||
non_separated_word=r"([\w,. ]|([^\s]-))"
|
||||
)
|
||||
)
|
||||
|
||||
REGEXES = OrderedDict([
|
||||
("created-correspondent-title-tags", re.compile(
|
||||
r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
|
||||
r"(?P<correspondent>.*) - "
|
||||
r"(?P<title>.*) - "
|
||||
r"(?P<tags>[a-z0-9\-,]*)"
|
||||
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
|
||||
flags=re.IGNORECASE
|
||||
)),
|
||||
("created-title-tags", re.compile(
|
||||
r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
|
||||
r"(?P<title>.*) - "
|
||||
r"(?P<tags>[a-z0-9\-,]*)"
|
||||
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
|
||||
flags=re.IGNORECASE
|
||||
)),
|
||||
("created-correspondent-title", re.compile(
|
||||
r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
|
||||
r"(?P<correspondent>.*) - "
|
||||
r"(?P<title>.*)"
|
||||
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
|
||||
flags=re.IGNORECASE
|
||||
)),
|
||||
("created-title", re.compile(
|
||||
r"^(?P<created>\d\d\d\d\d\d\d\d(\d\d\d\d\d\d)?Z) - "
|
||||
r"(?P<title>.*)"
|
||||
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
|
||||
flags=re.IGNORECASE
|
||||
)),
|
||||
("correspondent-title-tags", re.compile(
|
||||
r"(?P<correspondent>.*) - "
|
||||
r"(?P<title>.*) - "
|
||||
r"(?P<tags>[a-z0-9\-,]*)"
|
||||
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
|
||||
flags=re.IGNORECASE
|
||||
)),
|
||||
("correspondent-title", re.compile(
|
||||
r"(?P<correspondent>.*) - "
|
||||
r"(?P<title>.*)?"
|
||||
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
|
||||
flags=re.IGNORECASE
|
||||
)),
|
||||
("title", re.compile(
|
||||
r"(?P<title>.*)"
|
||||
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff)$",
|
||||
flags=re.IGNORECASE
|
||||
))
|
||||
])
|
||||
|
||||
def __init__(self, created=None, correspondent=None, title=None, tags=(),
|
||||
extension=None):
|
||||
|
||||
self.created = created
|
||||
self.title = title
|
||||
self.extension = extension
|
||||
self.correspondent = correspondent
|
||||
self.tags = tags
|
||||
|
||||
@classmethod
|
||||
def _get_created(cls, created):
|
||||
return dateutil.parser.parse("{:0<14}Z".format(created[:-1]))
|
||||
|
||||
@classmethod
|
||||
def _get_correspondent(cls, name):
|
||||
if not name:
|
||||
return None
|
||||
return Correspondent.objects.get_or_create(name=name, defaults={
|
||||
"slug": slugify(name)
|
||||
})[0]
|
||||
|
||||
@classmethod
|
||||
def _get_title(cls, title):
|
||||
return title
|
||||
|
||||
@classmethod
|
||||
def _get_tags(cls, tags):
|
||||
r = []
|
||||
for t in tags.split(","):
|
||||
r.append(
|
||||
Tag.objects.get_or_create(slug=t, defaults={"name": t})[0])
|
||||
return tuple(r)
|
||||
|
||||
@classmethod
|
||||
def _get_extension(cls, extension):
|
||||
r = extension.lower()
|
||||
if r == "jpeg":
|
||||
return "jpg"
|
||||
return r
|
||||
|
||||
@classmethod
|
||||
def _mangle_property(cls, properties, name):
|
||||
if name in properties:
|
||||
properties[name] = getattr(cls, "_get_{}".format(name))(
|
||||
properties[name]
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def from_path(cls, path):
|
||||
"""
|
||||
We use a crude naming convention to make handling the correspondent,
|
||||
title, and tags easier:
|
||||
"<correspondent> - <title> - <tags>.<suffix>"
|
||||
"<correspondent> - <title>.<suffix>"
|
||||
"<title>.<suffix>"
|
||||
"""
|
||||
|
||||
for regex in cls.REGEXES.values():
|
||||
m = regex.match(os.path.basename(path))
|
||||
if m:
|
||||
properties = m.groupdict()
|
||||
cls._mangle_property(properties, "created")
|
||||
cls._mangle_property(properties, "correspondent")
|
||||
cls._mangle_property(properties, "title")
|
||||
cls._mangle_property(properties, "tags")
|
||||
cls._mangle_property(properties, "extension")
|
||||
return cls(**properties)
|
||||
|
||||
Reference in New Issue
Block a user