Merge branch 'ENH_text_consumer' of git://github.com/jat255/paperless into jat255-ENH_text_consumer

This commit is contained in:
Daniel Quinn
2018-09-09 20:52:59 +01:00
9 changed files with 203 additions and 23 deletions

View File

@@ -192,7 +192,11 @@ class Document(models.Model):
TYPE_JPG = "jpg"
TYPE_GIF = "gif"
TYPE_TIF = "tiff"
TYPES = (TYPE_PDF, TYPE_PNG, TYPE_JPG, TYPE_GIF, TYPE_TIF,)
TYPE_TXT = "txt"
TYPE_CSV = "csv"
TYPE_MD = "md"
TYPES = (TYPE_PDF, TYPE_PNG, TYPE_JPG, TYPE_GIF, TYPE_TIF,
TYPE_TXT, TYPE_CSV, TYPE_MD)
STORAGE_TYPE_UNENCRYPTED = "unencrypted"
STORAGE_TYPE_GPG = "gpg"
@@ -365,51 +369,52 @@ class FileInfo:
)
)
formats = "pdf|jpe?g|png|gif|tiff?|te?xt|md|csv"
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?)$",
r"\.(?P<extension>{})$".format(formats),
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?)$",
r"\.(?P<extension>{})$".format(formats),
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?)$",
r"\.(?P<extension>{})$".format(formats),
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?)$",
r"\.(?P<extension>{})$".format(formats),
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?)$",
r"\.(?P<extension>{})$".format(formats),
flags=re.IGNORECASE
)),
("correspondent-title", re.compile(
r"(?P<correspondent>.*) - "
r"(?P<title>.*)?"
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
r"\.(?P<extension>{})$".format(formats),
flags=re.IGNORECASE
)),
("title", re.compile(
r"(?P<title>.*)"
r"\.(?P<extension>pdf|jpe?g|png|gif|tiff?)$",
r"\.(?P<extension>{})$".format(formats),
flags=re.IGNORECASE
))
])