SickGear/lib/hachoir/parser/image/iptc.py
JackDandy 980e05cc99 Change Hachoir can't support PY2 so backport their PY3 to prevent a need for system dependant external binaries like mediainfo.
Backported 400 revisions from rev 1de4961-8897c5b (2018-2014).
Move core/benchmark, core/cmd_line, core/memory, core/profiler and core/timeout to core/optional/*
Remove metadata/qt*

PORT: Version 2.0a3 (inline with 3.0a3 @ f80c7d5).
Basic Support for XMP Packets.
tga: improvements to adhere more closely to the spec.
pdf: slightly improved parsing.
rar: fix TypeError on unknown block types.
Add MacRoman win32 codepage.
tiff/exif: support SubIFDs and tiled images.
Add method to export metadata in dictionary.
mpeg_video: don't attempt to parse Stream past length.
mpeg_video: parse ESCR correctly, add SCR value.
Change centralise CustomFragments.
field: don't set parser class if class is None, to enable autodetect.
field: add value/display for CustomFragment.
parser: inline warning to enable tracebacks in debug mode.
Fix empty bytestrings in makePrintable.
Fix contentSize in jpeg.py to account for image_data blocks.
Fix the ELF parser.
Enhance the AR archive parser.
elf parser: fix wrong wrong fields order in parsing little endian section flags.
elf parser: add s390 as a machine type.
Flesh out mp4 parser.

PORT: Version 2.0a1 (inline with 3.0a1).
Major refactoring and PEP8.
Fix ResourceWarning warnings on files. Add a close() method and support for the context manager protocol ("with obj: ...") to parsers, input and output streams.
metadata: get comment from ZIP.
Support for InputIOStream.read(0).
Fix sizeGe when size is None.
Remove unused new_seekable_field_set file.
Remove parser Mapsforge .map.
Remove parser Parallel Realities Starfighter .pak files.
sevenzip: fix for newer archives.
java: update access flags and modifiers for Java 1.7 and update description text for most recent Java.
Support ustar prefix field in tar archives.
Remove file_system* parsers.
Remove misc parsers 3d0, 3ds, gnome_keyring, msoffice*, mstask, ole*, word*.
Remove program parsers macho, nds, prc.
Support non-8bit Character subclasses.
Python parser supports Python 3.7.
Enhance mpeg_ts parser to support MTS/M2TS.
Support for creation date in tiff.
Change don't hardcode errno constant.

PORT: 1.9.1
Internal Only: The following are legacy reference to upstream commit messages.
Relevant changes up to b0a115f8.
Use integer division.
Replace HACHOIR_ERRORS with Exception.
Fix metadata.Data: make it sortable.
Import fixes from e7de492.
PORT: Version 2.0a1 (inline with 3.0a1 @ e9f8fad).
Replace hachoir.core.field with hachoir.field
Replace hachoir.core.stream with hachoir.stream
Remove the compatibility module for PY1.5 to PY2.5.
metadata: support TIFF picture.
metadata: fix string normalization.
metadata: fix datetime regex Fix hachoir bug #57.
FileFromInputStream: fix comparison between None and an int.
InputIOStream: open the file in binary mode.
2018-03-28 00:43:11 +01:00

117 lines
4.2 KiB
Python

"""
IPTC metadata parser (can be found in a JPEG picture for example)
Sources:
- Image-MetaData Perl module:
http://www.annocpan.org/~BETTELLI/Image-MetaData-JPEG-0.15/...
...lib/Image/MetaData/JPEG/TagLists.pod
- IPTC tag name and description:
http://peccatte.karefil.com/software/IPTCTableau.pdf
Author: Victor Stinner
"""
from hachoir.field import (FieldSet, ParserError,
UInt8, UInt16, String, RawBytes, NullBytes)
from hachoir.core.text_handler import textHandler, hexadecimal
def IPTC_String(parent, name, desc=None):
# Charset may be utf-8, ISO-8859-1, or ...
return String(parent, name, parent["size"].value, desc,
strip=" ")
dataset1 = {
}
dataset2 = {
0: ("record_version", "Record version (2 for JPEG)", UInt16),
5: ("obj_name", "Object name", None),
7: ("edit_stat", "Edit status", None),
10: ("urgency", "Urgency", UInt8),
15: ("category[]", "Category", None),
22: ("fixture", "Fixture identifier", IPTC_String),
25: ("keyword[]", "Keywords", IPTC_String),
30: ("release_date", "Release date", IPTC_String),
35: ("release_time", "Release time", IPTC_String),
40: ("instruction", "Special instructions", IPTC_String),
55: ("date_created", "Date created", IPTC_String),
60: ("time_created", "Time created (ISO 8601)", IPTC_String),
65: ("originating_prog", "Originating program", IPTC_String),
70: ("prog_ver", "Program version", IPTC_String),
80: ("author", "By-line (Author)", IPTC_String),
85: ("author_job", "By-line (Author precision)", IPTC_String),
90: ("city", "City", IPTC_String),
95: ("state", "Province / State", IPTC_String),
100: ("country_code", "Country / Primary location code", IPTC_String),
101: ("country_name", "Country / Primary location name", IPTC_String),
103: ("trans_ref", "Original transmission reference", IPTC_String),
105: ("headline", "Headline", IPTC_String),
110: ("credit", "Credit", IPTC_String),
115: ("source", "Source", IPTC_String),
116: ("copyright", "Copyright notice", IPTC_String),
120: ("caption", "Caption/Abstract", IPTC_String),
122: ("writer", "Writer/editor", IPTC_String),
231: ("history[]", "Document history (timestamp)", IPTC_String)
}
datasets = {1: dataset1, 2: dataset2}
class IPTC_Size(FieldSet):
def __init__(self, *args, **kw):
FieldSet.__init__(self, *args, **kw)
value = 0
for field in self:
value <<= 15
value += (field.value & 0x7fff)
self.createValue = lambda: value
def createFields(self):
while True:
field = UInt16(self, "value[]")
yield field
if field.value < 0x8000:
break
class IPTC_Chunk(FieldSet):
def __init__(self, *args, **kw):
FieldSet.__init__(self, *args, **kw)
number = self["dataset_nb"].value
self.dataset_info = None
if number in datasets:
tag = self["tag"].value
if tag in datasets[number]:
self.dataset_info = datasets[number][tag]
self._name = self.dataset_info[0]
self._description = self.dataset_info[1]
size_chunk = self["size"]
self._size = 3 * 8 + size_chunk.size + size_chunk.value * 8
def createFields(self):
yield textHandler(UInt8(self, "signature", "IPTC signature (0x1c)"), hexadecimal)
if self["signature"].value != 0x1C:
raise ParserError("Wrong IPTC signature")
yield textHandler(UInt8(self, "dataset_nb", "Dataset number"), hexadecimal)
yield UInt8(self, "tag", "Tag")
yield IPTC_Size(self, "size", "Content size")
size = self["size"].value
if 0 < size:
if self.dataset_info:
cls = self.dataset_info[2]
else:
cls = None
if cls:
yield cls(self, "content")
else:
yield RawBytes(self, "content", size)
class IPTC(FieldSet):
def createFields(self):
while 5 <= (self._size - self.current_size) // 8:
yield IPTC_Chunk(self, "chunk[]")
size = (self._size - self.current_size) // 8
if 0 < size:
yield NullBytes(self, "padding", size)