CLAM Formats¶
-
class
clam.common.formats.
AlpinoXMLFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'text/xml'¶
-
name
= 'Alpino XML'¶
-
scheme
= ''¶
-
-
class
clam.common.formats.
BinaryDataFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'application/octet-stream'¶
-
name
= 'Application-specific Binary Data'¶
-
-
class
clam.common.formats.
CSVFormat
(file, **kwargs)¶ -
attributes
= {'language': False, 'encoding': True}¶
-
mimetype
= 'text/csv'¶
-
name
= 'Comma separated file'¶
-
-
class
clam.common.formats.
DCOIFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'text/xml'¶
-
name
= 'DCOI format'¶
-
scheme
= ''¶
-
-
class
clam.common.formats.
DjVuFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'image/x-djvu'¶
-
name
= 'DjVu format'¶
-
-
class
clam.common.formats.
ExampleFormat
(file, **kwargs)¶ This is an Example format, please inspect its source code if you want to create custom formats!
-
allowcustomattributes
= True¶
-
httpheaders
()¶ HTTP headers to output for this format. Yields (key,value) tuples.
-
loadinlinemetadata
()¶ If there is metadata IN the actual file, this method should extract it and assign it to this object. Will be automatically called from constructor. Note that the file (CLAMFile) is accessible through self.file
-
mimetype
= 'text/plain'¶
-
saveinlinemetadata
()¶ If there is metadata that should be IN the actual file, this method can store it. Note that the file (CLAMFile) is accessible through self.file
-
scheme
= None¶
-
validate
()¶ Add your validation method here, should return True or False
-
-
class
clam.common.formats.
FoLiAXMLFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'text/xml'¶
-
name
= 'FoLiA XML'¶
-
scheme
= ''¶
-
-
class
clam.common.formats.
GifImageFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'image/gif'¶
-
name
= 'Gif Image'¶
-
-
class
clam.common.formats.
HTMLFormat
(file, **kwargs)¶ HTML Format Definition. This format has one required attribute: encoding
-
attributes
= {'language': False, 'encoding': True}¶
-
httpheaders
()¶ HTTP headers to output for this format. Yields (key,value) tuples.
-
mimetype
= 'text/html'¶
-
-
class
clam.common.formats.
JpegImageFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'image/jpeg'¶
-
name
= 'Jpeg Image'¶
-
-
class
clam.common.formats.
KBXMLFormat
(file, **kwargs)¶ -
mimetype
= 'text/xml'¶
-
name
= 'Koninklijke Bibliotheek XML-formaat'¶
-
scheme
= ''¶
-
-
class
clam.common.formats.
MP3AudioFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'audio/mpeg'¶
-
name
= 'MP3 Audio File'¶
-
-
class
clam.common.formats.
MSWordFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'application/msword'¶
-
name
= 'Microsoft Word format'¶
-
scheme
= ''¶
-
-
class
clam.common.formats.
MpegVideoFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'video/mpeg'¶
-
name
= 'Mpeg Video'¶
-
-
class
clam.common.formats.
OggAudioFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'audio/ogg'¶
-
name
= 'Ogg Audio File'¶
-
-
class
clam.common.formats.
OggVideoFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'audio/ogg'¶
-
name
= 'Ogg Video File'¶
-
-
class
clam.common.formats.
OpenDocumentTextFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'application/vnd.oasis.opendocument.text'¶
-
name
= 'Open Document Text Format'¶
-
-
class
clam.common.formats.
PDFFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'application/pdf'¶
-
name
= 'PDF'¶
-
-
class
clam.common.formats.
PlainTextFormat
(file, **kwargs)¶ Plain Text Format Definition. This format has one required attribute: encoding
-
attributes
= {'language': False, 'encoding': True}¶
-
httpheaders
()¶ HTTP headers to output for this format. Yields (key,value) tuples.
-
mimetype
= 'text/plain'¶
-
-
class
clam.common.formats.
PngImageFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'image/png'¶
-
name
= 'PNG Image'¶
-
-
class
clam.common.formats.
TICCLShadowOutputXML
(file, **kwargs)¶ -
mimetype
= 'text/xml'¶
-
name
= 'Ticcl Shadow Output'¶
-
scheme
= ''¶
-
-
class
clam.common.formats.
TICCLVariantOutputXML
(file, **kwargs)¶ -
mimetype
= 'text/xml'¶
-
name
= 'Ticcl Variant Output'¶
-
scheme
= ''¶
-
-
class
clam.common.formats.
TadpoleFormat
(file, **kwargs)¶ -
attributes
= {'morphologicalanalysis': ['yes', 'no'], 'postagging': ['yes', 'no'], 'parsing': ['yes', 'no'], 'mwudetection': ['yes', 'no'], 'tokenisation': 'yes', 'lemmatisation': ['yes', 'no']}¶
-
mimetype
= 'text/plain'¶
-
name
= 'Tadpole Columned Output Format'¶
-
-
class
clam.common.formats.
TiffImageFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'image/tiff'¶
-
name
= 'Tiff Image'¶
-
-
class
clam.common.formats.
UndefinedXMLFormat
(file, **kwargs)¶ -
mimetype
= 'text/xml'¶
-
name
= 'Undefined XML Format'¶
-
scheme
= ''¶
-
-
class
clam.common.formats.
WaveAudioFormat
(file, **kwargs)¶ -
attributes
= {}¶
-
mimetype
= 'audio/wav'¶
-
name
= 'Wave Audio File'¶
-