matthias/mayan-edms
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Refactored the converter backend system

Browse Source
This commit is contained in:
Roberto Rosario
2011-07-13 22:53:33 -04:00
parent 082c3e699c
commit 415f0c8daa
16 changed files with 317 additions and 238 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
apps/converter/__init__.py
View File

@@ -2,10 +2,6 @@ from django.utils.translation import ugettext_lazy as _
from navigation.api import register_sidebar_template from navigation.api import register_sidebar_template
TRANFORMATION_CHOICES = {
u'rotate': u'-rotate %(degrees)d'
}
formats_list = {'text': _('file formats'), 'view': 'formats_list', 'famfam': 'pictures'} formats_list = {'text': _('file formats'), 'view': 'formats_list', 'famfam': 'pictures'}
register_sidebar_template(['formats_list'], 'converter_file_formats_help.html') register_sidebar_template(['formats_list'], 'converter_file_formats_help.html')

70
apps/converter/api.py
View File

@@ -3,62 +3,28 @@ import subprocess
from django.utils.importlib import import_module from django.utils.importlib import import_module
from django.template.defaultfilters import slugify from django.template.defaultfilters import slugify
from django.core.exceptions import ImproperlyConfigured
from converter.conf.settings import UNPAPER_PATH
from converter.conf.settings import OCR_OPTIONS
from converter.conf.settings import DEFAULT_OPTIONS
from converter.conf.settings import LOW_QUALITY_OPTIONS
from converter.conf.settings import HIGH_QUALITY_OPTIONS
from converter.conf.settings import PRINT_QUALITY_OPTIONS
from converter.conf.settings import GRAPHICS_BACKEND
from converter.conf.settings import UNOCONV_PATH
from converter.exceptions import UnpaperError, OfficeConversionError
from common import TEMPORARY_DIRECTORY from common import TEMPORARY_DIRECTORY
from documents.utils import document_save_to_temp_dir from documents.utils import document_save_to_temp_dir
DEFAULT_ZOOM_LEVEL = 100 from converter.conf.settings import UNPAPER_PATH
DEFAULT_ROTATION = 0 from converter.conf.settings import OCR_OPTIONS
DEFAULT_PAGE_INDEX_NUMBER = 0 from converter.conf.settings import UNOCONV_PATH
DEFAULT_FILE_FORMAT = u'jpg' from converter.exceptions import UnpaperError, OfficeConversionError
DEFAULT_OCR_FILE_FORMAT = u'tif' from converter.utils import load_backend
from converter.literals import DEFAULT_PAGE_INDEX_NUMBER, \
QUALITY_DEFAULT = u'quality_default' DEFAULT_OCR_FILE_FORMAT, QUALITY_DEFAULT, DEFAULT_ZOOM_LEVEL, \
QUALITY_LOW = u'quality_low' DEFAULT_ROTATION, DEFAULT_FILE_FORMAT, QUALITY_PRINT
QUALITY_HIGH = u'quality_high'
QUALITY_PRINT = u'quality_print'
QUALITY_SETTINGS = {
QUALITY_DEFAULT: DEFAULT_OPTIONS,
QUALITY_LOW: LOW_QUALITY_OPTIONS,
QUALITY_HIGH: HIGH_QUALITY_OPTIONS,
QUALITY_PRINT: PRINT_QUALITY_OPTIONS
}
CONVERTER_OFFICE_FILE_EXTENSIONS = [ CONVERTER_OFFICE_FILE_EXTENSIONS = [
u'ods', u'docx', u'doc' u'ods', u'docx', u'doc'
] ]
def _lazy_load(fn):
_cached = []
def _decorated():
if not _cached:
_cached.append(fn())
return _cached[0]
return _decorated
@_lazy_load
def _get_backend():
return import_module(GRAPHICS_BACKEND)
try: try:
backend = _get_backend() backend = load_backend().ConverterClass()
except ImportError: except ImproperlyConfigured:
raise ImportError(u'Missing or incorrect converter backend: %s' % GRAPHICS_BACKEND) raise ImproperlyConfigured(u'Missing or incorrect converter backend: %s' % GRAPHICS_BACKEND)
def cleanup(filename): def cleanup(filename):
@@ -173,7 +139,7 @@ def convert(input_filepath, *args, **kwargs):
if format == u'jpg': if format == u'jpg':
extra_options += u' -quality 85' extra_options += u' -quality 85'
try: try:
backend.execute_convert(input_filepath=input_arg, arguments=extra_options, output_filepath=u'%s:%s' % (file_format, output_filepath), quality=quality) backend.convert_file(input_filepath=input_arg, arguments=extra_options, output_filepath=u'%s:%s' % (file_format, output_filepath), quality=quality)
finally: finally:
if cleanup_files: if cleanup_files:
cleanup(input_filepath) cleanup(input_filepath)
@@ -185,7 +151,7 @@ def convert(input_filepath, *args, **kwargs):
def get_page_count(input_filepath): def get_page_count(input_filepath):
try: try:
return len(backend.execute_identify(unicode(input_filepath)).splitlines()) return len(backend.identify_file(unicode(input_filepath)).splitlines())
except: except:
#TODO: send to other page number identifying program #TODO: send to other page number identifying program
return 1 return 1
@@ -195,7 +161,7 @@ def get_document_dimensions(document, *args, **kwargs):
document_filepath = create_image_cache_filename(document.checksum, *args, **kwargs) document_filepath = create_image_cache_filename(document.checksum, *args, **kwargs)
if os.path.exists(document_filepath): if os.path.exists(document_filepath):
options = [u'-format', u'%w %h'] options = [u'-format', u'%w %h']
return [int(dimension) for dimension in backend.execute_identify(unicode(document_filepath), options).split()] return [int(dimension) for dimension in backend.identify_file(unicode(document_filepath), options).split()]
else: else:
return [0, 0] return [0, 0]
@@ -219,13 +185,13 @@ def convert_document_for_ocr(document, page=DEFAULT_PAGE_INDEX_NUMBER, file_form
transformation_string, warnings = document_page.get_transformation_string() transformation_string, warnings = document_page.get_transformation_string()
#Apply default transformations #Apply default transformations
backend.execute_convert(input_filepath=input_arg, quality=QUALITY_HIGH, arguments=transformation_string, output_filepath=transformation_output_file) backend.convert_file(input_filepath=input_arg, quality=QUALITY_HIGH, arguments=transformation_string, output_filepath=transformation_output_file)
#Do OCR operations #Do OCR operations
backend.execute_convert(input_filepath=transformation_output_file, arguments=OCR_OPTIONS, output_filepath=unpaper_input_file) backend.convert_file(input_filepath=transformation_output_file, arguments=OCR_OPTIONS, output_filepath=unpaper_input_file)
# Process by unpaper # Process by unpaper
execute_unpaper(input_filepath=unpaper_input_file, output_filepath=unpaper_output_file) execute_unpaper(input_filepath=unpaper_input_file, output_filepath=unpaper_output_file)
# Convert to tif # Convert to tif
backend.execute_convert(input_filepath=unpaper_output_file, output_filepath=convert_output_file) backend.convert_file(input_filepath=unpaper_output_file, output_filepath=convert_output_file)
finally: finally:
cleanup(transformation_output_file) cleanup(transformation_output_file)
cleanup(unpaper_input_file) cleanup(unpaper_input_file)

43
apps/converter/backends/__init__.py
View File

@@ -0,0 +1,43 @@
class ConverterBase(object):
"""
Base class that all backend classes must inherit
"""
def identify_file(self, input_filepath, *args, **kwargs):
raise NotImplementedError("Your %s class has not defined a identify_file() method, which is required." % self.__class__.__name__)
def identify_document(self, document, *args, **kwargs):
raise NotImplementedError("Your %s class has not defined a identify_document() method, which is required." % self.__class__.__name__)
def convert_file(self, input_filepath, *args, **kwargs):
raise NotImplementedError("Your %s class has not defined a convert_file() method, which is required." % self.__class__.__name__)
def convert_document(self, document, *args, **kwargs):
raise NotImplementedError("Your %s class has not defined a convert_document() method, which is required." % self.__class__.__name__)
def get_format_list(self):
raise NotImplementedError("Your %s class has not defined a get_format_list() method, which is required." % self.__class__.__name__)
def get_available_transformations(self):
raise NotImplementedError("Your %s class has not defined a get_available_transformations() method, which is required." % self.__class__.__name__)
def get_available_transformations_labels(self):
return ([(name, data['label']) for name, data in self.get_available_transformations().items()])
def get_transformation_string(self, transformation_list):
transformations = []
warnings = []
transformation_choices = self.get_available_transformations()
for transformation in transformation_list:
try:
if transformation['transformation'] in transformation_choices:
transformations.append(
transformation_choices[transformation['transformation']]['command_line'] % eval(
transformation['arguments']
)
)
except Exception, e:
warnings.append(e)
return u' '.join(transformations), warnings

71
apps/converter/backends/graphicsmagick.py
View File

@@ -1,71 +0,0 @@
import subprocess
import re
from converter.conf.settings import GM_PATH
from converter.conf.settings import GM_SETTINGS
from converter.api import QUALITY_DEFAULT, QUALITY_SETTINGS
from converter.exceptions import ConvertError, UnknownFormat, IdentifyError
CONVERTER_ERROR_STRING_NO_DECODER = u'No decode delegate for this image format'
CONVERTER_ERROR_STARTS_WITH = u'starts with'
def execute_identify(input_filepath, arguments=None):
command = []
command.append(unicode(GM_PATH))
command.append(u'identify')
if arguments:
command.extend(arguments)
command.append(unicode(input_filepath))
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
raise IdentifyError(proc.stderr.readline())
return proc.stdout.read()
def execute_convert(input_filepath, output_filepath, quality=QUALITY_DEFAULT, arguments=None):
command = []
command.append(unicode(GM_PATH))
command.append(u'convert')
command.extend(unicode(QUALITY_SETTINGS[quality]).split())
command.extend(unicode(GM_SETTINGS).split())
command.append(unicode(input_filepath))
if arguments:
command.extend(unicode(arguments).split())
command.append(unicode(output_filepath))
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
#Got an error from convert program
error_line = proc.stderr.readline()
if (CONVERTER_ERROR_STRING_NO_DECODER in error_line) or (CONVERTER_ERROR_STARTS_WITH in error_line):
#Try to determine from error message which class of error is it
raise UnknownFormat
else:
raise ConvertError(error_line)
def get_format_list():
"""
Call GraphicsMagick to parse all of it's supported file formats, and
return a list of the names and descriptions
"""
format_regex = re.compile(' *([A-Z0-9]+)[*]? +([A-Z0-9]+) +([rw\-+]+) *(.*).*')
formats = []
command = []
command.append(unicode(GM_PATH))
command.append(u'convert')
command.append(u'-list')
command.append(u'formats')
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
raise ConvertError(proc.stderr.readline())
for line in proc.stdout.readlines():
fields = format_regex.findall(line)
if fields:
formats.append((fields[0][0], fields[0][3]))
return formats

0
apps/converter/backends/graphicsmagick/__init__.py Normal file
View File

85
apps/converter/backends/graphicsmagick/base.py Normal file
View File

@@ -0,0 +1,85 @@
import subprocess
import re
from django.utils.translation import ugettext_lazy as _
from converter.conf.settings import GM_PATH
from converter.conf.settings import GM_SETTINGS
from converter.literals import QUALITY_DEFAULT, QUALITY_SETTINGS
from converter.exceptions import ConvertError, UnknownFormat, IdentifyError
from converter.backends import ConverterBase
CONVERTER_ERROR_STRING_NO_DECODER = u'No decode delegate for this image format'
CONVERTER_ERROR_STARTS_WITH = u'starts with'
class ConverterClass(ConverterBase):
def identify_file(self, input_filepath, arguments=None):
command = []
command.append(unicode(GM_PATH))
command.append(u'identify')
if arguments:
command.extend(arguments)
command.append(unicode(input_filepath))
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
raise IdentifyError(proc.stderr.readline())
return proc.stdout.read()
def convert_file(self, input_filepath, output_filepath, quality=QUALITY_DEFAULT, arguments=None):
command = []
command.append(unicode(GM_PATH))
command.append(u'convert')
command.extend(unicode(QUALITY_SETTINGS[quality]).split())
command.extend(unicode(GM_SETTINGS).split())
command.append(unicode(input_filepath))
if arguments:
command.extend(unicode(arguments).split())
command.append(unicode(output_filepath))
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
#Got an error from convert program
error_line = proc.stderr.readline()
if (CONVERTER_ERROR_STRING_NO_DECODER in error_line) or (CONVERTER_ERROR_STARTS_WITH in error_line):
#Try to determine from error message which class of error is it
raise UnknownFormat
else:
raise ConvertError(error_line)
def get_format_list(self):
"""
Call GraphicsMagick to parse all of it's supported file formats, and
return a list of the names and descriptions
"""
format_regex = re.compile(' *([A-Z0-9]+)[*]? +([A-Z0-9]+) +([rw\-+]+) *(.*).*')
formats = []
command = []
command.append(unicode(GM_PATH))
command.append(u'convert')
command.append(u'-list')
command.append(u'formats')
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
raise ConvertError(proc.stderr.readline())
for line in proc.stdout.readlines():
fields = format_regex.findall(line)
if fields:
formats.append((fields[0][0], fields[0][3]))
return formats
def get_available_transformations(self):
return {
'rotate': {
'label': _(u'Rotate [degrees]'),
'arguments': [{'name': 'degrees'}],
'command_line': u'-rotate %(degrees)d'
}
}

68
apps/converter/backends/imagemagick.py
View File

@@ -1,68 +0,0 @@
import subprocess
import re
from converter.conf.settings import IM_IDENTIFY_PATH
from converter.conf.settings import IM_CONVERT_PATH
from converter.api import QUALITY_DEFAULT, QUALITY_SETTINGS
from converter.exceptions import ConvertError, UnknownFormat, \
IdentifyError
CONVERTER_ERROR_STRING_NO_DECODER = u'no decode delegate for this image format'
def execute_identify(input_filepath, arguments=None):
command = []
command.append(unicode(IM_IDENTIFY_PATH))
if arguments:
command.extend(arguments)
command.append(unicode(input_filepath))
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
raise IdentifyError(proc.stderr.readline())
return proc.stdout.read()
def execute_convert(input_filepath, output_filepath, quality=QUALITY_DEFAULT, arguments=None):
command = []
command.append(unicode(IM_CONVERT_PATH))
command.extend(unicode(QUALITY_SETTINGS[quality]).split())
command.append(unicode(input_filepath))
if arguments:
command.extend(unicode(arguments).split())
command.append(unicode(output_filepath))
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
#Got an error from convert program
error_line = proc.stderr.readline()
if CONVERTER_ERROR_STRING_NO_DECODER in error_line:
#Try to determine from error message which class of error is it
raise UnknownFormat
else:
raise ConvertError(error_line)
def get_format_list():
"""
Call ImageMagick to parse all of it's supported file formats, and
return a list of the names and descriptions
"""
format_regex = re.compile(' *([A-Z0-9]+)[*]? +([A-Z0-9]+) +([rw\-+]+) *(.*).*')
formats = []
command = []
command.append(unicode(IM_CONVERT_PATH))
command.append(u'-list')
command.append(u'format')
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
raise ConvertError(proc.stderr.readline())
for line in proc.stdout.readlines():
fields = format_regex.findall(line)
if fields:
formats.append((fields[0][0], fields[0][3]))
return formats

0
apps/converter/backends/imagemagick/__init__.py Normal file
View File

82
apps/converter/backends/imagemagick/base.py Normal file
View File

@@ -0,0 +1,82 @@
import subprocess
import re
from django.utils.translation import ugettext_lazy as _
from converter.conf.settings import IM_IDENTIFY_PATH
from converter.conf.settings import IM_CONVERT_PATH
from converter.api import QUALITY_DEFAULT, QUALITY_SETTINGS
from converter.exceptions import ConvertError, UnknownFormat, \
IdentifyError
from converter.backends import ConverterBase
CONVERTER_ERROR_STRING_NO_DECODER = u'no decode delegate for this image format'
class ConverterClass(ConverterBase):
def identify_file(self, input_filepath, arguments=None):
command = []
command.append(unicode(IM_IDENTIFY_PATH))
if arguments:
command.extend(arguments)
command.append(unicode(input_filepath))
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
raise IdentifyError(proc.stderr.readline())
return proc.stdout.read()
def convert_file(self, input_filepath, output_filepath, quality=QUALITY_DEFAULT, arguments=None):
command = []
command.append(unicode(IM_CONVERT_PATH))
command.extend(unicode(QUALITY_SETTINGS[quality]).split())
command.append(unicode(input_filepath))
if arguments:
command.extend(unicode(arguments).split())
command.append(unicode(output_filepath))
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
#Got an error from convert program
error_line = proc.stderr.readline()
if CONVERTER_ERROR_STRING_NO_DECODER in error_line:
#Try to determine from error message which class of error is it
raise UnknownFormat
else:
raise ConvertError(error_line)
def get_format_list(self):
"""
Call ImageMagick to parse all of it's supported file formats, and
return a list of the names and descriptions
"""
format_regex = re.compile(' *([A-Z0-9]+)[*]? +([A-Z0-9]+) +([rw\-+]+) *(.*).*')
formats = []
command = []
command.append(unicode(IM_CONVERT_PATH))
command.append(u'-list')
command.append(u'format')
proc = subprocess.Popen(command, close_fds=True, stderr=subprocess.PIPE, stdout=subprocess.PIPE)
return_code = proc.wait()
if return_code != 0:
raise ConvertError(proc.stderr.readline())
for line in proc.stdout.readlines():
fields = format_regex.findall(line)
if fields:
formats.append((fields[0][0], fields[0][3]))
return formats
def get_available_transformations(self):
return {
'rotate': {
'label': _(u'Rotate [degrees]'),
'arguments': [{'name': 'degrees'}],
'command_line': u'-rotate %(degrees)d'
}
}

22
apps/converter/literals.py Normal file
View File

@@ -0,0 +1,22 @@
from converter.conf.settings import DEFAULT_OPTIONS
from converter.conf.settings import LOW_QUALITY_OPTIONS
from converter.conf.settings import HIGH_QUALITY_OPTIONS
from converter.conf.settings import PRINT_QUALITY_OPTIONS
DEFAULT_ZOOM_LEVEL = 100
DEFAULT_ROTATION = 0
DEFAULT_PAGE_INDEX_NUMBER = 0
DEFAULT_FILE_FORMAT = u'jpg'
DEFAULT_OCR_FILE_FORMAT = u'tif'
QUALITY_DEFAULT = u'quality_default'
QUALITY_LOW = u'quality_low'
QUALITY_HIGH = u'quality_high'
QUALITY_PRINT = u'quality_print'
QUALITY_SETTINGS = {
QUALITY_DEFAULT: DEFAULT_OPTIONS,
QUALITY_LOW: LOW_QUALITY_OPTIONS,
QUALITY_HIGH: HIGH_QUALITY_OPTIONS,
QUALITY_PRINT: PRINT_QUALITY_OPTIONS
}

55
apps/converter/utils.py
View File

@@ -1,6 +1,10 @@
import os
from django.core.exceptions import ImproperlyConfigured
from django.utils.importlib import import_module
#http://stackoverflow.com/questions/123198/how-do-i-copy-a-file-in-python #http://stackoverflow.com/questions/123198/how-do-i-copy-a-file-in-python
def copyfile(source, dest, buffer_size=1024 * 1024): def copyfile(source, dest, buffer_size=1024 * 1024):
""" """
Copy a file from source to dest. source and dest Copy a file from source to dest. source and dest
@@ -21,3 +25,50 @@ def copyfile(source, dest, buffer_size=1024 * 1024):
source.close() source.close()
dest.close() dest.close()
def _lazy_load(fn):
_cached = []
def _decorated():
if not _cached:
_cached.append(fn())
return _cached[0]
return _decorated
@_lazy_load
def load_backend():
from converter.conf.settings import GRAPHICS_BACKEND as backend_name
try:
module = import_module('.base', 'converter.backends.%s' % backend_name)
import warnings
warnings.warn(
"Short names for CONVERTER_BACKEND are deprecated; prepend with 'converter.backends.'",
PendingDeprecationWarning
)
return module
except ImportError, e:
# Look for a fully qualified converter backend name
try:
return import_module('.base', backend_name)
except ImportError, e_user:
# The converter backend wasn't found. Display a helpful error message
# listing all possible (built-in) converter backends.
backend_dir = os.path.join(os.path.dirname(__file__), 'backends')
try:
available_backends = [f for f in os.listdir(backend_dir)
if os.path.isdir(os.path.join(backend_dir, f))
and not f.startswith('.')]
except EnvironmentError:
available_backends = []
available_backends.sort()
if backend_name not in available_backends:
error_msg = ("%r isn't an available converter backend. \n" +
"Try using converter.backends.XXX, where XXX is one of:\n %s\n" +
"Error was: %s") % \
(backend_name, ", ".join(map(repr, available_backends)), e_user)
raise ImproperlyConfigured(error_msg)
else:
raise # If there's some other error, this must be an error in Mayan itself.

6
apps/documents/conf/settings.py
View File

@@ -18,10 +18,6 @@ def default_uuid():
"""unicode(uuid.uuid4())""" """unicode(uuid.uuid4())"""
return unicode(uuid.uuid4()) return unicode(uuid.uuid4())
available_transformations = {
'rotate': {'label': _(u'Rotate [degrees]'), 'arguments': [{'name': 'degrees'}]}
}
register_settings( register_settings(
namespace=u'documents', namespace=u'documents',
module=u'documents.conf.settings', module=u'documents.conf.settings',
@@ -31,8 +27,6 @@ register_settings(
{'name': u'UUID_FUNCTION', 'global_name': u'DOCUMENTS_UUID_FUNCTION', 'default': default_uuid}, {'name': u'UUID_FUNCTION', 'global_name': u'DOCUMENTS_UUID_FUNCTION', 'default': default_uuid},
# Storage # Storage
{'name': u'STORAGE_BACKEND', 'global_name': u'DOCUMENTS_STORAGE_BACKEND', 'default': FileBasedStorage}, {'name': u'STORAGE_BACKEND', 'global_name': u'DOCUMENTS_STORAGE_BACKEND', 'default': FileBasedStorage},
# Transformations
{'name': u'AVAILABLE_TRANSFORMATIONS', 'global_name': u'DOCUMENTS_AVAILABLE_TRANSFORMATIONS', 'default': available_transformations},
# Usage # Usage
{'name': u'PREVIEW_SIZE', 'global_name': u'DOCUMENTS_PREVIEW_SIZE', 'default': u'640x480'}, {'name': u'PREVIEW_SIZE', 'global_name': u'DOCUMENTS_PREVIEW_SIZE', 'default': u'640x480'},
{'name': u'PRINT_SIZE', 'global_name': u'DOCUMENTS_PRINT_SIZE', 'default': u'1400'}, {'name': u'PRINT_SIZE', 'global_name': u'DOCUMENTS_PRINT_SIZE', 'default': u'1400'},

22
apps/documents/models.py
View File

@@ -12,16 +12,13 @@ from python_magic import magic
from taggit.managers import TaggableManager from taggit.managers import TaggableManager
from dynamic_search.api import register from dynamic_search.api import register
from converter.api import get_page_count from converter.api import get_page_count
from converter import TRANFORMATION_CHOICES from converter.api import backend
from documents.conf.settings import CHECKSUM_FUNCTION from documents.conf.settings import CHECKSUM_FUNCTION
from documents.conf.settings import UUID_FUNCTION from documents.conf.settings import UUID_FUNCTION
from documents.conf.settings import STORAGE_BACKEND from documents.conf.settings import STORAGE_BACKEND
from documents.conf.settings import AVAILABLE_TRANSFORMATIONS
from documents.managers import RecentDocumentManager from documents.managers import RecentDocumentManager
available_transformations = ([(name, data['label']) for name, data in AVAILABLE_TRANSFORMATIONS.items()])
def get_filename_from_uuid(instance, filename): def get_filename_from_uuid(instance, filename):
""" """
@@ -263,20 +260,7 @@ class DocumentPage(models.Model):
return ('document_page_view', [self.pk]) return ('document_page_view', [self.pk])
def get_transformation_string(self): def get_transformation_string(self):
transformation_list = [] return backend.get_transformation_string(self.documentpagetransformation_set.values('transformation', 'arguments'))
warnings = []
for page_transformation in self.documentpagetransformation_set.all():
try:
if page_transformation.transformation in TRANFORMATION_CHOICES:
transformation_list.append(
TRANFORMATION_CHOICES[page_transformation.transformation] % eval(
page_transformation.arguments
)
)
except Exception, e:
warnings.append(e)
return u' '.join(transformation_list), warnings
class DocumentPageTransformation(models.Model): class DocumentPageTransformation(models.Model):
@@ -286,7 +270,7 @@ class DocumentPageTransformation(models.Model):
""" """
document_page = models.ForeignKey(DocumentPage, verbose_name=_(u'document page')) document_page = models.ForeignKey(DocumentPage, verbose_name=_(u'document page'))
order = models.PositiveIntegerField(default=0, blank=True, null=True, verbose_name=_(u'order'), db_index=True) order = models.PositiveIntegerField(default=0, blank=True, null=True, verbose_name=_(u'order'), db_index=True)
transformation = models.CharField(choices=available_transformations, max_length=128, verbose_name=_(u'transformation')) transformation = models.CharField(choices=backend.get_available_transformations_labels(), max_length=128, verbose_name=_(u'transformation'))
arguments = models.TextField(blank=True, null=True, verbose_name=_(u'arguments'), help_text=_(u'Use dictionaries to indentify arguments, example: {\'degrees\':90}')) arguments = models.TextField(blank=True, null=True, verbose_name=_(u'arguments'), help_text=_(u'Use dictionaries to indentify arguments, example: {\'degrees\':90}'))
def __unicode__(self): def __unicode__(self):

4
apps/documents/urls.py
View File

@@ -1,14 +1,12 @@
from django.conf.urls.defaults import patterns, url from django.conf.urls.defaults import patterns, url
from converter.api import QUALITY_HIGH, QUALITY_PRINT from converter.literals import QUALITY_HIGH, QUALITY_PRINT
from documents.conf.settings import PREVIEW_SIZE from documents.conf.settings import PREVIEW_SIZE
from documents.conf.settings import PRINT_SIZE from documents.conf.settings import PRINT_SIZE
from documents.conf.settings import THUMBNAIL_SIZE from documents.conf.settings import THUMBNAIL_SIZE
from documents.conf.settings import DISPLAY_SIZE from documents.conf.settings import DISPLAY_SIZE
from documents.conf.settings import MULTIPAGE_PREVIEW_SIZE from documents.conf.settings import MULTIPAGE_PREVIEW_SIZE
#from documents.literals import UPLOAD_SOURCE_LOCAL, \
# UPLOAD_SOURCE_STAGING, UPLOAD_SOURCE_USER_STAGING
urlpatterns = patterns('documents.views', urlpatterns = patterns('documents.views',
url(r'^list/$', 'document_list', (), 'document_list'), url(r'^list/$', 'document_list', (), 'document_list'),

6
apps/sources/models.py
View File

@@ -4,14 +4,12 @@ from django.contrib.contenttypes.models import ContentType
from django.contrib.contenttypes import generic from django.contrib.contenttypes import generic
from documents.models import DocumentType from documents.models import DocumentType
from documents.conf.settings import AVAILABLE_TRANSFORMATIONS
from documents.managers import RecentDocumentManager from documents.managers import RecentDocumentManager
from metadata.models import MetadataType from metadata.models import MetadataType
from converter.api import backend
from sources.managers import SourceTransformationManager from sources.managers import SourceTransformationManager
available_transformations = ([(name, data['label']) for name, data in AVAILABLE_TRANSFORMATIONS.items()])
SOURCE_UNCOMPRESS_CHOICE_Y = 'y' SOURCE_UNCOMPRESS_CHOICE_Y = 'y'
SOURCE_UNCOMPRESS_CHOICE_N = 'n' SOURCE_UNCOMPRESS_CHOICE_N = 'n'
SOURCE_UNCOMPRESS_CHOICE_ASK = 'a' SOURCE_UNCOMPRESS_CHOICE_ASK = 'a'
@@ -164,7 +162,7 @@ class SourceTransformation(models.Model):
object_id = models.PositiveIntegerField() object_id = models.PositiveIntegerField()
content_object = generic.GenericForeignKey('content_type', 'object_id') content_object = generic.GenericForeignKey('content_type', 'object_id')
order = models.PositiveIntegerField(default=0, blank=True, null=True, verbose_name=_(u'order'), db_index=True) order = models.PositiveIntegerField(default=0, blank=True, null=True, verbose_name=_(u'order'), db_index=True)
transformation = models.CharField(choices=available_transformations, max_length=128, verbose_name=_(u'transformation')) transformation = models.CharField(choices=backend.get_available_transformations_labels(), max_length=128, verbose_name=_(u'transformation'))
arguments = models.TextField(blank=True, null=True, verbose_name=_(u'arguments'), help_text=_(u'Use dictionaries to indentify arguments, example: {\'degrees\':90}')) arguments = models.TextField(blank=True, null=True, verbose_name=_(u'arguments'), help_text=_(u'Use dictionaries to indentify arguments, example: {\'degrees\':90}'))
objects = SourceTransformationManager() objects = SourceTransformationManager()

17
apps/sources/staging.py
View File

@@ -8,7 +8,6 @@ from django.utils.translation import ugettext
from django.contrib import messages from django.contrib import messages
from django.utils.translation import ugettext_lazy as _ from django.utils.translation import ugettext_lazy as _
from converter import TRANFORMATION_CHOICES
from converter.api import convert, cache_cleanup from converter.api import convert, cache_cleanup
DEFAULT_STAGING_DIRECTORY = u'/tmp' DEFAULT_STAGING_DIRECTORY = u'/tmp'
@@ -136,13 +135,13 @@ class StagingFile(object):
def get_transformation_string(transformations): def get_transformation_string(transformations):
transformation_list = [] transformation_list = []
errors = [] errors = []
for transformation in transformations: #for transformation in transformations:
try: # try:
if transformation['name'] in TRANFORMATION_CHOICES: # if transformation['name'] in TRANFORMATION_CHOICES:
output = TRANFORMATION_CHOICES[transformation['name']] % eval(transformation['arguments']) # output = TRANFORMATION_CHOICES[transformation['name']] % eval(transformation['arguments'])
transformation_list.append(output) # transformation_list.append(output)
except Exception, e: # except Exception, e:
errors.append(e) # errors.append(e)
tranformation_string = ' '.join(transformation_list) #tranformation_string = ' '.join(transformation_list)
return tranformation_string, errors return tranformation_string, errors