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

Add support for new document page structure

Browse Source 
Documents now have their own dedicated DocumentPage
submodel. The old DocumentPage is now called DocumentVersionPage.
This allows mappings between document pages and document version
pages, allowing renumbering, appending pages.
DocumentPages have a content_object to map them to any other
object. For now they only map to DocumentVersionPages.
New option added to the version upload form to append the
pages of the new version.
A new view was added to just append new pages with wraps the
new document version upload form and hides the append pages
checkbox set to True.
Add a new action, reset_pages to reset the pages of the
document to those of the latest version.

Missing: appending tests, checks for proper content_object in OCR and
document parsing.

Author: Roberto Rosario <roberto.rosario@mayan-edms.com>
Date:   Thu Oct 11 12:00:25 2019 -0400
This commit is contained in:
Roberto Rosario
2019-10-10 11:55:42 -04:00
parent 4a99a9df3e
commit 0699ad0556
87 changed files with 1973 additions and 707 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
mayan/apps/document_parsing/parsers.py
View File

@@ -23,11 +23,13 @@ class Parser(object):
_registry = {}
@classmethod
def parse_document_page(cls, document_page):
for parser_class in cls._registry.get(document_page.document_version.mimetype, ()):
def parse_document_version_page(cls, document_version_page):
for parser_class in cls._registry.get(document_version_page.document_version.mimetype, ()):
try:
parser = parser_class()
parser.process_document_page(document_page)
parser.process_document_page(
document_version_page=document_version_page
)
except ParserError:
# If parser raises error, try next parser in the list
pass
@@ -41,7 +43,9 @@ class Parser(object):
for parser_class in cls._registry.get(document_version.mimetype, ()):
try:
parser = parser_class()
parser.process_document_version(document_version)
parser.process_document_version(
document_version=document_version
)
except ParserError:
# If parser raises error, try next parser in the list
pass
@@ -64,29 +68,33 @@ class Parser(object):
)
logger.debug('document version: %d', document_version.pk)
for document_page in document_version.pages.all():
self.process_document_page(document_page=document_page)
for document_version_page in document_version.pages.all():
self.process_document_version_page(
document_version_page=document_version_page
)
def process_document_page(self, document_page):
DocumentPageContent = apps.get_model(
app_label='document_parsing', model_name='DocumentPageContent'
def process_document_version_page(self, document_version_page):
DocumentVersionPageContent = apps.get_model(
app_label='document_parsing',
model_name='DocumentVersionPageContent'
)
logger.info(
'Processing page: %d of document version: %s',
document_page.page_number, document_page.document_version
document_version_page.page_number,
document_version_page.document_version
)
file_object = document_page.document_version.get_intermediate_file()
file_object = document_version_page.document_version.get_intermediate_file()
try:
document_page_content, created = DocumentPageContent.objects.get_or_create(
document_page=document_page
document_version_page_content, created = DocumentVersionPageContent.objects.get_or_create(
document_version_page=document_version_page
)
document_page_content.content = self.execute(
file_object=file_object, page_number=document_page.page_number
document_version_page_content.content = self.execute(
file_object=file_object, page_number=document_version_page.page_number
)
document_page_content.save()
document_version_page_content.save()
except Exception as exception:
error_message = _('Exception parsing page; %s') % exception
logger.error(error_message)
@@ -96,7 +104,8 @@ class Parser(object):
logger.info(
'Finished processing page: %d of document version: %s',
document_page.page_number, document_page.document_version
document_version_page.page_number,
document_version_page.document_version
)
def execute(self, file_object, page_number):