Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
cloudooo
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Issues
0
Issues
0
List
Boards
Labels
Milestones
Merge Requests
0
Merge Requests
0
Analytics
Analytics
Repository
Value Stream
Wiki
Wiki
Snippets
Snippets
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Create a new issue
Commits
Issue Boards
Open sidebar
Roque
cloudooo
Commits
25b527d4
Commit
25b527d4
authored
Feb 14, 2017
by
Boris Kocherov
Committed by
Romain Courteaud
Feb 26, 2018
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
x2t: add support new version x2t and metadata
parent
b472db7e
Changes
3
Hide whitespace changes
Inline
Side-by-side
Showing
3 changed files
with
233 additions
and
80 deletions
+233
-80
cloudooo/handler/x2t/handler.py
cloudooo/handler/x2t/handler.py
+202
-71
cloudooo/handler/x2t/tests/data/test_with_metadata.xlsy
cloudooo/handler/x2t/tests/data/test_with_metadata.xlsy
+0
-0
cloudooo/handler/x2t/tests/testX2tHandler.py
cloudooo/handler/x2t/tests/testX2tHandler.py
+31
-9
No files found.
cloudooo/handler/x2t/handler.py
View file @
25b527d4
...
@@ -27,43 +27,133 @@
...
@@ -27,43 +27,133 @@
##############################################################################
##############################################################################
from
xml.etree
import
ElementTree
from
xml.etree
import
ElementTree
from
subprocess
import
Popen
,
PIPE
from
subprocess
import
Popen
,
PIPE
from
tempfile
import
NamedTemporaryFile
,
mktemp
import
sys
import
os
import
os
import
json
import
io
from
mimetypes
import
guess_type
from
zope.interface
import
implements
from
zope.interface
import
implements
from
cloudooo.interfaces.handler
import
IHandler
from
cloudooo.interfaces.handler
import
IHandler
from
cloudooo.file
import
File
from
cloudooo.file
import
File
from
cloudooo.util
import
logger
,
zipTree
,
unzip
,
parseContentType
from
cloudooo.util
import
logger
,
unzip
,
parseContentType
from
cloudooo.handler.ooo.handler
import
Handler
as
OOoHandler
from
cloudooo.handler.ooo.handler
import
Handler
as
OOoHandler
AVS_OFFICESTUDIO_FILE_UNKNOWN
=
"0"
from
zipfile
import
ZipFile
,
ZIP_DEFLATED
AVS_OFFICESTUDIO_FILE_DOCUMENT_DOCX
=
"65"
AVS_OFFICESTUDIO_FILE_PRESENTATION_PPTX
=
"129"
AVS_OFFICESTUDIO_FILE_UNKNOWN
=
0x0000
AVS_OFFICESTUDIO_FILE_PRESENTATION_PPSX
=
"132"
AVS_OFFICESTUDIO_FILE_SPREADSHEET_XLSX
=
"257"
AVS_OFFICESTUDIO_FILE_DOCUMENT
=
0x0040
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM_PDF
=
"513"
AVS_OFFICESTUDIO_FILE_DOCUMENT_DOCX
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x0001
AVS_OFFICESTUDIO_FILE_TEAMLAB_DOCY
=
"4097"
AVS_OFFICESTUDIO_FILE_DOCUMENT_DOC
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x0002
AVS_OFFICESTUDIO_FILE_TEAMLAB_XLSY
=
"4098"
AVS_OFFICESTUDIO_FILE_DOCUMENT_ODT
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x0003
AVS_OFFICESTUDIO_FILE_TEAMLAB_PPTY
=
"4099"
AVS_OFFICESTUDIO_FILE_DOCUMENT_RTF
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x0004
AVS_OFFICESTUDIO_FILE_CANVAS_WORD
=
"8193"
AVS_OFFICESTUDIO_FILE_DOCUMENT_TXT
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x0005
AVS_OFFICESTUDIO_FILE_CANVAS_SPREADSHEET
=
"8194"
AVS_OFFICESTUDIO_FILE_DOCUMENT_HTML
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x0006
AVS_OFFICESTUDIO_FILE_CANVAS_PRESENTATION
=
"8195"
AVS_OFFICESTUDIO_FILE_DOCUMENT_MHT
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x0007
AVS_OFFICESTUDIO_FILE_OTHER_HTMLZIP
=
"2051"
AVS_OFFICESTUDIO_FILE_DOCUMENT_EPUB
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x0008
AVS_OFFICESTUDIO_FILE_OTHER_ZIP
=
"2057"
AVS_OFFICESTUDIO_FILE_DOCUMENT_FB2
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x0009
AVS_OFFICESTUDIO_FILE_DOCUMENT_MOBI
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x000a
AVS_OFFICESTUDIO_FILE_DOCUMENT_DOCM
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x000b
AVS_OFFICESTUDIO_FILE_DOCUMENT_DOTX
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x000c
AVS_OFFICESTUDIO_FILE_DOCUMENT_DOTM
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x000d
AVS_OFFICESTUDIO_FILE_DOCUMENT_ODT_FLAT
=
AVS_OFFICESTUDIO_FILE_DOCUMENT
+
0x000e
AVS_OFFICESTUDIO_FILE_PRESENTATION
=
0x0080
AVS_OFFICESTUDIO_FILE_PRESENTATION_PPTX
=
AVS_OFFICESTUDIO_FILE_PRESENTATION
+
0x0001
AVS_OFFICESTUDIO_FILE_PRESENTATION_PPT
=
AVS_OFFICESTUDIO_FILE_PRESENTATION
+
0x0002
AVS_OFFICESTUDIO_FILE_PRESENTATION_ODP
=
AVS_OFFICESTUDIO_FILE_PRESENTATION
+
0x0003
AVS_OFFICESTUDIO_FILE_PRESENTATION_PPSX
=
AVS_OFFICESTUDIO_FILE_PRESENTATION
+
0x0004
AVS_OFFICESTUDIO_FILE_PRESENTATION_PPTM
=
AVS_OFFICESTUDIO_FILE_PRESENTATION
+
0x0005
AVS_OFFICESTUDIO_FILE_PRESENTATION_PPSM
=
AVS_OFFICESTUDIO_FILE_PRESENTATION
+
0x0006
AVS_OFFICESTUDIO_FILE_PRESENTATION_POTX
=
AVS_OFFICESTUDIO_FILE_PRESENTATION
+
0x0007
AVS_OFFICESTUDIO_FILE_PRESENTATION_POTM
=
AVS_OFFICESTUDIO_FILE_PRESENTATION
+
0x0008
AVS_OFFICESTUDIO_FILE_PRESENTATION_ODP_FLAT
=
AVS_OFFICESTUDIO_FILE_PRESENTATION
+
0x0009
AVS_OFFICESTUDIO_FILE_SPREADSHEET
=
0x0100
AVS_OFFICESTUDIO_FILE_SPREADSHEET_XLSX
=
AVS_OFFICESTUDIO_FILE_SPREADSHEET
+
0x0001
AVS_OFFICESTUDIO_FILE_SPREADSHEET_XLS
=
AVS_OFFICESTUDIO_FILE_SPREADSHEET
+
0x0002
AVS_OFFICESTUDIO_FILE_SPREADSHEET_ODS
=
AVS_OFFICESTUDIO_FILE_SPREADSHEET
+
0x0003
AVS_OFFICESTUDIO_FILE_SPREADSHEET_CSV
=
AVS_OFFICESTUDIO_FILE_SPREADSHEET
+
0x0004
AVS_OFFICESTUDIO_FILE_SPREADSHEET_XLSM
=
AVS_OFFICESTUDIO_FILE_SPREADSHEET
+
0x0005
AVS_OFFICESTUDIO_FILE_SPREADSHEET_XLTX
=
AVS_OFFICESTUDIO_FILE_SPREADSHEET
+
0x0006
AVS_OFFICESTUDIO_FILE_SPREADSHEET_XLTM
=
AVS_OFFICESTUDIO_FILE_SPREADSHEET
+
0x0007
AVS_OFFICESTUDIO_FILE_SPREADSHEET_ODS_FLAT
=
AVS_OFFICESTUDIO_FILE_SPREADSHEET
+
0x0008
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM
=
0x0200
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM_PDF
=
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM
+
0x0001
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM_SWF
=
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM
+
0x0002
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM_DJVU
=
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM
+
0x0003
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM_XPS
=
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM
+
0x0004
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM_SVG
=
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM
+
0x0005
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM_HTMLR
=
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM
+
0x0006
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM_HTMLRMenu
=
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM
+
0x0007
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM_HTMLRCanvas
=
AVS_OFFICESTUDIO_FILE_CROSSPLATFORM
+
0x0008
AVS_OFFICESTUDIO_FILE_IMAGE
=
0x0400
AVS_OFFICESTUDIO_FILE_IMAGE_JPG
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x0001
AVS_OFFICESTUDIO_FILE_IMAGE_TIFF
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x0002
AVS_OFFICESTUDIO_FILE_IMAGE_TGA
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x0003
AVS_OFFICESTUDIO_FILE_IMAGE_GIF
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x0004
AVS_OFFICESTUDIO_FILE_IMAGE_PNG
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x0005
AVS_OFFICESTUDIO_FILE_IMAGE_EMF
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x0006
AVS_OFFICESTUDIO_FILE_IMAGE_WMF
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x0007
AVS_OFFICESTUDIO_FILE_IMAGE_BMP
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x0008
AVS_OFFICESTUDIO_FILE_IMAGE_CR2
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x0009
AVS_OFFICESTUDIO_FILE_IMAGE_PCX
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x000a
AVS_OFFICESTUDIO_FILE_IMAGE_RAS
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x000b
AVS_OFFICESTUDIO_FILE_IMAGE_PSD
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x000c
AVS_OFFICESTUDIO_FILE_IMAGE_ICO
=
AVS_OFFICESTUDIO_FILE_IMAGE
+
0x000d
AVS_OFFICESTUDIO_FILE_OTHER
=
0x0800
AVS_OFFICESTUDIO_FILE_OTHER_EXTRACT_IMAGE
=
AVS_OFFICESTUDIO_FILE_OTHER
+
0x0001
AVS_OFFICESTUDIO_FILE_OTHER_MS_OFFCRYPTO
=
AVS_OFFICESTUDIO_FILE_OTHER
+
0x0002
AVS_OFFICESTUDIO_FILE_OTHER_HTMLZIP
=
AVS_OFFICESTUDIO_FILE_OTHER
+
0x0003
AVS_OFFICESTUDIO_FILE_OTHER_OLD_DOCUMENT
=
AVS_OFFICESTUDIO_FILE_OTHER
+
0x0004
AVS_OFFICESTUDIO_FILE_OTHER_OLD_PRESENTATION
=
AVS_OFFICESTUDIO_FILE_OTHER
+
0x0005
AVS_OFFICESTUDIO_FILE_OTHER_OLD_DRAWING
=
AVS_OFFICESTUDIO_FILE_OTHER
+
0x0006
AVS_OFFICESTUDIO_FILE_OTHER_TEAMLAB_INNER
=
AVS_OFFICESTUDIO_FILE_OTHER
+
0x0007
AVS_OFFICESTUDIO_FILE_OTHER_JSON
=
AVS_OFFICESTUDIO_FILE_OTHER
+
0x0008
AVS_OFFICESTUDIO_FILE_OTHER_ZIP
=
AVS_OFFICESTUDIO_FILE_OTHER
+
0x0009
AVS_OFFICESTUDIO_FILE_TEAMLAB
=
0x1000
AVS_OFFICESTUDIO_FILE_TEAMLAB_DOCY
=
AVS_OFFICESTUDIO_FILE_TEAMLAB
+
0x0001
AVS_OFFICESTUDIO_FILE_TEAMLAB_XLSY
=
AVS_OFFICESTUDIO_FILE_TEAMLAB
+
0x0002
AVS_OFFICESTUDIO_FILE_TEAMLAB_PPTY
=
AVS_OFFICESTUDIO_FILE_TEAMLAB
+
0x0003
AVS_OFFICESTUDIO_FILE_CANVAS
=
0x2000
AVS_OFFICESTUDIO_FILE_CANVAS_WORD
=
AVS_OFFICESTUDIO_FILE_CANVAS
+
0x0001
AVS_OFFICESTUDIO_FILE_CANVAS_SPREADSHEET
=
AVS_OFFICESTUDIO_FILE_CANVAS
+
0x0002
AVS_OFFICESTUDIO_FILE_CANVAS_PRESENTATION
=
AVS_OFFICESTUDIO_FILE_CANVAS
+
0x0003
AVS_OFFICESTUDIO_FILE_CANVAS_PDF
=
AVS_OFFICESTUDIO_FILE_CANVAS
+
0x0004
format_code_map
=
{
format_code_map
=
{
"docy"
:
AVS_OFFICESTUDIO_FILE_CANVAS_WORD
,
"odt"
:
AVS_OFFICESTUDIO_FILE_DOCUMENT_ODT
,
"ods"
:
AVS_OFFICESTUDIO_FILE_SPREADSHEET_ODS
,
"odp"
:
AVS_OFFICESTUDIO_FILE_PRESENTATION_ODP
,
"docx"
:
AVS_OFFICESTUDIO_FILE_DOCUMENT_DOCX
,
"docx"
:
AVS_OFFICESTUDIO_FILE_DOCUMENT_DOCX
,
"xlsy"
:
AVS_OFFICESTUDIO_FILE_CANVAS_SPREADSHEET
,
"xlsx"
:
AVS_OFFICESTUDIO_FILE_SPREADSHEET_XLSX
,
"xlsx"
:
AVS_OFFICESTUDIO_FILE_SPREADSHEET_XLSX
,
"ppty"
:
AVS_OFFICESTUDIO_FILE_CANVAS_PRESENTATION
,
"pptx"
:
AVS_OFFICESTUDIO_FILE_PRESENTATION_PPTX
,
"pptx"
:
AVS_OFFICESTUDIO_FILE_PRESENTATION_PPTX
,
"docy"
:
AVS_OFFICESTUDIO_FILE_CANVAS_WORD
,
"xlsy"
:
AVS_OFFICESTUDIO_FILE_CANVAS_SPREADSHEET
,
"ppty"
:
AVS_OFFICESTUDIO_FILE_CANVAS_PRESENTATION
,
}
format_code_map_output
=
{
"docy"
:
AVS_OFFICESTUDIO_FILE_TEAMLAB_DOCY
,
"xlsy"
:
AVS_OFFICESTUDIO_FILE_TEAMLAB_XLSY
,
"ppty"
:
AVS_OFFICESTUDIO_FILE_TEAMLAB_PPTY
,
}
yformat_map
=
{
'docy'
:
'docx'
,
'xlsy'
:
'xlsx'
,
'ppty'
:
'pptx'
,
}
}
yformat_tuple
=
(
"docy"
,
"xlsy"
,
"ppty"
)
yformat_tuple
=
(
"docy"
,
"xlsy"
,
"ppty"
)
class
Handler
(
object
):
class
Handler
(
object
):
"""
"""
X2T Handler is used to convert Microsoft Office 2007 documents to OnlyOffice
X2T Handler is used to convert Microsoft Office 2007 documents to OnlyOffice
...
@@ -95,34 +185,37 @@ class Handler(object):
...
@@ -95,34 +185,37 @@ class Handler(object):
# init vars and xml configuration file
# init vars and xml configuration file
in_format
=
format_code_map
[
source_format
]
in_format
=
format_code_map
[
source_format
]
out_format
=
format_code_map
[
destination_format
]
out_format
=
format_code_map_output
.
get
(
destination_format
,
format_code_map
[
destination_format
])
root_dir
=
self
.
file
.
directory_name
root_dir
=
self
.
file
.
directory_name
input_dir
=
os
.
path
.
join
(
root_dir
,
"input"
);
input_dir
=
os
.
path
.
join
(
root_dir
,
"input"
);
output_dir
=
os
.
path
.
join
(
root_dir
,
"output"
);
final_file_name
=
os
.
path
.
join
(
root_dir
,
"document.%s"
%
destination_format
)
input_file_name
=
self
.
file
.
getUrl
()
input_file_name
=
self
.
file
.
getUrl
()
output_file_name
=
final_file_name
output_file_name
=
os
.
path
.
join
(
root_dir
,
"document.%s"
%
destination_format
)
config_file_name
=
os
.
path
.
join
(
root_dir
,
"config.xml"
)
config_file_name
=
os
.
path
.
join
(
root_dir
,
"config.xml"
)
metadata
=
None
output_data
=
None
if
source_format
in
yformat_tuple
:
if
source_format
in
yformat_tuple
:
if
self
.
_data
.
startswith
(
"PK
\
x03
\
x04
"
):
if
self
.
_data
.
startswith
(
"PK
\
x03
\
x04
"
):
os
.
mkdir
(
input_dir
)
os
.
mkdir
(
input_dir
)
unzip
(
self
.
file
.
getUrl
(),
input_dir
)
unzip
(
self
.
file
.
getUrl
(),
input_dir
)
for
_
,
_
,
files
in
os
.
walk
(
input_dir
):
input_file_name
=
os
.
path
.
join
(
input_dir
,
"body.txt"
)
input_file_name
,
=
files
if
not
os
.
path
.
isfile
(
input_file_name
):
break
input_file_name
=
os
.
path
.
join
(
input_dir
,
"Editor.bin"
)
input_file_name
=
os
.
path
.
join
(
input_dir
,
input_file_name
)
if
not
os
.
path
.
isfile
(
input_file_name
):
if
destination_format
in
yformat_tuple
:
raise
RuntimeError
(
"input format incorrect: Editor.bin absent in zip archive"
)
os
.
mkdir
(
output_dir
)
metadata_file_name
=
os
.
path
.
join
(
input_dir
,
"metadata.json"
)
output_file_name
=
os
.
path
.
join
(
output_dir
,
"body.txt"
)
if
os
.
path
.
isfile
(
metadata_file_name
):
with
open
(
metadata_file_name
)
as
metadata_file
:
metadata
=
json
.
loads
(
metadata_file
.
read
())
with
open
(
config_file_name
,
"w"
)
as
config_file
:
with
open
(
config_file_name
,
"w"
)
as
config_file
:
config
=
{
config
=
{
# 'm_sKey': 'from',
# 'm_sKey': 'from',
'm_sFileFrom'
:
input_file_name
,
'm_sFileFrom'
:
input_file_name
,
'm_nFormatFrom'
:
in_format
,
'm_nFormatFrom'
:
str
(
in_format
)
,
'm_sFileTo'
:
output_file_name
,
'm_sFileTo'
:
output_file_name
,
'm_nFormatTo'
:
out_format
,
'm_nFormatTo'
:
str
(
out_format
)
,
# 'm_bPaid': 'true',
# 'm_bPaid': 'true',
# 'm_bEmbeddedFonts': 'false',
# 'm_bEmbeddedFonts': 'false',
# 'm_bFromChanges': 'false',
# 'm_bFromChanges': 'false',
...
@@ -132,7 +225,8 @@ class Handler(object):
...
@@ -132,7 +225,8 @@ class Handler(object):
root
=
ElementTree
.
Element
(
'root'
)
root
=
ElementTree
.
Element
(
'root'
)
for
key
,
value
in
config
.
items
():
for
key
,
value
in
config
.
items
():
ElementTree
.
SubElement
(
root
,
key
).
text
=
value
ElementTree
.
SubElement
(
root
,
key
).
text
=
value
ElementTree
.
ElementTree
(
root
).
write
(
config_file
,
encoding
=
'utf-8'
,
xml_declaration
=
True
,
default_namespace
=
None
,
method
=
"xml"
)
ElementTree
.
ElementTree
(
root
).
write
(
config_file
,
encoding
=
'utf-8'
,
xml_declaration
=
True
,
default_namespace
=
None
,
method
=
"xml"
)
# run convertion binary
# run convertion binary
p
=
Popen
(
p
=
Popen
(
...
@@ -144,56 +238,93 @@ class Handler(object):
...
@@ -144,56 +238,93 @@ class Handler(object):
)
)
stdout
,
stderr
=
p
.
communicate
()
stdout
,
stderr
=
p
.
communicate
()
if
p
.
returncode
!=
0
:
if
p
.
returncode
!=
0
:
raise
RuntimeError
(
"x2t: exit code %d != 0
\
n
+ %s
\
n
> stdout: %s
\
n
> stderr: %s@ x2t xml:
\
n
%s"
%
(
p
.
returncode
,
" "
.
join
([
"x2t"
,
config_file
.
name
]),
stdout
,
stderr
,
" "
+
open
(
config_file
.
name
).
read
().
replace
(
"
\
n
"
,
"
\
n
"
)))
raise
RuntimeError
(
"x2t: exit code %d != 0
\
n
+ %s
\
n
> stdout: %s
\
n
> stderr: %s@ x2t xml:
\
n
%s"
%
(
p
.
returncode
,
" "
.
join
([
"x2t"
,
config_file
.
name
]),
stdout
,
stderr
,
if
destination_format
in
yformat_tuple
:
" "
+
open
(
config_file
.
name
).
read
().
replace
(
"
\
n
"
,
"
\
n
"
)))
zipTree
(
final_file_name
,
(
output_file_name
,
""
),
(
os
.
path
.
join
(
os
.
path
.
dirname
(
output_file_name
),
"media"
),
""
),
)
self
.
file
.
reload
(
final
_file_name
)
self
.
file
.
reload
(
output
_file_name
)
try
:
try
:
return
self
.
file
.
getContent
()
if
source_format
in
yformat_tuple
:
if
metadata
:
output_data
=
OOoHandler
(
self
.
base_folder_url
,
self
.
file
.
getContent
(),
source_format
,
**
self
.
_init_kw
)
\
.
setMetadata
(
metadata
)
else
:
output_data
=
self
.
file
.
getContent
()
elif
destination_format
in
yformat_tuple
:
if
not
metadata
:
if
source_format
not
in
yformat_tuple
:
metadata
=
OOoHandler
(
self
.
base_folder_url
,
self
.
_data
,
source_format
,
**
self
.
_init_kw
).
getMetadata
()
if
not
metadata
:
metadata
=
{}
metadata
.
pop
(
'MIMEType'
,
None
)
metadata
.
pop
(
'Generator'
,
None
)
metadata
.
pop
(
'AppVersion'
,
None
)
metadata
.
pop
(
'ImplementationName'
,
None
)
with
ZipFile
(
output_file_name
,
mode
=
"a"
)
as
zipfile
:
zipfile
.
writestr
(
"metadata.json"
,
json
.
dumps
(
metadata
))
output_data
=
self
.
file
.
getContent
()
finally
:
finally
:
self
.
file
.
trash
()
self
.
file
.
trash
()
return
output_data
def
_getContentType
(
self
):
mimetype_type
=
None
if
"/"
not
in
self
.
_source_format
:
mimetype_type
=
guess_type
(
'a.'
+
self
.
_source_format
)[
0
]
if
mimetype_type
is
None
:
mimetype_type
=
self
.
_source_format
return
mimetype_type
def
getMetadata
(
self
,
base_document
=
False
):
def
getMetadata
(
self
,
base_document
=
False
):
r"""Returns a dictionary with all metadata of document.
r"""Returns a dictionary with all metadata of document.
/!\
No
t Implemented: no format are handled correctly.
"""
"""
# XXX Cloudooo takes the first handler that can "handle" source_mimetype.
if
self
.
_source_format
in
yformat_tuple
and
self
.
_data
.
startswith
(
"PK
\
x03
\
x04
"
):
# However, docx documents metadata can only be "handled" by the ooo handler.
if
base_document
:
# Handlers should provide a way to tell if such capability is available for the required source mimetype.
openxml_format
=
yformat_map
[
self
.
_source_format
]
# We have to define a precise direction on how to know/get what are handlers capabilities according to Cloudooo configuration.
data
=
self
.
convert
(
yformat_map
[
self
.
_source_format
])
# And then, this method MUST raise on unhandled format. Here xformats are "handled" by cheating.
return
OOoHandler
(
self
.
base_folder_url
,
data
,
openxml_format
,
**
self
.
_init_kw
).
getMetadata
(
base_document
)
if
self
.
_source_format
in
(
else
:
"docx"
,
"application/vnd.openxmlformats-officedocument.wordprocessingml.document"
,
with
io
.
BytesIO
(
self
.
_data
)
as
memfile
,
ZipFile
(
memfile
)
as
zipfile
:
"xlsx"
,
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
,
try
:
"pptx"
,
"application/vnd.openxmlformats-officedocument.presentationml.presentation"
,
metadata
=
zipfile
.
read
(
"metadata.json"
)
):
except
KeyError
:
return
OOoHandler
(
self
.
base_folder_url
,
self
.
_data
,
self
.
_source_format
,
**
self
.
_init_kw
).
getMetadata
(
base_document
)
metadata
=
'{}'
return
{}
metadata
=
json
.
loads
(
metadata
)
metadata
[
'MIMEType'
]
=
self
.
_getContentType
()
def
setMetadata
(
self
,
metadata
=
{}):
return
metadata
else
:
return
OOoHandler
(
self
.
base_folder_url
,
self
.
_data
,
self
.
_source_format
,
**
self
.
_init_kw
)
\
.
getMetadata
(
base_document
)
def
setMetadata
(
self
,
metadata
=
None
):
r"""Returns document with new metadata.
r"""Returns document with new metadata.
/!\
No
t Implemented: no format are handled correctly.
Keyword arguments:
Keyword arguments:
metadata -- expected an dictionary with metadata.
metadata -- expected an dictionary with metadata.
"""
"""
# XXX Cloudooo takes the first handler that can "handle" source_mimetype.
if
metadata
is
None
:
# However, docx documents metadata can only be "handled" by the ooo handler.
metadata
=
{}
# Handlers should provide a way to tell if such capability is available for the required source mimetype.
if
self
.
_source_format
in
yformat_tuple
and
self
.
_data
.
startswith
(
"PK
\
x03
\
x04
"
):
# We have to define a precise direction on how to know/get what are handlers capabilities according to Cloudooo configuration.
root_dir
=
self
.
file
.
directory_name
# And then, this method MUST raise on unhandled format. Here xformats are "handled" by cheating.
output_file_name
=
os
.
path
.
join
(
root_dir
,
"tmp"
)
if
self
.
_source_format
in
(
try
:
"docx"
,
"application/vnd.openxmlformats-officedocument.wordprocessingml.document"
,
input_dir
=
os
.
path
.
join
(
root_dir
,
"input"
)
"xlsx"
,
"application/vnd.openxmlformats-officedocument.spreadsheetml.sheet"
,
os
.
mkdir
(
input_dir
)
"pptx"
,
"application/vnd.openxmlformats-officedocument.presentationml.presentation"
,
unzip
(
self
.
file
.
getUrl
(),
input_dir
)
):
with
open
(
os
.
path
.
join
(
input_dir
,
"metadata.json"
),
"w"
)
as
metadata_file
:
metadata_file
.
write
(
json
.
dumps
(
metadata
))
with
ZipFile
(
output_file_name
,
"w"
)
as
zipfile
:
for
root
,
_
,
files
in
os
.
walk
(
input_dir
):
relative_root
=
root
.
replace
(
input_dir
,
''
)
for
file_name
in
files
:
absolute_path
=
os
.
path
.
join
(
root
,
file_name
)
file_name
=
os
.
path
.
join
(
relative_root
,
file_name
)
zipfile
.
write
(
absolute_path
,
file_name
)
output_data
=
open
(
output_file_name
).
read
()
finally
:
os
.
unlink
(
output_file_name
)
return
output_data
else
:
return
OOoHandler
(
self
.
base_folder_url
,
self
.
_data
,
self
.
_source_format
,
**
self
.
_init_kw
).
setMetadata
(
metadata
)
return
OOoHandler
(
self
.
base_folder_url
,
self
.
_data
,
self
.
_source_format
,
**
self
.
_init_kw
).
setMetadata
(
metadata
)
return
self
.
file
.
getContent
()
@
staticmethod
@
staticmethod
def
getAllowedConversionFormatList
(
source_mimetype
):
def
getAllowedConversionFormatList
(
source_mimetype
):
...
...
cloudooo/handler/x2t/tests/data/test_with_metadata.xlsy
0 → 100644
View file @
25b527d4
File added
cloudooo/handler/x2t/tests/testX2tHandler.py
View file @
25b527d4
...
@@ -34,6 +34,9 @@ from cStringIO import StringIO
...
@@ -34,6 +34,9 @@ from cStringIO import StringIO
from
cloudooo.handler.x2t.handler
import
Handler
from
cloudooo.handler.x2t.handler
import
Handler
from
cloudooo.tests.handlerTestCase
import
HandlerTestCase
,
make_suite
from
cloudooo.tests.handlerTestCase
import
HandlerTestCase
,
make_suite
OPENOFFICE
=
True
class
TestHandler
(
HandlerTestCase
):
class
TestHandler
(
HandlerTestCase
):
def
afterSetUp
(
self
):
def
afterSetUp
(
self
):
...
@@ -84,18 +87,37 @@ class TestHandler(HandlerTestCase):
...
@@ -84,18 +87,37 @@ class TestHandler(HandlerTestCase):
y_zip
.
open
(
"media/image1.png"
)
y_zip
.
open
(
"media/image1.png"
)
def
testgetMetadata
(
self
):
def
testgetMetadata
(
self
):
"""Test getMetadata from yformats
(not implemented)
"""
"""Test getMetadata from yformats"""
handler
=
Handler
(
self
.
tmp_url
,
""
,
"xlsy"
,
**
self
.
kw
)
handler
=
Handler
(
self
.
tmp_url
,
""
,
"xlsy"
,
**
self
.
kw
)
# Of course, expected behavior should be a dict of internal metadata
self
.
assertEquals
(
handler
.
getMetadata
(),
{
# but don't know how to handle it so far.
u'CreationDate'
:
u'00/00/0000 00:00:00'
,
self
.
assertEquals
(
handler
.
getMetadata
(),
{})
u'ImplementationName'
:
u'com.sun.star.comp.comphelper.OPropertyBag'
,
u'MIMEType'
:
u'text/plain'
,
u'ModificationDate'
:
u'00/00/0000 00:00:00'
,
u'PrintDate'
:
u'00/00/0000 00:00:00'
,
u'TemplateDate'
:
u'00/00/0000 00:00:00'
,
})
handler
=
Handler
(
self
.
tmp_url
,
open
(
"data/test_with_metadata.xlsy"
).
read
(),
"xlsy"
,
**
self
.
kw
)
self
.
assertEquals
(
handler
.
getMetadata
(),
{
u'CreationDate'
:
u'31/01/2018 21:09:10'
,
u'Keywords'
:
[
u'
\
u0442
\
u0435
\
u0441
\
u0442
'
,
u'
\
u0441
\
u0430
\
u0431
\
u0436
\
u0435
\
u043a
\
u0442
'
],
'MIMEType'
:
'xlsy'
,
u'ModificationDate'
:
u'31/01/2018 21:22:36'
,
u'PrintDate'
:
u'00/00/0000 00:00:00'
,
u'Subject'
:
u'
\
u0432
\
u044b
\
u043a
\
u043b
\
u044e
\
u0447
\
u0438
\
u0442
\
u0435
\
u043b
\
u0435
\
u0432
\
u0438
\
u0437
\
u043e
\
u0440
'
,
u'TemplateDate'
:
u'00/00/0000 00:00:00'
,
u'Title'
:
u'kesha'
})
def
testsetMetadata
(
self
):
def
testsetMetadata
(
self
):
"""Test setMetadata for yformats (not implemented)"""
"""Test setMetadata for yformats"""
handler
=
Handler
(
self
.
tmp_url
,
""
,
"xlsy"
,
**
self
.
kw
)
handler
=
Handler
(
self
.
tmp_url
,
open
(
"data/test_with_metadata.xlsy"
).
read
(),
"xlsy"
,
**
self
.
kw
)
# Of course, expected behavior should be an updated data with new
new_mime_data
=
handler
.
setMetadata
({
# internal metadata but don't know how to handle it so far.
"Title"
:
"test title"
,
self
.
assertEquals
(
handler
.
setMetadata
(),
""
)
"Subject"
:
"test subject"
,
"Keywords"
:
"test keywords"
,
})
handler
=
Handler
(
self
.
tmp_url
,
new_mime_data
,
"xlsy"
,
**
self
.
kw
)
self
.
assertEquals
(
handler
.
getMetadata
(),
{
u'Keywords'
:
u'test keywords'
,
'MIMEType'
:
'xlsy'
,
u'Title'
:
u'test title'
,
u'Subject'
:
u'test subject'
})
def
testGetAllowedConversionFormatList
(
self
):
def
testGetAllowedConversionFormatList
(
self
):
"""Test all combination of mimetype
"""Test all combination of mimetype
...
...
Write
Preview
Markdown
is supported
0%
Try again
or
attach a new file
Attach a file
Cancel
You are about to add
0
people
to the discussion. Proceed with caution.
Finish editing this message first!
Cancel
Please
register
or
sign in
to comment