Skip to content
Projects
Groups
Snippets
Help
Loading...
Help
Support
Keyboard shortcuts
?
Submit feedback
Contribute to GitLab
Sign in / Register
Toggle navigation
erp5
Project overview
Project overview
Details
Activity
Releases
Repository
Repository
Files
Commits
Branches
Tags
Contributors
Graph
Compare
Labels
Merge Requests
7
Merge Requests
7
CI / CD
CI / CD
Pipelines
Jobs
Schedules
Analytics
Analytics
CI / CD
Repository
Value Stream
Members
Members
Collapse sidebar
Close sidebar
Activity
Graph
Jobs
Commits
Open sidebar
Jérome Perrin
erp5
Commits
2ddb82bc
Commit
2ddb82bc
authored
1 year ago
by
Emmy Vouriot
Committed by
Jérome Perrin
9 months ago
Browse files
Options
Browse Files
Download
Email Patches
Plain Diff
bytes to str when reading html or convert to text WIP
parent
8f489804
Changes
1
Hide whitespace changes
Inline
Side-by-side
Showing
1 changed file
with
5 additions
and
5 deletions
+5
-5
bt5/erp5_dms/DocumentTemplateItem/portal_components/document.erp5.PDFDocument.py
...mplateItem/portal_components/document.erp5.PDFDocument.py
+5
-5
No files found.
bt5/erp5_dms/DocumentTemplateItem/portal_components/document.erp5.PDFDocument.py
View file @
2ddb82bc
...
...
@@ -194,7 +194,7 @@ class PDFDocument(Image):
context
=
self
,
filename
=
filename
,
mimetype
=
self
.
getContentType
())
if
result
:
return
result
return
bytes2str
(
result
)
else
:
# Try to use OCR from ghostscript, but tolerate that the command might
# not be available.
...
...
@@ -282,7 +282,7 @@ class PDFDocument(Image):
command
=
[
'pdftohtml'
,
'-enc'
,
'UTF-8'
,
'-stdout'
,
'-noframes'
,
'-i'
,
tmp
.
name
]
try
:
command_result
=
Popen
(
command
,
stdout
=
PIPE
).
communicate
()[
0
]
command_result
=
bytes2str
(
Popen
(
command
,
stdout
=
PIPE
).
communicate
()[
0
])
except
OSError
as
e
:
if
e
.
errno
==
errno
.
ENOENT
:
raise
ConversionError
(
'pdftohtml was not found'
)
...
...
@@ -291,10 +291,10 @@ class PDFDocument(Image):
finally
:
tmp
.
close
()
# Quick hack to remove bg color - XXX
h
=
command_result
.
replace
(
b'<BODY bgcolor="#A0A0A0"'
,
b
'<BODY '
)
h
=
command_result
.
replace
(
'<BODY bgcolor="#A0A0A0"'
,
'<BODY '
)
# Make links relative
h
=
h
.
replace
(
str2bytes
(
'href="%s.html'
%
tmp
.
name
.
split
(
os
.
sep
)[
-
1
])
,
b
'href="asEntireHTML'
)
h
=
h
.
replace
(
'href="%s.html'
%
tmp
.
name
.
split
(
os
.
sep
)[
-
1
]
,
'href="asEntireHTML'
)
return
h
security
.
declarePrivate
(
'_convertToDJVU'
)
...
...
This diff is collapsed.
Click to expand it.
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