From cee0b53606fc9a86c7a82adc475f57eb3fef361b Mon Sep 17 00:00:00 2001
From: Nicolas Delaby <nicolas@nexedi.com>
Date: Tue, 30 Nov 2010 13:47:51 +0000
Subject: [PATCH] Use subprocesstransform for better transformation handling.
changes in argument: '-enc' use UTF-8 by defaults '-layout' Maintain (as
best as possible) the original physical layout of the text. '-nopgbrk' Don't
insert page breaks
git-svn-id: https://svn.erp5.org/repos/public/erp5/trunk@40925 20353a03-c40f-0410-a6d1-a30d3c3de9de
---
product/PortalTransforms/transforms/pdf_to_text.py | 8 +++++---
1 file changed, 5 insertions(+), 3 deletions(-)
diff --git a/product/PortalTransforms/transforms/pdf_to_text.py b/product/PortalTransforms/transforms/pdf_to_text.py
index da5ce4d45a..fd38c596cc 100644
--- a/product/PortalTransforms/transforms/pdf_to_text.py
+++ b/product/PortalTransforms/transforms/pdf_to_text.py
@@ -1,3 +1,4 @@
+# -*- coding: utf-8 -*-
"""
Uses the xpdf (www.foolabs.com/xpdf)
"""
@@ -6,10 +7,11 @@ from Products.PortalTransforms.interfaces import itransform
from Products.PortalTransforms.libtransforms.utils import bin_search, sansext
from Products.PortalTransforms.libtransforms.commandtransform import commandtransform
from Products.PortalTransforms.libtransforms.commandtransform import popentransform
+from Products.PortalTransforms.libtransforms.commandtransform import subprocesstransform
import os
from zope.interface import implements
-class pdf_to_text(popentransform):
+class pdf_to_text(subprocesstransform):
implements(itransform)
__name__ = "pdf_to_text"
@@ -20,8 +22,8 @@ class pdf_to_text(popentransform):
__version__ = '2004-07-02.01'
binaryName = "pdftotext"
- binaryArgs = "%(infile)s -enc UTF-8 -"
- useStdin = False
+ binaryArgs = "-layout -nopgbrk %(infile)s -"
+ useStdin = True
class old_pdf_to_text(commandtransform):
implements(itransform)
--
GitLab