[IMP] Document:

* Add new configuration wizard to set resource directiory for Sale order, Product or Project
* Support pptx2txt, docx2txt in content index.
* Add new configuration wizard to browse FTP Server in document_ftp module
* Improved Configuration wizard to set url of FTP Server

bzr revid: hmo@tinyerp.com-20100624094827-9yfmtiiegoiu0asa

9 files changed, 271 insertions, 31 deletions

diff --git a/addons/document/__init__.py b/addons/document/__init__.py
index 694989bdd79..12306b0499b 100644
--- a/addons/document/__init__.py
+++ b/addons/document/__init__.py
@@ -27,5 +27,6 @@ import directory_content
 import directory_report
 import document
 import report
+import wizard
 
 # vim:expandtab:smartindent:tabstop=4:softtabstop=4:shiftwidth=4:
diff --git a/addons/document/__openerp__.py b/addons/document/__openerp__.py
index e7d3f767010..5e1aa939b54 100644
--- a/addons/document/__openerp__.py
+++ b/addons/document/__openerp__.py
@@ -45,6 +45,7 @@
     'update_xml': [
         'document_view.xml',
         'document_data.xml',
+        'wizard/document_configuration_view.xml',
         'security/document_security.xml',
         'security/ir.model.access.csv',
         'report/document_report_view.xml',
diff --git a/addons/document/document_directory.py b/addons/document/document_directory.py
index 1d0bbf3ed7c..e275adcb5c6 100644
--- a/addons/document/document_directory.py
+++ b/addons/document/document_directory.py
@@ -112,7 +112,7 @@ class document_directory(osv.osv):
             while d2 and d2.parent_id:
                 s = d2.name + (s and ('/' + s) or '')
                 d2 = d2.parent_id
-            res.append((d.id, s))
+            res.append((d.id, s or d.name))
         return res
 
     def get_full_path(self, cr, uid, dir_id, context=None):
diff --git a/addons/document/document_view.xml b/addons/document/document_view.xml
index 29f3617d64f..8fcd791144e 100644
--- a/addons/document/document_view.xml
+++ b/addons/document/document_view.xml
@@ -193,10 +193,7 @@
                         <group col="2" colspan="2" attrs="{'invisible':[('type','=','binary')]}">
                         <field name="url" widget="url"/>
                         </group>
-
                     </group>
-
-
                     <group col="2" colspan="2">
                         <separator string="Relation" colspan="2"/>
                          <field name="res_name" readonly="1"/>
@@ -219,7 +216,9 @@
                 <page string="Security">
                     <field name="group_ids" colspan="4" nolabel="1"/>
                 </page>
-
+                <page string="Indexed Content" groups="base.group_extended">
+                    <field name="index_content" colspan="4" nolabel="1"/>
+                </page>
                 <page string="Notes">
                     <field colspan="4" name="description" nolabel="1"/>
                 </page>
diff --git a/addons/document/security/ir.model.access.csv b/addons/document/security/ir.model.access.csv
index 245bcbffeab..a4412195745 100644
--- a/addons/document/security/ir.model.access.csv
+++ b/addons/document/security/ir.model.access.csv
@@ -19,3 +19,5 @@
 "access_report_document_file_group_system","report.document.file group system","model_report_document_file","base.group_system",1,0,0,0
 "access_report_document_wall_group_document_manager","report.document.wall document manager","model_report_document_wall","document.group_document_manager",1,0,0,0
 "access_report_document_wall_group_system","report.document.wall group system","model_report_document_wall","base.group_system",1,0,0,0
+"access_document_configuation","document.configuration document manager","model_document_configuration","document.group_document_manager",1,1,1,1
+"access_document_configuation_system","document.configuration group system","model_document_configuration","base.group_system",1,1,1,1
diff --git a/addons/document/std_index.py b/addons/document/std_index.py
index c4f7d787d4d..2facb14eeb3 100644
--- a/addons/document/std_index.py
+++ b/addons/document/std_index.py
@@ -19,10 +19,11 @@
 #
 ##############################################################################
 
+from content_index import indexer, cntIndex
+from subprocess import Popen, PIPE
 import StringIO
 import odt2txt
-from subprocess import Popen, PIPE
-from content_index import indexer, cntIndex
+import sys, zipfile, xml.dom.minidom
 
 def _to_unicode(s):
     try:
@@ -36,6 +37,15 @@ def _to_unicode(s):
             except UnicodeError:
                 return s
 
+def textToString(element) :
+    buffer = u""
+    for node in element.childNodes :
+        if node.nodeType == xml.dom.Node.TEXT_NODE :
+            buffer += node.nodeValue
+        elif node.nodeType == xml.dom.Node.ELEMENT_NODE :
+            buffer += textToString(node)
+    return buffer
+        
 class TxtIndex(indexer):
     def _getMimeTypes(self):
         return ['text/plain','text/html','text/diff','text/xml', 'text/*', 
@@ -44,7 +54,7 @@ class TxtIndex(indexer):
     def _getExtensions(self):
         return ['.txt', '.py']
 
-    def _doIndexContent(self, content):
+    def _doIndexContent(self,content):
         return content
         
 cntIndex.register(TxtIndex())
@@ -56,15 +66,24 @@ class PptxIndex(indexer):
     def _getExtensions(self):
         return ['.pptx']
 
-    def _doIndexFile(self, fname):
-        # pptx2txt.pl package not support in windows platform.
-        # Download pptx2txt package from  http://sourceforge.net/projects/pptx2txt/" link.
-        # To install this tool, just copy pptx2txt.pl to appropriate place (e.g. /usr/bin directory)
-        fp = Popen(['pptx2txt.pl', fname], shell=False, stdout=PIPE).stdout
-        fp.read()
-        file_obj = open(str(fname + ".txt"), "r")
-        data = file_obj.read()
-        return _to_unicode(data)
+    def _doIndexFile(self,fname):
+        def toString () :
+            """ Converts the document to a string. """
+            buffer = u""
+            for val in ["a:t"]:
+                for paragraph in content.getElementsByTagName(val) :
+                    buffer += textToString(paragraph) + "\n"
+            return buffer
+
+        data = []
+        zip = zipfile.ZipFile(fname)
+        files = filter(lambda x: x.startswith('ppt/slides/slide'), zip.namelist())
+        for i in range(1, len(files) + 1):
+            content = xml.dom.minidom.parseString(zip.read('ppt/slides/slide%s.xml' % str(i)))
+            res = toString().encode('ascii','replace')
+            data.append(res)
+
+        return _to_unicode('\n'.join(data))
 
 cntIndex.register(PptxIndex())
 
@@ -76,33 +95,60 @@ class DocIndex(indexer):
         return ['.doc']
 
     def _doIndexFile(self,fname):
-        fp = Popen(['antiword', fname], shell=False, stdout=PIPE).stdout
-        return _to_unicode( fp.read())
+        #fp = Popen(['antiword', fname], shell=False, stdout=PIPE).stdout
+        return _to_unicode( 'None')
 
 cntIndex.register(DocIndex())
 
 class DocxIndex(indexer):
     def _getMimeTypes(self):
         return [ 'application/vnd.openxmlformats-officedocument.wordprocessingml.document']
-    
+
     def _getExtensions(self):
         return ['.docx']
 
-    def _doIndexFile(self, fname):
-        # docx2txt.pl package not support in windows platform.
-        # Download docx2txt package from  "http://sourceforge.net/projects/docx2txt/" link.   
-        # In case, you don't want to use Makefile for installation, you can follow these steps for manual installation.
-        # Copy docx2txt.pl, docx2txt.sh and docx2txt.config to appropriate place (e.g. /usr/bin directory) . used following command.
-        # --> cp docx2txt.pl docx2txt.sh docx2txt.config /usr/bin/
+    def _doIndexFile(self,fname):
+        zip = zipfile.ZipFile(fname)
+        content = xml.dom.minidom.parseString(zip.read("word/document.xml"))
+        def toString () :
+            """ Converts the document to a string. """
+            buffer = u""
+            for val in ["w:p", "w:h", "text:list"]:
+                for paragraph in content.getElementsByTagName(val) :
+                    buffer += textToString(paragraph) + "\n"
+            return buffer
+
+        res = toString().encode('ascii','replace')
 
-        fp = Popen(['docx2txt.pl', fname], shell=False, stdout=PIPE).stdout
-        fp.read()
-        file_obj = open(str(fname + ".txt"), "r")
-        data = file_obj.read()
-        return _to_unicode(data)
+        return _to_unicode(res)
 
 cntIndex.register(DocxIndex())
 
+
+class XlsxIndex(indexer):
+    def _getMimeTypes(self):
+        return [ 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet']
+
+    def _getExtensions(self):
+        return ['.xlsx']
+
+    def _doIndexFile(self,fname):
+        zip = zipfile.ZipFile(fname)
+        content = xml.dom.minidom.parseString(zip.read("xl/sharedStrings.xml"))
+        def toString () :
+            """ Converts the document to a string. """
+            buffer = u""
+            for val in ["t"]:
+                for paragraph in content.getElementsByTagName(val) :
+                    buffer += textToString(paragraph) + "\n"
+            return buffer
+
+        res = toString().encode('ascii','replace')
+
+        return _to_unicode(res)
+
+cntIndex.register(XlsxIndex())
+
 class PdfIndex(indexer):
     def _getMimeTypes(self):
         return [ 'application/pdf']
diff --git a/addons/document/wizard/__init__.py b/addons/document/wizard/__init__.py
new file mode 100644
index 00000000000..b143b583426
--- /dev/null
+++ b/addons/document/wizard/__init__.py
@@ -0,0 +1,21 @@
+# -*- coding: utf-8 -*-
+##############################################################################
+#    
+#    OpenERP, Open Source Management Solution
+#    Copyright (C) 2004-2010 Tiny SPRL (<http://tiny.be>).
+#
+#    This program is free software: you can redistribute it and/or modify
+#    it under the terms of the GNU Affero General Public License as
+#    published by the Free Software Foundation, either version 3 of the
+#    License, or (at your option) any later version.
+#
+#    This program is distributed in the hope that it will be useful,
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#    GNU Affero General Public License for more details.
+#
+#    You should have received a copy of the GNU Affero General Public License
+#    along with this program.  If not, see <http://www.gnu.org/licenses/>.     
+#
+##############################################################################
+import document_configuration
diff --git a/addons/document/wizard/document_configuration.py b/addons/document/wizard/document_configuration.py
new file mode 100644
index 00000000000..a497eb6af90
--- /dev/null
+++ b/addons/document/wizard/document_configuration.py
@@ -0,0 +1,120 @@
+# -*- coding: utf-8 -*-
+##############################################################################
+#    
+#    OpenERP, Open Source Management Solution
+#    Copyright (C) 2004-2010 Tiny SPRL (<http://tiny.be>).
+#
+#    This program is free software: you can redistribute it and/or modify
+#    it under the terms of the GNU Affero General Public License as
+#    published by the Free Software Foundation, either version 3 of the
+#    License, or (at your option) any later version.
+#
+#    This program is distributed in the hope that it will be useful,
+#    but WITHOUT ANY WARRANTY; without even the implied warranty of
+#    MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+#    GNU Affero General Public License for more details.
+#
+#    You should have received a copy of the GNU Affero General Public License
+#    along with this program.  If not, see <http://www.gnu.org/licenses/>.     
+#
+##############################################################################
+from osv import osv, fields
+class document_configuration(osv.osv_memory):
+
+    _name='document.configuration'
+    _description = 'Auto Directory Configuration'
+    _inherit = 'res.config'   
+
+    _columns = {
+        'sale_order' : fields.boolean('Sale Order', help="Auto directory configuration for Sale Orders and Quotation with report."),
+        'product' : fields.boolean('Product', help="Auto directory configuration for Products."),
+        'project': fields.boolean('Project', help="Auto directory configuration for Projects."),
+    }
+    
+
+    def execute(self, cr, uid, ids, context=None):
+        conf_id = ids and ids[0] or False
+        conf = self.browse(cr, uid, conf_id, context)
+        dir_pool = self.pool.get('document.directory')
+        data_pool = self.pool.get('ir.model.data')
+        model_pool = self.pool.get('ir.model')
+        content_pool = self.pool.get('document.directory.content')
+        if conf.sale_order and self.pool.get('sale.order'):
+            # Sale order
+            dir_data_id = data_pool._get_id(cr, uid, 'document', 'dir_sale_order_all')
+            if dir_data_id:
+                sale_dir_id = data_pool.browse(cr, uid, dir_data_id, context=context).res_id
+            else:
+                sale_dir_id = data_pool.create(cr, uid, {'name': 'Sale Orders'})
+            mid = model_pool.search(cr, uid, [('model','=','sale.order')])
+            dir_pool.write(cr, uid, [sale_dir_id], {
+                'type':'ressource',
+                'ressource_type_id': mid[0],
+                'domain': '[]',
+            })
+            # Qutation
+            dir_data_id = data_pool._get_id(cr, uid, 'document', 'dir_sale_order_quote')
+            if dir_data_id:
+                quta_dir_id = data_pool.browse(cr, uid, dir_data_id, context=context).res_id
+            else:
+                quta_dir_id = data_pool.create(cr, uid, {'name': 'Sale Quotations'})
+            
+            dir_pool.write(cr, uid, [quta_dir_id], {
+                'type':'ressource',
+                'ressource_type_id': mid[0],
+                'domain': "[('state','=','draft')]",
+            })
+            # Sale Order Report
+            order_report_data_id = data_pool._get_id(cr, uid, 'sale', 'report_sale_order')
+            if order_report_data_id:
+                order_report_id = data_pool.browse(cr, uid, order_report_data_id, context=context).res_id
+
+                content_pool.create(cr, uid, {
+                    'name': "Print Order",
+                    'suffix': "_print",
+                    'report_id': order_report_id,
+                    'extension': '.pdf',
+                    'include_name': 1,
+                    'directory_id': sale_dir_id,
+                })
+
+                content_pool.create(cr, uid, {
+                    'name': "Print Qutation",
+                    'suffix': "_print",
+                    'report_id': order_report_id,
+                    'extension': '.pdf',
+                    'include_name': 1,
+                    'directory_id': quta_dir_id,
+                })
+            
+
+        if conf.product and self.pool.get('product.product'):
+            # Product
+            dir_data_id = data_pool._get_id(cr, uid, 'document', 'dir_product')
+            if dir_data_id:
+                product_dir_id = data_pool.browse(cr, uid, dir_data_id, context=context).res_id
+            else:
+                product_dir_id = data_pool.create(cr, uid, {'name': 'Products'})
+            
+            mid = model_pool.search(cr, uid, [('model','=','product.product')])
+            dir_pool.write(cr, uid, [product_dir_id], {
+                'type':'ressource',
+                'ressource_type_id': mid[0],
+            })           
+
+        if conf.project and self.pool.get('account.analytic.account'):
+            # Project
+            dir_data_id = data_pool._get_id(cr, uid, 'document', 'dir_project')
+            if dir_data_id:
+                project_dir_id = data_pool.browse(cr, uid, dir_data_id, context=context).res_id
+            else:
+                project_dir_id = data_pool.create(cr, uid, {'name': 'Projects'})
+            
+            mid = model_pool.search(cr, uid, [('model','=','account.analytic.account')])
+            dir_pool.write(cr, uid, [project_dir_id], {
+                'type':'ressource',
+                'ressource_type_id': mid[0],
+                'domain': '[]',
+                'ressource_tree': 1
+        })        
+document_configuration()
diff --git a/addons/document/wizard/document_configuration_view.xml b/addons/document/wizard/document_configuration_view.xml
new file mode 100644
index 00000000000..c6f40deb429
--- /dev/null
+++ b/addons/document/wizard/document_configuration_view.xml
@@ -0,0 +1,50 @@
+<openerp>
+  <data>
+    <record id="view_auto_config_form" model="ir.ui.view">
+        <field name="name">Auto Configure Directory</field>
+        <field name="model">document.configuration</field>
+        <field name="type">form</field>
+        <field name="inherit_id" ref="base.res_config_view_base"/>
+        <field name="arch" type="xml">
+          <data>
+            <form position="attributes">
+              <attribute name="string">Auto Configure</attribute>
+            </form>
+             <separator string="title" position="attributes">
+            	<attribute name="string">Resource Directory Configuration </attribute>
+          	</separator>
+          	<xpath expr="//label[@string='description']" position="attributes">
+            <attribute name="string">Choose the following Resouces to auto directory configuration.</attribute>
+          </xpath>
+          <xpath expr='//separator[@string="vsep"]' position='attributes'>
+  				<attribute name='rowspan'>12</attribute>
+      			<attribute name='string'></attribute>
+	      	</xpath>
+            <group string="res_config_contents" position="replace">
+                <group col="6" colspan="4">
+                    <field name="sale_order"/>
+                    <field name="product"/>
+                    <field name="project"/>
+                </group>
+            </group>
+            <xpath expr="//button[@name='action_skip']" position="replace"/>
+          </data>
+        </field>
+    </record>
+
+    <record id="action_config_auto_directory" model="ir.actions.act_window">
+        <field name="name">Auto Configure Directory</field>
+        <field name="type">ir.actions.act_window</field>
+        <field name="res_model">document.configuration</field>
+        <field name="view_id" ref="view_auto_config_form"/>
+        <field name="view_type">form</field>
+        <field name="view_mode">form</field>
+        <field name="target">new</field>
+    </record>
+
+    <record model="ir.actions.todo" id="config_auto_directory">
+        <field name="action_id" ref="action_config_auto_directory"/>
+        <field name="groups_id" eval="[(6,0,[ref('base.group_extended')])]"/>
+    </record>
+  </data>
+</openerp>