Ticket 75 clear before import xml

README.rst

@@ -351,6 +351,8 @@ You can also import XML files into your InDesign® documents. The following rule
   corresponding element into the idml document **and** its children.
 - A node having the attribute ``simpleidml-setcontent="delete"`` will remove the corresponding
   element into the idml document (Story and Spread elements).
+- A node having the attribute ``simpleidml-setcontent="clear"`` will clear the text in the
+  element.
 - A node having the attribute ``simpleidml-setcontent="remove-previous-br"`` will remove the new-line
   characters before the element.
 - You can mix several flags using a comma (i.e.: ``simpleidml-setcontent="delete,remove-previous-br"``)
@@ -457,6 +459,11 @@ installed in your PATH.
 Revisions
 =========
 
+1.2.0
+-----
+
+- Add flag ``simpleidml-setcontent="clear"`` to import XML.
+
 1.1.8
 -----
 

setup.py

@@ -9,7 +9,7 @@
 
 setup(
     name="SimpleIDML",
-    version="1.1.8a1",
+    version="1.1.8a3",
     license='BSD Licence',
     author='Stanislas Guerra',
     author_email='[email protected]',

src/simple_idml/__init__.py

@@ -1,6 +1,6 @@
 # -*- coding: utf-8 -*-
 
-VERSION = "1.1.8a1"
+VERSION = "1.1.8a3"
 IdPkgNS = "http://ns.adobe.com/AdobeInDesign/idml/1.0/packaging"
 BACKINGSTORY = "XML/BackingStory.xml"
 

src/simple_idml/components.py

@@ -444,9 +444,12 @@ def remove_element(self, element_id, synchronize=False):
         if synchronize:
             self.synchronize()
 
-    def remove_children(self, element_id, synchronize=False):
+    def remove_children(self, element_id, keep_style=False, synchronize=False):
         elt = self.get_element_by_id(element_id).element
-        for child in elt.iterchildren():
+
+        for i, child in enumerate(elt.iterchildren()):
+            if i == 0 and keep_style and child.tag in ['ParagraphStyleRange', 'CharacterStyleRange']:
+                continue
             elt.remove(child)
         if synchronize:
             self.synchronize()

src/simple_idml/idml.py

@@ -92,12 +92,14 @@ def append_childs(source_node, destination_node):
                     if elt.get("XMLContent"):
                         xml_content_value = elt.get("XMLContent")
                         story_name = f"Stories/Story_{xml_content_value}.xml"
-                        story = Story(self, name=story_name)
+                        story = Story(self, name=story_name, working_copy_path=self.working_copy_path)
                         try:
                             new_source_node = story.get_element_by_id(elt.get("Self"))
-                        # The story does not exists.
+                        # The story does not exists (i.e. for an image).
                         except KeyError:
                             continue
+                        except FileNotFoundError:
+                            continue
                         else:
                             append_childs(new_source_node, new_destination_node)
                     else:
@@ -454,9 +456,44 @@ def _import_node(source_node, at=None, element_id=None, story=None, ignoreconten
 
                     _move_siblings_content(at, element_id)
 
+        self._clear_destination(source_node, at)
+        self.init_lazy_references()
         _import_node(source_node, at)
         return self
 
+    def _clear_destination(self, source_node, at):
+        """ Remove content marked for removal before importing XML. """
+
+        element_id = self.xml_structure.xpath(at)[0].get("Self")
+        items = dict(source_node.items())
+
+        content_flags = items.get(SETCONTENT_TAG, "").split(',')
+        if "clear" in content_flags:
+            story = self.get_story_object_by_xpath(at)
+            story.remove_children(element_id, keep_style=True, synchronize=True)
+            self._xml_structure.xpath(at)[0].clear()
+
+        source_node_children = source_node.getchildren()
+        if len(source_node_children):
+            source_node_children_tags = [n.tag for n in source_node_children]
+            destination_node = self.xml_structure.xpath(at)[0]
+            destination_node_children = destination_node.iterchildren()
+            destination_node_children_tags = [n.tag for n in destination_node.iterchildren()]
+
+            if destination_node_children_tags == source_node_children_tags:
+                for s, d in zip(source_node_children,
+                                [self.xml_structure_tree.getpath(c) for c in destination_node_children]):
+                    self._clear_destination(s, at=d)
+
+            # Step-by-step iteration.
+            else:
+                destination_node_child = next(destination_node_children, None)
+                for source_child in source_node_children:
+                    if destination_node_child is not None and source_child.tag == destination_node_child.tag:
+                        self._clear_destination(source_child,
+                                                at=self.xml_structure_tree.getpath(destination_node_child))
+                        destination_node_child = next(destination_node_children, None)
+
     @use_working_copy
     def import_pdf(self, pdf_path, at, crop="CropContentVisibleLayers", page_number=1):
         self.set_attributes(at, {'href': f'{pdf_path}'})

tests/regressiontests/XML/interview_en.xml

@@ -0,0 +1,22 @@
+<dossier template="PR_206001.idml" reference="PR_206001_EN" standalone="1" support="PLF" parution="206" cahier="publi_redac">
+  <module>
+    <annonce simpleidml-setcontent="false">
+      <accroche simpleidml-setcontent="false">
+        <titre>Pyramid Cabinet</titre>
+        <sous_titre>Where people met goods</sous_titre>
+      </accroche>
+      <article simpleidml-setcontent="false">
+        <question simpleidml-setcontent="clear"><black>Guerra S.</black> Tell us about the history and added value of your agency</question>
+        <reponse simpleidml-setcontent="clear"><bold>Henri D.</bold> Our cabinet has been established by my great-great-grand father in the 90's.</reponse><br />
+        <question simpleidml-setcontent="clear">Which areas do you cover?</question>
+        <reponse simpleidml-setcontent="clear"><bold>H.D.</bold> South east of France.</reponse>
+      </article>
+      <article simpleidml-setcontent="false">
+        <question>Any tactical advantage over your pairs?</question>
+        <reponse simpleidml-setcontent="clear">Our dedication is top-tier.</reponse>
+      </article>
+      <exergue>« Please, contact us! »</exergue>
+      <nom>Henri Dupond</nom>
+    </annonce>
+  </module>
+</dossier>

tests/regressiontests/idml.py

@@ -620,6 +620,33 @@ def test_import_xml_force_content3(self):
     </Story>
   </module>
 </Root>
+""")
+
+    def test_import_xml_clear_content(self):
+        """Example of an article to be translated using an existing composition. """
+        shutil.copy2(os.path.join(IDMLFILES_DIR, "interview.idml"),
+                     os.path.join(OUTPUT_DIR, "interview_origin.idml"))
+        with IDMLPackage(os.path.join(OUTPUT_DIR, "interview_origin.idml")) as idml_file,\
+            open(os.path.join(XML_DIR, "interview_en.xml"), "r") as xml_file:
+            with idml_file.import_xml(xml_file.read(), at="/Root/dossier") as f:
+                xml = f.export_xml()
+                self.assertXMLEqual(xml,
+"""<Root>
+  <dossier template="PR_206001.idml" reference="PR_206001_EN" support="PLF" parution="206" cahier="publi_redac" standalone="1">
+    <module>
+      <annonce simpleidml-setcontent="false">
+        <accroche simpleidml-setcontent="false"><titre>Pyramid Cabinet</titre> <sous_titre>Where people met goods</sous_titre></accroche>
+        <article simpleidml-setcontent="false"><question simpleidml-setcontent="clear"><black>Guerra S.</black> Tell us about the history and added value of your agency</question><reponse simpleidml-setcontent="clear"><bold>Henri D.</bold> Our cabinet has been established by my great-great-grand father in the 90's.</reponse>&#8232;&#8232;<question simpleidml-setcontent="clear">Which areas do you cover?</question><reponse simpleidml-setcontent="clear"><bold>H.D.</bold> South east of France.</reponse></article>
+        <article simpleidml-setcontent="false">
+          <question>Any tactical advantage over your pairs?</question>
+          <reponse simpleidml-setcontent="clear">Our dedication is top-tier.</reponse>
+        </article>
+        <exergue>&#171; Please, contact us! &#187;</exergue>
+        <nom>Henri Dupond</nom>
+      </annonce>
+    </module>
+  </dossier>
+</Root>
 """)
 
     def test_import_pdf(self):

tests/runtests.py

@@ -1,3 +1,5 @@
+#!/usr/bin/env python
+
 import os
 import sys
 import unittest