Include texts from all struct types

In addition to `front_page`, `chapter` and `section`, all other
elements from the DFG viewer struct set now contribute to the text
extraction.

Fixes #43

Changelog

@@ -4,6 +4,15 @@ All notable changes to this project will be documented in this file.
 The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/),
 and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
 
+## [Unreleased]
+### Changed
+- Added tests for TEI API
+- Evaluate texts from all struct types
+- Add `front`, `body` and `back` per default
+
+### Fixed
+- https://github.com/slub/mets-mods2tei/issues/43
+
 ## [0.1.1] - 2020-05-11
 ### Added
 - Treat nested AMD-type (non-logical) divs in logical struct map (i.e.

mets_mods2tei/api/tei.py

@@ -684,38 +684,26 @@ def add_div_structure(self, div):
         # div structure has to be added to text
         text = self.tree.xpath('//tei:text', namespaces=ns)[0]
 
-        # relevant divs
-        struct_divs = list(filter(lambda x: x.get_ADMID() is None, div.get_div()))
-        amd_divs = list(filter(lambda x: x.get_ADMID() is not None, div.get_div()))
-
-        # do not add front node to unstructured volumes
-        if struct_divs:
-            front = etree.SubElement(text, "%sfront" % TEI)
-
-        # body must be present
+        # decent to the deepest AMD
+        while div.get_ADMID() is None:
+            div = div.get_div()[0]
+        start_div = div.get_div()[0]
+        while start_div.get_div() and start_div.get_div()[0].get_ADMID() is not None:
+            div = start_div
+            start_div = start_div.get_div()[0]
+        
+        front = etree.SubElement(text, "%sfront" % TEI)
         body = etree.SubElement(text, "%sbody" % TEI)
+        back = etree.SubElement(text, "%sback" % TEI)
 
-        # do not add back node to unstructured volumes
-        if struct_divs:
-            back = etree.SubElement(text, "%sback" % TEI)
-        else:
-            # default div for unstructured volumes
-            body = etree.SubElement(body, "%sdiv" % TEI)
-            # newspaper case: decent to the deepest div!
-            if amd_divs:
-                div = amd_divs[0]
-                while div.get_div():
-                    div = div.get_div()[0]
-            body.set("id", div.get_ID())
-
-        for sub_div in struct_divs:
+        entry_point = front
+
+        for sub_div in div.get_div():
             if sub_div.get_TYPE() == "title_page":
-                self.__add_div(front, sub_div, 1, "titlePage")
-            elif sub_div.get_TYPE() == "chapter" or sub_div.get_TYPE() == "section":
-                self.__add_div(body, sub_div, 1)
+                self.__add_div(entry_point, sub_div, 1, "titlePage")
             else:
-                #FIXME
-                pass
+                entry_point = body
+                self.__add_div(entry_point, sub_div, 1)
 
     def __add_div(self, insert_node, div, n, tag="div"):
         """

tests/test_tei.py

@@ -1,6 +1,32 @@
 # -*- coding: utf-8 -*-
 
+import os
+import pytest
+import warnings
+
+# the import of dir_util introduces a deprecation warning
+# we can't do much about it
+with warnings.catch_warnings():
+    warnings.simplefilter("ignore")
+    from distutils import dir_util
+
 from mets_mods2tei import Tei
+from mets_mods2tei import Mets
+
+@pytest.fixture
+def datadir(tmpdir, request):
+    '''
+    Fixture responsible for searching a folder with the same name of test
+    module and, if available, moving all contents to a temporary directory so
+    tests can use them freely.
+    '''
+    filename = request.module.__file__
+    test_dir, _ = os.path.splitext(filename)
+
+    if os.path.isdir(test_dir):
+        dir_util.copy_tree(test_dir, str(tmpdir))
+
+    return tmpdir
 
 def test_constructor():
     '''
@@ -9,6 +35,16 @@ def test_constructor():
     tei = Tei()
     assert(tei.tree is not None)
 
+def test_reading_local_file(datadir):
+    '''
+    Test reading from a local mets file
+    '''
+    f = open(datadir.join('test_mets.xml'))
+    mets = Mets.read(f)
+    tei = Tei()
+    tei.fill_from_mets(mets, ocr=False)
+    assert(tei.tree is not None)
+
 def test_string_dumping():
     tei = Tei()
     assert(tei.tostring().startswith(b"<"))