Merge pull request #178 from elifesciences/develop

PR for version 0.74.0 release

elifecleaner/__init__.py

@@ -1,7 +1,7 @@
 import logging
 
 
-__version__ = "0.73.0"
+__version__ = "0.74.0"
 
 
 LOGGER = logging.getLogger(__name__)

elifecleaner/block.py

@@ -130,6 +130,19 @@ def tag_index_groups(body_tag, sub_article_id, block_type, identifier):
     return fig_index_groups
 
 
+def graphic_href_list(body_tag, index_groups):
+    "collect a list of xlink:href values of graphic tags from the index_groups"
+    href_list = []
+    for group in index_groups:
+        if group.get("inline_graphic_index"):
+            inline_graphic_p = body_tag[group.get("inline_graphic_index")]
+            inline_graphic_tag = inline_graphic_tag_from_tag(inline_graphic_p)
+            image_href = utils.xlink_href(inline_graphic_tag)
+            if image_href:
+                href_list.append(image_href)
+    return href_list
+
+
 def title_paragraph_content(string_list):
     "from list of strings repair inline formatting tags and split into title and paragraph"
     # check for nested inline formatting tags

elifecleaner/fig.py

@@ -2,11 +2,6 @@
 from elifecleaner import block, utils
 
 
-def inf_file_identifier(inf_file_name):
-    "specific part of an inline graphic file name, e.g. inf1 in elife-70493-inf1.png"
-    return inf_file_name.rsplit(".", 1)[0].rsplit("-", 1)[-1]
-
-
 def fig_file_name_identifier(sub_article_id, fig_index):
     "create the unique portion of a fig file name"
     return "%s-fig%s" % (sub_article_id, fig_index)
@@ -20,7 +15,8 @@ def fig_id(sub_article_id, fig_index):
 def fig_file_name(inf_file_name, sub_article_id, fig_index):
     "from inf file name create a new fig file name"
     return inf_file_name.replace(
-        inf_file_identifier(inf_file_name), "%s-fig%s" % (sub_article_id, fig_index)
+        utils.inf_file_identifier(inf_file_name),
+        "%s-fig%s" % (sub_article_id, fig_index),
     )
 
 
@@ -45,13 +41,7 @@ def inline_graphic_hrefs(sub_article_root, identifier):
     if body_tag is not None:
         # match paragraphs with fig data in them and record the tag indexes
         fig_index_groups = fig_tag_index_groups(body_tag, sub_article_id, identifier)
-        for group in fig_index_groups:
-            if group.get("inline_graphic_index"):
-                inline_graphic_p = body_tag[group.get("inline_graphic_index")]
-                inline_graphic_tag = block.inline_graphic_tag_from_tag(inline_graphic_p)
-                image_href = utils.xlink_href(inline_graphic_tag)
-                if image_href:
-                    href_list.append(image_href)
+        href_list = block.graphic_href_list(body_tag, fig_index_groups)
     return href_list
 
 

elifecleaner/table.py

@@ -10,11 +10,32 @@ def table_wrap_id(sub_article_id, table_index):
     return "%stable%s" % (sub_article_id, table_index)
 
 
+def table_file_name(inf_file_name, sub_article_id, table_index):
+    "from inf file name create a new table file name"
+    return inf_file_name.replace(
+        utils.inf_file_identifier(inf_file_name),
+        "%s-table%s" % (sub_article_id, table_index),
+    )
+
+
 def table_tag_index_groups(body_tag, sub_article_id, identifier):
     "iterate through the tags in body_tag and find groups of tags to be converted to a table-wrap"
     return block.tag_index_groups(body_tag, sub_article_id, "table", identifier)
 
 
+def table_inline_graphic_hrefs(sub_article_root, identifier):
+    "get inline-graphic href values"
+    sub_article_id, body_tag = block.sub_article_tag_parts(sub_article_root)
+    href_list = []
+    if body_tag is not None:
+        # match paragraphs with table data in them and record the tag indexes
+        table_index_groups = table_tag_index_groups(
+            body_tag, sub_article_id, identifier
+        )
+        href_list = block.graphic_href_list(body_tag, table_index_groups)
+    return href_list
+
+
 def transform_table_group(body_tag, table_index, table_group, sub_article_id):
     "transform one set of p tags into table-wrap tags as specified in the table_group dict"
     inline_graphic_p_tag = body_tag[table_group.get("inline_graphic_index")]
@@ -30,8 +51,10 @@ def transform_table_group(body_tag, table_index, table_group, sub_article_id):
             inline_graphic_p_tag, body_tag, table_group.get("caption_index")
         )
 
+    # rename the image file
+    new_file_name = table_file_name(image_href, sub_article_id, table_index)
+
     # graphic tag
-    new_file_name = image_href
     block.set_graphic_tag(inline_graphic_p_tag, image_href, new_file_name)
 
     # convert inline-graphic p tag to a table-wrap tag

elifecleaner/utils.py

@@ -13,6 +13,11 @@ def file_extension(file_name):
     return file_name.rsplit(".", 1)[-1]
 
 
+def inf_file_identifier(inf_file_name):
+    "specific part of an inline graphic file name, e.g. inf1 in elife-70493-inf1.png"
+    return inf_file_name.rsplit(".", 1)[0].rsplit("-", 1)[-1]
+
+
 # match ascii characters from decimal 0 to 31, as hexidecimal character entitiy strings
 # e.g.  or 
 CONTROL_CHARACTER_ENTITY_MATCH_PATTERN = r"&#x0{0,2}[0-1][0-9A-Fa-f];"

tests/test_fig.py

@@ -10,16 +10,6 @@
 )
 
 
-class TestInfFileIdentifier(unittest.TestCase):
-    "tests for fig.inf_file_identifier()"
-
-    def test_inf_file_identifer(self):
-        "identifier portion of an inline-graphic file name"
-        inf_file_name = "elife-70493-inf1.png"
-        expected = "inf1"
-        self.assertEqual(fig.inf_file_identifier(inf_file_name), expected)
-
-
 class TestFigFileNameIdentifer(unittest.TestCase):
     "tests for fig.fig_file_name_identifier()"
 

tests/test_table.py

@@ -40,6 +40,28 @@ def table_sub_article_xml_fixture():
     )
 
 
+class TestTableInlineGraphicHrefs(unittest.TestCase):
+    "tests for table.table_inline_graphic_hrefs()"
+
+    def test_table_inline_graphic_hrefs(self):
+        "get a list of xlink:href values from inline-graphic tags to be converted to table-wrap"
+        xml_string = (
+            b'<sub-article id="sa1" xmlns:xlink="http://www.w3.org/1999/xlink">'
+            b"<body>"
+            b"<p><bold>Review table 1.</bold></p>"
+            b'<p><inline-graphic xlink:href="elife-70493-inf1.png"/></p>'
+            b"<p>Next paragraph is not an inline-graphic href.</p>"
+            b'<p><inline-graphic xlink:href="elife-70493-inf2.png"/></p>'
+            b"</body>"
+            b"</sub-article>"
+        )
+        identifier = "test.zip"
+        tag = ElementTree.fromstring(xml_string)
+        expected = ["elife-70493-inf1.png"]
+        result = table.table_inline_graphic_hrefs(tag, identifier)
+        self.assertEqual(result, expected)
+
+
 class TestTransformTable(unittest.TestCase):
     "tests for table.transform_table()"
 
@@ -77,7 +99,7 @@ def test_referee_report(self):
                 "<title>Table title.</title>"
                 "<p>This is the caption for this table that describes what it contains.</p>"
                 "</caption>"
-                '<graphic mimetype="image" mime-subtype="png" xlink:href="elife-70493-inf1.png" />'
+                '<graphic mimetype="image" mime-subtype="png" xlink:href="elife-70493-sa1-table1.png" />'
                 "</table-wrap>"
                 "<p>Another paragraph with an inline graphic "
                 '<inline-graphic xlink:href="elife-70493-inf2.jpg" />'

tests/test_utils.py

@@ -19,6 +19,16 @@ def test_file_extension(self):
             )
 
 
+class TestInfFileIdentifier(unittest.TestCase):
+    "tests for utils.inf_file_identifier()"
+
+    def test_inf_file_identifer(self):
+        "identifier portion of an inline-graphic file name"
+        inf_file_name = "elife-70493-inf1.png"
+        expected = "inf1"
+        self.assertEqual(utils.inf_file_identifier(inf_file_name), expected)
+
+
 class TestMatchControlCharacterEntities(unittest.TestCase):
     def test_match_control_character_entities(self):
         self.assertEqual([], utils.match_control_character_entities(""))