Code cleanup

fix_tei.py

@@ -51,7 +51,7 @@
 RUNNING_DIRECTORY = os.path.dirname(os.path.realpath(__file__))
 logging.debug("The script is run from {}".format(RUNNING_DIRECTORY))
 TEI_BOILERPLATE = os.path.sep.join([RUNNING_DIRECTORY, "data", "tei_boilerplate.cfg"])
-print(TEI_BOILERPLATE)
+
 if not os.path.exists(TEI_BOILERPLATE):
     logging.error("Could not find TEI boilerplate config. Exiting.")
     sys.exit()
@@ -70,8 +70,8 @@ def parse_bibtex(bibfile):
 
     all_references.update(tmp_dict)
 
-    return tmp_dict
     # return all_references
+    return tmp_dict
 # def parse_bibtex ends here
 
 def restore_xml_tags(text):
@@ -119,7 +119,8 @@ def fixup(m):
                 text = chr(html.entities.name2codepoint[text[1:-1]])
             except KeyError:
                 pass
-        return text # leave as is
+        # leave as is
+        return text
     return re.sub(r"&#?\w+;", fixup, text)
 # def unescape ends here
 
@@ -295,7 +296,7 @@ def cleanup_xml(xml_tree):
     logging.info("Found %s colour attributes." % len(color_attrib))
 
     for attribute in metypeset_attrib:
-        logging.info("number of attributes: %s" % len(attribute.attrib))
+        logging.info("Number of attributes: %s" % len(attribute.attrib))
         attribute.attrib.pop("meTypesetSize")
 
     for attribute in color_attrib:
@@ -385,7 +386,7 @@ def fix_tei_header(xml_tree, bibfile_string, bibtype):
     respname = etree.SubElement(example_resp, "persName")
     surname = etree.SubElement(respname, "surname").text = "N"
     forename = etree.SubElement(respname, "forename").text = "N"
-    libeoaconvert.insert_after(example_resp, author_element)
+    author_element.addnext(example_resp)
 
     edition = xml_tree.xpath("//t:editionStmt/t:edition", namespaces=NS_MAP)[0]
     edition_date = edition.find("t:date", namespaces=NS_MAP)
@@ -402,7 +403,8 @@ def fix_tei_header(xml_tree, bibfile_string, bibtype):
     extent_element = etree.Element("extent")
     pages = etree.SubElement(extent_element, "measure", commodity="pages", quantity="0")
     price = etree.SubElement(extent_element, "measure", type="price", unit="EUR", quantity="0")
-    libeoaconvert.insert_after(extent_element, publication_statement, before=True)
+
+    publication_statement.addprevious(extent_element)
 
     publisher_element = etree.SubElement(publication_statement, "publisher")
     overall_org = etree.SubElement(publisher_element, "orgName", n="EOA", ref=BOILERPLATES.get("Header","eoa_url"))
@@ -423,9 +425,8 @@ def fix_tei_header(xml_tree, bibfile_string, bibtype):
     resp_names = etree.SubElement(resp_stmt, "name", type="serieseditors")
     resp_names.text = BOILERPLATES.get("Header","mprl_series_editors")
     series_number = etree.SubElement(series_stmt, "idno", type="number").text = "number"
-    publication_stmt_parent = publication_statement.getparent()
-    series_stmt_insertion_point = libeoaconvert.get_place_in_xml_tree(publication_statement, publication_stmt_parent) + 1
-    publication_stmt_parent.insert(series_stmt_insertion_point, series_stmt)
+
+    publication_statement.addnext(series_stmt)
 
     source_desc = xml_tree.xpath("//t:sourceDesc", namespaces=NS_MAP)[0]
     suggested_citation = etree.SubElement(source_desc, "ab", type="suggestedcitation").text = "Suggested Citation"
@@ -495,29 +496,33 @@ def add_tei_frontpart():
 def evaluate_report(report):
     """Print report of conversion."""
 
-    print("="*60)
-    print(' '*4, "Conversion report")
-    print("-"*60)
+    report_string = "="*60 + "\n"
+    report_string += ' '*4 + "Conversion report\n"
+    report_string += "-"*60 + "\n"
     if len(report["bad_figures"]) > 0:
-        print("{} {} could not be linked to a file in the image directory:".format(len(report["bad_figures"]), libeoaconvert.plural(len(report["bad_figures"]), "figure")))
+        report_string += "{} {} could not be linked to a file in the image directory:\n".format(len(report["bad_figures"]), libeoaconvert.plural(len(report["bad_figures"]), "figure"))
         for item in report["bad_figures"]:
-            print(' '*4, item)
+            report_string += ' '*4 + item + "\n"
     else:
-        print("All figures were linked.")
+        report_string += "All figures were linked.\n"
     if len(report["citekeys_not_in_bib"]) > 0:
-        print("{} of {} {} could not be found in the bibliography database:".format(len(report["citekeys_not_in_bib"]), report["len_citekeys"], libeoaconvert.plural(len(report["citekeys_not_in_bib"]), "citation")))
+        report_string += "{} of {} {} could not be found in the bibliography database:\n".format(len(report["citekeys_not_in_bib"]), report["len_citekeys"], libeoaconvert.plural(len(report["citekeys_not_in_bib"]), "citation"))
         for item in report["citekeys_not_in_bib"]:
-            print(' '*4, item)
-        print("\nThe missing citations were also stored in the pickle file and can be re-used by the create_tmpbib tool.\n")
+            report_string += ' '*4 +  item + "\n"
+        report_string += "\nThe missing citations were also stored in the pickle file and can be re-used by the create_tmpbib tool.\n"
     else:
-        print("All citekeys were found in the bibliography database.")
+        report_string += "All citekeys were found in the bibliography database.\n"
     if len(report["bad_pageref"]) > 0:
-        print("{} page {} could not be parsed into start and end value:".format(len(report["bad_pageref"]), libeoaconvert.plural(len(report["bad_pageref"]), "reference")))
+        report_string += "{} page {} could not be parsed into start and end value:".format(len(report["bad_pageref"]), libeoaconvert.plural(len(report["bad_pageref"]), "reference"))
         for item in report["bad_pageref"]:
-            print(' '*4, item)
+            report_string += ' '*4 + item + "\n"
     else:
-        print("All page references could be parsed into discrete values.")
-    print("="*60)
+        report_string += ("All page references could be parsed into discrete values.\n")
+    report_string += "="*60 + "\n"
+
+    print(report_string)
+
+    return
 # def evaluate_report ends here
 
 def main():
@@ -581,7 +586,7 @@ def main():
     try:
         xml_tree2 = etree.fromstring(mod_string3)
     except etree.XMLSyntaxError:
-        print("\nXML syntax error when trying to parse modified tree. Dumped it to %s." % debug_output)
+        logging.error("\nXML syntax error when trying to parse modified tree. Dumped it to %s." % debug_output)
         print("-"*60)
         traceback.print_exc(file=sys.stdout)
         print("-"*60)