Adapted fix_tei to current version of RNC schema

fix_tei.py

@@ -39,21 +39,18 @@
 import argparse
 import traceback
 import libeoaconvert
+import configparser
 
 logging.basicConfig(level=logging.INFO, format=' %(asctime)s - %(levelname)s - %(message)s')
 
-# do things like in latex2eoa: search and replace things by regex
-# also, delete elements and attributes inserted by metypeset
-# and, rename elements according to our schema
-
-# treat
-# assignment of identifiers
-
 ns_tei = "http://www.tei-c.org/ns/1.0"
 NS_MAP = {"t" : ns_tei}
 
 TMP_DIR = os.path.expanduser("tmp_files")
 
+BOILERPLATES = configparser.ConfigParser()
+BOILERPLATES.read("data/tei_boilerplate.cfg")
+
 def get_place_in_xml_tree(element, tree):
     """Find out the position of an element in a tree.
 
@@ -82,6 +79,25 @@ def parse_bibtex(bibfile):
     # return all_references
 # def parse_bibtex ends here
 
+def restore_xml_tags(text):
+    """Convert XML entities back to code
+
+    &lt; => <
+    """
+
+    replacements = {
+        "&lt;" : "<",
+        "&gt;" : ">",
+        "&apos;" : "'",
+        "&amp;" : "&"
+        }
+
+    for item in replacements:
+        text = text.replace(item, replacements[item])
+
+    return text
+# def restore_xml_tags ends here
+
 def unescape(text):
     """Remove HTML or XML character references and entities from a text
     string. Return a Unicode string.
@@ -271,10 +287,11 @@ def make_figure_elements(list_of_figures, figure_directory):
 # def make_figure_elements ends here
 
 def cleanup_xml(xml_tree):
-    """Perform some cleaning on XML"""
+    """Perform some cleaning on XML
 
-    # also, delete elements and attributes inserted by metypeset
-    # and, rename elements according to our schema
+    Also, delete elements and attributes inserted by metypeset and
+    rename elements according to our schema
+    """
 
     metypeset_attrib = xml_tree.findall("//t:*[@meTypesetSize]", namespaces=NS_MAP)
     color_attrib = xml_tree.xpath("//t:hi[contains(@rend, 'color') or contains(@rend, 'background')]", namespaces=NS_MAP)
@@ -343,61 +360,121 @@ def fix_document_structure(xml_tree, highest_level):
             subsection.set("type", "subsection")
         for subsubsection in subsubsection_divs:
             subsubsection.set("type", "subsubsection")
-
-    # section_divs = xml_tree.xpath("//t:body/t:div", namespaces=NS_MAP)
-    # subsection_divs = xml_tree.xpath("//t:body/t:div/t:div", namespaces=NS_MAP)
-    # subsubsection_divs = xml_tree.xpath("//t:body/t:div/t:div/t:div", namespaces=NS_MAP)
-
-    # for section in section_divs:
-    #     section.set("type", "section")
-    # for subsection in subsection_divs:
-    #     subsection.set("type", "subsection")
-    # for subsubsection in subsubsection_divs:
-    #     subsubsection.set("type", "subsubsection")
 # def fix_document_structure ends here
 
 def fix_tei_header(xml_tree, bibfile_string):
     """Populate TEI header with mandatory data"""
 
     title_statement = xml_tree.xpath("//t:titleStmt", namespaces=NS_MAP)[0]
     title_element = title_statement.find("t:title", namespaces=NS_MAP)
-    title_element.set("level", "s")
-    title_element.set("n", "20")
-    title_element.text = "Titel der Serie"
 
-    main_title = etree.Element("title", type="main")
-    main_title.text = "FotoObjekte"
-    title_statement.insert(0, main_title)
+    title_element.set("type", "main")
+    title_element.set("level", "m")
+    if title_element.text is None:
+        title_element.text = "Insert title of publication here"
+    else:
+        pass
 
-    # series = etree.SubElement(title_statement, "title", level="s", n="20").text = "Studies"
-    # subtitle = etree.SubElement(title_statement, "title", level="sub").text = "Artikelsammlung"
+    edition = xml_tree.xpath("//t:editionStmt/t:edition", namespaces=NS_MAP)[0]
+    edition_date = edition.find("t:date", namespaces=NS_MAP)
+    edition_date.clear()
+    edition_date.tag = "tagtobestripped"
+    edition.text = "First published {} by {}".format(datetime.now().strftime("%Y"), BOILERPLATES.get("Header","eoa_name"))
 
     publication_statement = xml_tree.xpath("//t:publicationStmt", namespaces=NS_MAP)[0]
     unknown_paragraph = publication_statement.find("t:p", namespaces=NS_MAP)
     if unknown_paragraph.text == "unknown":
         unknown_paragraph.clear()
         unknown_paragraph.tag = "tagtobestripped"
 
-    etree.SubElement(publication_statement, "publisher").text = "Edition Open Access"
+    publisher_element = etree.SubElement(publication_statement, "publisher")
+    overall_org = etree.SubElement(publisher_element, "orgName", n="EOA", ref=BOILERPLATES.get("Header","eoa_url"))
+    overall_org.text = BOILERPLATES.get("Header","eoa_name")
+    publishing_org = etree.SubElement(publisher_element, "orgName", n="Press", ref=BOILERPLATES.get("Header","mprl_url"))
+    publishing_org.text = BOILERPLATES.get("Header","mprl_name")
+
     pub_date = etree.SubElement(publication_statement, "date", when=datetime.now().strftime("%Y-%m-%d"))
     availability = etree.SubElement(publication_statement, "availability")
-    licence = etree.SubElement(availability, "licence", target="https://creativecommons.org/licenses/by-nc-sa/3.0/de/deed.en")
-    licence.text = "by-nc-sa"
-    # licence_text = etree.SubElement(licence, "p").text = """Distributed under the Creative Commons Attribution-NonCommercial-ShareAlike 3.0 Germany License."""
+    licence = etree.SubElement(availability, "licence", target=BOILERPLATES.get("Header","licence_url"))
+    licence.text = BOILERPLATES.get("Header","licence_text")
+
+    # series statement
+    series_stmt = etree.Element("seriesStmt")
+    title_element = etree.SubElement(series_stmt, "title").text = "Series title"
+    resp_stmt = etree.SubElement(series_stmt, "respStmt")
+    resp_title = etree.SubElement(resp_stmt, "resp").text = "Series Editors"
+    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 = get_place_in_xml_tree(publication_statement, publication_stmt_parent) + 1
+    publication_stmt_parent.insert(series_stmt_insertion_point, series_stmt)
 
     source_desc = xml_tree.xpath("//t:sourceDesc", namespaces=NS_MAP)[0]
-    bibfile = etree.SubElement(source_desc, "ab", type="bibliography")
+    suggested_citation = etree.SubElement(source_desc, "ab", type="suggestedcitation").text = "Suggested Citation"
+    bibfile = etree.SubElement(source_desc, "ab", type="bibdatabase")
     etree.SubElement(bibfile, "ref", type="monograph", target=bibfile_string)
 
+    # profile description
     profile_desc = etree.Element("profileDesc")
+    brief_abstract = etree.SubElement(profile_desc, "abstract", n="BriefDescription")
+    brief_abstract_p = etree.SubElement(brief_abstract, "p").text = "Short abstract"
+    detailed_abstract = etree.SubElement(profile_desc, "abstract", n="DetailedDescription")
+    detailed_abstract_p = etree.SubElement(detailed_abstract, "p").text = "Long abstract"
+    additional_text = etree.SubElement(profile_desc, "abstract", n="additional")
+    additional_text_p = etree.SubElement(additional_text, "p").text = "Additional text"
+    textclass = etree.SubElement(profile_desc, "textClass")
+    keywords = etree.SubElement(textclass, "keywords")
+    list_keywords = etree.SubElement(keywords, "list")
+    keyword_item = etree.SubElement(list_keywords, "item").text = BOILERPLATES.get("Header","eoa_name")
     langusage = etree.SubElement(profile_desc, "langUsage")
-    language = etree.SubElement(langusage, "language", ident="en").text = "English"
+    language = etree.SubElement(langusage, "language", ident="principal language")
+    xml_tree.insert(1, profile_desc)
+
+    encoding_desc = xml_tree.xpath("//t:encodingDesc", namespaces=NS_MAP)[0]
+
+    project_desc = etree.Element("projectDesc")
+    eoainfo_p1 = etree.SubElement(project_desc, "p", n="eoainfo").text = BOILERPLATES.get("Header","eoainfo_p1")
+    eoainfo_p2 = etree.SubElement(project_desc, "p", n="eoainfo").text = BOILERPLATES.get("Header","eoainfo_p2")
+    mprlinformation = etree.SubElement(project_desc, "p", n="mprlinformation").text = BOILERPLATES.get("Header","mprlinformation")
+    scientificboard = etree.SubElement(project_desc, "p", n="scientificboard").text = BOILERPLATES.get("Header","scientificboard")
+    eoadevteam = etree.SubElement(project_desc, "p", n="eoadevteam").text = BOILERPLATES.get("Header","eoadevteam")
+    encoding_desc.insert(0, project_desc)
 
-    xml_tree.insert(2, profile_desc)
+    appinfo = encoding_desc.find("t:appInfo", namespaces=NS_MAP)
+    fix_tei_info = etree.Element("application", ident="fix_tei", version=__version__)
+    fix_tei_info.attrib["{http://www.w3.org/XML/1998/namespace}id"] = "fixtei"
+    fix_tei_label = etree.SubElement(fix_tei_info, "label").text = "Fix TEI for EOA"
+    appinfo.insert(-1, fix_tei_info)
+
+    revision_desc = xml_tree.xpath("//t:revisionDesc", namespaces=NS_MAP)[0]
+    olderchanges = revision_desc.find("t:listChange", namespaces=NS_MAP)
+    olderchanges.clear()
+    olderchanges.tag = "tagtobestripped"
+
+    first_change = etree.SubElement(revision_desc, "change", when=datetime.now().strftime("%Y-%m-%d"), who="#fixtei")
+    first_change.text = "Fixed TEI created by oxgarage conversion"
 
     return xml_tree
 # def fix_tei_header ends here
 
+def add_tei_frontpart():
+    """Add a small front part
+
+    Contains a cover image and an optional dedication.
+    """
+
+    frontpart = etree.Element("front")
+    cover_image = etree.SubElement(frontpart, "figure", type="cover")
+    cover_url = etree.SubElement(cover_image, "graphic", url="images/Cover.jpg")
+    cover_caption = etree.SubElement(cover_image, "head").text = "Cover caption"
+
+    dedication = etree.SubElement(frontpart, "div", type="dedication")
+    dedication_text = etree.SubElement(dedication, "ab").text = "Dedication text"
+
+    return frontpart
+# def add_tei_frontpart ends here
+
 def evaluate_report(report):
     """Print report of conversion."""
 
@@ -510,6 +587,10 @@ def main():
         tei_header = xml_tree2.xpath("//t:teiHeader", namespaces=NS_MAP)
         fix_tei_header(tei_header[0], str(args.bibfile))
 
+        tei_text = xml_tree2.xpath("/t:TEI/t:text", namespaces=NS_MAP)[0]
+        tei_front_part = add_tei_frontpart()
+        tei_text.insert(0, tei_front_part)
+
     etree.strip_tags(xml_tree2, "tagtobestripped")
 
     dictChapters = {}