Citations and bibliography

tei2imxml.py

@@ -222,12 +222,12 @@ def render_reference(list_of_xml_elements, cited_data):
         element.text = cited_data[citekey][2]
 # def render_reference ends here
 
-def write_citation_markdown(used_citekeys):
+def write_citation_markdown(used_citekeys, citations_filename):
     """Write markdown file with citekeys for bibliography rendering"""
 
     md_file_header = "---\nlang: en\ntitle: Citations\n...\n\n"
 
-    with open(TMP_DIR + os.path.sep + "used_citations.md", "w") as citation_formatter:
+    with open(TMP_DIR + os.path.sep + citations_filename, "w") as citation_formatter:
         citation_formatter.write(md_file_header)
         # citation_formatter.write("# Full parentheses\n")
         citation_formatter.write("# citeauthoryear\n")
@@ -245,36 +245,41 @@ def write_citation_markdown(used_citekeys):
     logging.info("Wrote citation formatter.")
 # def write_citation_markdown ends here
 
-def format_citations(used_citekeys, bibdata):
-    """Return a formatted entry of the used citations"""
+def format_reference_list(used_citekeys, html_file):
+    """Create an HTML formatted list of references"""
 
-    with open(TMP_DIR + os.path.sep + "formatted_citations.html", "r") as ding:
-        cites = BeautifulSoup(ding, "html.parser")
-    with open(TMP_DIR + os.path.sep + "formatted_citations.html", "r") as ding:
+    # second part of function
+    with open(TMP_DIR + os.path.sep + html_file, "r") as ding:
         reference_list = soupparser.fromstring(ding, features="html.parser")
 
-    # references = dd.xpath("//div[@class='references']")
-    # with open("tmp_files/formatted_citations.html", "r") as ding:
-
     references = reference_list.xpath("//div[@class='references']")[0]
 
-    # full_paren_cites = cites.select("#full-parentheses ~ p > span")
-    # year_paren_cites = cites.select("#year-parentheses ~ p > span")
+    return references
+# def format_reference_list ends here
+
+def format_citations(used_citekeys, bibdata, html_file):
+    """Return a formatted entry of the used citations"""
+
+    # print(used_citekeys)
+
+    with open(TMP_DIR + os.path.sep + html_file, "r") as ding:
+        cites = BeautifulSoup(ding, "html.parser")
 
     citation_dict = {}
 
     for entry in used_citekeys:
         for entry_2 in bibdata:
             if entry_2["id"] == entry:
                 current_citation = entry
+                # logging.info("%s: The title %s" % (html_file, entry_2["title"]))
                 strTitle = entry_2["title"]
 
-        title = strTitle
-        authoryear_citation = cites.select("#citeauthoryear ~ p > span[data-cites='%s']" % entry)[0].text
-        year_citation = cites.select("#citeyear ~ p > span[data-cites='%s']" % entry)[0].text
-        citation_dict[entry] = (authoryear_citation, year_citation, title)
+                title = strTitle
+                authoryear_citation = cites.select("#citeauthoryear ~ p > span[data-cites='%s']" % entry)[0].text[1:-1]
+                year_citation = cites.select("#citeyear ~ p > span[data-cites='%s']" % entry)[0].text[1:-1]
+                citation_dict[entry] = (authoryear_citation, year_citation, title)
 
-    return citation_dict, references
+    return citation_dict
 # def format_citations ends here
 
 def format_pagerange(pagerange_start, pagerange_end):
@@ -378,9 +383,18 @@ def transform_body(xml_tree, cited_data, authors, publang):
         citation.set("data-placement", "bottom")
 
         if len(cited_range) > 0:
-            pagerange_start = cited_range[0].get("from")
-            pagerange_end = cited_range[0].get("to")
-            pagerange = ", " + format_pagerange(pagerange_start, pagerange_end)
+            if cited_range[0].text is not None and cited_range[0].get("from") is not None:
+                print("You must not use 'from' attribute and text in citedRange at the same time. Exiting.")
+                sys.exit()
+            elif cited_range[0].text is not None:
+                # might contain markup!
+                pagerange = ", {}".format(cited_range[0].text)
+                # clear the text
+                cited_range[0].text = ""
+            elif cited_range[0].get("from") is not None:
+                pagerange_start = cited_range[0].get("from")
+                pagerange_end = cited_range[0].get("to")
+                pagerange = ", " + format_pagerange(pagerange_start, pagerange_end)
             cited_range[0].tag = "tagtobestripped"
 
         if cite_render == 'inline':
@@ -572,7 +586,57 @@ def assign_ids(xml_tree, data):
     return xml_tree, data
 # def assign_ids ends here
 
-def add_bibliography(xml_tree, refs_for_bib_chapter):
+def update_ids(xml_tree):
+    """Update the references in EOAref to the id value assigned in assign_ids"""
+
+    xmlReferences = xml_tree.findall(".//EOAref")
+
+    for xmlReference in xmlReferences:
+        eoa_reference = xmlReference.find("ref")
+
+        label_text = xmlReference.find("Label").text[1:]
+        logging.debug("label text is %s" % label_text)
+
+        # if label_text.endswith("-hi"):
+        #     logging.debug("%s is a hyperimage reference. Leaving out for now." % label_text)
+        #     pass
+        # else:
+        corresponding_eoa_id_element = xml_tree.xpath("//*[@xml:id='{}']".format(label_text))
+        if len(corresponding_eoa_id_element) == 0:
+            print("There seems to be no corresponding xml:id for %s. Exiting." % label_text)
+            sys.exit()
+        elif len(corresponding_eoa_id_element) > 1:
+            print("The xml:id %s has been assigned more than once. This is not allowed. Exiting." % corresponding_eoa_id_element)
+            sys.exit()
+        else:
+            eoa_id_element = corresponding_eoa_id_element[0]
+
+        eoa_id = eoa_id_element.get("id")
+        eoa_reference.set("target", eoa_id)
+
+    return xml_tree
+# def update_ids ends here
+
+def prepare_bibliography(bib_data):
+    """Create a JSON version of bibliography data, using pandoc-citeproc"""
+
+    # json
+    interim_bib_json_file = TMP_DIR + os.path.sep + "tmp-bib.json"
+    citeproc_command = "pandoc-citeproc --bib2json  %s" % bib_data["source"]
+    citeproc_arguments = shlex.split(citeproc_command)
+    citeproc_process = subprocess.Popen(citeproc_arguments, stdout=subprocess.PIPE)
+    citeproc_json = citeproc_process.stdout.read()
+    citations_json = json.loads(citeproc_json)
+
+    with open(interim_bib_json_file, 'w') as json_file:
+        json_file.write(citeproc_json.decode('utf-8'))
+
+    logging.info("Wrote json file")
+
+    return citations_json
+# def prepare_bibliography ends here
+
+def add_bibliography_monograph(xml_tree, refs_for_bib_chapter):
     """Add another chapter containing the bibliography."""
 
     root_element = xml_tree.getroot()