From 2c1d168981496a12dcff6588cedf38baedde6502 Mon Sep 17 00:00:00 2001
From: kthoden <kthoden@gwdg.de>
Date: Fri, 21 Dec 2018 13:35:05 +0100
Subject: [PATCH] Option for disabling citedRange parser

---
 fix_tei.py | 50 +++++++++++++++++++++++++++++++-------------------
 1 file changed, 31 insertions(+), 19 deletions(-)

diff --git a/fix_tei.py b/fix_tei.py
index b52c542..b05af46 100644
--- a/fix_tei.py
+++ b/fix_tei.py
@@ -136,7 +136,7 @@ def convert_references(string):
     return string
 # def convert_references ends here
 
-def convert_citations(string):
+def convert_citations(string, citedrangetext):
     """Find citation shorthand using regex.
 
     Return a tuple of the modified string and a list of found citations
@@ -155,12 +155,18 @@ def convert_citations(string):
     year_citations_pattern = re.compile(r"(§|&#xA7;|&#167;)(§|&#xA7;|&#167;)(?P<citekey>.+?)(\!(?P<pages>.*?))?(§|&#xA7;|&#167;)(§|&#xA7;|&#167;)")
     year_citations = re.findall(year_citations_pattern, string)
     logging.info("Found %s year citations." % len(year_citations))
-    string = re.sub(year_citations_pattern, r"<bibl><ref type='inline' target='#\g<citekey>'/><citedRange from='\g<pages>'/></bibl>", string)
+    if citedrangetext:
+        string = re.sub(year_citations_pattern, r"<bibl><ref type='inline' target='#\g<citekey>'/><citedRange>\g<pages></citedRange></bibl>", string)
+    else:
+        string = re.sub(year_citations_pattern, r"<bibl><ref type='inline' target='#\g<citekey>'/><citedRange from='\g<pages>'/></bibl>", string)
 
     authoryear_citation_pattern = re.compile(r"(§|&#xA7;|&#167;)(?P<citekey>.+?)(\!(?P<pages>.*?))?(§|&#xA7;|&#167;)")
     authoryear_citations = re.findall(authoryear_citation_pattern, string)
     logging.info("Found %s author/year citations." % len(authoryear_citations))
-    string = re.sub(authoryear_citation_pattern, r"<bibl><ref target='#\g<citekey>'/><citedRange from='\g<pages>'/></bibl>", string)
+    if citedrangetext:
+        string = re.sub(authoryear_citation_pattern, r"<bibl><ref target='#\g<citekey>'/><citedRange>\g<pages></citedRange></bibl>", string)
+    else:
+        string = re.sub(authoryear_citation_pattern, r"<bibl><ref target='#\g<citekey>'/><citedRange from='\g<pages>'/></bibl>", string)
 
     for year_citation in year_citations:
         citations.append(year_citation[2])
@@ -179,23 +185,27 @@ def parse_cited_range(list_of_xml_elements):
         cited_range = reference.find("t:citedRange", namespaces=NS_MAP)
         from_value = (cited_range.get("from"))
 
-        split_values = re.findall(r"[\w']+", from_value)
-        if len(from_value) == 0:
-            cited_range.tag = "tagtobestripped"
-            cited_range.attrib.pop("from")
-        elif len(split_values) == 1:
-            cited_range.set("from", split_values[0])
-        elif len(split_values) == 2:
-            cited_range.set("from", split_values[0])
-            cited_range.set("to", split_values[1])
-        elif len(split_values) == 3:
-            cited_range.set("from", split_values[0])
-            cited_range.set("to", split_values[2])
+        if from_value is None:
+            pass
         else:
-            logging.info("Splitting the page range produced unexpected result. Tried to split %s. Wrote to text field." % from_value)
-            cited_range.text = from_value
-            cited_range.attrib.pop("from")
-            unsplittable_pageref.append(from_value)
+
+            split_values = re.findall(r"[\w']+", from_value)
+            if len(from_value) == 0:
+                cited_range.tag = "tagtobestripped"
+                cited_range.attrib.pop("from")
+            elif len(split_values) == 1:
+                cited_range.set("from", split_values[0])
+            elif len(split_values) == 2:
+                cited_range.set("from", split_values[0])
+                cited_range.set("to", split_values[1])
+            elif len(split_values) == 3:
+                cited_range.set("from", split_values[0])
+                cited_range.set("to", split_values[2])
+            else:
+                logging.info("Splitting the page range produced unexpected result. Tried to split %s. Wrote to text field." % from_value)
+                cited_range.text = from_value
+                cited_range.attrib.pop("from")
+                unsplittable_pageref.append(from_value)
 
     return unsplittable_pageref
 # def parse_cited_range ends here
@@ -551,9 +561,11 @@ def main():
     parser.add_argument("-d", "--dochighestorder", default='chapter', help="Specify which divider is at the highest level, possible values: part, chapter. Default is chapter.")
     parser.add_argument("-p", "--bibtexparserlog", help="Display logging output of bibtexparser", action="store_true")
     parser.add_argument("-f", "--finalize", help="Finalize a publication.", action="store_true")
+    parser.add_argument("-t", "--citedrangetext", help="Do not try to parse cited range values.", action="store_true")
     parser.add_argument("-b", "--bibtype", help="Specify the type of bibliography, possible values: anthology, monograph.", default="monograph")
     parser.add_argument("-c", "--chapter", help="Treat the TEI as one chapter, discards header.", action="store_true")
     parser.add_argument("-a", "--addbibliography", help="Add a section with bibliography PI.", action="store_true")
+    parser.add_argument("-l", "--printlog", help="Write logfile to stdout instead of writing to file.", action="store_true")
     parser.add_argument("teifile", help="Output from oxgarage/metypeset, an TEI XML file.")
     parser.add_argument("bibfile", help="The bibliography database of the publication.")
     parser.add_argument("figdir", help="The directory that contains the figures belonging to the publication.")