Move common functions for hyperlink formatting to library

src/imxml2django.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8; mode: python -*-
-# Time-stamp: <2019-12-17 16:35:51 (kthoden)>
+# Time-stamp: <2019-12-18 10:27:58 (kthoden)>
 
 """
 Create an XML file that can be inserted into the Django database
@@ -24,7 +24,6 @@
 import argparse
 import configparser
 import logging
-from datetime import datetime
 from copy import deepcopy
 from lxml import etree
 from pathlib import Path
@@ -1022,22 +1021,6 @@ def check_publication_cfg(configuration_file):
     return
 # def check_publication_cfg ends here
 
-def format_date(accessed_date, language):
-    """Format date string"""
-
-    parsed_date = datetime.strptime(accessed_date, "%Y-%m-%d")
-
-    if language == "en":
-        accessed_string = f"accessed {parsed_date:%B} {parsed_date.day}, {parsed_date:%Y}"
-    elif language == "de":
-        accessed_string = f"besucht am {parsed_date.day}.{parsed_date:%m}.{parsed_date:%Y}"
-    else:
-        logging.error("Got an unrecognized language: %s. Exiting.", language)
-        sys.exit(1)
-
-    return accessed_string
-# def format_date ends here
-
 
 # Iterate over Chapters, Sections, Subsections, and Subsubsections and
 # Put all on one level: EOAchapter
@@ -1439,23 +1422,7 @@ def bring_footnote_down_django(footnote, fragment, footnote_number, object_numbe
             del xmlEmph.attrib["rend"]
     xmlHyperlinks = xmlEOAchapter.findall(".//xref")
     for xmlHyperlink in xmlHyperlinks:
-        strURL = xmlHyperlink.get('url')
-        if strURL.startswith("http://") == False:
-            if strURL.startswith("https://") == False:
-                strURL = "http://" + strURL
-        xmlHyperlink.tag = "a"
-        del xmlHyperlink.attrib["url"]
-        xmlHyperlink.set("href", strURL)
-        etree.strip_elements(xmlHyperlink, with_tail=True, *['allowbreak'])
-        accessed_date_element = xmlHyperlink.find("./date")
-        accessed_date = accessed_date_element.get("when")
-        formatted_date = format_date(accessed_date, libeoaconvert.two_letter_language(strLanguage))
-        # etree.strip_elements(accessed_date_element, with_tail=True)
-        accessed_date_element.tag = "elementtobestripped"
-        accessed_date_element.tail = ""
-        url_tail = xmlHyperlink.tail
-        xmlHyperlink.tail = f", {formatted_date}{url_tail}"
-        xmlHyperlink.text = strURL
+        libeoaconvert.format_hyperlinks_django_epub(xmlHyperlink, strLanguage)
     # Convert bold text
     xmlBolds = xmlEOAchapter.findall(".//EOAbold")
     for xmlBold in xmlBolds:

src/imxml2epub.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8; mode: python -*-
-# Time-stamp: <2019-12-18 09:44:30 (kthoden)>
+# Time-stamp: <2019-12-18 10:13:44 (kthoden)>
 
 """ Convert a customized DocBook XML file into a set of files that
 constitute the contents of an EPUB file.
@@ -1204,17 +1204,16 @@ class FootnoteError(Exception):
 
 logging.info(f"{logseparator}Preparing Hyperlinks")
 for xmlChapter in xmlChapters:
+    xmlLanguage = xmlChapter.get("language")
+    if xmlLanguage is not None:
+        # KT changing this after separating the big script
+        strLanguage = xmlLanguage #or "english"
+    else:
+        strLanguage = "english"
+
     xmlHyperlinks = xmlChapter.findall(".//xref")
     for xmlHyperlink in xmlHyperlinks:
-        strURL = xmlHyperlink.get('url')
-        if strURL.startswith("http://") == False:
-            if strURL.startswith("https://") == False:
-                strURL = "http://" + strURL
-        xmlHyperlink.tag = "a"
-        del xmlHyperlink.attrib["url"]
-        xmlHyperlink.set("href", strURL)
-        etree.strip_elements(xmlHyperlink, with_tail=True, *['allowbreak'])
-        xmlHyperlink.text = strURL
+        libeoaconvert.format_hyperlinks_django_epub(xmlHyperlink, strLanguage)
 
 logging.info(f"{logseparator}Convert emphasized text")
 for xmlChapter in xmlChapters:

src/utils/libeoaconvert.py

@@ -11,6 +11,7 @@
 import shlex
 import logging
 import configparser
+from datetime import datetime
 from lxml import etree
 from lxml.html import soupparser
 from pathlib import Path
@@ -484,3 +485,49 @@ def escape_xml(text_bytes):
 
     return text
 # def escape_xml ends here
+
+
+def format_hyperlinks_django_epub(xmlHyperlink, strLanguage):
+    """Convert IMXML element to href and append localized accessed date"""
+
+    strURL = xmlHyperlink.get('url')
+    if strURL.startswith("http://") == False:
+        if strURL.startswith("https://") == False:
+            strURL = "http://" + strURL
+    xmlHyperlink.tag = "a"
+    del xmlHyperlink.attrib["url"]
+    xmlHyperlink.set("href", strURL)
+    etree.strip_elements(xmlHyperlink, with_tail=True, *['allowbreak'])
+    accessed_date_element = xmlHyperlink.find("./date")
+    if accessed_date_element is not None:
+        accessed_date = accessed_date_element.get("when")
+        formatted_date = format_date(accessed_date, two_letter_language(strLanguage))
+        # etree.strip_elements(accessed_date_element, with_tail=True)
+        accessed_date_element.tag = "elementtobestripped"
+        accessed_date_element.tail = ""
+        url_tail = xmlHyperlink.tail
+        xmlHyperlink.tail = f", {formatted_date}{url_tail}"
+        xmlHyperlink.text = strURL
+    else:
+        logging.error(f"Found no accessed date at url {strURL}. Exiting.")
+        sys.exit()
+
+    return
+# def format_hyperlinks_django_epub ends here
+
+
+def format_date(accessed_date, language):
+    """Format date string"""
+
+    parsed_date = datetime.strptime(accessed_date, "%Y-%m-%d")
+
+    if language == "en":
+        accessed_string = f"accessed {parsed_date:%B} {parsed_date.day}, {parsed_date:%Y}"
+    elif language == "de":
+        accessed_string = f"besucht am {parsed_date:%d}.{parsed_date:%m}.{parsed_date:%Y}"
+    else:
+        logging.error("Got an unrecognized language: %s. Exiting.", language)
+        sys.exit(1)
+
+    return accessed_string
+# def format_date ends here