Merge branch 'feature_ebooklinking' into dev

src/imxml2epub.py

@@ -1,6 +1,6 @@
 #!/usr/bin/env python3
 # -*- coding: utf-8; mode: python -*-
-# Time-stamp: <2021-11-15 21:09:52 (kthoden)>
+# Time-stamp: <2021-11-16 08:57:52 (kthoden)>
 
 """ Convert a customized DocBook XML file into a set of files that
 constitute the contents of an EPUB file.
@@ -863,6 +863,7 @@ def add_css_snippet(css_snippet, css_file):
     xmlFigure.clear()
     xmlFigure.tag = "p"
     xmlFigure.set("class", "centered_image")
+    xmlFigure.set("id", idFigure)
     xmlFigureImage = etree.Element("img")
     xmlFigureImage.set("src", "images/" + strImageFileDir + strImageFileNamewoSuffix + "." + extension_and_mime)
     xmlFigureImage.set("alt", "")
@@ -1770,6 +1771,12 @@ class FootnoteError(Exception):
 
 logging.info(f"{logseparator}Preparing Cross-References")
 
+libeoaconvert.debug_xml_here(
+        xmlEbookTree,
+        "epubtree_beforecrossreferences",
+        DEBUG_DIR
+)
+
 # restart chapter counter
 intChapterNumber = 1
 for xmlChapter in xmlChapters:
@@ -1800,9 +1807,43 @@ class FootnoteError(Exception):
 
         reference_type = xmlReference.get("type")
 
+        xmlReferenceLabel = xmlReference.find("Label")
+        xmlReferenceLabelText = xmlReferenceLabel.text
+
+        xmlReferenceRef = xmlReference.find("ref")
+        xmlReferenceRefTarget = xmlReferenceRef.get("target")
+
         if reference_type == "text":
             tmpTail = xmlReference.tail or ""
             ref_is_text = True
+
+            logging.debug(f"{xmlReferenceRefTarget} is a text link")
+            ref_is_text = True
+            xmlReferenceRef = xmlReference.find("ref")
+            xmlReferenceRefTarget = xmlReferenceRef.get("target")
+            xmlReferenceLabel = xmlReference.find("Label")
+            xmlReferenceLabelText = xmlReferenceLabel.text
+
+            pararef = xmlEbookTree.xpath("//*[@id='%s']" % xmlReferenceRefTarget)
+            logging.info(pararef[0].get("id"))
+            if len(pararef) == 0:
+                logging.warning("There seems to be no corresponding xml:id for %s." % xmlReferenceRefTarget)
+                failed_ids.append(f"{xmlReferenceRefTarget} ({xmlReferenceLabelText})\n")
+            elif len(pararef) > 1:
+                logging.error("The xml:id %s is assigned more than once. This is not allowed. Exiting." % xmlReferenceLabelText)
+                sys.exit(2)
+            else:
+                closest_ancestor_with_id = pararef[0].xpath("ancestor::*[starts-with(name(), 'div') and @id][1]")
+                closest_id = closest_ancestor_with_id[0].get("id")
+
+                for xmlParent in pararef[0].iterancestors():
+                    if xmlParent.tag == "EOAchapter":
+                        strChapterOrder = xmlParent.get("order")
+                for xmlParent in pararef[0].iterancestors():
+                    if xmlParent.tag == "EOAparagraph":
+                        strObjectOrder = xmlParent.get("order")
+
+
             all_children = list(xmlReference)
             text_has_children = all_children[:-2]
             if text_has_children:
@@ -1825,37 +1866,31 @@ class FootnoteError(Exception):
         elif reference_type == "number":
             strResult = "!!! Cross Reference !!!"
 
-            xmlReferenceLabel = xmlReference.find("Label")
-            xmlReferenceLabelText = xmlReferenceLabel.text
-
-            xmlReferenceRef = xmlReference.find("ref")
-            xmlReferenceRefTarget = xmlReferenceRef.get("target")
-
             if xmlReferenceLabelText in dictEquations:
                 logging.info("Found link to array:" + xmlReferenceLabelText)
                 strResult = dictEquations[xmlReferenceLabelText]
-            if xmlReferenceRefTarget in dictEquations:
+            elif xmlReferenceRefTarget in dictEquations:
                 logging.info("Found link to equation:" + xmlReferenceRefTarget)
                 strResult = dictEquations[xmlReferenceRefTarget]
-            if xmlReferenceRefTarget in dictLists:
+            elif xmlReferenceRefTarget in dictLists:
                 logging.info("Found link to list")
                 strResult = dictLists[xmlReferenceRefTarget]
-            if xmlReferenceRefTarget in dictChapters:
+            elif xmlReferenceRefTarget in dictChapters:
                 logging.info("Found link to chapter")
                 strResult = dictChapters[xmlReferenceRefTarget]
-            if xmlReferenceRefTarget in dictSections:
+            elif xmlReferenceRefTarget in dictSections:
                 logging.info("Found link to section")
                 strResult = dictSections[xmlReferenceRefTarget]
-            if xmlReferenceRefTarget in dictFigures:
+            elif xmlReferenceRefTarget in dictFigures:
                 logging.info("Found link to figure")
                 strResult = dictFigures[xmlReferenceRefTarget]
-            if xmlReferenceRefTarget in dictFootnotes:
+            elif xmlReferenceRefTarget in dictFootnotes:
                 logging.info("Found link to footnote")
                 strResult = dictFootnotes[xmlReferenceRefTarget]
-            if xmlReferenceRefTarget in dictTheorems:
+            elif xmlReferenceRefTarget in dictTheorems:
                 logging.info("Found link to theorem")
                 strResult = dictTheorems[xmlReferenceRefTarget]
-            if xmlReferenceRefTarget in dictTables:
+            elif xmlReferenceRefTarget in dictTables:
                 logging.info("Found link to table")
                 strResult = dictTables[xmlReferenceRefTarget]
             tmpTail = xmlReference.tail or ""
@@ -1864,6 +1899,7 @@ class FootnoteError(Exception):
             logging.error("Found unknown reference type: %s. Exiting", reference_type)
             sys.exit(0)
         xmlReference.clear()
+
         if args.hyperimage and hitarget_id and reference_type in ["collage", "number"]:
             hyperimage_link = f"{publication_landingpage[:-11]}/{intChapterNumber}/index.html#{hitarget_id}"
             xmlReference.tag = "a"