minor ebook and html adjustments

entorb · Mar 27, 2024 · 68c6922 · 68c6922
1 parent 405e4eb
commit 68c6922
Show file tree

Hide file tree

Showing 2 changed files with 60 additions and 14 deletions.
diff --git a/scripts/ebook/3.py b/scripts/ebook/3.py
@@ -3,6 +3,7 @@
 """
 Modify flattened .tex file.
 """
+
 import datetime as dt
 import os
 import re
@@ -70,15 +71,46 @@
     cont,
 )
 
+# OMakeIV sections
+# not used in DE version
+
 # \censor
+cont = re.sub(r"\\censor\{.*?\}", r"xxxxxx", cont)
+
+
+# # remove Deathly_Hallows_Sign.pdf and other pdf images
+# # \includegraphics[scale=0.125]{images/Deathly_Hallows_Sign.pdf}
+# cont = re.sub(
+#     # r"\\includegraphics.*?\{images/Deathly_Hallows_Sign.*?\}",
+#     r"\\includegraphics.*?\.pdf\}",
+#     "",
+#     cont,
+# )
+
+# remove all images
 cont = re.sub(
-    r"\\censor\{.*?\}",
-    r"xxxxxx",
+    r"\\includegraphics\[.*?\]\{.*?\}",
+    "",
     cont,
+    flags=re.DOTALL,
 )
 
-# for spellcheck doc version -> not working, make_ebook-sh runs forever...
-# cont = re.sub(r"\\spell\{.*?\}+", "spell", cont)
+# remove empty envs
+cont = re.sub(
+    r"\\begin\{([^\}]*)\}\s*\\end\{\1}",
+    "",
+    cont,
+    flags=re.DOTALL,
+)
+
+# remove end stuff
+cont = re.sub(
+    r"(.*)\\end\{chapterOpeningAuthorNote\}.*?\\end\{document\}",
+    r"\1\\end{chapterOpeningAuthorNote}\n\\end{document}",
+    cont,
+    flags=re.DOTALL,
+    count=1,
+)
 
 with open(target_file, mode="w", encoding="utf-8", newline="\n") as fhOut:
     fhOut.write(cont)
diff --git a/scripts/ebook/6.py b/scripts/ebook/6.py
@@ -3,6 +3,7 @@
 """
 HTML modifications.
 """
+
 import os
 import re
 import sys
@@ -18,22 +19,13 @@
 with open(source_file, encoding="utf-8", newline="\n") as fhIn:
     cont = fhIn.read()
 
-# done via pandoc paramter -V lang=de in 5.sh
-# # set html lang to de
-# cont = re.sub(
-#     r'(<html .*?) lang="")',
-#     r'\1 lang="de"',
-#     cont,
-#     flags=re.IGNORECASE,
-#     count=1,
-# )
-
 # remove strange leftovers from tex -> html conversion
 cont = re.sub(
     r"(</header>).*?(<p>Fanfiction von)",
     r"\1\n\2",
     cont,
     flags=re.DOTALL | re.IGNORECASE,
+    count=1,
 )
 
 # remove duplication of author name
@@ -45,6 +37,28 @@
     count=1,
 )
 
+# now done via pandoc -V lang=de in 5.sh
+# # set language
+# cont = re.sub(
+#     r'(<html [^>]*) lang="" xml:lang=""',
+#     r'\1 lang="de" xml:lang="de"',
+#     cont,
+#     count=1,
+# )
+
+# remove training slashes to satisfy https://validator.w3.org
+cont = cont.replace("<br />", "<br>")
+cont = cont.replace("<hr />", "<hr>")
+
+cont = re.sub(
+    r"(<meta [^>]*) />",
+    r"\1>",
+    cont,
+)
+
+# remove bad span ids (containing spaces) from newspaper spans
+cont = re.sub(r'<span id="[^"]+" label="[^"]+">', r"<span>", cont, count=5)
+
 # doc structure (not needed any more, using calibi --level1-toc flag instead)
 # sed -i 's/<h1 /<h1 class="part"/g' $target_file
 # sed -i 's/<h2 /<h2 class="chapter"/g' $target_file