ebook: Check html syntax

Author: entorb

.github/workflows/check-and-ebook.yml

@@ -43,17 +43,20 @@ jobs:
           path: hash-chapters.txt
           key: chapter-hash-for-ebook-${{ github.ref_name }}-${{ steps.calculate-hash.outputs.hash }}
 
+      - name: Preparations
+        run: ln -s python-requirements.txt requirements.txt
+
       - name: Python set up
         uses: actions/setup-python@v5
         with:
           python-version: "3.12"
-          # no packages besides pytest installed, so no caching needed
-          # cache: "pip"
+          cache: "pip"
+
+      - name: Python packages
+        run: pip install -r python-requirements.txt
 
       - name: Run pytest unittests
-        run: |
-          pip install pytest
-          pytest
+        run: pytest
 
       - name: Check chapters for known issues
         run: python3 -O scripts/check_chapters.py
@@ -78,12 +81,17 @@ jobs:
           persist-credentials: false
           fetch-depth: 1 # 0 if you want to push to repo
 
+      - name: Preparations
+        run: ln -s python-requirements.txt requirements.txt
+
       - name: Python set up
         uses: actions/setup-python@v5
         with:
           python-version: "3.12"
-          # no packages installed, so no caching
-          # cache: "pip"
+          cache: "pip"
+
+      - name: Install Python packages
+        run: pip install -r python-requirements.txt
 
       #  - name: setup environment to DE lang
       #    run: |

Dockerfile

@@ -9,8 +9,9 @@ ENV TZ=Europe/Berlin
 # prevent keyboard input requests in apt install
 ENV DEBIAN_FRONTEND=noninteractive
 
+# install packages and cleanup afterwards
 RUN apt-get update && apt-get dist-upgrade -y && \
-    apt-get install -y python3 git texlive-xetex texlive-lang-greek texlive-lang-german latexmk texlive-extra-utils pandoc calibre imagemagick ghostscript && \
+    apt-get install -y python3 python3-lxml git texlive-xetex texlive-lang-greek texlive-lang-german latexmk texlive-extra-utils pandoc calibre imagemagick ghostscript && \
     apt-get clean autoclean && apt-get autoremove --yes && rm -rf /var/lib/{apt,dpkg,cache,log}/
 
 # set working directory

python-requirements.txt

@@ -0,0 +1,2 @@
+lxml
+pytest

scripts/ebook/step_6.py

@@ -10,6 +10,8 @@
 import sys
 from pathlib import Path
 
+from lxml import etree  # pip install lxml
+
 sys.path.append(str(Path(__file__).resolve().parent.parent))
 from check_chapters_settings import settings
 
@@ -19,6 +21,17 @@
 target_file = Path("hpmor.html")
 
 
+def check_html(cont: str) -> None:
+    """Check html syntax."""
+    parser = etree.XMLParser(recover=False)  # Do not auto-fix errors
+    try:
+        etree.fromstring(cont, parser)  # noqa: S320
+    except etree.XMLSyntaxError as e:
+        print("HTML Error:", e)
+        sys.exit(1)
+        # raise
+
+
 def fix_ellipsis(s: str) -> str:
     """
     Fix ellipsis spacing for ebooks.
@@ -41,6 +54,8 @@ def fix_ellipsis(s: str) -> str:
     s = re.sub(r"…(?=<em>)", "… ", s)
     # before opening EN-quotes: add space
     # s = re.sub(r"…(?=[“])", "… ", s)
+    # NO: before opening DE-quotes: add space
+    # s = re.sub(r"…(?=[„])", "… ", s)
     return s
 
 
@@ -49,6 +64,8 @@ def fix_ellipsis(s: str) -> str:
 
     with source_file.open(encoding="utf-8", newline="\n") as fh_in:
         cont = fh_in.read()
+    print("checking source html")
+    check_html(cont)
 
     # remove strange leftovers from tex -> html conversion
     cont = re.sub(
@@ -86,15 +103,6 @@ def fix_ellipsis(s: str) -> str:
     #     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,
-    )
-
     # fix spaces around ellipsis
     cont = fix_ellipsis(cont)
 
@@ -154,5 +162,17 @@ def fix_ellipsis(s: str) -> str:
         css = fh_in.read()
     cont = cont.replace("</style>\n", css + "\n</style>\n")
 
+    print("checking target html")
+    check_html(cont)
+
+    # 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,
+    )
+
     with target_file.open(mode="w", encoding="utf-8", newline="\n") as fh_out:
         fh_out.write(cont)

scripts/install_requirements_ebook.sh

@@ -1,6 +1,12 @@
 #!/bin/sh
 
+# ensure we are in the hpmor root dir
+script_dir=$(cd $(dirname $0) && pwd)
+cd $script_dir/..
+
 sudo apt-get install texlive-extra-utils pandoc calibre imagemagick ghostscript
 # pandoc calibre : for ebook converting
 # texlive-extra-utils : for latexpand
 # imagemagick ghostscript : for pdf title page to image conversion
+
+pip install -r python-requirements.txt

scripts/install_requirements_pdf.sh

@@ -1,3 +1,7 @@
 #!/bin/sh
 
+# ensure we are in the hpmor root dir
+script_dir=$(cd $(dirname $0) && pwd)
+cd $script_dir/..
+
 sudo apt-get install texlive-xetex texlive-lang-greek texlive-lang-german latexmk