refactor(docker, utils): streamline Dockerfile and update PDF build script

This change removes unnecessary dependencies and optimizes the PDF build
process, enhancing maintainability and reducing potential errors.

- Removed `python3-pypandoc` from Dockerfile to minimize dependency
  footprint.
- Replaced `texlive-xetex` with `texlive` in Dockerfile for broader TeX
  support.
- Introduced `subprocess` in `build_pdf.py` to replace `pypandoc`,
  improving process control.
- Added `run_process_with_params` function to handle command execution,
  increasing code modularity and error handling.
- Created `build_pdf.old.py` as a backup of the original script for
  reference.

Signed-off-by: Glenn Y. Rolland <glenux@glenux.net>

docker/Dockerfile

@@ -5,7 +5,7 @@ ENV DOCMACHINE_DOCS_ENABLE=1
 ENV DOCMACHINE_SLIDES_ENABLE=1
 
 RUN apt-get update \
- && apt-get install -y --no-install-recommends python3 python3-pip python-is-python3 pipenv python3-pypandoc \
+ && apt-get install -y --no-install-recommends python3 python3-pip python-is-python3 pipenv \
  && apt-get clean \
  && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
  && truncate -s 0 /var/log/*log
@@ -19,7 +19,7 @@ RUN apt-get update \
 
 # Tools for building pdfs
 RUN apt-get update \
- && apt-get install -y --no-install-recommends make m4 chromium pandoc ghc libghc-pandoc-dev lmodern texlive-xetex texlive-fonts-extra texlive-fonts-recommended librsvg2-bin fonts-noto-mono \
+ && apt-get install -y --no-install-recommends make m4 chromium pandoc ghc libghc-pandoc-dev lmodern texlive texlive-xetex texlive-fonts-extra texlive-fonts-recommended librsvg2-bin fonts-noto-mono \
  && apt-get clean \
  && rm -rf /var/lib/apt/lists/* /tmp/* /var/tmp/* \
  && truncate -s 0 /var/log/*log

utils/docs/build_pdf.old.py

@@ -0,0 +1,71 @@
+#!/usr/bin/env python
+
+# Usage: ./build.py INPUT_DIR OUTPUT_FILE
+
+import os
+# import re
+import sys
+import pypandoc
+
+
+def gx_usage():
+    """Show usage"""
+    print(f"Usage: {sys.argv[0]} METADATA_FILE INPUT_FILE OUTPUT_FILE")
+    print()
+
+
+if len(sys.argv) != 4:
+    gx_usage()
+
+metadata_file = sys.argv[1]
+if not os.path.exists(metadata_file):
+    print(f"Metadata file not found: {metadata_file}")
+    sys.exit(1)
+
+input_file = sys.argv[2]
+if not os.path.exists(input_file):
+    print(f"Input file not found: {input_file}")
+    sys.exit(1)
+
+# Get second
+output_file = sys.argv[3]
+if os.path.exists(output_file):
+    print(f"Output file already exists: {output_file}")
+    sys.exit(1)
+
+print(f"Metadata: {metadata_file}")
+print(f"Input: {input_file}")
+print(f"Output: {output_file}")
+
+# Build the pandoc options as a string
+pandoc_cmd = [
+    "--verbose",
+    "--toc",
+    "--number-sections",
+    "--include-in-header", "utils/docs/main.tex",
+    "--metadata-file", metadata_file,
+    # "-V", "linkcolor:blue",
+    # "-V", "geometry:a4paper",
+    # "-V", "geometry:margin=1.8cm",
+    "-V", "mainfont=DejaVu Serif",
+    "-V", "monofont=Noto Sans Mono",
+    "--pdf-engine=xelatex",
+    "--resource-path=utils/docs",
+    "--filter=./utils/docs/filter-nobg.hs",
+]
+
+# from glob import glob
+# input_files = [os.path.join(dp, f) for dp, dn, filenames in os.walk(input_dir) for f in filenames if re.search(r'^[0-9].*\.md$', f)]
+# input_files.sort()
+
+# Convert all markdown files in the chapters/ subdirectory.
+pypandoc.convert_file(
+    input_file,
+    "pdf",
+    outputfile=output_file,
+    extra_args=pandoc_cmd,
+)
+
+print(f"Conversion completed. Output saved to: {output_file}")
+
+#

utils/docs/build_pdf.py

@@ -2,11 +2,10 @@
 
 # Usage: ./build.py INPUT_DIR OUTPUT_FILE
 
-import os
 # import re
+import os
 import sys
-import pypandoc
-
+import subprocess
 
 def gx_usage():
     """Show usage"""
@@ -14,6 +13,31 @@ def gx_usage():
     print()
 
 
+def run_process_with_params(command_params):
+    """
+    Runs a process with parameters provided in the command_params list.
+
+    Args:
+    - command_params (list): List of parameters to run the process. 
+      The first item in the list should be the command (executable).
+    """
+    try:
+        # Run the process using subprocess.run (Python 3.5+)
+        result = subprocess.run(command_params, check=True, text=True, capture_output=True)
+        
+        # If the process ran successfully, print the output
+        print("Process output:", result.stdout)
+        print("Process error output (if any):", result.stderr)
+    except subprocess.CalledProcessError as e:
+        print(f"An error occurred while running the process: {e}")
+        print("Error Output:", e.stderr)
+    except Exception as e:
+        print(f"Unexpected error: {e}")
+
+# Example usage
+if __name__ == "__main__":
+    # Define the parameters for the command
+    # Example: Running `ls -l /home` on a Unix-like system
     if len(sys.argv) != 4:
         gx_usage()
 
@@ -33,12 +57,9 @@ if os.path.exists(output_file):
         print(f"Output file already exists: {output_file}")
         sys.exit(1)
 
-print(f"Metadata: {metadata_file}")
-print(f"Input: {input_file}")
-print(f"Output: {output_file}")
-
     # Build the pandoc options as a string
     pandoc_cmd = [
+        "pandoc",
         "--verbose",
         "--toc",
         "--number-sections",
@@ -52,20 +73,17 @@ pandoc_cmd = [
         "--pdf-engine=xelatex",
         "--resource-path=utils/docs",
         "--filter=./utils/docs/filter-nobg.hs",
+        "-f", "markdown",
+        "-t", "pdf",
+        "-o", output_file,
+        input_file
     ]
 
-# from glob import glob
-# input_files = [os.path.join(dp, f) for dp, dn, filenames in os.walk(input_dir) for f in filenames if re.search(r'^[0-9].*\.md$', f)]
-# input_files.sort()
+    print(f"Metadata: {metadata_file}")
+    print(f"Input: {input_file}")
+    print(f"Output: {output_file}")
 
-# Convert all markdown files in the chapters/ subdirectory.
-pypandoc.convert_file(
-    input_file,
-    "pdf",
-    outputfile=output_file,
-    extra_args=pandoc_cmd,
-)
-
-print(f"Conversion completed. Output saved to: {output_file}")
+    # Call the function to run the process
+    run_process_with_params(pandoc_cmd)
 
 #

utils/docs/main.tex

@@ -2,8 +2,25 @@
 
 % Set the document language to English
 \usepackage[english]{babel}
-% \usepackage[utf8]{inputenc}
+\usepackage{newunicodechar}
+
+% Define command \DeclareUnicodeCharacter (which was defined in inputenc for non-utf8 engines)
+\newcommand{\DeclareUnicodeCharacter}[2]{%
+    \begingroup\lccode`|=\string"#1\relax
+    	\lowercase{\endgroup\newunicodechar{|}}{#2}%
+}
+
+\def\bitcoinA{%
+  \leavevmode
+  \vtop{\offinterlineskip %\bfseries
+    \setbox0=\hbox{B}%
+    \setbox2=\hbox to\wd0{\hfil\hskip-.03em
+    \vrule height .3ex width .15ex\hskip .08em
+    \vrule height .3ex width .15ex\hfil}
+    \vbox{\copy2\box0}\box2}}
+
 % \DeclareUnicodeCharacter{21D2}{$\Rightarrow$}
+\DeclareUnicodeCharacter{20BF}{\bitcoinA}
 
 % Adjust page geometry
 \usepackage[