Tools voor het converteren van LaTeX naar Markdown

# Ubuntu/Debian
sudo apt-get install pandoc

# macOS
brew install pandoc

# Windows
choco install pandoc

# Of download vanaf https://pandoc.org/installing.html

# Eenvoudige conversie
pandoc document.tex -o document.md

# Met specifieke uitvoerformaat
pandoc document.tex -f latex -t markdown -o document.md

# Wiskunde behouden
pandoc document.tex -t markdown+tex_math_dollars -o document.md

# Conversie met bibliografie
pandoc document.tex --bibliography=refs.bib --citeproc -o document.md

# Inbedde afbeeldingen extraheren
pandoc document.tex --extract-media=./media -o document.md

# Eigenaar document met metadata
pandoc document.tex -s --wrap=none -o document.md

# Aangepaste sjabloon
pandoc document.tex --template=custom.md -o document.md

# Installatie
sudo apt-get install latexml

# Basisconversie
latexml document.tex | latexmlpost --dest=document.html -

# Met wiskunde als MathML
latexmlc document.tex --dest=document.html --mathimages=false

pip install latex2markdown

# Opdrachtregelgebruik
python -m latex2markdown document.tex document.md

#!/usr/bin/env python3
from pandocfilters import toJSONFilter, Str

def custom_transform(key, value, format, meta):
    if key == 'Str':
        # Transformeer specifieke teksten of patronen
        if value.startswith('\\customcommand'):
            return Str(value.replace('\\customcommand', 'Custom: '))

if __name__ == "__main__":
    toJSONFilter(custom_transform)

pandoc document.tex --filter=./custom_filter.py -o document.md

# Maak back-up
cp -r latex_project/ latex_project_backup/
git commit -am "Voor-conversie back-up"

# Extraheer alle aangepaste opdrachten
grep -E '\\newcommand|\\def|\\newenvironment' *.tex > custom_commands.txt

% Vervang of verwijder
% \usepackage{tikz}
% \usepackage{custom_package}

# Uitgebreide conversieopdracht
pandoc main.tex \
  --from=latex \
  --to=markdown+pipe_tables+backtick_code_blocks+fenced_code_attributes \
  --wrap=none \
  --extract-media=./assets \
  --standalone \
  --bibliography=references.bib \
  --citeproc \
  --output=output.md

# Script om tabellen op te schonen
sed -i 's/|:--|:--|/|:---|:---|/g' output.md

# Controleer citeertekstformaat
grep -E '\[@\w+\]|\@\w+' output.md

# Werk relatieve paden bij
sed -i 's|!\[\](assets/|![](../assets/|g' output.md

# Controleer inline wiskunde
grep -E '\$[^$]+\$' output.md

# Controleer display wiskunde
grep -E '\$\$[^$]+\$\$' output.md

#!/usr/bin/env python3
import re
import sys

def validate_markdown(filename):
    with open(filename, 'r') as f:
        content = f.read()
    
    issues = []
    
    # Controleer ongeconverteerde LaTeX-opdrachten
    latex_commands = re.findall(r'\\[a-zA-Z]+\{', content)
    if latex_commands:
        issues.append(f"Ongewijzigde LaTeX-opdrachten: {set(latex_commands)}")
    
    # Controleer gebroken links
    links = re.findall(r'\[([^\]]+)\]\(([^\)]+)\)', content)
    for text, url in links:
        if url.startswith('file://'):
            issues.append(f"Bestandsprotocol link: {url}")
    
    # Controleer wiskundescheidingstekens
    single_dollars = re.findall(r'(?<!\$)\$(?!\$)[^$]+\$(?!\$)', content)
    if len(single_dollars) % 2 != 0:
        issues.append("Niet overeenkomende inline wiskundescheidingstekens")
    
    return issues

if __name__ == "__main__":
    issues = validate_markdown(sys.argv[1])
    if issues:
        print("Validatieproblemen gevonden:")
        for issue in issues:
            print(f"  - {issue}")
        sys.exit(1)
    else:
        print("Validatie geslaagd!")
        sys.exit(0)

# Behoud LaTeX-wiskunde precies zoals het is
pandoc document.tex -t markdown+raw_tex -o output.md

pandoc document.tex -t markdown_strict+tex_math_dollars+raw_tex -o output.md

# Converteer .bib naar YAML voor Pandoc
pandoc-citeproc --bib2yaml refs.bib > refs.yaml

# Gebruik bij conversie
pandoc document.tex --metadata bibliography=refs.yaml --citeproc -o output.md

# Probeer verschillende tabelstijlen
pandoc document.tex -t markdown+pipe_tables -o output1.md
pandoc document.tex -t markdown+grid_tables -o output2.md

# Extraheer alle media naar georganiseerde map
pandoc document.tex --extract-media=./figures -o output.md

# Verwerk met relatieve paden
pandoc document.tex --resource-path=.:./figures --extract-media=./assets/img -o output.md

#!/usr/bin/env python3
import re
import sys

def expand_custom_commands(content):
    # Definieer aangepaste opdrachtkaarten
    commands = {
        r'\\customemph\{([^}]+)\}': r'***\1***',
        r'\\customsection\{([^}]+)\}': r'\n## \1\n',
        r'\\code\{([^}]+)\}': r'`\1`',
    }
    
    for pattern, replacement in commands.items():
        content = re.sub(pattern, replacement, content)
    
    return content

if __name__ == "__main__":
    with open(sys.argv[1], 'r') as f:
        content = f.read()
    
    expanded = expand_custom_commands(content)
    
    with open(sys.argv[2], 'w') as f:
        f.write(expanded)

# Voorverwerken, dan converteren
python expand_commands.py document.tex document_expanded.tex
pandoc document_expanded.tex -o document.md

#!/bin/bash
# convert_all.sh - Converteer alle .tex-bestanden in map naar Markdown

INPUT_DIR="${1:-.}"
OUTPUT_DIR="${2:-./markdown_output}"

mkdir -p "$OUTPUT_DIR"

find "$INPUT_DIR" -name "*.tex" | while read -r tex_file; do
    base_name=$(basename "$tex_file" .tex)
    output_file="$OUTPUT_DIR/${base_name}.md"
    
    echo "Converteer: $tex_file -> $output_file"
    
    pandoc "$tex_file" \
        --from=latex \
        --to=markdown \
        --wrap=none \
        --extract-media="$OUTPUT_DIR/media" \
        --standalone \
        --output="$output_file"
    
    if [ $? -eq 0 ]; then
        echo "✓ Succesvol geconverteerd $base_name"
    else
        echo "✗ Fout bij converteren $base_name"
    fi
done

echo "Batchconversie voltooid!"

#!/usr/bin/env python3
import os
import subprocess
from pathlib import Path

def batch_convert(input_dir, output_dir, extensions=['.tex']):
    """Converteer alle LaTeX-bestanden in mapstructuur naar Markdown."""
    
    input_path = Path(input_dir)
    output_path = Path(output_dir)
    output_path.mkdir(parents=True, exist_ok=True)
    
    for ext in extensions:
        for tex_file in input_path.rglob(f'*{ext}'):
            # Bewaar mapstructuur
            relative_path = tex_file.relative_to(input_path)
            output_file = output_path / relative_path.with_suffix('.md')
            output_file.parent.mkdir(parents=True, exist_ok=True)
            
            print(f"Converteer: {tex_file}")
            
            cmd = [
                'pandoc',
                str(tex_file),
                '--from=latex',
                '--to=markdown',
                '--wrap=none',
                f'--extract-media={output_file.parent}/media',
                '--standalone',
                f'--output={output_file}'
            ]
            
            try:
                subprocess.run(cmd, check=True, capture_output=True, text=True)
                print(f"✓ Succes: {output_file}")
            except subprocess.CalledProcessError as e:
                print(f"✗ Fout: {tex_file}")
                print(f"  {e.stderr}")

if __name__ == "__main__":
    import sys
    input_dir = sys.argv[1] if len(sys.argv) > 1 else '.'
    output_dir = sys.argv[2] if len(sys.argv) > 2 else './markdown'
    
    batch_convert(input_dir, output_dir)

#!/bin/bash
# .git/hooks/pre-commit

# Vind alle gewijzigde .tex-bestanden
changed_tex=$(git diff --cached --name-only --diff-filter=ACM | grep '\.tex$')

if [ -n "$changed_tex" ]; then
    echo "Converteer gewijzigde LaTeX-bestanden..."
    
    for tex_file in $changed_tex; do
        md_file="${tex_file%.tex}.md"
        pandoc "$tex_file" -o "$md_file"
        git add "$md_file"
        echo "Geconverteerd en toegevoegd: $md_file"
    done
fi

# Makefile voor LaTeX naar Markdown conversie

SRC_DIR := latex_src
OUT_DIR := markdown_out
TEX_FILES := $(wildcard $(SRC_DIR)/*.tex)
MD_FILES := $(patsubst $(SRC_DIR)/%.tex,$(OUT_DIR)/%.md,$(TEX_FILES))

.PHONY: all clean validate

all: $(MD_FILES)

$(OUT_DIR)/%.md: $(SRC_DIR)/%.tex
	@mkdir -p $(OUT_DIR)
	pandoc $< \
		--from=latex \
		--to=markdown \
		--wrap=none \
		--extract-media=$(OUT_DIR)/media \
		--standalone \
		--output=$@
	@echo "Geconverteerd: $< -> $@"

clean:
	rm -rf $(OUT_DIR)

validate: $(MD_FILES)
	@for md in $(MD_FILES); do \
		echo "Valideren $$md..."; \
		python validate_markdown.py $$md; \
	done

#!/bin/bash
# Converteer LaTeX artikel naar Hugo post

INPUT_TEX="$1"
OUTPUT_DIR="content/posts"
POST_NAME=$(basename "$INPUT_TEX" .tex)

# Converteer
pandoc "$INPUT_TEX" \
    --to=markdown \
    --wrap=none \
    --extract-media="static/img/$POST_NAME" \
    --output="temp_$POST_NAME.md"

# Voeg Hugo front matter toe
cat > "$OUTPUT_DIR/$POST_NAME.md" << EOF
---
title: "$(grep '\\title' "$INPUT_TEX" | sed 's/\\title{\(.*\)}/\1/')"
date: $(date +%Y-%m-%dT%H:%M:%S%z)
draft: false
math: true
---

EOF

# Voeg geconverteerde inhoud toe
cat "temp_$POST_NAME.md" >> "$OUTPUT_DIR/$POST_NAME.md"

# Fix afbeeldingspaden
sed -i "s|media/|/img/$POST_NAME/|g" "$OUTPUT_DIR/$POST_NAME.md"

# Cleanup
rm "temp_$POST_NAME.md"

echo "Hugo post gemaakt: $OUTPUT_DIR/$POST_NAME.md"

#!/bin/bash
# Converteer naar Jekyll post

INPUT_TEX="$1"
POST_DATE=$(date +%Y-%m-%d)
POST_NAME=$(basename "$INPUT_TEX" .tex)
OUTPUT_FILE="_posts/$POST_DATE-$POST_NAME.md"

pandoc "$INPUT_TEX" \
    --to=markdown_strict \
    --extract-media="assets/img" \
    --template=jekyll_template.md \
    --output="$OUTPUT_FILE"

echo "Jekyll post gemaakt: $OUTPUT_FILE"

git init latex-to-markdown-project
git add latex_src/ markdown_out/
git commit -m "Initiële LaTeX-bronnen en Markdown-conversie"

# Conversie Notities

## Aangepaste Opdrachten Kaart
- `\customemph{text}` → `***text***`
- `\code{text}` → `` `text` ``

## Bekende Problemen
- Complexe TikZ-diagrammen worden omgezet in tijdelijke bestanden
- Sommige tabeluitlijningen vereisen handmatige aanpassing

## Post-verwerkingstappen
1. Voer `fix_tables.py` uit
2. Valideer met `validate_markdown.py`
3. Controleer wiskunde-afbeelding met voorvertoning

# Converteer hoofdstuk voor hoofdstuk
pandoc chapter1.tex -o chapter1.md
# Bekijk en corrigeer problemen
pandoc chapter2.tex -o chapter2.md
# Bekijk en corrigeer problemen
# etc.

-- custom_filter.lua
function Math(el)
  if el.mathtype == "InlineMath" then
    return pandoc.RawInline('markdown', '$' .. el.text .. '$')
  else
    return pandoc.RawBlock('markdown', '$$' .. el.text .. '$$')
  end
end

function Image(el)
  -- Voeg aangepaste klassen of attributen toe
  el.classes = {'responsive-image'}
  return el
end

pandoc document.tex --lua-filter=custom_filter.lua -o output.md

# Toestaan van ruwe LaTeX in Markdown voor complexe gevallen
pandoc document.tex -t markdown+raw_tex -o output.md

#!/usr/bin/env python3
# test_conversion.py
import subprocess
import difflib

def test_conversion():
    """Test dat conversie de verwachte uitvoer produceert."""
    
    # Converteer testbestand
    subprocess.run([
        'pandoc', 'test_input.tex',
        '-o', 'test_output.md'
    ], check=True)
    
    # Vergelijk met verwachte uitvoer
    with open('test_output.md', 'r') as f:
        actual = f.readlines()
    
    with open('expected_output.md', 'r') as f:
        expected = f.readlines()
    
    diff = list(difflib.unified_diff(expected, actual, lineterm=''))
    
    if diff:
        print("Conversie-uitvoer verschilt van verwacht:")
        print('\n'.join(diff))
        return False
    else:
        print("✓ Conversietest geslaagd")
        return True

if __name__ == "__main__":
    import sys
    sys.exit(0 if test_conversion() else 1)

# Genereer PDF van LaTeX
pdflatex document.tex

# Genereer PDF van geconverteerde Markdown via Pandoc
pandoc output.md -o output_from_markdown.pdf

# Visueel vergelijk beide PDF's

#!/usr/bin/env python3
import re
import os
from pathlib import Path

def check_links(md_file):
    """Controleer dat alle links in Markdown geldig zijn."""
    
    with open(md_file, 'r') as f:
        content = f.read()
    
    # Extraheer alle links
    links = re.findall(r'\[([^\]]+)\]\(([^\)]+)\)', content)
    
    broken_links = []
    for text, url in links:
        if not url.startswith(('http://', 'https://', '#')):
            # Controleer of bestand bestaat
            link_path = Path(md_file).parent / url
            if not link_path.exists():
                broken_links.append((text, url))
    
    return broken_links

if __name__ == "__main__":
    import sys
    broken = check_links(sys.argv[1])
    
    if broken:
        print("Gebroken links gevonden:")
        for text, url in broken:
            print(f"  [{text}]({url})")
        sys.exit(1)
    else:
        print("✓ Alle links geldig")
        sys.exit(0)

#!/usr/bin/env python3
from multiprocessing import Pool
import subprocess
from pathlib import Path

def convert_file(tex_file):
    """Converteer enkel bestand."""
    output_file = tex_file.with_suffix('.md')
    subprocess.run([
        'pandoc', str(tex_file),
        '-o', str(output_file)
    ], check=True)
    return str(output_file)

def parallel_convert(input_dir, num_processes=4):
    """Converteer bestanden parallel."""
    tex_files = list(Path(input_dir).rglob('*.tex'))
    
    with Pool(num_processes) as pool:
        results = pool.map(convert_file, tex_files)
    
    return results

if __name__ == "__main__":
    import sys
    converted = parallel_convert(sys.argv[1])
    print(f"Geconverteerd {len(converted)} bestanden")

#!/usr/bin/env python3
import hashlib
import subprocess
from pathlib import Path
import pickle

CACHE_FILE = '.conversion_cache.pkl'

def file_hash(filepath):
    """Bereken bestandshash."""
    with open(filepath, 'rb') as f:
        return hashlib.md5(f.read()).hexdigest()

def cached_convert(tex_file, cache):
    """Converteer alleen als bestand veranderd is."""
    current_hash = file_hash(tex_file)
    
    if tex_file in cache and cache[tex_file] == current_hash:
        print(f"Overslaan {tex_file} (ongewijzigd)")
        return
    
    # Converteer bestand
    output_file = tex_file.with_suffix('.md')
    subprocess.run([
        'pandoc', str(tex_file),
        '-o', str(output_file)
    ], check=True)
    
    # Update cache
    cache[tex_file] = current_hash
    print(f"Geconverteerd {tex_file}")

def main():
    # Laad cache
    try:
        with open(CACHE_FILE, 'rb') as f:
            cache = pickle.load(f)
    except FileNotFoundError:
        cache = {}
    
    # Verwerk bestanden
    for tex_file in Path('.').rglob('*.tex'):
        cached_convert(tex_file, cache)
    
    # Sla cache op
    with open(CACHE_FILE, 'wb') as f:
        pickle.dump(cache, f)

if __name__ == "__main__":
    main()