pdf_signature_extraction/paper/build_docx.sh

#!/bin/bash
# Build complete Paper A Word document from section markdown files
# Uses pandoc with embedded figures

PAPER_DIR="/Volumes/NV2/pdf_recognize/paper"
FIG_DIR="/Volumes/NV2/PDF-Processing/signature-analysis/paper_figures"
OUTPUT="$PAPER_DIR/Paper_A_IEEE_TAI_Draft_v2.docx"

# Create combined markdown with title page
cat > "$PAPER_DIR/_combined.md" << 'TITLEEOF'
---
title: "Automated Detection of Digitally Replicated Signatures in Large-Scale Financial Audit Reports"
author: "[Authors removed for double-blind review]"
date: ""
geometry: margin=1in
fontsize: 11pt
---

TITLEEOF

# Append each section (strip the # heading line if it duplicates)
for section in \
    paper_a_abstract.md \
    paper_a_impact_statement.md \
    paper_a_introduction.md \
    paper_a_related_work.md \
    paper_a_methodology.md \
    paper_a_results.md \
    paper_a_discussion.md \
    paper_a_conclusion.md \
    paper_a_references.md
do
    echo "" >> "$PAPER_DIR/_combined.md"
    # Strip HTML comments and append
    sed '/^<!--/,/-->$/d' "$PAPER_DIR/$section" >> "$PAPER_DIR/_combined.md"
    echo "" >> "$PAPER_DIR/_combined.md"
done

# Insert figure references as actual images
# Fig 1 after "Fig. 1 illustrates"
sed -i '' "s|Fig. 1 illustrates the overall architecture.|Fig. 1 illustrates the overall architecture.\n\n![Fig. 1. Pipeline architecture for automated signature replication detection.]($FIG_DIR/fig1_pipeline.png){width=100%}\n|" "$PAPER_DIR/_combined.md"

# Fig 2 after "Fig. 2 presents the cosine"
sed -i '' "s|Fig. 2 presents the cosine similarity distributions|Fig. 2 presents the cosine similarity distributions|" "$PAPER_DIR/_combined.md"
sed -i '' "/^Fig. 2 presents the cosine/a\\
\\
![Fig. 2. Cosine similarity distributions: intra-class vs. inter-class. KDE crossover at 0.837.]($FIG_DIR/fig2_intra_inter_kde.png){width=60%}\\
" "$PAPER_DIR/_combined.md"

# Fig 3 after "Fig. 3 presents"
sed -i '' "/^Fig. 3 presents/a\\
\\
![Fig. 3. Per-signature best-match cosine similarity: Firm A vs. other CPAs.]($FIG_DIR/fig3_firm_a_calibration.png){width=60%}\\
" "$PAPER_DIR/_combined.md"

# Fig 4 after "we compared three pre-trained"
sed -i '' "/^To validate the choice of ResNet-50.*we conducted/a\\
\\
![Fig. 4. Ablation study: backbone comparison.]($FIG_DIR/fig4_ablation.png){width=100%}\\
" "$PAPER_DIR/_combined.md"

# Build with pandoc
pandoc "$PAPER_DIR/_combined.md" \
    -o "$OUTPUT" \
    --reference-doc=/dev/null \
    -f markdown \
    --wrap=none \
    2>&1

# If reference-doc fails, try without it
if [ $? -ne 0 ]; then
    pandoc "$PAPER_DIR/_combined.md" \
        -o "$OUTPUT" \
        -f markdown \
        --wrap=none \
        2>&1
fi

# Clean up
rm -f "$PAPER_DIR/_combined.md"

echo "Output: $OUTPUT"
ls -lh "$OUTPUT"