Update app.py

app.py

@@ -162,240 +162,7 @@ def markdown_to_pdf_content(markdown_text, render_with_bold, auto_bold_numbers,
     lines = markdown_text.strip().split('\n')
     pdf_content = []
     number_pattern = re.compile(r'^\d+\.\s')
-    heading_pattern = re.compile(r'^(#{1,4})\s+(.+)
-
-def create_pdf(markdown_text, base_font_size, render_with_bold, auto_bold_numbers, enlarge_numbered, num_columns, add_space_before_numbered, headings_to_fonts):
-    buffer = io.BytesIO()
-    page_width = A4[0] * 2
-    page_height = A4[1]
-    doc = SimpleDocTemplate(buffer, pagesize=(page_width, page_height), leftMargin=36, rightMargin=36, topMargin=36, bottomMargin=36)
-    styles = getSampleStyleSheet()
-    spacer_height = 10
-    pdf_content, total_lines = markdown_to_pdf_content(markdown_text, render_with_bold, auto_bold_numbers, add_space_before_numbered, headings_to_fonts)
-    try:
-        available_font_files = glob.glob("*.ttf")
-        if not available_font_files:
-            st.error("No .ttf font files found.")
-            return
-        selected_font_path = next((f for f in available_font_files if "NotoEmoji-Bold" in f), None)
-        if selected_font_path:
-            pdfmetrics.registerFont(TTFont("NotoEmoji-Bold", selected_font_path))
-        pdfmetrics.registerFont(TTFont("DejaVuSans", "DejaVuSans.ttf"))
-    except Exception as e:
-        st.error(f"Font registration error: {e}")
-        return
-    total_chars = sum(len(line) for line in pdf_content)
-    hierarchy_weight = sum(1.5 if line.startswith("<b>") else 1 for line in pdf_content)
-    content_density = total_lines * hierarchy_weight + total_chars / 50
-    usable_height = page_height - 72 - spacer_height
-    usable_width = page_width - 72
-    avg_line_chars = total_chars / total_lines if total_lines > 0 else 50
-    ideal_lines_per_col = 20
-    suggested_columns = max(1, min(6, int(total_lines / ideal_lines_per_col) + 1))
-    num_columns = num_columns if num_columns != 0 else suggested_columns
-    col_width = usable_width / num_columns
-    min_font_size = 6
-    max_font_size = 16
-    lines_per_col = total_lines / num_columns if num_columns > 0 else total_lines
-    target_height_per_line = usable_height / lines_per_col if lines_per_col > 0 else usable_height
-    estimated_font_size = int(target_height_per_line / 1.5)
-    adjusted_font_size = max(min_font_size, min(max_font_size, estimated_font_size))
-    if avg_line_chars > col_width / adjusted_font_size * 10:
-        adjusted_font_size = int(col_width / (avg_line_chars / 10))
-        adjusted_font_size = max(min_font_size, adjusted_font_size)
-    item_style = ParagraphStyle(
-        'ItemStyle', parent=styles['Normal'], fontName="DejaVuSans",
-        fontSize=adjusted_font_size, leading=adjusted_font_size * 1.15, spaceAfter=1,
-        linkUnderline=True
-    )
-    numbered_bold_style = ParagraphStyle(
-        'NumberedBoldStyle', parent=styles['Normal'], fontName="NotoEmoji-Bold",
-        fontSize=adjusted_font_size + 1 if enlarge_numbered else adjusted_font_size,
-        leading=(adjusted_font_size + 1) * 1.15 if enlarge_numbered else adjusted_font_size * 1.15, spaceAfter=1,
-        linkUnderline=True
-    )
-    section_style = ParagraphStyle(
-        'SectionStyle', parent=styles['Heading2'], fontName="DejaVuSans",
-        textColor=colors.darkblue, fontSize=adjusted_font_size * 1.1, leading=adjusted_font_size * 1.32, spaceAfter=2,
-        linkUnderline=True
-    )
-    columns = [[] for _ in range(num_columns)]
-    lines_per_column = total_lines / num_columns if num_columns > 0 else total_lines
-    current_line_count = 0
-    current_column = 0
-    number_pattern = re.compile(r'^\d+\.\s')
-    for item in pdf_content:
-        if current_line_count >= lines_per_column and current_column < num_columns - 1:
-            current_column += 1
-            current_line_count = 0
-        columns[current_column].append(item)
-        current_line_count += 1
-    column_cells = [[] for _ in range(num_columns)]
-    for col_idx, column in enumerate(columns):
-        for item in column:
-            if isinstance(item, str) and item.startswith("<b>") and item.endswith("</b>"):
-                content = item[3:-4].strip()
-                if number_pattern.match(content):
-                    column_cells[col_idx].append(Paragraph(apply_emoji_font(content, "NotoEmoji-Bold"), numbered_bold_style))
-                else:
-                    column_cells[col_idx].append(Paragraph(apply_emoji_font(content, "NotoEmoji-Bold"), section_style))
-            else:
-                column_cells[col_idx].append(Paragraph(apply_emoji_font(item, "DejaVuSans"), item_style))
-    max_cells = max(len(cells) for cells in column_cells) if column_cells else 0
-    for cells in column_cells:
-        cells.extend([Paragraph("", item_style)] * (max_cells - len(cells)))
-    table_data = list(zip(*column_cells)) if column_cells else [[]]
-    table = Table(table_data, colWidths=[col_width] * num_columns, hAlign='CENTER')
-    table.setStyle(TableStyle([
-        ('VALIGN', (0, 0), (-1, -1), 'TOP'),
-        ('ALIGN', (0, 0), (-1, -1), 'LEFT'),
-        ('BACKGROUND', (0, 0), (-1, -1), colors.white),
-        ('GRID', (0, 0), (-1, -1), 0, colors.white),
-        ('LINEAFTER', (0, 0), (num_columns-1, -1), 0.5, colors.grey),
-        ('LEFTPADDING', (0, 0), (-1, -1), 2),
-        ('RIGHTPADDING', (0, 0), (-1, -1), 2),
-        ('TOPPADDING', (0, 0), (-1, -1), 1),
-        ('BOTTOMPADDING', (0, 0), (-1, -1), 1),
-    ]))
-    story = [Spacer(1, spacer_height), table]
-    doc.build(story)
-    buffer.seek(0)
-    return buffer.getvalue()
-
-def pdf_to_image(pdf_bytes):
-    try:
-        doc = fitz.open(stream=pdf_bytes, filetype="pdf")
-        images = []
-        for page in doc:
-            pix = page.get_pixmap(matrix=fitz.Matrix(2.0, 2.0))
-            img = Image.frombytes("RGB", [pix.width, pix.height], pix.samples)
-            images.append(img)
-        doc.close()
-        return images
-    except Exception as e:
-        st.error(f"Failed to render PDF preview: {e}")
-        return None
-
-md_files = [f for f in glob.glob("*.md") if os.path.basename(f) != "README.md"]
-md_options = [os.path.splitext(os.path.basename(f))[0] for f in md_files]
-
-with st.sidebar:
-    st.markdown("### PDF Options")
-    if md_options:
-        selected_md = st.selectbox("Select Markdown File", options=md_options, index=0)
-        with open(f"{selected_md}.md", "r", encoding="utf-8") as f:
-            st.session_state.markdown_content = f.read()
-    else:
-        st.warning("No markdown file found. Please add one to your folder.")
-        selected_md = None
-        st.session_state.markdown_content = ""
-    available_font_files = {os.path.splitext(os.path.basename(f))[0]: f for f in glob.glob("*.ttf")}
-    selected_font_name = st.selectbox("Select Emoji Font", options=list(available_font_files.keys()), 
-                                      index=list(available_font_files.keys()).index("NotoEmoji-Bold") if "NotoEmoji-Bold" in available_font_files else 0)
-    base_font_size = st.slider("Font Size (points)", min_value=6, max_value=16, value=8, step=1)
-    render_with_bold = st.checkbox("Render with Bold Formatting (remove ** markers)", value=True, key="render_with_bold")
-    auto_bold_numbers = st.checkbox("Auto Bold Numbered Lines", value=True, key="auto_bold_numbers")
-    enlarge_numbered = st.checkbox("Enlarge Font Size for Numbered Lines", value=True, key="enlarge_numbered")
-    add_space_before_numbered = st.checkbox("Add Space Ahead of Numbered Lines", value=False, key="add_space_before_numbered")
-    
-    # Add AutoColumns option to automatically determine column count based on line length
-    auto_columns = st.checkbox("AutoColumns", value=False, key="auto_columns")
-    
-    # Auto-determine column count based on longest line if AutoColumns is checked
-    if auto_columns and 'markdown_content' in st.session_state:
-        current_markdown = st.session_state.markdown_content
-        lines = current_markdown.strip().split('\n')
-        longest_line_words = 0
-        for line in lines:
-            if line.strip():  # Skip empty lines
-                word_count = len(line.split())
-                longest_line_words = max(longest_line_words, word_count)
-        
-        # Set recommended columns based on word count
-        if longest_line_words > 25:
-            recommended_columns = 1  # Very long lines need a single column
-        elif longest_line_words >= 18:
-            recommended_columns = 2  # Long lines need 2 columns
-        elif longest_line_words >= 11:
-            recommended_columns = 3  # Medium lines can use 3 columns
-        else:
-            recommended_columns = "Auto"  # Default to auto for shorter lines
-            
-        st.info(f"Longest line has {longest_line_words} words. Recommending {recommended_columns} columns.")
-    else:
-        recommended_columns = "Auto"
-    
-    column_options = ["Auto"] + list(range(1, 7))
-    num_columns = st.selectbox("Number of Columns", options=column_options, 
-                              index=0 if recommended_columns == "Auto" else column_options.index(recommended_columns))
-    num_columns = 0 if num_columns == "Auto" else int(num_columns)
-    st.info("Font size and columns adjust to fit one page.")
-    
-    # Changed label from "Modify the markdown content below:" to "Input Markdown"
-    edited_markdown = st.text_area("Input Markdown", value=st.session_state.markdown_content, height=300, key=f"markdown_{selected_md}_{selected_font_name}_{num_columns}")
-    
-    # Added emoji to "Update PDF" button and created a two-column layout for buttons
-    col1, col2 = st.columns(2)
-    with col1:
-        if st.button("🔄📄 Update PDF"):
-            st.session_state.markdown_content = edited_markdown
-            if selected_md:
-                with open(f"{selected_md}.md", "w", encoding="utf-8") as f:
-                    f.write(edited_markdown)
-            st.rerun()
-    
-    # Added "Trim Emojis" button in second column
-    with col2:
-        if st.button("✂️ Trim Emojis"):
-            trimmed_content = trim_emojis_except_numbered(edited_markdown)
-            st.session_state.markdown_content = trimmed_content
-            if selected_md:
-                with open(f"{selected_md}.md", "w", encoding="utf-8") as f:
-                    f.write(trimmed_content)
-            st.rerun()
-    
-    prefix = get_timestamp_prefix()
-    st.download_button(
-        label="💾📝 Save Markdown",
-        data=st.session_state.markdown_content,
-        file_name=f"{prefix} {selected_md}.md" if selected_md else f"{prefix} default.md",
-        mime="text/markdown"
-    )
-    st.markdown("### Text-to-Speech")
-    VOICES = ["en-US-AriaNeural", "en-US-JennyNeural", "en-GB-SoniaNeural", "en-US-GuyNeural", "en-US-AnaNeural"]
-    selected_voice = st.selectbox("Select Voice for TTS", options=VOICES, index=0)
-    if st.button("Generate Audio"):
-        cleaned_text = clean_for_speech(st.session_state.markdown_content)
-        audio_filename = f"{prefix} {selected_md} {selected_voice}.mp3" if selected_md else f"{prefix} default {selected_voice}.mp3"
-        audio_file = asyncio.run(generate_audio(cleaned_text, selected_voice, audio_filename))
-        st.audio(audio_file)
-        with open(audio_file, "rb") as f:
-            audio_bytes = f.read()
-        st.download_button(
-            label="💾🔊 Save Audio",
-            data=audio_bytes,
-            file_name=audio_filename,
-            mime="audio/mpeg"
-        )
-
-with st.spinner("Generating PDF..."):
-    pdf_bytes = create_pdf(st.session_state.markdown_content, base_font_size, render_with_bold, auto_bold_numbers, enlarge_numbered, num_columns, add_space_before_numbered)
-
-with st.container():
-    pdf_images = pdf_to_image(pdf_bytes)
-    if pdf_images:
-        for img in pdf_images:
-            st.image(img, use_container_width=True)
-    else:
-        st.info("Download the PDF to view it locally.")
-
-with st.sidebar:
-    st.download_button(
-        label="💾📄 Save PDF",
-        data=pdf_bytes,
-        file_name=f"{prefix} {selected_md}.pdf" if selected_md else f"{prefix} output.pdf",
-        mime="application/pdf"
-    ))
+    heading_pattern = re.compile(r'^(#{1,4})\s+(.+)$')
     
     # Track if we've seen the first numbered line already
     first_numbered_seen = False
@@ -448,14 +215,14 @@ with st.sidebar:
     total_lines = len(pdf_content)
     return pdf_content, total_lines
 
-def create_pdf(markdown_text, base_font_size, render_with_bold, auto_bold_numbers, enlarge_numbered, num_columns, add_space_before_numbered):
+def create_pdf(markdown_text, base_font_size, render_with_bold, auto_bold_numbers, enlarge_numbered, num_columns, add_space_before_numbered, headings_to_fonts):
     buffer = io.BytesIO()
     page_width = A4[0] * 2
     page_height = A4[1]
     doc = SimpleDocTemplate(buffer, pagesize=(page_width, page_height), leftMargin=36, rightMargin=36, topMargin=36, bottomMargin=36)
     styles = getSampleStyleSheet()
     spacer_height = 10
-    pdf_content, total_lines = markdown_to_pdf_content(markdown_text, render_with_bold, auto_bold_numbers, add_space_before_numbered)
+    pdf_content, total_lines = markdown_to_pdf_content(markdown_text, render_with_bold, auto_bold_numbers, add_space_before_numbered, headings_to_fonts)
     try:
         available_font_files = glob.glob("*.ttf")
         if not available_font_files:
@@ -517,14 +284,36 @@ def create_pdf(markdown_text, base_font_size, render_with_bold, auto_bold_number
     column_cells = [[] for _ in range(num_columns)]
     for col_idx, column in enumerate(columns):
         for item in column:
-            if isinstance(item, str) and item.startswith("<b>") and item.endswith("</b>"):
-                content = item[3:-4].strip()
-                if number_pattern.match(content):
-                    column_cells[col_idx].append(Paragraph(apply_emoji_font(content, "NotoEmoji-Bold"), numbered_bold_style))
+            if isinstance(item, str):
+                # Handle heading tags if headings_to_fonts is enabled
+                heading_match = re.match(r'<h(\d)>(.*?)</h\1>', item) if headings_to_fonts else None
+                if heading_match:
+                    level = int(heading_match.group(1))
+                    heading_text = heading_match.group(2)
+                    # Create heading styles based on level
+                    heading_style = ParagraphStyle(
+                        f'Heading{level}Style', 
+                        parent=styles['Heading1'],
+                        fontName="DejaVuSans",
+                        textColor=colors.darkblue if level == 1 else (colors.black if level > 2 else colors.blue),
+                        fontSize=adjusted_font_size * (1.6 - (level-1)*0.15),  # Size decreases with level
+                        leading=adjusted_font_size * (1.8 - (level-1)*0.15),
+                        spaceAfter=4 - (level-1),
+                        spaceBefore=6 - (level-1),
+                        linkUnderline=True
+                    )
+                    column_cells[col_idx].append(Paragraph(apply_emoji_font(heading_text, "NotoEmoji-Bold"), heading_style))
+                # Handle regular bold items
+                elif item.startswith("<b>") and item.endswith("</b>"):
+                    content = item[3:-4].strip()
+                    if number_pattern.match(content):
+                        column_cells[col_idx].append(Paragraph(apply_emoji_font(content, "NotoEmoji-Bold"), numbered_bold_style))
+                    else:
+                        column_cells[col_idx].append(Paragraph(apply_emoji_font(content, "NotoEmoji-Bold"), section_style))
                 else:
-                    column_cells[col_idx].append(Paragraph(apply_emoji_font(content, "NotoEmoji-Bold"), section_style))
+                    column_cells[col_idx].append(Paragraph(apply_emoji_font(item, "DejaVuSans"), item_style))
             else:
-                column_cells[col_idx].append(Paragraph(apply_emoji_font(item, "DejaVuSans"), item_style))
+                column_cells[col_idx].append(Paragraph(apply_emoji_font(str(item), "DejaVuSans"), item_style))
     max_cells = max(len(cells) for cells in column_cells) if column_cells else 0
     for cells in column_cells:
         cells.extend([Paragraph("", item_style)] * (max_cells - len(cells)))
@@ -581,6 +370,8 @@ with st.sidebar:
     auto_bold_numbers = st.checkbox("Auto Bold Numbered Lines", value=True, key="auto_bold_numbers")
     enlarge_numbered = st.checkbox("Enlarge Font Size for Numbered Lines", value=True, key="enlarge_numbered")
     add_space_before_numbered = st.checkbox("Add Space Ahead of Numbered Lines", value=False, key="add_space_before_numbered")
+    headings_to_fonts = st.checkbox("Headings to Fonts", value=False, key="headings_to_fonts", 
+                               help="Convert Markdown headings (# Heading) and emphasis (*word*) to appropriate font styles")
     
     # Add AutoColumns option to automatically determine column count based on line length
     auto_columns = st.checkbox("AutoColumns", value=False, key="auto_columns")
@@ -663,7 +454,7 @@ with st.sidebar:
         )
 
 with st.spinner("Generating PDF..."):
-    pdf_bytes = create_pdf(st.session_state.markdown_content, base_font_size, render_with_bold, auto_bold_numbers, enlarge_numbered, num_columns, add_space_before_numbered)
+    pdf_bytes = create_pdf(st.session_state.markdown_content, base_font_size, render_with_bold, auto_bold_numbers, enlarge_numbered, num_columns, add_space_before_numbered, headings_to_fonts)
 
 with st.container():
     pdf_images = pdf_to_image(pdf_bytes)