report_structure.py

# report_structure.py
from reportlab.lib.pagesizes import letter
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak, Table, TableStyle
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.enums import TA_JUSTIFY, TA_LEFT, TA_CENTER
from reportlab.lib import colors
import re
import time

def generate_report(research_output: str, filename="research_report.pdf"):
    """
    Generates a structured PDF research report from the raw research output.

    Args:
        research_output: The raw string output from the Open Deep Research agent.
        filename: The desired filename for the PDF.

    Returns:
        The research report as a string (same as the input to this function, but it
        will also have generated the PDF as a side-effect).
    """
    doc = SimpleDocTemplate(filename, pagesize=letter,
                            rightMargin=72, leftMargin=72,
                            topMargin=72, bottomMargin=18)
    styles = getSampleStyleSheet()
    story = []

    # Custom Styles
    title_style = ParagraphStyle(
        'TitleStyle',
        parent=styles['Title'],
        fontSize=24,
        alignment=TA_CENTER,
        spaceAfter=24
    )
    h1_style = ParagraphStyle(
        'H1Style',
        parent=styles['Heading1'],
        fontSize=18,
        spaceBefore=12,
        spaceAfter=6
    )
    h2_style = ParagraphStyle(
        'H2Style',
        parent=styles['Heading2'],
        fontSize=14,
        spaceBefore=10,
        spaceAfter=4
    )
    normal_style = ParagraphStyle(
        'NormalStyle',
        parent=styles['Normal'],
        fontSize=12,
        alignment=TA_JUSTIFY
    )
    toc_h1_style = ParagraphStyle(
        'TOC_H1_Style',
        parent=styles['Heading2'],
    )

    # --- Title Page ---
    title = extract_title(research_output)
    story.append(Paragraph(title, title_style))
    story.append(Spacer(1, 36))
    story.append(Paragraph("Generated by MyPod Research Agent", styles['Normal']))
    story.append(Spacer(1, 12))
    story.append(Paragraph("Date: {}".format(time.strftime("%Y-%m-%d")), styles['Normal']))  # Add date
    story.append(PageBreak())

    # --- Table of Contents (Placeholder) ---
    story.append(Paragraph("Table of Contents", h1_style))
    toc_entries = extract_toc(research_output)
    for level, title_text in toc_entries:
         story.append(Paragraph(f"{title_text}", styles['Normal']))
    story.append(PageBreak())

    # --- Main Content ---
    sections = split_into_sections(research_output)
    for section_title, section_content in sections.items():
        story.append(Paragraph(section_title, h1_style))
        paragraphs = section_content.split('\n\n')  # Split by double newlines
        for para in paragraphs:
             story.append(Paragraph(para.strip(), normal_style))
             story.append(Spacer(1, 12))

    doc.build(story, onFirstPage=add_page_number, onLaterPages=add_page_number)
    return research_output

def extract_title(text):
    """Extracts the title from the research output (simple heuristic)."""
    lines = text.split("\n")
    for line in lines:
        if line.strip():
            return line.strip()
    return "Research Report"  # Default title

def extract_toc(text):
    """Extracts a simple table of contents (heuristic).  Looks for lines starting with #."""
    toc = []
    lines = text.split("\n")
    for i,line in enumerate(lines):
        if line.startswith("# ") and line.count(".")<=3:
            toc.append((1, line[2:].strip()))
        elif line.startswith("## ") and line.count(".")<=3:
            toc.append((2, line[3:].strip()))
    return toc

def split_into_sections(text):
    """Splits the research output into sections based on headings."""
    sections = {}
    current_section = "Introduction"  # Default section
    sections[current_section] = ""

    lines = text.split("\n")
    for line in lines:
        if line.startswith("# "):
            current_section = line[2:].strip()
            sections[current_section] = ""
        elif line.startswith("## "):
             current_section = line[3:].strip()
             sections[current_section] = ""
        else:
            sections[current_section] += line + "\n"

    return sections

def add_page_number(canvas, doc):
    """Adds page numbers to the footer."""
    canvas.saveState()
    canvas.setFont('Times-Roman', 9)
    canvas.drawString(letter[0] - 72, 0.75 * 72, "Page %d" % doc.page)
    canvas.restoreState()