Spaces:
Paused
Paused
File size: 8,171 Bytes
342973b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 |
"""
PDF Generator - Generate professional PDF documents
"""
import io
from typing import Dict, List, Optional
from datetime import datetime
import logging
logger = logging.getLogger(__name__)
class PDFGenerator:
"""
Generate professional PDF documents with formatting, headers, footers, and citations.
"""
def __init__(self):
"""Initialize PDF generator."""
self.page_size = "A4"
self.margins = {"top": 1.0, "bottom": 1.0, "left": 1.0, "right": 1.0}
self.font_name = "Arial"
self.font_size = 12
self.line_spacing = 1.5
def generate_pdf(
self,
title: str,
content: Dict[str, str],
author: str = "AI Academic Suite",
include_toc: bool = True,
include_citations: bool = False,
citations: List[str] = None,
) -> bytes:
"""
Generate PDF document.
Args:
title: Document title
content: Dictionary of section titles and content
author: Document author
include_toc: Include table of contents
include_citations: Include bibliography
citations: List of citations
Returns:
PDF bytes
"""
try:
from reportlab.lib.pagesizes import A4
from reportlab.lib.styles import getSampleStyleSheet, ParagraphStyle
from reportlab.lib.units import inch
from reportlab.platypus import SimpleDocTemplate, Paragraph, Spacer, PageBreak, Table, TableStyle
from reportlab.lib import colors
# Create PDF in memory
pdf_buffer = io.BytesIO()
doc = SimpleDocTemplate(
pdf_buffer,
pagesize=A4,
rightMargin=1 * inch,
leftMargin=1 * inch,
topMargin=1 * inch,
bottomMargin=1 * inch,
)
# Create story (content)
story = []
# Add title page
story.extend(self._create_title_page(title, author))
story.append(PageBreak())
# Add table of contents
if include_toc:
story.extend(self._create_toc(content))
story.append(PageBreak())
# Add sections
styles = getSampleStyleSheet()
for section_title, section_content in content.items():
story.append(Paragraph(section_title, styles["Heading1"]))
story.append(Spacer(1, 0.2 * inch))
# Split content into paragraphs
paragraphs = section_content.split("\n\n")
for para_text in paragraphs:
if para_text.strip():
story.append(Paragraph(para_text, styles["Normal"]))
story.append(Spacer(1, 0.1 * inch))
story.append(Spacer(1, 0.3 * inch))
# Add bibliography
if include_citations and citations:
story.append(PageBreak())
story.append(Paragraph("References", styles["Heading1"]))
story.append(Spacer(1, 0.2 * inch))
for citation in citations:
story.append(Paragraph(citation, styles["Normal"]))
story.append(Spacer(1, 0.1 * inch))
# Build PDF
doc.build(story)
pdf_buffer.seek(0)
return pdf_buffer.getvalue()
except ImportError:
logger.warning("reportlab not available, using fallback")
return self._generate_pdf_fallback(title, content)
def _create_title_page(self, title: str, author: str) -> list:
"""Create title page elements."""
try:
from reportlab.lib.styles import getSampleStyleSheet
from reportlab.platypus import Paragraph, Spacer
from reportlab.lib.units import inch
styles = getSampleStyleSheet()
story = []
story.append(Spacer(1, 1 * inch))
story.append(Paragraph(title, styles["Title"]))
story.append(Spacer(1, 0.5 * inch))
story.append(Paragraph(f"By {author}", styles["Normal"]))
story.append(Spacer(1, 0.2 * inch))
story.append(Paragraph(datetime.now().strftime("%B %d, %Y"), styles["Normal"]))
return story
except:
return []
def _create_toc(self, content: Dict[str, str]) -> list:
"""Create table of contents."""
try:
from reportlab.lib.styles import getSampleStyleSheet
from reportlab.platypus import Paragraph, Spacer
from reportlab.lib.units import inch
styles = getSampleStyleSheet()
story = []
story.append(Paragraph("Table of Contents", styles["Heading1"]))
story.append(Spacer(1, 0.3 * inch))
for i, section in enumerate(content.keys(), 1):
story.append(Paragraph(f"{i}. {section}", styles["Normal"]))
story.append(Spacer(1, 0.1 * inch))
return story
except:
return []
def _generate_pdf_fallback(self, title: str, content: Dict[str, str]) -> bytes:
"""Fallback PDF generation using fpdf2."""
try:
from fpdf import FPDF
pdf = FPDF()
pdf.add_page()
pdf.set_font("Arial", "B", 16)
# Title
pdf.cell(0, 10, title, ln=True, align="C")
pdf.ln(10)
# Content
pdf.set_font("Arial", "", 12)
for section_title, section_content in content.items():
pdf.set_font("Arial", "B", 14)
pdf.cell(0, 10, section_title, ln=True)
pdf.set_font("Arial", "", 12)
# Add content with text wrapping
for line in section_content.split("\n"):
pdf.multi_cell(0, 10, line)
pdf.ln(5)
return pdf.output(dest="S").encode("latin-1")
except ImportError:
# Fallback to simple text
return f"PDF Generation Failed - {title}".encode("utf-8")
def add_header_footer(self, pdf_content: bytes, header: str = "", footer: str = "") -> bytes:
"""
Add header and footer to PDF.
Args:
pdf_content: Original PDF bytes
header: Header text
footer: Footer text
Returns:
PDF with header/footer
"""
try:
from PyPDF2 import PdfReader, PdfWriter
from reportlab.pdfgen import canvas
from reportlab.lib.pagesizes import A4
import io
# Create header/footer canvas
header_buffer = io.BytesIO()
c = canvas.Canvas(header_buffer, pagesize=A4)
c.setFont("Arial", 10)
if header:
c.drawString(50, 750, header)
if footer:
c.drawString(50, 30, footer)
c.save()
header_buffer.seek(0)
# Merge with original PDF
reader = PdfReader(io.BytesIO(pdf_content))
writer = PdfWriter()
for page in reader.pages:
page.merge_page(PdfReader(header_buffer).pages[0])
writer.add_page(page)
output_buffer = io.BytesIO()
writer.write(output_buffer)
output_buffer.seek(0)
return output_buffer.getvalue()
except:
return pdf_content # Return original if header/footer fails
def extract_text_from_pdf(self, pdf_content: bytes) -> str:
"""
Extract text from PDF.
Args:
pdf_content: PDF bytes
Returns:
Extracted text
"""
try:
import pdfplumber
import io
with pdfplumber.open(io.BytesIO(pdf_content)) as pdf:
text = ""
for page in pdf.pages:
text += page.extract_text() + "\n"
return text
except:
return "PDF text extraction failed"
|